1 files changed, 53 insertions, 10 deletions

diff --git a/src/backend/parser/keywords.c b/src/backend/parser/keywords.c
index 7936f3a580..c8f5f2c0e9 100644
--- a/src/backend/parser/keywords.c
+++ b/src/backend/parser/keywords.c
@@ -1,23 +1,22 @@
 /*-------------------------------------------------------------------------
  *
  * keywords.c
- *	  lexical token lookup for reserved words in postgres SQL
+ *	  lexical token lookup for reserved words in PostgreSQL
  *
  * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/parser/keywords.c,v 1.88 2001/01/24 19:43:01 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/parser/keywords.c,v 1.89 2001/02/21 18:53:46 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
-#include <ctype.h>
-
 #include "postgres.h"
 
+#include <ctype.h>
+
 #include "nodes/parsenodes.h"
-#include "nodes/pg_list.h"
 #include "parser/keywords.h"
 #include "parser/parse.h"
 
@@ -286,18 +285,62 @@ static ScanKeyword ScanKeywords[] = {
 	{"zone", ZONE},
 };
 
+/*
+ * ScanKeywordLookup - see if a given word is a keyword
+ *
+ * Returns a pointer to the ScanKeyword table entry, or NULL if no match.
+ *
+ * The match is done case-insensitively.  Note that we deliberately use a
+ * dumbed-down case conversion that will only translate 'A'-'Z' into 'a'-'z',
+ * even if we are in a locale where tolower() would produce more or different
+ * translations.  This is to conform to the SQL99 spec, which says that
+ * keywords are to be matched in this way even though non-keyword identifiers
+ * receive a different case-normalization mapping.
+ */
 ScanKeyword *
 ScanKeywordLookup(char *text)
 {
-	ScanKeyword *low = &ScanKeywords[0];
-	ScanKeyword *high = endof(ScanKeywords) - 1;
-	ScanKeyword *middle;
-	int			difference;
+	int			len,
+				i;
+	char		word[NAMEDATALEN];
+	ScanKeyword *low;
+	ScanKeyword *high;
+
+	len = strlen(text);
+	/* We assume all keywords are shorter than NAMEDATALEN. */
+	if (len >= NAMEDATALEN)
+		return NULL;
+
+	/*
+	 * Apply an ASCII-only downcasing.  We must not use tolower() since
+	 * it may produce the wrong translation in some locales (eg, Turkish),
+	 * and we don't trust isupper() very much either.  In an ASCII-based
+	 * encoding the tests against A and Z are sufficient, but we also check
+	 * isupper() so that we will work correctly under EBCDIC.  The actual
+	 * case conversion step should work for either ASCII or EBCDIC.
+	 */
+	for (i = 0; i < len; i++)
+	{
+		char	ch = text[i];
 
+		if (ch >= 'A' && ch <= 'Z' && isupper((unsigned char) ch))
+			ch += 'a' - 'A';
+		word[i] = ch;
+	}
+	word[len] = '\0';
+
+	/*
+	 * Now do a binary search using plain strcmp() comparison.
+	 */
+	low = &ScanKeywords[0];
+	high = endof(ScanKeywords) - 1;
 	while (low <= high)
 	{
+		ScanKeyword *middle;
+		int			difference;
+
 		middle = low + (high - low) / 2;
-		difference = strcmp(middle->name, text);
+		difference = strcmp(middle->name, word);
 		if (difference == 0)
 			return middle;
 		else if (difference < 0)