2 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
6 % TTTTT OOO K K EEEEE N N %
8 % T O O KKK EEE N N N %
10 % T OOO K K EEEEE N N %
13 % MagickCore Token Methods %
20 % Copyright 1999-2012 ImageMagick Studio LLC, a non-profit organization %
21 % dedicated to making software imaging solutions freely available. %
23 % You may not use this file except in compliance with the License. You may %
24 % obtain a copy of the License at %
26 % http://www.imagemagick.org/script/license.php %
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. %
34 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
43 #include "MagickCore/studio.h"
44 #include "MagickCore/exception.h"
45 #include "MagickCore/exception-private.h"
46 #include "MagickCore/image.h"
47 #include "MagickCore/memory_.h"
48 #include "MagickCore/string_.h"
49 #include "MagickCore/string-private.h"
50 #include "MagickCore/token.h"
51 #include "MagickCore/token-private.h"
52 #include "MagickCore/utility.h"
53 #include "MagickCore/utility-private.h"
56 Typedef declaractions.
77 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
81 % A c q u i r e T o k e n I n f o %
85 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
87 % AcquireTokenInfo() allocates the TokenInfo structure.
89 % The format of the AcquireTokenInfo method is:
91 % TokenInfo *AcquireTokenInfo()
94 MagickExport TokenInfo *AcquireTokenInfo(void)
99 token_info=(TokenInfo *) AcquireMagickMemory(sizeof(*token_info));
100 if (token_info == (TokenInfo *) NULL)
101 ThrowFatalException(ResourceLimitFatalError,"MemoryAllocationFailed");
102 token_info->signature=MagickSignature;
107 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
111 % D e s t r o y T o k e n I n f o %
115 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
117 % DestroyTokenInfo() deallocates memory associated with an TokenInfo
120 % The format of the DestroyTokenInfo method is:
122 % TokenInfo *DestroyTokenInfo(TokenInfo *token_info)
124 % A description of each parameter follows:
126 % o token_info: Specifies a pointer to an TokenInfo structure.
129 MagickExport TokenInfo *DestroyTokenInfo(TokenInfo *token_info)
131 (void) LogMagickEvent(TraceEvent,GetMagickModule(),"...");
132 assert(token_info != (TokenInfo *) NULL);
133 assert(token_info->signature == MagickSignature);
134 token_info->signature=(~MagickSignature);
135 token_info=(TokenInfo *) RelinquishMagickMemory(token_info);
140 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
144 + G e t M a g i c k T o k e n %
148 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
150 % GetMagickToken() gets a token from the token stream. A token is defined as
151 % a sequence of characters delimited by whitespace (e.g. clip-path), a
152 % sequence delimited with quotes (.e.g "Quote me"), or a sequence enclosed in
153 % parenthesis (e.g. rgb(0,0,0)). GetMagickToken() also recognizes these
154 % separator characters: ':', '=', ',', and ';'.
156 % The format of the GetMagickToken method is:
158 % void GetMagickToken(const char *start,const char **end,char *token)
160 % A description of each parameter follows:
162 % o start: the start of the token sequence.
164 % o end: point to the end of the token sequence.
166 % o token: copy the token to this buffer.
169 MagickExport void GetMagickToken(const char *start,const char **end,char *token)
180 assert(start != (const char *) NULL);
181 assert(token != (char *) NULL);
183 for (p=start; *p != '\0'; )
185 while ((isspace((int) ((unsigned char) *p)) != 0) && (*p != '\0'))
201 case '"': escape='"'; break;
202 case '\'': escape='\''; break;
203 case '`': escape='\''; break;
204 case '{': escape='}'; break;
205 default: escape=(*p); break;
207 for (p++; *p != '\0'; p++)
209 if ((*p == '\\') && ((*(p+1) == escape) || (*(p+1) == '\\')))
224 if ((*p == '>') || (*p == '/'))
233 value=StringToDouble(p,&q);
235 if ((p != q) && (*p != ','))
237 for ( ; (p < q) && (*p != ','); p++)
243 if ((*p != '\0') && (isalpha((int) ((unsigned char) *p)) == 0) &&
244 (*p != *DirectorySeparator) && (*p != '#') && (*p != '<'))
249 for ( ; *p != '\0'; p++)
251 if (((isspace((int) ((unsigned char) *p)) != 0) || (*p == '=') ||
252 (*p == ':') || (*p == ',') || (*p == '|') || (*p == ';')) &&
255 if ((i > 0) && (*p == '<'))
261 for (p++; *p != '\0'; p++)
264 if ((*p == ')') && (*(p-1) != '\\'))
274 if (LocaleNCompare(token,"url(",4) == 0)
280 if (token[offset] == '#')
282 i=(ssize_t) strlen(token);
283 (void) CopyMagickString(token,token+offset,MaxTextExtent);
284 token[i-offset-1]='\0';
286 while (isspace((int) ((unsigned char) *p)) != 0)
288 if (end != (const char **) NULL)
289 *end=(const char *) p;
293 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
297 % G l o b E x p r e s s i o n %
301 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
303 % GlobExpression() returns MagickTrue if the expression matches the pattern.
305 % The format of the GlobExpression function is:
307 % MagickBooleanType GlobExpression(const char *expression,
308 % const char *pattern,const MagickBooleanType case_insensitive)
310 % A description of each parameter follows:
312 % o expression: Specifies a pointer to a text string containing a file name.
314 % o pattern: Specifies a pointer to a text string containing a pattern.
316 % o case_insensitive: set to MagickTrue to ignore the case when matching
320 MagickExport MagickBooleanType GlobExpression(const char *expression,
321 const char *pattern,const MagickBooleanType case_insensitive)
331 Return on empty pattern or '*'.
333 if (pattern == (char *) NULL)
335 if (GetUTFCode(pattern) == 0)
337 if (LocaleCompare(pattern,"*") == 0)
339 p=pattern+strlen(pattern)-1;
340 if ((GetUTFCode(p) == ']') && (strchr(pattern,'[') != (char *) NULL))
349 Determine if pattern is a scene, i.e. img0001.pcd[2].
351 image_info=AcquireImageInfo();
352 (void) CopyMagickString(image_info->filename,pattern,MaxTextExtent);
353 exception=AcquireExceptionInfo();
354 (void) SetImageInfo(image_info,0,exception);
355 exception=DestroyExceptionInfo(exception);
356 if (LocaleCompare(image_info->filename,pattern) != 0)
358 image_info=DestroyImageInfo(image_info);
361 image_info=DestroyImageInfo(image_info);
364 Evaluate glob expression.
367 while ((GetUTFCode(pattern) != 0) && (done == MagickFalse))
369 if (GetUTFCode(expression) == 0)
370 if ((GetUTFCode(pattern) != '{') && (GetUTFCode(pattern) != '*'))
372 switch (GetUTFCode(pattern))
380 pattern+=GetUTFOctets(pattern);
381 while ((GetUTFCode(expression) != 0) && (status == MagickFalse))
383 status=GlobExpression(expression,pattern,case_insensitive);
384 expression+=GetUTFOctets(expression);
386 if (status != MagickFalse)
388 while (GetUTFCode(expression) != 0)
389 expression+=GetUTFOctets(expression);
390 while (GetUTFCode(pattern) != 0)
391 pattern+=GetUTFOctets(pattern);
400 pattern+=GetUTFOctets(pattern);
403 if ((GetUTFCode(pattern) == 0) || (GetUTFCode(pattern) == ']'))
408 if (GetUTFCode(pattern) == '\\')
410 pattern+=GetUTFOctets(pattern);
411 if (GetUTFCode(pattern) == 0)
417 if (GetUTFCode(pattern+GetUTFOctets(pattern)) == '-')
419 c=GetUTFCode(pattern);
420 pattern+=GetUTFOctets(pattern);
421 pattern+=GetUTFOctets(pattern);
422 if (GetUTFCode(pattern) == ']')
427 if (GetUTFCode(pattern) == '\\')
429 pattern+=GetUTFOctets(pattern);
430 if (GetUTFCode(pattern) == 0)
436 if ((GetUTFCode(expression) < c) ||
437 (GetUTFCode(expression) > GetUTFCode(pattern)))
439 pattern+=GetUTFOctets(pattern);
444 if (GetUTFCode(pattern) != GetUTFCode(expression))
446 pattern+=GetUTFOctets(pattern);
449 pattern+=GetUTFOctets(pattern);
450 while ((GetUTFCode(pattern) != ']') && (GetUTFCode(pattern) != 0))
452 if ((GetUTFCode(pattern) == '\\') &&
453 (GetUTFCode(pattern+GetUTFOctets(pattern)) > 0))
454 pattern+=GetUTFOctets(pattern);
455 pattern+=GetUTFOctets(pattern);
457 if (GetUTFCode(pattern) != 0)
459 pattern+=GetUTFOctets(pattern);
460 expression+=GetUTFOctets(expression);
468 pattern+=GetUTFOctets(pattern);
469 expression+=GetUTFOctets(expression);
477 pattern+=GetUTFOctets(pattern);
478 while ((GetUTFCode(pattern) != '}') && (GetUTFCode(pattern) != 0))
482 while ((GetUTFCode(p) != 0) && (GetUTFCode(pattern) != 0) &&
483 (GetUTFCode(pattern) != ',') && (GetUTFCode(pattern) != '}') &&
484 (match != MagickFalse))
486 if (GetUTFCode(pattern) == '\\')
487 pattern+=GetUTFOctets(pattern);
488 match=(GetUTFCode(pattern) == GetUTFCode(p)) ? MagickTrue :
491 pattern+=GetUTFOctets(pattern);
493 if (GetUTFCode(pattern) == 0)
500 if (match != MagickFalse)
503 while ((GetUTFCode(pattern) != '}') &&
504 (GetUTFCode(pattern) != 0))
506 pattern+=GetUTFOctets(pattern);
507 if (GetUTFCode(pattern) == '\\')
509 pattern+=GetUTFOctets(pattern);
510 if (GetUTFCode(pattern) == '}')
511 pattern+=GetUTFOctets(pattern);
517 while ((GetUTFCode(pattern) != '}') &&
518 (GetUTFCode(pattern) != ',') &&
519 (GetUTFCode(pattern) != 0))
521 pattern+=GetUTFOctets(pattern);
522 if (GetUTFCode(pattern) == '\\')
524 pattern+=GetUTFOctets(pattern);
525 if ((GetUTFCode(pattern) == '}') ||
526 (GetUTFCode(pattern) == ','))
527 pattern+=GetUTFOctets(pattern);
531 if (GetUTFCode(pattern) != 0)
532 pattern+=GetUTFOctets(pattern);
538 pattern+=GetUTFOctets(pattern);
539 if (GetUTFCode(pattern) == 0)
544 if (case_insensitive != MagickFalse)
546 if (tolower((int) GetUTFCode(expression)) !=
547 tolower((int) GetUTFCode(pattern)))
554 if (GetUTFCode(expression) != GetUTFCode(pattern))
559 expression+=GetUTFOctets(expression);
560 pattern+=GetUTFOctets(pattern);
564 while (GetUTFCode(pattern) == '*')
565 pattern+=GetUTFOctets(pattern);
566 match=(GetUTFCode(expression) == 0) && (GetUTFCode(pattern) == 0) ?
567 MagickTrue : MagickFalse;
572 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
580 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
582 % IsGlob() returns MagickTrue if the path specification contains a globbing
585 % The format of the IsGlob method is:
587 % MagickBooleanType IsGlob(const char *geometry)
589 % A description of each parameter follows:
594 MagickPrivate MagickBooleanType IsGlob(const char *path)
597 status = MagickFalse;
602 if (IsPathAccessible(path) != MagickFalse)
604 for (p=path; *p != '\0'; p++)
626 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
630 % T o k e n i z e r %
634 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
636 % Tokenizer() is a generalized, finite state token parser. It extracts tokens
637 % one at a time from a string of characters. The characters used for white
638 % space, for break characters, and for quotes can be specified. Also,
639 % characters in the string can be preceded by a specifiable escape character
640 % which removes any special meaning the character may have.
642 % Here is some terminology:
644 % o token: A single unit of information in the form of a group of
647 % o white space: Apace that gets ignored (except within quotes or when
648 % escaped), like blanks and tabs. in addition, white space terminates a
651 % o break set: One or more characters that separates non-quoted tokens.
652 % Commas are a common break character. The usage of break characters to
653 % signal the end of a token is the same as that of white space, except
654 % multiple break characters with nothing or only white space between
655 % generate a null token for each two break characters together.
657 % For example, if blank is set to be the white space and comma is set to
658 % be the break character, the line
662 % ... consists of 5 tokens:
667 % 4) "" (the null string)
670 % o Quote character: A character that, when surrounding a group of other
671 % characters, causes the group of characters to be treated as a single
672 % token, no matter how many white spaces or break characters exist in
673 % the group. Also, a token always terminates after the closing quote.
674 % For example, if ' is the quote character, blank is white space, and
675 % comma is the break character, the following string
679 % ... consists of 4 tokens:
682 % 2) " B, CD" (note the blanks & comma)
686 % The quote characters themselves do not appear in the resultant
687 % tokens. The double quotes are delimiters i use here for
688 % documentation purposes only.
690 % o Escape character: A character which itself is ignored but which
691 % causes the next character to be used as is. ^ and \ are often used
692 % as escape characters. An escape in the last position of the string
693 % gets treated as a "normal" (i.e., non-quote, non-white, non-break,
694 % and non-escape) character. For example, assume white space, break
695 % character, and quote are the same as in the above examples, and
696 % further, assume that ^ is the escape character. Then, in the string
698 % ABC, ' DEF ^' GH' I ^ J K^ L ^
700 % ... there are 7 tokens:
705 % 4) " " (a lone blank)
708 % 7) "^" (passed as is at end of line)
710 % The format of the Tokenizer method is:
712 % int Tokenizer(TokenInfo *token_info,const unsigned flag,char *token,
713 % const size_t max_token_length,const char *line,const char *white,
714 % const char *break_set,const char *quote,const char escape,
715 % char *breaker,int *next,char *quoted)
717 % A description of each parameter follows:
719 % o flag: right now, only the low order 3 bits are used.
721 % 1 => convert non-quoted tokens to upper case
722 % 2 => convert non-quoted tokens to lower case
723 % 0 => do not convert non-quoted tokens
725 % o token: a character string containing the returned next token
727 % o max_token_length: the maximum size of "token". Characters beyond
728 % "max_token_length" are truncated.
730 % o string: the string to be parsed.
732 % o white: a string of the valid white spaces. example:
734 % char whitesp[]={" \t"};
736 % blank and tab will be valid white space.
738 % o break: a string of the valid break characters. example:
740 % char breakch[]={";,"};
742 % semicolon and comma will be valid break characters.
744 % o quote: a string of the valid quote characters. An example would be
746 % char whitesp[]={"'\"");
748 % (this causes single and double quotes to be valid) Note that a
749 % token starting with one of these characters needs the same quote
750 % character to terminate it.
756 % is unterminated, but
760 % are properly terminated. Note that different quote characters
761 % can appear on the same line; only for a given token do the quote
762 % characters have to be the same.
764 % o escape: the escape character (NOT a string ... only one
765 % allowed). Use zero if none is desired.
767 % o breaker: the break character used to terminate the current
768 % token. If the token was quoted, this will be the quote used. If
769 % the token is the last one on the line, this will be zero.
771 % o next: this variable points to the first character of the
772 % next token. it gets reset by "tokenizer" as it steps through the
773 % string. Set it to 0 upon initialization, and leave it alone
774 % after that. You can change it if you want to jump around in the
775 % string or re-parse from the beginning, but be careful.
777 % o quoted: set to True if the token was quoted and MagickFalse
778 % if not. You may need this information (for example: in C, a
779 % string with quotes around it is a character string, while one
780 % without is an identifier).
782 % o result: 0 if we haven't reached EOS (end of string), and 1
792 static ssize_t sindex(int c,const char *string)
797 for (p=string; *p != '\0'; p++)
799 return((ssize_t) (p-string));
803 static void StoreToken(TokenInfo *token_info,char *string,
804 size_t max_token_length,int c)
809 if ((token_info->offset < 0) ||
810 ((size_t) token_info->offset >= (max_token_length-1)))
812 i=token_info->offset++;
814 if (token_info->state == IN_QUOTE)
816 switch (token_info->flag & 0x03)
820 string[i]=(char) toupper(c);
825 string[i]=(char) tolower(c);
833 MagickExport int Tokenizer(TokenInfo *token_info,const unsigned flag,
834 char *token,const size_t max_token_length,const char *line,const char *white,
835 const char *break_set,const char *quote,const char escape,char *breaker,
836 int *next,char *quoted)
846 if (line[*next] == '\0')
848 token_info->state=IN_WHITE;
849 token_info->quote=(char) MagickFalse;
850 token_info->flag=flag;
851 for (token_info->offset=0; (int) line[*next] != 0; (*next)++)
854 i=sindex(c,break_set);
857 switch (token_info->state)
864 *breaker=break_set[i];
865 token[token_info->offset]='\0';
870 StoreToken(token_info,token,max_token_length,c);
879 switch (token_info->state)
883 token_info->state=IN_QUOTE;
884 token_info->quote=quote[i];
885 *quoted=(char) MagickTrue;
890 if (quote[i] != token_info->quote)
891 StoreToken(token_info,token,max_token_length,c);
894 token_info->state=IN_OZONE;
895 token_info->quote='\0';
903 token[token_info->offset]='\0';
912 switch (token_info->state)
919 token_info->state=IN_OZONE;
924 StoreToken(token_info,token,max_token_length,c);
930 if (c == (int) escape)
932 if (line[(*next)+1] == '\0')
935 StoreToken(token_info,token,max_token_length,c);
937 token[token_info->offset]='\0';
940 switch (token_info->state)
945 token_info->state=IN_TOKEN;
953 StoreToken(token_info,token,max_token_length,c);
958 token[token_info->offset]='\0';
964 switch (token_info->state)
967 token_info->state=IN_TOKEN;
971 StoreToken(token_info,token,max_token_length,c);
976 token[token_info->offset]='\0';
981 token[token_info->offset]='\0';