Replace the now-incompatible-with-core contrib/tsearch2 module with a

compatibility package.  This supports importing dumps from past versions
using tsearch2, and provides the old names and API for most functions
that were changed.  (rewrite(ARRAY[...]) is a glaring omission, though.)

Pavel Stehule and Tom Lane

contrib/tsearch2/Makefile

-# $PostgreSQL: pgsql/contrib/tsearch2/Makefile,v 1.19 2007/06/26 22:05:03 tgl Exp $
+# $PostgreSQL: pgsql/contrib/tsearch2/Makefile,v 1.20 2007/11/13 21:02:28 tgl Exp $
 
-MODULE_big = tsearch2
-OBJS = dict_ex.o dict.o snmap.o stopword.o common.o prs_dcfg.o \
-       dict_snowball.o dict_ispell.o dict_syn.o dict_thesaurus.o \
-       wparser.o wparser_def.o \
-       ts_cfg.o tsvector.o query_cleanup.o crc32.o query.o gistidx.o \
-       tsvector_op.o rank.o ts_stat.o \
-       query_util.o query_support.o query_rewrite.o query_gist.o \
-       ts_locale.o ts_lexize.o ginidx.o
-
-SUBDIRS     = snowball ispell wordparser
-SUBDIROBJS  = $(SUBDIRS:%=%/SUBSYS.o)
-
-OBJS	+= $(SUBDIROBJS)
-
-PG_CPPFLAGS = -I$(srcdir)/snowball -I$(srcdir)/ispell -I$(srcdir)/wordparser
-
-DATA = stopword/english.stop stopword/russian.stop stopword/russian.stop.utf8 thesaurus
-DATA_built = tsearch2.sql uninstall_tsearch2.sql
-DOCS = README.tsearch2
+MODULES = tsearch2
+DATA_built = tsearch2.sql
+DATA = uninstall_tsearch2.sql
 REGRESS = tsearch2
 
-SHLIB_LINK += $(filter -lm, $(LIBS))
-
-
 ifdef USE_PGXS
 PG_CONFIG = pg_config
 PGXS := $(shell $(PG_CONFIG) --pgxs)
@@ -34,23 +15,3 @@ top_builddir = ../..
 include $(top_builddir)/src/Makefile.global
 include $(top_srcdir)/contrib/contrib-global.mk
 endif
-
-
-$(SUBDIROBJS): $(SUBDIRS:%=%-recursive) ;
-
-.PHONY: $(SUBDIRS:%=%-recursive)
-
-$(SUBDIRS:%=%-recursive):
-	$(MAKE) -C $(subst -recursive,,$@) SUBSYS.o
-
-tsearch2.sql: tsearch.sql.in
-	sed -e 's,MODULE_PATHNAME,$$libdir/$(MODULE_big),g' $< >$@
-
-uninstall_tsearch2.sql: untsearch.sql.in
-	cp $< $@
-
-.PHONY: subclean
-clean: subclean
-
-subclean:
-	for dir in $(SUBDIRS); do $(MAKE) -C $$dir clean || exit; done

contrib/tsearch2/common.c

-#include "postgres.h"
-
-#include "fmgr.h"
-#include "catalog/pg_namespace.h"
-#include "catalog/pg_proc.h"
-#include "utils/syscache.h"
-#include "miscadmin.h"
-
-#include "ts_cfg.h"
-#include "dict.h"
-#include "wparser.h"
-#include "snmap.h"
-#include "common.h"
-#include "tsvector.h"
-
-
-
-#include "common.h"
-#include "wparser.h"
-#include "ts_cfg.h"
-#include "dict.h"
-
-
-Oid			TSNSP_FunctionOid = InvalidOid;
-
-
-text *
-char2text(char *in)
-{
-	return charl2text(in, strlen(in));
-}
-
-text *
-charl2text(char *in, int len)
-{
-	text	   *out = (text *) palloc(len + VARHDRSZ);
-
-	memcpy(VARDATA(out), in, len);
-	SET_VARSIZE(out, len + VARHDRSZ);
-	return out;
-}
-
-char
-		   *
-text2char(text *in)
-{
-	char	   *out = palloc(VARSIZE(in));
-
-	memcpy(out, VARDATA(in), VARSIZE(in) - VARHDRSZ);
-	out[VARSIZE(in) - VARHDRSZ] = '\0';
-	return out;
-}
-
-char
-		   *
-pnstrdup(char *in, int len)
-{
-	char	   *out = palloc(len + 1);
-
-	memcpy(out, in, len);
-	out[len] = '\0';
-	return out;
-}
-
-text
-		   *
-ptextdup(text *in)
-{
-	text	   *out = (text *) palloc(VARSIZE(in));
-
-	memcpy(out, in, VARSIZE(in));
-	return out;
-}
-
-text
-		   *
-mtextdup(text *in)
-{
-	text	   *out = (text *) malloc(VARSIZE(in));
-
-	if (!out)
-		ts_error(ERROR, "No memory");
-	memcpy(out, in, VARSIZE(in));
-	return out;
-}
-
-void
-ts_error(int state, const char *format,...)
-{
-	va_list		args;
-	int			tlen = 128,
-				len = 0;
-	char	   *buf;
-
-	reset_cfg();
-	reset_dict();
-	reset_prs();
-
-	va_start(args, format);
-	buf = palloc(tlen);
-	len = vsnprintf(buf, tlen - 1, format, args);
-	if (len >= tlen)
-	{
-		tlen = len + 1;
-		buf = repalloc(buf, tlen);
-		vsnprintf(buf, tlen - 1, format, args);
-	}
-	va_end(args);
-
-	/* ?? internal error ?? */
-	elog(state, "%s", buf);
-	pfree(buf);
-}
-
-int
-text_cmp(text *a, text *b)
-{
-	if (VARSIZE(a) == VARSIZE(b))
-		return strncmp(VARDATA(a), VARDATA(b), VARSIZE(a) - VARHDRSZ);
-	return (int) VARSIZE(a) - (int) VARSIZE(b);
-
-}
-
-char *
-get_namespace(Oid funcoid)
-{
-	HeapTuple	tuple;
-	Form_pg_proc proc;
-	Form_pg_namespace nsp;
-	Oid			nspoid;
-	char	   *txt;
-
-	tuple = SearchSysCache(PROCOID, ObjectIdGetDatum(funcoid), 0, 0, 0);
-	if (!HeapTupleIsValid(tuple))
-		elog(ERROR, "cache lookup failed for proc oid %u", funcoid);
-	proc = (Form_pg_proc) GETSTRUCT(tuple);
-	nspoid = proc->pronamespace;
-	ReleaseSysCache(tuple);
-
-	tuple = SearchSysCache(NAMESPACEOID, ObjectIdGetDatum(nspoid), 0, 0, 0);
-	if (!HeapTupleIsValid(tuple))
-		elog(ERROR, "cache lookup failed for namespace oid %u", nspoid);
-	nsp = (Form_pg_namespace) GETSTRUCT(tuple);
-	txt = pstrdup(NameStr((nsp->nspname)));
-	ReleaseSysCache(tuple);
-
-	return txt;
-}
-
-Oid
-get_oidnamespace(Oid funcoid)
-{
-	HeapTuple	tuple;
-	Form_pg_proc proc;
-	Oid			nspoid;
-
-	tuple = SearchSysCache(PROCOID, ObjectIdGetDatum(funcoid), 0, 0, 0);
-	if (!HeapTupleIsValid(tuple))
-		elog(ERROR, "cache lookup failed for proc oid %u", funcoid);
-	proc = (Form_pg_proc) GETSTRUCT(tuple);
-	nspoid = proc->pronamespace;
-	ReleaseSysCache(tuple);
-
-	return nspoid;
-}
-
- /* if path is relative, take it as relative to share dir */
-char *
-to_absfilename(char *filename)
-{
-	if (!is_absolute_path(filename))
-	{
-		char		sharepath[MAXPGPATH];
-		char	   *absfn;
-
-#ifdef	WIN32
-		char		delim = '\\';
-#else
-		char		delim = '/';
-#endif
-		get_share_path(my_exec_path, sharepath);
-		absfn = palloc(strlen(sharepath) + strlen(filename) + 2);
-		sprintf(absfn, "%s%c%s", sharepath, delim, filename);
-		filename = absfn;
-	}
-
-	return filename;
-}

contrib/tsearch2/common.h

-#ifndef __TS_COMMON_H__
-#define __TS_COMMON_H__
-
-#include "postgres.h"
-#include "fmgr.h"
-#include "utils/array.h"
-
-text	   *char2text(char *in);
-text	   *charl2text(char *in, int len);
-char	   *text2char(text *in);
-char	   *pnstrdup(char *in, int len);
-text	   *ptextdup(text *in);
-text	   *mtextdup(text *in);
-
-int			text_cmp(text *a, text *b);
-
-char	   *to_absfilename(char *filename);
-
-#define NEXTVAL(x) ( (text*)( (char*)(x) + INTALIGN( VARSIZE(x) ) ) )
-#define ARRNELEMS(x)  ArrayGetNItems( ARR_NDIM(x), ARR_DIMS(x))
-
-void		ts_error(int state, const char *format,...);
-
-extern Oid	TSNSP_FunctionOid;	/* oid of called function, needed only for
-								 * determ namespace, no more */
-char	   *get_namespace(Oid funcoid);
-Oid			get_oidnamespace(Oid funcoid);
-
-#define SET_FUNCOID()	do {											\
-		if ( fcinfo->flinfo && fcinfo->flinfo->fn_oid != InvalidOid )	\
-				TSNSP_FunctionOid = fcinfo->flinfo->fn_oid;					  \
-} while(0)
-
-#endif

contrib/tsearch2/crc32.c

-/* Both POSIX and CRC32 checksums */
-
-/* $PostgreSQL: pgsql/contrib/tsearch2/crc32.c,v 1.4 2007/07/15 22:40:28 tgl Exp $ */
-
-#include <sys/types.h>
-#include <stdio.h>
-#include <sys/types.h>
-
-#include "crc32.h"
-
-/*
- * This code implements the AUTODIN II polynomial
- * The variable corresponding to the macro argument "crc" should
- * be an unsigned long.
- * Oroginal code  by Spencer Garrett <srg@quick.com>
- */
-
-#define _CRC32_(crc, ch)	 ((crc) = ((crc) >> 8) ^ crc32tab[((crc) ^ (ch)) & 0xff])
-
-/* generated using the AUTODIN II polynomial
- *	x^32 + x^26 + x^23 + x^22 + x^16 +
- *	x^12 + x^11 + x^10 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + 1
- */
-
-static const unsigned int crc32tab[256] = {
-	0x00000000, 0x77073096, 0xee0e612c, 0x990951ba,
-	0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3,
-	0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
-	0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91,
-	0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
-	0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
-	0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec,
-	0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5,
-	0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
-	0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
-	0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940,
-	0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
-	0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116,
-	0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f,
-	0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
-	0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d,
-	0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a,
-	0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
-	0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818,
-	0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
-	0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
-	0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457,
-	0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c,
-	0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
-	0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
-	0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb,
-	0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
-	0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9,
-	0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086,
-	0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
-	0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4,
-	0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad,
-	0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
-	0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683,
-	0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
-	0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
-	0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe,
-	0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7,
-	0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
-	0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
-	0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252,
-	0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
-	0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60,
-	0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79,
-	0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
-	0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f,
-	0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04,
-	0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
-	0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a,
-	0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
-	0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
-	0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21,
-	0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e,
-	0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
-	0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
-	0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45,
-	0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
-	0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db,
-	0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0,
-	0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
-	0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6,
-	0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf,
-	0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
-	0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d,
-};
-
-unsigned int
-crc32_sz(char *buf, int size)
-{
-	unsigned int crc = ~((unsigned int) 0);
-	char	   *p;
-	int			len,
-				nr;
-
-	len = 0;
-	nr = size;
-	for (len += nr, p = buf; nr--; ++p)
-		_CRC32_(crc, *p);
-	return ~crc;
-}

contrib/tsearch2/crc32.h

-#ifndef _CRC32_H
-#define _CRC32_H
-
-/* $PostgreSQL: pgsql/contrib/tsearch2/crc32.h,v 1.2 2006/03/11 04:38:30 momjian Exp $ */
-
-/* Returns crc32 of data block */
-extern unsigned int crc32_sz(char *buf, int size);
-
-/* Returns crc32 of null-terminated string */
-#define crc32(buf) crc32_sz((buf),strlen(buf))
-
-#endif

contrib/tsearch2/dict.c

-/* $PostgreSQL: pgsql/contrib/tsearch2/dict.c,v 1.13 2006/10/04 00:29:46 momjian Exp $ */
-
-/*
- * interface functions to dictionary
- * Teodor Sigaev <teodor@sigaev.ru>
- */
-#include "postgres.h"
-
-#include <ctype.h>
-
-#include "catalog/pg_type.h"
-#include "executor/spi.h"
-#include "fmgr.h"
-#include "utils/array.h"
-#include "utils/memutils.h"
-
-#include "dict.h"
-#include "common.h"
-#include "snmap.h"
-
-/*********top interface**********/
-
-void
-init_dict(Oid id, DictInfo * dict)
-{
-	Oid			arg[1];
-	bool		isnull;
-	Datum		pars[1];
-	int			stat;
-	void	   *plan;
-	char		buf[1024];
-	char	   *nsp = get_namespace(TSNSP_FunctionOid);
-
-	arg[0] = OIDOID;
-	pars[0] = ObjectIdGetDatum(id);
-
-	memset(dict, 0, sizeof(DictInfo));
-	SPI_connect();
-	sprintf(buf, "select dict_init, dict_initoption, dict_lexize from %s.pg_ts_dict where oid = $1", nsp);
-	pfree(nsp);
-	plan = SPI_prepare(buf, 1, arg);
-	if (!plan)
-		ts_error(ERROR, "SPI_prepare() failed");
-
-	stat = SPI_execp(plan, pars, " ", 1);
-	if (stat < 0)
-		ts_error(ERROR, "SPI_execp return %d", stat);
-	if (SPI_processed > 0)
-	{
-		Datum		opt;
-		Oid			oid = InvalidOid;
-
-		/* setup dictlexize method */
-		oid = DatumGetObjectId(SPI_getbinval(SPI_tuptable->vals[0], SPI_tuptable->tupdesc, 3, &isnull));
-		if (isnull || oid == InvalidOid)
-			ts_error(ERROR, "Null dict_lexize for dictonary %d", id);
-		fmgr_info_cxt(oid, &(dict->lexize_info), TopMemoryContext);
-
-		/* setup and call dictinit method, optinally */
-		oid = DatumGetObjectId(SPI_getbinval(SPI_tuptable->vals[0], SPI_tuptable->tupdesc, 1, &isnull));
-		if (!(isnull || oid == InvalidOid))
-		{
-			opt = SPI_getbinval(SPI_tuptable->vals[0], SPI_tuptable->tupdesc, 2, &isnull);
-			dict->dictionary = (void *) DatumGetPointer(OidFunctionCall1(oid, opt));
-		}
-		dict->dict_id = id;
-	}
-	else
-		ts_error(ERROR, "No dictionary with id %d", id);
-	SPI_freeplan(plan);
-	SPI_finish();
-}
-
-typedef struct
-{
-	DictInfo   *last_dict;
-	int			len;
-	int			reallen;
-	DictInfo   *list;
-	SNMap		name2id_map;
-}	DictList;
-
-static DictList DList = {NULL, 0, 0, NULL, {0, 0, NULL}};
-
-void
-reset_dict(void)
-{
-	freeSNMap(&(DList.name2id_map));
-	/* XXX need to free DList.list[*].dictionary */
-	if (DList.list)
-		free(DList.list);
-	memset(&DList, 0, sizeof(DictList));
-}
-
-
-static int
-comparedict(const void *a, const void *b)
-{
-	if (((DictInfo *) a)->dict_id == ((DictInfo *) b)->dict_id)
-		return 0;
-	return (((DictInfo *) a)->dict_id < ((DictInfo *) b)->dict_id) ? -1 : 1;
-}
-
-static void
-insertdict(Oid id)
-{
-	DictInfo	newdict;
-
-	if (DList.len == DList.reallen)
-	{
-		DictInfo   *tmp;
-		int			reallen = (DList.reallen) ? 2 * DList.reallen : 16;
-
-		tmp = (DictInfo *) realloc(DList.list, sizeof(DictInfo) * reallen);
-		if (!tmp)
-			ts_error(ERROR, "No memory");
-		DList.reallen = reallen;
-		DList.list = tmp;
-	}
-	init_dict(id, &newdict);
-
-	DList.list[DList.len] = newdict;
-	DList.len++;
-
-	qsort(DList.list, DList.len, sizeof(DictInfo), comparedict);
-}
-
-DictInfo *
-finddict(Oid id)
-{
-	/* last used dict */
-	if (DList.last_dict && DList.last_dict->dict_id == id)
-		return DList.last_dict;
-
-
-	/* already used dict */
-	if (DList.len != 0)
-	{
-		DictInfo	key;
-
-		key.dict_id = id;
-		DList.last_dict = bsearch(&key, DList.list, DList.len, sizeof(DictInfo), comparedict);
-		if (DList.last_dict != NULL)
-			return DList.last_dict;
-	}
-
-	/* insert new dictionary */
-	insertdict(id);
-	return finddict(id); /* qsort changed order!! */ ;
-}
-
-Oid
-name2id_dict(text *name)
-{
-	Oid			arg[1];
-	bool		isnull;
-	Datum		pars[1];
-	int			stat;
-	Oid			id = findSNMap_t(&(DList.name2id_map), name);
-	void	   *plan;
-	char		buf[1024],
-			   *nsp;
-
-	arg[0] = TEXTOID;
-	pars[0] = PointerGetDatum(name);
-
-	if (id)
-		return id;
-
-	nsp = get_namespace(TSNSP_FunctionOid);
-	SPI_connect();
-	sprintf(buf, "select oid from %s.pg_ts_dict where dict_name = $1", nsp);
-	pfree(nsp);
-	plan = SPI_prepare(buf, 1, arg);
-	if (!plan)
-		ts_error(ERROR, "SPI_prepare() failed");
-
-	stat = SPI_execp(plan, pars, " ", 1);
-	if (stat < 0)
-		ts_error(ERROR, "SPI_execp return %d", stat);
-	if (SPI_processed > 0)
-		id = DatumGetObjectId(SPI_getbinval(SPI_tuptable->vals[0], SPI_tuptable->tupdesc, 1, &isnull));
-	else
-		ts_error(ERROR, "No dictionary with name '%s'", text2char(name));
-	SPI_freeplan(plan);
-	SPI_finish();
-	addSNMap_t(&(DList.name2id_map), name, id);
-	return id;
-}
-
-
-/******sql-level interface******/
-PG_FUNCTION_INFO_V1(lexize);
-Datum		lexize(PG_FUNCTION_ARGS);
-
-Datum
-lexize(PG_FUNCTION_ARGS)
-{
-	text	   *in = PG_GETARG_TEXT_P(1);
-	DictInfo   *dict;
-	TSLexeme   *res,
-			   *ptr;
-	Datum	   *da;
-	ArrayType  *a;
-	DictSubState dstate = {false, false, NULL};
-
-	SET_FUNCOID();
-	dict = finddict(PG_GETARG_OID(0));
-
-	ptr = res = (TSLexeme *) DatumGetPointer(
-										  FunctionCall4(&(dict->lexize_info),
-										   PointerGetDatum(dict->dictionary),
-												PointerGetDatum(VARDATA(in)),
-									   Int32GetDatum(VARSIZE(in) - VARHDRSZ),
-													 PointerGetDatum(&dstate)
-														)
-		);
-
-	if (dstate.getnext)
-	{
-		dstate.isend = true;
-		ptr = res = (TSLexeme *) DatumGetPointer(
-										  FunctionCall4(&(dict->lexize_info),
-										   PointerGetDatum(dict->dictionary),
-												PointerGetDatum(VARDATA(in)),
-									   Int32GetDatum(VARSIZE(in) - VARHDRSZ),
-													 PointerGetDatum(&dstate)
-														)
-			);
-	}
-
-	PG_FREE_IF_COPY(in, 1);
-	if (!res)
-	{
-		if (PG_NARGS() > 2)
-			PG_RETURN_POINTER(NULL);
-		else
-			PG_RETURN_NULL();
-	}
-
-	while (ptr->lexeme)
-		ptr++;
-	da = (Datum *) palloc(sizeof(Datum) * (ptr - res + 1));
-	ptr = res;
-	while (ptr->lexeme)
-	{
-		da[ptr - res] = PointerGetDatum(char2text(ptr->lexeme));
-		ptr++;
-	}
-
-	a = construct_array(
-						da,
-						ptr - res,
-						TEXTOID,
-						-1,
-						false,
-						'i'
-		);
-
-	ptr = res;
-	while (ptr->lexeme)
-	{
-		pfree(DatumGetPointer(da[ptr - res]));
-		pfree(ptr->lexeme);
-		ptr++;
-	}
-	pfree(res);
-	pfree(da);
-
-	PG_RETURN_POINTER(a);
-}
-
-PG_FUNCTION_INFO_V1(lexize_byname);
-Datum		lexize_byname(PG_FUNCTION_ARGS);
-Datum
-lexize_byname(PG_FUNCTION_ARGS)
-{
-	text	   *dictname = PG_GETARG_TEXT_P(0);
-	Datum		res;
-
-	SET_FUNCOID();
-
-	res = DirectFunctionCall3(
-							  lexize,
-							  ObjectIdGetDatum(name2id_dict(dictname)),
-							  PG_GETARG_DATUM(1),
-							  (Datum) 0
-		);
-	PG_FREE_IF_COPY(dictname, 0);
-	if (res)
-		PG_RETURN_DATUM(res);
-	else
-		PG_RETURN_NULL();
-}
-
-static Oid	currect_dictionary_id = 0;
-
-PG_FUNCTION_INFO_V1(set_curdict);
-Datum		set_curdict(PG_FUNCTION_ARGS);
-Datum
-set_curdict(PG_FUNCTION_ARGS)
-{
-	SET_FUNCOID();
-	finddict(PG_GETARG_OID(0));
-	currect_dictionary_id = PG_GETARG_OID(0);
-	PG_RETURN_VOID();
-}
-
-PG_FUNCTION_INFO_V1(set_curdict_byname);
-Datum		set_curdict_byname(PG_FUNCTION_ARGS);
-Datum
-set_curdict_byname(PG_FUNCTION_ARGS)
-{
-	text	   *dictname = PG_GETARG_TEXT_P(0);
-
-	SET_FUNCOID();
-	DirectFunctionCall1(
-						set_curdict,
-						ObjectIdGetDatum(name2id_dict(dictname))
-		);
-	PG_FREE_IF_COPY(dictname, 0);
-	PG_RETURN_VOID();
-}
-
-PG_FUNCTION_INFO_V1(lexize_bycurrent);
-Datum		lexize_bycurrent(PG_FUNCTION_ARGS);
-Datum
-lexize_bycurrent(PG_FUNCTION_ARGS)
-{
-	Datum		res;
-
-	SET_FUNCOID();
-	if (currect_dictionary_id == 0)
-		ereport(ERROR,
-				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
-				 errmsg("no currect dictionary"),
-				 errhint("Execute select set_curdict().")));
-
-	res = DirectFunctionCall3(
-							  lexize,
-							  ObjectIdGetDatum(currect_dictionary_id),
-							  PG_GETARG_DATUM(0),
-							  (Datum) 0
-		);
-	if (res)
-		PG_RETURN_DATUM(res);
-	else
-		PG_RETURN_NULL();
-}

contrib/tsearch2/dict.h

-/* $PostgreSQL: pgsql/contrib/tsearch2/dict.h,v 1.8 2006/10/04 00:29:46 momjian Exp $ */
-
-#ifndef __DICT_H__
-#define __DICT_H__
-#include "postgres.h"
-#include "fmgr.h"
-#include "ts_cfg.h"
-
-typedef struct
-{
-	int			len;
-	char	  **stop;
-	char	   *(*wordop) (char *);
-}	StopList;
-
-void		sortstoplist(StopList * s);
-void		freestoplist(StopList * s);
-void		readstoplist(text *in, StopList * s);
-bool		searchstoplist(StopList * s, char *key);
-
-typedef struct
-{
-	Oid			dict_id;
-	FmgrInfo	lexize_info;
-	void	   *dictionary;
-}	DictInfo;
-
-void		init_dict(Oid id, DictInfo * dict);
-DictInfo   *finddict(Oid id);
-Oid			name2id_dict(text *name);
-void		reset_dict(void);
-
-typedef struct
-{
-	bool		isend;			/* in: marks for lexize_info about text end is
-								 * reached */
-	bool		getnext;		/* out: dict wants next lexeme */
-	void	   *private;		/* internal dict state between calls with
-								 * getnext == true */
-}	DictSubState;
-
-/* simple parser of cfg string */
-typedef struct
-{
-	char	   *key;
-	char	   *value;
-}	Map;
-
-void		parse_cfgdict(text *in, Map ** m);
-
-/* return struct for any lexize function */
-typedef struct
-{
-	/*
-	 * number of variant of split word , for example Word 'fotballklubber'
-	 * (norwegian) has two varian to split: ( fotball, klubb ) and ( fot,
-	 * ball, klubb ). So, dictionary should return: nvariant lexeme 1
-	 * fotball 1	  klubb 2	   fot 2	  ball 2	  klubb
-	 */
-	uint16		nvariant;
-
-	uint16		flags;
-
-	/* C-string */
-	char	   *lexeme;
-}	TSLexeme;
-
-#define TSL_ADDPOS		0x01
-
-
-/*
- * Lexize subsystem
- */
-
-typedef struct ParsedLex
-{
-	int			type;
-	char	   *lemm;
-	int			lenlemm;
-	bool		resfollow;
-	struct ParsedLex *next;
-}	ParsedLex;
-
-typedef struct ListParsedLex
-{
-	ParsedLex  *head;
-	ParsedLex  *tail;
-}	ListParsedLex;
-
-typedef struct
-{
-	TSCfgInfo  *cfg;
-	Oid			curDictId;
-	int			posDict;
-	DictSubState dictState;
-	ParsedLex  *curSub;
-	ListParsedLex towork;		/* current list to work */
-	ListParsedLex waste;		/* list of lexemes that already lexized */
-
-	/*
-	 * fields to store last variant to lexize (basically, thesaurus or similar
-	 * to, which wants	several lexemes
-	 */
-
-	ParsedLex  *lastRes;
-	TSLexeme   *tmpRes;
-}	LexizeData;
-
-
-void		LexizeInit(LexizeData * ld, TSCfgInfo * cfg);
-void		LexizeAddLemm(LexizeData * ld, int type, char *lemm, int lenlemm);
-TSLexeme   *LexizeExec(LexizeData * ld, ParsedLex ** correspondLexem);
-
-#endif

contrib/tsearch2/dict_ex.c

-/* $PostgreSQL: pgsql/contrib/tsearch2/dict_ex.c,v 1.9 2006/11/20 14:03:30 teodor Exp $ */
-
-/*
- * example of dictionary
- * Teodor Sigaev <teodor@sigaev.ru>
- */
-#include "postgres.h"
-
-#include "dict.h"
-#include "common.h"
-#include "ts_locale.h"
-
-typedef struct
-{
-	StopList	stoplist;
-}	DictExample;
-
-
-PG_FUNCTION_INFO_V1(dex_init);
-Datum		dex_init(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(dex_lexize);
-Datum		dex_lexize(PG_FUNCTION_ARGS);
-
-Datum
-dex_init(PG_FUNCTION_ARGS)
-{
-	DictExample *d = (DictExample *) malloc(sizeof(DictExample));
-
-	if (!d)
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	memset(d, 0, sizeof(DictExample));
-
-	d->stoplist.wordop = lowerstr;
-
-	if (!PG_ARGISNULL(0) && PG_GETARG_POINTER(0) != NULL)
-	{
-		text	   *in = PG_GETARG_TEXT_P(0);
-
-		readstoplist(in, &(d->stoplist));
-		sortstoplist(&(d->stoplist));
-		PG_FREE_IF_COPY(in, 0);
-	}
-
-	PG_RETURN_POINTER(d);
-}
-
-Datum
-dex_lexize(PG_FUNCTION_ARGS)
-{
-	DictExample *d = (DictExample *) PG_GETARG_POINTER(0);
-	char	   *in = (char *) PG_GETARG_POINTER(1);
-	char	   *utxt = pnstrdup(in, PG_GETARG_INT32(2));
-	TSLexeme   *res = palloc(sizeof(TSLexeme) * 2);
-	char	   *txt = lowerstr(utxt);
-
-	pfree(utxt);
-	memset(res, 0, sizeof(TSLexeme) * 2);
-
-	if (*txt == '\0' || searchstoplist(&(d->stoplist), txt))
-	{
-		pfree(txt);
-	}
-	else
-		res[0].lexeme = txt;
-
-	PG_RETURN_POINTER(res);
-}

contrib/tsearch2/dict_ispell.c

-/* $PostgreSQL: pgsql/contrib/tsearch2/dict_ispell.c,v 1.10 2006/03/11 04:38:30 momjian Exp $ */
-
-/*
- * ISpell interface
- * Teodor Sigaev <teodor@sigaev.ru>
- */
-#include "postgres.h"
-
-#include <ctype.h>
-
-#include "dict.h"
-#include "common.h"
-#include "ispell/spell.h"
-#include "ts_locale.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;
-	TSLexeme   *res;
-	TSLexeme   *ptr,
-			   *cptr;
-
-	if (!PG_GETARG_INT32(2))
-		PG_RETURN_POINTER(NULL);
-
-	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->lexeme)
-	{
-		if (searchstoplist(&(d->stoplist), ptr->lexeme))
-		{
-			pfree(ptr->lexeme);
-			ptr->lexeme = NULL;
-			ptr++;
-		}
-		else
-		{
-			memcpy(cptr, ptr, sizeof(TSLexeme));
-			cptr++;
-			ptr++;
-		}
-	}
-	cptr->lexeme = NULL;
-
-	PG_RETURN_POINTER(res);
-}

contrib/tsearch2/dict_snowball.c

-/* $PostgreSQL: pgsql/contrib/tsearch2/dict_snowball.c,v 1.13 2006/11/20 14:03:30 teodor Exp $ */
-
-/*
- * example of Snowball dictionary
- * http://snowball.tartarus.org/
- * Teodor Sigaev <teodor@sigaev.ru>
- */
-#include "postgres.h"
-
-#include "dict.h"
-#include "common.h"
-#include "snowball/english_stem.h"
-#include "snowball/header.h"
-#include "snowball/russian_stem.h"
-#include "snowball/russian_stem_UTF8.h"
-#include "ts_locale.h"
-
-typedef struct
-{
-	struct SN_env *z;
-	StopList	stoplist;
-	int			(*stem) (struct SN_env * z);
-}	DictSnowball;
-
-
-PG_FUNCTION_INFO_V1(snb_en_init);
-Datum		snb_en_init(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(snb_ru_init_koi8);
-Datum		snb_ru_init_koi8(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(snb_ru_init_utf8);
-Datum		snb_ru_init_utf8(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(snb_lexize);
-Datum		snb_lexize(PG_FUNCTION_ARGS);
-
-Datum
-snb_en_init(PG_FUNCTION_ARGS)
-{
-	DictSnowball *d = (DictSnowball *) malloc(sizeof(DictSnowball));
-
-	if (!d)
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	memset(d, 0, sizeof(DictSnowball));
-	d->stoplist.wordop = lowerstr;
-
-	if (!PG_ARGISNULL(0) && PG_GETARG_POINTER(0) != NULL)
-	{
-		text	   *in = PG_GETARG_TEXT_P(0);
-
-		readstoplist(in, &(d->stoplist));
-		sortstoplist(&(d->stoplist));
-		PG_FREE_IF_COPY(in, 0);
-	}
-
-	d->z = english_ISO_8859_1_create_env();
-	if (!d->z)
-	{
-		freestoplist(&(d->stoplist));
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	}
-	d->stem = english_ISO_8859_1_stem;
-
-	PG_RETURN_POINTER(d);
-}
-
-Datum
-snb_ru_init_koi8(PG_FUNCTION_ARGS)
-{
-	DictSnowball *d = (DictSnowball *) malloc(sizeof(DictSnowball));
-
-	if (!d)
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	memset(d, 0, sizeof(DictSnowball));
-	d->stoplist.wordop = lowerstr;
-
-	if (!PG_ARGISNULL(0) && PG_GETARG_POINTER(0) != NULL)
-	{
-		text	   *in = PG_GETARG_TEXT_P(0);
-
-		readstoplist(in, &(d->stoplist));
-		sortstoplist(&(d->stoplist));
-		PG_FREE_IF_COPY(in, 0);
-	}
-
-	d->z = russian_KOI8_R_create_env();
-	if (!d->z)
-	{
-		freestoplist(&(d->stoplist));
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	}
-	d->stem = russian_KOI8_R_stem;
-
-	PG_RETURN_POINTER(d);
-}
-
-Datum
-snb_ru_init_utf8(PG_FUNCTION_ARGS)
-{
-	DictSnowball *d = (DictSnowball *) malloc(sizeof(DictSnowball));
-
-	if (!d)
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	memset(d, 0, sizeof(DictSnowball));
-	d->stoplist.wordop = lowerstr;
-
-	if (!PG_ARGISNULL(0) && PG_GETARG_POINTER(0) != NULL)
-	{
-		text	   *in = PG_GETARG_TEXT_P(0);
-
-		readstoplist(in, &(d->stoplist));
-		sortstoplist(&(d->stoplist));
-		PG_FREE_IF_COPY(in, 0);
-	}
-
-	d->z = russian_UTF_8_create_env();
-	if (!d->z)
-	{
-		freestoplist(&(d->stoplist));
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	}
-	d->stem = russian_UTF_8_stem;
-
-	PG_RETURN_POINTER(d);
-}
-
-Datum
-snb_lexize(PG_FUNCTION_ARGS)
-{
-	DictSnowball *d = (DictSnowball *) PG_GETARG_POINTER(0);
-	char	   *in = (char *) PG_GETARG_POINTER(1);
-	char	   *utxt = pnstrdup(in, PG_GETARG_INT32(2));
-	TSLexeme   *res = palloc(sizeof(TSLexeme) * 2);
-	char	   *txt = lowerstr(utxt);
-	
-	pfree(utxt);
-	memset(res, 0, sizeof(TSLexeme) * 2);
-	if (*txt == '\0' || searchstoplist(&(d->stoplist), txt))
-	{
-		pfree(txt);
-	}
-	else
-	{
-		SN_set_current(d->z, strlen(txt), (symbol *) txt);
-		(d->stem) (d->z);
-		if (d->z->p && d->z->l)
-		{
-			txt = repalloc(txt, d->z->l + 1);
-			memcpy(txt, d->z->p, d->z->l);
-			txt[d->z->l] = '\0';
-		}
-		res->lexeme = txt;
-	}
-
-	PG_RETURN_POINTER(res);
-}

contrib/tsearch2/dict_syn.c

-/* $PostgreSQL: pgsql/contrib/tsearch2/dict_syn.c,v 1.14 2007/03/28 01:28:34 tgl Exp $ */
-
-/*
- * ISpell interface
- * Teodor Sigaev <teodor@sigaev.ru>
- */
-#include "postgres.h"
-
-#include <ctype.h>
-
-#include "dict.h"
-#include "common.h"
-#include "ts_locale.h"
-
-#define SYNBUFLEN	4096
-typedef struct
-{
-	char	   *in;
-	char	   *out;
-}	Syn;
-
-typedef struct
-{
-	int			len;
-	Syn		   *syn;
-}	DictSyn;
-
-PG_FUNCTION_INFO_V1(syn_init);
-Datum		syn_init(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(syn_lexize);
-Datum		syn_lexize(PG_FUNCTION_ARGS);
-
-static char *
-findwrd(char *in, char **end)
-{
-	char	   *start;
-
-	*end = NULL;
-	while (*in && isspace((unsigned char) *in))
-		in++;
-
-	if (*in=='\0')
-		return NULL;
-	start = in;
-
-	while (*in && !isspace((unsigned char) *in))
-		in++;
-
-	*end = in;
-	return start;
-}
-
-static int
-compareSyn(const void *a, const void *b)
-{
-	return strcmp(((Syn *) a)->in, ((Syn *) b)->in);
-}
-
-
-Datum
-syn_init(PG_FUNCTION_ARGS)
-{
-	text	   *in;
-	DictSyn    *d;
-	int			cur = 0;
-	FILE	   *fin;
-	char	   *filename;
-	char		buf[SYNBUFLEN];
-	char	   *starti,
-			   *starto,
-			   *end = NULL;
-	int			slen;
-
-	if (PG_ARGISNULL(0) || PG_GETARG_POINTER(0) == NULL)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("NULL config")));
-
-	in = PG_GETARG_TEXT_P(0);
-	if (VARSIZE(in) - VARHDRSZ == 0)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-				 errmsg("VOID config")));
-
-	filename = text2char(in);
-	PG_FREE_IF_COPY(in, 0);
-	if ((fin = fopen(filename, "r")) == NULL)
-		ereport(ERROR,
-				(errcode_for_file_access(),
-				 errmsg("could not open file \"%s\": %m",
-						filename)));
-
-	d = (DictSyn *) malloc(sizeof(DictSyn));
-	if (!d)
-	{
-		fclose(fin);
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	}
-	memset(d, 0, sizeof(DictSyn));
-
-	while (fgets(buf, sizeof(buf), fin))
-	{
-		slen = strlen(buf);	
-		pg_verifymbstr(buf, slen, false);
-		if (cur == d->len)
-		{
-			d->len = (d->len) ? 2 * d->len : 16;
-			d->syn = (Syn *) realloc(d->syn, sizeof(Syn) * d->len);
-			if (!d->syn)
-			{
-				fclose(fin);
-				ereport(ERROR,
-						(errcode(ERRCODE_OUT_OF_MEMORY),
-						 errmsg("out of memory")));
-			}
-		}
-
-		starti = findwrd(buf, &end);
-		if (!starti)
-			continue;
-		*end = '\0';
-		if (end >= buf + slen)
-			continue;
-
-		starto = findwrd(end + 1, &end);
-		if (!starto)
-			continue;
-		*end = '\0';
-
-		d->syn[cur].in = strdup(lowerstr(starti));
-		d->syn[cur].out = strdup(lowerstr(starto));
-		if (!(d->syn[cur].in && d->syn[cur].out))
-		{
-			fclose(fin);
-			ereport(ERROR,
-					(errcode(ERRCODE_OUT_OF_MEMORY),
-					 errmsg("out of memory")));
-		}
-
-		cur++;
-	}
-
-	fclose(fin);
-
-	d->len = cur;
-	if (cur > 1)
-		qsort(d->syn, d->len, sizeof(Syn), compareSyn);
-
-	pfree(filename);
-	PG_RETURN_POINTER(d);
-}
-
-Datum
-syn_lexize(PG_FUNCTION_ARGS)
-{
-	DictSyn    *d = (DictSyn *) PG_GETARG_POINTER(0);
-	char	   *in = (char *) PG_GETARG_POINTER(1);
-	Syn			key,
-			   *found;
-	TSLexeme   *res = NULL;
-	char	   *wrd;
-
-	if (!PG_GETARG_INT32(2))
-		PG_RETURN_POINTER(NULL);
-
-	key.out = NULL;
-	wrd = pnstrdup(in, PG_GETARG_INT32(2));
-	key.in = lowerstr(wrd);
-	pfree(wrd);
-
-	found = (Syn *) bsearch(&key, d->syn, d->len, sizeof(Syn), compareSyn);
-	pfree(key.in);
-
-	if (!found)
-		PG_RETURN_POINTER(NULL);
-
-	res = palloc(sizeof(TSLexeme) * 2);
-	memset(res, 0, sizeof(TSLexeme) * 2);
-	res[0].lexeme = pstrdup(found->out);
-
-	PG_RETURN_POINTER(res);
-}

contrib/tsearch2/gendict/Makefile.IN

-subdir = contrib/CFG_DIR
-top_builddir = ../..
-include $(top_builddir)/src/Makefile.global
-
-MODULE_big = dict_CFG_MODNAME
-OBJS = CFG_OFILE
-DATA_built = dict_CFG_MODNAME.sql
-DOCS = README.CFG_MODNAME
-PG_CPPFLAGS =
-SHLIB_LINK = ../tsearch2/libtsearch2.a
-
-include $(top_srcdir)/contrib/contrib-global.mk

contrib/tsearch2/gendict/README.gendict

-Gendict - generate dictionary templates for contrib/tsearch2 module.
-
-This utility aims to help people creating dictionary for contrib/tsearch v2
-module. Particularly, it has built-in support for snowball stemmers.
-
-Programming API to tsearch2 dictionaries is described in tsearch v2 
-documentation.
-
-
-Prerequisities:
-
-* PostgreSQL 7.3 and above.
-
-* You need tsearch2 module sources already compiled
-
-* Rights to install contrib modules
-
-Usage:
-
-    run config.sh without parameters to see options and arguments
-
-Usage:
-./config.sh -n DICTNAME ( [ -s [ -p PREFIX ] ] | [ -c CFILES ] [ -h HFILES ] [ -i ] ) [ -v ] [ -d DIR ] [ -C COMMENT ]
-    -v - be verbose
-    -d DIR - name of directory in PGSQL_SRC/contrib (default dict_DICTNAME)
-    -C COMMENT - dictionary comment
-Generate Snowball stemmer:
-./config.sh -n DICTNAME -s [ -p PREFIX ] [ -v ] [ -d DIR ] [ -C COMMENT ]
-    -s - generate Snowball wrapper
-    -p - prefix of Snowball's function, (default DICTNAME)
-Generate template dictionary:
-./config.sh -n DICTNAME [ -c CFILES ] [ -h HFILES ] [ -i ] [ -v ] [ -d DIR ] [ -C COMMENT ]
-    -c CFILES - source files, must be placed in contrib/tsearch2/gendict directory.
-                These files will be used in Makefile.
-    -h HFILES - header files, must be placed in contrib/tsearch2/gendict directory.
-                These files will be used in Makefile and subinclude.h
-    -i - dictionary has init method
-
-
-Example 1:
-
-   Create Portuguese stemmer
- 
-   0. cd PGSQL_SRC/contrib/tsearch2/gendict
-
-   1. Obtain stem.{c,h} files for Portuguese
-
-      wget http://snowball.tartarus.org/portuguese/stem.c
-      wget http://snowball.tartarus.org/portuguese/stem.h
-   
-   2. Create template files for Portuguese
-
-      ./config.sh -n pt -s -p portuguese_ISO_8859_1 -v -C'Snowball stemmer for Portuguese'
-
-      Note, that argument for -p option should be *the same* as name of stemming
-      function in stem.c (without _stem)
-
-      A bunch of files will be generated and placed in PGSQL_SRC/contrib/dict_pt
-      directory.
-
-   3. Compile and install dictionary
-
-	cd PGSQL_SRC/contrib/dict_pt
-	make
-	make install
-
-   4. Test it 
-
-	Sample portuguese words with the stemmed forms are available
-        from http://snowball.tartarus.org/portuguese/stemmer.html
-
- 	createdb testdict
-	psql testdict < /usr/local/pgsql/share/contrib/tsearch2.sql
-	psql testdict < /usr/local/pgsql/share/contrib/dict_pt.sql
-	psql -d testdict -c "select lexize('pt','bobagem');"
-	 lexize  
-	---------
-	 {bobag}
-	(1 row)
-
-	Here is what I have in pg_ts_dict table
-
-	psql -d testdict -c "select * from pg_ts_dict where dict_name='pt';"
-	 dict_name |     dict_init      | dict_initoption |              dict_lexize              |          dict_comment           
-	-----------+--------------------+-----------------+---------------------------------------+---------------------------------
-	 pt        | dinit_pt(internal) |                 | snb_lexize(internal,internal,integer) | Snowball stemmer for Portuguese
-
-	(1 row)
-
- 
-        Note, that you have already installed dictionary and corresponding
-	entry in tsearch configuration and you may modify it using
-	plain SQL commands, for example, specify stop words.
-
-Example 2:
-
-      a) Simple template dictionary with init method 
-
-       ./config.sh -n wow -v -i -C WOW
-
-      b) Create simple template dict (without init method):
-	./config.sh -n wow -v  -C WOW
-
-        The same as above, but dictionary will have not init method
-
-       Dictionaries obtained in a) and b) are fully working and ready
-       for use: 
-	  a) lowercase input word and remove it if it is a stop word
-	  b) recognizes any word
-
-      c) Simple template dictionary with source files (with init method):
-
-       ./config.sh -n wow -v -i -c a.c -h a.h -C WOW
-
-        Source files ( a.c ) must be placed in contrib/tsearch2/gendict directory.
-        These files will be used in Makefile.
-
-        Header files ( a.h ), must be placed in contrib/tsearch2/gendict directory.
-        These files will be used in Makefile and subinclude.h
-
-      d) Simple template dictionary with source files (without init method):
-
-	./config.sh -n wow -v  -c a.c -h a.h -C WOW
-
-	The same as above, but dictionary will have not init method
-
-       After that you have sources in PGSQL_SRC/contrib/dict_wow and
-       you may edit them to create actual dictionary.
-
-  Please, check Tsearch2 home page (http://www.sai.msu.su/~megera/postgres/gist/tsearch/V2/)
-  for additional information about "Gendict tutorial" and dictionaries.

contrib/tsearch2/gendict/dict_snowball.c.IN

-/* $PostgreSQL: pgsql/contrib/tsearch2/gendict/dict_snowball.c.IN,v 1.5 2006/07/14 05:28:27 tgl Exp $ */
-
-/* 
- * example of Snowball dictionary
- * http://snowball.tartarus.org/ 
- * Teodor Sigaev <teodor@sigaev.ru>
- */
-#include "postgres.h"
-
-#include "dict.h"
-#include "common.h"
-#include "snowball/header.h"
-#include "subinclude.h"
-#include "ts_locale.h"
-
-typedef struct {
-	struct SN_env *z;
-	StopList	stoplist;
-	int	(*stem)(struct SN_env * z);
-} DictSnowball;
-
-
-PG_FUNCTION_INFO_V1(dinit_CFG_MODNAME);
-Datum dinit_CFG_MODNAME(PG_FUNCTION_ARGS);
-
-Datum 
-dinit_CFG_MODNAME(PG_FUNCTION_ARGS) {
-	DictSnowball	*d = (DictSnowball*)malloc( sizeof(DictSnowball) );
-
-	if ( !d )
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	memset(d,0,sizeof(DictSnowball));
-	d->stoplist.wordop=lowerstr;
-		
-	if ( !PG_ARGISNULL(0) && PG_GETARG_POINTER(0)!=NULL ) {
-		text       *in = PG_GETARG_TEXT_P(0);
-		readstoplist(in, &(d->stoplist));
-		sortstoplist(&(d->stoplist));
-		PG_FREE_IF_COPY(in, 0);
-	}
-
-	d->z = CFG_PREFIX_create_env();
-	if (!d->z) {
-		freestoplist(&(d->stoplist));
-		ereport(ERROR,
-				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("out of memory")));
-	}
-	d->stem=CFG_PREFIX_stem;
-
-	PG_RETURN_POINTER(d);
-}
-
-

contrib/tsearch2/gendict/sql.IN

-SET search_path = public;
-BEGIN;
-
-HASINIT create function dinit_CFG_MODNAME(internal)
-HASINIT         returns internal
-HASINIT         as 'MODULE_PATHNAME'
-HASINIT         language C;
-
-NOSNOWBALL create function dlexize_CFG_MODNAME(internal,internal,int4)
-NOSNOWBALL        returns internal
-NOSNOWBALL        as 'MODULE_PATHNAME'
-NOSNOWBALL        language C
-NOSNOWBALL        returns null on null input;
-
-insert into pg_ts_dict select
-        'CFG_MODNAME',
-HASINIT        (select oid from pg_proc where proname='dinit_CFG_MODNAME'),
-NOINIT        null,
-        null,
-ISSNOWBALL        (select oid from pg_proc where proname='snb_lexize'),
-NOSNOWBALL        (select oid from pg_proc where proname='dlexize_CFG_MODNAME'),
-        CFG_COMMENT
-;
-
-
-END;