X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=util%2Fcharmap.c;h=31642bcea4c4a67f445250ca0915105662cc7590;hb=cad3d9cf6b923f0bd0adb6731db88e3ff6bac80a;hp=a80bbffdf20940b66a01ca7ca2bc4d3d4685347a;hpb=b6d668f5407b24e0c9a05f5a3ee4fa4c93377c5c;p=idzebra-moved-to-github.git diff --git a/util/charmap.c b/util/charmap.c index a80bbff..31642bc 100644 --- a/util/charmap.c +++ b/util/charmap.c @@ -1,11 +1,26 @@ -/* - * Copyright (C) 1996-2002, Index Data - * All rights reserved. - * Sebastian Hammer, Adam Dickmeiss - * - * $Id: charmap.c,v 1.24 2002-07-26 14:43:09 adam Exp $ - * - */ +/* $Id: charmap.c,v 1.27 2003-01-13 10:53:16 oleg Exp $ + Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002 + Index Data Aps + +This file is part of the Zebra server. + +Zebra is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 2, or (at your option) any later +version. + +Zebra is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +You should have received a copy of the GNU General Public License +along with Zebra; see the file LICENSE.zebra. If not, write to the +Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA +02111-1307, USA. +*/ + + /* * Support module to handle character-conversions into and out of the @@ -16,17 +31,6 @@ #include #include -#if HAVE_ICONV_H -#include -#else -typedef int iconv_t; -static size_t iconv(iconv_t t, char **buf, size_t *inbytesleft, - char **outbuf, size_t *outbytesleft) -{ - return -1; -} -#endif - typedef unsigned ucs4_t; #include @@ -368,18 +372,18 @@ static void fun_add_qmap(const char *s, void *data, int num) logf (LOG_DEBUG, " %3d", (unsigned char) *s); } -static int scan_to_utf8 (iconv_t t, ucs4_t *from, size_t inlen, +static int scan_to_utf8 (yaz_iconv_t t, ucs4_t *from, size_t inlen, char *outbuf, size_t outbytesleft) { size_t inbytesleft = inlen * sizeof(ucs4_t); char *inbuf = (char*) from; size_t ret; - if (t == (iconv_t)(-1)) + if (t == 0) *outbuf++ = *from; /* ISO-8859-1 is OK here */ else { - ret = iconv (t, &inbuf, &inbytesleft, &outbuf, &outbytesleft); + ret = yaz_iconv (t, &inbuf, &inbytesleft, &outbuf, &outbytesleft); if (ret == (size_t) (-1)) { yaz_log (LOG_WARN|LOG_ERRNO, "bad unicode sequence"); @@ -391,7 +395,7 @@ static int scan_to_utf8 (iconv_t t, ucs4_t *from, size_t inlen, } static int scan_string(char *s_native, - iconv_t t_unicode, iconv_t t_utf8, + yaz_iconv_t t_unicode, yaz_iconv_t t_utf8, void (*fun)(const char *c, void *data, int num), void *data, int *num) { @@ -400,16 +404,17 @@ static int scan_string(char *s_native, ucs4_t arg[512]; ucs4_t *s0, *s = arg; ucs4_t c, begin, end; - size_t i, j; + size_t i; - if (t_unicode != (iconv_t)(-1)) + if (t_unicode != 0) { char *outbuf = (char *) arg; char *inbuf = s_native; size_t outbytesleft = sizeof(arg)-4; size_t inbytesleft = strlen(s_native); - size_t ret; - ret = iconv(t_unicode, &inbuf, &inbytesleft, &outbuf, &outbytesleft); + size_t ret; + ret = yaz_iconv(t_unicode, &inbuf, &inbytesleft, + &outbuf, &outbytesleft); if (ret == (size_t)(-1)) return -1; i = (outbuf - (char*) arg)/sizeof(ucs4_t); @@ -481,17 +486,16 @@ chrmaptab chrmaptab_create(const char *tabpath, const char *name, int map_only, int errors = 0; int argc, num = (int) *CHR_BASE, i; NMEM nmem; - iconv_t t_unicode = (iconv_t)(-1); - iconv_t t_utf8 = (iconv_t)(-1); + yaz_iconv_t t_unicode = 0; + yaz_iconv_t t_utf8 = 0; unsigned endian = 31; const char *ucs4_native = "UCS-4"; if (*(char*) &endian == 31) /* little endian? */ ucs4_native = "UCS-4LE"; -#if HAVE_ICONV_H - t_utf8 = iconv_open ("UTF-8", ucs4_native); -#endif + t_utf8 = yaz_iconv_open ("UTF-8", ucs4_native); + logf (LOG_DEBUG, "maptab %s open", name); if (!(f = yaz_fopen(tabpath, name, "r", tabroot))) { @@ -639,13 +643,25 @@ chrmaptab chrmaptab_create(const char *tabpath, const char *name, int map_only, } else if (!yaz_matchstr(argv[0], "encoding")) { -#if HAVE_ICONV_H - if (t_unicode != (iconv_t)(-1)) - iconv_close (t_unicode); - t_unicode = iconv_open (ucs4_native, argv[1]); -#else - logf (LOG_WARN, "Encoding ignored. iconv not installed"); -#endif + /* + * Fix me. When t_unicode==0 and use encoding directive in *.chr file the beheviour of the + * zebra need to comment next part of code. + */ + + /* + if (t_unicode != 0) + yaz_iconv_close (t_unicode); + t_unicode = yaz_iconv_open (ucs4_native, argv[1]); + */ + + /* + * Fix me. It is additional staff for conversion of characters from local encoding + * of *.chr file to UTF-8 (internal encoding). + * NOTE: The derective encoding must be first directive in *.chr file. + */ + if (t_utf8 != 0) + yaz_iconv_close(t_utf8); + t_utf8 = yaz_iconv_open ("UTF-8", argv[1]); } else { @@ -659,12 +675,10 @@ chrmaptab chrmaptab_create(const char *tabpath, const char *name, int map_only, res = 0; } logf (LOG_DEBUG, "maptab %s close %d errors", name, errors); -#if HAVE_ICONV_H - if (t_utf8 != (iconv_t)(-1)) - iconv_close(t_utf8); - if (t_unicode != (iconv_t)(-1)) - iconv_close(t_unicode); -#endif + if (t_utf8 != 0) + yaz_iconv_close(t_utf8); + if (t_unicode != 0) + yaz_iconv_close(t_unicode); return res; }