database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-09 06:21:09 +03:00
Code Activity

Change case-folding of keywords to conform to SQL99 and fix misbehavior

Browse Source 
in Turkish locale.  Keywords are now checked under pure ASCII case-folding
rules ('A'-'Z'->'a'-'z' and nothing else).  However, once a word is
determined not to be a keyword, it will be case-folded under the current
locale, same as before.  See pghackers discussion 20-Feb-01.
This commit is contained in:
Tom Lane
2001-02-21 18:53:47 +00:00
parent 496373e2e4
commit be92ad49e0
6 changed files with 231 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
src/backend/parser/keywords.c
View File

@@ -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)