1
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
2
/* ***** BEGIN LICENSE BLOCK *****
3
* Version: NPL 1.1/GPL 2.0/LGPL 2.1
5
* The contents of this file are subject to the Netscape Public License
6
* Version 1.1 (the "License"); you may not use this file except in
7
* compliance with the License. You may obtain a copy of the License at
8
* http://www.mozilla.org/NPL/
10
* Software distributed under the License is distributed on an "AS IS" basis,
11
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
12
* for the specific language governing rights and limitations under the
15
* The Original Code is mozilla.org code.
17
* The Initial Developer of the Original Code is
18
* Netscape Communications Corporation.
19
* Portions created by the Initial Developer are Copyright (C) 1998
20
* the Initial Developer. All Rights Reserved.
24
* Alternatively, the contents of this file may be used under the terms of
25
* either the GNU General Public License Version 2 or later (the "GPL"), or
26
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
27
* in which case the provisions of the GPL or the LGPL are applicable instead
28
* of those above. If you wish to allow use of your version of this file only
29
* under the terms of either the GPL or the LGPL, and not to allow others to
30
* use your version of this file under the terms of the NPL, indicate your
31
* decision by deleting the provisions above and replace them with the notice
32
* and other provisions required by the GPL or the LGPL. If you do not delete
33
* the provisions above, a recipient may use your version of this file under
34
* the terms of any one of the NPL, the GPL or the LGPL.
36
* ***** END LICENSE BLOCK ***** */
43
* Much as I hate to do it, we were using string compares wrong.
44
* Often, programmers call functions like strcmp(s1,s2), and pass
45
* one or more null strings. Rather than blow up on these, I've
46
* added quick checks to ensure that cases like this don't cause
49
* In general, if you pass a null into any of these string compare
50
* routines, we simply return 0.
55
#include "nsIServiceManager.h"
57
// XXX Bug: These tables don't lowercase the upper 128 characters properly
59
// This table maps uppercase characters to lower case characters;
60
// characters that are neither upper nor lower case are unaffected.
61
static const unsigned char kUpper2Lower[256] = {
62
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
63
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
64
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
65
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
68
// upper band mapped to lower [A-Z] => [a-z]
69
97, 98, 99,100,101,102,103,104,105,106,107,108,109,110,111,
70
112,113,114,115,116,117,118,119,120,121,122,
73
96, 97, 98, 99,100,101,102,103,104,105,106,107,108,109,110,111,
74
112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,
75
128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,
76
144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,
77
160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,
78
176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,
79
192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,
80
208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,
81
224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,
82
240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255
85
static const unsigned char kLower2Upper[256] = {
86
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
87
16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
88
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
89
48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
90
64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79,
91
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95,
94
// lower band mapped to upper [a-z] => [A-Z]
95
65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79,
96
80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90,
99
128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,
100
144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,
101
160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,
102
176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,
103
192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,
104
208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,
105
224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,
106
240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255
109
//----------------------------------------------------------------------
111
char nsCRT::ToUpper(char aChar)
113
return (char)kLower2Upper[(unsigned char)aChar];
116
char nsCRT::ToLower(char aChar)
118
return (char)kUpper2Lower[(unsigned char)aChar];
121
PRBool nsCRT::IsUpper(char aChar)
123
return aChar != nsCRT::ToLower(aChar);
126
PRBool nsCRT::IsLower(char aChar)
128
return aChar != nsCRT::ToUpper(aChar);
131
////////////////////////////////////////////////////////////////////////////////
132
// My lovely strtok routine
134
#define IS_DELIM(m, c) ((m)[(c) >> 3] & (1 << ((c) & 7)))
135
#define SET_DELIM(m, c) ((m)[(c) >> 3] |= (1 << ((c) & 7)))
136
#define DELIM_TABLE_SIZE 32
138
char* nsCRT::strtok(char* string, const char* delims, char* *newStr)
140
NS_ASSERTION(string, "Unlike regular strtok, the first argument cannot be null.");
142
char delimTable[DELIM_TABLE_SIZE];
147
for (i = 0; i < DELIM_TABLE_SIZE; i++)
148
delimTable[i] = '\0';
150
for (i = 0; delims[i]; i++) {
151
SET_DELIM(delimTable, NS_STATIC_CAST(PRUint8, delims[i]));
153
NS_ASSERTION(delims[i] == '\0', "too many delimiters");
156
while (*str && IS_DELIM(delimTable, NS_STATIC_CAST(PRUint8, *str))) {
161
// fix up the end of the token
163
if (IS_DELIM(delimTable, NS_STATIC_CAST(PRUint8, *str))) {
171
return str == result ? NULL : result;
174
////////////////////////////////////////////////////////////////////////////////
176
PRUint32 nsCRT::strlen(const PRUnichar* s)
189
* Compare unichar string ptrs, stopping at the 1st null
190
* NOTE: If both are null, we return 0.
191
* NOTE: We terminate the search upon encountering a NULL
193
* @update gess 11/10/99
194
* @param s1 and s2 both point to unichar strings
195
* @return 0 if they match, -1 if s1<s2; 1 if s1>s2
197
PRInt32 nsCRT::strcmp(const PRUnichar* s1, const PRUnichar* s2) {
200
PRUnichar c1 = *s1++;
201
PRUnichar c2 = *s2++;
203
if (c1 < c2) return -1;
206
if ((0==c1) || (0==c2)) break;
210
if (s1) // s2 must have been null
212
if (s2) // s1 must have been null
219
* Compare unichar string ptrs, stopping at the 1st null or nth char.
220
* NOTE: If either is null, we return 0.
221
* NOTE: We DO NOT terminate the search upon encountering NULL's before N
223
* @update gess 11/10/99
224
* @param s1 and s2 both point to unichar strings
225
* @return 0 if they match, -1 if s1<s2; 1 if s1>s2
227
PRInt32 nsCRT::strncmp(const PRUnichar* s1, const PRUnichar* s2, PRUint32 n) {
231
PRUnichar c1 = *s1++;
232
PRUnichar c2 = *s2++;
234
if (c1 < c2) return -1;
243
PRUnichar* nsCRT::strdup(const PRUnichar* str)
245
PRUint32 len = nsCRT::strlen(str);
246
return strndup(str, len);
249
PRUnichar* nsCRT::strndup(const PRUnichar* str, PRUint32 len)
251
nsCppSharedAllocator<PRUnichar> shared_allocator;
252
PRUnichar* rslt = shared_allocator.allocate(len + 1); // add one for the null
253
// PRUnichar* rslt = new PRUnichar[len + 1];
255
if (rslt == NULL) return NULL;
256
memcpy(rslt, str, len * sizeof(PRUnichar));
262
* |nsCRT::HashCode| is identical to |PL_HashString|, which tests
263
* (http://bugzilla.mozilla.org/showattachment.cgi?attach_id=26596)
264
* show to be the best hash among several other choices.
266
* We re-implement it here rather than calling it for two reasons:
267
* (1) in this interface, we also calculate the length of the
268
* string being hashed; and (2) the narrow and wide and `buffer' versions here
269
* will hash equivalent strings to the same value, e.g., "Hello" and L"Hello".
271
PRUint32 nsCRT::HashCode(const char* str, PRUint32* resultingStrLen)
280
h = (h>>28) ^ (h<<4) ^ c;
282
if ( resultingStrLen )
283
*resultingStrLen = (s-str)-1;
287
PRUint32 nsCRT::HashCode(const PRUnichar* str, PRUint32* resultingStrLen)
290
const PRUnichar* s = str;
296
h = (h>>28) ^ (h<<4) ^ c;
298
if ( resultingStrLen )
299
*resultingStrLen = (s-str)-1;
303
PRUint32 nsCRT::HashCodeAsUTF8(const PRUnichar* str, PRUint32* resultingStrLen)
306
const PRUnichar* s = str;
309
PRUint16 W1 = 0; // the first UTF-16 word in a two word tuple
310
PRUint32 U = 0; // the current char as UCS-4
311
int code_length = 0; // the number of bytes in the UTF-8 sequence for the current char
317
* On the fly, decoding from UTF-16 (and/or UCS-2) into UTF-8 as per
318
* http://www.ietf.org/rfc/rfc2781.txt
319
* http://www.ietf.org/rfc/rfc2279.txt
324
if ( W < 0xD800 || 0xDFFF < W )
329
else if ( W <= 0x07FF )
334
else if ( /* 0xD800 <= W1 && */ W <= 0xDBFF )
339
// as required by the standard, this code is careful to
340
// throw out illegal sequences
342
if ( 0xDC00 <= W && W <= 0xDFFF )
344
U = PRUint32( (W1&0x03FF)<<10 | (W&0x3FFF) );
345
if ( U <= 0x001FFFFF )
347
else if ( U <= 0x3FFFFFF )
356
if ( code_length > 0 )
358
static const PRUint16 sBytePrefix[7] = { 0x0000, 0x0000, 0x00C0, 0x00E0, 0x00F0, 0x00F8, 0x00FC };
359
static const PRUint16 sShift[7] = { 0, 0, 6, 12, 18, 24, 30 };
362
* Unlike the algorithm in http://www.ietf.org/rfc/rfc2279.txt
363
* we must calculate the bytes in left to right order so that
364
* our hash result matches what the narrow version would calculate
365
* on an already UTF-8 string.
368
// hash the first (and often, only, byte)
369
h = (h>>28) ^ (h<<4) ^ (sBytePrefix[code_length] | (U>>sShift[code_length]));
371
// an unrolled loop for hashing any remaining bytes in this sequence
372
switch ( code_length )
373
{ // falling through in each case
374
case 6: h = (h>>28) ^ (h<<4) ^ (0x80 | ((U>>24) & 0x003F));
375
case 5: h = (h>>28) ^ (h<<4) ^ (0x80 | ((U>>18) & 0x003F));
376
case 4: h = (h>>28) ^ (h<<4) ^ (0x80 | ((U>>12) & 0x003F));
377
case 3: h = (h>>28) ^ (h<<4) ^ (0x80 | ((U>>6 ) & 0x003F));
378
case 2: h = (h>>28) ^ (h<<4) ^ (0x80 | ( U & 0x003F));
379
default: code_length = 0;
386
if ( resultingStrLen )
387
*resultingStrLen = (s-str)-1;
391
PRUint32 nsCRT::BufferHashCode(const char* s, PRUint32 len)
394
const char* done = s + len;
397
h = (h>>28) ^ (h<<4) ^ PRUint8(*s++); // cast to unsigned to prevent possible sign extension
402
PRUint32 nsCRT::BufferHashCode(const PRUnichar* s, PRUint32 len)
405
const PRUnichar* done = s + len;
408
h = (h>>28) ^ (h<<4) ^ PRUint16(*s++); // cast to unsigned to prevent possible sign extension
413
// This should use NSPR but NSPR isn't exporting its PR_strtoll function
415
PRInt64 nsCRT::atoll(const char *str)
420
PRInt64 ll = LL_Zero(), digitll = LL_Zero();
422
while (*str && *str >= '0' && *str <= '9') {
424
LL_UI2L(digitll, (*str - '0'));
425
LL_ADD(ll, ll, digitll);
433
* Determine if given char in valid ascii range
435
* @update ftang 04.27.2000
436
* @param aChar is character to be tested
437
* @return TRUE if in ASCII range
439
PRBool nsCRT::IsAscii(PRUnichar aChar) {
440
return (0x0080 > aChar);
443
* Determine if given char in valid ascii range
445
* @update ftang 10.02.2001
446
* @param aString is null terminated to be tested
447
* @return TRUE if all characters aare in ASCII range
449
PRBool nsCRT::IsAscii(const PRUnichar *aString) {
451
if( 0x0080 <= *aString)
458
* Determine if given char in valid ascii range
460
* @update ftang 10.02.2001
461
* @param aString is null terminated to be tested
462
* @return TRUE if all characters aare in ASCII range
464
PRBool nsCRT::IsAscii(const char *aString) {
473
* Determine whether the given string consists of valid ascii chars
475
* @param aString is null terminated
476
* @param aLength is the number of chars to test. This must be at most
477
* the number of chars in aString before the null terminator
478
* @return PR_TRUE if all chars are valid ASCII chars, PR_FALSE otherwise
480
PRBool nsCRT::IsAscii(const char* aString, PRUint32 aLength)
482
const char* end = aString + aLength;
483
while (aString < end) {
484
NS_ASSERTION(*aString, "Null byte before end of data!");
493
* Determine if given char in valid alpha range
495
* @update rickg 03.10.2000
496
* @param aChar is character to be tested
497
* @return TRUE if in alpha range
499
PRBool nsCRT::IsAsciiAlpha(PRUnichar aChar) {
501
if (((aChar >= 'A') && (aChar <= 'Z')) || ((aChar >= 'a') && (aChar <= 'z'))) {
508
* Determine if given char is a valid space character
510
* @update rickg 03.10.2000
511
* @param aChar is character to be tested
512
* @return TRUE if is valid space char
514
PRBool nsCRT::IsAsciiSpace(PRUnichar aChar) {
516
if ((aChar == ' ') || (aChar == '\r') || (aChar == '\n') || (aChar == '\t')) {
525
* Determine if given char is valid digit
527
* @update rickg 03.10.2000
528
* @param aChar is character to be tested
529
* @return TRUE if char is a valid digit
531
PRBool nsCRT::IsAsciiDigit(PRUnichar aChar) {
533
return PRBool((aChar >= '0') && (aChar <= '9'));