Fix some wide-character bugs in the text-search parser.

tglsfdc · tglsfdc · commit 3c7b4ef70fb4 · 2014-02-01T18:27:54.000-05:00
In p_isdigit and other character class test functions generated by the
p_iswhat macro, the code path for non-C locales with multibyte encodings
contained a bogus pointer cast that would accidentally fail to malfunction
if types wchar_t and wint_t have the same width.  Apparently that is true
on most platforms, but not on recent Cygwin releases.  Remove the cast,
as it seems completely unnecessary (I think it arose from a false analogy
to the need to cast to unsigned char when dealing with the &lt;ctype.h&gt;
functions).  Per bug #8970 from Marco Atzeri.

In the same functions, the code path for C locale with a multibyte encoding
simply ANDed each wide character with 0xFF before passing it to the
corresponding &lt;ctype.h&gt; function.  This could result in false positive
answers for some non-ASCII characters, so use a range test instead.
Noted by me while investigating Marco's complaint.

Also, remove some useless though not actually buggy maskings and casts
in the hand-coded p_isalnum and p_isalpha functions, which evidently
got tested a bit more carefully than the macro-generated functions.
diff --git a/src/backend/tsearch/wparser_def.c b/src/backend/tsearch/wparser_def.c
@@ -426,7 +426,7 @@ TParserCopyClose(TParser *prs)
  *    or give wrong result. 
  *  - multibyte encoding and C-locale often are used for 
  *    Asian languages.
- *  - if locale is C the we use pgwstr instead of wstr
+ *  - if locale is C then we use pgwstr instead of wstr.
  */
 
 #ifdef USE_WIDE_UPPER_LOWER
@@ -438,9 +438,13 @@ p_is##type(TParser *prs) {													\
 	if ( prs->usewide )														\
 	{																		\
 		if ( prs->pgwstr )													\
-			return is##type( 0xff & *( prs->pgwstr + prs->state->poschar) );\
-																			\
-		return isw##type( *(wint_t*)( prs->wstr + prs->state->poschar ) );	\
+		{																	\
+			unsigned int c = *(prs->pgwstr + prs->state->poschar);			\
+			if ( c > 0x7f )													\
+				return 0;													\
+			return is##type( c );											\
+		}																	\
+		return isw##type( *( prs->wstr + prs->state->poschar ) );			\
 	}																		\
 																			\
 	return is##type( *(unsigned char*)( prs->str + prs->state->posbyte ) ); \
@@ -469,10 +473,10 @@ p_isalnum(TParser *prs)
 			if (c > 0x7f)
 				return 1;
 
-			return isalnum(0xff & c);
+			return isalnum(c);
 		}
 
-		return iswalnum((wint_t) *(prs->wstr + prs->state->poschar));
+		return iswalnum(*(prs->wstr + prs->state->poschar));
 	}
 
 	return isalnum(*(unsigned char *) (prs->str + prs->state->posbyte));
@@ -501,10 +505,10 @@ p_isalpha(TParser *prs)
 			if (c > 0x7f)
 				return 1;
 
-			return isalpha(0xff & c);
+			return isalpha(c);
 		}
 
-		return iswalpha((wint_t) *(prs->wstr + prs->state->poschar));
+		return iswalpha(*(prs->wstr + prs->state->poschar));
 	}
 
 	return isalpha(*(unsigned char *) (prs->str + prs->state->posbyte));
