From 9e9c077c6e4192153d095aa13457015b9b0cf538 Mon Sep 17 00:00:00 2001
From: Vreixo Formoso <metalpain2002@yahoo.es>
Date: Sat, 22 Dec 2007 19:44:02 +0100
Subject: [PATCH] Minimize charset conversion errors, ignoring when we can't do
 better.

If a file name is encoded in a different encoding than default input, current
implementation make image generation to be cancelled. As this can happen quite
frequent, due to files from discs or Windows partitions incorrectly mounted,
the best we can do is just ignore this, replacing the wrong character with a
'_'.
---
 src/ecma119_tree.c |  1 +
 src/util.c         | 32 +++++++++++++++++++++++---------
 2 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/src/ecma119_tree.c b/src/ecma119_tree.c
index 07658d8..ea479e5 100644
--- a/src/ecma119_tree.c
+++ b/src/ecma119_tree.c
@@ -34,6 +34,7 @@ int get_iso_name(Ecma119Image *img, IsoNode *iso, char **name)
     // TODO add support for other input charset
     ret = str2ascii("UTF-8", iso->name, &ascii_name);
     if (ret < 0) {
+        iso_msg_debug(img->image, "Can't convert %s", iso->name);
         return ret;
     }
 
diff --git a/src/util.c b/src/util.c
index f4cb9ea..1d8b96c 100644
--- a/src/util.c
+++ b/src/util.c
@@ -68,20 +68,34 @@ int str2wchar(const char *icharset, const char *input, wchar_t **output)
     n = iconv(conv, &src, &inbytes, &ret, &outbytes);
     while (n == -1) {
         
-        if( errno != EINVAL ) {
+        if (errno == E2BIG) {
             /* error, should never occur */
             iconv_close(conv);
             free(wstr);
             return ISO_CHARSET_CONV_ERROR;
-        }
+        } else {
+            wchar_t *wret;
             
-        /* invalid input string charset, just ignore */
-        /* printf("String %s is not encoded in %s\n", str, codeset); */
-        inbytes--;
-
-        if (!inbytes)
-            break;
-        n = iconv(conv, &src, &inbytes, &ret, &outbytes);
+            /* 
+             * Invalid input string charset.
+             * This can happen if input is in fact encoded in a charset 
+             * different than icharset.
+             * We can't do anything better than replace by "_" and continue.
+             */
+            /* TODO we need a way to report this */
+            /* printf("String %s is not encoded in %s\n", str, codeset); */
+            inbytes--;
+            src++;
+            
+            wret = (wchar_t*) ret;
+            *wret++ = (wchar_t) '_';
+            ret = (char *) wret;
+            outbytes -= sizeof(wchar_t);
+
+            if (!inbytes)
+                break;
+            n = iconv(conv, &src, &inbytes, &ret, &outbytes);
+        }
     }
     iconv_close(conv);