« back to all changes in this revision
Viewing changes to imdb/parser/sql/__init__.py
- browse files at revision 9
- compare with another revision
- download diff
- download tarball
- view history from revision 9
- Committer: Bazaar Package Importer
- Author(s): Ana Beatriz Guerrero Lopez
- Date: 2008-04-20 19:51:14 UTC
- mfrom: (1.1.6 upstream)
- Revision ID: james.westby@ubuntu.com-20080420195114-csn8kwgswrqlr63h
Tags: 3.5-1
New upstream version.
- files added:
- bin/characters4local.py
- files modified:
- bin/get_character.py
added
removed
imdb/parser/sql/__init__.py
7
7
the imdb.IMDb function will return an instance of this class when
8
8
called with the 'accessSystem' argument set to "sql", "database" or "db".
9
9
10
Copyright 2005-2007 Davide Alberani <da@erlug.linux.it>
10
Copyright 2005-2008 Davide Alberani <da@erlug.linux.it>
11
11
12
12
This program is free software; you can redistribute it and/or modify
13
13
it under the terms of the GNU General Public License as published by
34
34
from dbschema import *
35
35
36
36
from imdb.parser.common.locsql import IMDbLocalAndSqlAccessSystem, \
37
scan_names, scan_titles, titleVariations, nameVariations
38
from imdb.utils import canonicalTitle, canonicalName, normalizeTitle, \
39
normalizeName, build_title, build_name, \
40
analyze_name, analyze_title, re_episodes, _articles
37
scan_names, scan_titles, titleVariations, \
38
nameVariations, merge_roles
39
from imdb.utils import normalizeTitle, normalizeName, build_title, \
40
build_name, analyze_name, analyze_title, \
41
re_episodes, _articles
41
42
from imdb.Person import Person
42
43
from imdb.Movie import Movie
43
44
from imdb._exceptions import IMDbDataAccessError, IMDbError
286
287
raise IMDbError, 'personID "%s" can\'t be converted to integer' % \
287
288
personID
288
289
290
def _normalize_characterID(self, characterID):
291
"""Normalize the given characterID."""
292
try:
293
return int(characterID)
294
except (ValueError, OverflowError):
295
raise IMDbError, 'characterID "%s" can\'t be converted to integer' \
296
% characterID
289
297
290
298
def get_imdbMovieID(self, movieID):
291
299
"""Translate a movieID in an imdbID.
326
334
except: pass
327
335
return imdbID
328
336
337
def get_imdbCharacterID(self, characterID):
338
"""Translate a characterID in an imdbID.
339
If not in the database, try an Exact Primary Name search on IMDb;
340
return None if it's unable to get the imdbID.
341
"""
342
try: character = CharName.get(characterID)
343
except SQLObjectNotFound: return None
344
imdbID = character.imdbID
345
if imdbID is not None: return '%07d' % imdbID
346
n_dict = {'name': character.name, 'imdbIndex': character.imdbIndex}
347
namline = build_name(n_dict, canonical=1)
348
imdbID = self.character2imdbID(namline)
349
if imdbID is not None:
350
try: character.imdbID = int(imdbID)
351
except: pass
352
return imdbID
353
329
354
def do_adult_search(self, doAdult):
330
355
"""If set to 0 or False, movies in the Adult category are not
331
356
episodeOf = title_dict.get('episode of')
431
456
if not res:
432
457
raise IMDbDataAccessError, 'unable to get movieID "%s"' % movieID
433
458
# Collect cast information.
434
castdata = [[cd.personID, cd.personRole, cd.note, cd.nrOrder,
459
castdata = [[cd.personID, cd.personRoleID, cd.note, cd.nrOrder,
435
460
self._role[cd.roleID]]
436
461
for cd in CastInfo.select(CastInfo.q.movieID == movieID)]
437
462
for p in castdata:
444
469
for group in castdata:
445
470
duty = group[0][4]
446
471
for pdata in group:
472
curRole = pdata[1]
473
curRoleID = None
474
if curRole is not None:
475
robj = CharName.get(curRole)
476
curRole = robj.name
477
curRoleID = robj.id
447
478
p = Person(personID=pdata[0], name=pdata[5],
448
currentRole=pdata[1] or u'', notes=pdata[2] or u'',
479
currentRole=curRole or u'',
480
roleID=curRoleID,
481
notes=pdata[2] or u'',
449
482
accessSystem='sql')
450
483
if pdata[6]: p['imdbIndex'] = pdata[6]
451
484
p.billingPos = pdata[3]
452
485
res.setdefault(duty, []).append(p)
486
if duty == 'cast':
487
res[duty] = merge_roles(res[duty])
453
488
res[duty].sort()
454
489
# Info about the movie.
455
490
minfo = [(self._info[m.infoTypeID], m.info, m.note)
612
647
raise IMDbDataAccessError, \
613
648
'unable to search the database: "%s"' % str(e)
614
649
615
resultsST = results
616
if not self.doAdult: resultsST = 0
617
res = scan_names(qr, name1, name2, name3, resultsST)
618
if results > 0: res[:] = res[:results]
650
res = scan_names(qr, name1, name2, name3, results)
619
651
res[:] = [x[1] for x in res]
620
652
# Purge empty imdbIndex.
621
653
returnl = []
639
671
if not res:
640
672
raise IMDbDataAccessError, 'unable to get personID "%s"' % personID
641
673
# Collect cast information.
642
castdata = [(cd.movieID, cd.personRole, cd.note, self._role[cd.roleID],
674
castdata = [(cd.movieID, cd.personRoleID, cd.note,
675
self._role[cd.roleID],
643
676
get_movie_data(cd.movieID, self._kind))
644
677
for cd in CastInfo.select(CastInfo.q.personID == personID)]
645
678
# Regroup by role/duty (cast, writer, director, ...)
656
689
if orig_duty not in ('actor', 'actress'):
657
690
if note: note = ' %s' % note
658
691
note = '[%s]%s' % (orig_duty, note)
692
curRole = mdata[1]
693
curRoleID = None
694
if curRole is not None:
695
robj = CharName.get(curRole)
696
curRole = robj.name
697
curRoleID = robj.id
659
698
m = Movie(movieID=mdata[0], data=mdata[4],
660
currentRole=mdata[1] or u'',
699
currentRole=curRole or u'',
700
roleID=curRoleID,
661
701
notes=note, accessSystem='sql')
662
702
if duty != 'episodes':
663
703
res.setdefault(duty, []).append(m)
670
710
res['episodes'] = episodes
671
711
for duty in seenDuties:
672
712
if res.has_key(duty):
713
if duty in ('actor', 'actress', 'himself', 'herself',
714
'themselves'):
715
res[duty] = merge_roles(res[duty])
673
716
res[duty].sort()
674
717
# XXX: is 'guest' still needed? I think every GA reference in
675
718
# the biographies.list file was removed.
733
776
get_person_episodes = get_person_main
734
777
735
778
def _search_character(self, name, results):
736
import warnings
737
warnings.warn('Character objects still unsupported for "sql"')
738
return []
739
740
def get_character_main(self, characterID):
741
import warnings
742
warnings.warn('Character objects still unsupported for "sql"')
743
return {}
779
name = name.strip()
780
if not name: return []
781
s_name = analyze_name(name)['name']
782
if not s_name: return []
783
if isinstance(s_name, UnicodeType):
784
s_name = s_name.encode('ascii', 'ignore')
785
s_name = normalizeName(s_name)
786
soundexCode = soundex(s_name)
787
surname = s_name.split(' ')[-1]
788
surnameSoundex = soundex(surname)
789
name2 = ''
790
soundexName2 = None
791
nsplit = s_name.split()
792
if len(nsplit) > 1:
793
name2 = '%s %s' % (nsplit[-1], ' '.join(nsplit[:-1]))
794
if s_name == name2:
795
name2 = ''
796
else:
797
soundexName2 = soundex(name2)
798
# If the soundex is None, compare only with the first
799
# phoneticCode column.
800
if soundexCode is not None:
801
if soundexName2 is not None:
802
condition = OR(surnameSoundex == CharName.q.surnamePcode,
803
IN(CharName.q.namePcodeNf, [soundexCode,
804
soundexName2]),
805
IN(CharName.q.surnamePcode, [soundexCode,
806
soundexName2]))
807
else:
808
condition = OR(surnameSoundex == CharName.q.surnamePcode,
809
IN(soundexCode, [CharName.q.namePcodeNf,
810
CharName.q.surnamePcode]))
811
else:
812
condition = ISNULL(Name.q.namePcodeNf)
813
try:
814
qr = [(q.id, {'name': q.name, 'imdbIndex': q.imdbIndex})
815
for q in CharName.select(condition)]
816
except SQLObjectNotFound, e:
817
raise IMDbDataAccessError, \
818
'unable to search the database: "%s"' % str(e)
819
res = scan_names(qr, s_name, name2, '', results,
820
_scan_character=True)
821
res[:] = [x[1] for x in res]
822
# Purge empty imdbIndex.
823
returnl = []
824
for x in res:
825
tmpd = x[1]
826
if tmpd['imdbIndex'] is None:
827
del tmpd['imdbIndex']
828
returnl.append((x[0], tmpd))
829
return returnl
830
831
def get_character_main(self, characterID, results=1000):
832
# Every person information is retrieved from here.
833
infosets = self.get_character_infoset()
834
try:
835
c = CharName.get(characterID)
836
except SQLObjectNotFound, e:
837
raise IMDbDataAccessError, \
838
'unable to get characterID "%s": "%s"' % (characterID, e)
839
res = {'name': c.name, 'imdbIndex': c.imdbIndex}
840
if res['imdbIndex'] is None: del res['imdbIndex']
841
if not res:
842
raise IMDbDataAccessError, 'unable to get characterID "%s"' % \
843
characterID
844
# Collect filmography information.
845
items = CastInfo.select(CastInfo.q.personRoleID == characterID)
846
if results > 0:
847
items = items[:results]
848
filmodata = [(cd.movieID, cd.personID, cd.note,
849
get_movie_data(cd.movieID, self._kind)) for cd in items
850
if self._role[cd.roleID] in ('actor', 'actress')]
851
fdata = []
852
for f in filmodata:
853
curRole = None
854
curRoleID = f[1]
855
note = f[2] or u''
856
if curRoleID is not None:
857
robj = Name.get(curRoleID)
858
curRole = robj.name
859
m = Movie(movieID=f[0], data=f[3],
860
currentRole=curRole or u'',
861
roleID=curRoleID, roleIsPerson=True,
862
notes=note, accessSystem='sql')
863
fdata.append(m)
864
fdata = merge_roles(fdata)
865
fdata.sort()
866
if fdata:
867
res['filmography'] = fdata
868
return {'data': res, 'info sets': infosets}
869
744
870
get_character_filmography = get_character_main
745
871
get_character_biography = get_character_main
746
872
Loggerhead is a web-based interface for Breezy
Version: 2.0.1