kwlookup.c

Go to the documentation of this file.

/*-------------------------------------------------------------------------
 *
 * kwlookup.c
 *    Key word lookup for PostgreSQL
 *
 *
 * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *    src/common/kwlookup.c
 *
 *-------------------------------------------------------------------------
 */
#include "c.h"
 
#include "common/kwlookup.h"
 
 
/*
 * ScanKeywordLookup - see if a given word is a keyword
 *
 * The list of keywords to be matched against is passed as a ScanKeywordList.
 *
 * Returns the keyword number (0..N-1) of the keyword, or -1 if no match.
 * Callers typically use the keyword number to index into information
 * arrays, but that is no concern of this code.
 *
 * 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.
 */
int
ScanKeywordLookup(const char *str,
                  const ScanKeywordList *keywords)
{
    size_t      len;
    int         h;
    const char *kw;
 
    /*
     * Reject immediately if too long to be any keyword.  This saves useless
     * hashing and downcasing work on long strings.
     */
    len = strlen(str);
    if (len > keywords->max_kw_len)
        return -1;
 
    /*
     * Compute the hash function.  We assume it was generated to produce
     * case-insensitive results.  Since it's a perfect hash, we need only
     * match to the specific keyword it identifies.
     */
    h = keywords->hash(str, len);
 
    /* An out-of-range result implies no match */
    if (h < 0 || h >= keywords->num_keywords)
        return -1;
 
    /*
     * Compare character-by-character to see if we have a match, applying an
     * ASCII-only downcasing to the input characters.  We must not use
     * tolower() since it may produce the wrong translation in some locales
     * (eg, Turkish).
     */
    kw = GetScanKeyword(h, keywords);
    while (*str != '\0')
    {
        char        ch = *str++;
 
        if (ch >= 'A' && ch <= 'Z')
            ch += 'a' - 'A';
        if (ch != *kw++)
            return -1;
    }
    if (*kw != '\0')
        return -1;
 
    /* Success! */
    return h;
}