« back to all changes in this revision
Viewing changes to api/macroapi.c
- browse files at revision 5
- compare with another revision
- download diff
- download tarball
- view history from revision 5
- Committer: Bazaar Package Importer
- Author(s): Aaron M. Ucko
- Date: 2008-07-14 19:43:15 UTC
- mfrom: (2.1.12 intrepid)
- Revision ID: james.westby@ubuntu.com-20080714194315-ed44u9ek7txva2rz
Tags: 6.1.20080302-3
tools/readdb.c: enable madvise()-based code on all glibc (hence all
Debian) systems, not just Linux. (Closes: #490437.)
Debian) systems, not just Linux. (Closes: #490437.)
- files added:
- access/mla2.asn
- make/msvc800_prj/demo/asnbarval
- make/msvc800_prj/demo/asndisc
- make/msvc800_prj/demo/asnstrip
- make/msvc800_prj/demo/raw2delt
- make/msvc_prj/demo/asnbarval
- make/msvc_prj/demo/asndisc
- make/msvc_prj/demo/asnmacro
- make/msvc_prj/demo/asnstrip
- make/msvc_prj/demo/cleanasn
- make/msvc_prj/demo/cspeedtest
- make/msvc_prj/demo/raw2delt
- make/xCode/ncbicguiapp
- make/xCode/ncbicguiapp/English.lproj
- make/xCode/ncbicguiapp/ncbicguiapp.xcodeproj
- make/xCode/ncbictoolkit
- make/xCode/ncbictoolkit/English.lproj
- make/xCode/ncbictoolkit/ncbictoolkit.xcodeproj
- files removed:
- algo/blast/core/blast_dust.c
- debian/man.unused
- debian/old-blast-man
- make/msvc800_prj/demo/entrezcf
- make/msvc800_prj/demo/getseq
- make/msvc_prj/demo/entrezcf
- make/msvc_prj/demo/getseq
- files modified:
- VERSION
- biostruc/RESEARCH/res.shtml *
- biostruc/RESEARCH/threading.shtml *
- biostruc/VastAlign/Makefile *
- biostruc/cblast/cblast.h *
- biostruc/newVSch/Makefile *
- biostruc/pdbeast/interface.c *
- biostruc/pdbeast/interface.h *
- biostruc/pdbeast/mmdborgcpy.c *
- biostruc/pdbeast/orgmatch.c *
- biostruc/pdbeast/para.h *
- biostruc/pdbeast/pdbeast.c *
- biostruc/pdbeast/pdbeast.h *
- biostruc/pdbeast/tax_index.c *
- cn3d/cn3dmatn.c *
- cn3d/cn3dmsg.c *
- cn3d/cn3dmsg.h *
- corelib/tsprintf.h *
- doc/images/affil.png *
- doc/images/annot.png *
- doc/images/authors.png *
- doc/images/cds_edit.png *
- doc/images/contact.png *
- doc/images/desktop.png *
- doc/images/format.png *
- doc/images/genbank.png *
- doc/images/graphic.png *
- doc/images/net_cfg.png *
- doc/images/nucset.png *
- doc/images/nucsing1.png *
- doc/images/nucsing2.png *
- doc/images/organism.png *
- doc/images/protein1.png *
- doc/images/protein2.png *
- doc/images/sequence.png *
- doc/images/update.png *
- doc/images/validate.png *
- doc/images/welcome.png *
- link/macmet/MW-BSD-limits-fix.h *
- sequin/sbtedit.c *
- vibrant/vibrgb.h *
- webdesign/designs/cubby/storedsearch/Templates/edit.gif *
- webdesign/designs/cubby/storedsearch/Templates/mail.gif *
- webdesign/designs/cubby/storedsearch/Templates/plus.gif *
- webdesign/designs/cubby/storedsearch/Templates/run.gif *
- webdesign/designs/cubby/storedsearch/Templates/whatsnew.gif *
- webdesign/designs/cubby/storedsearch/Templates/x.gif *
- webdesign/designs/pmc/layout.css *
added
removed
api/macroapi.c
1
/* macro.c
2
* ===========================================================================
3
*
4
* PUBLIC DOMAIN NOTICE
5
* National Center for Biotechnology Information (NCBI)
6
*
7
* This software/database is a "United States Government Work" under the
8
* terms of the United States Copyright Act. It was written as part of
9
* the author's official duties as a United States Government employee and
10
* thus cannot be copyrighted. This software/database is freely available
11
* to the public for use. The National Library of Medicine and the U.S.
12
* Government do not place any restriction on its use or reproduction.
13
* We would, however, appreciate having the NCBI and the author cited in
14
* any work or product based on this material
15
*
16
* Although all reasonable efforts have been taken to ensure the accuracy
17
* and reliability of the software and data, the NLM and the U.S.
18
* Government do not and cannot warrant the performance or results that
19
* may be obtained by using this software or data. The NLM and the U.S.
20
* Government disclaim all warranties, express or implied, including
21
* warranties of performance, merchantability or fitness for any particular
22
* purpose.
23
*
24
* ===========================================================================
25
*
26
* File Name: macro.c
27
*
28
* Author: Colleen Bollin
29
*
30
* Version Creation Date: 11/8/2007
31
*
32
* $Revision: 1.58 $
33
*
34
* File Description:
35
*
36
* Modifications:
37
* --------------------------------------------------------------------------
38
* Date Name Description of modification
39
* ------- ---------- -----------------------------------------------------
40
*
41
*
42
* ==========================================================================
43
*/
44
45
#include <asn.h>
46
#include <objmacro.h>
47
#include <objfeat.h>
48
#include <subutil.h>
49
#include <objmgr.h>
50
#include <objfdef.h>
51
#include <gbftdef.h>
52
#include <sqnutils.h>
53
#include <edutil.h>
54
#include <gather.h>
55
#include <asn2gnbi.h>
56
#define NLM_GENERATED_CODE_PROTO
57
#include <macroapi.h>
58
#include <seqport.h>
59
60
/* structure and create/free functions for CGPSet, used for handling CDS-Gene-Prot sets */
61
typedef struct cgpset
62
{
63
ValNodePtr cds_list;
64
ValNodePtr gene_list;
65
ValNodePtr prot_list;
66
ValNodePtr mrna_list;
67
} CGPSetData, PNTR CGPSetPtr;
68
69
70
71
static CGPSetPtr CGPSetNew (void)
72
{
73
CGPSetPtr c;
74
75
c = (CGPSetPtr) MemNew (sizeof (CGPSetData));
76
c->cds_list = NULL;
77
c->gene_list = NULL;
78
c->prot_list = NULL;
79
c->mrna_list = NULL;
80
return c;
81
}
82
83
84
static CGPSetPtr CGPSetFree (CGPSetPtr c)
85
{
86
if (c != NULL) {
87
c->cds_list = ValNodeFree (c->cds_list);
88
c->gene_list = ValNodeFree (c->gene_list);
89
c->prot_list = ValNodeFree (c->prot_list);
90
c->mrna_list = ValNodeFree (c->mrna_list);
91
c = MemFree (c);
92
}
93
return c;
94
}
95
96
97
static ValNodePtr FreeCGPSetList (ValNodePtr vnp)
98
{
99
ValNodePtr vnp_next;
100
101
while (vnp != NULL) {
102
vnp_next = vnp->next;
103
vnp->next = NULL;
104
vnp->data.ptrvalue = CGPSetFree (vnp->data.ptrvalue);
105
vnp = ValNodeFree (vnp);
106
vnp = vnp_next;
107
}
108
return NULL;
109
}
110
111
112
/* generic functions for mapping constraints */
113
114
typedef struct feattypefeatdef {
115
Int4 feattype;
116
Int4 featdef;
117
CharPtr featname;
118
} FeatTypeFeatDefData, PNTR FeatTypeFeatDefPtr;
119
120
static FeatTypeFeatDefData feattype_featdef[] = {
121
{ Feature_type_any , FEATDEF_ANY , "any" } ,
122
{ Feature_type_gene , FEATDEF_GENE , "gene" } ,
123
{ Feature_type_org , FEATDEF_ORG , "org" } ,
124
{ Feature_type_cds , FEATDEF_CDS , "CDS" } ,
125
{ Feature_type_prot , FEATDEF_PROT , "Protein" } ,
126
{ Feature_type_preRNA , FEATDEF_preRNA , "preRNA" } ,
127
{ Feature_type_mRNA , FEATDEF_mRNA , "mRNA" } ,
128
{ Feature_type_tRNA , FEATDEF_tRNA , "tRNA" } ,
129
{ Feature_type_rRNA , FEATDEF_rRNA , "rRNA" } ,
130
{ Feature_type_snRNA , FEATDEF_snRNA , "snRNA" } ,
131
{ Feature_type_scRNA , FEATDEF_scRNA , "scRNA" } ,
132
{ Feature_type_otherRNA , FEATDEF_otherRNA , "misc_RNA" } ,
133
{ Feature_type_pub , FEATDEF_PUB , "pub" } ,
134
{ Feature_type_seq , FEATDEF_SEQ , "seq" } ,
135
{ Feature_type_imp , FEATDEF_IMP , "imp" } ,
136
{ Feature_type_allele , FEATDEF_allele , "allele" } ,
137
{ Feature_type_attenuator , FEATDEF_attenuator , "attenuator" } ,
138
{ Feature_type_c_region , FEATDEF_C_region , "c_region" } ,
139
{ Feature_type_caat_signal , FEATDEF_CAAT_signal , "caat_signal" } ,
140
{ Feature_type_imp_CDS , FEATDEF_Imp_CDS , "imp_CDS" } ,
141
{ Feature_type_conflict , FEATDEF_conflict , "conflict" } ,
142
{ Feature_type_d_loop , FEATDEF_D_loop , "d_loop" } ,
143
{ Feature_type_d_segment , FEATDEF_D_segment , "d_segment" } ,
144
{ Feature_type_enhancer , FEATDEF_enhancer , "enhancer" } ,
145
{ Feature_type_exon , FEATDEF_exon , "exon" } ,
146
{ Feature_type_gC_signal , FEATDEF_GC_signal , "gC_signal" } ,
147
{ Feature_type_iDNA , FEATDEF_iDNA , "iDNA" } ,
148
{ Feature_type_intron , FEATDEF_intron , "intron" } ,
149
{ Feature_type_j_segment , FEATDEF_J_segment , "j_segment" } ,
150
{ Feature_type_ltr , FEATDEF_LTR , "ltr" } ,
151
{ Feature_type_mat_peptide , FEATDEF_mat_peptide , "mat_peptide" } ,
152
{ Feature_type_misc_binding , FEATDEF_misc_binding , "misc_binding" } ,
153
{ Feature_type_misc_difference , FEATDEF_misc_difference , "misc_difference" } ,
154
{ Feature_type_misc_feature , FEATDEF_misc_feature , "misc_feature" } ,
155
{ Feature_type_misc_recomb , FEATDEF_misc_recomb , "misc_recomb" } ,
156
{ Feature_type_misc_RNA , FEATDEF_misc_RNA , "misc_RNA" } ,
157
{ Feature_type_misc_signal , FEATDEF_misc_signal , "misc_signal" } ,
158
{ Feature_type_misc_structure , FEATDEF_misc_structure , "misc_structure" } ,
159
{ Feature_type_modified_base , FEATDEF_modified_base , "modified_base" } ,
160
{ Feature_type_mutation , FEATDEF_mutation , "mutation" } ,
161
{ Feature_type_n_region , FEATDEF_N_region , "n_region" } ,
162
{ Feature_type_old_sequence , FEATDEF_old_sequence , "old_sequence" } ,
163
{ Feature_type_polyA_signal , FEATDEF_polyA_signal , "polyA_signal" } ,
164
{ Feature_type_polyA_site , FEATDEF_polyA_site , "polyA_site" } ,
165
{ Feature_type_precursor_RNA , FEATDEF_precursor_RNA , "precursor_RNA" } ,
166
{ Feature_type_prim_transcript , FEATDEF_prim_transcript , "prim_transcript" } ,
167
{ Feature_type_primer_bind , FEATDEF_primer_bind , "primer_bind" } ,
168
{ Feature_type_promoter , FEATDEF_promoter , "promoter" } ,
169
{ Feature_type_protein_bind , FEATDEF_protein_bind , "protein_bind" } ,
170
{ Feature_type_rbs , FEATDEF_RBS , "rbs" } ,
171
{ Feature_type_repeat_region , FEATDEF_repeat_region , "repeat_region" } ,
172
{ Feature_type_repeat_unit , FEATDEF_repeat_unit , "repeat_unit" } ,
173
{ Feature_type_rep_origin , FEATDEF_rep_origin , "rep_origin" } ,
174
{ Feature_type_s_region , FEATDEF_S_region , "s_region" } ,
175
{ Feature_type_satellite , FEATDEF_satellite , "satellite" } ,
176
{ Feature_type_sig_peptide , FEATDEF_sig_peptide , "sig_peptide" } ,
177
{ Feature_type_source , FEATDEF_source , "source" } ,
178
{ Feature_type_stem_loop , FEATDEF_stem_loop , "stem_loop" } ,
179
{ Feature_type_sts , FEATDEF_STS , "sts" } ,
180
{ Feature_type_tata_signal , FEATDEF_TATA_signal , "tata_signal" } ,
181
{ Feature_type_terminator , FEATDEF_terminator , "terminator" } ,
182
{ Feature_type_transit_peptide , FEATDEF_transit_peptide , "transit_peptide" } ,
183
{ Feature_type_unsure , FEATDEF_unsure , "unsure" } ,
184
{ Feature_type_v_region , FEATDEF_V_region , "v_region" } ,
185
{ Feature_type_v_segment , FEATDEF_V_segment , "v_segment" } ,
186
{ Feature_type_variation , FEATDEF_variation , "variation" } ,
187
{ Feature_type_virion , FEATDEF_virion , "virion" } ,
188
{ Feature_type_n3clip , FEATDEF_3clip , "3clip" } ,
189
{ Feature_type_n3UTR , FEATDEF_3UTR , "3UTR" } ,
190
{ Feature_type_n5clip , FEATDEF_5clip , "5clip" } ,
191
{ Feature_type_n5UTR , FEATDEF_5UTR , "5UTR" } ,
192
{ Feature_type_n10_signal , FEATDEF_10_signal , "10_signal" } ,
193
{ Feature_type_n35_signal , FEATDEF_35_signal , "35_signal" } ,
194
{ Feature_type_site_ref , FEATDEF_site_ref , "site_ref" } ,
195
{ Feature_type_region , FEATDEF_REGION , "region" } ,
196
{ Feature_type_comment , FEATDEF_COMMENT , "comment" } ,
197
{ Feature_type_bond , FEATDEF_BOND , "bond" } ,
198
{ Feature_type_site , FEATDEF_SITE , "site" } ,
199
{ Feature_type_rsite , FEATDEF_RSITE , "rsite" } ,
200
{ Feature_type_user , FEATDEF_USER , "user" } ,
201
{ Feature_type_txinit , FEATDEF_TXINIT , "txinit" } ,
202
{ Feature_type_num , FEATDEF_NUM , "num" } ,
203
{ Feature_type_psec_str , FEATDEF_PSEC_STR , "psec_str" } ,
204
{ Feature_type_non_std_residue , FEATDEF_NON_STD_RESIDUE , "non_std_residue" } ,
205
{ Feature_type_het , FEATDEF_HET , "het" } ,
206
{ Feature_type_biosrc , FEATDEF_BIOSRC , "biosrc" } ,
207
{ Feature_type_preprotein , FEATDEF_preprotein , "preprotein" } ,
208
{ Feature_type_mat_peptide_aa , FEATDEF_mat_peptide_aa , "mat_peptide_aa" } ,
209
{ Feature_type_sig_peptide_aa , FEATDEF_sig_peptide_aa , "sig_peptide_aa" } ,
210
{ Feature_type_transit_peptide_aa , FEATDEF_transit_peptide_aa , "transit_peptide_aa" } ,
211
{ Feature_type_snoRNA , FEATDEF_snoRNA , "snoRNA" } ,
212
{ Feature_type_gap , FEATDEF_gap , "gap" } ,
213
{ Feature_type_operon , FEATDEF_operon , "operon" } ,
214
{ Feature_type_oriT , FEATDEF_oriT , "oriT" } ,
215
{ Feature_type_ncRNA , FEATDEF_ncRNA , "ncRNA" } ,
216
{ Feature_type_tmRNA , FEATDEF_tmRNA , "tmRNA" }};
217
218
#define NUM_feattype_featdef sizeof (feattype_featdef) / sizeof (FeatTypeFeatDefData)
219
220
NLM_EXTERN Int4 GetFeatdefFromFeatureType (Int4 feature_type)
221
{
222
Int4 i;
223
224
for (i = 0; i < NUM_feattype_featdef; i++) {
225
if (feature_type == feattype_featdef[i].feattype) {
226
return feattype_featdef[i].featdef;
227
}
228
}
229
return FEATDEF_BAD;
230
}
231
232
233
NLM_EXTERN CharPtr GetFeatureNameFromFeatureType (Int4 feature_type)
234
{
235
CharPtr str = NULL;
236
Int4 i;
237
238
for (i = 0; i < NUM_feattype_featdef && str == NULL; i++) {
239
if (feature_type == feattype_featdef[i].feattype) {
240
str = feattype_featdef[feature_type].featname;
241
}
242
}
243
if (str == NULL) {
244
str = "Unknown feature type";
245
}
246
return str;
247
}
248
249
250
static Boolean Matchnamestring (CharPtr name1, CharPtr name2)
251
{
252
if (name1 == NULL && name2 == NULL) {
253
return TRUE;
254
} else if (name1 == NULL || name2 == NULL) {
255
return FALSE;
256
} else {
257
while (*name1 != 0 && *name2 != 0) {
258
while (*name1 == ' ' || *name1 == '-' || *name1 == '_') {
259
name1++;
260
}
261
while (*name2 == ' ' || *name2 == '-' || *name2 == '_') {
262
name2++;
263
}
264
if (*name1 != *name2) {
265
return FALSE;
266
}
267
name1++;
268
name2++;
269
}
270
if (*name1 == 0 && *name2 == 0) {
271
return TRUE;
272
} else {
273
return FALSE;
274
}
275
}
276
}
277
278
279
NLM_EXTERN Int4 GetFeatureTypeByName (CharPtr feat_name)
280
{
281
Int4 i;
282
283
for (i = 0; i < NUM_feattype_featdef; i++) {
284
if (Matchnamestring (feattype_featdef[i].featname, feat_name)) {
285
return feattype_featdef[i].feattype;
286
}
287
}
288
return -1;
289
}
290
291
292
NLM_EXTERN void AddImportFeaturesToChoiceList (ValNodePtr PNTR feature_type_list)
293
{
294
Int4 i, seqfeattype;
295
CharPtr featname;
296
ValNodePtr tmp_list = NULL;
297
298
for (i = 1; i < NUM_feattype_featdef; i++) {
299
if (feattype_featdef[i].feattype == Feature_type_gap) continue;
300
seqfeattype = FindFeatFromFeatDefType (feattype_featdef[i].featdef);
301
if (seqfeattype == SEQFEAT_IMP) {
302
featname = GetFeatureNameFromFeatureType (feattype_featdef[i].feattype);
303
if (featname != NULL) {
304
ValNodeAddPointer (&tmp_list, feattype_featdef[i].feattype, StringSave (featname));
305
}
306
}
307
}
308
tmp_list = ValNodeSort (tmp_list, SortVnpByString);
309
ValNodeLink (feature_type_list, tmp_list);
310
}
311
312
313
314
static Boolean IsMostUsedFeature (Uint1 val)
315
{
316
if (val == Feature_type_gene
317
|| val == Feature_type_cds
318
|| val == Feature_type_prot
319
|| val == Feature_type_exon
320
|| val == Feature_type_intron
321
|| val == Feature_type_mRNA
322
|| val == Feature_type_rRNA
323
|| val == Feature_type_otherRNA) {
324
return TRUE;
325
} else {
326
return FALSE;
327
}
328
}
329
330
331
static int LIBCALLBACK SortVnpByFeatureName (VoidPtr ptr1, VoidPtr ptr2)
332
333
{
334
CharPtr str1;
335
CharPtr str2;
336
ValNodePtr vnp1;
337
ValNodePtr vnp2;
338
Boolean most_used1, most_used2;
339
340
if (ptr1 != NULL && ptr2 != NULL) {
341
vnp1 = *((ValNodePtr PNTR) ptr1);
342
vnp2 = *((ValNodePtr PNTR) ptr2);
343
if (vnp1 != NULL && vnp2 != NULL) {
344
most_used1 = IsMostUsedFeature (vnp1->choice);
345
most_used2 = IsMostUsedFeature (vnp2->choice);
346
if (most_used1 && !most_used2) {
347
return -1;
348
} else if (!most_used1 && most_used2) {
349
return 1;
350
} else {
351
str1 = (CharPtr) vnp1->data.ptrvalue;
352
str2 = (CharPtr) vnp2->data.ptrvalue;
353
if (str1 != NULL && str2 != NULL) {
354
return StringICmp (str1, str2);
355
}
356
}
357
}
358
}
359
return 0;
360
}
361
362
363
NLM_EXTERN void AddAllFeaturesToChoiceList (ValNodePtr PNTR feature_type_list)
364
{
365
Int4 i;
366
CharPtr featname;
367
ValNodePtr tmp_list = NULL;
368
369
for (i = 1; i < NUM_feattype_featdef; i++) {
370
if (feattype_featdef[i].feattype == Feature_type_gap) continue;
371
featname = GetFeatureNameFromFeatureType (feattype_featdef[i].feattype);
372
if (featname != NULL) {
373
ValNodeAddPointer (&tmp_list, feattype_featdef[i].feattype, StringSave (featname));
374
}
375
}
376
tmp_list = ValNodeSort (tmp_list, SortVnpByFeatureName);
377
ValNodeLink (feature_type_list, tmp_list);
378
}
379
380
381
typedef struct featqualgbqual {
382
Int4 featqual;
383
Int4 gbqual;
384
CharPtr qualname;
385
} FeatQualGBQualData, PNTR FeatQualGBQualPtr;
386
387
static FeatQualGBQualData featqual_gbqual[] = {
388
{ Feat_qual_legal_allele , GBQUAL_allele , "allele" } ,
389
{ Feat_qual_legal_anticodon , GBQUAL_anticodon , "anticodon" } ,
390
{ Feat_qual_legal_bound_moiety , GBQUAL_bound_moiety , "bound-moiety" } ,
391
{ Feat_qual_legal_chromosome , GBQUAL_chromosome , "chromosome" } ,
392
{ Feat_qual_legal_citation , GBQUAL_citation , "citation" } ,
393
{ Feat_qual_legal_codon , GBQUAL_codon , "codon" } ,
394
{ Feat_qual_legal_codon_start , GBQUAL_codon_start , "codon-start" } ,
395
{ Feat_qual_legal_compare , GBQUAL_compare , "compare" } ,
396
{ Feat_qual_legal_cons_splice , GBQUAL_cons_splice , "cons-splice" } ,
397
{ Feat_qual_legal_db_xref , GBQUAL_db_xref , "db-xref" } ,
398
{ Feat_qual_legal_direction , GBQUAL_direction , "direction" } ,
399
{ Feat_qual_legal_environmental_sample , GBQUAL_environmental_sample , "environmental-sample" } ,
400
{ Feat_qual_legal_evidence , GBQUAL_evidence , "evidence" } ,
401
{ Feat_qual_legal_exception , GBQUAL_exception , "exception" } ,
402
{ Feat_qual_legal_experiment , GBQUAL_experiment , "experiment" } ,
403
{ Feat_qual_legal_focus , GBQUAL_focus , "focus" } ,
404
{ Feat_qual_legal_frequency , GBQUAL_frequency , "frequency" } ,
405
{ Feat_qual_legal_function , GBQUAL_function , "function" } ,
406
{ Feat_qual_legal_gene , GBQUAL_gene , "locus" } ,
407
{ Feat_qual_legal_inference , GBQUAL_inference , "inference" } ,
408
{ Feat_qual_legal_label , GBQUAL_label , "label" } ,
409
{ Feat_qual_legal_locus_tag , GBQUAL_locus_tag , "locus-tag" } ,
410
{ Feat_qual_legal_map , GBQUAL_map , "map" } ,
411
{ Feat_qual_legal_mobile_element , GBQUAL_mobile_element , "mobile-element" } ,
412
{ Feat_qual_legal_mod_base , GBQUAL_mod_base , "mod-base" } ,
413
{ Feat_qual_legal_mol_type , GBQUAL_mol_type , "mol-type" } ,
414
{ Feat_qual_legal_ncRNA_class , GBQUAL_ncRNA_class , "ncRNA-class" } ,
415
{ Feat_qual_legal_note , GBQUAL_note , "note" } ,
416
{ Feat_qual_legal_number , GBQUAL_number , "number" } ,
417
{ Feat_qual_legal_old_locus_tag , GBQUAL_old_locus_tag , "old-locus-tag" } ,
418
{ Feat_qual_legal_operon , GBQUAL_operon , "operon" } ,
419
{ Feat_qual_legal_organism , GBQUAL_organism , "organism" } ,
420
{ Feat_qual_legal_organelle , GBQUAL_organelle , "organelle" } ,
421
{ Feat_qual_legal_partial , GBQUAL_partial , "partial" } ,
422
{ Feat_qual_legal_phenotype , GBQUAL_phenotype , "phenotype" } ,
423
{ Feat_qual_legal_plasmid , GBQUAL_plasmid , "plasmid" } ,
424
{ Feat_qual_legal_product , GBQUAL_product , "product" } ,
425
{ Feat_qual_legal_protein_id , GBQUAL_protein_id , "protein-id" } ,
426
{ Feat_qual_legal_pseudo , GBQUAL_pseudo , "pseudo" } ,
427
{ Feat_qual_legal_rearranged , GBQUAL_rearranged , "rearranged" } ,
428
{ Feat_qual_legal_replace , GBQUAL_replace , "replace" } ,
429
{ Feat_qual_legal_rpt_family , GBQUAL_rpt_family , "rpt-family" } ,
430
{ Feat_qual_legal_rpt_type , GBQUAL_rpt_type , "rpt-type" } ,
431
{ Feat_qual_legal_rpt_unit , GBQUAL_rpt_unit , "rpt-unit" } ,
432
{ Feat_qual_legal_rpt_unit_seq , GBQUAL_rpt_unit_seq , "rpt-unit-seq" } ,
433
{ Feat_qual_legal_rpt_unit_range , GBQUAL_rpt_unit_range , "rpt-unit-range" } ,
434
{ Feat_qual_legal_segment , GBQUAL_segment , "segment" } ,
435
{ Feat_qual_legal_sequenced_mol , GBQUAL_sequenced_mol , "sequenced-mol" } ,
436
{ Feat_qual_legal_standard_name , GBQUAL_standard_name , "standard-name" } ,
437
{ Feat_qual_legal_transcript_id , GBQUAL_transcript_id , "transcript-id" } ,
438
{ Feat_qual_legal_transgenic , GBQUAL_transgenic , "transgenic" } ,
439
{ Feat_qual_legal_translation , GBQUAL_translation , "translation" } ,
440
{ Feat_qual_legal_transl_except , GBQUAL_transl_except , "transl-except" } ,
441
{ Feat_qual_legal_transl_table , GBQUAL_transl_table , "transl-table" } ,
442
{ Feat_qual_legal_usedin , GBQUAL_usedin , "usedin" } };
443
444
#define NUM_featqual_gbqual sizeof (featqual_gbqual) / sizeof (FeatQualGBQualData)
445
446
447
NLM_EXTERN Int4 GetNumFeatQual (void)
448
{
449
return NUM_featqual_gbqual;
450
}
451
452
453
static Int4 GetGBQualFromFeatQual (Int4 featqual)
454
{
455
Int4 i;
456
457
for (i = 0; i < NUM_featqual_gbqual; i++) {
458
if (featqual == featqual_gbqual[i].featqual) {
459
return featqual_gbqual[i].gbqual;
460
}
461
}
462
return -1;
463
}
464
465
466
NLM_EXTERN CharPtr GetFeatQualName (Int4 featqual)
467
{
468
Int4 i;
469
470
for (i = 0; i < NUM_featqual_gbqual; i++) {
471
if (featqual == featqual_gbqual[i].featqual) {
472
return featqual_gbqual[i].qualname;
473
}
474
}
475
return NULL;
476
}
477
478
479
NLM_EXTERN Int4 GetFeatQualByName (CharPtr qualname)
480
{
481
Int4 i;
482
483
for (i = 0; i < NUM_featqual_gbqual; i++) {
484
if (Matchnamestring (featqual_gbqual[i].qualname, qualname)) {
485
return featqual_gbqual[i].featqual;
486
}
487
}
488
return -1;
489
}
490
491
492
NLM_EXTERN void AddAllFeatureFieldsToChoiceList (ValNodePtr PNTR field_list)
493
{
494
Int4 i;
495
496
for (i = 1; i < NUM_featqual_gbqual; i++) {
497
ValNodeAddPointer (field_list, featqual_gbqual[i].featqual, StringSave (featqual_gbqual[i].qualname));
498
}
499
}
500
501
502
#define IS_ORGMOD 1
503
#define IS_SUBSRC 2
504
#define IS_OTHER 3
505
506
typedef struct srcqualscqual {
507
Int4 srcqual;
508
Int4 subtype;
509
Int4 typeflag;
510
CharPtr qualname;
511
} SrcQualSCQualData, PNTR SrcQualSCQualPtr;
512
513
static SrcQualSCQualData srcqual_scqual[] = {
514
{ Source_qual_acronym , ORGMOD_acronym , IS_ORGMOD , "acronym" } ,
515
{ Source_qual_anamorph , ORGMOD_anamorph , IS_ORGMOD , "anamorph" } ,
516
{ Source_qual_authority , ORGMOD_authority , IS_ORGMOD , "authority" } ,
517
{ Source_qual_bio_material , ORGMOD_bio_material , IS_ORGMOD , "bio-material" } ,
518
{ Source_qual_biotype , ORGMOD_biotype , IS_ORGMOD , "biotype" } ,
519
{ Source_qual_biovar , ORGMOD_biovar , IS_ORGMOD , "biovar" } ,
520
{ Source_qual_breed , ORGMOD_breed , IS_ORGMOD , "breed" } ,
521
{ Source_qual_cell_line , SUBSRC_cell_line , IS_SUBSRC , "cell-line" } ,
522
{ Source_qual_cell_type , SUBSRC_cell_type , IS_SUBSRC , "cell-type" } ,
523
{ Source_qual_chemovar , ORGMOD_chemovar , IS_ORGMOD , "chemovar" } ,
524
{ Source_qual_chromosome , SUBSRC_chromosome , IS_SUBSRC , "chromosome" } ,
525
{ Source_qual_clone , SUBSRC_clone , IS_SUBSRC , "clone" } ,
526
{ Source_qual_clone_lib , SUBSRC_clone_lib , IS_SUBSRC , "clone-lib" } ,
527
{ Source_qual_collected_by , SUBSRC_collected_by , IS_SUBSRC , "collected-by" } ,
528
{ Source_qual_collection_date , SUBSRC_collection_date , IS_SUBSRC , "collection-date" } ,
529
{ Source_qual_common , ORGMOD_common , IS_ORGMOD , "common" } ,
530
{ Source_qual_common_name , 0 , IS_OTHER , "common name" } ,
531
{ Source_qual_country , SUBSRC_country , IS_SUBSRC , "country" } ,
532
{ Source_qual_cultivar , ORGMOD_cultivar , IS_ORGMOD , "cultivar" } ,
533
{ Source_qual_culture_collection , ORGMOD_culture_collection , IS_ORGMOD , "culture-collection" } ,
534
{ Source_qual_dev_stage , SUBSRC_dev_stage , IS_SUBSRC , "dev-stage" } ,
535
{ Source_qual_division , 0 , IS_OTHER, "divistion" } ,
536
{ Source_qual_dosage , ORGMOD_dosage , IS_ORGMOD , "dosage" } ,
537
{ Source_qual_ecotype , ORGMOD_ecotype , IS_ORGMOD , "ecotype" } ,
538
{ Source_qual_endogenous_virus_name , SUBSRC_endogenous_virus_name , IS_SUBSRC , "endogenous-virus-name" } ,
539
{ Source_qual_environmental_sample , SUBSRC_environmental_sample , IS_SUBSRC , "environmental-sample" } ,
540
{ Source_qual_forma , ORGMOD_forma , IS_ORGMOD , "forma" } ,
541
{ Source_qual_forma_specialis , ORGMOD_forma_specialis , IS_ORGMOD , "forma-specialis" } ,
542
{ Source_qual_frequency , SUBSRC_frequency , IS_SUBSRC , "frequency" } ,
543
{ Source_qual_fwd_primer_name , SUBSRC_fwd_primer_name , IS_SUBSRC , "fwd-primer-name" } ,
544
{ Source_qual_fwd_primer_seq , SUBSRC_fwd_primer_seq , IS_SUBSRC , "fwd-primer-seq" } ,
545
{ Source_qual_gb_acronym , ORGMOD_gb_acronym , IS_ORGMOD , "gb-acronym" } ,
546
{ Source_qual_gb_anamorph , ORGMOD_gb_anamorph , IS_ORGMOD , "gb-anamorph" } ,
547
{ Source_qual_gb_synonym , ORGMOD_gb_synonym , IS_ORGMOD , "gb-synonym" } ,
548
{ Source_qual_genotype , SUBSRC_genotype , IS_SUBSRC , "genotype" } ,
549
{ Source_qual_germline , SUBSRC_germline , IS_SUBSRC , "germline" } ,
550
{ Source_qual_group , ORGMOD_group , IS_ORGMOD , "group" } ,
551
{ Source_qual_haplotype , SUBSRC_haplotype , IS_SUBSRC , "haplotype" } ,
552
{ Source_qual_identified_by , SUBSRC_identified_by , IS_SUBSRC , "identified-by" } ,
553
{ Source_qual_insertion_seq_name , SUBSRC_insertion_seq_name , IS_SUBSRC , "insertion-seq-name" } ,
554
{ Source_qual_isolate , ORGMOD_isolate , IS_ORGMOD , "isolate" } ,
555
{ Source_qual_isolation_source , SUBSRC_isolation_source , IS_SUBSRC , "isolation-source" } ,
556
{ Source_qual_lab_host , SUBSRC_lab_host , IS_SUBSRC , "lab-host" } ,
557
{ Source_qual_lat_lon , SUBSRC_lat_lon , IS_SUBSRC , "lat-lon" } ,
558
{ Source_qual_lineage , 0, IS_OTHER, "lineage" } ,
559
{ Source_qual_map , SUBSRC_map , IS_SUBSRC , "map" } ,
560
{ Source_qual_metagenome_source , ORGMOD_metagenome_source , IS_ORGMOD , "metagenome-source" } ,
561
{ Source_qual_metagenomic , SUBSRC_metagenomic , IS_SUBSRC , "metagenomic" } ,
562
{ Source_qual_old_lineage , ORGMOD_old_lineage , IS_ORGMOD , "old-lineage" } ,
563
{ Source_qual_old_name , ORGMOD_old_name , IS_ORGMOD , "old-name" } ,
564
{ Source_qual_orgmod_note , ORGMOD_other, IS_ORGMOD, "orgmod note" } ,
565
{ Source_qual_nat_host , ORGMOD_nat_host , IS_ORGMOD , "nat-host" } ,
566
{ Source_qual_pathovar , ORGMOD_pathovar , IS_ORGMOD , "pathovar" } ,
567
{ Source_qual_plasmid_name , SUBSRC_plasmid_name , IS_SUBSRC , "plasmid-name" } ,
568
{ Source_qual_plastid_name , SUBSRC_plastid_name , IS_SUBSRC , "plastid-name" } ,
569
{ Source_qual_pop_variant , SUBSRC_pop_variant , IS_SUBSRC , "pop-variant" } ,
570
{ Source_qual_rearranged , SUBSRC_rearranged , IS_SUBSRC , "rearranged" } ,
571
{ Source_qual_rev_primer_name , SUBSRC_rev_primer_name , IS_SUBSRC , "rev-primer-name" } ,
572
{ Source_qual_rev_primer_seq , SUBSRC_rev_primer_seq , IS_SUBSRC , "rev-primer-seq" } ,
573
{ Source_qual_segment , SUBSRC_segment , IS_SUBSRC , "segment" } ,
574
{ Source_qual_serogroup , ORGMOD_serogroup , IS_ORGMOD , "serogroup" } ,
575
{ Source_qual_serotype , ORGMOD_serotype , IS_ORGMOD , "serotype" } ,
576
{ Source_qual_serovar , ORGMOD_serovar , IS_ORGMOD , "serovar" } ,
577
{ Source_qual_sex , SUBSRC_sex , IS_SUBSRC , "sex" } ,
578
{ Source_qual_specimen_voucher , ORGMOD_specimen_voucher , IS_ORGMOD , "specimen-voucher" } ,
579
{ Source_qual_strain , ORGMOD_strain , IS_ORGMOD , "strain" } ,
580
{ Source_qual_subclone , SUBSRC_subclone , IS_SUBSRC , "subclone" } ,
581
{ Source_qual_subgroup , ORGMOD_subgroup , IS_ORGMOD , "subgroup" } ,
582
{ Source_qual_subsource_note , SUBSRC_other , IS_SUBSRC , "subsource note" } ,
583
{ Source_qual_sub_species , ORGMOD_sub_species , IS_ORGMOD , "sub-species" } ,
584
{ Source_qual_substrain , ORGMOD_substrain , IS_ORGMOD , "substrain" } ,
585
{ Source_qual_subtype , ORGMOD_subtype , IS_ORGMOD , "subtype" } ,
586
{ Source_qual_synonym , ORGMOD_synonym , IS_ORGMOD , "synonym" } ,
587
{ Source_qual_taxname , 0 , IS_OTHER , "taxname" } ,
588
{ Source_qual_teleomorph , ORGMOD_teleomorph , IS_ORGMOD , "teleomorph" } ,
589
{ Source_qual_tissue_lib , SUBSRC_tissue_lib , IS_SUBSRC , "tissue-lib" } ,
590
{ Source_qual_tissue_type , SUBSRC_tissue_type , IS_SUBSRC , "tissue-type" } ,
591
{ Source_qual_transgenic , SUBSRC_transgenic , IS_SUBSRC , "transgenic" } ,
592
{ Source_qual_transposon_name , SUBSRC_transposon_name , IS_SUBSRC , "transposon-name" } ,
593
{ Source_qual_type , ORGMOD_type , IS_ORGMOD , "type" } ,
594
{ Source_qual_variety , ORGMOD_variety , IS_ORGMOD , "variety" } };
595
596
#define NUM_srcqual_scqual sizeof (srcqual_scqual) / sizeof (SrcQualSCQualData)
597
598
static Int4 GetSubSrcQualFromSrcQual (Int4 srcqual)
599
{
600
Int4 i;
601
602
for (i = 0; i < NUM_srcqual_scqual; i++) {
603
if (srcqual == srcqual_scqual[i].srcqual) {
604
if (srcqual_scqual[i].typeflag == IS_SUBSRC) {
605
return srcqual_scqual[i].subtype;
606
} else {
607
return -1;
608
}
609
}
610
}
611
return -1;
612
}
613
614
615
static Int4 GetOrgModQualFromSrcQual (Int4 srcqual)
616
{
617
Int4 i;
618
619
for (i = 0; i < NUM_srcqual_scqual; i++) {
620
if (srcqual == srcqual_scqual[i].srcqual) {
621
if (srcqual_scqual[i].typeflag == IS_ORGMOD) {
622
return srcqual_scqual[i].subtype;
623
} else {
624
return -1;
625
}
626
}
627
}
628
return -1;
629
}
630
631
632
NLM_EXTERN Boolean IsNonTextSourceQual (Int4 srcqual)
633
{
634
if (srcqual == Source_qual_transgenic
635
|| srcqual == Source_qual_germline
636
|| srcqual == Source_qual_metagenomic
637
|| srcqual == Source_qual_environmental_sample
638
|| srcqual == Source_qual_rearranged)
639
{
640
return TRUE;
641
}
642
else
643
{
644
return FALSE;
645
}
646
}
647
648
649
NLM_EXTERN CharPtr GetSourceQualName (Int4 srcqual)
650
{
651
CharPtr str = NULL;
652
Int4 i;
653
654
for (i = 0; i < NUM_srcqual_scqual && str == NULL; i++) {
655
if (srcqual_scqual[i].srcqual == srcqual) {
656
str = srcqual_scqual[i].qualname;
657
}
658
}
659
if (str == NULL) {
660
str = "Unknown source qualifier";
661
}
662
return str;
663
}
664
665
666
NLM_EXTERN Int4 GetSourceQualTypeByName (CharPtr qualname)
667
{
668
Int4 i;
669
670
for (i = 0; i < NUM_srcqual_scqual; i++) {
671
if (Matchnamestring(srcqual_scqual[i].qualname, qualname)) {
672
return srcqual_scqual[i].srcqual;
673
}
674
}
675
return -1;
676
}
677
678
679
NLM_EXTERN ValNodePtr GetSourceQualList (void)
680
{
681
ValNodePtr list = NULL;
682
Int4 i;
683
684
for (i = 0; i < NUM_srcqual_scqual; i++) {
685
ValNodeAddPointer (&list, 0, StringSave (srcqual_scqual[i].qualname));
686
}
687
return list;
688
}
689
690
typedef struct srclocgenome {
691
Int4 srcloc;
692
Int4 genome;
693
CharPtr name;
694
} SrcLocGenomeData, PNTR SrcLocGenomePtr;
695
696
static SrcLocGenomeData srcloc_genome[] = {
697
{ Source_location_unknown , GENOME_unknown , "unknown" } ,
698
{ Source_location_genomic , GENOME_genomic , "genomic" } ,
699
{ Source_location_chloroplast , GENOME_chloroplast , "chloroplast" } ,
700
{ Source_location_chromoplast , GENOME_chromoplast , "chromoplast" } ,
701
{ Source_location_kinetoplast , GENOME_kinetoplast , "kinetoplast" } ,
702
{ Source_location_mitochondrion , GENOME_mitochondrion , "mitochondrion" } ,
703
{ Source_location_plastid , GENOME_plastid , "plastid" } ,
704
{ Source_location_macronuclear , GENOME_macronuclear , "macronuclear" } ,
705
{ Source_location_extrachrom , GENOME_extrachrom , "extrachrom" } ,
706
{ Source_location_plasmid , GENOME_plasmid , "plasmid" } ,
707
{ Source_location_transposon , GENOME_transposon , "transposon" } ,
708
{ Source_location_insertion_seq , GENOME_insertion_seq , "insertion-seq" } ,
709
{ Source_location_cyanelle , GENOME_cyanelle , "cyanelle" } ,
710
{ Source_location_proviral , GENOME_proviral , "proviral" } ,
711
{ Source_location_virion , GENOME_virion , "virion" } ,
712
{ Source_location_nucleomorph , GENOME_nucleomorph , "nucleomorph" } ,
713
{ Source_location_apicoplast , GENOME_apicoplast , "apicoplast" } ,
714
{ Source_location_leucoplast , GENOME_leucoplast , "leucoplast" } ,
715
{ Source_location_proplastid , GENOME_proplastid , "proplastid" } ,
716
{ Source_location_endogenous_virus , GENOME_endogenous_virus , "endogenous-virus" } ,
717
{ Source_location_hydrogenosome , GENOME_hydrogenosome , "hydrogenosome" } ,
718
{ Source_location_chromosome , 21 , "chromosome" } ,
719
{ Source_location_chromatophore , 22 , "chromatophore" } };
720
721
#define NUM_srcloc_genome sizeof (srcloc_genome) / sizeof (SrcLocGenomeData)
722
723
NLM_EXTERN Int4 GenomeFromSrcLoc (Int4 srcloc) \
724
{
725
Int4 i;
726
727
for (i = 0; i < NUM_srcloc_genome; i++) {
728
if (srcloc_genome[i].srcloc == srcloc) {
729
return srcloc_genome[i].genome;
730
}
731
}
732
return -1;
733
}
734
735
736
NLM_EXTERN CharPtr LocNameFromGenome (Int4 genome)
737
{
738
Int4 i;
739
740
for (i = 0; i < NUM_srcloc_genome; i++) {
741
if (srcloc_genome[i].genome == genome) {
742
return srcloc_genome[i].name;
743
}
744
}
745
return NULL;
746
}
747
748
749
static Int4 GenomeFromLocName (CharPtr loc_name)
750
{
751
Int4 i;
752
753
for (i = 0; i < NUM_srcloc_genome; i++) {
754
if (StringICmp (srcloc_genome[i].name, loc_name) == 0) {
755
return srcloc_genome[i].genome;
756
}
757
}
758
return -1;
759
}
760
761
762
NLM_EXTERN ValNodePtr GetLocationList (Boolean for_remove)
763
{
764
ValNodePtr list = NULL;
765
Int4 i;
766
767
for (i = 0; i < NUM_srcloc_genome; i++) {
768
if (for_remove && srcloc_genome[i].srcloc == Source_location_unknown) {
769
ValNodeAddPointer (&list, srcloc_genome[i].srcloc, StringSave ("any"));
770
} else {
771
ValNodeAddPointer (&list, srcloc_genome[i].srcloc, StringSave (srcloc_genome[i].name));
772
}
773
}
774
return list;
775
}
776
777
778
typedef struct srcorigorigin {
779
Int4 srcorig;
780
Int4 origin;
781
CharPtr name;
782
} SrcOrigOriginData, PNTR SrcrigOriginPtr;
783
784
static SrcOrigOriginData srcorig_origin[] = {
785
{ Source_origin_unknown , 0 , "unknown" } ,
786
{ Source_origin_natural , 1 , "natural" } ,
787
{ Source_origin_natmut , 2 , "natmut" } ,
788
{ Source_origin_mut , 3 , "mut" } ,
789
{ Source_origin_artificial , 4 , "artificial" } ,
790
{ Source_origin_synthetic , 5 , "synthetic" } ,
791
{ Source_origin_other , 255 , "other" } };
792
793
#define NUM_srcorig_origin sizeof (srcorig_origin) / sizeof (SrcOrigOriginData)
794
795
NLM_EXTERN Int4 OriginFromSrcOrig (Int4 srcorig)
796
{
797
Int4 i;
798
799
for (i = 0; i < NUM_srcorig_origin; i++) {
800
if (srcorig_origin[i].srcorig == srcorig) {
801
return srcorig_origin[i].origin;
802
}
803
}
804
return -1;
805
}
806
807
808
NLM_EXTERN CharPtr OriginNameFromOrigin (Int4 origin)
809
{
810
Int4 i;
811
812
for (i = 0; i < NUM_srcorig_origin; i++) {
813
if (srcorig_origin[i].origin == origin) {
814
return srcorig_origin[i].name;
815
}
816
}
817
return NULL;
818
}
819
820
821
static Int4 OriginFromOriginName (CharPtr origin_name)
822
{
823
Int4 i;
824
825
for (i = 0; i < NUM_srcorig_origin; i++) {
826
if (StringCmp (srcorig_origin[i].name, origin_name) == 0) {
827
return srcorig_origin[i].origin;
828
}
829
}
830
return -1;
831
}
832
833
834
NLM_EXTERN ValNodePtr GetOriginList (Boolean for_remove)
835
{
836
ValNodePtr list = NULL;
837
Int4 i;
838
839
for (i = 0; i < NUM_srcorig_origin; i++) {
840
if (for_remove && srcorig_origin[i].srcorig == Source_origin_unknown) {
841
ValNodeAddPointer (&list, srcorig_origin[i].srcorig, StringSave ("any"));
842
} else {
843
ValNodeAddPointer (&list, srcorig_origin[i].srcorig, StringSave (srcorig_origin[i].name));
844
}
845
}
846
return list;
847
}
848
849
850
typedef struct cdsgeneprotfieldname {
851
Int4 field;
852
CharPtr name;
853
} CDSGeneProtFieldNameData, PNTR CDSGeneProtFieldNamePtr;
854
855
static CDSGeneProtFieldNameData cdsgeneprotfield_name[] = {
856
{ CDSGeneProt_field_cds_comment , "CDS comment" } ,
857
{ CDSGeneProt_field_gene_locus , "gene locus" } ,
858
{ CDSGeneProt_field_gene_description , "gene description" } ,
859
{ CDSGeneProt_field_gene_comment , "gene comment" } ,
860
{ CDSGeneProt_field_gene_allele , "allele" } ,
861
{ CDSGeneProt_field_gene_maploc , "maploc" } ,
862
{ CDSGeneProt_field_gene_locus_tag , "locus tag" } ,
863
{ CDSGeneProt_field_gene_synonym , "synonym" } ,
864
{ CDSGeneProt_field_gene_old_locus_tag , "old locus tag" } ,
865
{ CDSGeneProt_field_mrna_product , "mRNA product" } ,
866
{ CDSGeneProt_field_mrna_comment , "mRNA comment" } ,
867
{ CDSGeneProt_field_prot_name , "protein name" } ,
868
{ CDSGeneProt_field_prot_description , "protein description" } ,
869
{ CDSGeneProt_field_prot_ec_number , "protein EC number" } ,
870
{ CDSGeneProt_field_prot_activity , "protein activity" } ,
871
{ CDSGeneProt_field_prot_comment , "protein comment" } ,
872
{ CDSGeneProt_field_mat_peptide_name , "mat-peptide name" } ,
873
{ CDSGeneProt_field_mat_peptide_description , "mat-peptide description" } ,
874
{ CDSGeneProt_field_mat_peptide_ec_number , "mat-peptide EC number" } ,
875
{ CDSGeneProt_field_mat_peptide_activity , "mat-peptide activity" } ,
876
{ CDSGeneProt_field_mat_peptide_comment , "mat-peptide comment" } };
877
878
#define NUM_cdsgeneprotfield_name sizeof (cdsgeneprotfield_name) / sizeof (CDSGeneProtFieldNameData)
879
880
NLM_EXTERN CharPtr CDSGeneProtNameFromField (Int4 field)
881
{
882
Int4 i;
883
884
for (i = 0; i < NUM_cdsgeneprotfield_name; i++) {
885
if (cdsgeneprotfield_name[i].field == field) {
886
return cdsgeneprotfield_name[i].name;
887
}
888
}
889
return NULL;
890
}
891
892
893
NLM_EXTERN void AddAllCDSGeneProtFieldsToChoiceList (ValNodePtr PNTR field_list)
894
{
895
Int4 i;
896
897
for (i = 0; i < NUM_cdsgeneprotfield_name; i++) {
898
ValNodeAddPointer (field_list, cdsgeneprotfield_name[i].field, StringSave (cdsgeneprotfield_name[i].name));
899
}
900
}
901
902
903
typedef struct cdsgeneprotfeatname {
904
Int4 feature_type;
905
CharPtr name;
906
} CDSGeneProtFeatNameData, PNTR CDSGeneProtFeatNamePtr;
907
908
static CDSGeneProtFeatNameData cdsgeneprotfeat_name[] = {
909
{ CDSGeneProt_feature_type_constraint_gene , "gene" } ,
910
{ CDSGeneProt_feature_type_constraint_mRNA , "mRNA" } ,
911
{ CDSGeneProt_feature_type_constraint_cds , "CDS" } ,
912
{ CDSGeneProt_feature_type_constraint_prot , "protein" } ,
913
{ CDSGeneProt_feature_type_constraint_mat_peptide , "mat-peptide" }};
914
915
#define NUM_cdsgeneprotfeat_name sizeof (cdsgeneprotfeat_name) / sizeof (CDSGeneProtFeatNameData)
916
917
NLM_EXTERN CharPtr CDSGeneProtFeatureNameFromFeatureType (Int4 feature_type)
918
{
919
Int4 i;
920
921
for (i = 0; i < NUM_cdsgeneprotfeat_name; i++) {
922
if (cdsgeneprotfeat_name[i].feature_type == feature_type) {
923
return cdsgeneprotfeat_name[i].name;
924
}
925
}
926
return NULL;
927
}
928
929
930
NLM_EXTERN void AddAllCDSGeneProtFeaturesToChoiceList (ValNodePtr PNTR field_list)
931
{
932
Int4 i;
933
934
for (i = 0; i < NUM_cdsgeneprotfeat_name; i++) {
935
ValNodeAddPointer (field_list, cdsgeneprotfeat_name[i].feature_type, StringSave (cdsgeneprotfeat_name[i].name));
936
}
937
}
938
939
940
NLM_EXTERN FeatureFieldPtr FeatureFieldFromCDSGeneProtField (Uint2 cds_gene_prot_field)
941
{
942
FeatureFieldPtr f = NULL;
943
944
switch (cds_gene_prot_field) {
945
case CDSGeneProt_field_cds_comment:
946
f = FeatureFieldNew ();
947
f->type = Feature_type_cds;
948
f->field = ValNodeNew (NULL);
949
f->field->choice = FeatQualChoice_legal_qual;
950
f->field->data.intvalue = Feat_qual_legal_note;
951
break;
952
case CDSGeneProt_field_gene_locus:
953
f = FeatureFieldNew ();
954
f->type = Feature_type_gene;
955
f->field = ValNodeNew (NULL);
956
f->field->choice = FeatQualChoice_legal_qual;
957
f->field->data.intvalue = Feat_qual_legal_gene;
958
break;
959
case CDSGeneProt_field_gene_description:
960
f = FeatureFieldNew ();
961
f->type = Feature_type_gene;
962
f->field = ValNodeNew (NULL);
963
f->field->choice = FeatQualChoice_legal_qual;
964
f->field->data.intvalue = Feat_qual_legal_gene_description;
965
break;
966
case CDSGeneProt_field_gene_comment:
967
f = FeatureFieldNew ();
968
f->type = Feature_type_gene;
969
f->field = ValNodeNew (NULL);
970
f->field->choice = FeatQualChoice_legal_qual;
971
f->field->data.intvalue = Feat_qual_legal_note;
972
break;
973
case CDSGeneProt_field_gene_allele:
974
f = FeatureFieldNew ();
975
f->type = Feature_type_gene;
976
f->field = ValNodeNew (NULL);
977
f->field->choice = FeatQualChoice_legal_qual;
978
f->field->data.intvalue = Feat_qual_legal_allele;
979
break;
980
case CDSGeneProt_field_gene_maploc:
981
f = FeatureFieldNew ();
982
f->type = Feature_type_gene;
983
f->field = ValNodeNew (NULL);
984
f->field->choice = FeatQualChoice_legal_qual;
985
f->field->data.intvalue = Feat_qual_legal_map;
986
break;
987
case CDSGeneProt_field_gene_locus_tag:
988
f = FeatureFieldNew ();
989
f->type = Feature_type_gene;
990
f->field = ValNodeNew (NULL);
991
f->field->choice = FeatQualChoice_legal_qual;
992
f->field->data.intvalue = Feat_qual_legal_locus_tag;
993
break;
994
case CDSGeneProt_field_gene_synonym:
995
f = FeatureFieldNew ();
996
f->type = Feature_type_gene;
997
f->field = ValNodeNew (NULL);
998
f->field->choice = FeatQualChoice_legal_qual;
999
f->field->data.intvalue = Feat_qual_legal_synonym;
1000
break;
1001
case CDSGeneProt_field_gene_old_locus_tag:
1002
f = FeatureFieldNew ();
1003
f->type = Feature_type_gene;
1004
f->field = ValNodeNew (NULL);
1005
f->field->choice = FeatQualChoice_legal_qual;
1006
f->field->data.intvalue = Feat_qual_legal_old_locus_tag;
1007
break;
1008
case CDSGeneProt_field_mrna_product:
1009
f = FeatureFieldNew ();
1010
f->type = Feature_type_mRNA;
1011
f->field = ValNodeNew (NULL);
1012
f->field->choice = FeatQualChoice_legal_qual;
1013
f->field->data.intvalue = Feat_qual_legal_product;
1014
break;
1015
case CDSGeneProt_field_mrna_comment:
1016
f = FeatureFieldNew ();
1017
f->type = Feature_type_mRNA;
1018
f->field = ValNodeNew (NULL);
1019
f->field->choice = FeatQualChoice_legal_qual;
1020
f->field->data.intvalue = Feat_qual_legal_note;
1021
break;
1022
case CDSGeneProt_field_prot_name:
1023
f = FeatureFieldNew ();
1024
f->type = Feature_type_prot;
1025
f->field = ValNodeNew (NULL);
1026
f->field->choice = FeatQualChoice_legal_qual;
1027
f->field->data.intvalue = Feat_qual_legal_product;
1028
break;
1029
case CDSGeneProt_field_prot_description:
1030
f = FeatureFieldNew ();
1031
f->type = Feature_type_prot;
1032
f->field = ValNodeNew (NULL);
1033
f->field->choice = FeatQualChoice_legal_qual;
1034
f->field->data.intvalue = Feat_qual_legal_description;
1035
break;
1036
case CDSGeneProt_field_prot_ec_number:
1037
f = FeatureFieldNew ();
1038
f->type = Feature_type_prot;
1039
f->field = ValNodeNew (NULL);
1040
f->field->choice = FeatQualChoice_legal_qual;
1041
f->field->data.intvalue = Feat_qual_legal_ec_number;
1042
break;
1043
case CDSGeneProt_field_prot_activity:
1044
f = FeatureFieldNew ();
1045
f->type = Feature_type_prot;
1046
f->field = ValNodeNew (NULL);
1047
f->field->choice = FeatQualChoice_legal_qual;
1048
f->field->data.intvalue = Feat_qual_legal_activity;
1049
break;
1050
case CDSGeneProt_field_prot_comment:
1051
f = FeatureFieldNew ();
1052
f->type = Feature_type_prot;
1053
f->field = ValNodeNew (NULL);
1054
f->field->choice = FeatQualChoice_legal_qual;
1055
f->field->data.intvalue = Feat_qual_legal_note;
1056
break;
1057
case CDSGeneProt_field_mat_peptide_name:
1058
f = FeatureFieldNew ();
1059
f->type = Feature_type_mat_peptide;
1060
f->field = ValNodeNew (NULL);
1061
f->field->choice = FeatQualChoice_legal_qual;
1062
f->field->data.intvalue = Feat_qual_legal_product;
1063
break;
1064
case CDSGeneProt_field_mat_peptide_description:
1065
f = FeatureFieldNew ();
1066
f->type = Feature_type_mat_peptide;
1067
f->field = ValNodeNew (NULL);
1068
f->field->choice = FeatQualChoice_legal_qual;
1069
f->field->data.intvalue = Feat_qual_legal_description;
1070
break;
1071
case CDSGeneProt_field_mat_peptide_ec_number:
1072
f = FeatureFieldNew ();
1073
f->type = Feature_type_mat_peptide;
1074
f->field = ValNodeNew (NULL);
1075
f->field->choice = FeatQualChoice_legal_qual;
1076
f->field->data.intvalue = Feat_qual_legal_ec_number;
1077
break;
1078
case CDSGeneProt_field_mat_peptide_activity:
1079
f = FeatureFieldNew ();
1080
f->type = Feature_type_mat_peptide;
1081
f->field = ValNodeNew (NULL);
1082
f->field->choice = FeatQualChoice_legal_qual;
1083
f->field->data.intvalue = Feat_qual_legal_activity;
1084
break;
1085
case CDSGeneProt_field_mat_peptide_comment:
1086
f = FeatureFieldNew ();
1087
f->type = Feature_type_mat_peptide;
1088
f->field = ValNodeNew (NULL);
1089
f->field->choice = FeatQualChoice_legal_qual;
1090
f->field->data.intvalue = Feat_qual_legal_note;
1091
break;
1092
}
1093
return f;
1094
}
1095
1096
1097
/* Molinfo fields */
1098
typedef struct moleculetypebiomol {
1099
Int4 molecule_type;
1100
Int4 biomol;
1101
CharPtr name;
1102
} MoleculeTypeBiomolData, PNTR MoleculeTypeBiomolPtr;
1103
1104
static MoleculeTypeBiomolData moleculetype_biomol[] = {
1105
{ Molecule_type_unknown , 0, "unknown" } ,
1106
{ Molecule_type_genomic , MOLECULE_TYPE_GENOMIC , "genomic" } ,
1107
{ Molecule_type_precursor_RNA , MOLECULE_TYPE_PRE_MRNA , "precursor RNA" } ,
1108
{ Molecule_type_mRNA , MOLECULE_TYPE_MRNA , "mRNA" } ,
1109
{ Molecule_type_rRNA , MOLECULE_TYPE_RRNA , "rRNA" } ,
1110
{ Molecule_type_tRNA , MOLECULE_TYPE_TRNA , "tRNA" } ,
1111
{ Molecule_type_snRNA , MOLECULE_TYPE_SNRNA , "snRNA" } ,
1112
{ Molecule_type_scRNA , MOLECULE_TYPE_SCRNA , "scRNA" } ,
1113
{ Molecule_type_genomic_mRNA , MOLECULE_TYPE_GENOMIC_MRNA_MIX , "genomic mRNA" } ,
1114
{ Molecule_type_cRNA , MOLECULE_TYPE_CRNA , "cRNA" } ,
1115
{ Molecule_type_scRNA , MOLECULE_TYPE_SCRNA , "scRNA" } ,
1116
{ Molecule_type_scRNA , MOLECULE_TYPE_SCRNA , "scRNA" } ,
1117
{ Molecule_type_scRNA , MOLECULE_TYPE_SCRNA , "scRNA" } ,
1118
{ Molecule_type_snoRNA , MOLECULE_TYPE_SNORNA, "snoRNA" } ,
1119
{ Molecule_type_transcribed_RNA, MOLECULE_TYPE_TRANSCRIBED_RNA, "transcribed RNA" } ,
1120
{ Molecule_type_ncRNA, MOLECULE_TYPE_NCRNA, "ncRNA" } ,
1121
{ Molecule_type_transfer_messenger_RNA, MOLECULE_TYPE_TMRNA, "tmRNA" } ,
1122
{ Molecule_type_other, MOLECULE_TYPE_OTHER_GENETIC_MATERIAL, "other" }
1123
};
1124
1125
1126
#define NUM_moleculetype_biomol sizeof (moleculetype_biomol) / sizeof (MoleculeTypeBiomolData)
1127
1128
NLM_EXTERN Int4 BiomolFromMoleculeType (Int4 molecule_type)
1129
{
1130
Int4 i;
1131
1132
for (i = 0; i < NUM_moleculetype_biomol; i++) {
1133
if (moleculetype_biomol[i].molecule_type == molecule_type) {
1134
return moleculetype_biomol[i].biomol;
1135
}
1136
}
1137
return -1;
1138
}
1139
1140
1141
NLM_EXTERN CharPtr BiomolNameFromBiomol (Int4 biomol)
1142
{
1143
Int4 i;
1144
1145
for (i = 0; i < NUM_moleculetype_biomol; i++) {
1146
if (moleculetype_biomol[i].biomol == biomol) {
1147
return moleculetype_biomol[i].name;
1148
}
1149
}
1150
return NULL;
1151
}
1152
1153
1154
static Int4 BiomolFromBiomolName (CharPtr biomol_name)
1155
{
1156
Int4 i;
1157
1158
for (i = 0; i < NUM_moleculetype_biomol; i++) {
1159
if (StringCmp (moleculetype_biomol[i].name, biomol_name) == 0) {
1160
return moleculetype_biomol[i].biomol;
1161
}
1162
}
1163
return -1;
1164
}
1165
1166
1167
NLM_EXTERN ValNodePtr GetMoleculeTypeList (void)
1168
{
1169
ValNodePtr list = NULL;
1170
Int4 i;
1171
1172
for (i = 0; i < NUM_moleculetype_biomol; i++) {
1173
ValNodeAddPointer (&list, moleculetype_biomol[i].molecule_type, StringSave (moleculetype_biomol[i].name));
1174
}
1175
return list;
1176
}
1177
1178
1179
/* Technique fields */
1180
typedef struct techniquetypetech {
1181
Int4 technique_type;
1182
Int4 tech;
1183
CharPtr name;
1184
} TechniqueTypeTechData, PNTR TechniqueTypeTechPtr;
1185
1186
static TechniqueTypeTechData techniquetype_tech[] = {
1187
{ Technique_type_unknown , MI_TECH_unknown , "unknown" } ,
1188
{ Technique_type_standard , MI_TECH_standard , "standard" } ,
1189
{ Technique_type_est , MI_TECH_est , "EST" } ,
1190
{ Technique_type_sts , MI_TECH_sts , "STS" } ,
1191
{ Technique_type_survey , MI_TECH_survey , "survey" } ,
1192
{ Technique_type_genetic_map , MI_TECH_genemap , "genetic map" } ,
1193
{ Technique_type_physical_map , MI_TECH_physmap , "physical map" } ,
1194
{ Technique_type_derived , MI_TECH_derived , "derived" } ,
1195
{ Technique_type_concept_trans , MI_TECH_concept_trans , "concept-trans" } ,
1196
{ Technique_type_seq_pept , MI_TECH_seq_pept , "seq-pept" } ,
1197
{ Technique_type_both , MI_TECH_both , "both" } ,
1198
{ Technique_type_seq_pept_overlap , MI_TECH_seq_pept_overlap , "seq-pept-overlap" } ,
1199
{ Technique_type_seq_pept_homol , MI_TECH_seq_pept_homol, "seq-pept-homol" } ,
1200
{ Technique_type_concept_trans_a, MI_TECH_concept_trans_a, "concept-trans-a" } ,
1201
{ Technique_type_htgs_1, MI_TECH_htgs_1, "HTGS-1" } ,
1202
{ Technique_type_htgs_2, MI_TECH_htgs_2, "HTGS-2" } ,
1203
{ Technique_type_htgs_3, MI_TECH_htgs_3, "HTGS-3" } ,
1204
{ Technique_type_fli_cDNA, MI_TECH_fli_cdna, "fli-cDNA" } ,
1205
{ Technique_type_htgs_0, MI_TECH_htgs_0, "HTGS-0" } ,
1206
{ Technique_type_htc, MI_TECH_htc, "HTC" } ,
1207
{ Technique_type_wgs, MI_TECH_wgs, "WGS" } ,
1208
{ Technique_type_barcode, MI_TECH_barcode, "BARCODE" } ,
1209
{ Technique_type_composite_wgs_htgs, MI_TECH_composite_wgs_htgs, "composite WGS-HTGS" } ,
1210
{ Technique_type_tsa, MI_TECH_tsa, "TSA" } ,
1211
{ Technique_type_other, MI_TECH_other, "other" }
1212
};
1213
1214
1215
#define NUM_techniquetype_tech sizeof (techniquetype_tech) / sizeof (TechniqueTypeTechData)
1216
1217
NLM_EXTERN Int4 TechFromTechniqueType (Int4 technique_type)
1218
{
1219
Int4 i;
1220
1221
for (i = 0; i < NUM_techniquetype_tech; i++) {
1222
if (techniquetype_tech[i].technique_type == technique_type) {
1223
return techniquetype_tech[i].tech;
1224
}
1225
}
1226
return -1;
1227
}
1228
1229
1230
NLM_EXTERN CharPtr TechNameFromTech (Int4 tech)
1231
{
1232
Int4 i;
1233
1234
for (i = 0; i < NUM_techniquetype_tech; i++) {
1235
if (techniquetype_tech[i].tech == tech) {
1236
return techniquetype_tech[i].name;
1237
}
1238
}
1239
return NULL;
1240
}
1241
1242
1243
static Int4 TechFromTechName (CharPtr tech_name)
1244
{
1245
Int4 i;
1246
1247
for (i = 0; i < NUM_techniquetype_tech; i++) {
1248
if (StringCmp (techniquetype_tech[i].name, tech_name) == 0) {
1249
return techniquetype_tech[i].tech;
1250
}
1251
}
1252
return -1;
1253
}
1254
1255
1256
NLM_EXTERN ValNodePtr GetTechniqueTypeList (void)
1257
{
1258
ValNodePtr list = NULL;
1259
Int4 i;
1260
1261
for (i = 0; i < NUM_techniquetype_tech; i++) {
1262
ValNodeAddPointer (&list, techniquetype_tech[i].technique_type, StringSave (techniquetype_tech[i].name));
1263
}
1264
return list;
1265
}
1266
1267
1268
/* Completedness fields */
1269
typedef struct completednesstypecompleteness {
1270
Int4 completedness_type;
1271
Int4 completeness;
1272
CharPtr name;
1273
} CompletednessTypeCompletenessData, PNTR CompletednessTypeCompletenessPtr;
1274
1275
static CompletednessTypeCompletenessData completednesstype_completeness[] = {
1276
{ Completedness_type_unknown, 0, "unknown" } ,
1277
{ Completedness_type_complete, 1, "complete" } ,
1278
{ Completedness_type_partial, 2, "partial" } ,
1279
{ Completedness_type_no_left, 3, "no left" } ,
1280
{ Completedness_type_no_right, 4, "no right" } ,
1281
{ Completedness_type_no_ends, 5, "no ends" } ,
1282
{ Completedness_type_has_left, 6, "has left" } ,
1283
{ Completedness_type_has_right, 7, "has right" } ,
1284
{ Completedness_type_other, 255, "other" }
1285
};
1286
1287
#define NUM_completednesstype_completeness sizeof (completednesstype_completeness) / sizeof (CompletednessTypeCompletenessData)
1288
1289
NLM_EXTERN Int4 CompletenessFromCompletednessType (Int4 completedness_type)
1290
{
1291
Int4 i;
1292
1293
for (i = 0; i < NUM_completednesstype_completeness; i++) {
1294
if (completednesstype_completeness[i].completedness_type == completedness_type) {
1295
return completednesstype_completeness[i].completeness;
1296
}
1297
}
1298
return -1;
1299
}
1300
1301
1302
NLM_EXTERN CharPtr CompletenessNameFromCompleteness (Int4 completeness)
1303
{
1304
Int4 i;
1305
1306
for (i = 0; i < NUM_completednesstype_completeness; i++) {
1307
if (completednesstype_completeness[i].completeness == completeness) {
1308
return completednesstype_completeness[i].name;
1309
}
1310
}
1311
return NULL;
1312
}
1313
1314
1315
static Int4 CompletenessFromCompletenessName (CharPtr completeness_name)
1316
{
1317
Int4 i;
1318
1319
for (i = 0; i < NUM_completednesstype_completeness; i++) {
1320
if (StringCmp (completednesstype_completeness[i].name, completeness_name) == 0) {
1321
return completednesstype_completeness[i].completeness;
1322
}
1323
}
1324
return -1;
1325
}
1326
1327
1328
NLM_EXTERN ValNodePtr GetCompletednessTypeList (void)
1329
{
1330
ValNodePtr list = NULL;
1331
Int4 i;
1332
1333
for (i = 0; i < NUM_completednesstype_completeness; i++) {
1334
ValNodeAddPointer (&list, completednesstype_completeness[i].completedness_type, StringSave (completednesstype_completeness[i].name));
1335
}
1336
return list;
1337
}
1338
1339
1340
/* Molecule class fields */
1341
typedef struct moleculeclasstypemol {
1342
Int4 moleculeclass_type;
1343
Int4 mol;
1344
CharPtr name;
1345
} MoleculeClassTypeMolData, PNTR MoleculeClassTypeMolPtr;
1346
1347
static MoleculeClassTypeMolData moleculeclasstype_mol[] = {
1348
{ Molecule_class_type_unknown, 0, "unknown" } ,
1349
{ Molecule_class_type_dna, MOLECULE_CLASS_DNA, "DNA" } ,
1350
{ Molecule_class_type_rna, MOLECULE_CLASS_RNA, "RNA" } ,
1351
{ Molecule_class_type_protein, MOLECULE_CLASS_PROTEIN, "protein" } ,
1352
{ Molecule_class_type_nucleotide, MOLECULE_CLASS_NUC, "nucleotide" } ,
1353
{ Molecule_class_type_other, 255, "other" }
1354
};
1355
1356
1357
#define NUM_moleculeclasstype_mol sizeof (moleculeclasstype_mol) / sizeof (MoleculeClassTypeMolData)
1358
1359
NLM_EXTERN Int4 MolFromMoleculeClassType (Int4 moleculeclass_type)
1360
{
1361
Int4 i;
1362
1363
for (i = 0; i < NUM_moleculeclasstype_mol; i++) {
1364
if (moleculeclasstype_mol[i].moleculeclass_type == moleculeclass_type) {
1365
return moleculeclasstype_mol[i].mol;
1366
}
1367
}
1368
return -1;
1369
}
1370
1371
1372
NLM_EXTERN CharPtr MolNameFromMol (Int4 mol)
1373
{
1374
Int4 i;
1375
1376
for (i = 0; i < NUM_moleculeclasstype_mol; i++) {
1377
if (moleculeclasstype_mol[i].mol == mol) {
1378
return moleculeclasstype_mol[i].name;
1379
}
1380
}
1381
return NULL;
1382
}
1383
1384
1385
static Int4 MolFromMolName (CharPtr mol_name)
1386
{
1387
Int4 i;
1388
1389
for (i = 0; i < NUM_moleculeclasstype_mol; i++) {
1390
if (StringCmp (moleculeclasstype_mol[i].name, mol_name) == 0) {
1391
return moleculeclasstype_mol[i].mol;
1392
}
1393
}
1394
return -1;
1395
}
1396
1397
1398
NLM_EXTERN ValNodePtr GetMoleculeClassTypeList (void)
1399
{
1400
ValNodePtr list = NULL;
1401
Int4 i;
1402
1403
for (i = 0; i < NUM_moleculeclasstype_mol; i++) {
1404
ValNodeAddPointer (&list, moleculeclasstype_mol[i].moleculeclass_type, StringSave (moleculeclasstype_mol[i].name));
1405
}
1406
return list;
1407
}
1408
1409
1410
/* Topology fields */
1411
typedef struct topologytypetopology {
1412
Int4 topology_type;
1413
Int4 topology;
1414
CharPtr name;
1415
} TopologyTypeTopologyData, PNTR TopologyTypeTopologyPtr;
1416
1417
static TopologyTypeTopologyData topologytype_topology[] = {
1418
{ Topology_type_unknown, 0, "unknown" } ,
1419
{ Topology_type_linear, TOPOLOGY_LINEAR, "linear" } ,
1420
{ Topology_type_circular, TOPOLOGY_CIRCULAR, "circular" } ,
1421
{ Topology_type_tandem, TOPOLOGY_TANDEM, "tandem" } ,
1422
{ Topology_type_other, 255, "other" }
1423
};
1424
1425
#define NUM_topologytype_topology sizeof (topologytype_topology) / sizeof (TopologyTypeTopologyData)
1426
1427
NLM_EXTERN Int4 TopologyFromTopologyType (Int4 topology_type)
1428
{
1429
Int4 i;
1430
1431
for (i = 0; i < NUM_topologytype_topology; i++) {
1432
if (topologytype_topology[i].topology_type == topology_type) {
1433
return topologytype_topology[i].topology;
1434
}
1435
}
1436
return -1;
1437
}
1438
1439
1440
NLM_EXTERN CharPtr TopologyNameFromTopology (Int4 topology)
1441
{
1442
Int4 i;
1443
1444
for (i = 0; i < NUM_topologytype_topology; i++) {
1445
if (topologytype_topology[i].topology == topology) {
1446
return topologytype_topology[i].name;
1447
}
1448
}
1449
return NULL;
1450
}
1451
1452
1453
static Int4 TopologyFromTopologyName (CharPtr topology_name)
1454
{
1455
Int4 i;
1456
1457
for (i = 0; i < NUM_topologytype_topology; i++) {
1458
if (StringCmp (topologytype_topology[i].name, topology_name) == 0) {
1459
return topologytype_topology[i].topology;
1460
}
1461
}
1462
return -1;
1463
}
1464
1465
1466
NLM_EXTERN ValNodePtr GetTopologyTypeList (void)
1467
{
1468
ValNodePtr list = NULL;
1469
Int4 i;
1470
1471
for (i = 0; i < NUM_topologytype_topology; i++) {
1472
ValNodeAddPointer (&list, topologytype_topology[i].topology_type, StringSave (topologytype_topology[i].name));
1473
}
1474
return list;
1475
}
1476
1477
1478
/* strand fields */
1479
typedef struct strandtypestrand {
1480
Int4 strand_type;
1481
Int4 strand;
1482
CharPtr name;
1483
} StrandTypeStrandData, PNTR StrandTypeStrandPtr;
1484
1485
static StrandTypeStrandData strandtype_strand[] = {
1486
{ Strand_type_unknown, 0, "unknown" } ,
1487
{ Strand_type_single, STRANDEDNESS_SINGLE, "single" } ,
1488
{ Strand_type_double__, STRANDEDNESS_DOUBLE, "double" } ,
1489
{ Strand_type_mixed, 3, "mixed" } ,
1490
{ Strand_type_mixed_rev, 4, "mixed-rev" } ,
1491
{ Strand_type_other, 255, "other" }
1492
};
1493
1494
#define NUM_strandtype_strand sizeof (strandtype_strand) / sizeof (StrandTypeStrandData)
1495
1496
NLM_EXTERN Int4 StrandFromStrandType (Int4 strand_type)
1497
{
1498
Int4 i;
1499
1500
for (i = 0; i < NUM_strandtype_strand; i++) {
1501
if (strandtype_strand[i].strand_type == strand_type) {
1502
return strandtype_strand[i].strand;
1503
}
1504
}
1505
return -1;
1506
}
1507
1508
1509
NLM_EXTERN CharPtr StrandNameFromStrand (Int4 strand)
1510
{
1511
Int4 i;
1512
1513
for (i = 0; i < NUM_strandtype_strand; i++) {
1514
if (strandtype_strand[i].strand == strand) {
1515
return strandtype_strand[i].name;
1516
}
1517
}
1518
return NULL;
1519
}
1520
1521
1522
static Int4 StrandFromStrandName (CharPtr strand_name)
1523
{
1524
Int4 i;
1525
1526
for (i = 0; i < NUM_strandtype_strand; i++) {
1527
if (StringCmp (strandtype_strand[i].name, strand_name) == 0) {
1528
return strandtype_strand[i].strand;
1529
}
1530
}
1531
return -1;
1532
}
1533
1534
1535
NLM_EXTERN ValNodePtr GetStrandTypeList (void)
1536
{
1537
ValNodePtr list = NULL;
1538
Int4 i;
1539
1540
for (i = 0; i < NUM_strandtype_strand; i++) {
1541
ValNodeAddPointer (&list, strandtype_strand[i].strand_type, StringSave (strandtype_strand[i].name));
1542
}
1543
return list;
1544
}
1545
1546
1547
static CharPtr GetSequenceQualValName (ValNodePtr field)
1548
{
1549
CharPtr val = NULL;
1550
1551
if (field == NULL) return NULL;
1552
switch (field->choice) {
1553
case MolinfoField_molecule:
1554
val = BiomolNameFromBiomol (BiomolFromMoleculeType (field->data.intvalue));
1555
break;
1556
case MolinfoField_technique:
1557
val = TechNameFromTech (TechFromTechniqueType (field->data.intvalue));
1558
break;
1559
case MolinfoField_completedness:
1560
val = CompletenessNameFromCompleteness (CompletenessFromCompletednessType (field->data.intvalue));
1561
break;
1562
case MolinfoField_mol_class:
1563
val = MolNameFromMol (MolFromMoleculeClassType (field->data.intvalue));
1564
break;
1565
case MolinfoField_topology:
1566
val = TopologyNameFromTopology (TopologyFromTopologyType (field->data.intvalue));
1567
break;
1568
case MolinfoField_strand:
1569
val = StrandNameFromStrand (StrandFromStrandType (field->data.intvalue));
1570
break;
1571
}
1572
return val;
1573
}
1574
1575
1576
static CharPtr GetSequenceQualName (ValNodePtr field)
1577
{
1578
CharPtr str = NULL, fieldname = "invalid field", val = "invalid value";
1579
CharPtr fmt = "%s %s";
1580
1581
if (field == NULL) return NULL;
1582
switch (field->choice) {
1583
case MolinfoField_molecule:
1584
fieldname = "molecule";
1585
val = BiomolNameFromBiomol (BiomolFromMoleculeType (field->data.intvalue));
1586
break;
1587
case MolinfoField_technique:
1588
fieldname = "technique";
1589
val = TechNameFromTech (TechFromTechniqueType (field->data.intvalue));
1590
break;
1591
case MolinfoField_completedness:
1592
fieldname = "completeness";
1593
val = CompletenessNameFromCompleteness (CompletenessFromCompletednessType (field->data.intvalue));
1594
break;
1595
case MolinfoField_mol_class:
1596
fieldname = "class";
1597
val = MolNameFromMol (MolFromMoleculeClassType (field->data.intvalue));
1598
break;
1599
case MolinfoField_topology:
1600
fieldname = "topology";
1601
val = TopologyNameFromTopology (TopologyFromTopologyType (field->data.intvalue));
1602
break;
1603
case MolinfoField_strand:
1604
fieldname = "strand";
1605
val = StrandNameFromStrand (StrandFromStrandType (field->data.intvalue));
1606
break;
1607
}
1608
if (val == NULL) {
1609
val = "Invalid value";
1610
}
1611
str = (CharPtr) MemNew (sizeof (Char) * (StringLen (fmt) + StringLen (fieldname) + StringLen (val)));
1612
sprintf (str, fmt, fieldname, val);
1613
return str;
1614
}
1615
1616
1617
/* Simple constraints */
1618
static Boolean IsWholeWordMatch (CharPtr start, CharPtr found, Int4 match_len)
1619
{
1620
Boolean rval = TRUE;
1621
Char char_after;
1622
Char char_before;
1623
1624
if (match_len == 0)
1625
{
1626
rval = TRUE;
1627
}
1628
else if (start == NULL || found == NULL)
1629
{
1630
rval = FALSE;
1631
}
1632
else
1633
{
1634
char_after = *(found + match_len);
1635
if (found != start)
1636
{
1637
char_before = *(found - 1);
1638
if (isalpha ((Int4) char_before) || isdigit ((Int4) char_before))
1639
{
1640
rval = FALSE;
1641
}
1642
}
1643
if (char_after != 0 && (isalpha ((Int4) char_after) || isdigit ((Int4)char_after)))
1644
{
1645
rval = FALSE;
1646
}
1647
}
1648
return rval;
1649
}
1650
1651
1652
NLM_EXTERN Boolean IsStringConstraintEmpty (StringConstraintPtr scp)
1653
{
1654
if (scp == NULL || StringHasNoText (scp->match_text)) return TRUE;
1655
else return FALSE;
1656
}
1657
1658
1659
NLM_EXTERN Boolean DoesSingleStringMatchConstraint (CharPtr str, StringConstraintPtr scp)
1660
{
1661
CharPtr pFound;
1662
Boolean rval = FALSE;
1663
Char char_after = 0;
1664
1665
if (IsStringConstraintEmpty (scp)) return TRUE;
1666
if (StringHasNoText (str)) return FALSE;
1667
1668
switch (scp->match_location)
1669
{
1670
case String_location_contains:
1671
if (scp->case_sensitive)
1672
{
1673
pFound = StringSearch (str, scp->match_text);
1674
}
1675
else
1676
{
1677
pFound = StringISearch (str, scp->match_text);
1678
}
1679
if (pFound == NULL)
1680
{
1681
rval = FALSE;
1682
}
1683
else if (scp->whole_word)
1684
{
1685
rval = IsWholeWordMatch (str, pFound, StringLen (scp->match_text));
1686
while (!rval && pFound != NULL)
1687
{
1688
if (scp->case_sensitive)
1689
{
1690
pFound = StringSearch (pFound + 1, scp->match_text);
1691
}
1692
else
1693
{
1694
pFound = StringISearch (pFound + 1, scp->match_text);
1695
}
1696
if (pFound != NULL)
1697
{
1698
rval = IsWholeWordMatch (str, pFound, StringLen (scp->match_text));
1699
}
1700
}
1701
}
1702
else
1703
{
1704
rval = TRUE;
1705
}
1706
break;
1707
case String_location_starts:
1708
if (scp->case_sensitive)
1709
{
1710
pFound = StringSearch (str, scp->match_text);
1711
}
1712
else
1713
{
1714
pFound = StringISearch (str, scp->match_text);
1715
}
1716
if (pFound == str)
1717
{
1718
if (scp->whole_word)
1719
{
1720
rval = IsWholeWordMatch (str, pFound, StringLen (scp->match_text));
1721
}
1722
else
1723
{
1724
rval = TRUE;
1725
}
1726
}
1727
break;
1728
case String_location_ends:
1729
if (scp->case_sensitive)
1730
{
1731
pFound = StringSearch (str, scp->match_text);
1732
}
1733
else
1734
{
1735
pFound = StringISearch (str, scp->match_text);
1736
}
1737
while (pFound != NULL && !rval) {
1738
char_after = *(pFound + StringLen (scp->match_text));
1739
if (char_after == 0)
1740
{
1741
if (scp->whole_word)
1742
{
1743
rval = IsWholeWordMatch (str, pFound, StringLen (scp->match_text));
1744
}
1745
else
1746
{
1747
rval = TRUE;
1748
}
1749
/* stop the search, we're at the end of the string */
1750
pFound = NULL;
1751
}
1752
else
1753
{
1754
if (scp->case_sensitive)
1755
{
1756
pFound = StringSearch (pFound + 1, scp->match_text);
1757
}
1758
else
1759
{
1760
pFound = StringISearch (pFound + 1, scp->match_text);
1761
}
1762
}
1763
}
1764
break;
1765
case String_location_equals:
1766
if (scp->case_sensitive)
1767
{
1768
if (StringCmp (str, scp->match_text) == 0)
1769
{
1770
rval = TRUE;
1771
}
1772
}
1773
else
1774
{
1775
if (StringICmp (str, scp->match_text) == 0)
1776
{
1777
rval = TRUE;
1778
}
1779
}
1780
break;
1781
case String_location_inlist:
1782
if (scp->case_sensitive)
1783
{
1784
pFound = StringSearch (scp->match_text, str);
1785
}
1786
else
1787
{
1788
pFound = StringISearch (scp->match_text, str);
1789
}
1790
if (pFound == NULL)
1791
{
1792
rval = FALSE;
1793
}
1794
else
1795
{
1796
rval = IsWholeWordMatch (scp->match_text, pFound, StringLen (str));
1797
while (!rval && pFound != NULL)
1798
{
1799
if (scp->case_sensitive)
1800
{
1801
pFound = StringSearch (pFound + 1, str);
1802
}
1803
else
1804
{
1805
pFound = StringISearch (pFound + 1, str);
1806
}
1807
if (pFound != NULL)
1808
{
1809
rval = IsWholeWordMatch (scp->match_text, pFound, StringLen (str));
1810
}
1811
}
1812
}
1813
if (!rval) {
1814
/* look for spans */
1815
rval = IsStringInSpanInList (str, scp->match_text);
1816
}
1817
break;
1818
}
1819
return rval;
1820
}
1821
1822
1823
NLM_EXTERN Boolean DoesStringMatchConstraint (CharPtr str, StringConstraintPtr scp)
1824
{
1825
Boolean rval;
1826
1827
rval = DoesSingleStringMatchConstraint (str, scp);
1828
if (scp != NULL && scp->not_present) {
1829
rval = !rval;
1830
}
1831
return rval;
1832
}
1833
1834
1835
static Boolean DoesStringListMatchConstraint (ValNodePtr list, StringConstraintPtr scp)
1836
{
1837
Int4 len = 1;
1838
CharPtr tmp;
1839
Boolean rval = FALSE;
1840
ValNodePtr vnp;
1841
1842
if (IsStringConstraintEmpty (scp)) {
1843
return TRUE;
1844
}
1845
if (list == NULL) return FALSE;
1846
1847
for (vnp = list; vnp != NULL; vnp = vnp->next) {
1848
len += StringLen (vnp->data.ptrvalue) + 2;
1849
}
1850
1851
tmp = (CharPtr) MemNew (sizeof (Char) * len);
1852
for (vnp = list; vnp != NULL; vnp = vnp->next) {
1853
StringCat (tmp, vnp->data.ptrvalue);
1854
if (vnp->next != NULL) {
1855
StringCat (tmp, "; ");
1856
}
1857
}
1858
1859
rval = DoesStringMatchConstraint (tmp, scp);
1860
tmp = MemFree (tmp);
1861
return rval;
1862
}
1863
1864
1865
static Boolean DoesStrandMatchConstraint (SeqLocPtr slp, LocationConstraintPtr lcp)
1866
{
1867
Uint2 strand;
1868
Boolean rval = FALSE;
1869
1870
if (slp == NULL)
1871
{
1872
rval = FALSE;
1873
}
1874
else if (lcp == NULL || lcp->strand == Strand_constraint_any)
1875
{
1876
rval = TRUE;
1877
}
1878
else
1879
{
1880
strand = SeqLocStrand (slp);
1881
if (strand == Seq_strand_minus)
1882
{
1883
if (lcp->strand == Strand_constraint_minus)
1884
{
1885
rval = TRUE;
1886
}
1887
else
1888
{
1889
rval = FALSE;
1890
}
1891
}
1892
else
1893
{
1894
if (lcp->strand == Strand_constraint_plus)
1895
{
1896
rval = TRUE;
1897
}
1898
else
1899
{
1900
rval = FALSE;
1901
}
1902
}
1903
}
1904
return rval;
1905
}
1906
1907
1908
static Boolean DoesBioseqMatchSequenceType (BioseqPtr bsp, Uint2 seq_type)
1909
{
1910
Boolean rval = FALSE;
1911
1912
if (bsp == NULL) return FALSE;
1913
if (seq_type == Seqtype_constraint_any) return TRUE;
1914
1915
if (ISA_na (bsp->mol) && seq_type == Seqtype_constraint_nuc)
1916
{
1917
rval = TRUE;
1918
}
1919
else if (ISA_aa (bsp->mol) && seq_type == Seqtype_constraint_prot)
1920
{
1921
rval = TRUE;
1922
}
1923
return rval;
1924
}
1925
1926
1927
static Boolean DoesSequenceTypeMatchContraint (SeqLocPtr slp, LocationConstraintPtr lcp)
1928
{
1929
Boolean rval = FALSE;
1930
BioseqPtr bsp;
1931
1932
if (slp == NULL)
1933
{
1934
rval = FALSE;
1935
}
1936
else if (lcp == NULL || lcp->seq_type == Seqtype_constraint_any)
1937
{
1938
rval = TRUE;
1939
}
1940
else
1941
{
1942
bsp = BioseqFindFromSeqLoc (slp);
1943
rval = DoesBioseqMatchSequenceType (bsp, lcp->seq_type);
1944
}
1945
return rval;
1946
}
1947
1948
static Boolean DoesLocationMatchConstraint (SeqLocPtr slp, LocationConstraintPtr lcp)
1949
1950
{
1951
Boolean rval = FALSE;
1952
1953
if (slp == NULL)
1954
{
1955
rval = FALSE;
1956
}
1957
else if (lcp == NULL || (DoesStrandMatchConstraint (slp, lcp) && DoesSequenceTypeMatchContraint (slp, lcp)))
1958
{
1959
rval = TRUE;
1960
}
1961
return rval;
1962
}
1963
1964
1965
static Boolean DoesObjectMatchLocationConstraint (Uint1 choice, Pointer data, LocationConstraintPtr constraint)
1966
{
1967
SeqFeatPtr sfp;
1968
SeqDescrPtr sdp;
1969
CGPSetPtr cgp;
1970
BioseqPtr bsp = NULL;
1971
BioseqSetPtr bssp;
1972
ValNodePtr vnp;
1973
ObjValNodePtr ovp;
1974
SeqMgrFeatContext context;
1975
1976
if (data == NULL) return FALSE;
1977
1978
if (constraint == NULL
1979
|| (constraint->strand == Strand_constraint_any
1980
&& constraint->seq_type == Seqtype_constraint_any)) {
1981
return TRUE;
1982
}
1983
1984
if (choice == OBJ_SEQFEAT) {
1985
sfp = (SeqFeatPtr) data;
1986
bsp = BioseqFindFromSeqLoc (sfp->location);
1987
} else if (choice == OBJ_SEQDESC) {
1988
sdp = (SeqDescrPtr) data;
1989
if (sdp->extended != 0) {
1990
ovp = (ObjValNodePtr) sdp;
1991
if (ovp->idx.parenttype == OBJ_BIOSEQSET) {
1992
bssp = (BioseqSetPtr) ovp->idx.parentptr;
1993
if (bssp != NULL && bssp->seq_set != NULL && IS_Bioseq_set (bssp->seq_set)) {
1994
bsp = (BioseqPtr) bssp->seq_set->data.ptrvalue;
1995
}
1996
} else if (ovp->idx.parenttype == OBJ_BIOSEQ) {
1997
bsp = (BioseqPtr) ovp->idx.parentptr;
1998
}
1999
}
2000
} else if (choice == 0) {
2001
if (constraint->seq_type != Seqtype_constraint_any) {
2002
return FALSE;
2003
}
2004
cgp = (CGPSetPtr) data;
2005
if (cgp->cds_list != NULL && cgp->cds_list->data.ptrvalue != NULL) {
2006
sfp = (SeqFeatPtr) cgp->cds_list->data.ptrvalue;
2007
bsp = BioseqFindFromSeqLoc (sfp->location);
2008
} else if (cgp->gene_list != NULL && cgp->gene_list->data.ptrvalue != NULL) {
2009
sfp = (SeqFeatPtr) cgp->gene_list->data.ptrvalue;
2010
bsp = BioseqFindFromSeqLoc (sfp->location);
2011
} else if (cgp->mrna_list != NULL && cgp->mrna_list->data.ptrvalue != NULL) {
2012
sfp = (SeqFeatPtr) cgp->mrna_list->data.ptrvalue;
2013
bsp = BioseqFindFromSeqLoc (sfp->location);
2014
} else if (cgp->prot_list != NULL && cgp->prot_list->data.ptrvalue != NULL) {
2015
sfp = (SeqFeatPtr) cgp->prot_list->data.ptrvalue;
2016
bsp = BioseqFindFromSeqLoc (sfp->location);
2017
}
2018
}
2019
if (!DoesBioseqMatchSequenceType(bsp, constraint->seq_type)) {
2020
return FALSE;
2021
}
2022
if (constraint->strand != Strand_constraint_any && ISA_aa (bsp->mol)) {
2023
sfp = SeqMgrGetCDSgivenProduct (bsp, &context);
2024
if (constraint->strand == Strand_constraint_minus && context.strand != Seq_strand_minus) {
2025
return FALSE;
2026
}
2027
if (constraint->strand == Strand_constraint_plus && context.strand == Seq_strand_minus) {
2028
return FALSE;
2029
}
2030
} else if (constraint->strand != Strand_constraint_any) {
2031
if (choice == 0) {
2032
/* strand for CDS-Gene-Prot group */
2033
cgp = (CGPSetPtr) data;
2034
for (vnp = cgp->cds_list; vnp != NULL; vnp = vnp->next) {
2035
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
2036
if (sfp != NULL && !DoesStrandMatchConstraint (sfp->location, constraint)) {
2037
return FALSE;
2038
}
2039
}
2040
for (vnp = cgp->gene_list; vnp != NULL; vnp = vnp->next) {
2041
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
2042
if (sfp != NULL && !DoesStrandMatchConstraint (sfp->location, constraint)) {
2043
return FALSE;
2044
}
2045
}
2046
for (vnp = cgp->mrna_list; vnp != NULL; vnp = vnp->next) {
2047
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
2048
if (sfp != NULL && !DoesStrandMatchConstraint (sfp->location, constraint)) {
2049
return FALSE;
2050
}
2051
}
2052
} else if (choice == OBJ_SEQFEAT) {
2053
sfp = (SeqFeatPtr) data;
2054
if (!DoesStrandMatchConstraint (sfp->location, constraint)) {
2055
return FALSE;
2056
}
2057
} else {
2058
/* descriptors can't meet strand constraints */
2059
return FALSE;
2060
}
2061
}
2062
return TRUE;
2063
}
2064
2065
2066
/* for parsing and editing */
2067
static CharPtr GetTextPortionFromString (CharPtr str, TextPortionPtr text_portion)
2068
{
2069
CharPtr portion = NULL;
2070
CharPtr found_start, found_end;
2071
Int4 found_len;
2072
2073
if (StringHasNoText (str)) {
2074
return NULL;
2075
}
2076
if (text_portion == NULL) {
2077
return StringSave (str);
2078
}
2079
2080
if (text_portion->left_text == NULL || text_portion->left_text [0] == 0)
2081
{
2082
found_start = str;
2083
}
2084
else
2085
{
2086
if (text_portion->case_sensitive)
2087
{
2088
found_start = StringSearch (str, text_portion->left_text);
2089
}
2090
else
2091
{
2092
found_start = StringISearch (str, text_portion->left_text);
2093
}
2094
2095
if (text_portion->whole_word && ! IsWholeWordMatch (str, found_start, StringLen (text_portion->left_text)))
2096
{
2097
found_start = NULL;
2098
}
2099
}
2100
2101
if (found_start == NULL)
2102
{
2103
return NULL;
2104
}
2105
2106
if (!text_portion->include_left)
2107
{
2108
found_start += StringLen (text_portion->left_text);
2109
}
2110
2111
if (text_portion->right_text == NULL || text_portion->right_text [0] == 0)
2112
{
2113
found_len = StringLen (found_start);
2114
}
2115
else
2116
{
2117
if (text_portion->case_sensitive)
2118
{
2119
found_end = StringSearch (found_start, text_portion->right_text);
2120
}
2121
else
2122
{
2123
found_end = StringISearch (found_start, text_portion->right_text);
2124
}
2125
if (text_portion->whole_word && ! IsWholeWordMatch (str, found_end, StringLen (text_portion->right_text)))
2126
{
2127
found_end = NULL;
2128
}
2129
2130
if (found_end == NULL)
2131
{
2132
found_len = 0;
2133
}
2134
else if (text_portion->include_right)
2135
{
2136
found_len = (Int4)(found_end - found_start) + StringLen (text_portion->right_text);
2137
}
2138
else
2139
{
2140
found_len = found_end - found_start;
2141
}
2142
}
2143
2144
if (found_len > 0)
2145
{
2146
portion = (CharPtr) MemNew (sizeof (Char) * (found_len + 1));
2147
StringNCpy (portion, found_start, found_len);
2148
portion[found_len] = 0;
2149
}
2150
return portion;
2151
}
2152
2153
2154
2155
static CharPtr FindTextPortionLocationInString (CharPtr str, TextPortionPtr text_portion)
2156
{
2157
CharPtr start, stop;
2158
2159
if (str == NULL || text_portion == NULL) return FALSE;
2160
2161
if (text_portion->left_text != NULL) {
2162
start = StringSearch (str, text_portion->left_text);
2163
if (start != NULL) {
2164
if (!text_portion->include_left) {
2165
start += StringLen (text_portion->left_text);
2166
}
2167
}
2168
} else {
2169
start = str;
2170
}
2171
if (start != NULL) {
2172
if (text_portion->right_text != NULL) {
2173
stop = StringSearch (start, text_portion->right_text);
2174
if (stop == NULL) {
2175
start = NULL;
2176
}
2177
}
2178
}
2179
return start;
2180
}
2181
2182
2183
static void ReplaceStringForParse(CharPtr src_text, TextPortionPtr text_portion)
2184
{
2185
CharPtr src, dst;
2186
2187
if (src_text == NULL || text_portion == NULL) {
2188
return;
2189
}
2190
2191
dst = FindTextPortionLocationInString (src_text, text_portion);
2192
if (dst == NULL) return;
2193
if (text_portion->right_text == NULL) {
2194
*dst = 0;
2195
} else {
2196
src = StringSearch (src_text, text_portion->right_text);
2197
if (src != NULL) {
2198
if (text_portion->include_right) {
2199
src += StringLen (text_portion->right_text);
2200
}
2201
while (*src != 0) {
2202
*dst = *src;
2203
dst++;
2204
src++;
2205
}
2206
*dst = 0;
2207
}
2208
}
2209
}
2210
2211
2212
/* generic functions for getting string values */
2213
static Int4 GetDbtagStringLen (DbtagPtr db_tag)
2214
{
2215
Int4 len;
2216
2217
if (db_tag == NULL)
2218
{
2219
return 0;
2220
}
2221
2222
len = StringLen (db_tag->db) + 2;
2223
if (db_tag->tag != NULL)
2224
{
2225
if (db_tag->tag->str != NULL)
2226
{
2227
len += StringLen (db_tag->tag->str);
2228
}
2229
else
2230
{
2231
len += 10;
2232
}
2233
}
2234
return len;
2235
}
2236
2237
2238
static CharPtr GetDbtagString (DbtagPtr db_tag)
2239
{
2240
Int4 len;
2241
CharPtr str;
2242
2243
if (db_tag == NULL) {
2244
return NULL;
2245
}
2246
2247
len = GetDbtagStringLen (db_tag);
2248
if (len == 0) {
2249
return NULL;
2250
}
2251
2252
str = (CharPtr) MemNew (len * sizeof (Char));
2253
if (str != NULL) {
2254
StringCpy (str, db_tag->db);
2255
StringCat (str, ":");
2256
if (db_tag->tag != NULL) {
2257
if (db_tag->tag->str != NULL) {
2258
StringCat (str, db_tag->tag->str);
2259
} else {
2260
sprintf (str + StringLen (str), "%d", db_tag->tag->id);
2261
}
2262
}
2263
}
2264
return str;
2265
}
2266
2267
2268
/* generic functions for setting field values */
2269
static Boolean SetStringValue (CharPtr PNTR existing_val, CharPtr new_val, Uint2 existing_text)
2270
{
2271
Boolean rval = FALSE;
2272
Int4 len;
2273
CharPtr tmp;
2274
2275
if (existing_val == NULL) {
2276
return FALSE;
2277
}
2278
2279
if (StringHasNoText (*existing_val)) {
2280
*existing_val = MemFree (*existing_val);
2281
*existing_val = StringSave (new_val);
2282
rval = TRUE;
2283
} else {
2284
switch (existing_text) {
2285
case ExistingTextOption_replace_old :
2286
*existing_val = MemFree (*existing_val);
2287
*existing_val = StringSave (new_val);
2288
rval = TRUE;
2289
break;
2290
case ExistingTextOption_append_semi :
2291
len = StringLen (new_val) + StringLen (*existing_val) + 3;
2292
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2293
if (tmp != NULL) {
2294
sprintf (tmp, "%s; %s", *existing_val, new_val);
2295
MemFree (*existing_val);
2296
*existing_val = tmp;
2297
rval = TRUE;
2298
}
2299
break;
2300
case ExistingTextOption_append_space :
2301
len = StringLen (new_val) + StringLen (*existing_val) + 2;
2302
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2303
if (tmp != NULL) {
2304
sprintf (tmp, "%s %s", *existing_val, new_val);
2305
MemFree (*existing_val);
2306
*existing_val = tmp;
2307
rval = TRUE;
2308
}
2309
break;
2310
case ExistingTextOption_append_colon :
2311
len = StringLen (new_val) + StringLen (*existing_val) + 3;
2312
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2313
if (tmp != NULL) {
2314
sprintf (tmp, "%s: %s", *existing_val, new_val);
2315
MemFree (*existing_val);
2316
*existing_val = tmp;
2317
rval = TRUE;
2318
}
2319
break;
2320
case ExistingTextOption_append_none :
2321
len = StringLen (new_val) + StringLen (*existing_val) + 1;
2322
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2323
if (tmp != NULL) {
2324
sprintf (tmp, "%s%s", *existing_val, new_val);
2325
MemFree (*existing_val);
2326
*existing_val = tmp;
2327
rval = TRUE;
2328
}
2329
break;
2330
case ExistingTextOption_prefix_semi :
2331
len = StringLen (new_val) + StringLen (*existing_val) + 3;
2332
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2333
if (tmp != NULL) {
2334
sprintf (tmp, "%s; %s", new_val, *existing_val);
2335
MemFree (*existing_val);
2336
*existing_val = tmp;
2337
rval = TRUE;
2338
}
2339
break;
2340
case ExistingTextOption_prefix_space :
2341
len = StringLen (new_val) + StringLen (*existing_val) + 2;
2342
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2343
if (tmp != NULL) {
2344
sprintf (tmp, "%s %s", new_val, *existing_val);
2345
MemFree (*existing_val);
2346
*existing_val = tmp;
2347
rval = TRUE;
2348
}
2349
break;
2350
case ExistingTextOption_prefix_colon :
2351
len = StringLen (new_val) + StringLen (*existing_val) + 3;
2352
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2353
if (tmp != NULL) {
2354
sprintf (tmp, "%s: %s", new_val, *existing_val);
2355
MemFree (*existing_val);
2356
*existing_val = tmp;
2357
rval = TRUE;
2358
}
2359
break;
2360
case ExistingTextOption_prefix_none :
2361
len = StringLen (new_val) + StringLen (*existing_val) + 1;
2362
tmp = (CharPtr) MemNew (sizeof (Char) * len);
2363
if (tmp != NULL) {
2364
sprintf (tmp, "%s%s", new_val, *existing_val);
2365
MemFree (*existing_val);
2366
*existing_val = tmp;
2367
rval = TRUE;
2368
}
2369
break;
2370
case ExistingTextOption_leave_old :
2371
rval = FALSE;
2372
}
2373
}
2374
return rval;
2375
}
2376
2377
2378
static Boolean SetStringsInValNodeStringList (ValNodePtr PNTR list, StringConstraintPtr scp, CharPtr new_val, Uint2 existing_text)
2379
{
2380
ValNodePtr vnp;
2381
CharPtr cp;
2382
Boolean rval = FALSE;
2383
2384
if (list == NULL)
2385
{
2386
return FALSE;
2387
}
2388
2389
if (*list == NULL && (scp == NULL || StringHasNoText (scp->match_text))) {
2390
ValNodeAddPointer (list, 0, StringSave (new_val));
2391
rval = TRUE;
2392
} else if (existing_text == ExistingTextOption_append_semi) {
2393
if (DoesStringListMatchConstraint (*list, scp)) {
2394
ValNodeAddPointer (list, 0, StringSave (new_val));
2395
rval = TRUE;
2396
}
2397
} else if (existing_text == ExistingTextOption_prefix_semi) {
2398
if (DoesStringListMatchConstraint (*list, scp)) {
2399
vnp = ValNodeNew (NULL);
2400
vnp->data.ptrvalue = StringSave (new_val);
2401
vnp->next = *list;
2402
*list = vnp;
2403
rval = TRUE;
2404
}
2405
} else if (existing_text == ExistingTextOption_replace_old) {
2406
if (DoesStringListMatchConstraint (*list, scp)) {
2407
*list = ValNodeFreeData (*list);
2408
vnp = ValNodeNew (NULL);
2409
vnp->data.ptrvalue = StringSave (new_val);
2410
*list = vnp;
2411
rval = TRUE;
2412
}
2413
} else if (existing_text == ExistingTextOption_leave_old) {
2414
rval = FALSE;
2415
} else {
2416
for (vnp = *list; vnp != NULL; vnp = vnp->next)
2417
{
2418
cp = (CharPtr) vnp->data.ptrvalue;
2419
if (DoesStringMatchConstraint (cp, scp)) {
2420
rval |= SetStringValue (&cp, new_val, existing_text);
2421
vnp->data.ptrvalue = cp;
2422
}
2423
}
2424
}
2425
return rval;
2426
}
2427
2428
2429
static Boolean SetStringInGBQualList (GBQualPtr PNTR list, ValNodePtr field, StringConstraintPtr scp, CharPtr new_val, Uint2 existing_text)
2430
{
2431
Boolean rval = FALSE;
2432
Int4 gbqual;
2433
CharPtr qual_name = NULL;
2434
GBQualPtr gbq, last_gbq = NULL;
2435
2436
if (field == NULL) return FALSE;
2437
2438
if (field->choice == FeatQualChoice_legal_qual)
2439
{
2440
gbqual = GetGBQualFromFeatQual (field->data.intvalue);
2441
if (gbqual > -1) {
2442
qual_name = ParFlat_GBQual_names [gbqual].name;
2443
for (gbq = *list; gbq != NULL; gbq = gbq->next) {
2444
if (StringCmp (gbq->qual, qual_name) == 0
2445
&& DoesStringMatchConstraint (gbq->val, scp)) {
2446
rval |= SetStringValue (&(gbq->val), new_val, existing_text);
2447
}
2448
last_gbq = gbq;
2449
}
2450
if (!rval && (scp == NULL || scp->match_text == NULL)) {
2451
gbq = GBQualNew ();
2452
gbq->qual = StringSave (qual_name);
2453
gbq->val = StringSave (new_val);
2454
if (last_gbq == NULL) {
2455
*list = gbq;
2456
} else {
2457
last_gbq->next = gbq;
2458
}
2459
rval = TRUE;
2460
}
2461
}
2462
} else if (field->choice == FeatQualChoice_illegal_qual) {
2463
for (gbq = *list; gbq != NULL; gbq = gbq->next) {
2464
if (DoesStringMatchConstraint (gbq->qual, field->data.ptrvalue)
2465
&& DoesStringMatchConstraint (gbq->val, scp)) {
2466
rval |= SetStringValue (&(gbq->val), new_val, existing_text);
2467
}
2468
}
2469
}
2470
2471
return rval;
2472
}
2473
2474
2475
static Boolean IsAllDigits (CharPtr str)
2476
{
2477
CharPtr cp;
2478
2479
if (StringHasNoText (str)) return FALSE;
2480
2481
cp = str;
2482
while (*cp != 0 && isdigit (*cp)) {
2483
cp++;
2484
}
2485
if (*cp == 0) {
2486
return TRUE;
2487
} else {
2488
return FALSE;
2489
}
2490
}
2491
2492
2493
static Boolean SetObjectIdString (ObjectIdPtr oip, CharPtr value, Uint2 existing_text)
2494
{
2495
Boolean rval = FALSE;
2496
Char num[15];
2497
CharPtr tmp = NULL;
2498
2499
if (oip == NULL) {
2500
return FALSE;
2501
}
2502
2503
if (oip->id > 0) {
2504
sprintf (num, "%d", oip->id);
2505
tmp = StringSave (num);
2506
} else {
2507
tmp = StringSaveNoNull (oip->str);
2508
}
2509
if (SetStringValue (&tmp, value, existing_text)) {
2510
oip->str = MemFree (oip->str);
2511
oip->id = 0;
2512
if (IsAllDigits (tmp)) {
2513
oip->id = atoi (tmp);
2514
} else {
2515
oip->str = tmp;
2516
tmp = NULL;
2517
}
2518
rval = TRUE;
2519
}
2520
tmp = MemFree (tmp);
2521
return rval;
2522
}
2523
2524
2525
static Boolean SetDbtagString (DbtagPtr db_tag, CharPtr value, Uint2 existing_text)
2526
{
2527
Boolean rval = FALSE;
2528
CharPtr cp;
2529
Int4 dbxvalid;
2530
CharPtr tmp;
2531
CharPtr twoval;
2532
2533
if (db_tag == NULL || StringHasNoText (value)) {
2534
return FALSE;
2535
}
2536
2537
cp = StringChr (value, ':');
2538
if (cp == NULL) {
2539
tmp = StringSave (db_tag->db);
2540
if (SetStringValue (&tmp, value, existing_text)) {
2541
dbxvalid = IsDbxrefValid (tmp, NULL, NULL, TRUE, NULL);
2542
if (dbxvalid != 0) {
2543
db_tag->db = MemFree (db_tag->db);
2544
db_tag->db = tmp;
2545
tmp = NULL;
2546
rval = TRUE;
2547
}
2548
}
2549
if (!rval) {
2550
if (db_tag->tag == NULL) {
2551
db_tag->tag = ObjectIdNew();
2552
}
2553
rval = SetObjectIdString (db_tag->tag, value, existing_text);
2554
}
2555
tmp = MemFree (tmp);
2556
} else {
2557
twoval = StringSave (value);
2558
cp = StringChr (twoval, ':');
2559
*cp = 0;
2560
cp++;
2561
rval = SetStringValue (&(db_tag->db), twoval, existing_text);
2562
if (db_tag->tag == NULL) {
2563
db_tag->tag = ObjectIdNew ();
2564
}
2565
rval |= SetObjectIdString (db_tag->tag, cp, existing_text);
2566
twoval = MemFree (twoval);
2567
}
2568
return rval;
2569
}
2570
2571
2572
static Boolean SetDbxrefString (SeqFeatPtr sfp, StringConstraintPtr scp, CharPtr value, Uint2 existing_text)
2573
{
2574
ValNodePtr vnp;
2575
Boolean rval = FALSE, skip;
2576
DbtagPtr dbtag;
2577
CharPtr cp;
2578
2579
if (sfp == NULL) {
2580
return FALSE;
2581
}
2582
2583
if ((sfp->dbxref == NULL || existing_text == ExistingTextOption_append_semi) && (scp == NULL || StringHasNoText (scp->match_text))) {
2584
dbtag = DbtagNew ();
2585
rval = SetDbtagString (dbtag, value, existing_text);
2586
if (rval) {
2587
ValNodeAddPointer (&(sfp->dbxref), 0, dbtag);
2588
} else {
2589
dbtag = DbtagFree (dbtag);
2590
}
2591
} else {
2592
for (vnp = sfp->dbxref; vnp != NULL; vnp = vnp->next) {
2593
skip = FALSE;
2594
if (scp != NULL) {
2595
cp = GetDbtagString (vnp->data.ptrvalue);
2596
if (!DoesStringMatchConstraint (cp, scp)) {
2597
skip = TRUE;
2598
}
2599
cp = MemFree (cp);
2600
}
2601
if (!skip) {
2602
rval |= SetDbtagString (vnp->data.ptrvalue, value, existing_text);
2603
}
2604
}
2605
}
2606
return rval;
2607
}
2608
2609
2610
2611
static CharPtr GetFirstValNodeStringMatch (ValNodePtr vnp, StringConstraintPtr scp)
2612
{
2613
CharPtr str = NULL;
2614
while (vnp != NULL && str == NULL) {
2615
if (!StringHasNoText (vnp->data.ptrvalue)
2616
&& DoesStringMatchConstraint (vnp->data.ptrvalue, scp)) {
2617
str = StringSave (vnp->data.ptrvalue);
2618
}
2619
vnp = vnp->next;
2620
}
2621
return str;
2622
}
2623
2624
2625
static Boolean RemoveValNodeStringMatch (ValNodePtr PNTR list, StringConstraintPtr scp)
2626
{
2627
ValNodePtr vnp_prev = NULL, vnp_next, vnp;
2628
Boolean rval = FALSE;
2629
2630
if (list == NULL) return FALSE;
2631
vnp = *list;
2632
while (vnp != NULL) {
2633
vnp_next = vnp->next;
2634
if (!StringHasNoText (vnp->data.ptrvalue)
2635
&& DoesStringMatchConstraint (vnp->data.ptrvalue, scp)) {
2636
if (vnp_prev == NULL) {
2637
*list = vnp->next;
2638
} else {
2639
vnp_prev->next = vnp->next;
2640
}
2641
vnp->next = NULL;
2642
vnp = ValNodeFreeData (vnp);
2643
rval = TRUE;
2644
} else {
2645
vnp_prev = vnp;
2646
}
2647
vnp = vnp_next;
2648
}
2649
return rval;
2650
}
2651
2652
2653
static CharPtr GetFirstGBQualMatch (GBQualPtr qual, CharPtr qual_name, StringConstraintPtr scp)
2654
{
2655
CharPtr str = NULL;
2656
while (qual != NULL && str == NULL) {
2657
if (StringICmp (qual->qual, qual_name) == 0
2658
&&!StringHasNoText (qual->val)
2659
&& DoesStringMatchConstraint (qual->val, scp)) {
2660
str = StringSave (qual->val);
2661
}
2662
qual = qual->next;
2663
}
2664
return str;
2665
}
2666
2667
2668
static CharPtr GetFirstGBQualMatchConstraintName (GBQualPtr qual, StringConstraintPtr qual_name, StringConstraintPtr scp)
2669
{
2670
CharPtr str = NULL;
2671
while (qual != NULL && str == NULL) {
2672
if (DoesStringMatchConstraint (qual->qual, qual_name)
2673
&&!StringHasNoText (qual->val)
2674
&& DoesStringMatchConstraint (qual->val, scp)) {
2675
str = StringSave (qual->val);
2676
}
2677
qual = qual->next;
2678
}
2679
return str;
2680
}
2681
2682
2683
static Boolean RemoveGBQualMatch (GBQualPtr PNTR list, CharPtr qual_name, StringConstraintPtr scp)
2684
{
2685
GBQualPtr qual_prev = NULL, qual_next, qual;
2686
Boolean rval = FALSE;
2687
2688
if (list == NULL) return FALSE;
2689
qual = *list;
2690
while (qual != NULL) {
2691
qual_next = qual->next;
2692
if (StringICmp (qual->qual, qual_name) == 0
2693
&& !StringHasNoText (qual->val)
2694
&& DoesStringMatchConstraint (qual->val, scp)) {
2695
if (qual_prev == NULL) {
2696
*list = qual->next;
2697
} else {
2698
qual_prev->next = qual->next;
2699
}
2700
qual->next = NULL;
2701
qual = GBQualFree (qual);
2702
rval = TRUE;
2703
} else {
2704
qual_prev = qual;
2705
}
2706
qual = qual_next;
2707
}
2708
return rval;
2709
}
2710
2711
2712
static Boolean RemoveGBQualMatchConstraintName (GBQualPtr PNTR list, StringConstraintPtr qual_name, StringConstraintPtr scp)
2713
{
2714
GBQualPtr qual_prev = NULL, qual_next, qual;
2715
Boolean rval = FALSE;
2716
2717
if (list == NULL) return FALSE;
2718
qual = *list;
2719
while (qual != NULL) {
2720
qual_next = qual->next;
2721
if (DoesStringMatchConstraint (qual->qual, qual_name)
2722
&& !StringHasNoText (qual->val)
2723
&& DoesStringMatchConstraint (qual->val, scp)) {
2724
if (qual_prev == NULL) {
2725
*list = qual->next;
2726
} else {
2727
qual_prev->next = qual->next;
2728
}
2729
qual->next = NULL;
2730
qual = GBQualFree (qual);
2731
rval = TRUE;
2732
} else {
2733
qual_prev = qual;
2734
}
2735
qual = qual_next;
2736
}
2737
return rval;
2738
}
2739
2740
2741
static CharPtr GetDbxrefString (SeqFeatPtr sfp, StringConstraintPtr scp)
2742
{
2743
ValNodePtr vnp;
2744
Int4 len = 0;
2745
CharPtr str = NULL, cp;
2746
2747
if (sfp == NULL || sfp->dbxref == NULL) {
2748
return NULL;
2749
}
2750
2751
for (vnp = sfp->dbxref; vnp != NULL; vnp = vnp->next) {
2752
cp = GetDbtagString (vnp->data.ptrvalue);
2753
if (cp != NULL && DoesStringMatchConstraint(cp, scp)) {
2754
len += StringLen (cp) + 1;
2755
}
2756
cp = MemFree (cp);
2757
}
2758
2759
if (len == 0) {
2760
return NULL;
2761
}
2762
2763
str = (CharPtr) MemNew ((len + 1) * sizeof (Char));
2764
if (str != NULL) {
2765
for (vnp = sfp->dbxref; vnp != NULL; vnp = vnp->next) {
2766
cp = GetDbtagString (vnp->data.ptrvalue);
2767
if (cp != NULL && DoesStringMatchConstraint(cp, scp)) {
2768
StringCat (str, cp);
2769
StringCat (str, ";");
2770
}
2771
cp = MemFree (cp);
2772
}
2773
}
2774
if (StringLen (str) >1) {
2775
/* remove final semicolon */
2776
str [StringLen (str) - 2] = 0;
2777
}
2778
return str;
2779
}
2780
2781
2782
static Boolean RemoveDbxrefString (SeqFeatPtr sfp, StringConstraintPtr scp)
2783
{
2784
ValNodePtr vnp, vnp_prev = NULL, vnp_next;
2785
CharPtr cp;
2786
Boolean rval = FALSE;
2787
2788
if (sfp == NULL || sfp->dbxref == NULL) {
2789
return FALSE;
2790
}
2791
2792
vnp = sfp->dbxref;
2793
while (vnp != NULL) {
2794
vnp_next = vnp->next;
2795
cp = GetDbtagString (vnp->data.ptrvalue);
2796
if (DoesStringMatchConstraint(cp, scp)) {
2797
if (vnp_prev == NULL) {
2798
sfp->dbxref = vnp->next;
2799
} else {
2800
vnp_prev->next = vnp->next;
2801
}
2802
vnp->next = NULL;
2803
vnp->data.ptrvalue = DbtagFree (vnp->data.ptrvalue);
2804
vnp = ValNodeFree (vnp);
2805
rval = TRUE;
2806
} else {
2807
vnp_prev = vnp;
2808
}
2809
}
2810
return rval;
2811
}
2812
2813
2814
static CharPtr GetRNAProductString (SeqFeatPtr sfp, StringConstraintPtr scp)
2815
{
2816
RnaRefPtr rrp;
2817
SeqMgrFeatContext context;
2818
CharPtr str = NULL;
2819
2820
if (sfp == NULL || sfp->data.choice != SEQFEAT_RNA || sfp->data.value.ptrvalue == NULL) {
2821
return NULL;
2822
}
2823
2824
rrp = sfp->data.value.ptrvalue;
2825
if (rrp->ext.choice == 0
2826
|| (rrp->ext.choice == 1 && StringHasNoText (rrp->ext.value.ptrvalue))
2827
|| (rrp->ext.choice == 1
2828
&& (StringCmp (rrp->ext.value.ptrvalue, "ncRNA") == 0
2829
|| StringCmp (rrp->ext.value.ptrvalue, "tmRNA") == 0
2830
|| StringCmp (rrp->ext.value.ptrvalue, "misc_RNA") == 0))) {
2831
str = GetFirstGBQualMatch (sfp->qual, "product", scp);
2832
}
2833
2834
if (str == NULL) {
2835
if (rrp->ext.choice == 1 && !StringHasNoText (rrp->ext.value.ptrvalue)
2836
&& StringCmp (rrp->ext.value.ptrvalue, "ncRNA") != 0
2837
&& StringCmp (rrp->ext.value.ptrvalue, "tmRNA") != 0
2838
&& StringCmp (rrp->ext.value.ptrvalue, "misc_RNA") != 0) {
2839
str = StringSave (rrp->ext.value.ptrvalue);
2840
} else if (rrp->ext.choice == 2 && rrp->ext.value.ptrvalue != NULL) {
2841
if (SeqMgrGetDesiredFeature (sfp->idx.entityID, NULL, 0, 0, sfp, &context) != NULL
2842
&& !StringHasNoText (context.label)
2843
&& StringCmp (context.label, "tRNA") != 0) {
2844
str = (CharPtr) MemNew (sizeof (Char) + (StringLen (context.label) + 6));
2845
sprintf (str, "tRNA-%s", context.label);
2846
}
2847
}
2848
if (!DoesStringMatchConstraint(str, scp)) {
2849
str = MemFree (str);
2850
}
2851
}
2852
return str;
2853
}
2854
2855
2856
static Boolean IsParseabletRNAName (CharPtr name_string)
2857
{
2858
if (StringHasNoText(name_string))
2859
{
2860
return TRUE;
2861
}
2862
else if (StringNICmp (name_string, "trna-", 5) != 0)
2863
{
2864
return FALSE;
2865
}
2866
else if (StringLen (name_string) != 8)
2867
{
2868
return FALSE;
2869
}
2870
else if (ParseTRnaString (name_string, NULL, NULL, TRUE) == 0)
2871
{
2872
return FALSE;
2873
}
2874
else
2875
{
2876
return TRUE;
2877
}
2878
}
2879
2880
2881
static Boolean SetRNAProductString (SeqFeatPtr sfp, StringConstraintPtr scp, CharPtr new_val, Uint2 existing_text)
2882
{
2883
RnaRefPtr rrp;
2884
Boolean rval = FALSE;
2885
ValNode vn;
2886
CharPtr cp, tmp;
2887
tRNAPtr trp;
2888
Boolean justTrnaText = FALSE;
2889
Uint1 codon [6];
2890
2891
if (sfp == NULL || sfp->data.choice != SEQFEAT_RNA || sfp->data.value.ptrvalue == NULL) {
2892
return FALSE;
2893
}
2894
2895
rrp = sfp->data.value.ptrvalue;
2896
if (rrp->ext.choice == 0
2897
|| (rrp->ext.choice == 1 && StringHasNoText (rrp->ext.value.ptrvalue))
2898
|| (rrp->ext.choice == 1
2899
&& (StringCmp (rrp->ext.value.ptrvalue, "ncRNA") == 0
2900
|| StringCmp (rrp->ext.value.ptrvalue, "tmRNA") == 0
2901
|| StringCmp (rrp->ext.value.ptrvalue, "misc_RNA") == 0))) {
2902
vn.choice = FeatQualChoice_legal_qual;
2903
vn.data.intvalue = Feat_qual_legal_product;
2904
2905
rval = SetStringInGBQualList (&(sfp->qual), &vn, scp, new_val, existing_text);
2906
}
2907
2908
if (!rval) {
2909
if ((rrp->ext.choice == 0 || (rrp->ext.choice == 1 && StringHasNoText (rrp->ext.value.ptrvalue)))
2910
&& (scp == NULL || scp->match_text == NULL)) {
2911
rrp->ext.value.ptrvalue = MemFree (rrp->ext.value.ptrvalue);
2912
rrp->ext.value.ptrvalue = StringSave (new_val);
2913
rrp->ext.choice = 1;
2914
rval = TRUE;
2915
} else if (rrp->ext.choice == 1
2916
&& StringCmp (rrp->ext.value.ptrvalue, "ncRNA") != 0
2917
&& StringCmp (rrp->ext.value.ptrvalue, "tmRNA") != 0
2918
&& StringCmp (rrp->ext.value.ptrvalue, "misc_RNA") != 0
2919
&& DoesStringMatchConstraint (rrp->ext.value.ptrvalue, scp)) {
2920
cp = rrp->ext.value.ptrvalue;
2921
rval = SetStringValue (&cp, new_val, existing_text);
2922
rrp->ext.value.ptrvalue = cp;
2923
rval = TRUE;
2924
} else if (rrp->ext.choice == 2) {
2925
tmp = GetRNAProductString (sfp, NULL);
2926
if (DoesStringMatchConstraint (tmp, scp)
2927
&& SetStringValue (&tmp, new_val, existing_text)) {
2928
trp = (tRNAPtr) rrp->ext.value.ptrvalue;
2929
if (trp == NULL) {
2930
trp = MemNew (sizeof (tRNA));
2931
trp->aatype = 0;
2932
MemSet (trp->codon, 255, sizeof (trp->codon));
2933
trp->anticodon = NULL;
2934
rrp->ext.value.ptrvalue = trp;
2935
}
2936
2937
if (!IsParseabletRNAName(tmp))
2938
{
2939
if (trp->anticodon == NULL
2940
&& trp->codon[0] == 255
2941
&& trp->codon[1] == 255
2942
&& trp->codon[2] == 255
2943
&& trp->codon[3] == 255
2944
&& trp->codon[4] == 255
2945
&& trp->codon[5] == 255)
2946
{
2947
trp = MemFree (trp);
2948
rrp->ext.choice = 1;
2949
rrp->ext.value.ptrvalue = tmp;
2950
tmp = NULL;
2951
rval = TRUE;
2952
}
2953
else
2954
{
2955
vn.choice = FeatQualChoice_legal_qual;
2956
vn.data.intvalue = Feat_qual_legal_product;
2957
if (SetStringInGBQualList (&(sfp->qual), &vn, scp, new_val, existing_text)) {
2958
trp->aa = 0;
2959
rval = TRUE;
2960
}
2961
}
2962
}
2963
else
2964
{
2965
trp->aa = ParseTRnaString (tmp, &justTrnaText, codon, TRUE);
2966
trp->aatype = 2;
2967
rval = TRUE;
2968
}
2969
tmp = MemFree (tmp);
2970
}
2971
}
2972
}
2973
return rval;
2974
}
2975
2976
2977
static Boolean RemoveRNAProductString (SeqFeatPtr sfp, StringConstraintPtr scp)
2978
{
2979
RnaRefPtr rrp;
2980
Boolean rval = FALSE;
2981
2982
if (sfp == NULL || sfp->data.choice != SEQFEAT_RNA || sfp->data.value.ptrvalue == NULL) {
2983
return FALSE;
2984
}
2985
2986
rrp = sfp->data.value.ptrvalue;
2987
if (rrp->ext.choice == 0
2988
|| (rrp->ext.choice == 1 && StringHasNoText (rrp->ext.value.ptrvalue))
2989
|| (rrp->ext.choice == 1
2990
&& (StringCmp (rrp->ext.value.ptrvalue, "ncRNA") == 0
2991
|| StringCmp (rrp->ext.value.ptrvalue, "tmRNA") == 0
2992
|| StringCmp (rrp->ext.value.ptrvalue, "misc_RNA") == 0))) {
2993
rval = RemoveGBQualMatch (&(sfp->qual), "product", scp);
2994
}
2995
2996
if (!rval
2997
&& rrp->ext.choice == 1 && !StringHasNoText (rrp->ext.value.ptrvalue)
2998
&& StringCmp (rrp->ext.value.ptrvalue, "ncRNA") != 0
2999
&& StringCmp (rrp->ext.value.ptrvalue, "tmRNA") != 0
3000
&& StringCmp (rrp->ext.value.ptrvalue, "misc_RNA") != 0
3001
&& DoesStringMatchConstraint(rrp->ext.value.ptrvalue, scp)) {
3002
rrp->ext.value.ptrvalue = MemFree (rrp->ext.value.ptrvalue);
3003
rrp->ext.choice = 0;
3004
rval = TRUE;
3005
}
3006
return rval;
3007
}
3008
3009
3010
static SeqFeatPtr GetProtFeature (BioseqPtr protbsp)
3011
{
3012
SeqMgrFeatContext fcontext;
3013
SeqAnnotPtr sap;
3014
SeqFeatPtr prot_sfp;
3015
ProtRefPtr prp;
3016
3017
if (protbsp == NULL) return NULL;
3018
3019
prot_sfp = SeqMgrGetNextFeature (protbsp, NULL, 0, FEATDEF_PROT, &fcontext);
3020
if (prot_sfp == NULL) {
3021
sap = protbsp->annot;
3022
while (sap != NULL && prot_sfp == NULL) {
3023
if (sap->type == 1) {
3024
prot_sfp = sap->data;
3025
while (prot_sfp != NULL
3026
&& (prot_sfp->data.choice != SEQFEAT_PROT
3027
|| (prp = prot_sfp->data.value.ptrvalue) == NULL
3028
|| prp->processed != 0)) {
3029
prot_sfp = prot_sfp->next;
3030
}
3031
}
3032
sap = sap->next;
3033
}
3034
}
3035
return prot_sfp;
3036
}
3037
3038
3039
static ProtRefPtr GetProtRefForFeature (SeqFeatPtr sfp)
3040
{
3041
BioseqPtr protbsp;
3042
SeqFeatPtr protsfp;
3043
ProtRefPtr prp = NULL;
3044
SeqFeatXrefPtr xref;
3045
3046
if (sfp == NULL) return NULL;
3047
3048
if (sfp->data.choice == SEQFEAT_PROT) {
3049
prp = (ProtRefPtr) sfp->data.value.ptrvalue;
3050
} else if (sfp->data.choice == SEQFEAT_CDREGION) {
3051
xref = sfp->xref;
3052
while (xref != NULL && xref->data.choice != SEQFEAT_PROT) {
3053
xref = xref->next;
3054
}
3055
if (xref != NULL) {
3056
prp = xref->data.value.ptrvalue;
3057
}
3058
if (prp == NULL && sfp->product != NULL) {
3059
protbsp = BioseqFindFromSeqLoc (sfp->product);
3060
protsfp = GetProtFeature (protbsp);
3061
if (protsfp != NULL) {
3062
prp = protsfp->data.value.ptrvalue;
3063
}
3064
}
3065
}
3066
return prp;
3067
}
3068
3069
3070
NLM_EXTERN CharPtr GetQualFromFeature (SeqFeatPtr sfp, FeatureFieldPtr field, StringConstraintPtr scp)
3071
{
3072
CharPtr str = NULL;
3073
GeneRefPtr grp = NULL;
3074
ProtRefPtr prp = NULL;
3075
Int4 gbqual;
3076
3077
if (sfp == NULL || field == NULL || field->field == NULL)
3078
{
3079
return NULL;
3080
}
3081
if (field->type != Feature_type_any && sfp->idx.subtype != GetFeatdefFromFeatureType (field->type))
3082
{
3083
return NULL;
3084
}
3085
3086
// for gene fields
3087
if (sfp->idx.subtype == FEATDEF_GENE) {
3088
grp = sfp->data.value.ptrvalue;
3089
} else {
3090
grp = SeqMgrGetGeneXref (sfp);
3091
}
3092
3093
// for protein fields
3094
prp = GetProtRefForFeature (sfp);
3095
3096
/* fields common to all features */
3097
/* note, also known as comment */
3098
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_note)
3099
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("note", field->field->data.ptrvalue)))
3100
{
3101
if (!StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
3102
{
3103
str = StringSave (sfp->comment);
3104
}
3105
}
3106
/* db-xref */
3107
if (str == NULL
3108
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_db_xref)
3109
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("db_xref", field->field->data.ptrvalue))))
3110
{
3111
str = GetDbxrefString (sfp, scp);
3112
}
3113
/* exception */
3114
if (str == NULL
3115
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_exception)
3116
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("exception", field->field->data.ptrvalue))))
3117
{
3118
if (!StringHasNoText (sfp->except_text) && DoesStringMatchConstraint(sfp->except_text, scp))
3119
{
3120
str = StringSave (sfp->except_text);
3121
}
3122
}
3123
/* evidence */
3124
if (str == NULL
3125
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_evidence)
3126
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("evidence", field->field->data.ptrvalue))))
3127
{
3128
if (sfp->exp_ev == 1)
3129
{
3130
str = StringSave ("experimental");
3131
}
3132
else if (sfp->exp_ev == 2)
3133
{
3134
str = StringSave ("non-experimental");
3135
}
3136
if (!DoesStringMatchConstraint(str, scp)) {
3137
str = MemFree (str);
3138
}
3139
}
3140
3141
/* fields common to some features */
3142
/* product */
3143
if (str == NULL
3144
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_product)
3145
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("product", field->field->data.ptrvalue))))
3146
{
3147
if (prp != NULL) {
3148
str = GetFirstValNodeStringMatch (prp->name, scp);
3149
} else if (sfp->data.choice == SEQFEAT_RNA) {
3150
str = GetRNAProductString (sfp, scp);
3151
}
3152
}
3153
3154
/* Gene fields */
3155
/* locus */
3156
if (str == NULL
3157
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_gene)
3158
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("locus", field->field->data.ptrvalue)))
3159
&& grp != NULL)
3160
{
3161
if (!StringHasNoText (grp->locus) && DoesStringMatchConstraint(grp->locus, scp))
3162
{
3163
str = StringSave (grp->locus);
3164
}
3165
}
3166
/* description */
3167
if (str == NULL
3168
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_gene_description)
3169
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("description", field->field->data.ptrvalue)))
3170
&& grp != NULL)
3171
{
3172
if (!StringHasNoText (grp->desc) && DoesStringMatchConstraint(grp->desc, scp))
3173
{
3174
str = StringSave (grp->desc);
3175
}
3176
}
3177
/* maploc */
3178
if (str == NULL
3179
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_map)
3180
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("map", field->field->data.ptrvalue)))
3181
&& grp != NULL)
3182
{
3183
if (!StringHasNoText (grp->maploc) && DoesStringMatchConstraint(grp->maploc, scp))
3184
{
3185
str = StringSave (grp->maploc);
3186
}
3187
}
3188
/* allele */
3189
if (str == NULL
3190
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_allele)
3191
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("allele", field->field->data.ptrvalue)))
3192
&& grp != NULL)
3193
{
3194
if (!StringHasNoText (grp->allele) && DoesStringMatchConstraint(grp->allele, scp))
3195
{
3196
str = StringSave (grp->allele);
3197
}
3198
}
3199
/* locus_tag */
3200
if (str == NULL
3201
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_locus_tag)
3202
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("locus_tag", field->field->data.ptrvalue)))
3203
&& grp != NULL)
3204
{
3205
if (!StringHasNoText (grp->locus_tag) && DoesStringMatchConstraint(grp->locus_tag, scp))
3206
{
3207
str = StringSave (grp->locus_tag);
3208
}
3209
}
3210
/* synonym */
3211
if (str == NULL
3212
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_synonym)
3213
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("synonym", field->field->data.ptrvalue)))
3214
&& grp != NULL)
3215
{
3216
str = GetFirstValNodeStringMatch (grp->syn, scp);
3217
}
3218
3219
3220
/* protein fields */
3221
/* note - product handled above */
3222
/* description */
3223
if (str == NULL
3224
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_description)
3225
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("description", field->field->data.ptrvalue)))
3226
&& prp != NULL)
3227
{
3228
if (!StringHasNoText (prp->desc) && DoesStringMatchConstraint(prp->desc, scp)) {
3229
str = StringSave (prp->desc);
3230
}
3231
}
3232
/* ec_number */
3233
if (str == NULL
3234
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_ec_number)
3235
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("ec_number", field->field->data.ptrvalue)))
3236
&& prp != NULL)
3237
{
3238
str = GetFirstValNodeStringMatch (prp->ec, scp);
3239
}
3240
/* activity */
3241
if (str == NULL
3242
&& ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_activity)
3243
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("activity", field->field->data.ptrvalue)))
3244
&& prp != NULL)
3245
{
3246
str = GetFirstValNodeStringMatch (prp->activity, scp);
3247
}
3248
3249
3250
/* actual GenBank qualifiers */
3251
if (str == NULL)
3252
{
3253
if (field->field->choice == FeatQualChoice_legal_qual)
3254
{
3255
gbqual = GetGBQualFromFeatQual (field->field->data.intvalue);
3256
if (gbqual > -1) {
3257
str = GetFirstGBQualMatch (sfp->qual, ParFlat_GBQual_names [gbqual].name, scp);
3258
} else {
3259
/* need to do something with non-qualifier qualifiers */
3260
}
3261
} else {
3262
str = GetFirstGBQualMatchConstraintName (sfp->qual, field->field->data.ptrvalue, scp);
3263
}
3264
}
3265
return str;
3266
}
3267
3268
3269
static Boolean RemoveQualFromFeature (SeqFeatPtr sfp, FeatureFieldPtr field, StringConstraintPtr scp)
3270
{
3271
Boolean rval = FALSE;
3272
GeneRefPtr grp = NULL;
3273
ProtRefPtr prp = NULL;
3274
RnaRefPtr rrp;
3275
tRNAPtr trp;
3276
Int4 gbqual;
3277
3278
if (sfp == NULL || field == NULL || field->field == NULL)
3279
{
3280
return FALSE;
3281
}
3282
if (field->type != Feature_type_any && sfp->idx.subtype != GetFeatdefFromFeatureType (field->type))
3283
{
3284
return FALSE;
3285
}
3286
3287
// for gene fields
3288
if (sfp->idx.subtype == FEATDEF_GENE) {
3289
grp = sfp->data.value.ptrvalue;
3290
} else {
3291
grp = SeqMgrGetGeneXref (sfp);
3292
}
3293
3294
// for protein fields
3295
prp = GetProtRefForFeature (sfp);
3296
3297
// for RNA fields
3298
if (sfp->data.choice == SEQFEAT_RNA) {
3299
rrp = (RnaRefPtr) sfp->data.value.ptrvalue;
3300
}
3301
3302
/* fields common to all features */
3303
/* note, also known as comment */
3304
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_note)
3305
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("note", field->field->data.ptrvalue)))
3306
{
3307
if (!StringHasNoText (sfp->comment) && DoesStringMatchConstraint (sfp->comment, scp))
3308
{
3309
sfp->comment = MemFree (sfp->comment);
3310
rval = TRUE;
3311
}
3312
}
3313
/* db-xref */
3314
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_db_xref)
3315
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("db_xref", field->field->data.ptrvalue)))
3316
{
3317
rval = RemoveDbxrefString (sfp, scp);
3318
}
3319
/* exception */
3320
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_exception)
3321
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("exception", field->field->data.ptrvalue)))
3322
{
3323
if (!StringHasNoText (sfp->except_text) && DoesStringMatchConstraint (sfp->except_text, scp))
3324
{
3325
sfp->except_text = MemFree (sfp->except_text);
3326
rval = TRUE;
3327
}
3328
}
3329
/* evidence */
3330
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_evidence)
3331
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("evidence", field->field->data.ptrvalue)))
3332
{
3333
if ((sfp->exp_ev == 1 && DoesStringMatchConstraint("experimental", scp))
3334
|| (sfp->exp_ev == 2 && DoesStringMatchConstraint("non-experimental", scp))) {
3335
sfp->exp_ev = 0;
3336
rval = TRUE;
3337
}
3338
}
3339
3340
/* fields common to some features */
3341
/* product */
3342
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_product)
3343
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("product", field->field->data.ptrvalue)))
3344
{
3345
if (prp != NULL) {
3346
rval = RemoveValNodeStringMatch (&(prp->name), scp);
3347
} else if (sfp->data.choice == SEQFEAT_RNA) {
3348
rval = RemoveRNAProductString (sfp, scp);
3349
}
3350
}
3351
3352
/* Gene fields */
3353
/* locus */
3354
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_gene)
3355
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("locus", field->field->data.ptrvalue)))
3356
&& grp != NULL)
3357
{
3358
if (!StringHasNoText (grp->locus) && DoesStringMatchConstraint (grp->locus, scp)) {
3359
grp->locus = MemFree (grp->locus);
3360
rval = TRUE;
3361
}
3362
}
3363
/* description */
3364
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_gene_description)
3365
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("description", field->field->data.ptrvalue)))
3366
&& grp != NULL)
3367
{
3368
if (!StringHasNoText (grp->desc) && DoesStringMatchConstraint(grp->desc, scp))
3369
{
3370
grp->desc = MemFree (grp->desc);
3371
rval = TRUE;
3372
}
3373
}
3374
/* maploc */
3375
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_map)
3376
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("map", field->field->data.ptrvalue)))
3377
&& grp != NULL)
3378
{
3379
if (!StringHasNoText (grp->maploc) && DoesStringMatchConstraint(grp->maploc, scp))
3380
{
3381
grp->maploc = MemFree (grp->maploc);
3382
rval = TRUE;
3383
}
3384
}
3385
/* allele */
3386
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_allele)
3387
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("allele", field->field->data.ptrvalue)))
3388
&& grp != NULL)
3389
{
3390
if (!StringHasNoText (grp->allele) && DoesStringMatchConstraint(grp->allele, scp))
3391
{
3392
grp->allele = MemFree (grp->allele);
3393
rval = TRUE;
3394
}
3395
}
3396
/* locus_tag */
3397
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_locus_tag)
3398
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("locus_tag", field->field->data.ptrvalue)))
3399
&& grp != NULL)
3400
{
3401
if (!StringHasNoText (grp->locus_tag) && DoesStringMatchConstraint(grp->locus_tag, scp))
3402
{
3403
grp->locus_tag = MemFree (grp->locus_tag);
3404
rval = TRUE;
3405
}
3406
}
3407
/* synonym */
3408
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_synonym)
3409
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("synonym", field->field->data.ptrvalue)))
3410
&& grp != NULL)
3411
{
3412
rval = RemoveValNodeStringMatch (&(grp->syn), scp);
3413
}
3414
3415
/* protein fields */
3416
/* note - product handled above */
3417
/* description */
3418
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_description)
3419
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("description", field->field->data.ptrvalue)))
3420
&& prp != NULL)
3421
{
3422
if (!StringHasNoText (prp->desc) && DoesStringMatchConstraint(prp->desc, scp)) {
3423
prp->desc = MemFree (prp->desc);
3424
rval = TRUE;
3425
}
3426
}
3427
/* ec_number */
3428
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_ec_number)
3429
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("ec_number", field->field->data.ptrvalue)))
3430
&& prp != NULL)
3431
{
3432
rval = RemoveValNodeStringMatch (&(prp->ec), scp);
3433
}
3434
/* activity */
3435
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_activity)
3436
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("activity", field->field->data.ptrvalue)))
3437
&& prp != NULL)
3438
{
3439
rval = RemoveValNodeStringMatch (&(prp->activity), scp);
3440
}
3441
3442
/* RNA fields */
3443
/* anticodon */
3444
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_anticodon)
3445
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("anticodon", field->field->data.ptrvalue)))
3446
&& rrp != NULL && rrp->ext.choice == 2)
3447
{
3448
trp = (tRNAPtr) rrp->ext.value.ptrvalue;
3449
if (trp != NULL && trp->anticodon != NULL) {
3450
trp->anticodon = SeqLocFree (trp->anticodon);
3451
rval = TRUE;
3452
}
3453
}
3454
/* codons recognized */
3455
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_anticodon)
3456
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("anticodon", field->field->data.ptrvalue)))
3457
&& rrp != NULL && rrp->ext.choice == 2)
3458
{
3459
trp = (tRNAPtr) rrp->ext.value.ptrvalue;
3460
if (trp != NULL && (trp->codon[0] != 255 || trp->codon[1] != 255 || trp->codon[2] != 255
3461
|| trp->codon[3] != 255 || trp->codon[4] != 255 || trp->codon[5] != 255)) {
3462
trp->codon [0] = 255;
3463
trp->codon [1] = 255;
3464
trp->codon [2] = 255;
3465
trp->codon [3] = 255;
3466
trp->codon [4] = 255;
3467
trp->codon [5] = 255;
3468
rval = TRUE;
3469
}
3470
}
3471
3472
if (!rval) {
3473
/* actual GenBank qualifiers */
3474
if (field->field->choice == FeatQualChoice_legal_qual)
3475
{
3476
gbqual = GetGBQualFromFeatQual (field->field->data.intvalue);
3477
if (gbqual > -1) {
3478
rval = RemoveGBQualMatch (&(sfp->qual), ParFlat_GBQual_names [gbqual].name, scp);
3479
} else {
3480
/* need to do something with non-qualifier qualifiers */
3481
}
3482
} else {
3483
rval = RemoveGBQualMatchConstraintName (&(sfp->qual), field->field->data.ptrvalue, scp);
3484
}
3485
}
3486
3487
return rval;
3488
}
3489
3490
3491
static Boolean ChooseBestFrame (SeqFeatPtr sfp)
3492
{
3493
CdRegionPtr crp;
3494
Uint1 new_frame = 0, i, orig_frame;
3495
ByteStorePtr bs;
3496
Int4 lens [3];
3497
Int4 max;
3498
Boolean retval = TRUE;
3499
3500
if (sfp == NULL || sfp->data.choice != SEQFEAT_CDREGION) return FALSE;
3501
3502
crp = sfp->data.value.ptrvalue;
3503
if (crp == NULL) return FALSE;
3504
orig_frame = crp->frame;
3505
3506
max = 0;
3507
for (i = 1; i <= 3; i++) {
3508
crp->frame = i;
3509
bs = ProteinFromCdRegionEx (sfp, FALSE, FALSE);
3510
lens[i - 1] = BSLen (bs);
3511
BSFree (bs);
3512
if (lens[i - 1] > max) {
3513
max = lens[i - 1];
3514
new_frame = i;
3515
}
3516
}
3517
for (i = 1; i <= 3; i++) {
3518
if (lens [i - 1] == max && i != new_frame) {
3519
retval = FALSE;
3520
}
3521
}
3522
if (retval) {
3523
crp->frame = new_frame;
3524
} else {
3525
crp->frame = orig_frame;
3526
}
3527
return retval;
3528
}
3529
3530
3531
static Boolean SetQualOnFeature (SeqFeatPtr sfp, FeatureFieldPtr field, StringConstraintPtr scp, CharPtr value, Uint2 existing_text)
3532
{
3533
Boolean rval = FALSE;
3534
GeneRefPtr grp = NULL;
3535
ProtRefPtr prp = NULL;
3536
CharPtr tmp;
3537
CdRegionPtr crp;
3538
3539
if (sfp == NULL || field == NULL || field->field == NULL)
3540
{
3541
return FALSE;
3542
}
3543
if (field->type != Feature_type_any && sfp->idx.subtype != GetFeatdefFromFeatureType (field->type))
3544
{
3545
return FALSE;
3546
}
3547
3548
// for gene fields
3549
if (sfp->idx.subtype == FEATDEF_GENE) {
3550
grp = sfp->data.value.ptrvalue;
3551
} else {
3552
grp = SeqMgrGetGeneXref (sfp);
3553
}
3554
3555
// for protein fields
3556
prp = GetProtRefForFeature (sfp);
3557
3558
/* fields common to all features */
3559
/* note, also known as comment */
3560
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_note)
3561
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("note", field->field->data.ptrvalue)))
3562
{
3563
if (DoesStringMatchConstraint(sfp->comment, scp))
3564
{
3565
rval = SetStringValue ( &(sfp->comment), value, existing_text);
3566
}
3567
}
3568
/* db-xref */
3569
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_db_xref)
3570
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("db_xref", field->field->data.ptrvalue)))
3571
{
3572
rval = SetDbxrefString (sfp, scp, value, existing_text);
3573
}
3574
/* exception */
3575
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_exception)
3576
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("exception", field->field->data.ptrvalue)))
3577
{
3578
if (DoesStringMatchConstraint(sfp->except_text, scp))
3579
{
3580
rval = SetStringValue ( &(sfp->except_text), value, existing_text);
3581
}
3582
}
3583
/* evidence */
3584
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_evidence)
3585
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("evidence", field->field->data.ptrvalue)))
3586
{
3587
tmp = NULL;
3588
if (sfp->exp_ev == 1)
3589
{
3590
tmp = StringSave ("experimental");
3591
}
3592
else if (sfp->exp_ev == 2)
3593
{
3594
tmp = StringSave ("non-experimental");
3595
}
3596
if (DoesStringMatchConstraint(tmp, scp)) {
3597
rval = SetStringValue (&tmp, value, existing_text);
3598
if (rval) {
3599
rval = FALSE;
3600
if (StringICmp (tmp, "experimental") == 0) {
3601
sfp->exp_ev = 1;
3602
rval = TRUE;
3603
} else if (StringICmp (tmp, "non-experimental") == 0) {
3604
sfp->exp_ev = 2;
3605
rval = TRUE;
3606
} else if (StringHasNoText (tmp)) {
3607
sfp->exp_ev = 0;
3608
rval = TRUE;
3609
}
3610
}
3611
}
3612
tmp = MemFree (tmp);
3613
}
3614
3615
3616
/* fields common to some features */
3617
/* product */
3618
if ((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_product)
3619
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("product", field->field->data.ptrvalue)))
3620
{
3621
if (prp != NULL) {
3622
rval = SetStringsInValNodeStringList (&(prp->name), scp, value, existing_text);
3623
} else if (sfp->data.choice == SEQFEAT_RNA) {
3624
rval = SetRNAProductString (sfp, scp, value, existing_text);
3625
}
3626
}
3627
3628
/* Gene fields */
3629
/* locus */
3630
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_gene)
3631
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("locus", field->field->data.ptrvalue)))
3632
&& grp != NULL)
3633
{
3634
if (DoesStringMatchConstraint(grp->locus, scp))
3635
{
3636
rval = SetStringValue (&(grp->locus), value, existing_text);
3637
}
3638
}
3639
/* description */
3640
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_gene_description)
3641
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("description", field->field->data.ptrvalue)))
3642
&& grp != NULL)
3643
{
3644
if (DoesStringMatchConstraint(grp->desc, scp))
3645
{
3646
rval = SetStringValue (&(grp->desc), value, existing_text);
3647
}
3648
}
3649
/* maploc */
3650
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_map)
3651
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("map", field->field->data.ptrvalue)))
3652
&& grp != NULL)
3653
{
3654
if (DoesStringMatchConstraint(grp->maploc, scp))
3655
{
3656
rval = SetStringValue (&(grp->maploc), value, existing_text);
3657
}
3658
}
3659
/* allele */
3660
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_allele)
3661
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("allele", field->field->data.ptrvalue)))
3662
&& grp != NULL)
3663
{
3664
if (DoesStringMatchConstraint(grp->allele, scp))
3665
{
3666
rval = SetStringValue (&(grp->allele), value, existing_text);
3667
}
3668
}
3669
/* locus_tag */
3670
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_locus_tag)
3671
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("locus_tag", field->field->data.ptrvalue)))
3672
&& grp != NULL)
3673
{
3674
if (DoesStringMatchConstraint(grp->locus_tag, scp))
3675
{
3676
rval = SetStringValue (&(grp->locus_tag), value, existing_text);
3677
}
3678
}
3679
/* synonym */
3680
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_synonym)
3681
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("synonym", field->field->data.ptrvalue)))
3682
&& grp != NULL)
3683
{
3684
rval = SetStringsInValNodeStringList (&(grp->syn), scp, value, existing_text);
3685
}
3686
3687
3688
/* protein fields */
3689
/* note - product handled above */
3690
/* description */
3691
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_description)
3692
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("description", field->field->data.ptrvalue)))
3693
&& prp != NULL)
3694
{
3695
if (DoesStringMatchConstraint(prp->desc, scp)) {
3696
rval = SetStringValue (&(prp->desc), value, existing_text);
3697
}
3698
}
3699
/* ec_number */
3700
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_ec_number)
3701
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("ec_number", field->field->data.ptrvalue)))
3702
&& prp != NULL)
3703
{
3704
rval = SetStringsInValNodeStringList (&(prp->ec), scp, value, existing_text);
3705
}
3706
/* activity */
3707
if (((field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_activity)
3708
|| (field->field->choice == FeatQualChoice_illegal_qual && DoesStringMatchConstraint ("activity", field->field->data.ptrvalue)))
3709
&& prp != NULL)
3710
{
3711
rval = SetStringsInValNodeStringList (&(prp->activity), scp, value, existing_text);
3712
}
3713
3714
if (field->field->choice == FeatQualChoice_legal_qual && field->field->data.intvalue == Feat_qual_legal_codon_start
3715
&& sfp->data.choice == SEQFEAT_CDREGION)
3716
{
3717
crp = (CdRegionPtr) sfp->data.value.ptrvalue;
3718
if (StringICmp (value, "best") == 0)
3719
{
3720
rval = ChooseBestFrame (sfp);
3721
}
3722
else if (StringCmp (value, "1") == 0)
3723
{
3724
crp->frame = 1;
3725
rval = TRUE;
3726
}
3727
else if (StringCmp (value, "2") == 0)
3728
{
3729
crp->frame = 2;
3730
rval = TRUE;
3731
}
3732
else if (StringCmp (value, "3") == 0)
3733
{
3734
crp->frame = 3;
3735
rval = TRUE;
3736
}
3737
}
3738
3739
/* actual GenBank qualifiers */
3740
if (!rval)
3741
{
3742
rval = SetStringInGBQualList (&(sfp->qual), field->field, scp, value, existing_text);
3743
}
3744
return rval;
3745
}
3746
3747
3748
NLM_EXTERN CharPtr GetSourceQualFromBioSource (BioSourcePtr biop, SourceQualChoicePtr scp, StringConstraintPtr constraint)
3749
{
3750
CharPtr str = NULL;
3751
SubSourcePtr ssp;
3752
OrgModPtr mod;
3753
Int4 orgmod_subtype = -1, subsrc_subtype = -1;
3754
3755
if (biop == NULL || scp == NULL) return NULL;
3756
3757
switch (scp->choice)
3758
{
3759
case SourceQualChoice_textqual:
3760
if (scp->data.intvalue == Source_qual_taxname) {
3761
if (biop->org != NULL && !StringHasNoText (biop->org->taxname)
3762
&& DoesStringMatchConstraint (biop->org->taxname, constraint)) {
3763
str = StringSave (biop->org->taxname);
3764
}
3765
} else if (scp->data.intvalue == Source_qual_common_name) {
3766
if (biop->org != NULL && !StringHasNoText (biop->org->common)
3767
&& DoesStringMatchConstraint (biop->org->common, constraint)) {
3768
str = StringSave (biop->org->common);
3769
}
3770
} else if (scp->data.intvalue == Source_qual_lineage) {
3771
if (biop->org != NULL && biop->org->orgname != NULL && !StringHasNoText (biop->org->orgname->lineage)
3772
&& DoesStringMatchConstraint (biop->org->orgname->lineage, constraint)) {
3773
str = StringSave (biop->org->orgname->lineage);
3774
}
3775
} else if (scp->data.intvalue == Source_qual_division) {
3776
if (biop->org != NULL && biop->org->orgname != NULL && !StringHasNoText (biop->org->orgname->div)
3777
&& DoesStringMatchConstraint (biop->org->orgname->div, constraint)) {
3778
str = StringSave (biop->org->orgname->div);
3779
}
3780
} else {
3781
orgmod_subtype = GetOrgModQualFromSrcQual (scp->data.intvalue);
3782
if (orgmod_subtype == -1) {
3783
subsrc_subtype = GetSubSrcQualFromSrcQual (scp->data.intvalue);
3784
for (ssp = biop->subtype; ssp != NULL && str == NULL; ssp = ssp->next) {
3785
if (ssp->subtype == subsrc_subtype) {
3786
if (StringHasNoText (ssp->name)) {
3787
if (IsNonTextSourceQual (scp->data.intvalue)
3788
&& DoesStringMatchConstraint ("TRUE", constraint)) {
3789
str = StringSave ("TRUE");
3790
}
3791
} else {
3792
if (DoesStringMatchConstraint (ssp->name, constraint)) {
3793
str = StringSave (ssp->name);
3794
}
3795
}
3796
}
3797
}
3798
} else {
3799
if (biop->org != NULL && biop->org->orgname != NULL) {
3800
for (mod = biop->org->orgname->mod; mod != NULL && str == NULL; mod = mod->next) {
3801
if (mod->subtype == orgmod_subtype) {
3802
if (StringHasNoText (mod->subname)) {
3803
if (IsNonTextSourceQual (scp->data.intvalue)
3804
&& DoesStringMatchConstraint ("TRUE", constraint)) {
3805
str = StringSave ("TRUE");
3806
}
3807
} else {
3808
if (DoesStringMatchConstraint (mod->subname, constraint)) {
3809
str = StringSave (mod->subname);
3810
}
3811
}
3812
}
3813
}
3814
}
3815
}
3816
}
3817
break;
3818
case SourceQualChoice_location:
3819
str = LocNameFromGenome (biop->genome);
3820
if (DoesStringMatchConstraint (str, constraint)) {
3821
str = StringSave (str);
3822
} else {
3823
str = NULL;
3824
}
3825
break;
3826
case SourceQualChoice_origin:
3827
str = OriginNameFromOrigin (biop->origin);
3828
if (DoesStringMatchConstraint (str, constraint)) {
3829
str = StringSave (str);
3830
} else {
3831
str = NULL;
3832
}
3833
break;
3834
}
3835
return str;
3836
}
3837
3838
3839
static Boolean RemoveSourceQualFromBioSource (BioSourcePtr biop, SourceQualChoicePtr scp, StringConstraintPtr constraint)
3840
{
3841
SubSourcePtr ssp, ssp_prev = NULL, ssp_next;
3842
OrgModPtr mod, mod_prev = NULL, mod_next;
3843
Int4 orgmod_subtype = -1, subsrc_subtype = -1;
3844
CharPtr str;
3845
Boolean rval = FALSE;
3846
3847
if (biop == NULL || scp == NULL) return FALSE;
3848
3849
switch (scp->choice)
3850
{
3851
case SourceQualChoice_textqual:
3852
if (scp->data.intvalue == Source_qual_taxname) {
3853
if (biop->org != NULL && !StringHasNoText (biop->org->taxname)
3854
&& DoesStringMatchConstraint (biop->org->taxname, constraint)) {
3855
biop->org->taxname = MemFree (biop->org->taxname);
3856
rval = TRUE;
3857
}
3858
} else if (scp->data.intvalue == Source_qual_common_name) {
3859
if (biop->org != NULL && !StringHasNoText (biop->org->common)
3860
&& DoesStringMatchConstraint (biop->org->common, constraint)) {
3861
biop->org->common = MemFree (biop->org->common);
3862
rval = TRUE;
3863
}
3864
} else if (scp->data.intvalue == Source_qual_lineage) {
3865
if (biop->org != NULL && biop->org->orgname != NULL && !StringHasNoText (biop->org->orgname->lineage)
3866
&& DoesStringMatchConstraint (biop->org->orgname->lineage, constraint)) {
3867
biop->org->orgname->lineage = MemFree (biop->org->orgname->lineage);
3868
rval = TRUE;
3869
}
3870
} else if (scp->data.intvalue == Source_qual_division) {
3871
if (biop->org != NULL && biop->org->orgname != NULL && !StringHasNoText (biop->org->orgname->div)
3872
&& DoesStringMatchConstraint (biop->org->orgname->div, constraint)) {
3873
biop->org->orgname->div = MemFree (biop->org->orgname->div);
3874
rval = TRUE;
3875
}
3876
} else {
3877
orgmod_subtype = GetOrgModQualFromSrcQual (scp->data.intvalue);
3878
if (orgmod_subtype == -1) {
3879
subsrc_subtype = GetSubSrcQualFromSrcQual (scp->data.intvalue);
3880
ssp = biop->subtype;
3881
while (ssp != NULL) {
3882
ssp_next = ssp->next;
3883
if (ssp->subtype == subsrc_subtype
3884
&& DoesStringMatchConstraint (ssp->name, constraint)) {
3885
if (ssp_prev == NULL) {
3886
biop->subtype = ssp->next;
3887
} else {
3888
ssp_prev->next = ssp->next;
3889
}
3890
ssp->next = NULL;
3891
ssp = SubSourceFree (ssp);
3892
rval = TRUE;
3893
} else {
3894
ssp_prev = ssp;
3895
}
3896
ssp = ssp_next;
3897
}
3898
} else {
3899
if (biop->org != NULL && biop->org->orgname != NULL) {
3900
mod = biop->org->orgname->mod;
3901
while (mod != NULL) {
3902
mod_next = mod->next;
3903
if (mod->subtype == orgmod_subtype
3904
&& DoesStringMatchConstraint (mod->subname, constraint)) {
3905
if (mod_prev == NULL) {
3906
biop->org->orgname->mod = mod->next;
3907
} else {
3908
mod_prev->next = mod->next;
3909
}
3910
mod->next = NULL;
3911
mod = OrgModFree (mod);
3912
rval = TRUE;
3913
} else {
3914
mod_prev = mod;
3915
}
3916
mod = mod_next;
3917
}
3918
}
3919
}
3920
}
3921
break;
3922
case SourceQualChoice_location:
3923
str = LocNameFromGenome (biop->genome);
3924
if (DoesStringMatchConstraint (str, constraint)) {
3925
if (scp->data.intvalue == 0 || biop->genome == GenomeFromSrcLoc (scp->data.intvalue)) {
3926
biop->genome = 0;
3927
rval = TRUE;
3928
}
3929
}
3930
break;
3931
case SourceQualChoice_origin:
3932
str = OriginNameFromOrigin (biop->origin);
3933
if (DoesStringMatchConstraint (str, constraint)) {
3934
if (scp->data.intvalue == 0 || biop->origin == OriginFromSrcOrig (scp->data.intvalue)) {
3935
biop->origin = 0;
3936
rval = TRUE;
3937
}
3938
}
3939
break;
3940
}
3941
return rval;
3942
}
3943
3944
3945
NLM_EXTERN Boolean SetSourceQualInBioSource (BioSourcePtr biop, SourceQualChoicePtr scp, StringConstraintPtr constraint, CharPtr value, Uint2 existing_text)
3946
{
3947
SubSourcePtr ssp, ssp_prev = NULL, ssp_next;
3948
OrgModPtr mod, mod_prev = NULL, mod_next;
3949
Int4 orgmod_subtype = -1, subsrc_subtype = -1;
3950
CharPtr str;
3951
Boolean rval = FALSE, found = FALSE;
3952
3953
if (biop == NULL || scp == NULL) return FALSE;
3954
3955
switch (scp->choice)
3956
{
3957
case SourceQualChoice_textqual:
3958
if (scp->data.intvalue == Source_qual_taxname) {
3959
if (biop->org != NULL
3960
&& DoesStringMatchConstraint (biop->org->taxname, constraint)) {
3961
rval = SetStringValue (&(biop->org->taxname), value, existing_text);
3962
}
3963
} else if (scp->data.intvalue == Source_qual_common_name) {
3964
if (biop->org != NULL
3965
&& DoesStringMatchConstraint (biop->org->common, constraint)) {
3966
rval = SetStringValue (&(biop->org->common), value, existing_text);
3967
}
3968
} else if (scp->data.intvalue == Source_qual_lineage) {
3969
if (biop->org != NULL && biop->org->orgname != NULL
3970
&& DoesStringMatchConstraint (biop->org->orgname->lineage, constraint)) {
3971
rval = SetStringValue (&(biop->org->orgname->lineage), value, existing_text);
3972
}
3973
} else if (scp->data.intvalue == Source_qual_division) {
3974
if (biop->org != NULL && biop->org->orgname != NULL
3975
&& DoesStringMatchConstraint (biop->org->orgname->div, constraint)) {
3976
rval = SetStringValue (&(biop->org->orgname->div), value, existing_text);
3977
}
3978
} else {
3979
orgmod_subtype = GetOrgModQualFromSrcQual (scp->data.intvalue);
3980
if (orgmod_subtype == -1) {
3981
subsrc_subtype = GetSubSrcQualFromSrcQual (scp->data.intvalue);
3982
if (subsrc_subtype > -1) {
3983
ssp = biop->subtype;
3984
while (ssp != NULL) {
3985
ssp_next = ssp->next;
3986
if (ssp->subtype == subsrc_subtype
3987
&& DoesStringMatchConstraint (ssp->name, constraint)) {
3988
rval = SetStringValue (&(ssp->name), value, existing_text);
3989
found = TRUE;
3990
if (rval && StringHasNoText (ssp->name) && !IsNonTextSourceQual(scp->data.intvalue)) {
3991
if (ssp_prev == NULL) {
3992
biop->subtype = ssp->next;
3993
} else {
3994
ssp_prev->next = ssp->next;
3995
}
3996
ssp->next = NULL;
3997
ssp = SubSourceFree (ssp);
3998
} else {
3999
ssp_prev = ssp;
4000
}
4001
} else {
4002
ssp_prev = ssp;
4003
}
4004
ssp = ssp_next;
4005
}
4006
if (!found && IsStringConstraintEmpty (constraint)) {
4007
ssp = SubSourceNew ();
4008
ssp->subtype = subsrc_subtype;
4009
rval = SetStringValue (&(ssp->name), value, existing_text);
4010
if (ssp_prev == NULL) {
4011
biop->subtype = ssp;
4012
} else {
4013
ssp_prev->next = ssp;
4014
}
4015
}
4016
}
4017
} else {
4018
if (biop->org != NULL && biop->org->orgname != NULL) {
4019
mod = biop->org->orgname->mod;
4020
while (mod != NULL) {
4021
mod_next = mod->next;
4022
if (mod->subtype == orgmod_subtype
4023
&& DoesStringMatchConstraint (mod->subname, constraint)) {
4024
rval = SetStringValue (&(mod->subname), value, existing_text);
4025
found = TRUE;
4026
if (rval && StringHasNoText (mod->subname) && !IsNonTextSourceQual(scp->data.intvalue)) {
4027
if (mod_prev == NULL) {
4028
biop->org->orgname->mod = mod->next;
4029
} else {
4030
mod_prev->next = mod->next;
4031
}
4032
mod->next = NULL;
4033
mod = OrgModFree (mod);
4034
} else {
4035
mod_prev = mod;
4036
}
4037
} else {
4038
mod_prev = mod;
4039
}
4040
mod = mod_next;
4041
}
4042
}
4043
if (!found && IsStringConstraintEmpty (constraint)) {
4044
if (biop->org == NULL) {
4045
biop->org = OrgRefNew();
4046
}
4047
if (biop->org->orgname == NULL) {
4048
biop->org->orgname = OrgNameNew();
4049
}
4050
mod = OrgModNew ();
4051
mod->subtype = orgmod_subtype;
4052
rval = SetStringValue (&(mod->subname), value, existing_text);
4053
if (mod_prev == NULL) {
4054
biop->org->orgname->mod = mod;
4055
} else {
4056
mod_prev->next = mod;
4057
}
4058
}
4059
}
4060
}
4061
break;
4062
case SourceQualChoice_location:
4063
str = LocNameFromGenome (biop->genome);
4064
if (DoesStringMatchConstraint (str, constraint)) {
4065
biop->genome = GenomeFromSrcLoc (scp->data.intvalue);
4066
rval = TRUE;
4067
}
4068
break;
4069
case SourceQualChoice_origin:
4070
str = OriginNameFromOrigin (biop->origin);
4071
if (DoesStringMatchConstraint (str, constraint)) {
4072
biop->origin = OriginFromSrcOrig(scp->data.intvalue);
4073
rval = TRUE;
4074
}
4075
break;
4076
}
4077
return rval;
4078
}
4079
4080
4081
static BioseqPtr GetSequenceForObject (Uint1 choice, Pointer data)
4082
{
4083
BioseqPtr bsp = NULL;
4084
SeqFeatPtr sfp;
4085
SeqDescrPtr sdp;
4086
ObjValNodePtr ovp;
4087
CGPSetPtr cgp;
4088
ValNodePtr vnp;
4089
4090
if (data == NULL) return NULL;
4091
4092
switch (choice) {
4093
case OBJ_BIOSEQ:
4094
bsp = (BioseqPtr) data;
4095
break;
4096
case OBJ_SEQFEAT:
4097
sfp = (SeqFeatPtr) data;
4098
bsp = BioseqFindFromSeqLoc (sfp->location);
4099
break;
4100
case OBJ_SEQDESC:
4101
sdp = (SeqDescrPtr) data;
4102
if (sdp->extended) {
4103
ovp = (ObjValNodePtr) sdp;
4104
if (ovp->idx.parenttype == OBJ_BIOSEQ && ovp->idx.parentptr != NULL) {
4105
bsp = ovp->idx.parentptr;
4106
}
4107
}
4108
break;
4109
case 0:
4110
cgp = (CGPSetPtr) data;
4111
for (vnp = cgp->cds_list; vnp != NULL && bsp == NULL; vnp = vnp->next) {
4112
sfp = vnp->data.ptrvalue;
4113
if (sfp != NULL) {
4114
bsp = BioseqFindFromSeqLoc (sfp->location);
4115
}
4116
}
4117
for (vnp = cgp->mrna_list; vnp != NULL && bsp == NULL; vnp = vnp->next) {
4118
sfp = vnp->data.ptrvalue;
4119
if (sfp != NULL) {
4120
bsp = BioseqFindFromSeqLoc (sfp->location);
4121
}
4122
}
4123
break;
4124
for (vnp = cgp->gene_list; vnp != NULL && bsp == NULL; vnp = vnp->next) {
4125
sfp = vnp->data.ptrvalue;
4126
if (sfp != NULL) {
4127
bsp = BioseqFindFromSeqLoc (sfp->location);
4128
}
4129
}
4130
break;
4131
}
4132
return bsp;
4133
}
4134
4135
4136
NLM_EXTERN BioSourcePtr GetBioSourceFromObject (Uint1 choice, Pointer data)
4137
{
4138
BioSourcePtr biop = NULL;
4139
SeqDescrPtr sdp;
4140
SeqFeatPtr sfp;
4141
BioseqPtr bsp = NULL;
4142
SeqMgrDescContext context;
4143
4144
if (data == NULL) return NULL;
4145
4146
switch (choice)
4147
{
4148
case OBJ_SEQDESC:
4149
sdp = (SeqDescrPtr) data;
4150
if (sdp->choice == Seq_descr_source) {
4151
biop = sdp->data.ptrvalue;
4152
}
4153
break;
4154
case OBJ_SEQFEAT:
4155
sfp = (SeqFeatPtr) data;
4156
if (sfp->data.choice == SEQFEAT_BIOSRC) {
4157
biop = sfp->data.value.ptrvalue;
4158
}
4159
break;
4160
}
4161
if (biop == NULL) {
4162
bsp = GetSequenceForObject (choice, data);
4163
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_source, &context);
4164
if (sdp != NULL && sdp->choice == Seq_descr_source) {
4165
biop = sdp->data.ptrvalue;
4166
}
4167
}
4168
return biop;
4169
}
4170
4171
4172
/* functions for dealing with CDS-Gene-Prot sets */
4173
static CharPtr GetFieldValueFromCGPSet (CGPSetPtr c, Uint2 field, StringConstraintPtr scp)
4174
{
4175
CharPtr str = NULL;
4176
ValNodePtr vnp;
4177
SeqFeatPtr sfp;
4178
GeneRefPtr grp;
4179
RnaRefPtr rrp;
4180
ProtRefPtr prp;
4181
4182
if (c == NULL) return NULL;
4183
switch (field) {
4184
case CDSGeneProt_field_cds_comment:
4185
for (vnp = c->cds_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4186
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4187
if (sfp != NULL && !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4188
{
4189
str = StringSave (sfp->comment);
4190
}
4191
}
4192
break;
4193
case CDSGeneProt_field_gene_locus:
4194
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4195
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4196
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4197
&& (grp = sfp->data.value.ptrvalue) != NULL
4198
&& !StringHasNoText (grp->locus)
4199
&& DoesStringMatchConstraint(grp->locus, scp))
4200
{
4201
str = StringSave (grp->locus);
4202
}
4203
}
4204
break;
4205
case CDSGeneProt_field_gene_description:
4206
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4207
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4208
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4209
&& (grp = sfp->data.value.ptrvalue) != NULL
4210
&& !StringHasNoText (grp->desc)
4211
&& DoesStringMatchConstraint(grp->desc, scp))
4212
{
4213
str = StringSave (grp->desc);
4214
}
4215
}
4216
break;
4217
case CDSGeneProt_field_gene_comment:
4218
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4219
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4220
if (sfp != NULL && !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4221
{
4222
str = StringSave (sfp->comment);
4223
}
4224
}
4225
break;
4226
case CDSGeneProt_field_gene_allele:
4227
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4228
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4229
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4230
&& (grp = sfp->data.value.ptrvalue) != NULL
4231
&& !StringHasNoText (grp->allele)
4232
&& DoesStringMatchConstraint(grp->allele, scp))
4233
{
4234
str = StringSave (grp->allele);
4235
}
4236
}
4237
break;
4238
case CDSGeneProt_field_gene_maploc:
4239
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4240
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4241
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4242
&& (grp = sfp->data.value.ptrvalue) != NULL
4243
&& !StringHasNoText (grp->maploc)
4244
&& DoesStringMatchConstraint(grp->maploc, scp))
4245
{
4246
str = StringSave (grp->maploc);
4247
}
4248
}
4249
break;
4250
case CDSGeneProt_field_gene_locus_tag:
4251
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4252
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4253
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4254
&& (grp = sfp->data.value.ptrvalue) != NULL
4255
&& !StringHasNoText (grp->locus_tag)
4256
&& DoesStringMatchConstraint(grp->locus_tag, scp))
4257
{
4258
str = StringSave (grp->locus_tag);
4259
}
4260
}
4261
break;
4262
case CDSGeneProt_field_gene_synonym:
4263
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4264
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4265
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4266
&& (grp = sfp->data.value.ptrvalue) != NULL)
4267
{
4268
str = GetFirstValNodeStringMatch (grp->syn, scp);
4269
}
4270
}
4271
break;
4272
case CDSGeneProt_field_gene_old_locus_tag:
4273
for (vnp = c->gene_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4274
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4275
if (sfp != NULL) {
4276
str = GetFirstGBQualMatch (sfp->qual, "old-locus-tag", scp);
4277
}
4278
}
4279
break;
4280
case CDSGeneProt_field_mrna_product:
4281
for (vnp = c->mrna_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4282
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4283
if (sfp != NULL && sfp->data.choice == SEQFEAT_RNA
4284
&& (rrp = sfp->data.value.ptrvalue) != NULL
4285
&& rrp->ext.choice == 1
4286
&& !StringHasNoText (rrp->ext.value.ptrvalue)
4287
&& DoesStringMatchConstraint(rrp->ext.value.ptrvalue, scp))
4288
{
4289
str = StringSave (rrp->ext.value.ptrvalue);
4290
}
4291
}
4292
break;
4293
case CDSGeneProt_field_mrna_comment:
4294
for (vnp = c->mrna_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4295
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4296
if (sfp != NULL && !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4297
{
4298
str = StringSave (sfp->comment);
4299
}
4300
}
4301
break;
4302
case CDSGeneProt_field_prot_name:
4303
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4304
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4305
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4306
&& sfp->idx.subtype == FEATDEF_PROT
4307
&& (prp = sfp->data.value.ptrvalue) != NULL)
4308
{
4309
str = GetFirstValNodeStringMatch (prp->name, scp);
4310
}
4311
}
4312
break;
4313
case CDSGeneProt_field_prot_description:
4314
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4315
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4316
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4317
&& sfp->idx.subtype == FEATDEF_PROT
4318
&& (prp = sfp->data.value.ptrvalue) != NULL
4319
&& !StringHasNoText (prp->desc) && DoesStringMatchConstraint(prp->desc, scp)) {
4320
str = StringSave (prp->desc);
4321
}
4322
}
4323
break;
4324
case CDSGeneProt_field_prot_ec_number:
4325
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4326
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4327
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4328
&& sfp->idx.subtype == FEATDEF_PROT
4329
&& (prp = sfp->data.value.ptrvalue) != NULL)
4330
{
4331
str = GetFirstValNodeStringMatch (prp->ec, scp);
4332
}
4333
}
4334
break;
4335
case CDSGeneProt_field_prot_activity:
4336
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4337
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4338
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4339
&& sfp->idx.subtype == FEATDEF_PROT
4340
&& (prp = sfp->data.value.ptrvalue) != NULL)
4341
{
4342
str = GetFirstValNodeStringMatch (prp->activity, scp);
4343
}
4344
}
4345
break;
4346
case CDSGeneProt_field_prot_comment:
4347
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4348
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4349
if (sfp != NULL && sfp->idx.subtype == FEATDEF_PROT
4350
&& !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4351
{
4352
str = StringSave (sfp->comment);
4353
}
4354
}
4355
break;
4356
case CDSGeneProt_field_mat_peptide_name:
4357
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4358
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4359
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4360
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4361
&& (prp = sfp->data.value.ptrvalue) != NULL)
4362
{
4363
str = GetFirstValNodeStringMatch (prp->name, scp);
4364
}
4365
}
4366
break;
4367
case CDSGeneProt_field_mat_peptide_description:
4368
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4369
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4370
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4371
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4372
&& (prp = sfp->data.value.ptrvalue) != NULL
4373
&& !StringHasNoText (prp->desc) && DoesStringMatchConstraint(prp->desc, scp)) {
4374
str = StringSave (prp->desc);
4375
}
4376
}
4377
break;
4378
case CDSGeneProt_field_mat_peptide_ec_number:
4379
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4380
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4381
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4382
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4383
&& (prp = sfp->data.value.ptrvalue) != NULL)
4384
{
4385
str = GetFirstValNodeStringMatch (prp->ec, scp);
4386
}
4387
}
4388
break;
4389
case CDSGeneProt_field_mat_peptide_activity:
4390
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4391
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4392
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4393
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4394
&& (prp = sfp->data.value.ptrvalue) != NULL)
4395
{
4396
str = GetFirstValNodeStringMatch (prp->activity, scp);
4397
}
4398
}
4399
break;
4400
case CDSGeneProt_field_mat_peptide_comment:
4401
for (vnp = c->prot_list; vnp != NULL && str == NULL; vnp = vnp->next) {
4402
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4403
if (sfp != NULL && sfp->idx.subtype == FEATDEF_mat_peptide_aa
4404
&& !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4405
{
4406
str = StringSave (sfp->comment);
4407
}
4408
}
4409
break;
4410
}
4411
return str;
4412
}
4413
4414
4415
static Boolean RemoveFieldValueFromCGPSet (CGPSetPtr c, Uint2 field, StringConstraintPtr scp)
4416
{
4417
Boolean rval = FALSE;
4418
ValNodePtr vnp;
4419
SeqFeatPtr sfp;
4420
GeneRefPtr grp;
4421
RnaRefPtr rrp;
4422
ProtRefPtr prp;
4423
4424
if (c == NULL) return FALSE;
4425
switch (field) {
4426
case CDSGeneProt_field_cds_comment:
4427
for (vnp = c->cds_list; vnp != NULL; vnp = vnp->next) {
4428
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4429
if (sfp != NULL && !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4430
{
4431
sfp->comment = MemFree (sfp->comment);
4432
rval = TRUE;
4433
}
4434
}
4435
break;
4436
case CDSGeneProt_field_gene_locus:
4437
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4438
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4439
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4440
&& (grp = sfp->data.value.ptrvalue) != NULL
4441
&& !StringHasNoText (grp->locus)
4442
&& DoesStringMatchConstraint(grp->locus, scp))
4443
{
4444
grp->locus = MemFree (grp->locus);
4445
rval = TRUE;
4446
}
4447
}
4448
break;
4449
case CDSGeneProt_field_gene_description:
4450
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4451
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4452
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4453
&& (grp = sfp->data.value.ptrvalue) != NULL
4454
&& !StringHasNoText (grp->desc)
4455
&& DoesStringMatchConstraint(grp->desc, scp))
4456
{
4457
grp->desc = MemFree(grp->desc);
4458
rval = TRUE;
4459
}
4460
}
4461
break;
4462
case CDSGeneProt_field_gene_comment:
4463
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4464
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4465
if (sfp != NULL && !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4466
{
4467
sfp->comment = MemFree (sfp->comment);
4468
rval = TRUE;
4469
}
4470
}
4471
break;
4472
case CDSGeneProt_field_gene_allele:
4473
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4474
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4475
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4476
&& (grp = sfp->data.value.ptrvalue) != NULL
4477
&& !StringHasNoText (grp->allele)
4478
&& DoesStringMatchConstraint(grp->allele, scp))
4479
{
4480
grp->allele = MemFree (grp->allele);
4481
rval = TRUE;
4482
}
4483
}
4484
break;
4485
case CDSGeneProt_field_gene_maploc:
4486
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4487
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4488
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4489
&& (grp = sfp->data.value.ptrvalue) != NULL
4490
&& !StringHasNoText (grp->maploc)
4491
&& DoesStringMatchConstraint(grp->maploc, scp))
4492
{
4493
grp->maploc = MemFree (grp->maploc);
4494
rval = TRUE;
4495
}
4496
}
4497
break;
4498
case CDSGeneProt_field_gene_locus_tag:
4499
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4500
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4501
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4502
&& (grp = sfp->data.value.ptrvalue) != NULL
4503
&& !StringHasNoText (grp->locus_tag)
4504
&& DoesStringMatchConstraint(grp->locus_tag, scp))
4505
{
4506
grp->locus_tag = MemFree (grp->locus_tag);
4507
rval = TRUE;
4508
}
4509
}
4510
break;
4511
case CDSGeneProt_field_gene_synonym:
4512
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4513
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4514
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4515
&& (grp = sfp->data.value.ptrvalue) != NULL)
4516
{
4517
rval |= RemoveValNodeStringMatch (&(grp->syn), scp);
4518
}
4519
}
4520
break;
4521
case CDSGeneProt_field_gene_old_locus_tag:
4522
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4523
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4524
if (sfp != NULL) {
4525
rval |= RemoveGBQualMatch (&(sfp->qual), "old-locus-tag", scp);
4526
}
4527
}
4528
break;
4529
case CDSGeneProt_field_mrna_product:
4530
for (vnp = c->mrna_list; vnp != NULL; vnp = vnp->next) {
4531
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4532
if (sfp != NULL && sfp->data.choice == SEQFEAT_RNA
4533
&& (rrp = sfp->data.value.ptrvalue) != NULL
4534
&& rrp->ext.choice == 1
4535
&& !StringHasNoText (rrp->ext.value.ptrvalue)
4536
&& DoesStringMatchConstraint(rrp->ext.value.ptrvalue, scp))
4537
{
4538
rrp->ext.value.ptrvalue = MemFree (rrp->ext.value.ptrvalue);
4539
rrp->ext.choice = 0;
4540
rval = TRUE;
4541
}
4542
}
4543
break;
4544
case CDSGeneProt_field_mrna_comment:
4545
for (vnp = c->mrna_list; vnp != NULL; vnp = vnp->next) {
4546
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4547
if (sfp != NULL && !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4548
{
4549
sfp->comment = MemFree (sfp->comment);
4550
rval = TRUE;
4551
}
4552
}
4553
break;
4554
case CDSGeneProt_field_prot_name:
4555
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4556
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4557
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4558
&& sfp->idx.subtype == FEATDEF_PROT
4559
&& (prp = sfp->data.value.ptrvalue) != NULL)
4560
{
4561
rval |= RemoveValNodeStringMatch (&(prp->name), scp);
4562
}
4563
}
4564
break;
4565
case CDSGeneProt_field_prot_description:
4566
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4567
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4568
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4569
&& sfp->idx.subtype == FEATDEF_PROT
4570
&& (prp = sfp->data.value.ptrvalue) != NULL
4571
&& !StringHasNoText (prp->desc) && DoesStringMatchConstraint(prp->desc, scp)) {
4572
prp->desc = MemFree (prp->desc);
4573
rval = TRUE;
4574
}
4575
}
4576
break;
4577
case CDSGeneProt_field_prot_ec_number:
4578
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4579
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4580
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4581
&& sfp->idx.subtype == FEATDEF_PROT
4582
&& (prp = sfp->data.value.ptrvalue) != NULL)
4583
{
4584
rval |= RemoveValNodeStringMatch (&(prp->ec), scp);
4585
}
4586
}
4587
break;
4588
case CDSGeneProt_field_prot_activity:
4589
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4590
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4591
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4592
&& sfp->idx.subtype == FEATDEF_PROT
4593
&& (prp = sfp->data.value.ptrvalue) != NULL)
4594
{
4595
rval |= RemoveValNodeStringMatch (&(prp->activity), scp);
4596
}
4597
}
4598
break;
4599
case CDSGeneProt_field_prot_comment:
4600
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4601
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4602
if (sfp != NULL && sfp->idx.subtype == FEATDEF_PROT
4603
&& !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4604
{
4605
sfp->comment = MemFree (sfp->comment);
4606
rval = TRUE;
4607
}
4608
}
4609
break;
4610
case CDSGeneProt_field_mat_peptide_name:
4611
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4612
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4613
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4614
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4615
&& (prp = sfp->data.value.ptrvalue) != NULL)
4616
{
4617
rval |= RemoveValNodeStringMatch (&(prp->name), scp);
4618
}
4619
}
4620
break;
4621
case CDSGeneProt_field_mat_peptide_description:
4622
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4623
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4624
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4625
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4626
&& (prp = sfp->data.value.ptrvalue) != NULL
4627
&& !StringHasNoText (prp->desc) && DoesStringMatchConstraint(prp->desc, scp)) {
4628
prp->desc = MemFree (prp->desc);
4629
rval = TRUE;
4630
}
4631
}
4632
break;
4633
case CDSGeneProt_field_mat_peptide_ec_number:
4634
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4635
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4636
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4637
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4638
&& (prp = sfp->data.value.ptrvalue) != NULL)
4639
{
4640
rval |= RemoveValNodeStringMatch (&(prp->ec), scp);
4641
}
4642
}
4643
break;
4644
case CDSGeneProt_field_mat_peptide_activity:
4645
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4646
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4647
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4648
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4649
&& (prp = sfp->data.value.ptrvalue) != NULL)
4650
{
4651
rval |= RemoveValNodeStringMatch (&(prp->activity), scp);
4652
}
4653
}
4654
break;
4655
case CDSGeneProt_field_mat_peptide_comment:
4656
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4657
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4658
if (sfp != NULL && sfp->idx.subtype == FEATDEF_mat_peptide_aa
4659
&& !StringHasNoText (sfp->comment) && DoesStringMatchConstraint(sfp->comment, scp))
4660
{
4661
sfp->comment = MemFree (sfp->comment);
4662
rval = TRUE;
4663
}
4664
}
4665
break;
4666
}
4667
return rval;
4668
}
4669
4670
4671
static SeqFeatPtr CreateGeneForCGPSet (CGPSetPtr c)
4672
{
4673
SeqFeatPtr gene = NULL, sfp = NULL;
4674
BioseqPtr bsp;
4675
ValNodePtr vnp;
4676
4677
if (c == NULL) return NULL;
4678
4679
for (vnp = c->cds_list; vnp != NULL && sfp == NULL; vnp = vnp->next) {
4680
sfp = vnp->data.ptrvalue;
4681
}
4682
for (vnp = c->mrna_list; vnp != NULL && sfp == NULL; vnp = vnp->next) {
4683
sfp = vnp->data.ptrvalue;
4684
}
4685
if (sfp != NULL) {
4686
bsp = BioseqFindFromSeqLoc (sfp->location);
4687
if (bsp != NULL) {
4688
gene = CreateNewFeatureOnBioseq (bsp, SEQFEAT_GENE, sfp->location);
4689
if (gene != NULL) {
4690
gene->data.value.ptrvalue = GeneRefNew();
4691
}
4692
}
4693
}
4694
return gene;
4695
}
4696
4697
4698
static Boolean SetFieldValueInCGPSet (CGPSetPtr c, Uint2 field, StringConstraintPtr scp, CharPtr value, Uint2 existing_text)
4699
{
4700
Boolean rval = FALSE;
4701
ValNodePtr vnp;
4702
SeqFeatPtr sfp;
4703
GeneRefPtr grp;
4704
ProtRefPtr prp;
4705
4706
if (c == NULL) return FALSE;
4707
switch (field) {
4708
case CDSGeneProt_field_cds_comment:
4709
for (vnp = c->cds_list; vnp != NULL; vnp = vnp->next) {
4710
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4711
if (sfp != NULL && DoesStringMatchConstraint(sfp->comment, scp))
4712
{
4713
rval |= SetStringValue ( &(sfp->comment), value, existing_text);
4714
}
4715
}
4716
break;
4717
case CDSGeneProt_field_gene_locus:
4718
if (c->gene_list == NULL && scp == NULL) {
4719
sfp = CreateGeneForCGPSet (c);
4720
if (sfp != NULL) {
4721
ValNodeAddPointer (&(c->gene_list), 0, sfp);
4722
}
4723
}
4724
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4725
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4726
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4727
&& (grp = sfp->data.value.ptrvalue) != NULL
4728
&& DoesStringMatchConstraint(grp->locus, scp))
4729
{
4730
rval |= SetStringValue ( &(grp->locus), value, existing_text);
4731
}
4732
}
4733
break;
4734
case CDSGeneProt_field_gene_description:
4735
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4736
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4737
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4738
&& (grp = sfp->data.value.ptrvalue) != NULL
4739
&& DoesStringMatchConstraint(grp->desc, scp))
4740
{
4741
rval |= SetStringValue ( &(grp->desc), value, existing_text);
4742
}
4743
}
4744
break;
4745
case CDSGeneProt_field_gene_comment:
4746
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4747
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4748
if (sfp != NULL && DoesStringMatchConstraint(sfp->comment, scp))
4749
{
4750
rval |= SetStringValue ( &(sfp->comment), value, existing_text);
4751
}
4752
}
4753
break;
4754
case CDSGeneProt_field_gene_allele:
4755
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4756
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4757
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4758
&& (grp = sfp->data.value.ptrvalue) != NULL
4759
&& DoesStringMatchConstraint(grp->allele, scp))
4760
{
4761
rval |= SetStringValue (&(grp->allele), value, existing_text);
4762
}
4763
}
4764
break;
4765
case CDSGeneProt_field_gene_maploc:
4766
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4767
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4768
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4769
&& (grp = sfp->data.value.ptrvalue) != NULL
4770
&& DoesStringMatchConstraint(grp->maploc, scp))
4771
{
4772
rval |= SetStringValue ( &(grp->maploc), value, existing_text);
4773
}
4774
}
4775
break;
4776
case CDSGeneProt_field_gene_locus_tag:
4777
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4778
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4779
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4780
&& (grp = sfp->data.value.ptrvalue) != NULL
4781
&& DoesStringMatchConstraint(grp->locus_tag, scp))
4782
{
4783
rval |= SetStringValue ( &(grp->locus_tag), value, existing_text);
4784
}
4785
}
4786
break;
4787
case CDSGeneProt_field_gene_synonym:
4788
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4789
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4790
if (sfp != NULL && sfp->data.choice == SEQFEAT_GENE
4791
&& (grp = sfp->data.value.ptrvalue) != NULL)
4792
{
4793
rval |= SetStringsInValNodeStringList (&(grp->syn), scp, value, existing_text);
4794
}
4795
}
4796
break;
4797
case CDSGeneProt_field_gene_old_locus_tag:
4798
for (vnp = c->gene_list; vnp != NULL; vnp = vnp->next) {
4799
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4800
if (sfp != NULL) {
4801
rval |= RemoveGBQualMatch (&(sfp->qual), "old-locus-tag", scp);
4802
}
4803
}
4804
break;
4805
case CDSGeneProt_field_mrna_product:
4806
for (vnp = c->mrna_list; vnp != NULL; vnp = vnp->next) {
4807
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4808
rval |= SetRNAProductString (sfp, scp, value, existing_text);
4809
}
4810
break;
4811
case CDSGeneProt_field_mrna_comment:
4812
for (vnp = c->mrna_list; vnp != NULL; vnp = vnp->next) {
4813
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4814
if (sfp != NULL&& DoesStringMatchConstraint(sfp->comment, scp))
4815
{
4816
rval |= SetStringValue ( &(sfp->comment), value, existing_text);
4817
}
4818
}
4819
break;
4820
case CDSGeneProt_field_prot_name:
4821
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4822
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4823
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4824
&& sfp->idx.subtype == FEATDEF_PROT
4825
&& (prp = sfp->data.value.ptrvalue) != NULL)
4826
{
4827
rval |= SetStringsInValNodeStringList (&(prp->name), scp, value, existing_text);
4828
}
4829
}
4830
break;
4831
case CDSGeneProt_field_prot_description:
4832
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4833
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4834
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4835
&& sfp->idx.subtype == FEATDEF_PROT
4836
&& (prp = sfp->data.value.ptrvalue) != NULL
4837
&& DoesStringMatchConstraint(prp->desc, scp)) {
4838
rval |= SetStringValue ( &(prp->desc), value, existing_text);
4839
}
4840
}
4841
break;
4842
case CDSGeneProt_field_prot_ec_number:
4843
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4844
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4845
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4846
&& sfp->idx.subtype == FEATDEF_PROT
4847
&& (prp = sfp->data.value.ptrvalue) != NULL)
4848
{
4849
rval |= SetStringsInValNodeStringList (&(prp->ec), scp, value, existing_text);
4850
}
4851
}
4852
break;
4853
case CDSGeneProt_field_prot_activity:
4854
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4855
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4856
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4857
&& sfp->idx.subtype == FEATDEF_PROT
4858
&& (prp = sfp->data.value.ptrvalue) != NULL)
4859
{
4860
rval |= SetStringsInValNodeStringList (&(prp->activity), scp, value, existing_text);
4861
}
4862
}
4863
break;
4864
case CDSGeneProt_field_prot_comment:
4865
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4866
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4867
if (sfp != NULL && sfp->idx.subtype == FEATDEF_PROT
4868
&& DoesStringMatchConstraint(sfp->comment, scp))
4869
{
4870
rval |= SetStringValue ( &(sfp->comment), value, existing_text);
4871
}
4872
}
4873
break;
4874
case CDSGeneProt_field_mat_peptide_name:
4875
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4876
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4877
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4878
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4879
&& (prp = sfp->data.value.ptrvalue) != NULL)
4880
{
4881
rval |= SetStringsInValNodeStringList (&(prp->name), scp, value, existing_text);
4882
}
4883
}
4884
break;
4885
case CDSGeneProt_field_mat_peptide_description:
4886
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4887
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4888
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4889
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4890
&& (prp = sfp->data.value.ptrvalue) != NULL
4891
&& DoesStringMatchConstraint(prp->desc, scp)) {
4892
rval |= SetStringValue ( &(prp->desc), value, existing_text);
4893
}
4894
}
4895
break;
4896
case CDSGeneProt_field_mat_peptide_ec_number:
4897
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4898
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4899
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4900
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4901
&& (prp = sfp->data.value.ptrvalue) != NULL)
4902
{
4903
rval |= SetStringsInValNodeStringList (&(prp->ec), scp, value, existing_text);
4904
}
4905
}
4906
break;
4907
case CDSGeneProt_field_mat_peptide_activity:
4908
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4909
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4910
if (sfp != NULL && sfp->data.choice == SEQFEAT_PROT
4911
&& sfp->idx.subtype == FEATDEF_mat_peptide_aa
4912
&& (prp = sfp->data.value.ptrvalue) != NULL)
4913
{
4914
rval |= SetStringsInValNodeStringList (&(prp->activity), scp, value, existing_text);
4915
}
4916
}
4917
break;
4918
case CDSGeneProt_field_mat_peptide_comment:
4919
for (vnp = c->prot_list; vnp != NULL; vnp = vnp->next) {
4920
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
4921
if (sfp != NULL && sfp->idx.subtype == FEATDEF_mat_peptide_aa
4922
&& DoesStringMatchConstraint(sfp->comment, scp))
4923
{
4924
rval |= SetStringValue ( &(sfp->comment), value, existing_text);
4925
}
4926
}
4927
break;
4928
}
4929
return rval;
4930
}
4931
4932
4933
static MolInfoPtr GetMolInfoForBioseq (BioseqPtr bsp)
4934
{
4935
MolInfoPtr m = NULL;
4936
SeqDescrPtr sdp;
4937
4938
if (bsp == NULL) return NULL;
4939
sdp = bsp->descr;
4940
while (sdp != NULL && sdp->choice != Seq_descr_molinfo) {
4941
sdp = sdp->next;
4942
}
4943
if (sdp != NULL) {
4944
m = (MolInfoPtr) sdp->data.ptrvalue;
4945
}
4946
return m;
4947
}
4948
4949
4950
static CharPtr GetSequenceQualFromBioseq (BioseqPtr bsp, ValNodePtr field)
4951
{
4952
CharPtr rval = NULL;
4953
MolInfoPtr m;
4954
4955
if (bsp == NULL || field == NULL) return NULL;
4956
4957
switch (field->choice) {
4958
case MolinfoField_molecule:
4959
m = GetMolInfoForBioseq (bsp);
4960
if (m != NULL) {
4961
rval = BiomolNameFromBiomol (m->biomol);
4962
}
4963
break;
4964
case MolinfoField_technique:
4965
m = GetMolInfoForBioseq (bsp);
4966
if (m != NULL) {
4967
rval = TechNameFromTech (m->tech);
4968
}
4969
break;
4970
case MolinfoField_completedness:
4971
m = GetMolInfoForBioseq (bsp);
4972
if (m != NULL) {
4973
rval = CompletenessNameFromCompleteness (m->completeness);
4974
}
4975
break;
4976
case MolinfoField_mol_class:
4977
rval = MolNameFromMol (bsp->mol);
4978
break;
4979
case MolinfoField_topology:
4980
rval = TopologyNameFromTopology (bsp->topology);
4981
break;
4982
case MolinfoField_strand:
4983
rval = StrandNameFromStrand (bsp->strand);
4984
break;
4985
}
4986
if (rval != NULL) rval = StringSave (rval);
4987
return rval;
4988
}
4989
4990
4991
static Boolean RemoveSequenceQualFromBioseq (BioseqPtr bsp, ValNodePtr field)
4992
{
4993
MolInfoPtr m;
4994
Boolean rval = FALSE;
4995
4996
if (bsp == NULL || field == NULL) return FALSE;
4997
4998
switch (field->choice) {
4999
case MolinfoField_molecule:
5000
m = GetMolInfoForBioseq (bsp);
5001
if (m != NULL) {
5002
m->biomol = 0;
5003
rval = TRUE;
5004
}
5005
break;
5006
case MolinfoField_technique:
5007
m = GetMolInfoForBioseq (bsp);
5008
if (m != NULL) {
5009
m->tech = 0;
5010
rval = TRUE;
5011
}
5012
break;
5013
case MolinfoField_completedness:
5014
m = GetMolInfoForBioseq (bsp);
5015
if (m != NULL) {
5016
m->completeness = 0;
5017
rval = TRUE;
5018
}
5019
break;
5020
case MolinfoField_mol_class:
5021
bsp->mol = 0;
5022
rval = TRUE;
5023
break;
5024
case MolinfoField_topology:
5025
bsp->topology = 0;
5026
rval = TRUE;
5027
break;
5028
case MolinfoField_strand:
5029
bsp->strand = 0;
5030
rval = TRUE;
5031
break;
5032
}
5033
return rval;
5034
}
5035
5036
5037
static MolInfoPtr AddMolInfoToBioseq (BioseqPtr bsp)
5038
{
5039
SeqDescrPtr sdp;
5040
MolInfoPtr m;
5041
5042
sdp = CreateNewDescriptorOnBioseq (bsp, Seq_descr_molinfo);
5043
m = MolInfoNew ();
5044
sdp->data.ptrvalue = m;
5045
return m;
5046
}
5047
5048
5049
static Boolean SetSequenceQualOnBioseq (BioseqPtr bsp, ValNodePtr field)
5050
{
5051
MolInfoPtr m;
5052
Boolean rval = FALSE;
5053
5054
if (bsp == NULL || field == NULL) return FALSE;
5055
5056
switch (field->choice) {
5057
case MolinfoField_molecule:
5058
m = GetMolInfoForBioseq (bsp);
5059
if (m == NULL) {
5060
m = AddMolInfoToBioseq (bsp);
5061
}
5062
m->biomol = BiomolFromMoleculeType (field->data.intvalue);
5063
rval = TRUE;
5064
break;
5065
case MolinfoField_technique:
5066
m = GetMolInfoForBioseq (bsp);
5067
if (m == NULL) {
5068
m = AddMolInfoToBioseq (bsp);
5069
}
5070
m->tech = TechFromTechniqueType (field->data.intvalue);
5071
rval = TRUE;
5072
break;
5073
case MolinfoField_completedness:
5074
m = GetMolInfoForBioseq (bsp);
5075
if (m == NULL) {
5076
m = AddMolInfoToBioseq (bsp);
5077
}
5078
m->completeness = CompletenessFromCompletednessType (field->data.intvalue);
5079
rval = TRUE;
5080
break;
5081
case MolinfoField_mol_class:
5082
bsp->mol = MolFromMoleculeClassType (field->data.intvalue);
5083
rval = TRUE;
5084
break;
5085
case MolinfoField_topology:
5086
bsp->topology = TopologyFromTopologyType (field->data.intvalue);
5087
rval = TRUE;
5088
break;
5089
case MolinfoField_strand:
5090
bsp->strand = StrandFromStrandType (field->data.intvalue);
5091
rval = TRUE;
5092
break;
5093
}
5094
return rval;
5095
}
5096
5097
5098
NLM_EXTERN FieldTypePtr GetFromFieldFromFieldPair (FieldPairTypePtr fieldpair)
5099
{
5100
SourceQualChoicePtr ss = NULL;
5101
SourceQualPairPtr sqpp;
5102
FeatureFieldPairPtr fp;
5103
FeatureFieldPtr fs;
5104
FieldTypePtr f = NULL;
5105
CDSGeneProtFieldPairPtr cp;
5106
MolinfoFieldPairPtr mp;
5107
ValNodePtr vnp;
5108
5109
if (fieldpair == NULL) return NULL;
5110
switch (fieldpair->choice) {
5111
case FieldPairType_source_qual:
5112
sqpp = (SourceQualPairPtr) fieldpair->data.ptrvalue;
5113
if (sqpp != NULL) {
5114
ss = ValNodeNew (NULL);
5115
ss->choice = SourceQualChoice_textqual;
5116
ss->data.intvalue = sqpp->field_from;
5117
f = ValNodeNew (NULL);
5118
f->choice = FieldType_source_qual;
5119
f->data.ptrvalue = ss;
5120
}
5121
break;
5122
case FieldPairType_feature_field:
5123
fp = (FeatureFieldPairPtr) fieldpair->data.ptrvalue;
5124
if (fp != NULL) {
5125
fs = FeatureFieldNew ();
5126
fs->type = fp->type;
5127
fs->field = (FeatQualChoicePtr) AsnIoMemCopy (fp->field_from, (AsnReadFunc) FeatQualChoiceAsnRead, (AsnWriteFunc) FeatQualChoiceAsnWrite);
5128
f = ValNodeNew (NULL);
5129
f->choice = FieldType_feature_field;
5130
f->data.ptrvalue = fs;
5131
}
5132
break;
5133
case FieldPairType_cds_gene_prot:
5134
cp = (CDSGeneProtFieldPairPtr) fieldpair->data.ptrvalue;
5135
if (cp != NULL) {
5136
f = ValNodeNew (NULL);
5137
f->choice = FieldType_cds_gene_prot;
5138
f->data.intvalue = cp->field_from;
5139
}
5140
break;
5141
case FieldPairType_molinfo_field:
5142
mp = (MolinfoFieldPairPtr) fieldpair->data.ptrvalue;
5143
if (mp != NULL && mp->data.ptrvalue != NULL) {
5144
vnp = NULL;
5145
switch (mp->choice) {
5146
case MolinfoFieldPair_molecule:
5147
vnp = ValNodeNew (NULL);
5148
vnp->choice = MolinfoField_molecule;
5149
vnp->data.intvalue = ((MolinfoMoleculePairPtr)mp->data.ptrvalue)->from;
5150
break;
5151
case MolinfoFieldPair_technique:
5152
vnp = ValNodeNew (NULL);
5153
vnp->choice = MolinfoField_technique;
5154
vnp->data.intvalue = ((MolinfoTechniquePairPtr)mp->data.ptrvalue)->from;
5155
break;
5156
case MolinfoFieldPair_completedness:
5157
vnp = ValNodeNew (NULL);
5158
vnp->choice = MolinfoField_completedness;
5159
vnp->data.intvalue = ((MolinfoCompletednessPairPtr)mp->data.ptrvalue)->from;
5160
break;
5161
case MolinfoFieldPair_mol_class:
5162
vnp = ValNodeNew (NULL);
5163
vnp->choice = MolinfoField_mol_class;
5164
vnp->data.intvalue = ((MolinfoMolClassPairPtr)mp->data.ptrvalue)->from;
5165
break;
5166
case MolinfoFieldPair_topology:
5167
vnp = ValNodeNew (NULL);
5168
vnp->choice = MolinfoField_topology;
5169
vnp->data.intvalue = ((MolinfoTopologyPairPtr)mp->data.ptrvalue)->from;
5170
break;
5171
case MolinfoFieldPair_strand:
5172
vnp = ValNodeNew (NULL);
5173
vnp->choice = MolinfoField_strand;
5174
vnp->data.intvalue = ((MolinfoStrandPairPtr)mp->data.ptrvalue)->from;
5175
break;
5176
}
5177
if (vnp != NULL) {
5178
f = ValNodeNew (NULL);
5179
f->choice = FieldType_molinfo_field;
5180
f->data.ptrvalue = vnp;
5181
}
5182
}
5183
break;
5184
}
5185
return f;
5186
}
5187
5188
5189
NLM_EXTERN FieldTypePtr GetToFieldFromFieldPair (FieldPairTypePtr fieldpair)
5190
{
5191
SourceQualChoicePtr ss = NULL;
5192
SourceQualPairPtr sqpp;
5193
FeatureFieldPairPtr fp;
5194
FeatureFieldPtr fs;
5195
FieldTypePtr f = NULL;
5196
CDSGeneProtFieldPairPtr cp;
5197
MolinfoFieldPairPtr mp;
5198
ValNodePtr vnp;
5199
5200
if (fieldpair == NULL) return NULL;
5201
switch (fieldpair->choice) {
5202
case FieldPairType_source_qual:
5203
sqpp = (SourceQualPairPtr) fieldpair->data.ptrvalue;
5204
if (sqpp != NULL) {
5205
ss = ValNodeNew (NULL);
5206
ss->choice = SourceQualChoice_textqual;
5207
ss->data.intvalue = sqpp->field_to;
5208
f = ValNodeNew (NULL);
5209
f->choice = FieldType_source_qual;
5210
f->data.ptrvalue = ss;
5211
}
5212
break;
5213
case FieldPairType_feature_field:
5214
fp = (FeatureFieldPairPtr) fieldpair->data.ptrvalue;
5215
if (fp != NULL) {
5216
fs = FeatureFieldNew ();
5217
fs->type = fp->type;
5218
fs->field = (FeatQualChoicePtr) AsnIoMemCopy (fp->field_to, (AsnReadFunc) FeatQualChoiceAsnRead, (AsnWriteFunc) FeatQualChoiceAsnWrite);
5219
f = ValNodeNew (NULL);
5220
f->choice = FieldType_feature_field;
5221
f->data.ptrvalue = fs;
5222
}
5223
break;
5224
case FieldPairType_cds_gene_prot:
5225
cp = (CDSGeneProtFieldPairPtr) fieldpair->data.ptrvalue;
5226
if (cp != NULL) {
5227
f = ValNodeNew (NULL);
5228
f->choice = FieldType_cds_gene_prot;
5229
f->data.intvalue = cp->field_to;
5230
}
5231
break;
5232
case FieldPairType_molinfo_field:
5233
mp = (MolinfoFieldPairPtr) fieldpair->data.ptrvalue;
5234
if (mp != NULL && mp->data.ptrvalue != NULL) {
5235
vnp = NULL;
5236
switch (mp->choice) {
5237
case MolinfoFieldPair_molecule:
5238
vnp = ValNodeNew (NULL);
5239
vnp->choice = MolinfoField_molecule;
5240
vnp->data.intvalue = ((MolinfoMoleculePairPtr)mp->data.ptrvalue)->to;
5241
break;
5242
case MolinfoFieldPair_technique:
5243
vnp = ValNodeNew (NULL);
5244
vnp->choice = MolinfoField_technique;
5245
vnp->data.intvalue = ((MolinfoTechniquePairPtr)mp->data.ptrvalue)->to;
5246
break;
5247
case MolinfoFieldPair_completedness:
5248
vnp = ValNodeNew (NULL);
5249
vnp->choice = MolinfoField_completedness;
5250
vnp->data.intvalue = ((MolinfoCompletednessPairPtr)mp->data.ptrvalue)->to;
5251
break;
5252
case MolinfoFieldPair_mol_class:
5253
vnp = ValNodeNew (NULL);
5254
vnp->choice = MolinfoField_mol_class;
5255
vnp->data.intvalue = ((MolinfoMolClassPairPtr)mp->data.ptrvalue)->to;
5256
break;
5257
case MolinfoFieldPair_topology:
5258
vnp = ValNodeNew (NULL);
5259
vnp->choice = MolinfoField_topology;
5260
vnp->data.intvalue = ((MolinfoTopologyPairPtr)mp->data.ptrvalue)->to;
5261
break;
5262
case MolinfoFieldPair_strand:
5263
vnp = ValNodeNew (NULL);
5264
vnp->choice = MolinfoField_strand;
5265
vnp->data.intvalue = ((MolinfoStrandPairPtr)mp->data.ptrvalue)->to;
5266
break;
5267
}
5268
if (vnp != NULL) {
5269
f = ValNodeNew (NULL);
5270
f->choice = FieldType_molinfo_field;
5271
f->data.ptrvalue = vnp;
5272
}
5273
}
5274
break;
5275
}
5276
return f;
5277
}
5278
5279
5280
static Uint1 FieldTypeChoiceFromFieldPairTypeChoice (Uint1 field_pair_choice)
5281
{
5282
Uint1 field_type_choice = 0;
5283
5284
switch (field_pair_choice) {
5285
case FieldPairType_source_qual:
5286
field_type_choice = FieldType_source_qual;
5287
break;
5288
case FieldPairType_feature_field:
5289
field_type_choice = FieldType_feature_field;
5290
break;
5291
case FieldPairType_cds_gene_prot:
5292
field_type_choice = FieldType_cds_gene_prot;
5293
break;
5294
case FieldPairType_molinfo_field:
5295
field_type_choice = FieldType_molinfo_field;
5296
break;
5297
}
5298
5299
return field_type_choice;
5300
}
5301
5302
5303
NLM_EXTERN Uint1 FieldTypeFromAECRAction (AECRActionPtr action)
5304
{
5305
Uint1 field_type = 0;
5306
ApplyActionPtr a;
5307
EditActionPtr e;
5308
ConvertActionPtr v;
5309
CopyActionPtr c;
5310
SwapActionPtr s;
5311
RemoveActionPtr r;
5312
AECRParseActionPtr p;
5313
5314
if (action == NULL || action->action == NULL || action->action->data.ptrvalue == NULL) {
5315
return 0;
5316
}
5317
switch (action->action->choice) {
5318
case ActionChoice_apply:
5319
a = (ApplyActionPtr) action->action->data.ptrvalue;
5320
if (a->field != NULL) {
5321
field_type = a->field->choice;
5322
}
5323
break;
5324
case ActionChoice_edit:
5325
e = (EditActionPtr) action->action->data.ptrvalue;
5326
if (e->field != NULL) {
5327
field_type = e->field->choice;
5328
}
5329
break;
5330
case ActionChoice_convert:
5331
v = (ConvertActionPtr) action->action->data.ptrvalue;
5332
field_type = FieldTypeChoiceFromFieldPairTypeChoice (v->fields->choice);
5333
break;
5334
case ActionChoice_copy:
5335
c = (CopyActionPtr) action->action->data.ptrvalue;
5336
field_type = FieldTypeChoiceFromFieldPairTypeChoice (c->fields->choice);
5337
break;
5338
case ActionChoice_swap:
5339
s = (SwapActionPtr) action->action->data.ptrvalue;
5340
field_type = FieldTypeChoiceFromFieldPairTypeChoice (s->fields->choice);
5341
break;
5342
case ActionChoice_remove:
5343
r = (RemoveActionPtr) action->action->data.ptrvalue;
5344
if (r->field != NULL) {
5345
field_type = r->field->choice;
5346
}
5347
break;
5348
case ActionChoice_parse:
5349
p = (AECRParseActionPtr) action->action->data.ptrvalue;
5350
field_type = FieldTypeChoiceFromFieldPairTypeChoice (p->fields->choice);
5351
break;
5352
}
5353
return field_type;
5354
}
5355
5356
5357
static CharPtr GetFieldValueForObject (Uint1 choice, Pointer data, FieldTypePtr field, StringConstraintPtr scp)
5358
{
5359
CharPtr str = NULL;
5360
FeatureFieldPtr feature_field;
5361
5362
if (data == NULL || field == NULL || field->data.ptrvalue == NULL) return FALSE;
5363
5364
switch (field->choice) {
5365
case FieldType_source_qual :
5366
str = GetSourceQualFromBioSource (GetBioSourceFromObject (choice, data), (SourceQualChoicePtr) field->data.ptrvalue, scp);
5367
break;
5368
case FieldType_feature_field :
5369
if (choice == OBJ_SEQFEAT) {
5370
str = GetQualFromFeature ((SeqFeatPtr) data, (FeatureFieldPtr) field->data.ptrvalue, scp);
5371
}
5372
break;
5373
case FieldType_cds_gene_prot :
5374
if (choice == 0) {
5375
str = GetFieldValueFromCGPSet ((CGPSetPtr) data, field->data.intvalue, scp);
5376
} else if (choice == OBJ_SEQFEAT) {
5377
feature_field = FeatureFieldFromCDSGeneProtField (field->data.intvalue);
5378
str = GetQualFromFeature ((SeqFeatPtr) data, feature_field, scp);
5379
feature_field = FeatureFieldFree (feature_field);
5380
}
5381
break;
5382
case FieldType_molinfo_field :
5383
if (choice == OBJ_BIOSEQ) {
5384
str = GetSequenceQualFromBioseq ((BioseqPtr) data, field->data.ptrvalue);
5385
}
5386
break;
5387
}
5388
return str;
5389
}
5390
5391
5392
static Boolean RemoveFieldValueForObject (Uint1 choice, Pointer data, FieldTypePtr field, StringConstraintPtr scp)
5393
{
5394
Boolean rval = FALSE;
5395
FeatureFieldPtr feature_field;
5396
5397
if (data == NULL || field == NULL || field->data.ptrvalue == NULL) return FALSE;
5398
5399
switch (field->choice) {
5400
case FieldType_source_qual :
5401
rval = RemoveSourceQualFromBioSource (GetBioSourceFromObject (choice, data), (SourceQualChoicePtr) field->data.ptrvalue, scp);
5402
break;
5403
case FieldType_feature_field :
5404
if (choice == OBJ_SEQFEAT) {
5405
rval = RemoveQualFromFeature ((SeqFeatPtr) data, (FeatureFieldPtr) field->data.ptrvalue, scp);
5406
}
5407
break;
5408
case FieldType_cds_gene_prot:
5409
if (choice == 0) {
5410
rval = RemoveFieldValueFromCGPSet ((CGPSetPtr) data, field->data.intvalue, scp);
5411
} else if (choice == OBJ_SEQFEAT) {
5412
feature_field = FeatureFieldFromCDSGeneProtField (field->data.intvalue);
5413
rval = RemoveQualFromFeature ((SeqFeatPtr) data, feature_field, scp);
5414
feature_field = FeatureFieldFree (feature_field);
5415
}
5416
break;
5417
case FieldType_molinfo_field :
5418
if (choice == OBJ_BIOSEQ) {
5419
rval = RemoveSequenceQualFromBioseq ((BioseqPtr) data, field->data.ptrvalue);
5420
}
5421
break;
5422
}
5423
return rval;
5424
}
5425
5426
5427
static Boolean SetFieldValueForObject (Uint1 choice, Pointer data, FieldTypePtr field, StringConstraintPtr scp, CharPtr value, Uint2 existing_text)
5428
{
5429
Boolean rval = FALSE;
5430
FeatureFieldPtr feature_field;
5431
5432
if (data == NULL || field == NULL || field->data.ptrvalue == NULL) return FALSE;
5433
5434
switch (field->choice) {
5435
case FieldType_source_qual :
5436
rval = SetSourceQualInBioSource (GetBioSourceFromObject (choice, data), (SourceQualChoicePtr) field->data.ptrvalue, scp, value, existing_text);
5437
break;
5438
case FieldType_feature_field :
5439
if (choice == OBJ_SEQFEAT) {
5440
rval = SetQualOnFeature ((SeqFeatPtr) data, (FeatureFieldPtr) field->data.ptrvalue, scp, value, existing_text);
5441
}
5442
break;
5443
case FieldType_cds_gene_prot:
5444
if (choice == 0) {
5445
rval = SetFieldValueInCGPSet ((CGPSetPtr) data, field->data.intvalue, scp, value, existing_text);
5446
} else if (choice == OBJ_SEQFEAT) {
5447
feature_field = FeatureFieldFromCDSGeneProtField (field->data.intvalue);
5448
rval = SetQualOnFeature ((SeqFeatPtr) data, feature_field, scp, value, existing_text);
5449
feature_field = FeatureFieldFree (feature_field);
5450
}
5451
break;
5452
case FieldType_molinfo_field:
5453
if (choice == OBJ_BIOSEQ) {
5454
rval = SetSequenceQualOnBioseq ((BioseqPtr) data, field->data.ptrvalue);
5455
}
5456
break;
5457
}
5458
return rval;
5459
}
5460
5461
5462
static Boolean IsObjectAppropriateForFieldValue (Uint1 choice, Pointer data, FieldTypePtr field)
5463
{
5464
SeqFeatPtr sfp;
5465
SeqDescrPtr sdp;
5466
FeatureFieldPtr fp;
5467
Boolean rval = FALSE;
5468
5469
if (data == NULL || field == NULL) return FALSE;
5470
5471
switch (field->choice) {
5472
case FieldType_source_qual :
5473
if (choice == OBJ_SEQFEAT) {
5474
sfp = (SeqFeatPtr) data;
5475
if (sfp->data.choice == SEQFEAT_BIOSRC) {
5476
rval = TRUE;
5477
}
5478
} else if (choice == OBJ_SEQDESC) {
5479
sdp = (SeqDescrPtr) data;
5480
if (sdp->choice == Seq_descr_source) {
5481
rval = TRUE;
5482
}
5483
}
5484
break;
5485
case FieldType_feature_field :
5486
if (choice == OBJ_SEQFEAT) {
5487
sfp = (SeqFeatPtr) data;
5488
fp = (FeatureFieldPtr) field->data.ptrvalue;
5489
if (fp != NULL && (fp->type == Feature_type_any || GetFeatdefFromFeatureType (fp->type) == sfp->idx.subtype)) {
5490
rval = TRUE;
5491
}
5492
}
5493
break;
5494
case FieldType_cds_gene_prot :
5495
if (choice == 0) {
5496
rval = TRUE;
5497
}
5498
break;
5499
case FieldType_molinfo_field :
5500
if (choice == OBJ_BIOSEQ) {
5501
rval = TRUE;
5502
}
5503
break;
5504
}
5505
return rval;
5506
}
5507
5508
5509
static Boolean IsObjectAppropriateForFieldPair (Uint1 choice, Pointer data, FieldPairTypePtr fieldpair)
5510
{
5511
FieldTypePtr f;
5512
Boolean rval;
5513
5514
f = GetFromFieldFromFieldPair(fieldpair);
5515
rval = IsObjectAppropriateForFieldValue(choice, data, f);
5516
f = FieldTypeFree (f);
5517
return rval;
5518
}
5519
5520
5521
static Boolean DoFieldTypesMatch (FieldTypePtr field1, FieldTypePtr field2)
5522
{
5523
Boolean rval = FALSE;
5524
SourceQualChoicePtr scp1, scp2;
5525
FeatureFieldPtr fp1, fp2;
5526
5527
if (field1 == NULL || field2 == NULL) return FALSE;
5528
if (field1->choice != field2->choice) return FALSE;
5529
5530
switch (field1->choice) {
5531
case FieldType_source_qual :
5532
scp1 = (SourceQualChoicePtr) field1->data.ptrvalue;
5533
scp2 = (SourceQualChoicePtr) field2->data.ptrvalue;
5534
if (scp1 != NULL && scp2 != NULL && scp1->choice == scp2->choice) {
5535
switch (scp1->choice) {
5536
case SourceQualChoice_textqual:
5537
if (scp1->data.intvalue == scp2->data.intvalue) {
5538
rval = TRUE;
5539
}
5540
break;
5541
case SourceQualChoice_location:
5542
case SourceQualChoice_origin:
5543
rval = TRUE;
5544
break;
5545
}
5546
}
5547
break;
5548
case FieldType_feature_field :
5549
fp1 = (FeatureFieldPtr) field1->data.ptrvalue;
5550
fp2 = (FeatureFieldPtr) field2->data.ptrvalue;
5551
if (fp1 != NULL && fp2 != NULL
5552
&& (fp1->type == fp2->type || fp1->type == Feature_type_any || fp2->type == Feature_type_any)
5553
&& fp1->field != NULL && fp2->field != NULL
5554
&& fp1->field->choice == FeatQualChoice_legal_qual && fp2->field->choice == FeatQualChoice_legal_qual
5555
&& fp1->field->data.intvalue == fp2->field->data.intvalue) {
5556
rval = TRUE;
5557
}
5558
break;
5559
case FieldType_cds_gene_prot :
5560
if (field1->data.intvalue == field2->data.intvalue) {
5561
rval = TRUE;
5562
}
5563
break;
5564
}
5565
return rval;
5566
}
5567
5568
5569
static Boolean IsNonTextSourceQualPresent (BioSourcePtr biop, Int4 srcqual)
5570
{
5571
Int4 orgmod_subtype, subsrc_subtype;
5572
OrgModPtr mod;
5573
SubSourcePtr ssp;
5574
Boolean rval = FALSE;
5575
5576
if (biop == NULL) return FALSE;
5577
5578
orgmod_subtype = GetOrgModQualFromSrcQual (srcqual);
5579
if (orgmod_subtype == -1) {
5580
subsrc_subtype = GetSubSrcQualFromSrcQual (srcqual);
5581
for (ssp = biop->subtype; ssp != NULL && !rval; ssp = ssp->next) {
5582
if (ssp->subtype == subsrc_subtype) {
5583
rval = TRUE;
5584
}
5585
}
5586
} else {
5587
if (biop->org != NULL && biop->org->orgname != NULL) {
5588
for (mod = biop->org->orgname->mod; mod != NULL && !rval; mod = mod->next) {
5589
if (mod->subtype == orgmod_subtype) {
5590
rval = TRUE;
5591
}
5592
}
5593
}
5594
}
5595
return rval;
5596
}
5597
5598
5599
static Boolean IsSourceQualPresent (BioSourcePtr biop, SourceQualChoicePtr scp)
5600
{
5601
Boolean rval = FALSE;
5602
CharPtr str;
5603
5604
if (biop == NULL) return FALSE;
5605
if (scp == NULL) return TRUE;
5606
5607
switch (scp->choice) {
5608
case SourceQualChoice_textqual:
5609
if (IsNonTextSourceQual (scp->data.intvalue)) {
5610
rval = IsNonTextSourceQualPresent (biop, scp->data.intvalue);
5611
} else {
5612
str = GetSourceQualFromBioSource (biop, scp, NULL);
5613
if (!StringHasNoText (str)) {
5614
rval = TRUE;
5615
}
5616
str = MemFree (str);
5617
}
5618
break;
5619
case SourceQualChoice_location:
5620
if (biop->genome != 0) {
5621
rval = TRUE;
5622
}
5623
break;
5624
case SourceQualChoice_origin:
5625
if (biop->origin != 0) {
5626
rval = TRUE;
5627
}
5628
break;
5629
}
5630
return rval;
5631
}
5632
5633
5634
typedef struct objecthasstring
5635
{
5636
StringConstraintPtr scp;
5637
Boolean found;
5638
} ObjectHasStringData, PNTR ObjectHasStringPtr;
5639
5640
5641
static void LIBCALLBACK AsnWriteConstraintCallBack (AsnExpOptStructPtr pAEOS)
5642
5643
{
5644
CharPtr pchSource;
5645
ObjectHasStringPtr ohsp;
5646
5647
ohsp = (ObjectHasStringPtr) pAEOS->data;
5648
if (ISA_STRINGTYPE (AsnFindBaseIsa (pAEOS->atp)))
5649
{
5650
pchSource = (CharPtr) pAEOS->dvp->ptrvalue;
5651
ohsp->found |= DoesSingleStringMatchConstraint (pchSource, ohsp->scp);
5652
}
5653
}
5654
5655
5656
static Boolean DoesObjectMatchStringConstraint (Uint1 choice, Pointer data, StringConstraintPtr scp)
5657
5658
{
5659
ObjMgrPtr omp;
5660
ObjMgrTypePtr omtp;
5661
AsnIoPtr aip;
5662
AsnExpOptPtr aeop;
5663
ObjectHasStringData ohsd;
5664
SeqFeatPtr sfp, prot;
5665
SeqMgrFeatContext fcontext;
5666
CharPtr search_txt;
5667
CGPSetPtr c;
5668
ValNodePtr vnp;
5669
Boolean all_match = TRUE, any_match = FALSE, rval;
5670
BioseqPtr protbsp;
5671
5672
if (data == NULL) return FALSE;
5673
if (scp == NULL) return TRUE;
5674
5675
if (choice == 0) {
5676
/* CDS-Gene-Prot set */
5677
c = (CGPSetPtr) data;
5678
for (vnp = c->gene_list; vnp != NULL && (!any_match || all_match); vnp = vnp->next) {
5679
if (DoesObjectMatchStringConstraint (OBJ_SEQFEAT, vnp->data.ptrvalue, scp)) {
5680
any_match = TRUE;
5681
} else {
5682
all_match = FALSE;
5683
}
5684
}
5685
for (vnp = c->cds_list; vnp != NULL && (!any_match || all_match); vnp = vnp->next) {
5686
if (DoesObjectMatchStringConstraint (OBJ_SEQFEAT, vnp->data.ptrvalue, scp)) {
5687
any_match = TRUE;
5688
} else {
5689
all_match = FALSE;
5690
}
5691
}
5692
for (vnp = c->mrna_list; vnp != NULL && (!any_match || all_match); vnp = vnp->next) {
5693
if (DoesObjectMatchStringConstraint (OBJ_SEQFEAT, vnp->data.ptrvalue, scp)) {
5694
any_match = TRUE;
5695
} else {
5696
all_match = FALSE;
5697
}
5698
}
5699
for (vnp = c->prot_list; vnp != NULL && (!any_match || all_match); vnp = vnp->next) {
5700
if (DoesObjectMatchStringConstraint (OBJ_SEQFEAT, vnp->data.ptrvalue, scp)) {
5701
any_match = TRUE;
5702
} else {
5703
all_match = FALSE;
5704
}
5705
}
5706
if (scp->not_present) {
5707
rval = all_match;
5708
} else {
5709
rval = any_match;
5710
}
5711
} else {
5712
omp = ObjMgrGet ();
5713
omtp = ObjMgrTypeFind (omp, choice, NULL, NULL);
5714
if (omtp == NULL) return FALSE;
5715
aip = AsnIoNullOpen ();
5716
aeop = AsnExpOptNew (aip, NULL, NULL, AsnWriteConstraintCallBack);
5717
ohsd.found = FALSE;
5718
ohsd.scp = scp;
5719
if (aeop != NULL) {
5720
aeop->user_data = (Pointer) &ohsd;
5721
}
5722
5723
(omtp->asnwrite) (data, aip, NULL);
5724
5725
if (!ohsd.found && omtp->datatype == OBJ_SEQFEAT)
5726
{
5727
sfp = (SeqFeatPtr) data;
5728
if (sfp->data.choice == SEQFEAT_CDREGION) {
5729
protbsp = BioseqFindFromSeqLoc (sfp->product);
5730
prot = SeqMgrGetNextFeature (protbsp, NULL, 0, FEATDEF_PROT, &fcontext);
5731
if (prot != NULL) {
5732
(omtp->asnwrite) (prot, aip, NULL);
5733
}
5734
} else {
5735
if (SeqMgrFeaturesAreIndexed(sfp->idx.entityID) == 0) {
5736
SeqMgrIndexFeatures (sfp->idx.entityID, NULL);
5737
}
5738
if (sfp->idx.subtype == FEATDEF_tRNA) {
5739
sfp = SeqMgrGetDesiredFeature (sfp->idx.entityID, NULL, sfp->idx.itemID, 0, sfp, &fcontext);
5740
ohsd.found = DoesSingleStringMatchConstraint (fcontext.label, ohsd.scp);
5741
if (!ohsd.found && sfp != NULL && sfp->idx.subtype == FEATDEF_tRNA)
5742
{
5743
search_txt = (CharPtr) MemNew ((StringLen (fcontext.label) + 6) * sizeof (Char));
5744
if (search_txt != NULL)
5745
{
5746
sprintf (search_txt, "tRNA-%s", fcontext.label);
5747
ohsd.found = DoesSingleStringMatchConstraint (search_txt, ohsd.scp);
5748
search_txt = MemFree (search_txt);
5749
}
5750
}
5751
}
5752
}
5753
}
5754
AsnIoClose (aip);
5755
if (scp->not_present) {
5756
rval = !ohsd.found;
5757
} else {
5758
rval = ohsd.found;
5759
}
5760
}
5761
return rval;
5762
}
5763
5764
5765
NLM_EXTERN Boolean IsSourceConstraintEmpty (SourceConstraintPtr scp)
5766
{
5767
if (scp == NULL) return TRUE;
5768
5769
if (scp->field1 == NULL
5770
&& scp->field2 == NULL
5771
&& IsStringConstraintEmpty(scp->constraint)) {
5772
return TRUE;
5773
} else {
5774
return FALSE;
5775
}
5776
}
5777
5778
NLM_EXTERN Boolean DoesBiosourceMatchConstraint (BioSourcePtr biop, SourceConstraintPtr scp)
5779
{
5780
Boolean rval = FALSE;
5781
CharPtr str1, str2;
5782
ValNode vn;
5783
5784
if (biop == NULL) return FALSE;
5785
if (scp == NULL) return TRUE;
5786
5787
if (IsStringConstraintEmpty(scp->constraint)) {
5788
/* looking for qual present */
5789
if (scp->field1 != NULL && scp->field2 == NULL) {
5790
rval = IsSourceQualPresent (biop, scp->field1);
5791
} else if (scp->field2 != NULL && scp->field1 == NULL) {
5792
rval = IsSourceQualPresent (biop, scp->field2);
5793
/* looking for quals to match */
5794
} else if (scp->field1 != NULL && scp->field2 != NULL) {
5795
str1 = GetSourceQualFromBioSource (biop, scp->field1, NULL);
5796
str2 = GetSourceQualFromBioSource (biop, scp->field2, NULL);
5797
if (StringCmp (str1, str2) == 0) {
5798
rval = TRUE;
5799
}
5800
str1 = MemFree (str1);
5801
str2 = MemFree (str2);
5802
} else {
5803
/* nothing specified, automatic match */
5804
rval = TRUE;
5805
}
5806
} else {
5807
if (scp->field1 != NULL && scp->field2 == NULL) {
5808
str1 = GetSourceQualFromBioSource (biop, scp->field1, scp->constraint);
5809
if (str1 == NULL) {
5810
if (scp->constraint->not_present) {
5811
str1 = GetSourceQualFromBioSource (biop, scp->field1, NULL);
5812
if (str1 == NULL) {
5813
rval = TRUE;
5814
}
5815
}
5816
} else if (!StringHasNoText (str1)) {
5817
rval = TRUE;
5818
}
5819
str1 = MemFree (str1);
5820
} else if (scp->field2 != NULL && scp->field1 == NULL) {
5821
str2 = GetSourceQualFromBioSource (biop, scp->field2, scp->constraint);
5822
if (str2 == NULL) {
5823
if (scp->constraint->not_present) {
5824
str2 = GetSourceQualFromBioSource (biop, scp->field2, NULL);
5825
if (str2 == NULL) {
5826
rval = TRUE;
5827
}
5828
}
5829
} else if (!StringHasNoText (str2)) {
5830
rval = TRUE;
5831
}
5832
str2 = MemFree (str2);
5833
} else if (scp->field1 != NULL && scp->field2 != NULL) {
5834
str1 = GetSourceQualFromBioSource (biop, scp->field1, scp->constraint);
5835
str2 = GetSourceQualFromBioSource (biop, scp->field2, scp->constraint);
5836
if (StringCmp (str1, str2) == 0) {
5837
rval = TRUE;
5838
}
5839
str1 = MemFree (str1);
5840
str2 = MemFree (str2);
5841
} else {
5842
/* generic string constraint */
5843
vn.choice = Seq_descr_source;
5844
vn.next = NULL;
5845
vn.extended = 0;
5846
vn.data.ptrvalue = biop;
5847
rval = DoesObjectMatchStringConstraint (OBJ_SEQDESC, &vn, scp->constraint);
5848
}
5849
}
5850
return rval;
5851
}
5852
5853
5854
static Boolean DoesCGPSetMatchPseudoConstraint (CGPSetPtr c, CDSGeneProtPseudoConstraintPtr constraint)
5855
{
5856
Boolean any_pseudo = FALSE;
5857
ValNodePtr vnp;
5858
SeqFeatPtr sfp;
5859
Boolean rval = FALSE;
5860
5861
if (c == NULL) return FALSE;
5862
if (constraint == NULL) return TRUE;
5863
5864
switch (constraint->feature) {
5865
case CDSGeneProt_feature_type_constraint_gene :
5866
for (vnp = c->gene_list; vnp != NULL && !any_pseudo; vnp = vnp->next) {
5867
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
5868
if (sfp != NULL && sfp->pseudo) {
5869
any_pseudo = TRUE;
5870
}
5871
}
5872
break;
5873
case CDSGeneProt_feature_type_constraint_mRNA :
5874
for (vnp = c->mrna_list; vnp != NULL && !any_pseudo; vnp = vnp->next) {
5875
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
5876
if (sfp != NULL && sfp->pseudo) {
5877
any_pseudo = TRUE;
5878
}
5879
}
5880
break;
5881
case CDSGeneProt_feature_type_constraint_cds :
5882
for (vnp = c->mrna_list; vnp != NULL && !any_pseudo; vnp = vnp->next) {
5883
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
5884
if (sfp != NULL && sfp->pseudo) {
5885
any_pseudo = TRUE;
5886
}
5887
}
5888
break;
5889
case CDSGeneProt_feature_type_constraint_prot :
5890
for (vnp = c->mrna_list; vnp != NULL && !any_pseudo; vnp = vnp->next) {
5891
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
5892
if (sfp != NULL && sfp->pseudo && sfp->idx.subtype == FEATDEF_PROT) {
5893
any_pseudo = TRUE;
5894
}
5895
}
5896
break;
5897
case CDSGeneProt_feature_type_constraint_mat_peptide :
5898
for (vnp = c->mrna_list; vnp != NULL && !any_pseudo; vnp = vnp->next) {
5899
sfp = (SeqFeatPtr) vnp->data.ptrvalue;
5900
if (sfp != NULL && sfp->pseudo && sfp->idx.subtype == FEATDEF_mat_peptide_aa) {
5901
any_pseudo = TRUE;
5902
}
5903
}
5904
break;
5905
}
5906
5907
if ((any_pseudo && constraint->is_pseudo)
5908
|| (!any_pseudo && !constraint->is_pseudo)) {
5909
rval = TRUE;
5910
}
5911
return rval;
5912
}
5913
5914
5915
NLM_EXTERN Boolean IsCDSGeneProtQualConstraintEmpty (CDSGeneProtQualConstraintPtr constraint)
5916
{
5917
if (constraint == NULL) return TRUE;
5918
if (constraint->field1 == NULL && constraint->field2 == NULL && IsStringConstraintEmpty (constraint->constraint)) {
5919
return TRUE;
5920
} else {
5921
return FALSE;
5922
}
5923
}
5924
5925
5926
static Boolean DoesCGPSetMatchQualConstraint (CGPSetPtr c, CDSGeneProtQualConstraintPtr constraint)
5927
{
5928
Boolean rval = FALSE, any_match = FALSE, all_match = TRUE;
5929
CharPtr str, str1, str2;
5930
5931
if (c == NULL) return FALSE;
5932
if (constraint == NULL) return TRUE;
5933
5934
if (IsStringConstraintEmpty (constraint->constraint)) {
5935
/* looking for qual present */
5936
if (constraint->field1 != NULL && constraint->field2 == NULL) {
5937
str = GetFieldValueFromCGPSet (c, constraint->field1->data.intvalue, NULL);
5938
if (str != NULL) {
5939
rval = TRUE;
5940
str = MemFree (str);
5941
}
5942
} else if (constraint->field2 != NULL && constraint->field1 == NULL) {
5943
str = GetFieldValueFromCGPSet (c, constraint->field2->data.intvalue, NULL);
5944
if (str == NULL) {
5945
rval = FALSE;
5946
} else {
5947
str = MemFree (str);
5948
}
5949
/* looking for quals to match */
5950
} else if (constraint->field1 != NULL && constraint->field2 != NULL) {
5951
str1 = GetFieldValueFromCGPSet (c, constraint->field1->data.intvalue, NULL);
5952
str2 = GetFieldValueFromCGPSet (c, constraint->field2->data.intvalue, NULL);
5953
if (StringCmp (str1, str2) == 0) {
5954
rval = TRUE;
5955
}
5956
str1 = MemFree (str1);
5957
str2 = MemFree (str2);
5958
} else {
5959
/* nothing specified, automatic match */
5960
rval = TRUE;
5961
}
5962
} else {
5963
if (constraint->field1 != NULL && constraint->field2 == NULL) {
5964
str1 = GetFieldValueFromCGPSet (c, constraint->field1->data.intvalue, constraint->constraint);
5965
if (str1 == NULL) {
5966
if (constraint->constraint->not_present) {
5967
str1 = GetFieldValueFromCGPSet (c, constraint->field1->data.intvalue, NULL);
5968
if (str1 == NULL) {
5969
rval = TRUE;
5970
}
5971
}
5972
} else if (!StringHasNoText (str1)) {
5973
rval = TRUE;
5974
}
5975
str1 = MemFree (str1);
5976
} else if (constraint->field2 != NULL && constraint->field1 == NULL) {
5977
str2 = GetFieldValueFromCGPSet (c, constraint->field2->data.intvalue, constraint->constraint);
5978
if (str2 == NULL) {
5979
if (constraint->constraint->not_present) {
5980
str2 = GetFieldValueFromCGPSet (c, constraint->field2->data.intvalue, NULL);
5981
if (str2 == NULL) {
5982
rval = TRUE;
5983
}
5984
}
5985
} else if (!StringHasNoText (str2)) {
5986
rval = TRUE;
5987
}
5988
str2 = MemFree (str2);
5989
} else if (constraint->field1 != NULL && constraint->field2 != NULL) {
5990
str1 = GetFieldValueFromCGPSet (c, constraint->field1->data.intvalue, constraint->constraint);
5991
str2 = GetFieldValueFromCGPSet (c, constraint->field2->data.intvalue, constraint->constraint);
5992
if (StringCmp (str1, str2) == 0) {
5993
rval = TRUE;
5994
}
5995
str1 = MemFree (str1);
5996
str2 = MemFree (str2);
5997
} else {
5998
/* generic string constraint */
5999
rval = DoesObjectMatchStringConstraint (0, c, constraint->constraint);
6000
}
6001
}
6002
return rval;
6003
}
6004
6005
6006
NLM_EXTERN Boolean IsSequenceConstraintEmpty (SequenceConstraintPtr constraint)
6007
{
6008
if (constraint == NULL) return TRUE;
6009
if (constraint->seqtype != NULL && constraint->seqtype->choice != SequenceConstraintMolTypeConstraint_any) return FALSE;
6010
if (constraint->feature != Feature_type_any) return FALSE;
6011
if (!IsStringConstraintEmpty (constraint->id)) return FALSE;
6012
return TRUE;
6013
}
6014
6015
6016
extern Boolean DoesSeqIDListMeetStringConstraint (SeqIdPtr sip, StringConstraintPtr string_constraint)
6017
{
6018
Char id [41];
6019
CharPtr cp, cp_dst;
6020
SeqIdPtr tmp;
6021
Boolean match, changed;
6022
6023
if (sip == NULL)
6024
{
6025
return FALSE;
6026
}
6027
if (string_constraint == NULL)
6028
{
6029
return TRUE;
6030
}
6031
6032
while (sip != NULL)
6033
{
6034
/* temporary disconnect ID from list */
6035
tmp = sip->next;
6036
sip->next = NULL;
6037
id [0] = '\0';
6038
SeqIdWrite (sip, id, PRINTID_FASTA_LONG, sizeof (id) - 1);
6039
match = DoesSingleStringMatchConstraint (id, string_constraint);
6040
if (!match)
6041
{
6042
changed = FALSE;
6043
/* remove terminating pipe character */
6044
if (id[StringLen(id) - 1] == '|')
6045
{
6046
id[StringLen(id) - 1] = 0;
6047
changed = TRUE;
6048
}
6049
/* remove leading pipe identifier */
6050
cp = StringChr (id, '|');
6051
if (cp != NULL)
6052
{
6053
changed = TRUE;
6054
cp++;
6055
cp_dst = id;
6056
while (*cp != 0)
6057
{
6058
*cp_dst = *cp;
6059
cp_dst++;
6060
cp++;
6061
}
6062
*cp_dst = 0;
6063
}
6064
if (changed)
6065
{
6066
match = DoesSingleStringMatchConstraint (id, string_constraint);
6067
}
6068
6069
/* if search text doesn't have ., try ID without version */
6070
if (!match && StringChr (string_constraint->match_text, '.') == NULL)
6071
{
6072
cp = StringChr (id, '.');
6073
if (cp != NULL)
6074
{
6075
*cp = 0;
6076
match = DoesSingleStringMatchConstraint (id, string_constraint);
6077
}
6078
}
6079
}
6080
sip->next = tmp;
6081
6082
if (match)
6083
{
6084
if (string_constraint->not_present)
6085
{
6086
return FALSE;
6087
}
6088
else
6089
{
6090
return TRUE;
6091
}
6092
}
6093
sip = sip->next;
6094
}
6095
if (string_constraint->not_present)
6096
{
6097
return TRUE;
6098
}
6099
else
6100
{
6101
return FALSE;
6102
}
6103
}
6104
6105
6106
typedef struct rnatypebiomol {
6107
Int4 rnatype;
6108
Uint1 biomol;
6109
CharPtr rnamolname;
6110
} RnaTypeBiomolData, PNTR RnaTypeBiomolPtr;
6111
6112
static RnaTypeBiomolData rna_type_biomol[] = {
6113
{ Sequence_constraint_rnamol_genomic , MOLECULE_TYPE_GENOMIC, "Genomic RNA" } ,
6114
{ Sequence_constraint_rnamol_precursor_RNA , MOLECULE_TYPE_PRE_MRNA , "Precursor RNA" } ,
6115
{ Sequence_constraint_rnamol_mRNA , MOLECULE_TYPE_MRNA , "mRNA [cDNA]" } ,
6116
{ Sequence_constraint_rnamol_rRNA , MOLECULE_TYPE_RRNA , "Ribosomal RNA" } ,
6117
{ Sequence_constraint_rnamol_tRNA , MOLECULE_TYPE_TRNA , "Transfer RNA" } ,
6118
{ Sequence_constraint_rnamol_snRNA , MOLECULE_TYPE_SNRNA , "Small nuclear RNA" } ,
6119
{ Sequence_constraint_rnamol_scRNA , MOLECULE_TYPE_SCRNA , "Small cytoplasmic RNA" } ,
6120
{ Sequence_constraint_rnamol_genomic_mRNA , MOLECULE_TYPE_GENOMIC_MRNA_MIX , "Genomic-mRNA" } ,
6121
{ Sequence_constraint_rnamol_cRNA , MOLECULE_TYPE_CRNA , "cRNA" } ,
6122
{ Sequence_constraint_rnamol_snoRNA , MOLECULE_TYPE_SNORNA , "Small nucleolar RNA" } ,
6123
{ Sequence_constraint_rnamol_transcribed_RNA , MOLECULE_TYPE_TRANSCRIBED_RNA , "Transcribed RNA" } ,
6124
{ Sequence_constraint_rnamol_ncRNA , MOLECULE_TYPE_NCRNA , "Non-coding RNA" } ,
6125
{ Sequence_constraint_rnamol_transfer_messenger_RNA , MOLECULE_TYPE_TMRNA , "Transfer-messenger RNA" } } ;
6126
6127
#define NUM_rna_type_biomol sizeof (rna_type_biomol) / sizeof (RnaTypeBiomolData)
6128
6129
6130
NLM_EXTERN Uint1 GetBiomolForRnaType (Int4 rnatype)
6131
{
6132
Int4 i;
6133
6134
for (i = 0; i < NUM_rna_type_biomol; i++) {
6135
if (rna_type_biomol[i].rnatype == rnatype) {
6136
return rna_type_biomol[i].biomol;
6137
}
6138
}
6139
return 0;
6140
}
6141
6142
6143
NLM_EXTERN CharPtr GetBiomolNameForRnaType (Int4 rnatype)
6144
{
6145
Int4 i;
6146
6147
for (i = 0; i < NUM_rna_type_biomol; i++) {
6148
if (rna_type_biomol[i].rnatype == rnatype) {
6149
return rna_type_biomol[i].rnamolname;
6150
}
6151
}
6152
return "invalid RNA type";
6153
}
6154
6155
NLM_EXTERN void AddAllRNASubtypesToChoiceList (ValNodePtr PNTR field_list)
6156
{
6157
Int4 i;
6158
6159
if (field_list == NULL) return;
6160
6161
ValNodeAddPointer (field_list, Sequence_constraint_rnamol_any, StringSave ("Any RNA"));
6162
for (i = 0; i < NUM_rna_type_biomol; i++) {
6163
ValNodeAddPointer (field_list, rna_type_biomol[i].rnatype, StringSave (rna_type_biomol[i].rnamolname));
6164
}
6165
}
6166
6167
6168
static Boolean DoesSequenceMatchSequenceConstraint (BioseqPtr bsp, SequenceConstraintPtr constraint)
6169
{
6170
SeqFeatPtr sfp;
6171
SeqMgrFeatContext fcontext;
6172
SeqDescrPtr sdp;
6173
SeqMgrDescContext dcontext;
6174
MolInfoPtr mip;
6175
6176
if (bsp == NULL) return FALSE;
6177
if (IsSequenceConstraintEmpty (constraint)) return TRUE;
6178
6179
if (constraint->seqtype != NULL && constraint->seqtype->choice != SequenceConstraintMolTypeConstraint_any) {
6180
switch (constraint->seqtype->choice) {
6181
case SequenceConstraintMolTypeConstraint_nucleotide :
6182
if (ISA_aa (bsp->mol)) {
6183
return FALSE;
6184
}
6185
break;
6186
case SequenceConstraintMolTypeConstraint_dna :
6187
if (bsp->mol != Seq_mol_dna) {
6188
return FALSE;
6189
}
6190
break;
6191
case SequenceConstraintMolTypeConstraint_rna :
6192
if (bsp->mol != Seq_mol_rna) {
6193
return FALSE;
6194
}
6195
if (constraint->seqtype->data.intvalue != Sequence_constraint_rnamol_any) {
6196
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_molinfo, &dcontext);
6197
if (sdp == NULL || sdp->data.ptrvalue == NULL || sdp->choice != Seq_descr_molinfo) {
6198
return FALSE;
6199
}
6200
mip = (MolInfoPtr) sdp->data.ptrvalue;
6201
if (GetBiomolForRnaType (constraint->seqtype->data.intvalue) != mip->biomol) {
6202
return FALSE;
6203
}
6204
}
6205
break;
6206
case SequenceConstraintMolTypeConstraint_protein :
6207
if (!ISA_aa (bsp->mol)) {
6208
return FALSE;
6209
}
6210
break;
6211
}
6212
}
6213
6214
if (constraint->feature != Feature_type_any) {
6215
sfp = SeqMgrGetNextFeature (bsp, NULL, 0, GetFeatdefFromFeatureType (constraint->feature), &fcontext);
6216
if (sfp == NULL) {
6217
return FALSE;
6218
}
6219
}
6220
6221
if (!IsStringConstraintEmpty (constraint->id) && !DoesSeqIDListMeetStringConstraint (bsp->id, constraint->id)) {
6222
return FALSE;
6223
}
6224
return TRUE;
6225
}
6226
6227
static Boolean DoesSequenceInSetMatchSequenceConstraint (BioseqSetPtr bssp, SequenceConstraintPtr constraint)
6228
{
6229
Boolean rval = FALSE;
6230
SeqEntryPtr sep;
6231
6232
if (bssp == NULL) return FALSE;
6233
if (IsSequenceConstraintEmpty (constraint)) return TRUE;
6234
6235
for (sep = bssp->seq_set; sep != NULL && !rval; sep = sep->next) {
6236
if (IS_Bioseq (sep)) {
6237
rval = DoesSequenceMatchSequenceConstraint ((BioseqPtr) sep->data.ptrvalue, constraint);
6238
} else if (IS_Bioseq_set (sep)) {
6239
rval = DoesSequenceInSetMatchSequenceConstraint ((BioseqSetPtr) sep->data.ptrvalue, constraint);
6240
}
6241
}
6242
return rval;
6243
}
6244
6245
6246
static Boolean DoesObjectMatchSequenceConstraint (Uint1 choice, Pointer data, SequenceConstraintPtr constraint)
6247
{
6248
BioseqPtr bsp;
6249
SeqDescrPtr sdp;
6250
ObjValNodePtr ovp;
6251
Boolean rval = FALSE;
6252
6253
if (data == NULL) return FALSE;
6254
if (IsSequenceConstraintEmpty (constraint)) return TRUE;
6255
6256
bsp = GetSequenceForObject (choice, data);
6257
if (bsp == NULL) {
6258
if (choice == OBJ_SEQDESC) {
6259
sdp = (SeqDescrPtr) data;
6260
if (sdp->extended) {
6261
ovp = (ObjValNodePtr) sdp;
6262
if (ovp->idx.parenttype == OBJ_BIOSEQSET && ovp->idx.parentptr != NULL) {
6263
rval = DoesSequenceInSetMatchSequenceConstraint ((BioseqSetPtr) ovp->idx.parentptr, constraint);
6264
}
6265
}
6266
}
6267
} else {
6268
rval = DoesSequenceMatchSequenceConstraint (bsp, constraint);
6269
}
6270
return rval;
6271
}
6272
6273
6274
static Boolean DoesObjectMatchConstraint (Uint1 choice, Pointer data, ConstraintChoicePtr constraint)
6275
{
6276
Boolean rval = TRUE;
6277
6278
if (data == NULL) return FALSE;
6279
if (constraint == NULL) return TRUE;
6280
6281
switch (constraint->choice) {
6282
case ConstraintChoice_string :
6283
rval = DoesObjectMatchStringConstraint (choice, data, constraint->data.ptrvalue);
6284
break;
6285
case ConstraintChoice_location :
6286
rval = DoesObjectMatchLocationConstraint (choice, data, constraint->data.ptrvalue);
6287
break;
6288
case ConstraintChoice_source :
6289
rval = DoesBiosourceMatchConstraint (GetBioSourceFromObject (choice, data), constraint->data.ptrvalue);
6290
break;
6291
case ConstraintChoice_cdsgeneprot_qual :
6292
if (choice == 0) {
6293
rval = DoesCGPSetMatchQualConstraint (data, constraint->data.ptrvalue);
6294
} else {
6295
rval = FALSE;
6296
}
6297
break;
6298
case ConstraintChoice_cdsgeneprot_pseudo :
6299
if (choice == 0) {
6300
rval = DoesCGPSetMatchPseudoConstraint (data, constraint->data.ptrvalue);
6301
} else {
6302
rval = FALSE;
6303
}
6304
break;
6305
case ConstraintChoice_sequence :
6306
rval = DoesObjectMatchSequenceConstraint (choice, data, constraint->data.ptrvalue);
6307
break;
6308
}
6309
return rval;
6310
}
6311
6312
6313
static Boolean DoesObjectMatchConstraintChoiceSet (Uint1 choice, Pointer data, ConstraintChoiceSetPtr csp)
6314
{
6315
Boolean rval = TRUE;
6316
6317
if (data == NULL) return FALSE;
6318
6319
while (csp != NULL && rval) {
6320
rval = DoesObjectMatchConstraint (choice, data, csp);
6321
csp = csp->next;
6322
}
6323
return rval;
6324
}
6325
6326
6327
NLM_EXTERN StringConstraintPtr FindStringConstraintInConstraintSetForField (FieldTypePtr field, ConstraintChoiceSetPtr csp)
6328
{
6329
StringConstraintPtr scp = NULL;
6330
ConstraintChoicePtr constraint;
6331
SourceConstraintPtr source_constraint;
6332
CDSGeneProtQualConstraintPtr cgp_constraint;
6333
6334
while (csp != NULL) {
6335
constraint = (ConstraintChoicePtr) csp->data.ptrvalue;
6336
switch (constraint->choice) {
6337
case ConstraintChoice_string :
6338
scp = constraint->data.ptrvalue;
6339
break;
6340
case ConstraintChoice_source :
6341
source_constraint = (SourceConstraintPtr) constraint->data.ptrvalue;
6342
if (source_constraint != NULL && source_constraint->constraint != NULL
6343
&& ((source_constraint->field1 != NULL
6344
&& DoFieldTypesMatch (field, source_constraint->field1))
6345
|| (source_constraint->field2 != NULL
6346
&& DoFieldTypesMatch (field, source_constraint->field2)))) {
6347
scp = source_constraint->constraint;
6348
}
6349
break;
6350
case ConstraintChoice_cdsgeneprot_qual :
6351
cgp_constraint = (CDSGeneProtQualConstraintPtr) field->data.ptrvalue;
6352
if (field->choice == FieldType_cds_gene_prot
6353
&& cgp_constraint != NULL && cgp_constraint->constraint != NULL
6354
&& ((cgp_constraint->field1 != NULL && cgp_constraint->field1->data.intvalue == field->data.intvalue)
6355
|| (cgp_constraint->field2 != NULL && cgp_constraint->field2->data.intvalue == field->data.intvalue))) {
6356
scp = cgp_constraint->constraint;
6357
}
6358
break;
6359
}
6360
csp = csp->next;
6361
}
6362
return scp;
6363
}
6364
6365
6366
NLM_EXTERN StringConstraintPtr FindStringConstraintInConstraintSetForFieldPair (FieldPairTypePtr fieldpair, ConstraintChoiceSetPtr csp)
6367
{
6368
StringConstraintPtr scp;
6369
FieldTypePtr f;
6370
6371
f = GetFromFieldFromFieldPair (fieldpair);
6372
scp = FindStringConstraintInConstraintSetForField (f, csp);
6373
f = FieldTypeFree (f);
6374
return scp;
6375
}
6376
6377
6378
NLM_EXTERN StringConstraintPtr StringConstraintFromFieldEdit (FieldEditPtr edit)
6379
{
6380
StringConstraintPtr scp;
6381
6382
if (edit == NULL || edit->find_txt == NULL) return NULL;
6383
scp = StringConstraintNew ();
6384
scp->match_text = StringSave (edit->find_txt);
6385
6386
switch (edit->location) {
6387
case Field_edit_location_anywhere :
6388
scp->match_location = String_location_contains;
6389
break;
6390
case Field_edit_location_beginning :
6391
scp->match_location = String_location_starts;
6392
break;
6393
case Field_edit_location_end :
6394
scp->match_location = String_location_ends;
6395
break;
6396
}
6397
6398
scp->case_sensitive = TRUE;
6399
scp->whole_word = FALSE;
6400
scp->not_present = FALSE;
6401
6402
return scp;
6403
}
6404
6405
6406
static CharPtr ApplyEditToString (CharPtr str, FieldEditPtr edit)
6407
{
6408
CharPtr cp_found, new_str;
6409
Int4 found_len, replace_len, new_len;
6410
6411
if (edit == NULL) return StringSave (str);
6412
6413
str = StringSave (str);
6414
cp_found = StringISearch (str, edit->find_txt);
6415
6416
found_len = StringLen (edit->find_txt);
6417
replace_len = StringLen (edit->repl_txt);
6418
if (edit->location == Field_edit_location_beginning
6419
&& cp_found != str) {
6420
cp_found = NULL;
6421
}
6422
while (cp_found != NULL)
6423
{
6424
if (edit->location == Field_edit_location_end
6425
&& cp_found != str + StringLen (str) - found_len) {
6426
cp_found = StringISearch (cp_found + found_len, edit->find_txt);
6427
} else {
6428
new_len = StringLen (str) + 1 - found_len + replace_len;
6429
new_str = (CharPtr) MemNew (new_len * sizeof (Char));
6430
if (new_str != NULL)
6431
{
6432
if (cp_found != str)
6433
{
6434
StringNCpy (new_str, str, cp_found - str);
6435
}
6436
StringCat (new_str, edit->repl_txt);
6437
StringCat (new_str, cp_found + found_len);
6438
cp_found = new_str + (cp_found - str) + replace_len;
6439
str = MemFree (str);
6440
str = new_str;
6441
}
6442
cp_found = StringISearch (cp_found, edit->find_txt);
6443
}
6444
}
6445
return str;
6446
}
6447
6448
6449
typedef struct objectcollection {
6450
AECRActionPtr action;
6451
ValNodePtr object_list;
6452
} ObjectCollectionData, PNTR ObjectCollectionPtr;
6453
6454
6455
static void AECRActionObjectCollectionItemCallback (Uint1 objecttype, Pointer objectdata, ObjectCollectionPtr o)
6456
{
6457
ApplyActionPtr a;
6458
EditActionPtr e;
6459
ConvertActionPtr v;
6460
CopyActionPtr c;
6461
SwapActionPtr s;
6462
RemoveActionPtr r;
6463
AECRParseActionPtr p;
6464
CharPtr str, portion;
6465
StringConstraintPtr scp;
6466
FieldTypePtr field_from = NULL, field_to = NULL;
6467
6468
if (objectdata == NULL || o == NULL) return;
6469
6470
/* check to make sure object is appropriate for field and meets filter */
6471
switch (o->action->action->choice) {
6472
case ActionChoice_apply :
6473
a = (ApplyActionPtr) o->action->action->data.ptrvalue;
6474
if (a != NULL
6475
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, a->field)
6476
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6477
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6478
}
6479
break;
6480
case ActionChoice_edit :
6481
e = (EditActionPtr) o->action->action->data.ptrvalue;
6482
if (e != NULL
6483
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, e->field)
6484
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6485
scp = StringConstraintFromFieldEdit (e->edit);
6486
str = GetFieldValueForObject (objecttype, objectdata, e->field, scp);
6487
if (!StringHasNoText (str)) {
6488
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6489
}
6490
str = MemFree (str);
6491
}
6492
break;
6493
case ActionChoice_convert :
6494
v = (ConvertActionPtr) o->action->action->data.ptrvalue;
6495
if (v != NULL
6496
&& (field_from = GetFromFieldFromFieldPair(v->fields)) != NULL
6497
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_from)
6498
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6499
scp = FindStringConstraintInConstraintSetForField (field_from, o->action->constraint);
6500
str = GetFieldValueForObject (objecttype, objectdata, field_from, scp);
6501
if (!StringHasNoText (str)) {
6502
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6503
}
6504
str = MemFree (str);
6505
}
6506
field_from = FieldTypeFree (field_from);
6507
break;
6508
case ActionChoice_copy :
6509
c = (CopyActionPtr) o->action->action->data.ptrvalue;
6510
if (c != NULL
6511
&& (field_from = GetFromFieldFromFieldPair(c->fields)) != NULL
6512
&& (field_to = GetFromFieldFromFieldPair(c->fields)) != NULL
6513
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_from)
6514
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_to)
6515
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6516
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6517
}
6518
field_from = FieldTypeFree (field_from);
6519
field_to = FieldTypeFree (field_to);
6520
break;
6521
case ActionChoice_swap :
6522
s = (SwapActionPtr) o->action->action->data.ptrvalue;
6523
if (s != NULL
6524
&& (field_from = GetFromFieldFromFieldPair(s->fields)) != NULL
6525
&& (field_to = GetFromFieldFromFieldPair(s->fields)) != NULL
6526
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_from)
6527
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_to)
6528
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6529
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6530
}
6531
field_from = FieldTypeFree (field_from);
6532
field_to = FieldTypeFree (field_to);
6533
break;
6534
case ActionChoice_remove :
6535
r = (RemoveActionPtr) o->action->action->data.ptrvalue;
6536
if (r != NULL
6537
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, r->field)
6538
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6539
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6540
}
6541
break;
6542
case ActionChoice_parse :
6543
p = (AECRParseActionPtr) o->action->action->data.ptrvalue;
6544
if (p != NULL
6545
&& (field_from = GetFromFieldFromFieldPair(p->fields)) != NULL
6546
&& (field_to = GetFromFieldFromFieldPair(p->fields)) != NULL
6547
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_from)
6548
&& IsObjectAppropriateForFieldValue (objecttype, objectdata, field_to)
6549
&& DoesObjectMatchConstraintChoiceSet (objecttype, objectdata, o->action->constraint)) {
6550
scp = FindStringConstraintInConstraintSetForField (field_from, o->action->constraint);
6551
str = GetFieldValueForObject (objecttype, objectdata, field_from, scp);
6552
portion = GetTextPortionFromString (str, p->portion);
6553
if (!StringHasNoText (portion)) {
6554
ValNodeAddPointer (&(o->object_list), objecttype, objectdata);
6555
}
6556
portion = MemFree (portion);
6557
str = MemFree (str);
6558
}
6559
field_from = FieldTypeFree (field_from);
6560
field_to = FieldTypeFree (field_to);
6561
break;
6562
}
6563
6564
}
6565
6566
6567
static void AECRActionObjectCollectionFeatureCallback (SeqFeatPtr sfp, Pointer data)
6568
{
6569
ObjectCollectionPtr o;
6570
if (sfp == NULL || data == NULL) return;
6571
6572
o = (ObjectCollectionPtr) data;
6573
AECRActionObjectCollectionItemCallback (OBJ_SEQFEAT, sfp, o);
6574
6575
}
6576
6577
6578
static void AECRActionObjectCollectionDescriptorCallback (SeqDescrPtr sdp, Pointer data)
6579
{
6580
ObjectCollectionPtr o;
6581
6582
if (sdp == NULL || data == NULL) return;
6583
6584
o = (ObjectCollectionPtr) data;
6585
AECRActionObjectCollectionItemCallback (OBJ_SEQDESC, sdp, o);
6586
}
6587
6588
6589
static void AECRObjectCollectionBioseqCallback (BioseqPtr bsp, Pointer data)
6590
{
6591
ObjectCollectionPtr o;
6592
6593
if (bsp == NULL || data == NULL) return;
6594
6595
o = (ObjectCollectionPtr) data;
6596
AECRActionObjectCollectionItemCallback (OBJ_BIOSEQ, bsp, o);
6597
}
6598
6599
6600
NLM_EXTERN ValNodePtr GetObjectListForAECRAction (SeqEntryPtr sep, AECRActionPtr action)
6601
{
6602
ObjectCollectionData ocd;
6603
6604
ocd.action = action;
6605
ocd.object_list = NULL;
6606
6607
if (action == NULL) return NULL;
6608
if (FieldTypeFromAECRAction (action) == FieldType_molinfo_field) {
6609
VisitBioseqsInSep (sep, &ocd, AECRObjectCollectionBioseqCallback);
6610
} else {
6611
VisitFeaturesInSep (sep, &ocd, AECRActionObjectCollectionFeatureCallback);
6612
VisitDescriptorsInSep (sep, &ocd, AECRActionObjectCollectionDescriptorCallback);
6613
}
6614
return ocd.object_list;
6615
}
6616
6617
6618
typedef struct buildcgpset
6619
{
6620
ValNodePtr cds_list;
6621
ValNodePtr mrna_list;
6622
ValNodePtr gene_list;
6623
} BuildCGPSetData, PNTR BuildCGPSetPtr;
6624
6625
static void BuildCGPSetCallback (SeqFeatPtr sfp, Pointer userdata)
6626
{
6627
BuildCGPSetPtr b;
6628
6629
if (sfp == NULL || sfp->idx.deleteme || userdata == NULL) return;
6630
b = (BuildCGPSetPtr) userdata;
6631
if (sfp->data.choice == SEQFEAT_CDREGION)
6632
{
6633
ValNodeAddPointer (&(b->cds_list), OBJ_SEQFEAT, sfp);
6634
}
6635
else if (sfp->data.choice == SEQFEAT_GENE)
6636
{
6637
ValNodeAddPointer (&(b->gene_list), OBJ_SEQFEAT, sfp);
6638
}
6639
else if (sfp->idx.subtype == FEATDEF_mRNA)
6640
{
6641
ValNodeAddPointer (&(b->mrna_list), OBJ_SEQFEAT, sfp);
6642
}
6643
else if (SeqMgrGetGeneXref (sfp) != NULL)
6644
{
6645
ValNodeAddPointer (&(b->gene_list), OBJ_SEQFEAT, sfp);
6646
}
6647
}
6648
6649
6650
static CGPSetPtr BuildCGPSetFromCodingRegion (SeqFeatPtr cds, BoolPtr indexing_needed)
6651
{
6652
SeqMgrFeatContext fcontext;
6653
SeqFeatPtr gene = NULL, mrna, prot;
6654
BioseqPtr protbsp;
6655
CGPSetPtr cdsp;
6656
ProtRefPtr prp;
6657
6658
if (cds == NULL || cds->data.choice != SEQFEAT_CDREGION) return NULL;
6659
6660
cdsp = (CGPSetPtr) MemNew (sizeof (CGPSetData));
6661
ValNodeAddPointer (&(cdsp->cds_list), 0, cds);
6662
6663
gene = GetGeneForFeature (cds);
6664
if (gene != NULL)
6665
{
6666
ValNodeAddPointer (&(cdsp->gene_list), 0, gene);
6667
/* mark gene, so that we'll know it isn't lonely */
6668
gene->idx.deleteme = TRUE;
6669
}
6670
6671
mrna = SeqMgrGetOverlappingmRNA (cds->location, &fcontext);
6672
if (mrna != NULL)
6673
{
6674
ValNodeAddPointer (&(cdsp->mrna_list), 0, mrna);
6675
/* mark mrna, so that we'll know it's already in a set */
6676
mrna->idx.deleteme = TRUE;
6677
}
6678
6679
if (cds->product != NULL)
6680
{
6681
protbsp = BioseqFindFromSeqLoc (cds->product);
6682
if (protbsp != NULL)
6683
{
6684
prot = SeqMgrGetNextFeature (protbsp, NULL, SEQFEAT_PROT, FEATDEF_PROT, &fcontext);
6685
/* if there is no full-length protein feature, make one */
6686
if (prot == NULL)
6687
{
6688
prp = ProtRefNew ();
6689
prot = CreateNewFeatureOnBioseq (protbsp, SEQFEAT_PROT, NULL);
6690
if (prot != NULL)
6691
{
6692
prot->data.value.ptrvalue = prp;
6693
if (indexing_needed != NULL)
6694
{
6695
*indexing_needed = TRUE;
6696
}
6697
}
6698
}
6699
if (prot != NULL)
6700
{
6701
ValNodeAddPointer (&(cdsp->prot_list), 0, prot);
6702
}
6703
6704
/* also add in mat_peptides from protein feature */
6705
prot = SeqMgrGetNextFeature (protbsp, NULL, SEQFEAT_PROT, FEATDEF_mat_peptide_aa, &fcontext);
6706
while (prot != NULL)
6707
{
6708
ValNodeAddPointer (&(cdsp->prot_list), 0, prot);
6709
prot = SeqMgrGetNextFeature (protbsp, prot, SEQFEAT_PROT, FEATDEF_mat_peptide_aa, &fcontext);
6710
}
6711
}
6712
}
6713
return cdsp;
6714
}
6715
6716
6717
static CGPSetPtr BuildCGPSetFrommRNA (SeqFeatPtr mrna)
6718
{
6719
SeqFeatPtr gene;
6720
CGPSetPtr cdsp;
6721
6722
if (mrna == NULL || mrna->idx.deleteme || mrna->idx.subtype != FEATDEF_mRNA) return NULL;
6723
6724
cdsp = (CGPSetPtr) MemNew (sizeof (CGPSetData));
6725
ValNodeAddPointer (&(cdsp->mrna_list), 0, mrna);
6726
6727
gene = GetGeneForFeature (mrna);
6728
if (gene != NULL)
6729
{
6730
ValNodeAddPointer (&(cdsp->gene_list), 0, gene);
6731
/* mark gene, so that we'll know it isn't lonely */
6732
gene->idx.deleteme = TRUE;
6733
}
6734
6735
return cdsp;
6736
}
6737
6738
6739
static void UnmarkFeatureList (ValNodePtr list)
6740
{
6741
SeqFeatPtr sfp;
6742
6743
while (list != NULL)
6744
{
6745
sfp = list->data.ptrvalue;
6746
if (sfp != NULL)
6747
{
6748
sfp->idx.deleteme = FALSE;
6749
}
6750
list = list->next;
6751
}
6752
}
6753
6754
6755
static ValNodePtr BuildCGPSetList (Uint2 entityID, ValNodePtr constraint)
6756
{
6757
SeqEntryPtr sep;
6758
BuildCGPSetData b;
6759
CGPSetPtr cdsp;
6760
ValNodePtr vnp, vnp_next, vnp_prev;
6761
ValNodePtr cdset_list = NULL;
6762
SeqFeatPtr cds, gene, mrna;
6763
Boolean need_indexing = FALSE;
6764
6765
sep = GetTopSeqEntryForEntityID (entityID);
6766
6767
b.cds_list = NULL;
6768
b.gene_list = NULL;
6769
b.mrna_list = NULL;
6770
6771
VisitFeaturesInSep (sep, &b, BuildCGPSetCallback);
6772
6773
/* build cdsets that have coding regions */
6774
for (vnp = b.cds_list; vnp != NULL; vnp = vnp->next)
6775
{
6776
cds = (SeqFeatPtr) vnp->data.ptrvalue;
6777
if (cds == NULL) continue;
6778
cdsp = BuildCGPSetFromCodingRegion (cds, &need_indexing);
6779
if (cdsp != NULL)
6780
{
6781
ValNodeAddPointer (&cdset_list, 0, cdsp);
6782
}
6783
}
6784
if (need_indexing)
6785
{
6786
/* indexing because we have created full-length protein features */
6787
SeqMgrIndexFeatures (entityID, NULL);
6788
}
6789
6790
/* build cdsets for mrna features that don't have coding regions */
6791
for (vnp = b.mrna_list; vnp != NULL; vnp = vnp->next)
6792
{
6793
mrna = (SeqFeatPtr) vnp->data.ptrvalue;
6794
if (mrna == NULL || mrna->idx.deleteme) continue;
6795
cdsp = BuildCGPSetFrommRNA (mrna);
6796
if (cdsp != NULL)
6797
{
6798
ValNodeAddPointer (&cdset_list, 0, cdsp);
6799
}
6800
}
6801
6802
/* build cdsets for lonely genes / features with gene xrefs that are not coding regions or mrnas */
6803
for (vnp = b.gene_list; vnp != NULL; vnp = vnp->next)
6804
{
6805
gene = (SeqFeatPtr) vnp->data.ptrvalue;
6806
if (gene == NULL || gene->idx.deleteme) continue;
6807
cdsp = CGPSetNew ();
6808
ValNodeAddPointer (&(cdsp->gene_list), 0, gene);
6809
ValNodeAddPointer (&cdset_list, 0, cdsp);
6810
}
6811
6812
/* now unmark features */
6813
UnmarkFeatureList (b.cds_list);
6814
UnmarkFeatureList (b.mrna_list);
6815
UnmarkFeatureList (b.gene_list);
6816
6817
b.cds_list = ValNodeFree (b.cds_list);
6818
b.mrna_list = ValNodeFree (b.mrna_list);
6819
b.gene_list = ValNodeFree (b.gene_list);
6820
6821
/* now remove sets that don't match our choice constraint */
6822
vnp_prev = NULL;
6823
for (vnp = cdset_list; vnp != NULL; vnp = vnp_next)
6824
{
6825
vnp_next = vnp->next;
6826
if (!DoesObjectMatchConstraintChoiceSet (0, vnp->data.ptrvalue, constraint))
6827
{
6828
if (vnp_prev == NULL)
6829
{
6830
cdset_list = vnp->next;
6831
}
6832
else
6833
{
6834
vnp_prev->next = vnp->next;
6835
}
6836
vnp->next = NULL;
6837
FreeCGPSetList (vnp);
6838
}
6839
else
6840
{
6841
vnp_prev = vnp;
6842
}
6843
}
6844
6845
return cdset_list;
6846
}
6847
6848
6849
NLM_EXTERN Int4 DoApplyActionToObjectList (ApplyActionPtr action, ValNodePtr object_list, StringConstraintPtr scp)
6850
{
6851
ValNodePtr vnp;
6852
Int4 num_succeed = 0, num_fail = 0;
6853
6854
if (action == NULL || object_list == NULL) return 0;
6855
6856
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6857
if (SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, action->field, scp, action->value, action->existing_text)) {
6858
num_succeed ++;
6859
} else {
6860
num_fail++;
6861
}
6862
}
6863
return num_succeed;
6864
}
6865
6866
6867
NLM_EXTERN Int4 DoEditActionToObjectList (EditActionPtr action, ValNodePtr object_list)
6868
{
6869
ValNodePtr vnp;
6870
Int4 num_succeed = 0, num_fail = 0;
6871
StringConstraintPtr scp;
6872
CharPtr str, new_str;
6873
6874
if (action == NULL || object_list == NULL) return 0;
6875
scp = StringConstraintFromFieldEdit (action->edit);
6876
6877
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6878
str = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, action->field, scp);
6879
new_str = ApplyEditToString (str, action->edit);
6880
if (StringCmp (str, new_str) != 0
6881
&& SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, action->field, scp, new_str, ExistingTextOption_replace_old)) {
6882
num_succeed ++;
6883
} else {
6884
num_fail++;
6885
}
6886
new_str = MemFree (new_str);
6887
str = MemFree (str);
6888
}
6889
return num_succeed;
6890
}
6891
6892
6893
NLM_EXTERN Int4 DoConvertActionToObjectList (ConvertActionPtr action, ValNodePtr object_list, StringConstraintPtr scp)
6894
{
6895
ValNodePtr vnp;
6896
Int4 num_succeed = 0, num_fail = 0;
6897
CharPtr str, from_val;
6898
FieldTypePtr field_from, field_to;
6899
6900
if (action == NULL || object_list == NULL || action->fields == NULL) return 0;
6901
6902
field_from = GetFromFieldFromFieldPair (action->fields);
6903
field_to = GetToFieldFromFieldPair (action->fields);
6904
6905
if (action->fields->choice == FieldPairType_molinfo_field) {
6906
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6907
str = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, NULL);
6908
from_val = GetSequenceQualValName (field_from->data.ptrvalue);
6909
if (StringCmp (str, from_val) == 0
6910
&& SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_to, NULL, str, ExistingTextOption_replace_old)) {
6911
num_succeed ++;
6912
}
6913
str = MemFree (str);
6914
}
6915
} else {
6916
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6917
str = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp);
6918
if (SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_to, NULL, str, action->existing_text)
6919
&& RemoveFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp)) {
6920
num_succeed ++;
6921
} else {
6922
num_fail++;
6923
}
6924
str = MemFree (str);
6925
}
6926
}
6927
6928
field_from = FieldTypeFree (field_from);
6929
field_to = FieldTypeFree (field_to);
6930
6931
return num_succeed;
6932
}
6933
6934
6935
NLM_EXTERN Int4 DoCopyActionToObjectList (CopyActionPtr action, ValNodePtr object_list, StringConstraintPtr scp)
6936
{
6937
ValNodePtr vnp;
6938
Int4 num_succeed = 0, num_fail = 0;
6939
CharPtr str;
6940
FieldTypePtr field_from, field_to;
6941
6942
if (action == NULL || object_list == NULL) return 0;
6943
field_from = GetFromFieldFromFieldPair (action->fields);
6944
field_to = GetToFieldFromFieldPair (action->fields);
6945
6946
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6947
str = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp);
6948
if (SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_to, NULL, str, action->existing_text)) {
6949
num_succeed ++;
6950
} else {
6951
num_fail++;
6952
}
6953
str = MemFree (str);
6954
}
6955
6956
field_from = FieldTypeFree (field_from);
6957
field_to = FieldTypeFree (field_to);
6958
return num_succeed;
6959
}
6960
6961
6962
NLM_EXTERN Int4 DoSwapActionToObjectList (SwapActionPtr action, ValNodePtr object_list, StringConstraintPtr scp)
6963
{
6964
ValNodePtr vnp;
6965
Int4 num_succeed = 0, num_fail = 0;
6966
CharPtr str1, str2;
6967
FieldTypePtr field_from, field_to;
6968
6969
if (action == NULL || object_list == NULL) return 0;
6970
field_from = GetFromFieldFromFieldPair (action->fields);
6971
field_to = GetToFieldFromFieldPair (action->fields);
6972
6973
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6974
str1 = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp);
6975
str2 = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_to, NULL);
6976
if (SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_to, NULL, str1, ExistingTextOption_replace_old)
6977
&& SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp, str2, ExistingTextOption_replace_old)) {
6978
num_succeed ++;
6979
} else {
6980
num_fail++;
6981
}
6982
str1 = MemFree (str1);
6983
str2 = MemFree (str2);
6984
}
6985
field_from = FieldTypeFree (field_from);
6986
field_to = FieldTypeFree (field_to);
6987
return num_succeed;
6988
}
6989
6990
6991
NLM_EXTERN Int4 DoRemoveActionToObjectList (RemoveActionPtr action, ValNodePtr object_list, StringConstraintPtr scp)
6992
{
6993
ValNodePtr vnp;
6994
Int4 num_succeed = 0, num_fail = 0;
6995
6996
if (action == NULL || object_list == NULL) return 0;
6997
6998
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
6999
if (RemoveFieldValueForObject (vnp->choice, vnp->data.ptrvalue, action->field, scp)) {
7000
num_succeed ++;
7001
} else {
7002
num_fail++;
7003
}
7004
}
7005
return num_succeed;
7006
}
7007
7008
7009
NLM_EXTERN Int4 DoParseActionToObjectList (AECRParseActionPtr action, ValNodePtr object_list, StringConstraintPtr scp)
7010
{
7011
ValNodePtr vnp;
7012
CharPtr str1, str2, cp;
7013
Int4 len, num_succeed = 0;
7014
FieldTypePtr field_from, field_to;
7015
7016
if (action == NULL || object_list == NULL) return 0;
7017
field_from = GetFromFieldFromFieldPair (action->fields);
7018
field_to = GetToFieldFromFieldPair (action->fields);
7019
7020
for (vnp = object_list; vnp != NULL; vnp = vnp->next) {
7021
str1 = GetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp);
7022
str2 = GetTextPortionFromString (str1, action->portion);
7023
if (str2 != NULL) {
7024
if (action->remove_from_parsed) {
7025
cp = StringSearch (str1, str2);
7026
len = StringLen (str2);
7027
StringCpy (cp, cp + len);
7028
SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_from, scp, str1, ExistingTextOption_replace_old);
7029
}
7030
if (SetFieldValueForObject (vnp->choice, vnp->data.ptrvalue, field_to, NULL, str1, action->existing_text)) {
7031
num_succeed++;
7032
}
7033
}
7034
str1 = MemFree (str1);
7035
str2 = MemFree (str2);
7036
}
7037
field_from = FieldTypeFree (field_from);
7038
field_to = FieldTypeFree (field_to);
7039
return num_succeed;
7040
}
7041
7042
7043
static Int4 ApplyAECRActionToSeqEntry (AECRActionPtr act, SeqEntryPtr sep)
7044
{
7045
StringConstraintPtr scp;
7046
ApplyActionPtr a;
7047
ValNodePtr object_list = NULL;
7048
Uint1 field_type;
7049
Uint2 entityID;
7050
Int4 num_succeed = 0;
7051
7052
if (act == NULL || act->action == NULL) return 0;
7053
field_type = FieldTypeFromAECRAction (act);
7054
if (field_type == FieldType_cds_gene_prot) {
7055
entityID = ObjMgrGetEntityIDForChoice(sep);
7056
object_list = BuildCGPSetList (entityID, act->constraint);
7057
} else {
7058
object_list = GetObjectListForAECRAction (sep, act);
7059
}
7060
7061
switch (act->action->choice) {
7062
case ActionChoice_apply:
7063
a = (ApplyActionPtr) act->action->data.ptrvalue;
7064
scp = FindStringConstraintInConstraintSetForField (a->field, act->constraint);
7065
num_succeed = DoApplyActionToObjectList (act->action->data.ptrvalue, object_list, scp);
7066
scp = StringConstraintFree (scp);
7067
break;
7068
case ActionChoice_edit:
7069
num_succeed = DoEditActionToObjectList (act->action->data.ptrvalue, object_list);
7070
break;
7071
case ActionChoice_convert:
7072
num_succeed = DoConvertActionToObjectList (act->action->data.ptrvalue, object_list, NULL);
7073
break;
7074
case ActionChoice_swap:
7075
num_succeed = DoSwapActionToObjectList (act->action->data.ptrvalue, object_list, NULL);
7076
break;
7077
case ActionChoice_copy:
7078
num_succeed = DoCopyActionToObjectList (act->action->data.ptrvalue, object_list, NULL);
7079
break;
7080
case ActionChoice_remove:
7081
num_succeed = DoRemoveActionToObjectList (act->action->data.ptrvalue, object_list, NULL);
7082
break;
7083
case ActionChoice_parse:
7084
num_succeed = DoRemoveActionToObjectList (act->action->data.ptrvalue, object_list, NULL);
7085
break;
7086
}
7087
object_list = ValNodeFree (object_list);
7088
return num_succeed;
7089
}
7090
7091
7092
/* This section handles parsing where the source field and destination field may not be on the same
7093
* group of objects. */
7094
typedef struct parsesourceinfo
7095
{
7096
BioseqPtr bsp;
7097
SeqFeatPtr sfp;
7098
SeqDescrPtr sdp;
7099
SeqIdPtr sip;
7100
ValNodePtr dest_list;
7101
CharPtr parse_src_txt;
7102
} ParseSourceInfoData, PNTR ParseSourceInfoPtr;
7103
7104
static ParseSourceInfoPtr ParseSourceInfoNew (BioseqPtr bsp, SeqFeatPtr sfp, SeqDescrPtr sdp, SeqIdPtr sip, CharPtr parse_src_txt)
7105
{
7106
ParseSourceInfoPtr psip;
7107
7108
psip = (ParseSourceInfoPtr) MemNew (sizeof (ParseSourceInfoData));
7109
if (psip != NULL) {
7110
psip->bsp = bsp;
7111
psip->sdp = sdp;
7112
psip->sfp = sfp;
7113
psip->sip = sip;
7114
psip->dest_list = NULL;
7115
psip->parse_src_txt = parse_src_txt;
7116
}
7117
return psip;
7118
}
7119
7120
7121
static ParseSourceInfoPtr ParseSourceInfoFree (ParseSourceInfoPtr psip)
7122
{
7123
if (psip != NULL)
7124
{
7125
psip->dest_list = ValNodeFree (psip->dest_list);
7126
psip->parse_src_txt = MemFree (psip->parse_src_txt);
7127
psip = MemFree (psip);
7128
}
7129
return psip;
7130
}
7131
7132
static ParseSourceInfoPtr ParseSourceInfoCopy (ParseSourceInfoPtr psip)
7133
{
7134
ParseSourceInfoPtr pcopy = NULL;
7135
7136
if (psip != NULL)
7137
{
7138
pcopy = (ParseSourceInfoPtr) MemNew (sizeof (ParseSourceInfoData));
7139
if (pcopy != NULL) {
7140
pcopy->bsp = psip->bsp;
7141
pcopy->sfp = psip->sfp;
7142
pcopy->sdp = psip->sdp;
7143
pcopy->sip = psip->sip;
7144
pcopy->dest_list = NULL;
7145
pcopy->parse_src_txt = NULL;
7146
}
7147
}
7148
return pcopy;
7149
}
7150
7151
static ValNodePtr ParseSourceListFree (ValNodePtr vnp)
7152
{
7153
ValNodePtr vnp_next;
7154
while (vnp != NULL) {
7155
vnp_next = vnp->next;
7156
vnp->next = NULL;
7157
vnp->data.ptrvalue = ParseSourceInfoFree (vnp->data.ptrvalue);
7158
vnp = ValNodeFree (vnp);
7159
vnp = vnp_next;
7160
}
7161
return vnp;
7162
}
7163
7164
7165
static void
7166
GetDeflineSourcesForBioseq
7167
(BioseqPtr bsp,
7168
TextPortionPtr portion,
7169
ValNodePtr PNTR source_list)
7170
{
7171
SeqDescrPtr sdp;
7172
SeqMgrDescContext dcontext;
7173
CharPtr str;
7174
ParseSourceInfoPtr psip;
7175
7176
if (bsp == NULL || source_list == NULL)
7177
{
7178
return;
7179
}
7180
7181
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_title, &dcontext);
7182
while (sdp != NULL)
7183
{
7184
str = GetTextPortionFromString (sdp->data.ptrvalue, portion);
7185
if (str != NULL) {
7186
psip = ParseSourceInfoNew (bsp, NULL, sdp, NULL, str);
7187
if (psip != NULL) {
7188
ValNodeAddPointer (source_list, 0, psip);
7189
} else {
7190
str = MemFree (str);
7191
}
7192
}
7193
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_title, &dcontext);
7194
}
7195
}
7196
7197
7198
static CharPtr GetIDSrc (SeqIdPtr sip, Uint1 id_type, CharPtr tag)
7199
{
7200
DbtagPtr dbt = NULL;
7201
ObjectIdPtr oip = NULL;
7202
Char id_str[128];
7203
CharPtr str_src = NULL;
7204
7205
if (sip == NULL || sip->choice != id_type) return NULL;
7206
7207
if (id_type == SEQID_GENERAL)
7208
{
7209
dbt = (DbtagPtr) sip->data.ptrvalue;
7210
if (dbt == NULL || (tag != NULL && StringCmp (dbt->db, tag) != 0)) return NULL;
7211
oip = dbt->tag;
7212
}
7213
else if (id_type == SEQID_LOCAL)
7214
{
7215
oip = sip->data.ptrvalue;
7216
}
7217
7218
if (oip == NULL)
7219
{
7220
SeqIdWrite (sip, id_str, PRINTID_REPORT, sizeof (id_str));
7221
str_src = StringSave (id_str);
7222
}
7223
else
7224
{
7225
if (oip->str == NULL)
7226
{
7227
sprintf (id_str, "%d", oip->id);
7228
str_src = StringSave (id_str);
7229
}
7230
else
7231
{
7232
str_src = StringSave (oip->str);
7233
}
7234
}
7235
return str_src;
7236
}
7237
7238
7239
static void
7240
GetIDSourcesForBioseq
7241
(BioseqPtr bsp,
7242
TextPortionPtr portion,
7243
Uint1 id_type,
7244
CharPtr tag,
7245
ValNodePtr PNTR source_list)
7246
{
7247
SeqIdPtr sip;
7248
ParseSourceInfoPtr psip;
7249
CharPtr src_str = NULL, str;
7250
7251
if (bsp == NULL || source_list == NULL)
7252
{
7253
return;
7254
}
7255
7256
sip = bsp->id;
7257
while (sip != NULL)
7258
{
7259
if ((src_str = GetIDSrc (sip, id_type, tag)) != NULL) {
7260
str = GetTextPortionFromString (src_str, portion);
7261
if (str != NULL) {
7262
psip = ParseSourceInfoNew (bsp, NULL, NULL, sip, str);
7263
if (psip != NULL) {
7264
ValNodeAddPointer (source_list, 0, psip);
7265
} else {
7266
str = MemFree (str);
7267
}
7268
}
7269
src_str = MemFree (src_str);
7270
}
7271
sip = sip->next;
7272
}
7273
}
7274
7275
7276
static void
7277
GetLocalIDSourcesForBioseq
7278
(BioseqPtr bsp,
7279
TextPortionPtr tp,
7280
ValNodePtr PNTR source_list)
7281
{
7282
GetIDSourcesForBioseq (bsp, tp, SEQID_LOCAL, NULL, source_list);
7283
}
7284
7285
7286
static void GetNcbiFileSourceForBioseq
7287
(BioseqPtr bsp,
7288
TextPortionPtr tp,
7289
ValNodePtr PNTR source_list)
7290
{
7291
GetIDSourcesForBioseq (bsp, tp, SEQID_GENERAL, "NCBIFILE", source_list);
7292
}
7293
7294
7295
static void StripBankitCommentForParse (SeqDescrPtr sdp, TextPortionPtr tp)
7296
{
7297
UserObjectPtr uop;
7298
ObjectIdPtr oip;
7299
UserFieldPtr ufp;
7300
7301
if (sdp == NULL || sdp->choice != Seq_descr_user || tp == NULL) {
7302
return;
7303
}
7304
7305
/* Bankit Comments */
7306
uop = (UserObjectPtr) sdp->data.ptrvalue;
7307
if (uop != NULL && StringCmp (uop->_class, "SMART_V1.0") != 0) {
7308
oip = uop->type;
7309
if (oip != NULL && StringCmp (oip->str, "Submission") == 0) {
7310
for (ufp = uop->data; ufp != NULL; ufp = ufp->next) {
7311
oip = ufp->label;
7312
if (oip != NULL && StringCmp (oip->str, "AdditionalComment") == 0) {
7313
ReplaceStringForParse (ufp->data.ptrvalue, tp);
7314
}
7315
}
7316
}
7317
}
7318
}
7319
7320
7321
static void StripStructuredCommentForParse (SeqDescrPtr sdp, CharPtr comment_field, TextPortionPtr tp)
7322
{
7323
UserObjectPtr uop;
7324
ObjectIdPtr oip;
7325
UserFieldPtr ufp;
7326
7327
if (sdp == NULL || sdp->choice != Seq_descr_user || tp == NULL || StringHasNoText (comment_field)) {
7328
return;
7329
}
7330
7331
uop = (UserObjectPtr) sdp->data.ptrvalue;
7332
oip = uop->type;
7333
if (oip != NULL && StringCmp (oip->str, "StructuredComment") == 0) {
7334
for (ufp = uop->data; ufp != NULL; ufp = ufp->next) {
7335
oip = ufp->label;
7336
if (oip != NULL && StringCmp (oip->str, comment_field) == 0) {
7337
ReplaceStringForParse (ufp->data.ptrvalue, tp);
7338
}
7339
}
7340
}
7341
}
7342
7343
7344
static void
7345
GetBankitCommentSourcesForBioseq
7346
(BioseqPtr bsp,
7347
TextPortionPtr tp,
7348
ValNodePtr PNTR source_list)
7349
{
7350
SeqDescrPtr sdp;
7351
SeqMgrDescContext dcontext;
7352
ParseSourceInfoPtr psip;
7353
UserObjectPtr uop;
7354
ObjectIdPtr oip;
7355
UserFieldPtr ufp;
7356
CharPtr str = NULL;
7357
7358
if (bsp == NULL || source_list == NULL) {
7359
return;
7360
}
7361
7362
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_user, &dcontext);
7363
while (sdp != NULL) {
7364
if (sdp->extended != 0) {
7365
/* Bankit Comments */
7366
uop = (UserObjectPtr) sdp->data.ptrvalue;
7367
if (uop != NULL && StringCmp (uop->_class, "SMART_V1.0") != 0) {
7368
oip = uop->type;
7369
if (oip != NULL && StringCmp (oip->str, "Submission") == 0) {
7370
for (ufp = uop->data; ufp != NULL; ufp = ufp->next) {
7371
oip = ufp->label;
7372
if (oip != NULL && StringCmp (oip->str, "AdditionalComment") == 0) {
7373
str = GetTextPortionFromString (ufp->data.ptrvalue, tp);
7374
if (str != NULL) {
7375
psip = ParseSourceInfoNew (bsp, NULL, sdp, NULL, str);
7376
if (psip == NULL) {
7377
str = MemFree (str);
7378
} else {
7379
ValNodeAddPointer (source_list, 0, psip);
7380
}
7381
}
7382
}
7383
}
7384
}
7385
}
7386
}
7387
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_user, &dcontext);
7388
}
7389
}
7390
7391
7392
static void
7393
GetCommentSourcesForBioseq
7394
(BioseqPtr bsp,
7395
TextPortionPtr tp,
7396
ValNodePtr PNTR source_list)
7397
{
7398
SeqDescrPtr sdp;
7399
SeqFeatPtr sfp;
7400
SeqMgrFeatContext fcontext;
7401
SeqMgrDescContext dcontext;
7402
ParseSourceInfoPtr psip;
7403
CharPtr str;
7404
7405
if (bsp == NULL || source_list == NULL) {
7406
return;
7407
}
7408
7409
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_comment, &dcontext);
7410
while (sdp != NULL) {
7411
str = GetTextPortionFromString (sdp->data.ptrvalue, tp);
7412
if (str != NULL) {
7413
psip = ParseSourceInfoNew (bsp, NULL, sdp, NULL, str);
7414
if (psip == NULL) {
7415
str = MemFree (str);
7416
} else {
7417
ValNodeAddPointer (source_list, 0, psip);
7418
}
7419
}
7420
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_comment, &dcontext);
7421
}
7422
7423
sfp = SeqMgrGetNextFeature (bsp, NULL, SEQFEAT_COMMENT, 0, &fcontext);
7424
while (sfp != NULL) {
7425
str = GetTextPortionFromString (sfp->data.value.ptrvalue, tp);
7426
if (str != NULL) {
7427
psip = ParseSourceInfoNew (bsp, sfp, NULL, NULL, str);
7428
if (psip == NULL) {
7429
str = MemFree (str);
7430
} else {
7431
ValNodeAddPointer (source_list, 0, psip);
7432
}
7433
}
7434
sfp = SeqMgrGetNextFeature (bsp, sfp, SEQFEAT_COMMENT, 0, &fcontext);
7435
}
7436
GetBankitCommentSourcesForBioseq (bsp, tp, source_list);
7437
}
7438
7439
7440
static void
7441
GetStructuredCommentSourcesForBioseq
7442
(BioseqPtr bsp,
7443
TextPortionPtr tp,
7444
CharPtr comment_field,
7445
ValNodePtr PNTR source_list)
7446
{
7447
SeqDescrPtr sdp;
7448
UserObjectPtr uop;
7449
ObjectIdPtr oip;
7450
UserFieldPtr ufp;
7451
SeqMgrDescContext dcontext;
7452
CharPtr str;
7453
ParseSourceInfoPtr psip;
7454
7455
if (bsp == NULL || source_list == NULL)
7456
{
7457
return;
7458
}
7459
7460
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_user, &dcontext);
7461
while (sdp != NULL) {
7462
if (sdp->extended != 0
7463
&& sdp->data.ptrvalue != NULL) {
7464
uop = (UserObjectPtr) sdp->data.ptrvalue;
7465
oip = uop->type;
7466
if (oip != NULL && StringCmp (oip->str, "StructuredComment") == 0) {
7467
for (ufp = uop->data; ufp != NULL; ufp = ufp->next) {
7468
oip = ufp->label;
7469
if (oip != NULL && StringCmp (oip->str, comment_field) == 0) {
7470
str = GetTextPortionFromString (ufp->data.ptrvalue, tp);
7471
if (str != NULL) {
7472
psip = ParseSourceInfoNew (bsp, NULL, sdp, NULL, str);
7473
if (psip == NULL) {
7474
str = MemFree (str);
7475
} else {
7476
ValNodeAddPointer (source_list, 0, psip);
7477
}
7478
}
7479
}
7480
}
7481
}
7482
}
7483
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_user, &dcontext);
7484
}
7485
}
7486
7487
7488
const CharPtr nomial_keywords[] = {
7489
"f. sp. ",
7490
"var.",
7491
"pv.",
7492
"bv.",
7493
"serovar",
7494
"subsp." };
7495
7496
const Int4 num_nomial_keywords = sizeof(nomial_keywords) / sizeof (CharPtr);
7497
7498
static CharPtr GetTextAfterNomial (CharPtr taxname)
7499
7500
{
7501
CharPtr ptr, nomial_end;
7502
Int4 i;
7503
Boolean found_keyword = TRUE;
7504
7505
ptr = StringChr (taxname, ' ');
7506
if (ptr == NULL) return NULL;
7507
/* skip over the first word and the spaces after it. */
7508
while (*ptr == ' ') {
7509
ptr++;
7510
}
7511
ptr = StringChr (ptr, ' ');
7512
/* if there are only two words, give up. */
7513
if (ptr == NULL) {
7514
return NULL;
7515
}
7516
nomial_end = ptr;
7517
while (*ptr == ' ') {
7518
ptr++;
7519
}
7520
7521
while (found_keyword) {
7522
found_keyword = FALSE;
7523
/* if the next word is a nomial keyword, skip that plus the first word that follows it. */
7524
for (i = 0; i < num_nomial_keywords && *nomial_end != 0; i++) {
7525
if (StringNCmp (ptr, nomial_keywords[i], StringLen(nomial_keywords[i])) == 0) {
7526
ptr += StringLen(nomial_keywords[i]);
7527
while (*ptr == ' ' ) {
7528
ptr++;
7529
}
7530
nomial_end = StringChr (ptr, ' ');
7531
if (nomial_end == NULL) {
7532
nomial_end = ptr + StringLen (ptr);
7533
} else {
7534
ptr = nomial_end;
7535
while (*ptr == ' ') {
7536
ptr++;
7537
}
7538
found_keyword = TRUE;
7539
}
7540
}
7541
}
7542
}
7543
return nomial_end;
7544
}
7545
7546
7547
static void
7548
GetOrgParseSourcesForBioSource
7549
(BioSourcePtr biop,
7550
BioseqPtr bsp,
7551
SeqDescrPtr sdp,
7552
SeqFeatPtr sfp,
7553
ParseSrcOrgPtr o,
7554
TextPortionPtr tp,
7555
ValNodePtr PNTR source_list)
7556
{
7557
CharPtr str = NULL, portion, tmp;
7558
ValNode vn;
7559
ParseSourceInfoPtr psip;
7560
7561
if (biop == NULL || o == NULL || o->field == NULL || source_list == NULL) return;
7562
7563
switch (o->field->choice) {
7564
case ParseSrcOrgChoice_source_qual :
7565
vn.choice = SourceQualChoice_textqual;
7566
vn.data.intvalue = o->field->data.intvalue;
7567
vn.next = NULL;
7568
str = GetSourceQualFromBioSource (biop, &vn, NULL);
7569
break;
7570
case ParseSrcOrgChoice_taxname_after_binomial :
7571
vn.choice = SourceQualChoice_textqual;
7572
vn.data.intvalue = Source_qual_taxname;
7573
vn.next = NULL;
7574
str = GetSourceQualFromBioSource (biop, &vn, NULL);
7575
tmp = GetTextAfterNomial (str);
7576
tmp = StringSave (tmp);
7577
str = MemFree (str);
7578
str = tmp;
7579
break;
7580
}
7581
portion = GetTextPortionFromString (str, tp);
7582
if (portion != NULL) {
7583
psip = ParseSourceInfoNew (bsp, sfp, sdp, NULL, portion);
7584
if (psip == NULL) {
7585
portion = MemFree (portion);
7586
} else {
7587
ValNodeAddPointer (source_list, 0, psip);
7588
}
7589
}
7590
str = MemFree (str);
7591
}
7592
7593
7594
static void GetOrgParseSourcesForBioseq (BioseqPtr bsp, ParseSrcOrgPtr o, TextPortionPtr tp, ValNodePtr PNTR source_list)
7595
{
7596
SeqDescrPtr sdp;
7597
SeqFeatPtr sfp;
7598
SeqMgrFeatContext fcontext;
7599
SeqMgrDescContext dcontext;
7600
7601
if (bsp == NULL || o == NULL || source_list == NULL) return;
7602
7603
if (o->type == Object_type_constraint_any || o->type == Object_type_constraint_descriptor) {
7604
for (sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_source, &dcontext);
7605
sdp != NULL;
7606
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_source, &dcontext)) {
7607
GetOrgParseSourcesForBioSource (sdp->data.ptrvalue, bsp, sdp, NULL, o, tp, source_list);
7608
}
7609
}
7610
7611
if (o->type == Object_type_constraint_any || o->type == Object_type_constraint_feature) {
7612
for (sfp = SeqMgrGetNextFeature (bsp, NULL, SEQFEAT_BIOSRC, 0, &fcontext);
7613
sfp != NULL;
7614
sfp = SeqMgrGetNextFeature (bsp, sfp, SEQFEAT_BIOSRC, 0, &fcontext)) {
7615
GetOrgParseSourcesForBioSource (sfp->data.value.ptrvalue, bsp, NULL, sfp, o, tp, source_list);
7616
}
7617
}
7618
}
7619
7620
7621
typedef struct parsesrccollection {
7622
ParseSrcPtr src;
7623
TextPortionPtr portion;
7624
ValNodePtr src_list;
7625
} ParseSrcCollectionData, PNTR ParseSrcCollectionPtr;
7626
7627
7628
static void FindParseSourceBioseqCallback (BioseqPtr bsp, Pointer userdata)
7629
{
7630
ParseSrcCollectionPtr psp;
7631
7632
if (bsp == NULL || userdata == NULL)
7633
{
7634
return;
7635
}
7636
7637
psp = (ParseSrcCollectionPtr) userdata;
7638
if (psp->src == NULL) return;
7639
7640
switch (psp->src->choice)
7641
{
7642
case ParseSrc_defline:
7643
if (!ISA_aa (bsp->mol)) {
7644
GetDeflineSourcesForBioseq (bsp, psp->portion, &(psp->src_list));
7645
}
7646
break;
7647
case ParseSrc_local_id:
7648
if (! ISA_aa (bsp->mol) && bsp->repr != Seq_repr_seg) {
7649
GetLocalIDSourcesForBioseq (bsp, psp->portion, &(psp->src_list));
7650
}
7651
break;
7652
case ParseSrc_file_id:
7653
GetNcbiFileSourceForBioseq (bsp, psp->portion, &(psp->src_list));
7654
break;
7655
case ParseSrc_org:
7656
GetOrgParseSourcesForBioseq (bsp, psp->src->data.ptrvalue, psp->portion, &(psp->src_list));
7657
break;
7658
case ParseSrc_comment:
7659
GetCommentSourcesForBioseq (bsp, psp->portion, &(psp->src_list));
7660
break;
7661
case ParseSrc_structured_comment:
7662
GetStructuredCommentSourcesForBioseq(bsp, psp->portion, psp->src->data.ptrvalue, &(psp->src_list));
7663
break;
7664
case ParseSrc_bankit_comment:
7665
if (!ISA_aa (bsp->mol)) {
7666
GetBankitCommentSourcesForBioseq (bsp, psp->portion, &(psp->src_list));
7667
}
7668
break;
7669
}
7670
}
7671
7672
7673
static void GetOrgNamesInRecordCallback (BioSourcePtr biop, Pointer userdata)
7674
{
7675
ValNodePtr PNTR org_names;
7676
7677
if (biop == NULL || biop->org == NULL || StringHasNoText (biop->org->taxname)
7678
|| userdata == NULL)
7679
{
7680
return;
7681
}
7682
7683
org_names = (ValNodePtr PNTR) userdata;
7684
7685
ValNodeAddPointer (org_names, 0, biop->org->taxname);
7686
}
7687
7688
7689
static void SetToUpper (CharPtr cp)
7690
{
7691
if (cp == NULL) return;
7692
while (*cp != 0) {
7693
if (isalpha (*cp)) {
7694
*cp = toupper (*cp);
7695
}
7696
cp++;
7697
}
7698
}
7699
7700
7701
static void
7702
FixCapitalizationInString
7703
(CharPtr PNTR pTitle,
7704
Uint2 capitalization,
7705
ValNodePtr org_names)
7706
{
7707
if (pTitle == NULL || capitalization == Cap_change_none) return;
7708
7709
switch (capitalization) {
7710
case Cap_change_tolower:
7711
ResetCapitalization (FALSE, *pTitle);
7712
FixAbbreviationsInElement (pTitle);
7713
FixOrgNamesInString (*pTitle, org_names);
7714
break;
7715
case Cap_change_toupper:
7716
SetToUpper (*pTitle);
7717
FixAbbreviationsInElement (pTitle);
7718
FixOrgNamesInString (*pTitle, org_names);
7719
break;
7720
case Cap_change_firstcap:
7721
ResetCapitalization (TRUE, *pTitle);
7722
FixAbbreviationsInElement (pTitle);
7723
FixOrgNamesInString (*pTitle, org_names);
7724
break;
7725
}
7726
}
7727
7728
7729
static void AddDeflineDestinationsForBioseq (BioseqPtr bsp, ValNodePtr PNTR dest_list)
7730
{
7731
SeqDescrPtr sdp;
7732
SeqMgrDescContext dcontext;
7733
7734
if (bsp == NULL || dest_list == NULL) {
7735
return;
7736
}
7737
7738
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_title, &dcontext);
7739
while (sdp != NULL) {
7740
ValNodeAddPointer (dest_list, OBJ_SEQDESC, sdp);
7741
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_title, &dcontext);
7742
}
7743
}
7744
7745
7746
static void AddFeatureDestinationsForBioseq (BioseqPtr bsp, FeatureFieldLegalPtr featfield, ValNodePtr PNTR dest_list)
7747
{
7748
SeqFeatPtr sfp;
7749
SeqMgrFeatContext fcontext;
7750
Int4 featdef;
7751
7752
if (bsp == NULL || featfield == NULL || dest_list == NULL) return;
7753
7754
featdef = GetFeatdefFromFeatureType (featfield->type);
7755
for (sfp = SeqMgrGetNextFeature (bsp, NULL, 0, featdef, &fcontext);
7756
sfp != NULL;
7757
sfp = SeqMgrGetNextFeature (bsp, sfp, 0, featdef, &fcontext)) {
7758
ValNodeAddPointer (dest_list, OBJ_SEQFEAT, sfp);
7759
}
7760
}
7761
7762
7763
static void GetBioSourceDestinationsForBioseq (BioseqPtr bsp, Uint2 object_type, ValNodePtr PNTR dest_list)
7764
{
7765
SeqDescrPtr sdp;
7766
SeqFeatPtr sfp;
7767
SeqMgrFeatContext fcontext;
7768
SeqMgrDescContext dcontext;
7769
7770
if (bsp == NULL || dest_list == NULL)
7771
{
7772
return;
7773
}
7774
7775
if (object_type == Object_type_constraint_any || object_type == Object_type_constraint_descriptor)
7776
{
7777
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_source, &dcontext);
7778
while (sdp != NULL)
7779
{
7780
ValNodeAddPointer (dest_list, OBJ_SEQDESC, sdp);
7781
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_source, &dcontext);
7782
}
7783
}
7784
7785
if (object_type == Object_type_constraint_any || object_type == Object_type_constraint_feature)
7786
{
7787
sfp = SeqMgrGetNextFeature (bsp, NULL, SEQFEAT_BIOSRC, 0, &fcontext);
7788
while (sfp != NULL)
7789
{
7790
ValNodeAddPointer (dest_list, OBJ_SEQFEAT, sfp);
7791
sfp = SeqMgrGetNextFeature (bsp, sfp, SEQFEAT_BIOSRC, 0, &fcontext);
7792
}
7793
}
7794
}
7795
7796
7797
static void AddParseDestinations (ParseSourceInfoPtr psip, ParseDestPtr dst)
7798
{
7799
ParseDstOrgPtr o;
7800
7801
if (psip == NULL || dst == NULL) return;
7802
7803
switch (dst->choice) {
7804
case ParseDest_defline :
7805
AddDeflineDestinationsForBioseq (psip->bsp, &(psip->dest_list));
7806
break;
7807
case ParseDest_org :
7808
o = (ParseDstOrgPtr) dst->data.ptrvalue;
7809
if ((o->type == Object_type_constraint_any || o->type == Object_type_constraint_descriptor)
7810
&& psip->sdp != NULL && psip->sdp->choice == Seq_descr_source) {
7811
ValNodeAddPointer (&(psip->dest_list), OBJ_SEQDESC, psip->sdp);
7812
} else if ((o->type == Object_type_constraint_any || o->type == Object_type_constraint_feature)
7813
&& psip->sfp != NULL && psip->sfp->data.choice == SEQFEAT_BIOSRC) {
7814
ValNodeAddPointer (&(psip->dest_list), OBJ_SEQFEAT, psip->sfp);
7815
} else {
7816
GetBioSourceDestinationsForBioseq (psip->bsp, o->type, &(psip->dest_list));
7817
}
7818
break;
7819
case ParseDest_featqual :
7820
AddFeatureDestinationsForBioseq (psip->bsp, dst->data.ptrvalue, &(psip->dest_list));
7821
break;
7822
case ParseDest_dbxref :
7823
GetBioSourceDestinationsForBioseq (psip->bsp, Object_type_constraint_any, &(psip->dest_list));
7824
break;
7825
}
7826
}
7827
7828
7829
static Boolean SourceHasOneUndeletedDestination (ParseSourceInfoPtr source)
7830
{
7831
Int4 num_seen = 0;
7832
ValNodePtr vnp;
7833
7834
if (source == NULL
7835
|| source->dest_list == NULL)
7836
{
7837
return FALSE;
7838
}
7839
7840
vnp = source->dest_list;
7841
while (vnp != NULL && num_seen < 2)
7842
{
7843
if (vnp->choice > 1)
7844
{
7845
num_seen ++;
7846
}
7847
vnp = vnp->next;
7848
}
7849
if (num_seen == 1)
7850
{
7851
return TRUE;
7852
}
7853
else
7854
{
7855
return FALSE;
7856
}
7857
}
7858
7859
7860
static void CombineSourcesForDestinations (ValNodePtr PNTR source_list)
7861
{
7862
ValNodePtr source1_vnp, source2_vnp, dest1_vnp, dest2_vnp;
7863
ValNodePtr source_new, del_vnp;
7864
ParseSourceInfoPtr psip1, psip2, new_psip;
7865
CharPtr comb_txt;
7866
7867
for (source1_vnp = *source_list;
7868
source1_vnp != NULL;
7869
source1_vnp = source1_vnp->next)
7870
{
7871
psip1 = (ParseSourceInfoPtr) source1_vnp->data.ptrvalue;
7872
if (psip1 == NULL || psip1->dest_list == NULL)
7873
{
7874
continue;
7875
}
7876
for (source2_vnp = source1_vnp->next;
7877
source2_vnp != NULL;
7878
source2_vnp = source2_vnp->next)
7879
{
7880
if (source2_vnp->choice > 0)
7881
{
7882
/* already marked for deletion */
7883
continue;
7884
}
7885
psip2 = (ParseSourceInfoPtr) source2_vnp->data.ptrvalue;
7886
if (psip2 == NULL || psip2->dest_list == NULL)
7887
{
7888
continue;
7889
}
7890
for (dest1_vnp = psip1->dest_list;
7891
dest1_vnp != NULL;
7892
dest1_vnp = dest1_vnp->next)
7893
{
7894
if (dest1_vnp->choice == 0)
7895
{
7896
/* already marked for deletion */
7897
continue;
7898
}
7899
for (dest2_vnp = psip2->dest_list;
7900
dest2_vnp != NULL;
7901
dest2_vnp = dest2_vnp->next)
7902
{
7903
if (dest2_vnp->choice == 0)
7904
{
7905
/* already marked for deletion */
7906
continue;
7907
}
7908
if (dest1_vnp->choice == dest2_vnp->choice
7909
&& dest1_vnp->data.ptrvalue == dest2_vnp->data.ptrvalue)
7910
{
7911
comb_txt = (CharPtr) (MemNew (sizeof (Char)
7912
* (StringLen (psip1->parse_src_txt)
7913
+ StringLen (psip2->parse_src_txt)
7914
+ 2)));
7915
StringCpy (comb_txt, psip1->parse_src_txt);
7916
StringCat (comb_txt, ";");
7917
StringCat (comb_txt, psip2->parse_src_txt);
7918
7919
/* If the first source has a single destination, then we can
7920
* add the text from the second source to the first and remove
7921
* the destination from the second source.
7922
*/
7923
if (SourceHasOneUndeletedDestination (psip1))
7924
{
7925
7926
psip1->parse_src_txt = MemFree (psip1->parse_src_txt);
7927
psip1->parse_src_txt = comb_txt;
7928
dest2_vnp->choice = 0;
7929
}
7930
/* If the first source has more than one destination and
7931
* the second source has a single destination, then we can
7932
* remove the repeated desination from the first source
7933
* and add the text from the first source to the second source.
7934
*/
7935
else if (SourceHasOneUndeletedDestination (psip2))
7936
{
7937
psip2->parse_src_txt = MemFree (psip2->parse_src_txt);
7938
psip2->parse_src_txt = comb_txt;
7939
dest1_vnp->choice = 0;
7940
}
7941
/* If the first and second sources have multiple destinations,
7942
* we need to remove the repeated destination from both the first
7943
* and second source and create a new source with the combined
7944
* text for just the repeated destination.
7945
*/
7946
else
7947
{
7948
new_psip = ParseSourceInfoNew (NULL, NULL, NULL, NULL, comb_txt);
7949
ValNodeAddPointer (&(new_psip->dest_list),
7950
dest1_vnp->choice,
7951
dest1_vnp->data.ptrvalue);
7952
dest1_vnp->choice = 0;
7953
dest2_vnp->choice = 0;
7954
source_new = ValNodeNew (NULL);
7955
source_new->choice = 0;
7956
source_new->data.ptrvalue = new_psip;
7957
source_new->next = source1_vnp->next;
7958
source1_vnp->next = source_new;
7959
}
7960
}
7961
}
7962
}
7963
7964
del_vnp = ValNodeExtractList (&(psip1->dest_list), 0);
7965
del_vnp = ValNodeFree (del_vnp);
7966
if (psip1->dest_list == NULL)
7967
{
7968
source1_vnp->choice = 1;
7969
}
7970
del_vnp = ValNodeExtractList (&(psip2->dest_list), 0);
7971
del_vnp = ValNodeFree (del_vnp);
7972
if (psip2->dest_list == NULL)
7973
{
7974
source2_vnp->choice = 1;
7975
}
7976
}
7977
}
7978
7979
/* now remove sources deleted */
7980
del_vnp = ValNodeExtractList (source_list, 1);
7981
del_vnp = ParseSourceListFree (del_vnp);
7982
}
7983
7984
7985
static BioseqSetPtr GetPartsForSourceDescriptorOnSegSet (SeqDescrPtr sdp)
7986
{
7987
ObjValNodePtr ovp;
7988
BioseqSetPtr bssp;
7989
SeqEntryPtr sep;
7990
7991
if (sdp == NULL || sdp->extended != 1) {
7992
return NULL;
7993
}
7994
ovp = (ObjValNodePtr) sdp;
7995
if (ovp->idx.parenttype != OBJ_BIOSEQSET || ovp->idx.parentptr == NULL) {
7996
return NULL;
7997
}
7998
bssp = (BioseqSetPtr) ovp->idx.parentptr;
7999
8000
if (bssp->_class == BioseqseqSet_class_nuc_prot
8001
&& IS_Bioseq_set (bssp->seq_set)
8002
&& bssp->seq_set->data.ptrvalue != NULL) {
8003
bssp = (BioseqSetPtr) bssp->seq_set->data.ptrvalue;
8004
}
8005
8006
if (bssp->_class == BioseqseqSet_class_segset) {
8007
sep = bssp->seq_set;
8008
while (sep != NULL) {
8009
if (IS_Bioseq_set (sep) && sep->data.ptrvalue != NULL) {
8010
bssp = (BioseqSetPtr) sep->data.ptrvalue;
8011
if (bssp->_class == BioseqseqSet_class_parts) {
8012
return bssp;
8013
}
8014
}
8015
sep = sep->next;
8016
}
8017
}
8018
8019
return NULL;
8020
}
8021
8022
8023
static SeqDescrPtr FindSourceDescriptorInSeqEntry (SeqEntryPtr sep)
8024
{
8025
BioseqPtr bsp;
8026
BioseqSetPtr bssp;
8027
SeqDescrPtr sdp = NULL;
8028
8029
if (sep != NULL && sep->data.ptrvalue != NULL) {
8030
if (IS_Bioseq (sep)) {
8031
bsp = (BioseqPtr) sep->data.ptrvalue;
8032
sdp = bsp->descr;
8033
} else if (IS_Bioseq_set (sep)) {
8034
bssp = (BioseqSetPtr) sep->data.ptrvalue;
8035
sdp = bssp->descr;
8036
}
8037
while (sdp != NULL && sdp->choice != Seq_descr_source)
8038
{
8039
sdp = sdp->next;
8040
}
8041
}
8042
return sdp;
8043
}
8044
8045
8046
static SeqDescrPtr PropagateToSeqEntry (SeqEntryPtr sep, SeqDescrPtr sdp)
8047
{
8048
BioseqPtr bsp;
8049
BioseqSetPtr bssp;
8050
SeqDescrPtr new_sdp = NULL;
8051
8052
if (sep != NULL && sep->data.ptrvalue != NULL) {
8053
if (IS_Bioseq (sep)) {
8054
bsp = (BioseqPtr) sep->data.ptrvalue;
8055
new_sdp = AsnIoMemCopy ((Pointer) sdp,
8056
(AsnReadFunc) SeqDescrAsnRead,
8057
(AsnWriteFunc) SeqDescrAsnWrite);
8058
ValNodeLink (&(bsp->descr), new_sdp);
8059
} else if (IS_Bioseq_set (sep)) {
8060
bssp = (BioseqSetPtr) sep->data.ptrvalue;
8061
new_sdp = AsnIoMemCopy ((Pointer) sdp,
8062
(AsnReadFunc) SeqDescrAsnRead,
8063
(AsnWriteFunc) SeqDescrAsnWrite);
8064
ValNodeLink (&(bssp->descr), new_sdp);
8065
}
8066
}
8067
return new_sdp;
8068
}
8069
8070
8071
static void PropagateSourceOnSegSetForParse (ValNodePtr parse_source_list)
8072
{
8073
ParseSourceInfoPtr psip;
8074
ValNodePtr vnp_src, vnp_dst;
8075
SeqDescrPtr sdp, other_sdp;
8076
SeqEntryPtr sep;
8077
ValNodePtr extra_dests = NULL;
8078
BioseqSetPtr parts_bssp;
8079
8080
for (vnp_src = parse_source_list; vnp_src != NULL; vnp_src = vnp_src->next) {
8081
psip = (ParseSourceInfoPtr) vnp_src->data.ptrvalue;
8082
if (psip != NULL) {
8083
for (vnp_dst = psip->dest_list; vnp_dst != NULL; vnp_dst = vnp_dst->next) {
8084
if (vnp_dst->choice == OBJ_SEQDESC) {
8085
sdp = (SeqDescrPtr) vnp_dst->data.ptrvalue;
8086
if (sdp != NULL && sdp->choice == Seq_descr_source) {
8087
parts_bssp = GetPartsForSourceDescriptorOnSegSet (sdp);
8088
if (parts_bssp != NULL) {
8089
for (sep = parts_bssp->seq_set; sep != NULL; sep = sep->next) {
8090
if (IS_Bioseq(sep) && sep->data.ptrvalue == psip->bsp) {
8091
other_sdp = FindSourceDescriptorInSeqEntry (sep);
8092
if (other_sdp == NULL) {
8093
other_sdp = PropagateToSeqEntry (sep, sdp);
8094
ValNodeAddPointer (&extra_dests, OBJ_SEQDESC, other_sdp);
8095
}
8096
}
8097
}
8098
8099
/* set choice to 0 so master won't be a destination */
8100
vnp_dst->choice = 0;
8101
8102
}
8103
}
8104
}
8105
}
8106
/* add extra destinations to list */
8107
ValNodeLink (&psip->dest_list, extra_dests);
8108
extra_dests = NULL;
8109
}
8110
}
8111
8112
}
8113
8114
8115
static Boolean SetDBxrefForBioSource (BioSourcePtr biop, CharPtr db_name, CharPtr str, Uint2 existing_text)
8116
{
8117
ValNodePtr dbx;
8118
DbtagPtr dbtag;
8119
Boolean found = FALSE;
8120
Char buf[20];
8121
Boolean rval = FALSE;
8122
8123
if (biop == NULL || StringHasNoText (db_name) || StringHasNoText (str)) {
8124
return FALSE;
8125
}
8126
8127
if (biop->org == NULL)
8128
{
8129
biop->org = OrgRefNew();
8130
}
8131
dbx = biop->org->db;
8132
while (dbx != NULL && !found)
8133
{
8134
dbtag = (DbtagPtr) dbx->data.ptrvalue;
8135
if (dbtag != NULL && dbtag->tag != NULL
8136
&& StringCmp (dbtag->db, db_name) == 0)
8137
{
8138
found = TRUE;
8139
}
8140
if (!found)
8141
{
8142
dbx = dbx->next;
8143
}
8144
}
8145
if (!found)
8146
{
8147
dbtag = DbtagNew();
8148
dbtag->db = StringSave (db_name);
8149
ValNodeAddPointer (&(biop->org->db), 0, dbtag);
8150
}
8151
if (dbtag->tag == NULL)
8152
{
8153
dbtag->tag = ObjectIdNew();
8154
}
8155
/* if it was a number before, make it a string now */
8156
if (dbtag->tag->id > 0 && dbtag->tag->str == NULL)
8157
{
8158
sprintf (buf, "%s", dbtag->tag->id);
8159
dbtag->tag->id = 0;
8160
dbtag->tag->str = StringSave (buf);
8161
}
8162
rval = SetStringValue (&(dbtag->tag->str), str, existing_text);
8163
return rval;
8164
}
8165
8166
8167
static Int4 SetFieldForDestList (ValNodePtr dest_list, ParseDestPtr field, CharPtr str, Uint2 existing_text)
8168
{
8169
ValNodePtr vnp;
8170
SeqDescrPtr sdp;
8171
CharPtr cp;
8172
BioSourcePtr biop;
8173
ParseDstOrgPtr o;
8174
FeatureFieldLegalPtr fl;
8175
FeatureField f;
8176
Int4 num_succeeded = 0;
8177
8178
if (dest_list == NULL || field == NULL) return 0;
8179
8180
switch (field->choice) {
8181
case ParseDest_defline :
8182
for (vnp = dest_list; vnp != NULL; vnp = vnp->next) {
8183
if (vnp->choice == OBJ_SEQDESC && vnp->data.ptrvalue != NULL) {
8184
sdp = (SeqDescrPtr) vnp->data.ptrvalue;
8185
if (sdp->choice == Seq_descr_title) {
8186
cp = sdp->data.ptrvalue;
8187
if (SetStringValue (&cp, str, existing_text)) {
8188
num_succeeded++;
8189
}
8190
sdp->data.ptrvalue = cp;
8191
}
8192
}
8193
}
8194
break;
8195
case ParseDest_org :
8196
o = (ParseDstOrgPtr) field->data.ptrvalue;
8197
if (o != NULL) {
8198
for (vnp = dest_list; vnp != NULL; vnp = vnp->next) {
8199
biop = GetBioSourceFromObject (vnp->choice, vnp->data.ptrvalue);
8200
if (SetSourceQualInBioSource (biop, o->field, NULL, str, existing_text)) {
8201
num_succeeded++;
8202
}
8203
}
8204
}
8205
break;
8206
case ParseDest_featqual:
8207
fl = (FeatureFieldLegalPtr) field->data.ptrvalue;
8208
if (fl != NULL) {
8209
f.type = fl->type;
8210
f.field = ValNodeNew(NULL);
8211
f.field->next = NULL;
8212
f.field->choice = FeatQualChoice_legal_qual;
8213
f.field->data.intvalue = fl->field;
8214
for (vnp = dest_list; vnp != NULL; vnp = vnp->next) {
8215
if (SetQualOnFeature (vnp->data.ptrvalue, &f, NULL, str, existing_text)) {
8216
num_succeeded++;
8217
}
8218
}
8219
f.field = ValNodeFree (f.field);
8220
}
8221
break;
8222
case ParseDest_dbxref:
8223
if (!StringHasNoText (field->data.ptrvalue)) {
8224
for (vnp = dest_list; vnp != NULL; vnp = vnp->next) {
8225
biop = GetBioSourceFromObject (vnp->choice, vnp->data.ptrvalue);
8226
if (SetDBxrefForBioSource (biop, field->data.ptrvalue, str, existing_text)) {
8227
num_succeeded++;
8228
}
8229
}
8230
}
8231
break;
8232
}
8233
return num_succeeded;
8234
}
8235
8236
8237
static void StripFieldForSrcList (ParseSourceInfoPtr psip, ParseSrcPtr field, TextPortionPtr text_portion)
8238
{
8239
CharPtr str;
8240
ParseSrcOrgPtr o;
8241
BioSourcePtr biop;
8242
8243
if (psip == NULL || field == NULL || text_portion == NULL) return;
8244
8245
switch (field->choice) {
8246
case ParseSrc_defline :
8247
if (psip->sdp != NULL && psip->sdp->choice == Seq_descr_title) {
8248
ReplaceStringForParse (psip->sdp->data.ptrvalue, text_portion);
8249
}
8250
break;
8251
case ParseSrc_org :
8252
o = (ParseSrcOrgPtr) field->data.ptrvalue;
8253
if (o != NULL) {
8254
if (psip->sdp != NULL && psip->sdp->choice == Seq_descr_source) {
8255
biop = (BioSourcePtr) psip->sdp->data.ptrvalue;
8256
str = GetSourceQualFromBioSource (biop, o->field, NULL);
8257
ReplaceStringForParse (str, text_portion);
8258
SetSourceQualInBioSource (biop, o->field, NULL, str, ExistingTextOption_replace_old);
8259
str = MemFree (str);
8260
} else if (psip->sfp != NULL && psip->sfp->data.choice == SEQFEAT_BIOSRC) {
8261
biop = (BioSourcePtr) psip->sfp->data.value.ptrvalue;
8262
str = GetSourceQualFromBioSource (biop, o->field, NULL);
8263
ReplaceStringForParse (str, text_portion);
8264
SetSourceQualInBioSource (biop, o->field, NULL, str, ExistingTextOption_replace_old);
8265
str = MemFree (str);
8266
}
8267
}
8268
break;
8269
case ParseSrc_comment:
8270
if (psip->sdp != NULL) {
8271
if (psip->sdp->choice == Seq_descr_user) {
8272
StripBankitCommentForParse (psip->sdp, text_portion);
8273
} else if (psip->sdp->choice == Seq_descr_comment) {
8274
ReplaceStringForParse (psip->sdp->data.ptrvalue, text_portion);
8275
}
8276
}
8277
if (psip->sfp != NULL && psip->sfp->data.choice == SEQFEAT_COMMENT) {
8278
ReplaceStringForParse (psip->sfp->data.value.ptrvalue, text_portion);
8279
}
8280
break;
8281
case ParseSrc_bankit_comment:
8282
if (psip->sdp != NULL && psip->sdp->choice == Seq_descr_user) {
8283
StripBankitCommentForParse (psip->sdp, text_portion);
8284
}
8285
break;
8286
case ParseSrc_structured_comment:
8287
if (psip->sdp != NULL && psip->sdp->choice == Seq_descr_user) {
8288
StripStructuredCommentForParse (psip->sdp, field->data.ptrvalue, text_portion);
8289
}
8290
break;
8291
}
8292
}
8293
8294
8295
static Int4 ApplyParseActionToSeqEntry (ParseActionPtr action, SeqEntryPtr sep)
8296
{
8297
ParseSrcCollectionData psd;
8298
ParseSourceInfoPtr psip;
8299
ValNodePtr orgnames = NULL, source_list_for_removal = NULL, vnp;
8300
Int4 num_succeeded = 0;
8301
8302
if (action == NULL || sep == NULL) return 0;
8303
8304
psd.src = action->src;
8305
psd.portion = action->portion;
8306
psd.src_list = NULL;
8307
8308
/* first, we need to get a list of the parse sources */
8309
VisitBioseqsInSep (sep, &psd, FindParseSourceBioseqCallback);
8310
8311
if (action->capitalization != Cap_change_none) {
8312
/* if we will be fixing capitalization, get org names to use in fixes */
8313
VisitBioSourcesInSep (sep, &orgnames, GetOrgNamesInRecordCallback);
8314
}
8315
8316
/* for each parse source, we need to get a list of the destinations */
8317
for (vnp = psd.src_list; vnp != NULL; vnp = vnp->next)
8318
{
8319
if (vnp->data.ptrvalue == NULL) continue;
8320
psip = (ParseSourceInfoPtr) vnp->data.ptrvalue;
8321
if (action->remove_from_parsed) {
8322
ValNodeAddPointer (&source_list_for_removal, 0, ParseSourceInfoCopy (psip));
8323
}
8324
/* fix source text */
8325
FixCapitalizationInString (&(psip->parse_src_txt), action->capitalization, orgnames);
8326
8327
/* find destinations */
8328
AddParseDestinations (psip, action->dest);
8329
8330
}
8331
8332
/* free orgname list if we created it */
8333
orgnames = ValNodeFree (orgnames);
8334
8335
CombineSourcesForDestinations (&(psd.src_list));
8336
8337
if (action->dest->choice == ParseDest_org) {
8338
PropagateSourceOnSegSetForParse (psd.src_list);
8339
}
8340
8341
/* now do the parsing */
8342
for (vnp = psd.src_list; vnp != NULL; vnp = vnp->next) {
8343
psip = (ParseSourceInfoPtr) vnp->data.ptrvalue;
8344
num_succeeded += SetFieldForDestList (psip->dest_list, action->dest, psip->parse_src_txt, action->existing_text);
8345
}
8346
8347
/* now remove strings from sources */
8348
for (vnp = source_list_for_removal; vnp != NULL; vnp = vnp->next)
8349
{
8350
if (vnp->data.ptrvalue == NULL) continue;
8351
psip = (ParseSourceInfoPtr) vnp->data.ptrvalue;
8352
StripFieldForSrcList (psip, action->src, action->portion);
8353
}
8354
return num_succeeded;
8355
}
8356
8357
8358
static void SetCdRegionGeneticCode (SeqFeatPtr cds)
8359
{
8360
CdRegionPtr crp;
8361
SeqEntryPtr parent_sep;
8362
BioseqPtr bsp;
8363
Int4 genCode;
8364
ValNodePtr code, vnp;
8365
8366
if (cds == NULL || cds->data.choice != SEQFEAT_CDREGION) return;
8367
if (cds->data.value.ptrvalue == NULL) {
8368
cds->data.value.ptrvalue = CdRegionNew();
8369
}
8370
crp = (CdRegionPtr) cds->data.value.ptrvalue;
8371
bsp = BioseqFindFromSeqLoc (cds->location);
8372
if (bsp == NULL) return;
8373
parent_sep = GetBestTopParentForData (bsp->idx.entityID, bsp);
8374
genCode = SeqEntryToGeneticCode (parent_sep, NULL, NULL, 0);
8375
8376
code = ValNodeNew (NULL);
8377
if (code != NULL) {
8378
code->choice = 254;
8379
vnp = ValNodeNew (NULL);
8380
code->data.ptrvalue = vnp;
8381
if (vnp != NULL) {
8382
vnp->choice = 2;
8383
vnp->data.intvalue = genCode;
8384
}
8385
}
8386
crp->genetic_code = code;
8387
}
8388
8389
8390
static void CreateDataForFeature (SeqFeatPtr sfp, Int4 feature_type)
8391
{
8392
Int4 featdef, seqfeattype;
8393
CharPtr label = NULL;
8394
RnaRefPtr rrp;
8395
GBQualPtr gbq;
8396
ImpFeatPtr ifp;
8397
8398
featdef = GetFeatdefFromFeatureType (feature_type);
8399
sfp->idx.subtype = featdef;
8400
seqfeattype = FindFeatFromFeatDefType (featdef);
8401
switch (seqfeattype) {
8402
case SEQFEAT_GENE:
8403
sfp->data.value.ptrvalue = GeneRefNew();
8404
break;
8405
case SEQFEAT_CDREGION:
8406
sfp->data.value.ptrvalue = CdRegionNew();
8407
SetCdRegionGeneticCode (sfp);
8408
break;
8409
case SEQFEAT_RNA:
8410
rrp = RnaRefNew();
8411
rrp->ext.choice = 0;
8412
sfp->data.value.ptrvalue = rrp;
8413
switch (featdef) {
8414
case FEATDEF_preRNA:
8415
rrp->type = RNA_TYPE_premsg;
8416
break;
8417
case FEATDEF_mRNA:
8418
rrp->type = RNA_TYPE_mRNA;
8419
break;
8420
case FEATDEF_tRNA:
8421
rrp->type = RNA_TYPE_tRNA;
8422
break;
8423
case FEATDEF_rRNA:
8424
rrp->type = RNA_TYPE_rRNA;
8425
break;
8426
case FEATDEF_snRNA:
8427
rrp->type = RNA_TYPE_other;
8428
rrp->ext.choice = 1;
8429
rrp->ext.value.ptrvalue = StringSave ("ncRNA");
8430
gbq = GBQualNew ();
8431
gbq->qual = StringSave ("ncRNA_class");
8432
gbq->val = StringSave ("snRNA");
8433
break;
8434
case FEATDEF_scRNA:
8435
rrp->type = RNA_TYPE_other;
8436
rrp->ext.choice = 1;
8437
rrp->ext.value.ptrvalue = StringSave ("ncRNA");
8438
gbq = GBQualNew ();
8439
gbq->qual = StringSave ("ncRNA_class");
8440
gbq->val = StringSave ("scRNA");
8441
break;
8442
case FEATDEF_tmRNA:
8443
rrp->type = RNA_TYPE_other;
8444
rrp->ext.choice = 1;
8445
rrp->ext.value.ptrvalue = StringSave ("tmRNA");
8446
break;
8447
case FEATDEF_ncRNA:
8448
rrp->type = RNA_TYPE_other;
8449
rrp->ext.choice = 1;
8450
rrp->ext.value.ptrvalue = StringSave ("ncRNA");
8451
break;
8452
}
8453
break;
8454
case SEQFEAT_IMP:
8455
ifp = ImpFeatNew();
8456
sfp->data.value.ptrvalue = ifp;
8457
label = GetFeatureNameFromFeatureType (feature_type);
8458
ifp->key = StringSave (label);
8459
break;
8460
}
8461
}
8462
8463
8464
static void ExtraCDSCreationActions (SeqFeatPtr cds, SeqEntryPtr parent_sep)
8465
{
8466
ByteStorePtr bs;
8467
CharPtr prot, ptr;
8468
BioseqPtr bsp;
8469
Char ch;
8470
Int4 i;
8471
SeqEntryPtr psep, nsep;
8472
MolInfoPtr mip;
8473
ValNodePtr vnp, descr;
8474
SeqFeatPtr prot_sfp;
8475
ProtRefPtr prp;
8476
Boolean partial5, partial3;
8477
8478
if (cds == NULL) return;
8479
8480
CheckSeqLocForPartial (cds->location, &partial5, &partial3);
8481
8482
/* Create corresponding protein sequence data for the CDS */
8483
8484
bs = ProteinFromCdRegionEx (cds, TRUE, FALSE);
8485
if (NULL == bs)
8486
return;
8487
8488
prot = BSMerge (bs, NULL);
8489
bs = BSFree (bs);
8490
if (NULL == prot)
8491
return;
8492
8493
ptr = prot;
8494
ch = *ptr;
8495
while (ch != '\0') {
8496
*ptr = TO_UPPER (ch);
8497
ptr++;
8498
ch = *ptr;
8499
}
8500
i = StringLen (prot);
8501
if (i > 0 && prot [i - 1] == '*') {
8502
prot [i - 1] = '\0';
8503
}
8504
bs = BSNew (1000);
8505
if (bs != NULL) {
8506
ptr = prot;
8507
BSWrite (bs, (VoidPtr) ptr, (Int4) StringLen (ptr));
8508
}
8509
8510
/* Create the product protein Bioseq */
8511
8512
bsp = BioseqNew ();
8513
if (NULL == bsp)
8514
return;
8515
8516
bsp->repr = Seq_repr_raw;
8517
bsp->mol = Seq_mol_aa;
8518
bsp->seq_data_type = Seq_code_ncbieaa;
8519
bsp->seq_data = (SeqDataPtr) bs;
8520
bsp->length = BSLen (bs);
8521
bs = NULL;
8522
bsp->id = MakeNewProteinSeqId (cds->location, NULL);
8523
SeqMgrAddToBioseqIndex (bsp);
8524
8525
/* Create a new SeqEntry for the Prot Bioseq */
8526
8527
psep = SeqEntryNew ();
8528
if (NULL == psep)
8529
return;
8530
8531
psep->choice = 1;
8532
psep->data.ptrvalue = (Pointer) bsp;
8533
SeqMgrSeqEntry (SM_BIOSEQ, (Pointer) bsp, psep);
8534
8535
/* Add a descriptor to the protein Bioseq */
8536
8537
mip = MolInfoNew ();
8538
if (NULL == mip)
8539
return;
8540
8541
mip->biomol = 8;
8542
mip->tech = 8;
8543
if (partial5 && partial3) {
8544
mip->completeness = 5;
8545
} else if (partial5) {
8546
mip->completeness = 3;
8547
} else if (partial3) {
8548
mip->completeness = 4;
8549
}
8550
vnp = CreateNewDescriptor (psep, Seq_descr_molinfo);
8551
if (NULL == vnp)
8552
return;
8553
8554
vnp->data.ptrvalue = (Pointer) mip;
8555
8556
/**/
8557
8558
descr = ExtractBioSourceAndPubs (parent_sep);
8559
8560
AddSeqEntryToSeqEntry (parent_sep, psep, TRUE);
8561
nsep = FindNucSeqEntry (parent_sep);
8562
ReplaceBioSourceAndPubs (parent_sep, descr);
8563
SetSeqFeatProduct (cds, bsp);
8564
8565
prp = ProtRefNew ();
8566
8567
if (prp != NULL) {
8568
prot_sfp = CreateNewFeature (psep, NULL, SEQFEAT_PROT, NULL);
8569
if (prot_sfp != NULL) {
8570
prot_sfp->data.value.ptrvalue = (Pointer) prp;
8571
SetSeqLocPartial (prot_sfp->location, partial5, partial3);
8572
prot_sfp->partial = (partial5 || partial3);
8573
}
8574
}
8575
}
8576
8577
8578
static SeqLocPtr LocationFromApplyFeatureAction (BioseqPtr bsp, ApplyFeatureActionPtr action)
8579
{
8580
LocationIntervalPtr l;
8581
SeqLocPtr slp = NULL;
8582
Uint1 strand = Seq_strand_plus;
8583
Int4 from, to;
8584
8585
if (bsp == NULL || action == NULL || action->location == NULL) return NULL;
8586
8587
if (!action->plus_strand) {
8588
strand = Seq_strand_minus;
8589
}
8590
if (action->location->choice == LocationChoice_interval) {
8591
l = (LocationIntervalPtr) action->location->data.ptrvalue;
8592
if (l != NULL) {
8593
from = MIN (l->from, l->to);
8594
to = MAX (l->from, l->to);
8595
slp = SeqLocIntNew (from, to, strand, SeqIdFindWorst (bsp->id));
8596
}
8597
} else if (action->location->choice == LocationChoice_whole_sequence) {
8598
slp = SeqLocIntNew (0, bsp->length - 1, strand, SeqIdFindWorst (bsp->id));
8599
}
8600
SetSeqLocPartial (slp, action->partial5, action->partial3);
8601
return slp;
8602
}
8603
8604
8605
static Boolean OkToApplyToBioseq (ApplyFeatureActionPtr action, BioseqPtr bsp)
8606
{
8607
SeqFeatPtr sfp;
8608
SeqMgrFeatContext context;
8609
Int4 featdef;
8610
Boolean rval = TRUE;
8611
8612
if (action == NULL || bsp == NULL) return FALSE;
8613
8614
if (!action->add_redundant) {
8615
featdef = GetFeatdefFromFeatureType (action->type);
8616
sfp = SeqMgrGetNextFeature (bsp, NULL, 0, featdef, &context);
8617
if (sfp != NULL) {
8618
rval = FALSE;
8619
}
8620
}
8621
return rval;
8622
}
8623
8624
static void AddParts (ApplyFeatureActionPtr action, BioseqSetPtr parts, ValNodePtr PNTR bsp_list)
8625
{
8626
SeqEntryPtr sep;
8627
Int4 seg_num;
8628
8629
if (action == NULL || !action->apply_to_parts
8630
|| parts == NULL || parts->_class != BioseqseqSet_class_parts
8631
|| bsp_list == NULL) {
8632
return;
8633
}
8634
8635
if (action->only_seg_num > -1) {
8636
seg_num = 0;
8637
sep = parts->seq_set;
8638
while (seg_num < action->only_seg_num && sep != NULL) {
8639
sep = sep->next;
8640
seg_num++;
8641
}
8642
if (sep != NULL && IS_Bioseq (sep) && OkToApplyToBioseq (action, sep->data.ptrvalue)) {
8643
ValNodeAddPointer (bsp_list, OBJ_BIOSEQ, sep->data.ptrvalue);
8644
}
8645
} else {
8646
for (sep = parts->seq_set; sep != NULL; sep = sep->next) {
8647
if (IS_Bioseq (sep) && OkToApplyToBioseq (action, sep->data.ptrvalue)) {
8648
ValNodeAddPointer (bsp_list, OBJ_BIOSEQ, sep->data.ptrvalue);
8649
}
8650
}
8651
}
8652
}
8653
8654
8655
static void AddSequenceOrParts (ApplyFeatureActionPtr action, BioseqPtr bsp, ValNodePtr PNTR bsp_list)
8656
{
8657
BioseqSetPtr bssp, parts;
8658
SeqEntryPtr sep;
8659
8660
if (action == NULL || bsp == NULL || bsp_list == NULL) return;
8661
8662
if (bsp->idx.parenttype == OBJ_BIOSEQSET && bsp->idx.parentptr != NULL) {
8663
bssp = (BioseqSetPtr) bsp->idx.parentptr;
8664
if (bssp->_class == BioseqseqSet_class_segset) {
8665
if (action->apply_to_parts) {
8666
sep = bssp->seq_set;
8667
while (sep != NULL && !IS_Bioseq_set (sep)) {
8668
sep = sep->next;
8669
}
8670
if (sep != NULL) {
8671
AddParts (action, sep->data.ptrvalue, bsp_list);
8672
}
8673
} else {
8674
if (OkToApplyToBioseq (action, bsp)) {
8675
ValNodeAddPointer (bsp_list, OBJ_BIOSEQ, bsp);
8676
}
8677
}
8678
} else if (bssp->_class == BioseqseqSet_class_parts) {
8679
if (action->apply_to_parts) {
8680
AddParts (action, bssp, bsp_list);
8681
} else {
8682
parts = bssp;
8683
if (parts->idx.parenttype == OBJ_BIOSEQSET && parts->idx.parentptr != NULL) {
8684
bssp = (BioseqSetPtr) parts->idx.parentptr;
8685
if (IS_Bioseq (bssp->seq_set) && OkToApplyToBioseq (action, bssp->seq_set->data.ptrvalue)) {
8686
ValNodeAddPointer (bsp_list, OBJ_BIOSEQ, bsp_list);
8687
}
8688
}
8689
}
8690
} else {
8691
if (OkToApplyToBioseq (action, bsp)) {
8692
ValNodeAddPointer (bsp_list, OBJ_BIOSEQ, bsp);
8693
}
8694
}
8695
} else {
8696
if (OkToApplyToBioseq (action, bsp)) {
8697
ValNodeAddPointer (bsp_list, OBJ_BIOSEQ, bsp);
8698
}
8699
}
8700
}
8701
8702
static void AddSequenceOrPartsFromSeqEntry (ApplyFeatureActionPtr action, SeqEntryPtr sep, ValNodePtr PNTR bsp_list)
8703
{
8704
BioseqSetPtr bssp;
8705
SeqEntryPtr seq_set;
8706
8707
if (action == NULL || sep == NULL) return;
8708
8709
while (sep != NULL) {
8710
if (IS_Bioseq (sep)) {
8711
AddSequenceOrParts (action, sep->data.ptrvalue, bsp_list);
8712
} else if (IS_Bioseq_set (sep)) {
8713
bssp = (BioseqSetPtr) sep->data.ptrvalue;
8714
if (bssp->_class == BioseqseqSet_class_segset) {
8715
/* find master segment */
8716
seq_set = bssp->seq_set;
8717
while (seq_set != NULL && !IS_Bioseq (seq_set)) {
8718
seq_set = seq_set->next;
8719
}
8720
if (seq_set != NULL) {
8721
AddSequenceOrParts (action, seq_set->data.ptrvalue, bsp_list);
8722
}
8723
} else if (bssp->_class == BioseqseqSet_class_nuc_prot) {
8724
/* find nucleotide sequence */
8725
seq_set = bssp->seq_set;
8726
if (seq_set != NULL) {
8727
if (IS_Bioseq_set (seq_set)) {
8728
/* nucleotide is segmented set */
8729
bssp = (BioseqSetPtr) seq_set->data.ptrvalue;
8730
if (bssp != NULL && bssp->_class == BioseqseqSet_class_segset
8731
&& bssp->seq_set != NULL && IS_Bioseq (bssp->seq_set)) {
8732
AddSequenceOrParts (action, bssp->seq_set->data.ptrvalue, bsp_list);
8733
}
8734
} else if (IS_Bioseq (seq_set)) {
8735
AddSequenceOrParts (action, seq_set->data.ptrvalue, bsp_list);
8736
}
8737
}
8738
} else {
8739
/* add from set members */
8740
AddSequenceOrPartsFromSeqEntry (action, bssp->seq_set, bsp_list);
8741
}
8742
}
8743
sep = sep->next;
8744
}
8745
}
8746
8747
8748
static void AdjustProteinSequenceForReadingFrame (SeqFeatPtr cds)
8749
{
8750
BioseqPtr protbsp, bsp;
8751
ByteStorePtr bs;
8752
SeqFeatPtr prot_sfp;
8753
Boolean partial5, partial3;
8754
8755
if (cds == NULL || cds->data.choice != SEQFEAT_CDREGION) return;
8756
8757
protbsp = BioseqFindFromSeqLoc (cds->product);
8758
8759
if (protbsp == NULL) {
8760
bsp = BioseqFindFromSeqLoc (cds->location);
8761
if (bsp != NULL) {
8762
ExtraCDSCreationActions (cds, GetBestTopParentForData (bsp->idx.entityID, bsp));
8763
}
8764
} else {
8765
bs = ProteinFromCdRegionExWithTrailingCodonHandling (cds,
8766
TRUE,
8767
FALSE,
8768
FALSE);
8769
protbsp->seq_data = (SeqDataPtr) BSFree ((ByteStorePtr)(protbsp->seq_data));
8770
protbsp->seq_data = (SeqDataPtr) bs;
8771
protbsp->length = BSLen (bs);
8772
prot_sfp = GetProtFeature (protbsp);
8773
if (prot_sfp == NULL) {
8774
CheckSeqLocForPartial (cds->location, &partial5, &partial3);
8775
prot_sfp = CreateNewFeatureOnBioseq (protbsp, SEQFEAT_PROT, NULL);
8776
prot_sfp->data.value.ptrvalue = ProtRefNew ();
8777
SetSeqLocPartial (prot_sfp->location, partial5, partial3);
8778
prot_sfp->partial = (partial5 || partial3);
8779
} else {
8780
if (SeqLocLen (prot_sfp->location) != protbsp->length) {
8781
prot_sfp->location = SeqLocFree (prot_sfp->location);
8782
prot_sfp->location = SeqLocIntNew (0, protbsp->length - 1, Seq_strand_plus, SeqIdFindWorst (protbsp->id));
8783
}
8784
}
8785
}
8786
}
8787
8788
8789
static Int4 ApplyApplyFeatureActionToSeqEntry (ApplyFeatureActionPtr action, SeqEntryPtr sep)
8790
{
8791
ValNodePtr bsp_list = NULL, vnp, field_vnp;
8792
Int4 featdef, seqfeattype;
8793
BioseqPtr bsp;
8794
SeqFeatPtr sfp;
8795
SeqLocPtr slp;
8796
FeatQualLegalValPtr q;
8797
FeatureField f;
8798
SeqIdPtr sip;
8799
SeqFeatPtr gene;
8800
Int4 num_created = 0;
8801
8802
if (sep == NULL || action == NULL) return 0;
8803
8804
/* first, get list of Bioseqs to apply features to */
8805
/* relevant values : seq_list, add_redundant, apply_to_parts, only_seg_num */
8806
if (action->seq_list != NULL && action->seq_list->choice == SequenceListChoice_list) {
8807
for (vnp = action->seq_list->data.ptrvalue; vnp != NULL; vnp = vnp->next) {
8808
sip = CreateSeqIdFromText (vnp->data.ptrvalue, sep);
8809
bsp = BioseqFind (sip);
8810
if (bsp != NULL) {
8811
AddSequenceOrParts (action, bsp, &bsp_list);
8812
}
8813
}
8814
} else {
8815
AddSequenceOrPartsFromSeqEntry (action, sep, &bsp_list);
8816
}
8817
8818
/* now add feature to each bioseq in list */
8819
for (vnp = bsp_list; vnp != NULL; vnp = vnp->next) {
8820
bsp = vnp->data.ptrvalue;
8821
if (bsp == NULL) continue;
8822
featdef = GetFeatdefFromFeatureType (action->type);
8823
seqfeattype = FindFeatFromFeatDefType (featdef);
8824
slp = LocationFromApplyFeatureAction (bsp, action);
8825
sfp = CreateNewFeatureOnBioseq (bsp, seqfeattype, slp);
8826
if (sfp == NULL) continue;
8827
CreateDataForFeature (sfp, action->type);
8828
/* any extra actions */
8829
switch (action->type) {
8830
case (Feature_type_cds) :
8831
ExtraCDSCreationActions (sfp, GetBestTopParentForData (bsp->idx.entityID, bsp));
8832
break;
8833
}
8834
gene = NULL;
8835
for (field_vnp = action->fields; field_vnp != NULL; field_vnp = field_vnp->next) {
8836
q = (FeatQualLegalValPtr) field_vnp->data.ptrvalue;
8837
if (q != NULL) {
8838
f.field = ValNodeNew(NULL);
8839
f.field->next = NULL;
8840
f.field->choice = FeatQualChoice_legal_qual;
8841
f.field->data.intvalue = q->qual;
8842
if (sfp->data.choice != SEQFEAT_GENE
8843
&& (q->qual == Feat_qual_legal_gene || q->qual == Feat_qual_legal_gene_description)) {
8844
if (gene == NULL) {
8845
gene = CreateNewFeatureOnBioseq (bsp, SEQFEAT_GENE, slp);
8846
CreateDataForFeature (gene, Feature_type_gene);
8847
}
8848
f.type = Feature_type_gene;
8849
SetQualOnFeature (gene, &f, NULL, q->val, ExistingTextOption_replace_old);
8850
} else {
8851
f.type = action->type;
8852
SetQualOnFeature (sfp, &f, NULL, q->val, ExistingTextOption_replace_old);
8853
}
8854
}
8855
}
8856
if (action->type == Feature_type_cds) {
8857
/* retranslate, to account for change in reading frame */
8858
AdjustProteinSequenceForReadingFrame (sfp);
8859
/* after the feature has been created, then adjust it for gaps */
8860
/* Note - this step may result in multiple coding regions being created. */
8861
AdjustCDSLocationsForUnknownGapsCallback (sfp, NULL);
8862
}
8863
num_created++;
8864
}
8865
return num_created;
8866
}
8867
8868
8869
typedef struct convertandremovefeaturecollection {
8870
Uint1 featdef;
8871
ValNodePtr constraint_set;
8872
ValNodePtr feature_list;
8873
} ConvertAndRemoveFeatureCollectionData, PNTR ConvertAndRemoveFeatureCollectionPtr;
8874
8875
static void ConvertAndRemoveFeatureCollectionCallback (SeqFeatPtr sfp, Pointer data)
8876
{
8877
ConvertAndRemoveFeatureCollectionPtr p;
8878
8879
if (sfp == NULL || data == NULL) return;
8880
8881
p = (ConvertAndRemoveFeatureCollectionPtr) data;
8882
if (sfp->idx.subtype == p->featdef && DoesObjectMatchConstraintChoiceSet (OBJ_SEQFEAT, sfp, p->constraint_set)) {
8883
ValNodeAddPointer (&(p->feature_list), OBJ_SEQFEAT, sfp);
8884
}
8885
}
8886
8887
8888
static Int4 ApplyRemoveFeatureActionToSeqEntry (RemoveFeatureActionPtr action, SeqEntryPtr sep)
8889
{
8890
ConvertAndRemoveFeatureCollectionData d;
8891
ValNodePtr vnp;
8892
SeqFeatPtr sfp;
8893
Int4 num_deleted = 0;
8894
8895
if (action == NULL) return 0;
8896
8897
d.featdef = GetFeatdefFromFeatureType (action->type);
8898
d.constraint_set = action->constraint;
8899
d.feature_list = NULL;
8900
8901
VisitFeaturesInSep (sep, &d, ConvertAndRemoveFeatureCollectionCallback);
8902
for (vnp = d.feature_list; vnp != NULL; vnp = vnp->next) {
8903
sfp = vnp->data.ptrvalue;
8904
if (sfp != NULL) {
8905
sfp->idx.deleteme = TRUE;
8906
num_deleted ++;
8907
}
8908
}
8909
DeleteMarkedObjects (ObjMgrGetEntityIDForChoice(sep), 0, NULL);
8910
return num_deleted;
8911
}
8912
8913
8914
static Boolean DoesStrandMatch (Int4 strand_choice, Uint1 strand_val)
8915
{
8916
Boolean rval = FALSE;
8917
8918
switch (strand_choice)
8919
{
8920
case Feature_location_strand_from_any:
8921
rval = TRUE;
8922
break;
8923
case Feature_location_strand_from_unknown:
8924
if (strand_val == Seq_strand_unknown)
8925
{
8926
rval = TRUE;
8927
}
8928
break;
8929
case Feature_location_strand_from_plus:
8930
if (strand_val != Seq_strand_minus)
8931
{
8932
rval = TRUE;
8933
}
8934
break;
8935
case Feature_location_strand_from_minus:
8936
if (strand_val == Seq_strand_minus)
8937
{
8938
rval = TRUE;
8939
}
8940
break;
8941
case Feature_location_strand_from_both:
8942
if (strand_val == Seq_strand_both)
8943
{
8944
rval = TRUE;
8945
}
8946
break;
8947
}
8948
return rval;
8949
}
8950
8951
8952
static Uint1 GetNewStrandValue (Int4 strand_choice, Uint1 strand_val)
8953
{
8954
Uint1 rval = Seq_strand_unknown;
8955
8956
switch (strand_choice)
8957
{
8958
case Feature_location_strand_to_reverse:
8959
switch (strand_val)
8960
{
8961
case Seq_strand_plus:
8962
case Seq_strand_unknown:
8963
rval = Seq_strand_minus;
8964
break;
8965
case Seq_strand_minus:
8966
rval = Seq_strand_plus;
8967
break;
8968
default:
8969
rval = strand_val;
8970
break;
8971
}
8972
break;
8973
case Feature_location_strand_to_unknown:
8974
rval = Seq_strand_unknown;
8975
break;
8976
case Feature_location_strand_to_plus:
8977
rval = Seq_strand_plus;
8978
break;
8979
case Feature_location_strand_to_minus:
8980
rval = Seq_strand_minus;
8981
break;
8982
case Feature_location_strand_to_both:
8983
rval = Seq_strand_both;
8984
break;
8985
}
8986
return rval;
8987
}
8988
8989
8990
static Boolean ConvertLocationStrand (SeqLocPtr slp, Int4 fromStrand, Int4 toStrand)
8991
{
8992
SeqLocPtr loc;
8993
PackSeqPntPtr psp;
8994
SeqBondPtr sbp;
8995
SeqIntPtr sinp;
8996
SeqPntPtr spp;
8997
Boolean rval = FALSE;
8998
Uint1 strand_orig;
8999
9000
while (slp != NULL) {
9001
switch (slp->choice) {
9002
case SEQLOC_NULL :
9003
break;
9004
case SEQLOC_EMPTY :
9005
case SEQLOC_WHOLE :
9006
break;
9007
case SEQLOC_INT :
9008
sinp = (SeqIntPtr) slp->data.ptrvalue;
9009
if (sinp != NULL && DoesStrandMatch (fromStrand, sinp->strand))
9010
{
9011
strand_orig = sinp->strand;
9012
sinp->strand = GetNewStrandValue (toStrand, sinp->strand);
9013
if (strand_orig != sinp->strand) {
9014
rval = TRUE;
9015
}
9016
}
9017
break;
9018
case SEQLOC_PNT :
9019
spp = (SeqPntPtr) slp->data.ptrvalue;
9020
if (spp != NULL && DoesStrandMatch (fromStrand, spp->strand))
9021
{
9022
strand_orig = spp->strand;
9023
spp->strand = GetNewStrandValue (toStrand, spp->strand);
9024
if (strand_orig != spp->strand) {
9025
rval = TRUE;
9026
}
9027
}
9028
break;
9029
case SEQLOC_PACKED_PNT :
9030
psp = (PackSeqPntPtr) slp->data.ptrvalue;
9031
if (psp != NULL && DoesStrandMatch (fromStrand, psp->strand))
9032
{
9033
strand_orig = psp->strand;
9034
psp->strand = GetNewStrandValue (toStrand, psp->strand);
9035
if (strand_orig != psp->strand) {
9036
rval = TRUE;
9037
}
9038
}
9039
break;
9040
case SEQLOC_PACKED_INT :
9041
case SEQLOC_MIX :
9042
case SEQLOC_EQUIV :
9043
loc = (SeqLocPtr) slp->data.ptrvalue;
9044
while (loc != NULL) {
9045
rval |= ConvertLocationStrand (loc, fromStrand, toStrand);
9046
loc = loc->next;
9047
}
9048
break;
9049
case SEQLOC_BOND :
9050
sbp = (SeqBondPtr) slp->data.ptrvalue;
9051
if (sbp != NULL) {
9052
spp = (SeqPntPtr) sbp->a;
9053
if (spp != NULL && DoesStrandMatch (fromStrand, spp->strand))
9054
{
9055
strand_orig = spp->strand;
9056
spp->strand = GetNewStrandValue (toStrand, spp->strand);
9057
if (strand_orig != spp->strand) {
9058
rval = TRUE;
9059
}
9060
}
9061
spp = (SeqPntPtr) sbp->b;
9062
if (spp != NULL && DoesStrandMatch (fromStrand, spp->strand))
9063
{
9064
strand_orig = spp->strand;
9065
spp->strand = GetNewStrandValue (toStrand, spp->strand);
9066
if (strand_orig != spp->strand) {
9067
rval = TRUE;
9068
}
9069
}
9070
}
9071
break;
9072
case SEQLOC_FEAT :
9073
break;
9074
default :
9075
break;
9076
}
9077
slp = slp->next;
9078
}
9079
return rval;
9080
}
9081
9082
9083
static Boolean ApplyEditLocationStrandToSeqFeat (EditLocationStrandPtr edit, SeqFeatPtr sfp)
9084
{
9085
Boolean rval = FALSE;
9086
9087
if (edit == NULL || sfp == NULL) {
9088
return FALSE;
9089
}
9090
9091
rval = ConvertLocationStrand (sfp->location, edit->strand_from, edit->strand_to);
9092
return rval;
9093
}
9094
9095
9096
static Boolean At5EndOfSequence (SeqLocPtr slp, BioseqPtr bsp)
9097
{
9098
Uint1 strand;
9099
Int4 start;
9100
Boolean at_end = FALSE;
9101
9102
if (slp == NULL || bsp == NULL) return FALSE;
9103
9104
strand = SeqLocStrand (slp);
9105
9106
if (strand == Seq_strand_minus) {
9107
start = SeqLocStop (slp);
9108
if (start == bsp->length - 1) {
9109
at_end = TRUE;
9110
}
9111
} else {
9112
start = SeqLocStart (slp);
9113
if (start == 0) {
9114
at_end = TRUE;
9115
}
9116
}
9117
return at_end;
9118
}
9119
9120
9121
static Boolean HasGoodStartCodon (SeqFeatPtr sfp)
9122
{
9123
ByteStorePtr bs;
9124
CharPtr prot;
9125
Boolean has_start = FALSE;
9126
9127
if (sfp != NULL && sfp->data.choice == SEQFEAT_CDREGION) {
9128
bs = ProteinFromCdRegionEx (sfp, TRUE, FALSE);
9129
if (bs != NULL) {
9130
prot = BSMerge (bs, NULL);
9131
bs = BSFree (bs);
9132
if (prot != NULL && *prot == 'M') {
9133
has_start = TRUE;
9134
}
9135
prot = MemFree (prot);
9136
}
9137
}
9138
return has_start;
9139
}
9140
9141
9142
static Boolean ApplyPartial5SetActionToSeqFeat (Partial5SetActionPtr action, SeqFeatPtr sfp)
9143
{
9144
Boolean rval = FALSE;
9145
Boolean make_partial = FALSE;
9146
Uint1 strand;
9147
BioseqPtr bsp;
9148
CdRegionPtr crp;
9149
Boolean partial5, partial3;
9150
9151
if (action == NULL || sfp == NULL) return FALSE;
9152
bsp = BioseqFindFromSeqLoc (sfp->location);
9153
strand = SeqLocStrand (sfp->location);
9154
9155
switch (action->constraint) {
9156
case Partial_5_set_constraint_all:
9157
make_partial = TRUE;
9158
break;
9159
case Partial_5_set_constraint_at_end:
9160
make_partial = At5EndOfSequence (sfp->location, bsp);
9161
break;
9162
case Partial_5_set_constraint_bad_start:
9163
make_partial = HasGoodStartCodon (sfp);
9164
break;
9165
case Partial_5_set_constraint_frame_not_one:
9166
if (sfp->data.choice == SEQFEAT_CDREGION
9167
&& (crp = sfp->data.value.ptrvalue) != NULL
9168
&& crp->frame != 0 && crp->frame != 1) {
9169
make_partial = TRUE;
9170
}
9171
break;
9172
}
9173
9174
if (make_partial) {
9175
CheckSeqLocForPartial (sfp->location, &partial5, &partial3);
9176
if (!partial5) {
9177
SetSeqLocPartial (sfp->location, TRUE, partial3);
9178
if (action->extend && bsp != NULL) {
9179
ExtendSeqLocToEnd (sfp->location, bsp, TRUE);
9180
}
9181
rval = TRUE;
9182
}
9183
}
9184
return rval;
9185
}
9186
9187
9188
static Boolean ApplyClear5PartialToSeqFeat (Int4 action, SeqFeatPtr sfp)
9189
{
9190
Boolean rval = FALSE, clear_partial = FALSE;
9191
Boolean partial5, partial3;
9192
9193
if (sfp == NULL) return FALSE;
9194
9195
switch (action) {
9196
case Partial_5_clear_constraint_all:
9197
clear_partial = TRUE;
9198
break;
9199
case Partial_5_clear_constraint_not_at_end:
9200
clear_partial = !At5EndOfSequence(sfp->location, BioseqFindFromSeqLoc (sfp->location));
9201
break;
9202
case Partial_5_clear_constraint_good_start:
9203
clear_partial = !HasGoodStartCodon(sfp);
9204
break;
9205
}
9206
if (clear_partial) {
9207
CheckSeqLocForPartial (sfp->location, &partial5, &partial3);
9208
if (partial5) {
9209
SetSeqLocPartial (sfp->location, FALSE, partial3);
9210
rval = TRUE;
9211
}
9212
}
9213
return rval;
9214
}
9215
9216
9217
static Boolean At3EndOfSequence (SeqLocPtr slp, BioseqPtr bsp)
9218
{
9219
Uint1 strand;
9220
Int4 stop;
9221
Boolean at_end = FALSE;
9222
9223
if (slp == NULL || bsp == NULL) return FALSE;
9224
9225
strand = SeqLocStrand (slp);
9226
9227
if (strand == Seq_strand_minus) {
9228
stop = SeqLocStart (slp);
9229
if (stop == 0) {
9230
at_end = TRUE;
9231
}
9232
} else {
9233
stop = SeqLocStop (slp);
9234
if (stop == bsp->length - 1) {
9235
at_end = TRUE;
9236
}
9237
}
9238
return at_end;
9239
}
9240
9241
9242
static Boolean HasGoodStopCodon (SeqFeatPtr sfp)
9243
{
9244
ByteStorePtr bs;
9245
CharPtr prot;
9246
Boolean has_stop = FALSE;
9247
9248
if (sfp != NULL && sfp->data.choice == SEQFEAT_CDREGION) {
9249
bs = ProteinFromCdRegionEx (sfp, TRUE, FALSE);
9250
if (bs != NULL) {
9251
prot = BSMerge (bs, NULL);
9252
bs = BSFree (bs);
9253
if (prot != NULL && prot[StringLen (prot) - 1] == '*') {
9254
has_stop = TRUE;
9255
}
9256
prot = MemFree (prot);
9257
}
9258
}
9259
return has_stop;
9260
}
9261
9262
9263
static Boolean ApplyPartial3SetActionToSeqFeat (Partial3SetActionPtr action, SeqFeatPtr sfp)
9264
{
9265
Boolean rval = FALSE;
9266
Boolean make_partial = FALSE;
9267
Uint1 strand;
9268
BioseqPtr bsp;
9269
Boolean partial5, partial3;
9270
9271
if (action == NULL || sfp == NULL) return FALSE;
9272
bsp = BioseqFindFromSeqLoc (sfp->location);
9273
strand = SeqLocStrand (sfp->location);
9274
9275
switch (action->constraint) {
9276
case Partial_3_set_constraint_all:
9277
make_partial = TRUE;
9278
break;
9279
case Partial_3_set_constraint_at_end:
9280
make_partial = At3EndOfSequence (sfp->location, bsp);
9281
break;
9282
case Partial_3_set_constraint_bad_end:
9283
make_partial = HasGoodStopCodon (sfp);
9284
break;
9285
}
9286
9287
if (make_partial) {
9288
CheckSeqLocForPartial (sfp->location, &partial5, &partial3);
9289
if (!partial3) {
9290
SetSeqLocPartial (sfp->location, partial5, TRUE);
9291
if (action->extend && bsp != NULL) {
9292
ExtendSeqLocToEnd (sfp->location, bsp, FALSE);
9293
}
9294
rval = TRUE;
9295
}
9296
}
9297
return rval;
9298
}
9299
9300
9301
static Boolean ApplyClear3PartialToSeqFeat (Int4 action, SeqFeatPtr sfp)
9302
{
9303
Boolean rval = FALSE, clear_partial = FALSE;
9304
Boolean partial5, partial3;
9305
9306
if (sfp == NULL) return FALSE;
9307
9308
switch (action) {
9309
case Partial_3_clear_constraint_all:
9310
clear_partial = TRUE;
9311
break;
9312
case Partial_3_clear_constraint_not_at_end:
9313
clear_partial = !At3EndOfSequence(sfp->location, BioseqFindFromSeqLoc (sfp->location));
9314
break;
9315
case Partial_3_clear_constraint_good_end:
9316
clear_partial = !HasGoodStopCodon(sfp);
9317
break;
9318
}
9319
if (clear_partial) {
9320
CheckSeqLocForPartial (sfp->location, &partial5, &partial3);
9321
if (partial3) {
9322
SetSeqLocPartial (sfp->location, partial5, FALSE);
9323
rval = TRUE;
9324
}
9325
}
9326
return rval;
9327
}
9328
9329
9330
static Boolean ApplyConvertLocationToSeqFeat (Int4 convert_location, SeqFeatPtr sfp)
9331
{
9332
Boolean hasNulls, rval = FALSE;
9333
SeqLocPtr slp;
9334
BioseqPtr bsp;
9335
Boolean partial5, partial3;
9336
9337
if (sfp == NULL || (bsp = BioseqFindFromSeqLoc (sfp->location))== NULL) {
9338
return FALSE;
9339
}
9340
9341
CheckSeqLocForPartial (sfp->location, &partial5, &partial3);
9342
hasNulls = LocationHasNullsBetween (sfp->location);
9343
switch (convert_location)
9344
{
9345
case Convert_location_type_join :
9346
if (hasNulls)
9347
{
9348
slp = SeqLocMerge (bsp, sfp->location, NULL, FALSE, FALSE, FALSE);
9349
sfp->location = SeqLocFree (sfp->location);
9350
sfp->location = slp;
9351
if (bsp->repr == Seq_repr_seg)
9352
{
9353
slp = SegLocToPartsEx (bsp, sfp->location, FALSE);
9354
sfp->location = SeqLocFree (sfp->location);
9355
sfp->location = slp;
9356
hasNulls = LocationHasNullsBetween (sfp->location);
9357
sfp->partial = (sfp->partial || hasNulls);
9358
}
9359
FreeAllFuzz (sfp->location);
9360
SetSeqLocPartial (sfp->location, partial5, partial3);
9361
rval = TRUE;
9362
}
9363
break;
9364
case Convert_location_type_order :
9365
if (!hasNulls)
9366
{
9367
slp = SeqLocMerge (bsp, sfp->location, NULL, FALSE, FALSE, TRUE);
9368
sfp->location = SeqLocFree (sfp->location);
9369
sfp->location = slp;
9370
if (bsp->repr == Seq_repr_seg)
9371
{
9372
slp = SegLocToPartsEx (bsp, sfp->location, TRUE);
9373
sfp->location = SeqLocFree (sfp->location);
9374
sfp->location = slp;
9375
hasNulls = LocationHasNullsBetween (sfp->location);
9376
sfp->partial = (sfp->partial || hasNulls);
9377
}
9378
FreeAllFuzz (sfp->location);
9379
SetSeqLocPartial (sfp->location, partial5, partial3);
9380
rval = TRUE;
9381
}
9382
break;
9383
case Convert_location_type_merge :
9384
if (sfp->location->choice != SEQLOC_INT) {
9385
slp = SeqLocMerge (bsp, sfp->location, NULL, TRUE, FALSE, FALSE);
9386
sfp->location = SeqLocFree (sfp->location);
9387
sfp->location = slp;
9388
SetSeqLocPartial (sfp->location, partial5, partial3);
9389
rval = TRUE;
9390
}
9391
default:
9392
break;
9393
}
9394
return rval;
9395
}
9396
9397
9398
static Boolean ApplyLocationEditTypeToSeqFeat (ValNodePtr action, SeqFeatPtr sfp)
9399
{
9400
Boolean rval = FALSE;
9401
9402
if (action == NULL || sfp == NULL) {
9403
return FALSE;
9404
}
9405
9406
switch (action->choice) {
9407
case LocationEditType_strand:
9408
rval = ApplyEditLocationStrandToSeqFeat (action->data.ptrvalue, sfp);
9409
break;
9410
case LocationEditType_set_5_partial:
9411
rval = ApplyPartial5SetActionToSeqFeat (action->data.ptrvalue, sfp);
9412
break;
9413
case LocationEditType_clear_5_partial:
9414
rval = ApplyClear5PartialToSeqFeat (action->data.intvalue, sfp);
9415
break;
9416
case LocationEditType_set_3_partial:
9417
rval = ApplyPartial3SetActionToSeqFeat (action->data.ptrvalue, sfp);
9418
break;
9419
case LocationEditType_clear_3_partial:
9420
rval = ApplyClear3PartialToSeqFeat (action->data.intvalue, sfp);
9421
break;
9422
case LocationEditType_convert:
9423
rval = ApplyConvertLocationToSeqFeat (action->data.intvalue, sfp);
9424
break;
9425
}
9426
return rval;
9427
}
9428
9429
9430
static Int4 ApplyEditFeatureLocationActionToSeqEntry (EditFeatureLocationActionPtr action, SeqEntryPtr sep)
9431
{
9432
ConvertAndRemoveFeatureCollectionData d;
9433
ValNodePtr vnp;
9434
SeqFeatPtr sfp;
9435
Int4 num_affected = 0;
9436
9437
if (action == NULL) return 0;
9438
9439
d.featdef = GetFeatdefFromFeatureType (action->type);
9440
d.constraint_set = action->constraint;
9441
d.feature_list = NULL;
9442
9443
VisitFeaturesInSep (sep, &d, ConvertAndRemoveFeatureCollectionCallback);
9444
for (vnp = d.feature_list; vnp != NULL; vnp = vnp->next) {
9445
sfp = vnp->data.ptrvalue;
9446
if (sfp != NULL && ApplyLocationEditTypeToSeqFeat (action->action, sfp)) {
9447
num_affected++;
9448
}
9449
}
9450
return num_affected;
9451
}
9452
9453
9454
NLM_EXTERN void ApplyMacroToSeqEntry (SeqEntryPtr sep, ValNodePtr macro, Int4Ptr pNumFields, Int4Ptr pNumFeat)
9455
{
9456
Int4 num_AECR = 0, num_parse = 0, num_feature = 0, num_fields = 0;
9457
9458
while (macro != NULL) {
9459
switch (macro->choice) {
9460
case MacroActionChoice_aecr:
9461
num_AECR += ApplyAECRActionToSeqEntry ((AECRActionPtr) macro->data.ptrvalue, sep);
9462
break;
9463
case MacroActionChoice_parse:
9464
num_parse += ApplyParseActionToSeqEntry ((ParseActionPtr) macro->data.ptrvalue, sep);
9465
break;
9466
case MacroActionChoice_add_feature:
9467
num_feature += ApplyApplyFeatureActionToSeqEntry ((ApplyFeatureActionPtr) macro->data.ptrvalue, sep);
9468
SeqMgrIndexFeatures (ObjMgrGetEntityIDForChoice(sep), NULL);
9469
break;
9470
case MacroActionChoice_remove_feature:
9471
num_feature += ApplyRemoveFeatureActionToSeqEntry ((RemoveFeatureActionPtr) macro->data.ptrvalue, sep);
9472
break;
9473
case MacroActionChoice_edit_location:
9474
num_fields += ApplyEditFeatureLocationActionToSeqEntry ((EditFeatureLocationActionPtr) macro->data.ptrvalue, sep);
9475
break;
9476
}
9477
macro = macro->next;
9478
}
9479
if (pNumFields != NULL) {
9480
*pNumFields = num_AECR + num_parse + num_fields;
9481
}
9482
if (pNumFeat != NULL) {
9483
*pNumFeat = num_feature;
9484
}
9485
}
9486
9487
9488
/* for generating text descriptions of macro objects */
9489
NLM_EXTERN CharPtr SummarizeSourceQual (ValNodePtr field)
9490
{
9491
CharPtr summ = NULL, locname, origname;
9492
Int4 genome, origin;
9493
CharPtr loc_fmt = "location %s";
9494
CharPtr orig_fmt = "origin %s";
9495
9496
if (field == NULL) return NULL;
9497
switch (field->choice) {
9498
case SourceQualChoice_textqual:
9499
summ = StringSave (GetSourceQualName (field->data.intvalue));
9500
break;
9501
case SourceQualChoice_location:
9502
genome = GenomeFromSrcLoc (field->data.intvalue);
9503
locname = LocNameFromGenome (genome);
9504
summ = (CharPtr) MemNew (sizeof (Char) * (StringLen (loc_fmt) + StringLen (locname)));
9505
sprintf (summ, loc_fmt, locname);
9506
break;
9507
case SourceQualChoice_origin:
9508
origin = OriginFromSrcOrig (field->data.intvalue);
9509
origname = OriginNameFromOrigin (origin);
9510
summ = (CharPtr) MemNew (sizeof (Char) * (StringLen (orig_fmt) + StringLen (origname)));
9511
sprintf (summ, orig_fmt, origname);
9512
break;
9513
}
9514
return summ;
9515
}
9516
9517
9518
NLM_EXTERN CharPtr FeatureFieldLabel (CharPtr feature_name, ValNodePtr field)
9519
{
9520
CharPtr cp;
9521
CharPtr label = NULL;
9522
CharPtr legal_fmt = "%s %s";
9523
CharPtr illegal_fmt = "constrained field on %s";
9524
9525
if (feature_name == NULL) {
9526
feature_name = "Unknown feature";
9527
}
9528
9529
if (field == NULL) {
9530
return StringSave ("missing field");
9531
} else if (field->choice == FeatQualChoice_legal_qual) {
9532
cp = GetFeatQualName (field->data.intvalue);
9533
if (cp == NULL) cp = "Unknown field type";
9534
label = (CharPtr) MemNew (sizeof (Char) * (StringLen (legal_fmt) + StringLen (feature_name) + StringLen (cp)));
9535
sprintf (label, legal_fmt, feature_name, cp);
9536
} else if (field->choice == FeatQualChoice_illegal_qual) {
9537
label = (CharPtr) MemNew (sizeof (Char) * (StringLen (illegal_fmt) + StringLen (feature_name)));
9538
sprintf (label, illegal_fmt, feature_name);
9539
} else {
9540
label = StringSave ("illegal field value");
9541
}
9542
return label;
9543
}
9544
9545
9546
NLM_EXTERN Boolean IsFeatureFieldEmpty (FeatureFieldPtr field)
9547
{
9548
if (field == NULL) return TRUE;
9549
if (field->field == NULL) return TRUE;
9550
return FALSE;
9551
}
9552
9553
9554
NLM_EXTERN Boolean IsFieldTypeEmpty (FieldTypePtr field)
9555
{
9556
Boolean rval = TRUE;
9557
9558
if (field == NULL) return TRUE;
9559
switch (field->choice) {
9560
case FieldType_source_qual:
9561
if (field->data.ptrvalue != NULL) {
9562
rval = FALSE;
9563
}
9564
break;
9565
case FieldType_feature_field:
9566
if (!IsFeatureFieldEmpty (field->data.ptrvalue)) {
9567
rval = FALSE;
9568
}
9569
break;
9570
case FieldType_cds_gene_prot:
9571
rval = FALSE;
9572
break;
9573
}
9574
return rval;
9575
}
9576
9577
9578
NLM_EXTERN CharPtr SummarizeFieldType (ValNodePtr vnp)
9579
{
9580
FeatureFieldPtr ffp;
9581
CharPtr str = NULL;
9582
CharPtr label = NULL;
9583
9584
if (vnp == NULL) {
9585
str = StringSave ("missing field");
9586
} else {
9587
switch (vnp->choice) {
9588
case FieldType_source_qual:
9589
str = SummarizeSourceQual (vnp->data.ptrvalue);
9590
break;
9591
case FieldType_feature_field:
9592
ffp = (FeatureFieldPtr) vnp->data.ptrvalue;
9593
if (ffp == NULL || ffp->field == NULL) {
9594
str = StringSave ("missing field");
9595
} else {
9596
label = GetFeatureNameFromFeatureType (ffp->type);
9597
str = FeatureFieldLabel (label, ffp->field);
9598
}
9599
break;
9600
case FieldType_cds_gene_prot:
9601
str = StringSaveNoNull (CDSGeneProtNameFromField (vnp->data.intvalue));
9602
if (str == NULL) {
9603
str = StringSave ("Invalid CDS-Gene-Prot Field");
9604
}
9605
break;
9606
case FieldType_molinfo_field:
9607
str = GetSequenceQualName (vnp->data.ptrvalue);
9608
if (str == NULL) {
9609
str = StringSave ("Invalid Sequence Qual Field");
9610
}
9611
break;
9612
default:
9613
str = StringSave ("Invalid field type");
9614
break;
9615
}
9616
}
9617
return str;
9618
}
9619
9620
9621
/* for table readers that use the macro language functions */
9622
NLM_EXTERN TabColumnConfigPtr TabColumnConfigNew (void)
9623
{
9624
TabColumnConfigPtr t;
9625
9626
t = (TabColumnConfigPtr) MemNew (sizeof (TabColumnConfigData));
9627
t->field = NULL;
9628
t->existing_text = ExistingTextOption_replace_old;
9629
t->skip_blank = TRUE;
9630
return t;
9631
}
9632
9633
9634
9635
NLM_EXTERN TabColumnConfigPtr TabColumnConfigFree (TabColumnConfigPtr t)
9636
{
9637
if (t != NULL) {
9638
t->field = FieldTypeFree (t->field);
9639
t = MemFree (t);
9640
}
9641
return t;
9642
}
9643
9644
9645
NLM_EXTERN TabColumnConfigPtr TabColumnConfigCopy (TabColumnConfigPtr orig)
9646
{
9647
TabColumnConfigPtr t = NULL;
9648
9649
if (orig != NULL) {
9650
t = TabColumnConfigNew ();
9651
t->match_type = orig->match_type;
9652
t->existing_text = orig->existing_text;
9653
t->skip_blank = orig->skip_blank;
9654
t->match_mrna = orig->match_mrna;
9655
t->field = AsnIoMemCopy (orig->field, (AsnReadFunc) FieldTypeAsnRead, (AsnWriteFunc) FieldTypeAsnWrite);
9656
}
9657
return t;
9658
}
9659
9660
9661
NLM_EXTERN ValNodePtr TabColumnConfigListFree (ValNodePtr columns)
9662
{
9663
ValNodePtr vnp_next;
9664
9665
while (columns != NULL) {
9666
vnp_next = columns->next;
9667
columns->data.ptrvalue = TabColumnConfigFree (columns->data.ptrvalue);
9668
columns->next = NULL;
9669
columns = ValNodeFree (columns);
9670
columns = vnp_next;
9671
}
9672
return columns;
9673
}
9674
9675
9676
NLM_EXTERN ValNodePtr TabColumnConfigListCopy (ValNodePtr orig)
9677
{
9678
ValNodePtr new_list = NULL;
9679
TabColumnConfigPtr t;
9680
9681
while (orig != NULL) {
9682
t = TabColumnConfigCopy (orig->data.ptrvalue);
9683
ValNodeAddPointer (&new_list, 0, t);
9684
orig = orig->next;
9685
}
9686
return new_list;
9687
}
9688
9689
9690
9691
/* This checks the column names and returns a list of the feature fields */
9692
NLM_EXTERN ValNodePtr ValidateFeatureFieldColumnNames (ValNodePtr header_line, ValNodePtr PNTR perr_list)
9693
{
9694
ValNodePtr header_vnp;
9695
ValNodePtr err_list = NULL, col_list = NULL;
9696
Boolean rval = TRUE;
9697
TabColumnConfigPtr t;
9698
FeatureFieldPtr field;
9699
Int4 featqual, feat_type;
9700
CharPtr first_space;
9701
9702
if (header_line == NULL)
9703
{
9704
return FALSE;
9705
}
9706
9707
header_vnp = header_line->data.ptrvalue;
9708
if (header_vnp == NULL || header_vnp->next == NULL)
9709
{
9710
return FALSE;
9711
}
9712
9713
/* skip ID column */
9714
header_vnp = header_vnp->next;
9715
while (header_vnp != NULL && rval)
9716
{
9717
first_space = StringChr (header_vnp->data.ptrvalue, ' ');
9718
if (first_space != NULL) {
9719
*first_space = 0;
9720
feat_type = GetFeatureTypeByName (header_vnp->data.ptrvalue);
9721
featqual = GetFeatQualByName (first_space + 1);
9722
*first_space = ' ';
9723
if (feat_type < 0 || featqual < 0) {
9724
/* unable to recognize column name */
9725
ValNodeAddPointer (&err_list, 0, StringSave (header_vnp->data.ptrvalue));
9726
/* if we're not able to send back a list of errors, just quit now */
9727
if (perr_list == NULL) {
9728
rval = FALSE;
9729
}
9730
} else if (err_list == NULL) {
9731
/* if we've already found errors, don't bother collecting more fields */
9732
field = FeatureFieldNew ();
9733
field->type = feat_type;
9734
field->field = ValNodeNew (NULL);
9735
field->field->choice = FeatQualChoice_legal_qual;
9736
field->field->data.intvalue = featqual;
9737
t = TabColumnConfigNew ();
9738
t->field = ValNodeNew (NULL);
9739
t->field->choice = FieldType_feature_field;
9740
t->field->data.ptrvalue = field;
9741
ValNodeAddPointer (&col_list, 0, t);
9742
}
9743
} else {
9744
featqual = GetFeatQualByName (header_vnp->data.ptrvalue);
9745
if (featqual < 0) {
9746
/* unable to recognize column name */
9747
ValNodeAddPointer (&err_list, 0, StringSave (header_vnp->data.ptrvalue));
9748
/* if we're not able to send back a list of errors, just quit now */
9749
if (perr_list == NULL) {
9750
rval = FALSE;
9751
}
9752
} else if (err_list == NULL) {
9753
/* if we've already found errors, don't bother collecting more fields */
9754
field = FeatureFieldNew ();
9755
field->type = Feature_type_any;
9756
field->field = ValNodeNew (NULL);
9757
field->field->choice = FeatQualChoice_legal_qual;
9758
field->field->data.intvalue = featqual;
9759
t = TabColumnConfigNew ();
9760
t->field = ValNodeNew (NULL);
9761
t->field->choice = FieldType_feature_field;
9762
t->field->data.ptrvalue = field;
9763
ValNodeAddPointer (&col_list, 0, t);
9764
}
9765
}
9766
header_vnp = header_vnp->next;
9767
}
9768
if (err_list != NULL) {
9769
col_list = TabColumnConfigListFree (col_list);
9770
if (perr_list != NULL) {
9771
*perr_list = err_list;
9772
} else {
9773
err_list = ValNodeFreeData (err_list);
9774
}
9775
}
9776
return col_list;
9777
}
9778
9779
typedef struct findgenelocustag {
9780
CharPtr locus_tag;
9781
ValNodePtr gene_list;
9782
} FindGeneLocusTagData, PNTR FindGeneLocusTagPtr;
9783
9784
static void FindGeneByLocusTagBioseqCallback (BioseqPtr bsp, Pointer userdata)
9785
{
9786
FindGeneLocusTagPtr p;
9787
SeqFeatPtr gene;
9788
SeqMgrFeatContext fcontext;
9789
9790
if (bsp == NULL || userdata == NULL || !ISA_na (bsp->mol)) {
9791
return;
9792
}
9793
9794
p = (FindGeneLocusTagPtr) userdata;
9795
9796
gene = SeqMgrGetGeneByLocusTag (bsp, p->locus_tag, &fcontext);
9797
if (gene != NULL) {
9798
ValNodeAddPointer (&p->gene_list, OBJ_SEQFEAT, gene);
9799
}
9800
}
9801
9802
9803
typedef struct objbystr {
9804
ValNodePtr obj_list;
9805
CharPtr str;
9806
} ObjByStrData, PNTR ObjByStrPtr;
9807
9808
static void GetFeaturesByDbxrefCallback (SeqFeatPtr sfp, Pointer userdata)
9809
{
9810
ObjByStrPtr p;
9811
ValNodePtr vnp;
9812
DbtagPtr dbt;
9813
Char buf[20];
9814
Boolean found = FALSE;
9815
9816
if (sfp == NULL || sfp->dbxref == NULL || userdata == NULL) return;
9817
p = (ObjByStrPtr) userdata;
9818
9819
if (StringHasNoText (p->str)) return;
9820
9821
for (vnp = sfp->dbxref; vnp != NULL && !found; vnp = vnp->next) {
9822
dbt = (DbtagPtr) vnp->data.ptrvalue;
9823
if (dbt != NULL && dbt->tag != NULL) {
9824
if (dbt->tag->id > 0) {
9825
sprintf (buf, "%d", dbt->tag->id);
9826
if (StringCmp (buf, p->str) == 0) {
9827
found = TRUE;
9828
}
9829
} else if (StringCmp (dbt->tag->str, p->str) == 0) {
9830
found = TRUE;
9831
}
9832
}
9833
}
9834
if (found) {
9835
ValNodeAddPointer (&(p->obj_list), OBJ_SEQFEAT, sfp);
9836
}
9837
9838
}
9839
9840
9841
static ValNodePtr GetFeaturesByDbxref (SeqEntryPtr sep, CharPtr dbxref)
9842
{
9843
ObjByStrData d;
9844
9845
d.str = dbxref;
9846
d.obj_list = NULL;
9847
VisitFeaturesInSep (sep, &d, GetFeaturesByDbxrefCallback);
9848
return d.obj_list;
9849
}
9850
9851
9852
static void GetBioSourcesByTaxNameDescriptorCallback (SeqDescrPtr sdp, Pointer userdata)
9853
{
9854
ObjByStrPtr p;
9855
BioSourcePtr biop;
9856
9857
if (sdp == NULL || sdp->choice != Seq_descr_source || userdata == NULL) return;
9858
p = (ObjByStrPtr) userdata;
9859
9860
if (StringHasNoText (p->str)) return;
9861
9862
biop = (BioSourcePtr) sdp->data.ptrvalue;
9863
if (biop != NULL && biop->org != NULL && StringCmp (biop->org->taxname, p->str) == 0) {
9864
ValNodeAddPointer (&(p->obj_list), OBJ_SEQDESC, sdp);
9865
}
9866
9867
}
9868
9869
9870
static void GetBioSourcesByTaxNameFeatureCallback (SeqFeatPtr sfp, Pointer userdata)
9871
{
9872
ObjByStrPtr p;
9873
BioSourcePtr biop;
9874
9875
if (sfp == NULL || sfp->data.choice != SEQFEAT_BIOSRC || userdata == NULL) return;
9876
p = (ObjByStrPtr) userdata;
9877
9878
if (StringHasNoText (p->str)) return;
9879
9880
biop = (BioSourcePtr) sfp->data.value.ptrvalue;
9881
if (biop != NULL && biop->org != NULL && StringCmp (biop->org->taxname, p->str) == 0) {
9882
ValNodeAddPointer (&(p->obj_list), OBJ_SEQFEAT, sfp);
9883
}
9884
9885
}
9886
9887
9888
static ValNodePtr GetBioSourcesByTaxName (SeqEntryPtr sep, CharPtr taxname)
9889
{
9890
ObjByStrData d;
9891
9892
d.str = taxname;
9893
d.obj_list = NULL;
9894
VisitDescriptorsInSep (sep, &d, GetBioSourcesByTaxNameDescriptorCallback);
9895
9896
VisitFeaturesInSep (sep, &d, GetBioSourcesByTaxNameFeatureCallback);
9897
return d.obj_list;
9898
}
9899
9900
9901
9902
static ValNodePtr
9903
FindMatchForRow
9904
(ValNodePtr match_type,
9905
Uint2 entityID,
9906
SeqEntryPtr sep)
9907
{
9908
ValNodePtr match_list = NULL;
9909
SeqIdPtr sip;
9910
BioseqPtr bsp, nbsp = NULL;
9911
FindGeneLocusTagData fd;
9912
SeqFeatPtr sfp;
9913
SeqMgrFeatContext fcontext;
9914
9915
if (match_type == NULL || sep == NULL) return NULL;
9916
9917
switch (match_type->choice) {
9918
case eTableMatchFeatureID:
9919
sfp = SeqMgrGetFeatureByFeatID (entityID, NULL, match_type->data.ptrvalue, NULL, &fcontext);
9920
if (sfp != NULL) {
9921
ValNodeAddPointer (&match_list, OBJ_SEQFEAT, sfp);
9922
}
9923
break;
9924
case eTableMatchGeneLocusTag:
9925
fd.locus_tag = match_type->data.ptrvalue;
9926
fd.gene_list = NULL;
9927
VisitBioseqsInSep (sep, &fd, FindGeneByLocusTagBioseqCallback);
9928
ValNodeLink (&match_list, fd.gene_list);
9929
break;
9930
case eTableMatchProteinID:
9931
case eTableMatchNucID:
9932
sip = CreateSeqIdFromText (match_type->data.ptrvalue, sep);
9933
bsp = BioseqFind (sip);
9934
sip = SeqIdFree (sip);
9935
if (bsp != NULL)
9936
{
9937
ValNodeAddPointer (&match_list, OBJ_BIOSEQ, bsp);
9938
}
9939
break;
9940
case eTableMatchDbxref:
9941
match_list = GetFeaturesByDbxref (sep, match_type->data.ptrvalue);
9942
break;
9943
case eTableMatchBioSource:
9944
match_list = GetBioSourcesByTaxName (sep, match_type->data.ptrvalue);
9945
break;
9946
}
9947
return match_list;
9948
}
9949
9950
9951
static ValNodePtr GetFeatureListForProteinBioseq (Uint1 featdef, BioseqPtr bsp)
9952
{
9953
ValNodePtr feat_list = NULL;
9954
SeqFeatPtr sfp, cds;
9955
SeqMgrFeatContext fcontext;
9956
Int4 seqfeattype;
9957
9958
if (bsp == NULL || !ISA_aa (bsp->mol))
9959
{
9960
return NULL;
9961
}
9962
9963
seqfeattype = FindFeatFromFeatDefType (featdef);
9964
if (seqfeattype == SEQFEAT_PROT)
9965
{
9966
for (sfp = SeqMgrGetNextFeature (bsp, NULL, 0, featdef, &fcontext);
9967
sfp != NULL;
9968
sfp = SeqMgrGetNextFeature (bsp, sfp, 0, featdef, &fcontext))
9969
{
9970
ValNodeAddPointer (&feat_list, OBJ_SEQFEAT, sfp);
9971
}
9972
}
9973
else
9974
{
9975
cds = SeqMgrGetCDSgivenProduct (bsp, NULL);
9976
if (cds != NULL)
9977
{
9978
if (featdef == FEATDEF_CDS)
9979
{
9980
sfp = cds;
9981
}
9982
else if (featdef == FEATDEF_GENE)
9983
{
9984
sfp = GetGeneForFeature (cds);
9985
}
9986
else if (featdef == FEATDEF_mRNA)
9987
{
9988
sfp = SeqMgrGetOverlappingmRNA (cds->location, &fcontext);
9989
}
9990
if (sfp != NULL)
9991
{
9992
ValNodeAddPointer (&feat_list, OBJ_SEQFEAT, sfp);
9993
}
9994
}
9995
}
9996
return feat_list;
9997
}
9998
9999
10000
static ValNodePtr GetFeatureListForNucleotideBioseq (Uint1 featdef, BioseqPtr bsp)
10001
{
10002
ValNodePtr feat_list = NULL;
10003
SeqFeatPtr sfp;
10004
SeqMgrFeatContext fcontext;
10005
Int4 seqfeattype;
10006
BioseqPtr prot_bsp;
10007
10008
if (bsp == NULL || ISA_aa (bsp->mol))
10009
{
10010
return NULL;
10011
}
10012
10013
seqfeattype = FindFeatFromFeatDefType (featdef);
10014
if (seqfeattype == SEQFEAT_PROT)
10015
{
10016
for (sfp = SeqMgrGetNextFeature (bsp, NULL, 0, FEATDEF_CDS, &fcontext);
10017
sfp != NULL;
10018
sfp = SeqMgrGetNextFeature (bsp, sfp, 0, FEATDEF_CDS, &fcontext))
10019
{
10020
prot_bsp = BioseqFindFromSeqLoc (sfp->product);
10021
ValNodeLink (&feat_list, GetFeatureListForProteinBioseq (featdef, prot_bsp));
10022
}
10023
}
10024
else
10025
{
10026
for (sfp = SeqMgrGetNextFeature (bsp, NULL, 0, featdef, &fcontext);
10027
sfp != NULL;
10028
sfp = SeqMgrGetNextFeature (bsp, sfp, 0, featdef, &fcontext))
10029
{
10030
ValNodeAddPointer (&feat_list, OBJ_SEQFEAT, sfp);
10031
}
10032
}
10033
return feat_list;
10034
}
10035
10036
10037
static ValNodePtr GetFeaturesForGene (SeqFeatPtr gene, Uint1 featdef)
10038
{
10039
BioseqPtr bsp;
10040
SeqFeatPtr sfp;
10041
ValNodePtr feat_list = NULL;
10042
SeqMgrFeatContext fcontext;
10043
Int4 start, stop, swap;
10044
10045
if (gene == NULL) return NULL;
10046
10047
bsp = BioseqFindFromSeqLoc (gene->location);
10048
start = SeqLocStart (gene->location);
10049
stop = SeqLocStop (gene->location);
10050
if (stop < start)
10051
{
10052
swap = start;
10053
start = stop;
10054
stop = swap;
10055
}
10056
for (sfp = SeqMgrGetNextFeature (bsp, NULL, 0, featdef, &fcontext);
10057
sfp != NULL && fcontext.left < stop;
10058
sfp = SeqMgrGetNextFeature (bsp, sfp, 0, featdef, &fcontext))
10059
{
10060
if (fcontext.right >= start && gene == GetGeneForFeature (sfp))
10061
{
10062
ValNodeAddPointer (&feat_list, OBJ_SEQFEAT, sfp);
10063
}
10064
}
10065
return feat_list;
10066
}
10067
10068
10069
static ValNodePtr GetFeatureListForGene (Uint1 featdef, SeqFeatPtr gene)
10070
{
10071
ValNodePtr feat_list = NULL, cds_list, vnp;
10072
SeqFeatPtr sfp, cds;
10073
SeqMgrFeatContext fcontext;
10074
BioseqPtr protbsp;
10075
10076
if (gene == NULL)
10077
{
10078
return NULL;
10079
}
10080
10081
if (featdef == FEATDEF_GENE)
10082
{
10083
ValNodeAddPointer (&feat_list, OBJ_SEQFEAT, gene);
10084
}
10085
else if (FindFeatFromFeatDefType (featdef == SEQFEAT_PROT))
10086
{
10087
cds_list = GetFeaturesForGene (gene, FEATDEF_CDS);
10088
for (vnp = cds_list; vnp != NULL; vnp = vnp->next)
10089
{
10090
cds = vnp->data.ptrvalue;
10091
if (cds != NULL)
10092
{
10093
protbsp = BioseqFindFromSeqLoc (cds->product);
10094
for (sfp = SeqMgrGetNextFeature (protbsp, NULL, 0, featdef, &fcontext);
10095
sfp != NULL;
10096
sfp = SeqMgrGetNextFeature (protbsp, sfp, 0, featdef, &fcontext))
10097
{
10098
ValNodeAddPointer (&feat_list, OBJ_SEQFEAT, sfp);
10099
}
10100
}
10101
}
10102
cds_list = ValNodeFree (cds_list);
10103
}
10104
else
10105
{
10106
feat_list = GetFeaturesForGene (gene, featdef);
10107
}
10108
10109
return feat_list;
10110
}
10111
10112
10113
static ValNodePtr AddFeaturesFromBioseqSet (BioseqSetPtr bssp, Uint1 featdef)
10114
{
10115
SeqEntryPtr sep;
10116
BioseqPtr bsp;
10117
Int4 seqfeattype;
10118
ValNodePtr item_list = NULL;
10119
10120
if (bssp == NULL) return NULL;
10121
10122
seqfeattype = FindFeatFromFeatDefType (featdef);
10123
for (sep = bssp->seq_set; sep != NULL; sep = sep->next) {
10124
if (sep->data.ptrvalue == NULL) continue;
10125
if (IS_Bioseq (sep)) {
10126
bsp = sep->data.ptrvalue;
10127
if (seqfeattype == SEQFEAT_PROT) {
10128
if (ISA_aa (bsp->mol)) {
10129
ValNodeLink (&item_list, GetFeatureListForProteinBioseq (featdef, bsp));
10130
}
10131
} else if (!ISA_aa (bsp->mol)) {
10132
ValNodeLink (&item_list, GetFeatureListForNucleotideBioseq (featdef, bsp));
10133
}
10134
} else if (IS_Bioseq_set (sep)) {
10135
ValNodeLink (&item_list, AddFeaturesFromBioseqSet (sep->data.ptrvalue, featdef));
10136
}
10137
}
10138
return item_list;
10139
}
10140
10141
10142
static ValNodePtr GetFeatureListForBioSourceObjects (ValNodePtr item_list, FeatureFieldPtr field)
10143
{
10144
ValNodePtr vnp;
10145
SeqFeatPtr sfp;
10146
SeqDescrPtr sdp;
10147
BioseqPtr bsp;
10148
ObjValNodePtr ovp;
10149
ValNodePtr feature_list = NULL;
10150
10151
if (item_list == NULL || field == NULL) return NULL;
10152
10153
for (vnp = item_list; vnp != NULL; vnp = vnp->next) {
10154
if (vnp->choice == OBJ_SEQFEAT) {
10155
sfp = vnp->data.ptrvalue;
10156
if (sfp != NULL) {
10157
bsp = BioseqFindFromSeqLoc (sfp->location);
10158
ValNodeLink (&feature_list, GetFeatureListForNucleotideBioseq (GetFeatdefFromFeatureType(field->type), bsp));
10159
}
10160
} else if (vnp->choice == OBJ_SEQDESC) {
10161
sdp = vnp->data.ptrvalue;
10162
if (sdp != NULL && sdp->extended != 0) {
10163
ovp = (ObjValNodePtr) sdp;
10164
if (ovp->idx.parenttype == OBJ_BIOSEQSET) {
10165
ValNodeLink (&feature_list, AddFeaturesFromBioseqSet (ovp->idx.parentptr, GetFeatdefFromFeatureType(field->type)));
10166
} else if (ovp->idx.parenttype == OBJ_BIOSEQ) {
10167
bsp = (BioseqPtr) ovp->idx.parentptr;
10168
ValNodeLink (&feature_list, GetFeatureListForNucleotideBioseq (GetFeatdefFromFeatureType(field->type), bsp));
10169
}
10170
}
10171
}
10172
}
10173
return feature_list;
10174
}
10175
10176
10177
static ValNodePtr ValNodeCopyPtr (ValNodePtr orig)
10178
{
10179
ValNodePtr new_list = NULL, last_vnp = NULL, vnp;
10180
10181
while (orig != NULL) {
10182
vnp = ValNodeNew (NULL);
10183
vnp->choice = orig->choice;
10184
vnp->data.ptrvalue = orig->data.ptrvalue;
10185
if (last_vnp == NULL) {
10186
new_list = vnp;
10187
} else {
10188
last_vnp->next = vnp;
10189
}
10190
last_vnp = vnp;
10191
orig = orig->next;
10192
}
10193
return new_list;
10194
}
10195
10196
10197
static ValNodePtr GetFeatureListForRowAndColumn (Uint1 match_type, ValNodePtr match_list, FeatureFieldPtr field)
10198
{
10199
ValNodePtr feature_list = NULL, vnp;
10200
10201
if (match_list == NULL || field == NULL) return NULL;
10202
10203
switch (match_type) {
10204
case eTableMatchFeatureID:
10205
feature_list = ValNodeCopyPtr (match_list);
10206
break;
10207
case eTableMatchGeneLocusTag:
10208
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10209
ValNodeLink (&feature_list, GetFeatureListForGene (GetFeatdefFromFeatureType(field->type), vnp->data.ptrvalue));
10210
}
10211
break;
10212
case eTableMatchProteinID:
10213
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10214
ValNodeLink (&feature_list, GetFeatureListForProteinBioseq (GetFeatdefFromFeatureType(field->type), vnp->data.ptrvalue));
10215
}
10216
break;
10217
case eTableMatchDbxref:
10218
feature_list = ValNodeCopyPtr (match_list);
10219
break;
10220
case eTableMatchNucID:
10221
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10222
ValNodeLink (&feature_list, GetFeatureListForNucleotideBioseq (GetFeatdefFromFeatureType(field->type), vnp->data.ptrvalue));
10223
}
10224
break;
10225
case eTableMatchBioSource:
10226
ValNodeLink (&feature_list, GetFeatureListForBioSourceObjects (match_list, field));
10227
break;
10228
}
10229
return feature_list;
10230
}
10231
10232
10233
static void AddBioSourcesForBioseq (BioseqPtr bsp, ValNodePtr PNTR feature_list)
10234
{
10235
SeqDescrPtr sdp;
10236
SeqMgrDescContext context;
10237
10238
if (feature_list == NULL) return;
10239
for (sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_source, &context);
10240
sdp != NULL;
10241
sdp = SeqMgrGetNextDescriptor (bsp, sdp, Seq_descr_source, &context)) {
10242
ValNodeAddPointer (feature_list, OBJ_SEQDESC, sdp);
10243
}
10244
}
10245
10246
static void AddBioSourcesForFeature (SeqFeatPtr sfp, ValNodePtr PNTR feature_list)
10247
{
10248
BioseqPtr bsp;
10249
10250
if (sfp == NULL || feature_list == NULL) return;
10251
10252
if (sfp->data.choice == SEQFEAT_BIOSRC) {
10253
ValNodeAddPointer (feature_list, OBJ_SEQFEAT, sfp);
10254
} else {
10255
bsp = BioseqFindFromSeqLoc (sfp->location);
10256
AddBioSourcesForBioseq (bsp, feature_list);
10257
}
10258
}
10259
10260
10261
static ValNodePtr GetBioSourceListForRowAndColumn (Uint1 match_type, ValNodePtr match_list, FeatureFieldPtr field)
10262
{
10263
ValNodePtr feature_list = NULL, vnp;
10264
10265
if (match_list == NULL || field == NULL) return NULL;
10266
10267
switch (match_type) {
10268
case eTableMatchFeatureID:
10269
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10270
if (vnp->choice == OBJ_SEQFEAT && vnp->data.ptrvalue != NULL) {
10271
AddBioSourcesForFeature (vnp->data.ptrvalue, &feature_list);
10272
}
10273
}
10274
break;
10275
case eTableMatchGeneLocusTag:
10276
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10277
if (vnp->choice == OBJ_SEQFEAT && vnp->data.ptrvalue != NULL) {
10278
AddBioSourcesForFeature (vnp->data.ptrvalue, &feature_list);
10279
}
10280
}
10281
break;
10282
case eTableMatchProteinID:
10283
case eTableMatchNucID:
10284
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10285
if (vnp->choice == OBJ_BIOSEQ) {
10286
AddBioSourcesForBioseq (vnp->data.ptrvalue, &feature_list);
10287
}
10288
}
10289
break;
10290
case eTableMatchDbxref:
10291
for (vnp = match_list; vnp != NULL; vnp = vnp->next) {
10292
if (vnp->choice == OBJ_SEQFEAT && vnp->data.ptrvalue != NULL) {
10293
AddBioSourcesForFeature (vnp->data.ptrvalue, &feature_list);
10294
}
10295
}
10296
break;
10297
case eTableMatchBioSource:
10298
feature_list = ValNodeCopyPtr (match_list);
10299
break;
10300
}
10301
return feature_list;
10302
}
10303
10304
10305
static ValNodePtr GetTargetListForRowAndColumn (Uint1 match_type, ValNodePtr match_list, FieldTypePtr field)
10306
{
10307
ValNodePtr target_list = NULL;
10308
FeatureFieldPtr feature_field;
10309
10310
if (field == NULL) return NULL;
10311
switch (field->choice) {
10312
case FieldType_source_qual:
10313
target_list = GetBioSourceListForRowAndColumn (match_type, match_list, field->data.ptrvalue);
10314
break;
10315
case FieldType_feature_field:
10316
target_list = GetFeatureListForRowAndColumn (match_type, match_list, field->data.ptrvalue);
10317
break;
10318
case FieldType_cds_gene_prot:
10319
feature_field = FeatureFieldFromCDSGeneProtField (field->data.intvalue);
10320
target_list = GetFeatureListForRowAndColumn (match_type, match_list, feature_field);
10321
feature_field = FeatureFieldFree (feature_field);
10322
break;
10323
}
10324
return target_list;
10325
}
10326
10327
10328
static void ReportMissingTargets (ValNodePtr PNTR perr_list, FieldTypePtr ft, CharPtr match_val, Int4 col_num, Int4 line_num)
10329
{
10330
CharPtr feat_name;
10331
FeatureFieldPtr field;
10332
CharPtr no_feat_fmt = "No %s feature for %s (column %d, line %d)";
10333
CharPtr no_src_fmt = "No biosource for %s (column %d, line %d)";
10334
CharPtr err_msg;
10335
10336
if (perr_list == NULL || ft == NULL || match_val == NULL) return;
10337
10338
switch (ft->choice) {
10339
case FieldType_source_qual:
10340
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (no_feat_fmt)
10341
+ StringLen (match_val)
10342
+ 30));
10343
sprintf (err_msg, no_src_fmt, match_val, col_num, line_num);
10344
ValNodeAddPointer (perr_list, 0, err_msg);
10345
break;
10346
case FieldType_feature_field:
10347
field = (FeatureFieldPtr) ft->data.ptrvalue;
10348
if (field != NULL) {
10349
feat_name = GetFeatureNameFromFeatureType (field->type);
10350
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (no_feat_fmt)
10351
+ StringLen (feat_name)
10352
+ StringLen (match_val)
10353
+ 30));
10354
sprintf (err_msg, no_feat_fmt, feat_name, match_val, col_num, line_num);
10355
ValNodeAddPointer (perr_list, 0, err_msg);
10356
}
10357
break;
10358
case FieldType_cds_gene_prot:
10359
field = FeatureFieldFromCDSGeneProtField (ft->data.intvalue);
10360
if (field != NULL) {
10361
feat_name = GetFeatureNameFromFeatureType (field->type);
10362
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (no_feat_fmt)
10363
+ StringLen (feat_name)
10364
+ StringLen (match_val)
10365
+ 30));
10366
sprintf (err_msg, no_feat_fmt, feat_name, match_val, col_num, line_num);
10367
ValNodeAddPointer (perr_list, 0, err_msg);
10368
}
10369
field = FeatureFieldFree (field);
10370
break;
10371
}
10372
}
10373
10374
10375
static void ReportEmptyIDColumn (ValNodePtr PNTR perr_list, Int4 line_num)
10376
{
10377
CharPtr err_msg;
10378
CharPtr missing_id_fmt = "No ID for line %d";
10379
10380
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (missing_id_fmt) + 15));
10381
sprintf (err_msg, missing_id_fmt, line_num);
10382
ValNodeAddPointer (perr_list, 0, err_msg);
10383
}
10384
10385
static ValNodePtr FindMatchChoiceInLine (ValNodePtr val_vnp, ValNodePtr col_vnp)
10386
{
10387
TabColumnConfigPtr t;
10388
10389
while (val_vnp != NULL && col_vnp != NULL) {
10390
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
10391
if (t != NULL && t->match_type > 0) {
10392
val_vnp->choice = (Uint1) t->match_type;
10393
return val_vnp;
10394
}
10395
val_vnp = val_vnp->next;
10396
col_vnp = col_vnp->next;
10397
}
10398
return NULL;
10399
}
10400
10401
10402
NLM_EXTERN SeqFeatPtr GetmRNAForFeature (SeqFeatPtr sfp)
10403
{
10404
SeqMgrFeatContext fcontext;
10405
BioseqPtr pbsp;
10406
10407
if (sfp == NULL) return NULL;
10408
if (sfp->data.choice == SEQFEAT_PROT)
10409
{
10410
pbsp = BioseqFindFromSeqLoc (sfp->location);
10411
sfp = SeqMgrGetCDSgivenProduct (pbsp, NULL);
10412
if (sfp == NULL) return NULL;
10413
}
10414
return SeqMgrGetOverlappingmRNA (sfp->location, &fcontext);
10415
}
10416
10417
10418
NLM_EXTERN Boolean AdjustmRNAProductToMatchProteinProduct (SeqFeatPtr sfp)
10419
{
10420
SeqFeatPtr mrna;
10421
ProtRefPtr prp;
10422
RnaRefPtr rrp;
10423
10424
if (sfp == NULL || sfp->data.choice != SEQFEAT_PROT) return FALSE;
10425
10426
prp = (ProtRefPtr) sfp->data.value.ptrvalue;
10427
mrna = GetmRNAForFeature (sfp);
10428
10429
if (mrna == NULL) return FALSE;
10430
10431
rrp = (RnaRefPtr) mrna->data.value.ptrvalue;
10432
if (rrp == NULL)
10433
{
10434
rrp = RnaRefNew();
10435
mrna->data.value.ptrvalue = rrp;
10436
}
10437
10438
rrp->ext.value.ptrvalue = MemFree (rrp->ext.value.ptrvalue);
10439
if (prp == NULL || prp->name == NULL || StringHasNoText (prp->name->data.ptrvalue))
10440
{
10441
rrp->ext.choice = 0;
10442
}
10443
else
10444
{
10445
rrp->ext.choice = 1;
10446
rrp->ext.value.ptrvalue = StringSave (prp->name->data.ptrvalue);
10447
}
10448
return TRUE;
10449
}
10450
10451
10452
NLM_EXTERN Boolean IsFieldTypeCDSProduct (FieldTypePtr ft)
10453
{
10454
FeatureFieldPtr field;
10455
Boolean rval = FALSE;
10456
10457
if (ft == NULL) return FALSE;
10458
if (ft->choice == FieldType_feature_field) {
10459
field = (FeatureFieldPtr) ft->data.ptrvalue;
10460
if (field != NULL && field->type == Feature_type_cds
10461
&& field->field != NULL
10462
&& field->field->choice == FeatQualChoice_legal_qual
10463
&& field->field->data.intvalue == Feat_qual_legal_product) {
10464
rval = TRUE;
10465
}
10466
} else if (ft->choice == FieldType_cds_gene_prot) {
10467
if (ft->data.intvalue == CDSGeneProt_field_prot_name) {
10468
rval = TRUE;
10469
}
10470
}
10471
return rval;
10472
}
10473
10474
10475
static Boolean IsFieldTypeGeneLocusTag (FieldTypePtr ft)
10476
{
10477
FeatureFieldPtr field;
10478
Boolean rval = FALSE;
10479
10480
if (ft == NULL) return FALSE;
10481
if (ft->choice == FieldType_feature_field) {
10482
field = (FeatureFieldPtr) ft->data.ptrvalue;
10483
if (field != NULL && field->type == Feature_type_gene
10484
&& field->field != NULL
10485
&& field->field->choice == FeatQualChoice_legal_qual
10486
&& field->field->data.intvalue == Feat_qual_legal_locus_tag) {
10487
rval = TRUE;
10488
}
10489
} else if (ft->choice == FieldType_cds_gene_prot) {
10490
if (ft->data.intvalue == CDSGeneProt_field_gene_locus_tag) {
10491
rval = TRUE;
10492
}
10493
}
10494
return rval;
10495
}
10496
10497
10498
10499
NLM_EXTERN ValNodePtr ValidateTabTableValues (ValNodePtr table, ValNodePtr columns)
10500
{
10501
ValNodePtr err_list = NULL;
10502
ValNodePtr line_vnp, col_vnp, val_vnp;
10503
Int4 line_num, col_num;
10504
TabColumnConfigPtr t;
10505
ValNodePtr locus_tag_values = NULL, bad_locus_tags = NULL, vnp;
10506
CharPtr bad_format_fmt = "Locus tag %s has incorrect format";
10507
CharPtr dup_fmt = "Locus tag %s appears in the table more than once";
10508
CharPtr inconsistent_fmt = "Locus tag prefix for %s is inconsistent";
10509
CharPtr err_msg;
10510
10511
if (table == NULL || columns == NULL) {
10512
return NULL;
10513
}
10514
10515
for (line_vnp = table, line_num = 1;
10516
line_vnp != NULL;
10517
line_vnp = line_vnp->next, line_num++) {
10518
for (val_vnp = line_vnp->data.ptrvalue, col_vnp = columns, col_num = 1;
10519
val_vnp != NULL && col_vnp != NULL;
10520
val_vnp = val_vnp->next, col_vnp = col_vnp->next, col_num++) {
10521
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
10522
if (t == NULL || t->match_type > 0 || val_vnp == NULL || StringHasNoText (val_vnp->data.ptrvalue)) {
10523
continue;
10524
}
10525
if (IsFieldTypeGeneLocusTag (t->field)) {
10526
ValNodeAddPointer (&locus_tag_values, 0, val_vnp->data.ptrvalue);
10527
}
10528
}
10529
}
10530
10531
bad_locus_tags = FindBadLocusTagsInList (locus_tag_values);
10532
for (vnp = bad_locus_tags; vnp != NULL; vnp = vnp->next) {
10533
switch (vnp->choice) {
10534
case eLocusTagErrorBadFormat:
10535
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (bad_format_fmt) + StringLen (vnp->data.ptrvalue)));
10536
sprintf (err_msg, bad_format_fmt, vnp->data.ptrvalue);
10537
ValNodeAddPointer (&err_list, 0, err_msg);
10538
break;
10539
case eLocusTagErrorDuplicate:
10540
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (dup_fmt) + StringLen (vnp->data.ptrvalue)));
10541
sprintf (err_msg, dup_fmt, vnp->data.ptrvalue);
10542
ValNodeAddPointer (&err_list, 0, err_msg);
10543
break;
10544
case eLocusTagErrorInconsistentPrefix:
10545
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (inconsistent_fmt) + StringLen (vnp->data.ptrvalue)));
10546
sprintf (err_msg, inconsistent_fmt, vnp->data.ptrvalue);
10547
ValNodeAddPointer (&err_list, 0, err_msg);
10548
break;
10549
}
10550
}
10551
locus_tag_values = ValNodeFree (locus_tag_values);
10552
return err_list;
10553
}
10554
10555
10556
NLM_EXTERN ValNodePtr GetObjectTableForTabTable (SeqEntryPtr sep, ValNodePtr table, ValNodePtr columns, ValNodePtr PNTR p_err_list)
10557
{
10558
ValNodePtr err_list = NULL;
10559
ValNodePtr line_vnp, val_vnp, col_vnp;
10560
ValNodePtr obj_table = NULL, obj_row;
10561
Int4 line_num = 1, col_num;
10562
Uint2 entityID;
10563
ValNodePtr match_list, match_choice, target_list;
10564
TabColumnConfigPtr t;
10565
CharPtr err_msg;
10566
CharPtr no_match_fmt = "No match for %s, line %d";
10567
CharPtr bad_col_val_fmt = "Did not set value for column %d, line %d";
10568
CharPtr num_affected_fmt = "%d fields affected";
10569
Int4 num_fields_affected = 0;
10570
10571
if (sep == NULL) {
10572
ValNodeAddPointer (&err_list, 0, StringSave ("No SeqEntry"));
10573
}
10574
if (table == NULL) {
10575
ValNodeAddPointer (&err_list, 0, StringSave ("No table"));
10576
}
10577
if (columns == NULL) {
10578
ValNodeAddPointer (&err_list, 0, StringSave ("No column information"));
10579
}
10580
if (err_list != NULL) {
10581
if (p_err_list == NULL) {
10582
err_list = ValNodeFreeData (err_list);
10583
} else {
10584
*p_err_list = err_list;
10585
}
10586
return NULL;
10587
}
10588
10589
entityID = SeqMgrGetEntityIDForSeqEntry (sep);
10590
10591
for (line_vnp = table, line_num = 1; line_vnp != NULL; line_vnp = line_vnp->next, line_num++) {
10592
obj_row = NULL;
10593
match_choice = FindMatchChoiceInLine (line_vnp->data.ptrvalue, columns);
10594
if (match_choice == NULL || StringHasNoText (match_choice->data.ptrvalue)) {
10595
ReportEmptyIDColumn (&err_list, line_num);
10596
} else {
10597
match_list = FindMatchForRow (match_choice, entityID, sep);
10598
if (match_list == NULL) {
10599
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (no_match_fmt) + StringLen (match_choice->data.ptrvalue) + 15));
10600
sprintf (err_msg, no_match_fmt, match_choice->data.ptrvalue, line_num);
10601
ValNodeAddPointer (&err_list, 0, err_msg);
10602
} else {
10603
for (val_vnp = line_vnp->data.ptrvalue, col_vnp = columns, col_num = 1;
10604
col_vnp != NULL;
10605
col_vnp = col_vnp->next, col_num++) {
10606
target_list = NULL;
10607
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
10608
if (t == NULL || t->match_type > 0
10609
|| (t->skip_blank && (val_vnp == NULL || StringHasNoText (val_vnp->data.ptrvalue)))) {
10610
/* no targets */
10611
} else {
10612
target_list = GetTargetListForRowAndColumn (match_choice->choice, match_list, t->field);
10613
if (target_list == NULL) {
10614
ReportMissingTargets (&err_list, t->field, match_choice->data.ptrvalue, col_num, line_num);
10615
}
10616
}
10617
ValNodeAddPointer (&obj_row, 0, target_list);
10618
if (val_vnp != NULL) {
10619
val_vnp = val_vnp->next;
10620
}
10621
}
10622
}
10623
}
10624
ValNodeAddPointer (&obj_table, 0, obj_row);
10625
}
10626
10627
if (err_list != NULL) {
10628
if (p_err_list == NULL) {
10629
err_list = ValNodeFreeData (err_list);
10630
} else {
10631
*p_err_list = err_list;
10632
}
10633
}
10634
return obj_table;
10635
}
10636
10637
10638
NLM_EXTERN ValNodePtr FreeObjectTableForTabTable (ValNodePtr table)
10639
{
10640
ValNodePtr vnp_next, vnp_row, vnp_row_next;
10641
10642
while (table != NULL) {
10643
vnp_next = table->next;
10644
table->next = NULL;
10645
vnp_row = table->data.ptrvalue;
10646
while (vnp_row != NULL) {
10647
vnp_row_next = vnp_row->next;
10648
vnp_row->next = NULL;
10649
vnp_row->data.ptrvalue = ValNodeFree (vnp_row->data.ptrvalue);
10650
vnp_row = ValNodeFree (vnp_row);
10651
vnp_row = vnp_row_next;
10652
}
10653
table = ValNodeFree (table);
10654
table = vnp_next;
10655
}
10656
return table;
10657
}
10658
10659
10660
typedef struct countfeat {
10661
Uint1 featdef;
10662
Int4 num;
10663
} CountFeatData, PNTR CountFeatPtr;
10664
10665
10666
static void CountFeaturesCallback (SeqFeatPtr sfp, Pointer userdata)
10667
{
10668
CountFeatPtr p;
10669
10670
if (sfp == NULL || userdata == NULL) return;
10671
10672
p = (CountFeatPtr) userdata;
10673
if (sfp->idx.subtype == p->featdef) {
10674
p->num++;
10675
}
10676
}
10677
10678
static void CountBioSourceDescriptorsCallback (SeqDescrPtr sdp, Pointer userdata)
10679
{
10680
Int4Ptr p;
10681
10682
p = (Int4Ptr) userdata;
10683
if (sdp != NULL && p != NULL && sdp->choice == Seq_descr_source) {
10684
(*p)++;
10685
}
10686
}
10687
10688
10689
static ValNodePtr CountObjectsForColumnFields (SeqEntryPtr sep, ValNodePtr columns)
10690
{
10691
ValNodePtr count_list = NULL, vnp;
10692
TabColumnConfigPtr t;
10693
CountFeatData d;
10694
FeatureFieldPtr f;
10695
Int4 num;
10696
Uint1 featdef = 0;
10697
10698
d.featdef = 0;
10699
d.num = 0;
10700
for (vnp = columns; vnp != NULL; vnp = vnp->next) {
10701
num = 0;
10702
t = (TabColumnConfigPtr) vnp->data.ptrvalue;
10703
if (t != NULL && t->match_type == 0 && t->field != NULL) {
10704
switch (t->field->choice) {
10705
case FieldType_source_qual:
10706
if (featdef != FEATDEF_BIOSRC) {
10707
d.featdef = FEATDEF_BIOSRC;
10708
d.num = 0;
10709
VisitFeaturesInSep (sep, &d, CountFeaturesCallback);
10710
VisitDescriptorsInSep (sep, &(d.num), CountBioSourceDescriptorsCallback);
10711
}
10712
num = d.num;
10713
break;
10714
case FieldType_feature_field:
10715
f = (FeatureFieldPtr) t->field->data.ptrvalue;
10716
if (f != NULL) {
10717
featdef = GetFeatdefFromFeatureType(f->type);
10718
if (featdef != d.featdef) {
10719
d.featdef = featdef;
10720
d.num = 0;
10721
VisitFeaturesInSep (sep, &d, CountFeaturesCallback);
10722
}
10723
num = d.num;
10724
}
10725
break;
10726
case FieldType_cds_gene_prot:
10727
f = FeatureFieldFromCDSGeneProtField (t->field->data.intvalue);
10728
if (f != NULL) {
10729
featdef = GetFeatdefFromFeatureType(f->type);
10730
if (featdef != d.featdef) {
10731
d.featdef = featdef;
10732
d.num = 0;
10733
VisitFeaturesInSep (sep, &d, CountFeaturesCallback);
10734
}
10735
num = d.num;
10736
}
10737
f = FeatureFieldFree (f);
10738
break;
10739
}
10740
}
10741
ValNodeAddInt (&count_list, 0, num);
10742
}
10743
return count_list;
10744
}
10745
10746
10747
NLM_EXTERN ValNodePtr ApplyTableValuesToObjectTable (SeqEntryPtr sep, ValNodePtr table, ValNodePtr columns, ValNodePtr obj_table)
10748
{
10749
ValNodePtr val_line_vnp, obj_line_vnp;
10750
ValNodePtr val_vnp, obj_vnp, col_vnp;
10751
ValNodePtr target_vnp;
10752
TabColumnConfigPtr t;
10753
CharPtr val, qual_name;
10754
ValNodePtr err_list = NULL, count_list, count_affected_list = NULL, count_vnp, count_tot_vnp;
10755
CharPtr err_msg;
10756
CharPtr bad_col_val_fmt = "Did not set value for column %d, line %d";
10757
CharPtr num_affected_fmt = "%d fields affected";
10758
CharPtr col_num_affected_fmt = "For %s (column %d), %d items were affected out of %d total";
10759
Int4 num_fields_affected = 0, col_num, line_num, num_this_column;
10760
Boolean success;
10761
ValNodePtr count_msg = NULL;
10762
10763
count_list = CountObjectsForColumnFields (sep, columns);
10764
10765
for (val_line_vnp = table, obj_line_vnp = obj_table, line_num = 1;
10766
val_line_vnp != NULL && obj_line_vnp != NULL;
10767
val_line_vnp = val_line_vnp->next, obj_line_vnp = obj_line_vnp->next, line_num++) {
10768
val_vnp = val_line_vnp->data.ptrvalue;
10769
obj_vnp = obj_line_vnp->data.ptrvalue;
10770
col_vnp = columns;
10771
col_num = 1;
10772
count_vnp = count_affected_list;
10773
while (obj_vnp != NULL && col_vnp != NULL) {
10774
num_this_column = 0;
10775
if (obj_vnp->data.ptrvalue != NULL) {
10776
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
10777
if (t == NULL || t->match_type > 0
10778
|| (t->skip_blank && (val_vnp == NULL || StringHasNoText (val_vnp->data.ptrvalue)))) {
10779
/* ignore column or skip blank value */
10780
} else {
10781
if (val_vnp == NULL || val_vnp->data.ptrvalue == NULL) {
10782
val = "";
10783
} else {
10784
val = val_vnp->data.ptrvalue;
10785
}
10786
for (target_vnp = obj_vnp->data.ptrvalue; target_vnp != NULL; target_vnp = target_vnp->next) {
10787
if (val[0] == 0) {
10788
success = RemoveFieldValueForObject (target_vnp->choice, target_vnp->data.ptrvalue, t->field, NULL);
10789
} else {
10790
success = SetFieldValueForObject (target_vnp->choice, target_vnp->data.ptrvalue, t->field, NULL,
10791
val_vnp->data.ptrvalue, t->existing_text);
10792
}
10793
if (success) {
10794
num_fields_affected++;
10795
num_this_column++;
10796
if (t->match_mrna && IsFieldTypeCDSProduct (t->field)
10797
&& target_vnp->choice == OBJ_SEQFEAT) {
10798
if (AdjustmRNAProductToMatchProteinProduct (target_vnp->data.ptrvalue)) {
10799
num_fields_affected++;
10800
}
10801
}
10802
} else {
10803
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (bad_col_val_fmt) + 30));
10804
sprintf (err_msg, bad_col_val_fmt, col_num, line_num);
10805
ValNodeAddPointer (&err_list, 0, err_msg);
10806
}
10807
}
10808
}
10809
}
10810
if (val_vnp != NULL) {
10811
val_vnp = val_vnp->next;
10812
}
10813
if (count_vnp == NULL) {
10814
ValNodeAddInt (&count_affected_list, 0, num_this_column);
10815
} else {
10816
count_vnp->data.intvalue ++;
10817
count_vnp = count_vnp->next;
10818
}
10819
obj_vnp = obj_vnp->next;
10820
col_vnp = col_vnp->next;
10821
col_num++;
10822
}
10823
}
10824
10825
/* put message at top of list for number of fields affected */
10826
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (num_affected_fmt) + 15));
10827
sprintf (err_msg, num_affected_fmt, num_fields_affected);
10828
ValNodeAddPointer (&count_msg, 0, err_msg);
10829
10830
/* if any affected, list number of fields per column, and the total in the record */
10831
if (num_fields_affected > 0) {
10832
for (count_vnp = count_affected_list, count_tot_vnp = count_list, col_vnp = columns, col_num = 1;
10833
count_vnp != NULL && count_tot_vnp != NULL && col_vnp != NULL;
10834
count_vnp = count_vnp->next, count_tot_vnp = count_tot_vnp->next, col_vnp = col_vnp->next, col_num++) {
10835
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
10836
if (t != NULL && t->match_type == 0) {
10837
qual_name = SummarizeFieldType (t->field);
10838
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (col_num_affected_fmt) + StringLen (qual_name) + 45));
10839
sprintf (err_msg, col_num_affected_fmt, qual_name, col_num, count_vnp->data.intvalue, count_tot_vnp->data.intvalue);
10840
ValNodeAddPointer (&count_msg, 0, err_msg);
10841
qual_name = MemFree (qual_name);
10842
}
10843
}
10844
}
10845
10846
ValNodeLink (&count_msg, err_list);
10847
10848
count_list = ValNodeFree (count_list);
10849
count_affected_list = ValNodeFree (count_affected_list);
10850
10851
return count_msg;
10852
}
10853
10854
10855
static int LIBCALLBACK SortVnpByChoiceAndPtrvalue (VoidPtr ptr1, VoidPtr ptr2)
10856
10857
{
10858
ValNodePtr vnp1;
10859
ValNodePtr vnp2;
10860
10861
if (ptr1 != NULL && ptr2 != NULL) {
10862
vnp1 = *((ValNodePtr PNTR) ptr1);
10863
vnp2 = *((ValNodePtr PNTR) ptr2);
10864
if (vnp1 != NULL && vnp2 != NULL) {
10865
if (vnp1->choice > vnp2->choice) {
10866
return 1;
10867
} else if (vnp1->choice < vnp2->choice) {
10868
return -1;
10869
} else if (vnp1->data.ptrvalue > vnp2->data.ptrvalue) {
10870
return 1;
10871
} else if (vnp2->data.ptrvalue < vnp2->data.ptrvalue) {
10872
return -1;
10873
} else {
10874
return 0;
10875
}
10876
}
10877
}
10878
return 0;
10879
}
10880
10881
10882
NLM_EXTERN ValNodePtr CheckObjTableForRowsThatApplyToTheSameDestination (ValNodePtr obj_table)
10883
{
10884
Int4 col_num;
10885
ValNodePtr line_vnp, col_vnp, obj_vnp, vnp;
10886
ValNodePtr col_list = NULL, col_obj_list;
10887
Boolean any_column_values_left;
10888
ValNodePtr err_list = NULL;
10889
Boolean found_multi;
10890
CharPtr multi_fmt = "Multiple rows apply to the same object for column %d";
10891
CharPtr err_msg;
10892
10893
/* now, for each row, get pointer to first column */
10894
for (line_vnp = obj_table; line_vnp != NULL; line_vnp = line_vnp->next) {
10895
ValNodeAddPointer (&col_list, 0, line_vnp->data.ptrvalue);
10896
}
10897
10898
/* now for each column, make a list of all features in the column, then sort to see if there are duplicates */
10899
any_column_values_left = TRUE;
10900
col_num = 1;
10901
while (any_column_values_left) {
10902
any_column_values_left = FALSE;
10903
col_obj_list = NULL;
10904
for (vnp = col_list; vnp != NULL; vnp = vnp->next) {
10905
col_vnp = vnp->data.ptrvalue;
10906
if (col_vnp != NULL) {
10907
obj_vnp = col_vnp->data.ptrvalue;
10908
ValNodeLink (&col_obj_list, ValNodeCopyPtr (obj_vnp));
10909
vnp->data.ptrvalue = col_vnp->next;
10910
any_column_values_left = TRUE;
10911
}
10912
}
10913
if (col_obj_list != NULL) {
10914
found_multi = FALSE;
10915
col_obj_list = ValNodeSort (col_obj_list, SortVnpByChoiceAndPtrvalue);
10916
for (vnp = col_obj_list; vnp != NULL && vnp->next != NULL && !found_multi; vnp = vnp->next) {
10917
if (vnp->choice == vnp->next->choice
10918
&& vnp->data.ptrvalue == vnp->next->data.ptrvalue) {
10919
found_multi = TRUE;
10920
}
10921
}
10922
if (found_multi) {
10923
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (multi_fmt)
10924
+ 30));
10925
sprintf (err_msg, multi_fmt, col_num);
10926
ValNodeAddPointer (&err_list, col_num, err_msg);
10927
}
10928
col_obj_list = ValNodeFree (col_obj_list);
10929
}
10930
col_num++;
10931
}
10932
col_list = ValNodeFree (col_list);
10933
return err_list;
10934
}
10935
10936
10937
NLM_EXTERN ValNodePtr CheckObjTableForExistingText (SeqEntryPtr sep, ValNodePtr table, ValNodePtr columns, ValNodePtr obj_table)
10938
{
10939
ValNodePtr err_list = NULL, vnp;
10940
ValNodePtr val_line_vnp, obj_line_vnp;
10941
ValNodePtr val_vnp, obj_vnp, col_vnp;
10942
Int4 line_num = 1, col_num, num_existing_text = 0;
10943
Uint2 entityID;
10944
TabColumnConfigPtr t;
10945
CharPtr err_msg, str, qual_name, val;
10946
CharPtr already_has_val_fmt = "%s already has value '%s' (column %d), line %d. Replacement is '%s'";
10947
CharPtr num_existing_text_fmt = "%d fields already have text.";
10948
CharPtr mrna_warn_fmt = "%d coding region features have mRNAs, but %d do not.";
10949
ValNodePtr target_list, feat_vnp;
10950
Int4 num_with_mrna = 0, num_without_mrna = 0;
10951
10952
if (sep == NULL) {
10953
ValNodeAddPointer (&err_list, 1, StringSave ("No SeqEntry"));
10954
}
10955
if (table == NULL) {
10956
ValNodeAddPointer (&err_list, 1, StringSave ("No table"));
10957
}
10958
if (columns == NULL) {
10959
ValNodeAddPointer (&err_list, 1, StringSave ("No column information"));
10960
}
10961
if (err_list != NULL) {
10962
return err_list;
10963
}
10964
10965
entityID = SeqMgrGetEntityIDForSeqEntry (sep);
10966
10967
for (val_line_vnp = table, obj_line_vnp = obj_table, line_num = 1;
10968
val_line_vnp != NULL && obj_line_vnp != NULL;
10969
val_line_vnp = val_line_vnp->next, obj_line_vnp = obj_line_vnp->next, line_num++) {
10970
val_vnp = val_line_vnp->data.ptrvalue;
10971
obj_vnp = obj_line_vnp->data.ptrvalue;
10972
col_vnp = columns;
10973
if (val_vnp == NULL || obj_vnp == NULL) continue;
10974
col_num = 1;
10975
while (obj_vnp != NULL && col_vnp != NULL) {
10976
if (obj_vnp->data.ptrvalue != NULL) {
10977
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
10978
if (t == NULL || t->match_type > 0
10979
|| (t->skip_blank && (val_vnp == NULL || StringHasNoText (val_vnp->data.ptrvalue)))) {
10980
/* ignore column or skip blank value */
10981
} else {
10982
target_list = obj_vnp->data.ptrvalue;
10983
if (val_vnp == NULL || val_vnp->data.ptrvalue == NULL) {
10984
val = "";
10985
} else {
10986
val = val_vnp->data.ptrvalue;
10987
}
10988
for (feat_vnp = target_list; feat_vnp != NULL; feat_vnp = feat_vnp->next) {
10989
/* check for existing text */
10990
str = GetFieldValueForObject (feat_vnp->choice, feat_vnp->data.ptrvalue, t->field, NULL);
10991
if (!StringHasNoText (str)) {
10992
qual_name = SummarizeFieldType (t->field);
10993
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (already_has_val_fmt)
10994
+ StringLen (qual_name) + StringLen (str)
10995
+ StringLen (val)
10996
+ 30));
10997
sprintf (err_msg, already_has_val_fmt, qual_name, str, col_num, line_num, val);
10998
ValNodeAddPointer (&err_list, col_num, err_msg);
10999
num_existing_text ++;
11000
}
11001
str = MemFree (str);
11002
/* check for mrna if changing CDS product */
11003
if (IsFieldTypeCDSProduct (t->field) && feat_vnp->choice == OBJ_SEQFEAT) {
11004
if (GetmRNAForFeature (feat_vnp->data.ptrvalue) != NULL) {
11005
num_with_mrna++;
11006
} else {
11007
num_without_mrna++;
11008
}
11009
}
11010
}
11011
}
11012
}
11013
if (val_vnp != NULL) {
11014
val_vnp = val_vnp->next;
11015
}
11016
obj_vnp = obj_vnp->next;
11017
col_vnp = col_vnp->next;
11018
col_num++;
11019
}
11020
}
11021
if (num_existing_text > 0) {
11022
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (num_existing_text_fmt)
11023
+ 15));
11024
sprintf (err_msg, num_existing_text_fmt, num_existing_text);
11025
vnp = ValNodeNew (NULL);
11026
vnp->choice = 0;
11027
vnp->data.ptrvalue = err_msg;
11028
vnp->next = err_list;
11029
err_list = vnp;
11030
}
11031
if (num_with_mrna > 0 && num_without_mrna > 0) {
11032
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (mrna_warn_fmt)
11033
+ 30));
11034
sprintf (err_msg, mrna_warn_fmt, num_with_mrna, num_without_mrna);
11035
vnp = ValNodeNew (NULL);
11036
vnp->choice = 0;
11037
vnp->data.ptrvalue = err_msg;
11038
vnp->next = err_list;
11039
err_list = vnp;
11040
}
11041
11042
return err_list;
11043
}
11044
11045
11046
NLM_EXTERN ValNodePtr ApplyTableToFeatures (SeqEntryPtr sep, ValNodePtr table, ValNodePtr columns)
11047
{
11048
ValNodePtr err_list = NULL;
11049
ValNodePtr line_vnp, val_vnp, col_vnp;
11050
Int4 line_num = 1, col_num;
11051
Uint2 entityID;
11052
ValNodePtr match_list, match_choice, target_list, feat_vnp, vnp;
11053
TabColumnConfigPtr t;
11054
CharPtr err_msg;
11055
CharPtr no_match_fmt = "No match for %s, line %d";
11056
CharPtr bad_col_val_fmt = "Did not set value for column %d, line %d";
11057
CharPtr num_affected_fmt = "%d fields affected";
11058
Int4 num_fields_affected = 0;
11059
CharPtr val;
11060
Boolean success;
11061
11062
if (sep == NULL) {
11063
ValNodeAddPointer (&err_list, 0, StringSave ("No SeqEntry"));
11064
}
11065
if (table == NULL) {
11066
ValNodeAddPointer (&err_list, 0, StringSave ("No table"));
11067
}
11068
if (columns == NULL) {
11069
ValNodeAddPointer (&err_list, 0, StringSave ("No column information"));
11070
}
11071
if (err_list != NULL) {
11072
return err_list;
11073
}
11074
11075
entityID = SeqMgrGetEntityIDForSeqEntry (sep);
11076
11077
for (line_vnp = table, line_num = 1; line_vnp != NULL; line_vnp = line_vnp->next, line_num++) {
11078
match_choice = FindMatchChoiceInLine (line_vnp->data.ptrvalue, columns);
11079
if (match_choice == NULL || StringHasNoText (match_choice->data.ptrvalue)) {
11080
ReportEmptyIDColumn (&err_list, line_num);
11081
} else {
11082
match_list = FindMatchForRow (match_choice, entityID, sep);
11083
if (match_list == NULL) {
11084
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (no_match_fmt) + StringLen (match_choice->data.ptrvalue) + 15));
11085
sprintf (err_msg, no_match_fmt, match_choice->data.ptrvalue, line_num);
11086
ValNodeAddPointer (&err_list, 0, err_msg);
11087
} else {
11088
for (val_vnp = line_vnp->data.ptrvalue, col_vnp = columns, col_num = 1;
11089
col_vnp != NULL;
11090
col_vnp = col_vnp->next, col_num++) {
11091
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
11092
if (t == NULL || t->match_type > 0
11093
|| (t->skip_blank && (val_vnp == NULL || StringHasNoText (val_vnp->data.ptrvalue)))) {
11094
if (val_vnp != NULL) {
11095
val_vnp = val_vnp->next;
11096
}
11097
continue;
11098
}
11099
11100
target_list = GetTargetListForRowAndColumn (match_choice->choice, match_list, t->field);
11101
if (target_list == NULL) {
11102
ReportMissingTargets (&err_list, t->field, match_choice->data.ptrvalue, col_num, line_num);
11103
} else {
11104
if (val_vnp == NULL || val_vnp->data.ptrvalue == NULL) {
11105
val = "";
11106
} else {
11107
val = val_vnp->data.ptrvalue;
11108
}
11109
for (feat_vnp = target_list; feat_vnp != NULL; feat_vnp = feat_vnp->next) {
11110
if (val[0] == 0) {
11111
success = RemoveFieldValueForObject (feat_vnp->choice, feat_vnp->data.ptrvalue, t->field, NULL);
11112
} else {
11113
success = SetFieldValueForObject (feat_vnp->choice, feat_vnp->data.ptrvalue, t->field, NULL,
11114
val_vnp->data.ptrvalue, t->existing_text);
11115
}
11116
if (success) {
11117
num_fields_affected++;
11118
if (t->match_mrna && IsFieldTypeCDSProduct (t->field)
11119
&& feat_vnp->choice == OBJ_SEQFEAT) {
11120
if (AdjustmRNAProductToMatchProteinProduct (feat_vnp->data.ptrvalue)) {
11121
num_fields_affected++;
11122
}
11123
}
11124
} else {
11125
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (bad_col_val_fmt) + 30));
11126
sprintf (err_msg, bad_col_val_fmt, col_num, line_num);
11127
ValNodeAddPointer (&err_list, 0, err_msg);
11128
}
11129
}
11130
}
11131
target_list = ValNodeFree (target_list);
11132
if (val_vnp != NULL) {
11133
val_vnp = val_vnp->next;
11134
}
11135
}
11136
}
11137
match_list = ValNodeFree (match_list);
11138
}
11139
}
11140
11141
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (num_affected_fmt) + 15));
11142
sprintf (err_msg, num_affected_fmt, num_fields_affected);
11143
vnp = ValNodeNew (NULL);
11144
vnp->data.ptrvalue = err_msg;
11145
vnp->next = err_list;
11146
err_list = vnp;
11147
11148
return err_list;
11149
}
11150
11151
11152
NLM_EXTERN ValNodePtr CheckTableForExistingText (SeqEntryPtr sep, ValNodePtr table, ValNodePtr columns)
11153
{
11154
ValNodePtr err_list = NULL, vnp;
11155
ValNodePtr line_vnp, val_vnp, col_vnp;
11156
Int4 line_num = 1, col_num, num_existing_text = 0;
11157
Uint2 entityID;
11158
TabColumnConfigPtr t;
11159
CharPtr err_msg, str, qual_name, val;
11160
CharPtr no_match_fmt = "No match for %s, line %d";
11161
CharPtr no_feat_fmt = "No %s feature for %s (column %d, line %d)";
11162
CharPtr already_has_val_fmt = "%s already has value '%s' (column %d), line %d. Replacement is '%s'";
11163
CharPtr num_existing_text_fmt = "%d fields already have text.";
11164
ValNodePtr match_choice, match_list;
11165
ValNodePtr target_list, feat_vnp;
11166
11167
if (sep == NULL) {
11168
ValNodeAddPointer (&err_list, 1, StringSave ("No SeqEntry"));
11169
}
11170
if (table == NULL) {
11171
ValNodeAddPointer (&err_list, 1, StringSave ("No table"));
11172
}
11173
if (columns == NULL) {
11174
ValNodeAddPointer (&err_list, 1, StringSave ("No column information"));
11175
}
11176
if (err_list != NULL) {
11177
return err_list;
11178
}
11179
11180
entityID = SeqMgrGetEntityIDForSeqEntry (sep);
11181
11182
for (line_vnp = table, line_num = 1; line_vnp != NULL; line_vnp = line_vnp->next, line_num++) {
11183
match_choice = FindMatchChoiceInLine (line_vnp->data.ptrvalue, columns);
11184
if (match_choice == NULL || StringHasNoText (match_choice->data.ptrvalue)) {
11185
ReportEmptyIDColumn (&err_list, line_num);
11186
} else {
11187
match_list = FindMatchForRow (match_choice, entityID, sep);
11188
if (match_list == NULL) {
11189
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (no_match_fmt) + StringLen (match_choice->data.ptrvalue) + 15));
11190
sprintf (err_msg, no_match_fmt, match_choice->data.ptrvalue, line_num);
11191
ValNodeAddPointer (&err_list, 0, err_msg);
11192
} else {
11193
for (val_vnp = line_vnp->data.ptrvalue, col_vnp = columns, col_num = 1;
11194
col_vnp != NULL;
11195
col_vnp = col_vnp->next, col_num++) {
11196
t = (TabColumnConfigPtr) col_vnp->data.ptrvalue;
11197
if (t == NULL || t->match_type > 0
11198
|| (t->skip_blank && (val_vnp == NULL || StringHasNoText (val_vnp->data.ptrvalue)))) {
11199
if (val_vnp != NULL) {
11200
val_vnp = val_vnp->next;
11201
}
11202
continue;
11203
}
11204
target_list = GetTargetListForRowAndColumn (match_choice->choice, match_list, t->field);
11205
if (target_list == NULL) {
11206
ReportMissingTargets (&err_list, t->field, match_choice->data.ptrvalue, col_num, line_num);
11207
} else {
11208
if (val_vnp == NULL || val_vnp->data.ptrvalue == NULL) {
11209
val = "";
11210
} else {
11211
val = val_vnp->data.ptrvalue;
11212
}
11213
for (feat_vnp = target_list; feat_vnp != NULL; feat_vnp = feat_vnp->next) {
11214
str = GetFieldValueForObject (feat_vnp->choice, feat_vnp->data.ptrvalue, t->field, NULL);
11215
if (!StringHasNoText (str)) {
11216
qual_name = SummarizeFieldType (t->field);
11217
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (already_has_val_fmt)
11218
+ StringLen (qual_name) + StringLen (str)
11219
+ StringLen (val)
11220
+ 30));
11221
sprintf (err_msg, already_has_val_fmt, qual_name, str, col_num, line_num, val);
11222
ValNodeAddPointer (&err_list, col_num, err_msg);
11223
num_existing_text ++;
11224
}
11225
str = MemFree (str);
11226
}
11227
}
11228
target_list = ValNodeFree (target_list);
11229
if (val_vnp != NULL) {
11230
val_vnp = val_vnp->next;
11231
}
11232
}
11233
}
11234
match_list = ValNodeFree (match_list);
11235
}
11236
}
11237
if (num_existing_text > 0) {
11238
err_msg = (CharPtr) MemNew (sizeof (Char) * (StringLen (num_existing_text_fmt)
11239
+ 15));
11240
sprintf (err_msg, num_existing_text_fmt, num_existing_text);
11241
vnp = ValNodeNew (NULL);
11242
vnp->choice = 0;
11243
vnp->data.ptrvalue = err_msg;
11244
vnp->next = err_list;
11245
err_list = vnp;
11246
}
11247
11248
return err_list;
11249
}
11250
11251
11252
11253
11254
Loggerhead is a web-based interface for Breezy
Version: 2.0.1