MagickCore 7.1.1
Convert, Edit, Or Compose Bitmap Images
Loading...
Searching...
No Matches
token.c
1/*
2%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
3% %
4% %
5% %
6% TTTTT OOO K K EEEEE N N %
7% T O O K K E NN N %
8% T O O KKK EEE N N N %
9% T O O K K E N NN %
10% T OOO K K EEEEE N N %
11% %
12% %
13% MagickCore Token Methods %
14% %
15% Software Design %
16% Cristy %
17% January 1993 %
18% %
19% %
20% Copyright @ 1999 ImageMagick Studio LLC, a non-profit organization %
21% dedicated to making software imaging solutions freely available. %
22% %
23% You may not use this file except in compliance with the License. You may %
24% obtain a copy of the License at %
25% %
26% https://imagemagick.org/script/license.php %
27% %
28% Unless required by applicable law or agreed to in writing, software %
29% distributed under the License is distributed on an "AS IS" BASIS, %
30% WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. %
31% See the License for the specific language governing permissions and %
32% limitations under the License. %
33% %
34%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
35%
36%
37%
38*/
39
40/*
41 Include declarations.
42*/
43#include "MagickCore/studio.h"
44#include "MagickCore/exception.h"
45#include "MagickCore/exception-private.h"
46#include "MagickCore/image.h"
47#include "MagickCore/image-private.h"
48#include "MagickCore/locale-private.h"
49#include "MagickCore/memory_.h"
50#include "MagickCore/memory-private.h"
51#include "MagickCore/string_.h"
52#include "MagickCore/string-private.h"
53#include "MagickCore/token.h"
54#include "MagickCore/token-private.h"
55#include "MagickCore/utility.h"
56#include "MagickCore/utility-private.h"
57
58/*
59 Typedef declarations.
60*/
62{
63 int
64 state;
65
66 MagickStatusType
67 flag;
68
69 ssize_t
70 offset;
71
72 char
73 quote;
74
75 size_t
76 signature;
77};
78
79/*
80%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
81% %
82% %
83% %
84% A c q u i r e T o k e n I n f o %
85% %
86% %
87% %
88%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
89%
90% AcquireTokenInfo() allocates the TokenInfo structure.
91%
92% The format of the AcquireTokenInfo method is:
93%
94% TokenInfo *AcquireTokenInfo()
95%
96*/
97MagickExport TokenInfo *AcquireTokenInfo(void)
98{
100 *token_info;
101
102 token_info=(TokenInfo *) AcquireCriticalMemory(sizeof(*token_info));
103 token_info->signature=MagickCoreSignature;
104 return(token_info);
105}
106
107/*
108%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
109% %
110% %
111% %
112% D e s t r o y T o k e n I n f o %
113% %
114% %
115% %
116%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
117%
118% DestroyTokenInfo() deallocates memory associated with an TokenInfo
119% structure.
120%
121% The format of the DestroyTokenInfo method is:
122%
123% TokenInfo *DestroyTokenInfo(TokenInfo *token_info)
124%
125% A description of each parameter follows:
126%
127% o token_info: Specifies a pointer to an TokenInfo structure.
128%
129*/
130MagickExport TokenInfo *DestroyTokenInfo(TokenInfo *token_info)
131{
132 assert(token_info != (TokenInfo *) NULL);
133 assert(token_info->signature == MagickCoreSignature);
134 if (IsEventLogging() != MagickFalse)
135 (void) LogMagickEvent(TraceEvent,GetMagickModule(),"...");
136 token_info->signature=(~MagickCoreSignature);
137 token_info=(TokenInfo *) RelinquishMagickMemory(token_info);
138 return(token_info);
139}
140
141/*
142%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
143% %
144% %
145% %
146+ G e t N e x t T o k e n %
147% %
148% %
149% %
150%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
151%
152% GetNextToken() gets a token from the token stream. A token is defined as
153% a sequence of characters delimited by whitespace (e.g. clip-path), a
154% sequence delimited with quotes (.e.g "Quote me"), or a sequence enclosed in
155% parenthesis (e.g. rgb(0,0,0)). GetNextToken() also recognizes these
156% separator characters: ':', '=', ',', and ';'. GetNextToken() returns the
157% length of the consumed token.
158%
159% The format of the GetNextToken method is:
160%
161% size_t GetNextToken(const char *magick_restrict start,
162% const char **magick_restrict end,const size_t extent,
163% char *magick_restrict token)
164%
165% A description of each parameter follows:
166%
167% o start: the start of the token sequence.
168%
169% o end: point to the end of the token sequence.
170%
171% o extent: maximum extent of the token.
172%
173% o token: copy the token to this buffer.
174%
175*/
176MagickExport magick_hot_spot size_t GetNextToken(
177 const char *magick_restrict start,const char **magick_restrict end,
178 const size_t extent,char *magick_restrict token)
179{
180 char
181 *magick_restrict q;
182
183 const char
184 *magick_restrict p;
185
186 double
187 value;
188
189 ssize_t
190 i;
191
192 assert(start != (const char *) NULL);
193 assert(token != (char *) NULL);
194 i=0;
195 p=start;
196 while ((isspace((int) ((unsigned char) *p)) != 0) && (*p != '\0'))
197 p++;
198 switch (*p)
199 {
200 case '\0':
201 break;
202 case '"':
203 case '\'':
204 case '`':
205 case '{':
206 {
207 char
208 escape;
209
210 switch (*p)
211 {
212 case '"': escape='"'; break;
213 case '\'': escape='\''; break;
214 case '`': escape='\''; break;
215 case '{': escape='}'; break;
216 default: escape=(*p); break;
217 }
218 for (p++; *p != '\0'; p++)
219 {
220 if ((*p == '\\') && ((*(p+1) == escape) || (*(p+1) == '\\')))
221 p++;
222 else
223 if (*p == escape)
224 {
225 p++;
226 break;
227 }
228 if (i < (ssize_t) (extent-1))
229 token[i++]=(*p);
230 if ((size_t) (p-start) >= (extent-1))
231 break;
232 }
233 break;
234 }
235 case '/':
236 {
237 if (i < (ssize_t) (extent-1))
238 token[i++]=(*p);
239 p++;
240 if ((*p == '>') || (*p == '/'))
241 {
242 if (i < (ssize_t) (extent-1))
243 token[i++]=(*p);
244 p++;
245 }
246 break;
247 }
248 default:
249 {
250 value=StringToDouble(p,&q);
251 (void) value;
252 if ((p != q) && (*p != ','))
253 {
254 for ( ; (p < q) && (*p != ','); p++)
255 {
256 if (i < (ssize_t) (extent-1))
257 token[i++]=(*p);
258 if ((size_t) (p-start) >= (extent-1))
259 break;
260 }
261 if (*p == '%')
262 {
263 if (i < (ssize_t) (extent-1))
264 token[i++]=(*p);
265 p++;
266 }
267 break;
268 }
269 if ((*p != '\0') && (isalpha((int) ((unsigned char) *p)) == 0) &&
270 (*p != *DirectorySeparator) && (*p != '#') && (*p != '<'))
271 {
272 if (i < (ssize_t) (extent-1))
273 token[i++]=(*p);
274 p++;
275 break;
276 }
277 for ( ; *p != '\0'; p++)
278 {
279 if (((isspace((int) ((unsigned char) *p)) != 0) || (*p == '=') ||
280 (*p == ',') || (*p == ':') || (*p == ';')) && (*(p-1) != '\\'))
281 break;
282 if ((i > 0) && (*p == '<'))
283 break;
284 if (i < (ssize_t) (extent-1))
285 token[i++]=(*p);
286 if (*p == '>')
287 break;
288 if (*p == '(')
289 {
290 for (p++; *p != '\0'; p++)
291 {
292 if (i < (ssize_t) (extent-1))
293 token[i++]=(*p);
294 if ((*p == ')') && (*(p-1) != '\\'))
295 break;
296 if ((size_t) (p-start) >= (extent-1))
297 break;
298 }
299 if (*p == '\0')
300 break;
301 }
302 if ((size_t) (p-start) >= (extent-1))
303 break;
304 }
305 break;
306 }
307 }
308 token[i]='\0';
309 if (LocaleNCompare(token,"url(#",5) == 0)
310 {
311 q=strrchr(token,')');
312 if (q != (char *) NULL)
313 {
314 *q='\0';
315 (void) memmove(token,token+5,(size_t) (q-token-4));
316 }
317 }
318 while (isspace((int) ((unsigned char) *p)) != 0)
319 p++;
320 if (end != (const char **) NULL)
321 *end=(const char *) p;
322 return((size_t) (p-start+1));
323}
324
325/*
326%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
327% %
328% %
329% %
330% G l o b E x p r e s s i o n %
331% %
332% %
333% %
334%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
335%
336% GlobExpression() returns MagickTrue if the expression matches the pattern.
337%
338% The format of the GlobExpression function is:
339%
340% MagickBooleanType GlobExpression(const char *magick_restrict expression,
341% const char *magick_restrict pattern,
342% const MagickBooleanType case_insensitive)
343%
344% A description of each parameter follows:
345%
346% o expression: Specifies a pointer to a text string containing a file name.
347%
348% o pattern: Specifies a pointer to a text string containing a pattern.
349%
350% o case_insensitive: set to MagickTrue to ignore the case when matching
351% an expression.
352%
353*/
354MagickExport MagickBooleanType GlobExpression(
355 const char *magick_restrict expression,const char *magick_restrict pattern,
356 const MagickBooleanType case_insensitive)
357{
358 char
359 path[MagickPathExtent];
360
361 MagickBooleanType
362 done,
363 match;
364
365 /*
366 Return on empty pattern or '*'.
367 */
368 if (pattern == (char *) NULL)
369 return(MagickTrue);
370 if (GetUTFCode(pattern) == 0)
371 return(MagickTrue);
372 if (LocaleCompare(pattern,"*") == 0)
373 return(MagickTrue);
374 GetPathComponent(pattern,SubimagePath,path);
375 if (*path != '\0')
376 return(MagickFalse);
377 /*
378 Evaluate glob expression.
379 */
380 done=MagickFalse;
381 while ((GetUTFCode(pattern) != 0) && (done == MagickFalse))
382 {
383 if (GetUTFCode(expression) == 0)
384 if ((GetUTFCode(pattern) != '{') && (GetUTFCode(pattern) != '*'))
385 break;
386 switch (GetUTFCode(pattern))
387 {
388 case '*':
389 {
390 MagickBooleanType
391 status;
392
393 status=MagickFalse;
394 while (GetUTFCode(pattern) == '*')
395 pattern+=GetUTFOctets(pattern);
396 while ((GetUTFCode(expression) != 0) && (status == MagickFalse))
397 {
398 status=GlobExpression(expression,pattern,case_insensitive);
399 expression+=GetUTFOctets(expression);
400 }
401 if (status != MagickFalse)
402 {
403 while (GetUTFCode(expression) != 0)
404 expression+=GetUTFOctets(expression);
405 while (GetUTFCode(pattern) != 0)
406 pattern+=GetUTFOctets(pattern);
407 }
408 break;
409 }
410 case '[':
411 {
412 int
413 c;
414
415 pattern+=GetUTFOctets(pattern);
416 for ( ; ; )
417 {
418 if ((GetUTFCode(pattern) == 0) || (GetUTFCode(pattern) == ']'))
419 {
420 done=MagickTrue;
421 break;
422 }
423 if (GetUTFCode(pattern) == '\\')
424 {
425 pattern+=GetUTFOctets(pattern);
426 if (GetUTFCode(pattern) == 0)
427 {
428 done=MagickTrue;
429 break;
430 }
431 }
432 if (GetUTFCode(pattern+GetUTFOctets(pattern)) == '-')
433 {
434 c=GetUTFCode(pattern);
435 pattern+=GetUTFOctets(pattern);
436 pattern+=GetUTFOctets(pattern);
437 if (GetUTFCode(pattern) == ']')
438 {
439 done=MagickTrue;
440 break;
441 }
442 if (GetUTFCode(pattern) == '\\')
443 {
444 pattern+=GetUTFOctets(pattern);
445 if (GetUTFCode(pattern) == 0)
446 {
447 done=MagickTrue;
448 break;
449 }
450 }
451 if ((GetUTFCode(expression) < c) ||
452 (GetUTFCode(expression) > GetUTFCode(pattern)))
453 {
454 pattern+=GetUTFOctets(pattern);
455 continue;
456 }
457 }
458 else
459 if (GetUTFCode(pattern) != GetUTFCode(expression))
460 {
461 pattern+=GetUTFOctets(pattern);
462 continue;
463 }
464 pattern+=GetUTFOctets(pattern);
465 while ((GetUTFCode(pattern) != ']') && (GetUTFCode(pattern) != 0))
466 {
467 if ((GetUTFCode(pattern) == '\\') &&
468 (GetUTFCode(pattern+GetUTFOctets(pattern)) > 0))
469 pattern+=GetUTFOctets(pattern);
470 pattern+=GetUTFOctets(pattern);
471 }
472 if (GetUTFCode(pattern) != 0)
473 {
474 pattern+=GetUTFOctets(pattern);
475 expression+=GetUTFOctets(expression);
476 }
477 break;
478 }
479 break;
480 }
481 case '?':
482 {
483 pattern+=GetUTFOctets(pattern);
484 expression+=GetUTFOctets(expression);
485 break;
486 }
487 case '{':
488 {
489 char
490 *target;
491
492 char
493 *p;
494
495 target=AcquireString(pattern);
496 p=target;
497 pattern++;
498 while ((GetUTFCode(pattern) != '}') && (GetUTFCode(pattern) != 0))
499 {
500 *p++=(*pattern++);
501 if ((GetUTFCode(pattern) == ',') || (GetUTFCode(pattern) == '}'))
502 {
503 *p='\0';
504 match=GlobExpression(expression,target,case_insensitive);
505 if (match != MagickFalse)
506 {
507 expression+=MagickMin(strlen(expression),strlen(target));
508 break;
509 }
510 p=target;
511 pattern+=GetUTFOctets(pattern);
512 }
513 }
514 while ((GetUTFCode(pattern) != '}') && (GetUTFCode(pattern) != 0))
515 pattern+=GetUTFOctets(pattern);
516 if (GetUTFCode(pattern) != 0)
517 pattern+=GetUTFOctets(pattern);
518 target=DestroyString(target);
519 break;
520 }
521 case '\\':
522 {
523 pattern+=GetUTFOctets(pattern);
524 if (GetUTFCode(pattern) == 0)
525 break;
526 magick_fallthrough;
527 }
528 default:
529 {
530 if (case_insensitive != MagickFalse)
531 {
532 if (LocaleToLowercase((int) GetUTFCode(expression)) != LocaleToLowercase((int) GetUTFCode(pattern)))
533 {
534 done=MagickTrue;
535 break;
536 }
537 }
538 else
539 if (GetUTFCode(expression) != GetUTFCode(pattern))
540 {
541 done=MagickTrue;
542 break;
543 }
544 expression+=GetUTFOctets(expression);
545 pattern+=GetUTFOctets(pattern);
546 }
547 }
548 }
549 while (GetUTFCode(pattern) == '*')
550 pattern+=GetUTFOctets(pattern);
551 match=(GetUTFCode(expression) == 0) && (GetUTFCode(pattern) == 0) ?
552 MagickTrue : MagickFalse;
553 return(match);
554}
555
556/*
557%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
558% %
559% %
560% %
561+ I s G l o b %
562% %
563% %
564% %
565%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
566%
567% IsGlob() returns MagickTrue if the path specification contains a globbing
568% pattern.
569%
570% The format of the IsGlob method is:
571%
572% MagickBooleanType IsGlob(const char *geometry)
573%
574% A description of each parameter follows:
575%
576% o path: the path.
577%
578*/
579MagickPrivate MagickBooleanType IsGlob(const char *path)
580{
581 MagickBooleanType
582 status = MagickFalse;
583
584 const char
585 *p;
586
587 if (IsPathAccessible(path) != MagickFalse)
588 return(MagickFalse);
589 for (p=path; *p != '\0'; p++)
590 {
591 switch (*p)
592 {
593 case '*':
594 case '?':
595 case '{':
596 case '}':
597 case '[':
598 case ']':
599 {
600 status=MagickTrue;
601 break;
602 }
603 default:
604 break;
605 }
606 }
607 return(status);
608}
609
610/*
611%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
612% %
613% %
614% %
615% T o k e n i z e r %
616% %
617% %
618% %
619%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
620%
621% Tokenizer() is a generalized, finite state token parser. It extracts tokens
622% one at a time from a string of characters. The characters used for white
623% space, for break characters, and for quotes can be specified. Also,
624% characters in the string can be preceded by a specifiable escape character
625% which removes any special meaning the character may have.
626%
627% Here is some terminology:
628%
629% o token: A single unit of information in the form of a group of
630% characters.
631%
632% o white space: Apace that gets ignored (except within quotes or when
633% escaped), like blanks and tabs. in addition, white space terminates a
634% non-quoted token.
635%
636% o break set: One or more characters that separates non-quoted tokens.
637% Commas are a common break character. The usage of break characters to
638% signal the end of a token is the same as that of white space, except
639% multiple break characters with nothing or only white space between
640% generate a null token for each two break characters together.
641%
642% For example, if blank is set to be the white space and comma is set to
643% be the break character, the line
644%
645% A, B, C , , DEF
646%
647% ... consists of 5 tokens:
648%
649% 1) "A"
650% 2) "B"
651% 3) "C"
652% 4) "" (the null string)
653% 5) "DEF"
654%
655% o Quote character: A character that, when surrounding a group of other
656% characters, causes the group of characters to be treated as a single
657% token, no matter how many white spaces or break characters exist in
658% the group. Also, a token always terminates after the closing quote.
659% For example, if ' is the quote character, blank is white space, and
660% comma is the break character, the following string
661%
662% A, ' B, CD'EF GHI
663%
664% ... consists of 4 tokens:
665%
666% 1) "A"
667% 2) " B, CD" (note the blanks & comma)
668% 3) "EF"
669% 4) "GHI"
670%
671% The quote characters themselves do not appear in the resultant
672% tokens. The double quotes are delimiters i use here for
673% documentation purposes only.
674%
675% o Escape character: A character which itself is ignored but which
676% causes the next character to be used as is. ^ and \ are often used
677% as escape characters. An escape in the last position of the string
678% gets treated as a "normal" (i.e., non-quote, non-white, non-break,
679% and non-escape) character. For example, assume white space, break
680% character, and quote are the same as in the above examples, and
681% further, assume that ^ is the escape character. Then, in the string
682%
683% ABC, ' DEF ^' GH' I ^ J K^ L ^
684%
685% ... there are 7 tokens:
686%
687% 1) "ABC"
688% 2) " DEF ' GH"
689% 3) "I"
690% 4) " " (a lone blank)
691% 5) "J"
692% 6) "K L"
693% 7) "^" (passed as is at end of line)
694%
695% The format of the Tokenizer method is:
696%
697% int Tokenizer(TokenInfo *token_info,const unsigned flag,char *token,
698% const size_t max_token_length,const char *line,const char *white,
699% const char *break_set,const char *quote,const char escape,
700% char *breaker,int *next,char *quoted)
701%
702% A description of each parameter follows:
703%
704% o flag: right now, only the low order 3 bits are used.
705%
706% 1 => convert non-quoted tokens to upper case
707% 2 => convert non-quoted tokens to lower case
708% 0 => do not convert non-quoted tokens
709%
710% o token: a character string containing the returned next token
711%
712% o max_token_length: the maximum size of "token". Characters beyond
713% "max_token_length" are truncated.
714%
715% o string: the string to be parsed.
716%
717% o white: a string of the valid white spaces. example:
718%
719% char whitesp[]={" \t"};
720%
721% blank and tab will be valid white space.
722%
723% o break: a string of the valid break characters. example:
724%
725% char breakch[]={";,"};
726%
727% semicolon and comma will be valid break characters.
728%
729% o quote: a string of the valid quote characters. An example would be
730%
731% char whitesp[]={"'\"");
732%
733% (this causes single and double quotes to be valid) Note that a
734% token starting with one of these characters needs the same quote
735% character to terminate it.
736%
737% for example:
738%
739% "ABC '
740%
741% is unterminated, but
742%
743% "DEF" and 'GHI'
744%
745% are properly terminated. Note that different quote characters
746% can appear on the same line; only for a given token do the quote
747% characters have to be the same.
748%
749% o escape: the escape character (NOT a string ... only one
750% allowed). Use zero if none is desired.
751%
752% o breaker: the break character used to terminate the current
753% token. If the token was quoted, this will be the quote used. If
754% the token is the last one on the line, this will be zero.
755%
756% o next: this variable points to the first character of the
757% next token. it gets reset by "tokenizer" as it steps through the
758% string. Set it to 0 upon initialization, and leave it alone
759% after that. You can change it if you want to jump around in the
760% string or re-parse from the beginning, but be careful.
761%
762% o quoted: set to True if the token was quoted and MagickFalse
763% if not. You may need this information (for example: in C, a
764% string with quotes around it is a character string, while one
765% without is an identifier).
766%
767% o result: 0 if we haven't reached EOS (end of string), and 1
768% if we have.
769%
770*/
771
772#define IN_WHITE 0
773#define IN_TOKEN 1
774#define IN_QUOTE 2
775#define IN_OZONE 3
776
777static ssize_t sindex(int c,const char *string)
778{
779 const char
780 *p;
781
782 for (p=string; *p != '\0'; p++)
783 if (c == (int) (*p))
784 return((ssize_t) (p-string));
785 return(-1);
786}
787
788static void StoreToken(TokenInfo *token_info,char *string,
789 size_t max_token_length,int c)
790{
791 ssize_t
792 i;
793
794 if ((token_info->offset < 0) ||
795 ((size_t) token_info->offset >= (max_token_length-1)))
796 return;
797 i=token_info->offset++;
798 string[i]=(char) c;
799 if (token_info->state == IN_QUOTE)
800 return;
801 switch (token_info->flag & 0x03)
802 {
803 case 1:
804 {
805 string[i]=(char) LocaleToUppercase(c);
806 break;
807 }
808 case 2:
809 {
810 string[i]=(char) LocaleToLowercase(c);
811 break;
812 }
813 default:
814 break;
815 }
816}
817
818MagickExport int Tokenizer(TokenInfo *token_info,const unsigned flag,
819 char *token,const size_t max_token_length,const char *line,const char *white,
820 const char *break_set,const char *quote,const char escape,char *breaker,
821 int *next,char *quoted)
822{
823 int
824 c;
825
826 ssize_t
827 i;
828
829 *breaker='\0';
830 *quoted='\0';
831 if (line[*next] == '\0')
832 return(1);
833 token_info->state=IN_WHITE;
834 token_info->quote=(char) MagickFalse;
835 token_info->flag=flag;
836 for (token_info->offset=0; (int) line[*next] != 0; (*next)++)
837 {
838 c=(int) line[*next];
839 i=sindex(c,break_set);
840 if (i >= 0)
841 {
842 switch (token_info->state)
843 {
844 case IN_WHITE:
845 case IN_TOKEN:
846 case IN_OZONE:
847 {
848 (*next)++;
849 *breaker=break_set[i];
850 token[token_info->offset]='\0';
851 return(0);
852 }
853 case IN_QUOTE:
854 {
855 StoreToken(token_info,token,max_token_length,c);
856 break;
857 }
858 }
859 continue;
860 }
861 i=sindex(c,quote);
862 if (i >= 0)
863 {
864 switch (token_info->state)
865 {
866 case IN_WHITE:
867 {
868 token_info->state=IN_QUOTE;
869 token_info->quote=quote[i];
870 *quoted=(char) MagickTrue;
871 break;
872 }
873 case IN_QUOTE:
874 {
875 if (quote[i] != token_info->quote)
876 StoreToken(token_info,token,max_token_length,c);
877 else
878 {
879 token_info->state=IN_OZONE;
880 token_info->quote='\0';
881 }
882 break;
883 }
884 case IN_TOKEN:
885 case IN_OZONE:
886 {
887 *breaker=(char) c;
888 token[token_info->offset]='\0';
889 return(0);
890 }
891 }
892 continue;
893 }
894 i=sindex(c,white);
895 if (i >= 0)
896 {
897 switch (token_info->state)
898 {
899 case IN_WHITE:
900 case IN_OZONE:
901 break;
902 case IN_TOKEN:
903 {
904 token_info->state=IN_OZONE;
905 break;
906 }
907 case IN_QUOTE:
908 {
909 StoreToken(token_info,token,max_token_length,c);
910 break;
911 }
912 }
913 continue;
914 }
915 if (c == (int) escape)
916 {
917 if (line[(*next)+1] == '\0')
918 {
919 *breaker='\0';
920 StoreToken(token_info,token,max_token_length,c);
921 (*next)++;
922 token[token_info->offset]='\0';
923 return(0);
924 }
925 switch (token_info->state)
926 {
927 case IN_WHITE:
928 {
929 (*next)--;
930 token_info->state=IN_TOKEN;
931 break;
932 }
933 case IN_TOKEN:
934 case IN_QUOTE:
935 {
936 (*next)++;
937 c=(int) line[*next];
938 StoreToken(token_info,token,max_token_length,c);
939 break;
940 }
941 case IN_OZONE:
942 {
943 token[token_info->offset]='\0';
944 return(0);
945 }
946 }
947 continue;
948 }
949 switch (token_info->state)
950 {
951 case IN_WHITE:
952 {
953 token_info->state=IN_TOKEN;
954 StoreToken(token_info,token,max_token_length,c);
955 break;
956 }
957 case IN_TOKEN:
958 case IN_QUOTE:
959 {
960 StoreToken(token_info,token,max_token_length,c);
961 break;
962 }
963 case IN_OZONE:
964 {
965 token[token_info->offset]='\0';
966 return(0);
967 }
968 }
969 }
970 token[token_info->offset]='\0';
971 return(0);
972}