* editfns.c, systime.h (mktime_z) [!HAVE_TZALLOC]: Now static.

[gnu-emacs] / src / regex.c

diff --git a/src/regex.c b/src/regex.c
index 766ad26e709dbe43ad16126d219b1f583640a748..1afc5037594096ad0b1b8cdcda7158fb1dc48afe 100644 (file)
--- a/src/regex.c
+++ b/src/regex.c
@@ -2,7 +2,7 @@
    0.12.  (Implements POSIX draft P1003.2/D11.2, except for some of the
    internationalization features.)
 
    0.12.  (Implements POSIX draft P1003.2/D11.2, except for some of the
    internationalization features.)
 

-   Copyright (C) 1993-2014 Free Software Foundation, Inc.
+   Copyright (C) 1993-2015 Free Software Foundation, Inc.

 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by


@@ -324,12 +324,12 @@ enum syntaxcode { Swhitespace = 0, Sword = 1, Ssymbol = 2 };
                    ? (((c) >= 'a' && (c) <= 'z')       \
                       || ((c) >= 'A' && (c) <= 'Z')    \
                       || ((c) >= '0' && (c) <= '9'))   \
                    ? (((c) >= 'a' && (c) <= 'z')       \
                       || ((c) >= 'A' && (c) <= 'Z')    \
                       || ((c) >= '0' && (c) <= '9'))   \

-                   : SYNTAX (c) == Sword)
+                   : (alphabeticp (c) || decimalnump (c)))

 
 # define ISALPHA(c) (IS_REAL_ASCII (c)                 \
                    ? (((c) >= 'a' && (c) <= 'z')       \
                       || ((c) >= 'A' && (c) <= 'Z'))   \
 
 # define ISALPHA(c) (IS_REAL_ASCII (c)                 \
                    ? (((c) >= 'a' && (c) <= 'z')       \
                       || ((c) >= 'A' && (c) <= 'Z'))   \

-                   : SYNTAX (c) == Sword)
+                   : alphabeticp (c))

 
 # define ISLOWER(c) lowercasep (c)
 
 
 # define ISLOWER(c) lowercasep (c)
 


@@ -515,7 +515,7 @@ init_syntax_once (void)
 
 #define STREQ(s1, s2) ((strcmp (s1, s2) == 0))
 
 
 #define STREQ(s1, s2) ((strcmp (s1, s2) == 0))
 

-#ifndef emacs  
+#ifndef emacs

 # undef max
 # undef min
 # define max(a, b) ((a) > (b) ? (a) : (b))
 # undef max
 # undef min
 # define max(a, b) ((a) > (b) ? (a) : (b))


@@ -1632,7 +1632,7 @@ static boolean at_begline_loc_p (re_char *pattern, re_char *p,
 static boolean at_endline_loc_p (re_char *p, re_char *pend,
                                 reg_syntax_t syntax);
 static re_char *skip_one_char (re_char *p);
 static boolean at_endline_loc_p (re_char *p, re_char *pend,
                                 reg_syntax_t syntax);
 static re_char *skip_one_char (re_char *p);

-static int analyse_first (re_char *p, re_char *pend,
+static int analyze_first (re_char *p, re_char *pend,

                          char *fastmap, const int multibyte);
 
 /* Fetch the next character in the uncompiled pattern, with no
                          char *fastmap, const int multibyte);
 
 /* Fetch the next character in the uncompiled pattern, with no


@@ -1872,6 +1872,8 @@ struct range_table_work_area
 #define BIT_SPACE      0x8
 #define BIT_UPPER      0x10
 #define BIT_MULTIBYTE  0x20
 #define BIT_SPACE      0x8
 #define BIT_UPPER      0x10
 #define BIT_MULTIBYTE  0x20

+#define BIT_ALPHA      0x40
+#define BIT_ALNUM      0x80

 \f
 
 /* Set the bit for character C in a list.  */
 \f
 
 /* Set the bit for character C in a list.  */


@@ -2072,7 +2074,9 @@ re_wctype_to_bit (re_wctype_t cc)
     {
     case RECC_NONASCII: case RECC_PRINT: case RECC_GRAPH:
     case RECC_MULTIBYTE: return BIT_MULTIBYTE;
     {
     case RECC_NONASCII: case RECC_PRINT: case RECC_GRAPH:
     case RECC_MULTIBYTE: return BIT_MULTIBYTE;

-    case RECC_ALPHA: case RECC_ALNUM: case RECC_WORD: return BIT_WORD;
+    case RECC_ALPHA: return BIT_ALPHA;
+    case RECC_ALNUM: return BIT_ALNUM;
+    case RECC_WORD: return BIT_WORD;

     case RECC_LOWER: return BIT_LOWER;
     case RECC_UPPER: return BIT_UPPER;
     case RECC_PUNCT: return BIT_PUNCT;
     case RECC_LOWER: return BIT_LOWER;
     case RECC_UPPER: return BIT_UPPER;
     case RECC_PUNCT: return BIT_PUNCT;


@@ -2688,7 +2692,7 @@ regex_compile (const_re_char *pattern, size_t size, reg_syntax_t syntax,
                    size_t startoffset = 0;
                    re_opcode_t ofj =
                      /* Check if the loop can match the empty string.  */
                    size_t startoffset = 0;
                    re_opcode_t ofj =
                      /* Check if the loop can match the empty string.  */

-                     (simple || !analyse_first (laststart, b, NULL, 0))
+                     (simple || !analyze_first (laststart, b, NULL, 0))

                      ? on_failure_jump : on_failure_jump_loop;
                    assert (skip_one_char (laststart) <= b);
 
                      ? on_failure_jump : on_failure_jump_loop;
                    assert (skip_one_char (laststart) <= b);
 


@@ -2735,7 +2739,7 @@ regex_compile (const_re_char *pattern, size_t size, reg_syntax_t syntax,
                GET_BUFFER_SPACE (7); /* We might use less.  */
                if (many_times_ok)
                  {
                GET_BUFFER_SPACE (7); /* We might use less.  */
                if (many_times_ok)
                  {

-                   boolean emptyp = analyse_first (laststart, b, NULL, 0);
+                   boolean emptyp = analyze_first (laststart, b, NULL, 0);

 
                    /* The non-greedy multiple match looks like
                       a repeat..until: we only need a conditional jump
 
                    /* The non-greedy multiple match looks like
                       a repeat..until: we only need a conditional jump


@@ -2930,7 +2934,7 @@ regex_compile (const_re_char *pattern, size_t size, reg_syntax_t syntax,
 #endif /* emacs */
                        /* In most cases the matching rule for char classes
                           only uses the syntax table for multibyte chars,
 #endif /* emacs */
                        /* In most cases the matching rule for char classes
                           only uses the syntax table for multibyte chars,

-                          so that the content of the syntax-table it is not
+                          so that the content of the syntax-table is not

                           hardcoded in the range_table.  SPACE and WORD are
                           the two exceptions.  */
                        if ((1 << cc) & ((1 << RECC_SPACE) | (1 << RECC_WORD)))
                           hardcoded in the range_table.  SPACE and WORD are
                           the two exceptions.  */
                        if ((1 << cc) & ((1 << RECC_SPACE) | (1 << RECC_WORD)))


@@ -2945,7 +2949,7 @@ regex_compile (const_re_char *pattern, size_t size, reg_syntax_t syntax,
                        p = class_beg;
                        SET_LIST_BIT ('[');
 
                        p = class_beg;
                        SET_LIST_BIT ('[');
 

-                       /* Because the `:' may starts the range, we
+                       /* Because the `:' may start the range, we

                           can't simply set bit and repeat the loop.
                           Instead, just set it to C and handle below.  */
                        c = ':';
                           can't simply set bit and repeat the loop.
                           Instead, just set it to C and handle below.  */
                        c = ':';


@@ -3836,7 +3840,7 @@ group_in_compile_stack (compile_stack_type compile_stack, regnum_t regnum)
   return false;
 }
 \f
   return false;
 }
 \f

-/* analyse_first.
+/* analyze_first.

    If fastmap is non-NULL, go through the pattern and fill fastmap
    with all the possible leading chars.  If fastmap is NULL, don't
    bother filling it up (obviously) and only return whether the
    If fastmap is non-NULL, go through the pattern and fill fastmap
    with all the possible leading chars.  If fastmap is NULL, don't
    bother filling it up (obviously) and only return whether the


@@ -3847,7 +3851,7 @@ group_in_compile_stack (compile_stack_type compile_stack, regnum_t regnum)
    Return -1 if fastmap was not updated accurately.  */
 
 static int
    Return -1 if fastmap was not updated accurately.  */
 
 static int

-analyse_first (const_re_char *p, const_re_char *pend, char *fastmap,
+analyze_first (const_re_char *p, const_re_char *pend, char *fastmap,

               const int multibyte)
 {
   int j, k;
               const int multibyte)
 {
   int j, k;


@@ -4089,7 +4093,7 @@ analyse_first (const_re_char *p, const_re_char *pend, char *fastmap,
            { /* We have to look down both arms.
                 We first go down the "straight" path so as to minimize
                 stack usage when going through alternatives.  */
            { /* We have to look down both arms.
                 We first go down the "straight" path so as to minimize
                 stack usage when going through alternatives.  */

-             int r = analyse_first (p, pend, fastmap, multibyte);
+             int r = analyze_first (p, pend, fastmap, multibyte);

              if (r) return r;
              p += j;
            }
              if (r) return r;
              p += j;
            }


@@ -4139,7 +4143,7 @@ analyse_first (const_re_char *p, const_re_char *pend, char *fastmap,
   /* We reached the end without matching anything.  */
   return 1;
 
   /* We reached the end without matching anything.  */
   return 1;
 

-} /* analyse_first */
+} /* analyze_first */

 \f
 /* re_compile_fastmap computes a ``fastmap'' for the compiled pattern in
    BUFP.  A fastmap records which of the (1 << BYTEWIDTH) possible
 \f
 /* re_compile_fastmap computes a ``fastmap'' for the compiled pattern in
    BUFP.  A fastmap records which of the (1 << BYTEWIDTH) possible


@@ -4169,7 +4173,7 @@ re_compile_fastmap (struct re_pattern_buffer *bufp)
   memset (fastmap, 0, 1 << BYTEWIDTH);  /* Assume nothing's valid.  */
   bufp->fastmap_accurate = 1;      /* It will be when we're done.  */
 
   memset (fastmap, 0, 1 << BYTEWIDTH);  /* Assume nothing's valid.  */
   bufp->fastmap_accurate = 1;      /* It will be when we're done.  */
 

-  analysis = analyse_first (bufp->buffer, bufp->buffer + bufp->used,
+  analysis = analyze_first (bufp->buffer, bufp->buffer + bufp->used,

                            fastmap, RE_MULTIBYTE_P (bufp));
   bufp->can_be_null = (analysis != 0);
   return 0;
                            fastmap, RE_MULTIBYTE_P (bufp));
   bufp->can_be_null = (analysis != 0);
   return 0;


@@ -5513,7 +5517,9 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
                    | (class_bits & BIT_PUNCT && ISPUNCT (c))
                    | (class_bits & BIT_SPACE && ISSPACE (c))
                    | (class_bits & BIT_UPPER && ISUPPER (c))
                    | (class_bits & BIT_PUNCT && ISPUNCT (c))
                    | (class_bits & BIT_SPACE && ISSPACE (c))
                    | (class_bits & BIT_UPPER && ISUPPER (c))

-                   | (class_bits & BIT_WORD  && ISWORD (c)))
+                   | (class_bits & BIT_WORD  && ISWORD  (c))
+                   | (class_bits & BIT_ALPHA && ISALPHA (c))
+                   | (class_bits & BIT_ALNUM && ISALNUM (c)))

                  not = !not;
                else
                  CHARSET_LOOKUP_RANGE_TABLE_RAW (not, c, range_table, count);
                  not = !not;
                else
                  CHARSET_LOOKUP_RANGE_TABLE_RAW (not, c, range_table, count);