X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=util%2Fcharmap.c;h=31642bcea4c4a67f445250ca0915105662cc7590;hb=cad3d9cf6b923f0bd0adb6731db88e3ff6bac80a;hp=823fe6ad358872d7daf0da05c82e4d31adf24c4a;hpb=47ea1fc957c7b97bb30a26698f072109cae275e4;p=idzebra-moved-to-github.git

diff --git a/util/charmap.c b/util/charmap.c
index 823fe6a..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 1.23 2002-07-25 13:06:44 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 <string.h>
 #include <assert.h>
 
-#if HAVE_ICONV_H
-#include <iconv.h>
-#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 <yaz/yaz-util.h>
@@ -368,26 +372,21 @@ 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
     {
-        size_t i;
-        for (i = 0; i<inlen; i++)
-            yaz_log (LOG_LOG, "%08X", from[i]);
-        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");
-            for (i = 0; i<inlen; i++)
-                yaz_log (LOG_LOG, "%08X", from[i]);
             return -1;
         }
     }
@@ -396,7 +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)
 {
@@ -405,31 +404,27 @@ 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);
-        yaz_log (LOG_LOG, "to unicode");
     }
     else
     { 
         for (i = 0; s_native[i]; i++)
             arg[i] = s_native[i] & 255; /* ISO-8859-1 conversion */
-        yaz_log (LOG_LOG, "to virtual unicode");
     }
     arg[i] = 0;      /* terminate */
-    for (j = 0; j<i; j++)
-        yaz_log (LOG_LOG, " %d %8X %d %c", j, arg[j], arg[j],
-                 (arg[j] > 33 && arg[j] < 127) ? arg[j] : '?');
     if (s[0] == 0xfeff || s[0] == 0xfeff)  /* skip byte Order Mark */
         s++;
     while (*s)
@@ -491,17 +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)))
     {
@@ -649,13 +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
 	{
@@ -669,12 +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;
 }