Document 'help-go-forward'

[gnu-emacs] / src / regex.c

diff --git a/src/regex.c b/src/regex.c
index 1afc5037594096ad0b1b8cdcda7158fb1dc48afe..164eb4612ae01cb901caa6664b39b35a4fcaea4d 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.)
 
-   Copyright (C) 1993-2015 Free Software Foundation, Inc.
+   Copyright (C) 1993-2016 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
@@ -313,12 +313,12 @@ enum syntaxcode { Swhitespace = 0, Sword = 1, Ssymbol = 2 };
 /* The rest must handle multibyte characters.  */
 
 # define ISGRAPH(c) (SINGLE_BYTE_CHAR_P (c)                            \
-                   ? (c) > ' ' && !((c) >= 0177 && (c) <= 0237)        \
-                   : 1)
+                    ? (c) > ' ' && !((c) >= 0177 && (c) <= 0240)       \
+                    : graphicp (c))
 
 # define ISPRINT(c) (SINGLE_BYTE_CHAR_P (c)                            \
                    ? (c) >= ' ' && !((c) >= 0177 && (c) <= 0237)       \
-                   : 1)
+                    : printablep (c))
 
 # define ISALNUM(c) (IS_REAL_ASCII (c)                 \
                    ? (((c) >= 'a' && (c) <= 'z')       \
@@ -1544,9 +1544,9 @@ do {                                                                      \
   DEBUG_PRINT ("  Push frame index: %zd\n", fail_stack.frame);         \
   PUSH_FAILURE_INT (fail_stack.frame);                                 \
                                                                        \
-  DEBUG_PRINT ("  Push string %p: `", string_place);                   \
+  DEBUG_PRINT ("  Push string %p: \"", string_place);                  \
   DEBUG_PRINT_DOUBLE_STRING (string_place, string1, size1, string2, size2);\
-  DEBUG_PRINT ("'\n");                                                 \
+  DEBUG_PRINT ("\"\n");                                                        \
   PUSH_FAILURE_POINTER (string_place);                                 \
                                                                        \
   DEBUG_PRINT ("  Push pattern %p: ", pattern);                                \
@@ -1598,9 +1598,9 @@ do {                                                                      \
      on_failure_keep_string_jump opcode, and we want to throw away the \
      saved NULL, thus retaining our current position in the string.  */        \
   str = POP_FAILURE_POINTER ();                                                \
-  DEBUG_PRINT ("  Popping string %p: `", str);                         \
+  DEBUG_PRINT ("  Popping string %p: \"", str);                                \
   DEBUG_PRINT_DOUBLE_STRING (str, string1, size1, string2, size2);     \
-  DEBUG_PRINT ("'\n");                                                 \
+  DEBUG_PRINT ("\"\n");                                                        \
                                                                        \
   fail_stack.frame = POP_FAILURE_INT ();                               \
   DEBUG_PRINT ("  Popping  frame index: %zd\n", fail_stack.frame);     \
@@ -1865,7 +1865,8 @@ struct range_table_work_area
 #define RANGE_TABLE_WORK_ELT(work_area, i) ((work_area).table[i])
 
 /* Bits used to implement the multibyte-part of the various character classes
-   such as [:alnum:] in a charset's range table.  */
+   such as [:alnum:] in a charset's range table.  The code currently assumes
+   that only the low 16 bits are used.  */
 #define BIT_WORD       0x1
 #define BIT_LOWER      0x2
 #define BIT_PUNCT      0x4
@@ -1874,6 +1875,8 @@ struct range_table_work_area
 #define BIT_MULTIBYTE  0x20
 #define BIT_ALPHA      0x40
 #define BIT_ALNUM      0x80
+#define BIT_GRAPH      0x100
+#define BIT_PRINT      0x200
 \f
 
 /* Set the bit for character C in a list.  */
@@ -2072,7 +2075,7 @@ re_wctype_to_bit (re_wctype_t cc)
 {
   switch (cc)
     {
-    case RECC_NONASCII: case RECC_PRINT: case RECC_GRAPH:
+    case RECC_NONASCII:
     case RECC_MULTIBYTE: return BIT_MULTIBYTE;
     case RECC_ALPHA: return BIT_ALPHA;
     case RECC_ALNUM: return BIT_ALNUM;
@@ -2081,6 +2084,8 @@ re_wctype_to_bit (re_wctype_t cc)
     case RECC_UPPER: return BIT_UPPER;
     case RECC_PUNCT: return BIT_PUNCT;
     case RECC_SPACE: return BIT_SPACE;
+    case RECC_GRAPH: return BIT_GRAPH;
+    case RECC_PRINT: return BIT_PRINT;
     case RECC_ASCII: case RECC_DIGIT: case RECC_XDIGIT: case RECC_CNTRL:
     case RECC_BLANK: case RECC_UNIBYTE: case RECC_ERROR: return 0;
     default:
@@ -5122,9 +5127,9 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
 
   DEBUG_PRINT ("The compiled pattern is: ");
   DEBUG_PRINT_COMPILED_PATTERN (bufp, p, pend);
-  DEBUG_PRINT ("The string to match is: `");
+  DEBUG_PRINT ("The string to match is: \"");
   DEBUG_PRINT_DOUBLE_STRING (d, string1, size1, string2, size2);
-  DEBUG_PRINT ("'\n");
+  DEBUG_PRINT ("\"\n");
 
   /* This loops over pattern commands.  It exits by returning from the
      function if the match is complete, or it drops through if the match
@@ -5430,7 +5435,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
                    && buf_ch == '\000'))
              goto fail;
 
-           DEBUG_PRINT ("  Matched `%d'.\n", *d);
+           DEBUG_PRINT ("  Matched \"%d\".\n", *d);
            d += buf_charlen;
          }
          break;
@@ -5439,7 +5444,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
        case charset:
        case charset_not:
          {
-           register unsigned int c;
+           register unsigned int c, corig;
            boolean not = (re_opcode_t) *(p - 1) == charset_not;
            int len;
 
@@ -5468,7 +5473,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
              }
 
            PREFETCH ();
-           c = RE_STRING_CHAR_AND_LENGTH (d, len, target_multibyte);
+           corig = c = RE_STRING_CHAR_AND_LENGTH (d, len, target_multibyte);
            if (target_multibyte)
              {
                int c1;
@@ -5512,14 +5517,22 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
              {
                int class_bits = CHARSET_RANGE_TABLE_BITS (&p[-1]);
 
-               if (  (class_bits & BIT_LOWER && ISLOWER (c))
+               if (  (class_bits & BIT_LOWER
+                      && (ISLOWER (c)
+                          || (corig != c
+                              && c == upcase (corig) && ISUPPER(c))))
                    | (class_bits & BIT_MULTIBYTE)
                    | (class_bits & BIT_PUNCT && ISPUNCT (c))
                    | (class_bits & BIT_SPACE && ISSPACE (c))
-                   | (class_bits & BIT_UPPER && ISUPPER (c))
+                   | (class_bits & BIT_UPPER
+                      && (ISUPPER (c)
+                          || (corig != c
+                              && c == downcase (corig) && ISLOWER (c))))
                    | (class_bits & BIT_WORD  && ISWORD  (c))
                    | (class_bits & BIT_ALPHA && ISALPHA (c))
-                   | (class_bits & BIT_ALNUM && ISALNUM (c)))
+                   | (class_bits & BIT_ALNUM && ISALNUM (c))
+                   | (class_bits & BIT_GRAPH && ISGRAPH (c))
+                   | (class_bits & BIT_PRINT && ISPRINT (c)))
                  not = !not;
                else
                  CHARSET_LOOKUP_RANGE_TABLE_RAW (not, c, range_table, count);
@@ -5938,12 +5951,12 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
 #ifdef emacs
                ssize_t offset = PTR_TO_OFFSET (d - 1);
                ssize_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
-               UPDATE_SYNTAX_TABLE (charpos);
+               UPDATE_SYNTAX_TABLE_FAST (charpos);
 #endif
                GET_CHAR_BEFORE_2 (c1, d, string1, end1, string2, end2);
                s1 = SYNTAX (c1);
 #ifdef emacs
-               UPDATE_SYNTAX_TABLE_FORWARD (charpos + 1);
+               UPDATE_SYNTAX_TABLE_FORWARD_FAST (charpos + 1);
 #endif
                PREFETCH_NOLIMIT ();
                GET_CHAR_AFTER (c2, d, dummy);
@@ -5980,7 +5993,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
 #ifdef emacs
              ssize_t offset = PTR_TO_OFFSET (d);
              ssize_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
-             UPDATE_SYNTAX_TABLE (charpos);
+             UPDATE_SYNTAX_TABLE_FAST (charpos);
 #endif
              PREFETCH ();
              GET_CHAR_AFTER (c2, d, dummy);
@@ -6025,7 +6038,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
 #ifdef emacs
              ssize_t offset = PTR_TO_OFFSET (d) - 1;
              ssize_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
-             UPDATE_SYNTAX_TABLE (charpos);
+             UPDATE_SYNTAX_TABLE_FAST (charpos);
 #endif
              GET_CHAR_BEFORE_2 (c1, d, string1, end1, string2, end2);
              s1 = SYNTAX (c1);
@@ -6040,7 +6053,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
                  PREFETCH_NOLIMIT ();
                  GET_CHAR_AFTER (c2, d, dummy);
 #ifdef emacs
-                 UPDATE_SYNTAX_TABLE_FORWARD (charpos);
+                 UPDATE_SYNTAX_TABLE_FORWARD_FAST (charpos);
 #endif
                  s2 = SYNTAX (c2);
 
@@ -6069,7 +6082,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
 #ifdef emacs
              ssize_t offset = PTR_TO_OFFSET (d);
              ssize_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
-             UPDATE_SYNTAX_TABLE (charpos);
+             UPDATE_SYNTAX_TABLE_FAST (charpos);
 #endif
              PREFETCH ();
              c2 = RE_STRING_CHAR (d, target_multibyte);
@@ -6112,7 +6125,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
 #ifdef emacs
              ssize_t offset = PTR_TO_OFFSET (d) - 1;
              ssize_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
-             UPDATE_SYNTAX_TABLE (charpos);
+             UPDATE_SYNTAX_TABLE_FAST (charpos);
 #endif
              GET_CHAR_BEFORE_2 (c1, d, string1, end1, string2, end2);
              s1 = SYNTAX (c1);
@@ -6127,7 +6140,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
                  PREFETCH_NOLIMIT ();
                  c2 = RE_STRING_CHAR (d, target_multibyte);
 #ifdef emacs
-                 UPDATE_SYNTAX_TABLE_FORWARD (charpos + 1);
+                 UPDATE_SYNTAX_TABLE_FORWARD_FAST (charpos + 1);
 #endif
                  s2 = SYNTAX (c2);
 
@@ -6150,7 +6163,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1,
            {
              ssize_t offset = PTR_TO_OFFSET (d);
              ssize_t pos1 = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
-             UPDATE_SYNTAX_TABLE (pos1);
+             UPDATE_SYNTAX_TABLE_FAST (pos1);
            }
 #endif
            {