Mxx_ru 1.1.0

data/tests/c/pcre/pcre.h

@@ -0,0 +1,193 @@
+/*************************************************
+*       Perl-Compatible Regular Expressions      *
+*************************************************/
+
+/* Copyright (c) 1997-2003 University of Cambridge */
+
+#ifndef _PCRE_H
+#define _PCRE_H
+
+/* The file pcre.h is build by "configure". Do not edit it; instead
+make changes to pcre.in. */
+
+#define PCRE_MAJOR          @PCRE_MAJOR@
+#define PCRE_MINOR          @PCRE_MINOR@
+#define PCRE_DATE           @PCRE_DATE@
+
+/* Win32 uses DLL by default */
+
+#ifdef _WIN32
+#  ifdef PCRE_DEFINITION
+#    ifdef DLL_EXPORT
+#      define PCRE_DATA_SCOPE __declspec(dllexport)
+#    endif
+#  else
+#    ifndef PCRE_STATIC
+#      define PCRE_DATA_SCOPE extern __declspec(dllimport)
+#    endif
+#  endif
+#endif
+#ifndef PCRE_DATA_SCOPE
+#  define PCRE_DATA_SCOPE     extern
+#endif
+
+/* Have to include stdlib.h in order to ensure that size_t is defined;
+it is needed here for malloc. */
+
+#include <stdlib.h>
+
+/* Allow for C++ users */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Options */
+
+#define PCRE_CASELESS           0x0001
+#define PCRE_MULTILINE          0x0002
+#define PCRE_DOTALL             0x0004
+#define PCRE_EXTENDED           0x0008
+#define PCRE_ANCHORED           0x0010
+#define PCRE_DOLLAR_ENDONLY     0x0020
+#define PCRE_EXTRA              0x0040
+#define PCRE_NOTBOL             0x0080
+#define PCRE_NOTEOL             0x0100
+#define PCRE_UNGREEDY           0x0200
+#define PCRE_NOTEMPTY           0x0400
+#define PCRE_UTF8               0x0800
+#define PCRE_NO_AUTO_CAPTURE    0x1000
+#define PCRE_NO_UTF8_CHECK      0x2000
+
+/* Exec-time and get/set-time error codes */
+
+#define PCRE_ERROR_NOMATCH         (-1)
+#define PCRE_ERROR_NULL            (-2)
+#define PCRE_ERROR_BADOPTION       (-3)
+#define PCRE_ERROR_BADMAGIC        (-4)
+#define PCRE_ERROR_UNKNOWN_NODE    (-5)
+#define PCRE_ERROR_NOMEMORY        (-6)
+#define PCRE_ERROR_NOSUBSTRING     (-7)
+#define PCRE_ERROR_MATCHLIMIT      (-8)
+#define PCRE_ERROR_CALLOUT         (-9)  /* Never used by PCRE itself */
+#define PCRE_ERROR_BADUTF8        (-10)
+#define PCRE_ERROR_BADUTF8_OFFSET (-11)
+
+/* Request types for pcre_fullinfo() */
+
+#define PCRE_INFO_OPTIONS            0
+#define PCRE_INFO_SIZE               1
+#define PCRE_INFO_CAPTURECOUNT       2
+#define PCRE_INFO_BACKREFMAX         3
+#define PCRE_INFO_FIRSTBYTE          4
+#define PCRE_INFO_FIRSTCHAR          4  /* For backwards compatibility */
+#define PCRE_INFO_FIRSTTABLE         5
+#define PCRE_INFO_LASTLITERAL        6
+#define PCRE_INFO_NAMEENTRYSIZE      7
+#define PCRE_INFO_NAMECOUNT          8
+#define PCRE_INFO_NAMETABLE          9
+#define PCRE_INFO_STUDYSIZE         10
+
+/* Request types for pcre_config() */
+
+#define PCRE_CONFIG_UTF8                    0
+#define PCRE_CONFIG_NEWLINE                 1
+#define PCRE_CONFIG_LINK_SIZE               2
+#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD  3
+#define PCRE_CONFIG_MATCH_LIMIT             4
+#define PCRE_CONFIG_STACKRECURSE            5
+
+/* Bit flags for the pcre_extra structure */
+
+#define PCRE_EXTRA_STUDY_DATA          0x0001
+#define PCRE_EXTRA_MATCH_LIMIT         0x0002
+#define PCRE_EXTRA_CALLOUT_DATA        0x0004
+
+/* Types */
+
+struct real_pcre;                 /* declaration; the definition is private  */
+typedef struct real_pcre pcre;
+
+/* The structure for passing additional data to pcre_exec(). This is defined in
+such as way as to be extensible. */
+
+typedef struct pcre_extra {
+  unsigned long int flags;        /* Bits for which fields are set */
+  void *study_data;               /* Opaque data from pcre_study() */
+  unsigned long int match_limit;  /* Maximum number of calls to match() */
+  void *callout_data;             /* Data passed back in callouts */
+} pcre_extra;
+
+/* The structure for passing out data via the pcre_callout_function. We use a
+structure so that new fields can be added on the end in future versions,
+without changing the API of the function, thereby allowing old clients to work
+without modification. */
+
+typedef struct pcre_callout_block {
+  int          version;           /* Identifies version of block */
+  /* ------------------------ Version 0 ------------------------------- */
+  int          callout_number;    /* Number compiled into pattern */
+  int         *offset_vector;     /* The offset vector */
+  const char  *subject;           /* The subject being matched */
+  int          subject_length;    /* The length of the subject */
+  int          start_match;       /* Offset to start of this match attempt */
+  int          current_position;  /* Where we currently are */
+  int          capture_top;       /* Max current capture */
+  int          capture_last;      /* Most recently closed capture */
+  void        *callout_data;      /* Data passed in with the call */
+  /* ------------------------------------------------------------------ */
+} pcre_callout_block;
+
+/* Indirection for store get and free functions. These can be set to
+alternative malloc/free functions if required. Special ones are used in the
+non-recursive case for "frames". There is also an optional callout function
+that is triggered by the (?) regex item. Some magic is required for Win32 DLL;
+it is null on other OS. For Virtual Pascal, these have to be different again.
+*/
+
+#ifndef VPCOMPAT
+PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t);
+PCRE_DATA_SCOPE void  (*pcre_free)(void *);
+PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t);
+PCRE_DATA_SCOPE void  (*pcre_stack_free)(void *);
+PCRE_DATA_SCOPE int   (*pcre_callout)(pcre_callout_block *);
+#else   /* VPCOMPAT */
+extern void *pcre_malloc(size_t);
+extern void  pcre_free(void *);
+extern void *pcre_stack_malloc(size_t);
+extern void  pcre_stack_free(void *);
+extern int   pcre_callout(pcre_callout_block *);
+#endif  /* VPCOMPAT */
+
+/* Exported PCRE functions */
+
+extern pcre *pcre_compile(const char *, int, const char **,
+              int *, const unsigned char *);
+extern int  pcre_config(int, void *);
+extern int  pcre_copy_named_substring(const pcre *, const char *,
+              int *, int, const char *, char *, int);
+extern int  pcre_copy_substring(const char *, int *, int, int,
+              char *, int);
+extern int  pcre_exec(const pcre *, const pcre_extra *,
+              const char *, int, int, int, int *, int);
+extern void pcre_free_substring(const char *);
+extern void pcre_free_substring_list(const char **);
+extern int  pcre_fullinfo(const pcre *, const pcre_extra *, int,
+              void *);
+extern int  pcre_get_named_substring(const pcre *, const char *,
+              int *, int,  const char *, const char **);
+extern int  pcre_get_stringnumber(const pcre *, const char *);
+extern int  pcre_get_substring(const char *, int *, int, int,
+              const char **);
+extern int  pcre_get_substring_list(const char *, int *, int,
+              const char ***);
+extern int  pcre_info(const pcre *, int *, int *);
+extern const unsigned char *pcre_maketables(void);
+extern pcre_extra *pcre_study(const pcre *, int, const char **);
+extern const char *pcre_version(void);
+
+#ifdef __cplusplus
+}  /* extern "C" */
+#endif
+
+#endif /* End of pcre.h */

data/tests/c/pcre/pcre.rb

@@ -0,0 +1,14 @@
+require	'mxx_ru/cpp'
+
+Mxx_ru::setup_target(
+	Mxx_ru::Cpp::Lib_target.new( "pcre.rb" ) {
+		target( "lib/pcre.4.5" )
+
+		define( "PCRE_STATIC", Mxx_ru::Cpp::Target::OPT_UPSPREAD )
+
+		c_source( "get.c" )
+		c_source( "maketables.c" )
+		c_source( "pcre.c" )
+		c_source( "study.c" )
+	}
+)

data/tests/c/pcre/pcredemo.c

@@ -0,0 +1,316 @@
+/*************************************************
+*           PCRE DEMONSTRATION PROGRAM           *
+*************************************************/
+
+/* This is a demonstration program to illustrate the most straightforward ways
+of calling the PCRE regular expression library from a C program. See the
+pcresample documentation for a short discussion.
+
+Compile thuswise:
+  gcc -Wall pcredemo.c -I/opt/local/include -L/opt/local/lib \
+    -R/opt/local/lib -lpcre
+
+Replace "/opt/local/include" and "/opt/local/lib" with wherever the include and
+library files for PCRE are installed on your system. Only some operating
+systems (e.g. Solaris) use the -R option.
+*/
+
+
+#include <stdio.h>
+#include <string.h>
+#include <pcre.h>
+
+#define OVECCOUNT 30    /* should be a multiple of 3 */
+
+
+int main(int argc, char **argv)
+{
+pcre *re;
+const char *error;
+char *pattern;
+char *subject;
+unsigned char *name_table;
+int erroffset;
+int find_all;
+int namecount;
+int name_entry_size;
+int ovector[OVECCOUNT];
+int subject_length;
+int rc, i;
+
+
+/*************************************************************************
+* First, sort out the command line. There is only one possible option at *
+* the moment, "-g" to request repeated matching to find all occurrences, *
+* like Perl's /g option. We set the variable find_all non-zero if it is  *
+* present. Apart from that, there must be exactly two arguments.         *
+*************************************************************************/
+
+find_all = 0;
+for (i = 1; i < argc; i++)
+  {
+  if (strcmp(argv[i], "-g") == 0) find_all = 1;
+    else break;
+  }
+
+/* After the options, we require exactly two arguments, which are the pattern,
+and the subject string. */
+
+if (argc - i != 2)
+  {
+  printf("Two arguments required: a regex and a subject string\n");
+  return 1;
+  }
+
+pattern = argv[i];
+subject = argv[i+1];
+subject_length = (int)strlen(subject);
+
+
+/*************************************************************************
+* Now we are going to compile the regular expression pattern, and handle *
+* and errors that are detected.                                          *
+*************************************************************************/
+
+re = pcre_compile(
+  pattern,              /* the pattern */
+  0,                    /* default options */
+  &error,               /* for error message */
+  &erroffset,           /* for error offset */
+  NULL);                /* use default character tables */
+
+/* Compilation failed: print the error message and exit */
+
+if (re == NULL)
+  {
+  printf("PCRE compilation failed at offset %d: %s\n", erroffset, error);
+  return 1;
+  }
+
+
+/*************************************************************************
+* If the compilation succeeded, we call PCRE again, in order to do a     *
+* pattern match against the subject string. This just does ONE match. If *
+* further matching is needed, it will be done below.                     *
+*************************************************************************/
+
+rc = pcre_exec(
+  re,                   /* the compiled pattern */
+  NULL,                 /* no extra data - we didn't study the pattern */
+  subject,              /* the subject string */
+  subject_length,       /* the length of the subject */
+  0,                    /* start at offset 0 in the subject */
+  0,                    /* default options */
+  ovector,              /* output vector for substring information */
+  OVECCOUNT);           /* number of elements in the output vector */
+
+/* Matching failed: handle error cases */
+
+if (rc < 0)
+  {
+  switch(rc)
+    {
+    case PCRE_ERROR_NOMATCH: printf("No match\n"); break;
+    /*
+    Handle other special cases if you like
+    */
+    default: printf("Matching error %d\n", rc); break;
+    }
+  return 1;
+  }
+
+/* Match succeded */
+
+printf("\nMatch succeeded at offset %d\n", ovector[0]);
+
+
+/*************************************************************************
+* We have found the first match within the subject string. If the output *
+* vector wasn't big enough, set its size to the maximum. Then output any *
+* substrings that were captured.                                         *
+*************************************************************************/
+
+/* The output vector wasn't big enough */
+
+if (rc == 0)
+  {
+  rc = OVECCOUNT/3;
+  printf("ovector only has room for %d captured substrings\n", rc - 1);
+  }
+
+/* Show substrings stored in the output vector by number. Obviously, in a real
+application you might want to do things other than print them. */
+
+for (i = 0; i < rc; i++)
+  {
+  char *substring_start = subject + ovector[2*i];
+  int substring_length = ovector[2*i+1] - ovector[2*i];
+  printf("%2d: %.*s\n", i, substring_length, substring_start);
+  }
+
+
+/*************************************************************************
+* That concludes the basic part of this demonstration program. We have   *
+* compiled a pattern, and performed a single match. The code that follows*
+* first shows how to access named substrings, and then how to code for   *
+* repeated matches on the same subject.                                  *
+*************************************************************************/
+
+/* See if there are any named substrings, and if so, show them by name. First
+we have to extract the count of named parentheses from the pattern. */
+
+(void)pcre_fullinfo(
+  re,                   /* the compiled pattern */
+  NULL,                 /* no extra data - we didn't study the pattern */
+  PCRE_INFO_NAMECOUNT,  /* number of named substrings */
+  &namecount);          /* where to put the answer */
+
+if (namecount <= 0) printf("No named substrings\n"); else
+  {
+  unsigned char *tabptr;
+  printf("Named substrings\n");
+
+  /* Before we can access the substrings, we must extract the table for
+  translating names to numbers, and the size of each entry in the table. */
+
+  (void)pcre_fullinfo(
+    re,                       /* the compiled pattern */
+    NULL,                     /* no extra data - we didn't study the pattern */
+    PCRE_INFO_NAMETABLE,      /* address of the table */
+    &name_table);             /* where to put the answer */
+
+  (void)pcre_fullinfo(
+    re,                       /* the compiled pattern */
+    NULL,                     /* no extra data - we didn't study the pattern */
+    PCRE_INFO_NAMEENTRYSIZE,  /* size of each entry in the table */
+    &name_entry_size);        /* where to put the answer */
+
+  /* Now we can scan the table and, for each entry, print the number, the name,
+  and the substring itself. */
+
+  tabptr = name_table;
+  for (i = 0; i < namecount; i++)
+    {
+    int n = (tabptr[0] << 8) | tabptr[1];
+    printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+      ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
+    tabptr += name_entry_size;
+    }
+  }
+
+
+/*************************************************************************
+* If the "-g" option was given on the command line, we want to continue  *
+* to search for additional matches in the subject string, in a similar   *
+* way to the /g option in Perl. This turns out to be trickier than you   *
+* might think because of the possibility of matching an empty string.    *
+* What happens is as follows:                                            *
+*                                                                        *
+* If the previous match was NOT for an empty string, we can just start   *
+* the next match at the end of the previous one.                         *
+*                                                                        *
+* If the previous match WAS for an empty string, we can't do that, as it *
+* would lead to an infinite loop. Instead, a special call of pcre_exec() *
+* is made with the PCRE_NOTEMPTY and PCRE_ANCHORED flags set. The first  *
+* of these tells PCRE that an empty string is not a valid match; other   *
+* possibilities must be tried. The second flag restricts PCRE to one     *
+* match attempt at the initial string position. If this match succeeds,  *
+* an alternative to the empty string match has been found, and we can    *
+* proceed round the loop.                                                *
+*************************************************************************/
+
+if (!find_all) return 0;   /* Finish unless -g was given */
+
+/* Loop for second and subsequent matches */
+
+for (;;)
+  {
+  int options = 0;                 /* Normally no options */
+  int start_offset = ovector[1];   /* Start at end of previous match */
+
+  /* If the previous match was for an empty string, we are finished if we are
+  at the end of the subject. Otherwise, arrange to run another match at the
+  same point to see if a non-empty match can be found. */
+
+  if (ovector[0] == ovector[1])
+    {
+    if (ovector[0] == subject_length) break;
+    options = PCRE_NOTEMPTY | PCRE_ANCHORED;
+    }
+
+  /* Run the next matching operation */
+
+  rc = pcre_exec(
+    re,                   /* the compiled pattern */
+    NULL,                 /* no extra data - we didn't study the pattern */
+    subject,              /* the subject string */
+    subject_length,       /* the length of the subject */
+    start_offset,         /* starting offset in the subject */
+    options,              /* options */
+    ovector,              /* output vector for substring information */
+    OVECCOUNT);           /* number of elements in the output vector */
+
+  /* This time, a result of NOMATCH isn't an error. If the value in "options"
+  is zero, it just means we have found all possible matches, so the loop ends.
+  Otherwise, it means we have failed to find a non-empty-string match at a
+  point where there was a previous empty-string match. In this case, we do what
+  Perl does: advance the matching position by one, and continue. We do this by
+  setting the "end of previous match" offset, because that is picked up at the
+  top of the loop as the point at which to start again. */
+
+  if (rc == PCRE_ERROR_NOMATCH)
+    {
+    if (options == 0) break;
+    ovector[1] = start_offset + 1;
+    continue;    /* Go round the loop again */
+    }
+
+  /* Other matching errors are not recoverable. */
+
+  if (rc < 0)
+    {
+    printf("Matching error %d\n", rc);
+    return 1;
+    }
+
+  /* Match succeded */
+
+  printf("\nMatch succeeded again at offset %d\n", ovector[0]);
+
+  /* The match succeeded, but the output vector wasn't big enough. */
+
+  if (rc == 0)
+    {
+    rc = OVECCOUNT/3;
+    printf("ovector only has room for %d captured substrings\n", rc - 1);
+    }
+
+  /* As before, show substrings stored in the output vector by number, and then
+  also any named substrings. */
+
+  for (i = 0; i < rc; i++)
+    {
+    char *substring_start = subject + ovector[2*i];
+    int substring_length = ovector[2*i+1] - ovector[2*i];
+    printf("%2d: %.*s\n", i, substring_length, substring_start);
+    }
+
+  if (namecount <= 0) printf("No named substrings\n"); else
+    {
+    unsigned char *tabptr = name_table;
+    printf("Named substrings\n");
+    for (i = 0; i < namecount; i++)
+      {
+      int n = (tabptr[0] << 8) | tabptr[1];
+      printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+        ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
+      tabptr += name_entry_size;
+      }
+    }
+  }      /* End of loop to find second and subsequent matches */
+
+printf("\n");
+return 0;
+}
+
+/* End of pcredemo.c */