Improve [:alpha:] and [:alnum:] for multibyte characters (Bug#19878)

 src/character.c (alphabeticp, decimalnump): New functions.
 src/character.h (alphabeticp, decimalnump): Add prototypes.
 src/regex.c (ISALNUM, ISALPHA): Check Unicode character properties
 for multibyte characters by calling alphabeticp and decimalnump.
 (BIT_ALPHA, BIT_ALNUM): New bit masks.
 (re_wctype_to_bit): Return them when the class is RECC_ALPHA or
 RECC_ALNUM.
 (re_match_2_internal): Call ISALPHA and ISALNUM when appropriate.

 doc/lispref/searching.texi (Char Classes): Update the documentation of
 [:alpha:] and [:alnum:].

 etc/NEWS: Mention the changes in [:alpha:] and [:alnum:].

doc/lispref/ChangeLog

+2015-02-28  Eli Zaretskii  <eliz@gnu.org>
+
+	* searching.texi (Char Classes): Update the documentation of
+	[:alpha:] and [:alnum:].  (Bug#19878)
+
 2015-02-27  Eli Zaretskii  <eliz@gnu.org>
 
 	* os.texi (Startup Summary):

doc/lispref/searching.texi

@@ -541,11 +541,15 @@ and what they mean:
 @item [:ascii:]
 This matches any @acronym{ASCII} character (codes 0--127).
 @item [:alnum:]
-This matches any letter or digit.  (At present, for multibyte
-characters, it matches anything that has word syntax.)
+This matches any letter or digit.  For multibyte characters, it
+matches characters whose Unicode @samp{general-category} property
+(@pxref{Character Properties}) indicates they are alphabetic or
+decimal number characters.
 @item [:alpha:]
-This matches any letter.  (At present, for multibyte characters, it
-matches anything that has word syntax.)
+This matches any letter.  For multibyte characters, it matches
+characters whose Unicode @samp{general-category} property
+(@pxref{Character Properties}) indicates they are alphabetic
+characters.
 @item [:blank:]
 This matches space and tab only.
 @item [:cntrl:]

etc/NEWS

@@ -612,6 +612,12 @@ when signaling a file error.  For example, it now reports "Permission
 denied" instead of "permission denied".  The old behavior was problematic
 in languages like German where downcasing rules depend on grammar.
 
++++
+** The character classes [:alpha:] and [:alnum:] in regular expressions
+now match multibyte characters using Unicode character properties.
+If you want the old behavior where they matched any character with
+word syntax, use `\sw' instead.
+
 
 * Lisp Changes in Emacs 25.1
 

src/ChangeLog

+2015-02-28  Eli Zaretskii  <eliz@gnu.org>
+
+	* character.c (alphabeticp, decimalnump): New functions.
+	* character.h (alphabeticp, decimalnump): Add prototypes.
+
+	* regex.c (ISALNUM, ISALPHA): Check Unicode character properties
+	for multibyte characters by calling alphabeticp and decimalnump.
+	(BIT_ALPHA, BIT_ALNUM): New bit masks.
+	(re_wctype_to_bit): Return them when the class is RECC_ALPHA or
+	RECC_ALNUM.
+	(re_match_2_internal): Call ISALPHA and ISALNUM when appropriate.
+	(Bug#19878)
+
 2015-02-27  Jan Djärv  <jan.h.d@swipnet.se>
 
 	* xterm.h (x_real_pos_and_offsets): Take outer_border as arg also.

src/character.c

@@ -984,6 +984,48 @@ character is not ASCII nor 8-bit character, an error is signaled.  */)
 
 #ifdef emacs
 
+/* Return 'true' if C is an alphabetic character as defined by its
+   Unicode properties.  */
+bool
+alphabeticp (int c)
+{
+  Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
+
+  if (INTEGERP (category))
+    {
+      unicode_category_t gen_cat = XINT (category);
+
+      /* See UTS #18.  There are additional characters that should be
+	 here, those designated as Other_uppercase, Other_lowercase,
+	 and Other_alphabetic; FIXME.  */
+      return (gen_cat == UNICODE_CATEGORY_Lu
+	      || gen_cat == UNICODE_CATEGORY_Ll
+	      || gen_cat == UNICODE_CATEGORY_Lt
+	      || gen_cat == UNICODE_CATEGORY_Lm
+	      || gen_cat == UNICODE_CATEGORY_Lo
+	      || gen_cat == UNICODE_CATEGORY_Mn
+	      || gen_cat == UNICODE_CATEGORY_Mc
+	      || gen_cat == UNICODE_CATEGORY_Me
+	      || gen_cat == UNICODE_CATEGORY_Nl) ? true : false;
+    }
+}
+
+/* Return 'true' if C is an decimal-number character as defined by its
+   Unicode properties.  */
+bool
+decimalnump (int c)
+{
+  Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
+
+  if (INTEGERP (category))
+    {
+      unicode_category_t gen_cat = XINT (category);
+
+      /* See UTS #18.  */
+      return (gen_cat == UNICODE_CATEGORY_Nd) ? true : false;
+    }
+}
+
 void
 syms_of_character (void)
 {

src/character.h

@@ -660,6 +660,9 @@ extern ptrdiff_t lisp_string_width (Lisp_Object, ptrdiff_t,
 extern Lisp_Object Vchar_unify_table;
 extern Lisp_Object string_escape_byte8 (Lisp_Object);
 
+extern bool alphabeticp (int);
+extern bool decimalnump (int);
+
 /* Return a translation table of id number ID.  */
 #define GET_TRANSLATION_TABLE(id) \
   (XCDR (XVECTOR (Vtranslation_table_vector)->contents[(id)]))

src/regex.c

@@ -324,12 +324,12 @@ enum syntaxcode { Swhitespace = 0, Sword = 1, Ssymbol = 2 };
 		    ? (((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'))	\
-		    : SYNTAX (c) == Sword)
+		    : alphabeticp (c))
 
 # define ISLOWER(c) lowercasep (c)
 
@@ -1872,6 +1872,8 @@ struct range_table_work_area
 #define BIT_SPACE	0x8
 #define BIT_UPPER	0x10
 #define BIT_MULTIBYTE	0x20
+#define BIT_ALPHA	0x40
+#define BIT_ALNUM	0x80
 
 
 /* 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_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;
@@ -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,
-			   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)))
@@ -2945,7 +2949,7 @@ regex_compile (const_re_char *pattern, size_t size, reg_syntax_t syntax,
 			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 = ':';
@@ -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_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);