[PATCH] charset

[Paul P Komkoff Jr]

attached
-- 
Paul P 'Stingray' Komkoff Jr // http://stingr.net/key <- my pgp key
 This message represents the official view of the voices in my head

Index: gateway.A9/configure.in
===================================================================
--- gateway.A9.orig/configure.in        2004-11-06 17:36:55.728060912 +0300
+++ gateway.A9/configure.in     2004-11-06 17:46:21.818002160 +0300
@@ -216,6 +216,18 @@
 ]
 )
 
+AC_MSG_CHECKING([whether to do all wapbox xml processing in utf-8])
+AC_ARG_ENABLE(scharset,
+[  --enable-scharset           do all wapbox xml processing in utf-8],
+[
+  if test "$enableval" != yes; then
+    AC_MSG_RESULT(no)
+  else
+    AC_MSG_RESULT(yes)
+    AC_DEFINE(NEW_CHARSETS, 1, [Simplify wapbox charset processing])
+  fi
+])
+
 dnl Extra feature checks
 
 dnl GW_HAVE_TYPE_FROM(HDRNAME, TYPE, HAVENAME, DESCRIPTION)
Index: gateway.A9/gw/wap-appl.c
===================================================================
--- gateway.A9.orig/gw/wap-appl.c       2004-11-06 17:41:37.645202992 +0300
+++ gateway.A9/gw/wap-appl.c    2004-11-06 17:46:21.819002008 +0300
@@ -718,6 +718,10 @@
  * to handle those charsets for all content types, just WML/XHTML. */
 static void add_charset_headers(List *headers) 
 {
+#ifdef NEW_CHARSETS
+    if (!http_charset_accepted(headers, "utf-8"))
+        http_header_add(headers, "Accept-Charset", "utf-8");
+#else
     long i, len;
     
     gw_assert(charsets != NULL);
@@ -727,6 +731,7 @@
         if (!http_charset_accepted(headers, charset))
             http_header_add(headers, "Accept-Charset", charset);
     }
+#endif
 }
 
 
@@ -1055,11 +1060,29 @@
             
             /* get charset used in content body, default to utf-8 if not 
present */
             if ((charset = find_charset_encoding(content.body)) == NULL)
+#ifdef NEW_CHARSETS
+                if (octstr_len(content.charset) > 0) {
+                    charset = octstr_duplicate(content.charset);
+                } else {
+                    charset = octstr_imm("UTF-8");
+                }
+#else
                 charset = octstr_imm("UTF-8"); 
+#endif
 
             /* convert to utf-8 if original charset is not utf-8 
              * and device supports it */
 
+#ifdef NEW_CHARSETS
+            if (octstr_case_compare(charset, octstr_imm("UTF-8")) != 0) {
+                debug("wsp",0,"Converting wml/xhtml from charset <%s> to 
UTF-8",
+                    octstr_get_cstr(charset));
+                if (charset_convert(content.body, octstr_get_cstr(charset), 
"UTF-8") >= 0) {
+                    octstr_destroy(content.charset);
+                    content.charset = octstr_create("UTF-8");
+                }
+            }
+#else
             if (octstr_case_compare(charset, octstr_imm("UTF-8")) < 0 &&
                 !http_charset_accepted(device_headers, 
octstr_get_cstr(charset))) {
                 if (!http_charset_accepted(device_headers, "UTF-8")) {
@@ -1097,6 +1120,7 @@
                     }
                 }
             }
+#endif
 
             octstr_destroy(charset);
         }