mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-12-27 08:39:28 +08:00
0bd61548ab
conversion of basic ASCII letters. Remove all uses of strcasecmp and strncasecmp in favor of new functions pg_strcasecmp and pg_strncasecmp; remove most but not all direct uses of toupper and tolower in favor of pg_toupper and pg_tolower. These functions use the same notions of case folding already developed for identifier case conversion. I left the straight locale-based folding in place for situations where we are just manipulating user data and not trying to match it to built-in strings --- for example, the SQL upper() function is still locale dependent. Perhaps this will prove not to be what's wanted, but at the moment we can initdb and pass regression tests in Turkish locale.
197 lines
3.7 KiB
C
197 lines
3.7 KiB
C
/*
|
|
* ISpell interface
|
|
* Teodor Sigaev <teodor@sigaev.ru>
|
|
*/
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <ctype.h>
|
|
|
|
#include "postgres.h"
|
|
|
|
#include "dict.h"
|
|
#include "common.h"
|
|
#include "ispell/spell.h"
|
|
|
|
typedef struct
|
|
{
|
|
StopList stoplist;
|
|
IspellDict obj;
|
|
} DictISpell;
|
|
|
|
PG_FUNCTION_INFO_V1(spell_init);
|
|
Datum spell_init(PG_FUNCTION_ARGS);
|
|
|
|
PG_FUNCTION_INFO_V1(spell_lexize);
|
|
Datum spell_lexize(PG_FUNCTION_ARGS);
|
|
|
|
static void
|
|
freeDictISpell(DictISpell * d)
|
|
{
|
|
NIFree(&(d->obj));
|
|
freestoplist(&(d->stoplist));
|
|
free(d);
|
|
}
|
|
|
|
Datum
|
|
spell_init(PG_FUNCTION_ARGS)
|
|
{
|
|
DictISpell *d;
|
|
Map *cfg,
|
|
*pcfg;
|
|
text *in;
|
|
bool affloaded = false,
|
|
dictloaded = false,
|
|
stoploaded = false;
|
|
|
|
if (PG_ARGISNULL(0) || PG_GETARG_POINTER(0) == NULL)
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_CONFIG_FILE_ERROR),
|
|
errmsg("ISpell confguration error")));
|
|
|
|
d = (DictISpell *) malloc(sizeof(DictISpell));
|
|
if (!d)
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OUT_OF_MEMORY),
|
|
errmsg("out of memory")));
|
|
memset(d, 0, sizeof(DictISpell));
|
|
d->stoplist.wordop = lowerstr;
|
|
|
|
in = PG_GETARG_TEXT_P(0);
|
|
parse_cfgdict(in, &cfg);
|
|
PG_FREE_IF_COPY(in, 0);
|
|
pcfg = cfg;
|
|
while (pcfg->key)
|
|
{
|
|
if (pg_strcasecmp("DictFile", pcfg->key) == 0)
|
|
{
|
|
if (dictloaded)
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
|
|
errmsg("dictionary already loaded")));
|
|
}
|
|
if (NIImportDictionary(&(d->obj), pcfg->value))
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_CONFIG_FILE_ERROR),
|
|
errmsg("could not load dictionary file \"%s\"",
|
|
pcfg->value)));
|
|
}
|
|
dictloaded = true;
|
|
}
|
|
else if (pg_strcasecmp("AffFile", pcfg->key) == 0)
|
|
{
|
|
if (affloaded)
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
|
|
errmsg("affixes already loaded")));
|
|
}
|
|
if (NIImportAffixes(&(d->obj), pcfg->value))
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_CONFIG_FILE_ERROR),
|
|
errmsg("could not load affix file \"%s\"",
|
|
pcfg->value)));
|
|
}
|
|
affloaded = true;
|
|
}
|
|
else if (pg_strcasecmp("StopFile", pcfg->key) == 0)
|
|
{
|
|
text *tmp = char2text(pcfg->value);
|
|
|
|
if (stoploaded)
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
|
|
errmsg("stop words already loaded")));
|
|
}
|
|
readstoplist(tmp, &(d->stoplist));
|
|
sortstoplist(&(d->stoplist));
|
|
pfree(tmp);
|
|
stoploaded = true;
|
|
}
|
|
else
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_SYNTAX_ERROR),
|
|
errmsg("unrecognized option: %s => %s",
|
|
pcfg->key, pcfg->value)));
|
|
}
|
|
pfree(pcfg->key);
|
|
pfree(pcfg->value);
|
|
pcfg++;
|
|
}
|
|
pfree(cfg);
|
|
|
|
if (affloaded && dictloaded)
|
|
{
|
|
NISortDictionary(&(d->obj));
|
|
NISortAffixes(&(d->obj));
|
|
}
|
|
else if (!affloaded)
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
|
|
errmsg("no affixes")));
|
|
}
|
|
else
|
|
{
|
|
freeDictISpell(d);
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
|
|
errmsg("no dictionary")));
|
|
}
|
|
|
|
PG_RETURN_POINTER(d);
|
|
}
|
|
|
|
Datum
|
|
spell_lexize(PG_FUNCTION_ARGS)
|
|
{
|
|
DictISpell *d = (DictISpell *) PG_GETARG_POINTER(0);
|
|
char *in = (char *) PG_GETARG_POINTER(1);
|
|
char *txt;
|
|
char **res;
|
|
char **ptr,
|
|
**cptr;
|
|
|
|
if (!PG_GETARG_INT32(2))
|
|
PG_RETURN_POINTER(NULL);
|
|
|
|
res = palloc(sizeof(char *) * 2);
|
|
txt = pnstrdup(in, PG_GETARG_INT32(2));
|
|
res = NINormalizeWord(&(d->obj), txt);
|
|
pfree(txt);
|
|
|
|
if (res == NULL)
|
|
PG_RETURN_POINTER(NULL);
|
|
|
|
ptr = cptr = res;
|
|
while (*ptr)
|
|
{
|
|
if (searchstoplist(&(d->stoplist), *ptr))
|
|
{
|
|
pfree(*ptr);
|
|
*ptr = NULL;
|
|
ptr++;
|
|
}
|
|
else
|
|
{
|
|
*cptr = *ptr;
|
|
cptr++;
|
|
ptr++;
|
|
}
|
|
}
|
|
*cptr = NULL;
|
|
|
|
PG_RETURN_POINTER(res);
|
|
}
|