Hi Moritz!
You wrote:
> > I'm not sure what is happening, because the h->from is explicitly malloced
> > in process_xover(), which is also the only place in the source (afaics)
> > where any Slrn_Header_Type is malloced.
> > So, the only thing I can think of is that slrn messes with the from field
> > somewhere lese in the code. I'll try looking into it later today...
>
> Turns out I was wrong with the double free idea:
[...]
> I'll dig further on sunday.
Could you try if the attached replacement for
debian/patches/302_fallback_charset.diff fixes the problem?
Thanks!
--
Kind regards,
+--------------------------------------------------------------------+
| Bas Zoetekouw | GPG key: 0644fab7 |
|----------------------------| Fingerprint: c1f5 f24c d514 3fec 8bf6 |
| [EMAIL PROTECTED] | a2b1 2bae e41f 0644 fab7 |
+--------------------------------------------------------------------+
#! /bin/sh -e
if [ $# -ne 1 ]; then
echo >&2 "`basename $0`: script expects -patch|-unpatch as argument"
exit 1
fi
case "$1" in
-patch) patch -f --no-backup-if-mismatch -p1 < $0;;
-unpatch) patch -f --no-backup-if-mismatch -R -p1 < $0;;
*)
echo >&2 "`basename $0`: script expects -patch|-unpatch as argument"
exit 1;;
esac
exit 0
@DPATCH@
diff -Naur eerst/slrn-0.9.8.1pl1/src/art.c slrn-0.9.8.1pl1/src/art.c
--- art.c.eerst 2007-02-10 15:24:40.418301661 +0100
+++ slrn-0.9.8.1pl1/src/art.c 2007-02-10 15:29:38.486194048 +0100
@@ -473,6 +473,9 @@
remove_from_hash_table (h);
slrn_free (h->tree_ptr);
slrn_free (h->subject);
+#ifdef USE_ICONV /* we've copied this string */
+ if (h->from_malloced != NULL) slrn_free (h->from_malloced);
+#endif
slrn_free (h->date);
slrn_free (h->realname);
slrn_free_additional_headers (h->add_hdrs);
@@ -5519,7 +5522,7 @@
static Slrn_Header_Type *process_xover (Slrn_XOver_Type *xov)
{
Slrn_Header_Type *h;
- unsigned char *c;
+ char *c;
h = (Slrn_Header_Type *) slrn_safe_malloc (sizeof (Slrn_Header_Type));
@@ -5527,9 +5530,33 @@
Number_Total++;
#ifdef USE_ICONV
- /* ok, some news client (Outlook Express *sigh*) just put unencoded
+
+ /* Annoyingly, h->from wasn't malloced separately, but is part of the same
+ * buffer as h->subject (ie free()ing h->subject will also delete the memory
+ * space used by h->from(). That sucks, so make a copy of from, to make
+ * sure we can freely mess with the strings as we see fit.
+ * NOTE: h->from is free()ed in free_header()
+ */
+ h->from_malloced = slrn_safe_strmalloc( h->from );
+ h->from = h->from_malloced;
+
+ /* ok, some news clients (Outlook Express *sigh*) just put unencoded
* latin1/9 chars in their headers. As we don't know any charset at
- * this time, replace those chars by '?' chars */
+ * this time, try to translating them using the (user-specified) default
+ * charset, or if the user didn't specify any, replace all non-ASCII
+ * chars by question marks
+ */
+
+ /* if the user specified a fallback charset */
+ if ( Slrn_Fallback_Input_Charset_Default == 0 )
+ {
+ slrn_chmap_translate_string(Slrn_Fallback_Input_Charset,
+ Slrn_Charset, &(h->subject));
+ slrn_chmap_translate_string(Slrn_Fallback_Input_Charset,
+ Slrn_Charset, &(h->from));
+ }
+ else /* no fallback charset specified, so replace all high chars by ? */
+ {
c = h->subject;
while (*c!='\0' && *c!=0x0a && *c!=0x0d)
{
@@ -5540,6 +5567,8 @@
{
if (*c>=0x7f) *c = '?'; c++;
}
+ }
+
#endif /* USE_ICONV */
#if SLRN_HAS_MIME
diff -Naur eerst/slrn-0.9.8.1pl1/src/art.h slrn-0.9.8.1pl1/src/art.h
--- art.h.eerst 2007-02-10 15:24:55.290425513 +0100
+++ slrn-0.9.8.1pl1/src/art.h 2007-02-10 15:26:54.530374227 +0100
@@ -84,6 +84,11 @@
#endif /* NOT SLRNPULL_CODE */
+#ifdef USE_ICONV
+extern char *Slrn_Fallback_Input_Charset;
+extern short int Slrn_Fallback_Input_Charset_Default;
+#endif
+
typedef struct Slrn_Header_Line_Type
{
char *name;
@@ -123,6 +128,9 @@
int bytes;
char *subject; /* malloced separately */
char *from;
+#ifdef USE_ICONV
+ char *from_malloced; /* malloced */
+#endif
char *date; /* malloced */
char *msgid; /* pointers to above space */
char *refs;
diff -Naur eerst/slrn-0.9.8.1pl1/src/chmap.c slrn-0.9.8.1pl1/src/chmap.c
--- eerst/slrn-0.9.8.1pl1/src/chmap.c 2007-01-15 18:54:23.798361500 +0100
+++ slrn-0.9.8.1pl1/src/chmap.c 2007-01-15 19:01:51.939060247 +0100
@@ -75,6 +75,11 @@
#ifdef USE_ICONV
+/* the user-specified fallback charset */
+char *Slrn_Fallback_Input_Charset = NULL;
+/* is set to a true value if the user didn't specify an override fallback */
+short int Slrn_Fallback_Input_Charset_Default = 0;
+
const iconv_t ICONV_FAIL = (iconv_t) -1;
/* translate the string *str_ptr from charset cs_from to charset cs_to */
@@ -92,7 +97,7 @@
/* make sure the charsets are initialized */
- if (cs_from == NULL) cs_from = ICONV_DEFAULT_CHARSET;
+ if (cs_from == NULL) cs_from = Slrn_Fallback_Input_Charset;
if (cs_to == NULL) return *str_ptr;
/* don't translate if from and to charsets are equal */
@@ -258,7 +263,7 @@
#ifdef USE_ICONV
/* check if we need to translate */
if (a->charset == NULL)
- charset = ICONV_DEFAULT_CHARSET;
+ charset = Slrn_Fallback_Input_Charset;
else
charset = a->charset;
@@ -399,6 +404,22 @@
#if USE_ICONV
iconv_t cd;
+ /* first set the fallback input charset to ASCII if the user hasn't
+ * specified it */
+ if ( Slrn_Fallback_Input_Charset != NULL
+ && *Slrn_Fallback_Input_Charset == '\0' )
+ {
+ free( Slrn_Fallback_Input_Charset );
+ }
+ if ( Slrn_Fallback_Input_Charset == NULL )
+ {
+ Slrn_Fallback_Input_Charset = malloc( 9 );
+ strncpy( Slrn_Fallback_Input_Charset, "US-ASCII", 9 );
+ Slrn_Fallback_Input_Charset_Default = 1;
+ }
+
+ /* the rest of this function deals with the _output_ charset */
+
/* use environenment for locale */
setlocale (LC_ALL, "");
diff -Naur eerst/slrn-0.9.8.1pl1/src/chmap.h slrn-0.9.8.1pl1/src/chmap.h
--- eerst/slrn-0.9.8.1pl1/src/chmap.h 2007-01-15 18:54:23.798361500 +0100
+++ slrn-0.9.8.1pl1/src/chmap.h 2007-01-15 18:50:00.857329255 +0100
@@ -26,13 +26,12 @@
# undef USE_ICONV
#endif
-#define ICONV_DEFAULT_CHARSET "iso-8859-15"
-
extern int slrn_set_charset (char *);
extern int slrn_chmap_fix_file (char *, int);
#ifdef USE_ICONV
extern char * slrn_chmap_translate_string (
char *, char *, char **);
+extern char *Slrn_Fallback_Input_Charset;
#endif
extern void slrn_chmap_fix_body (Slrn_Article_Type *, int);
extern void slrn_chmap_fix_header (Slrn_Header_Type *);
diff -Naur eerst/slrn-0.9.8.1pl1/src/mime.c slrn-0.9.8.1pl1/src/mime.c
--- eerst/slrn-0.9.8.1pl1/src/mime.c 2007-01-15 18:54:23.831356987 +0100
+++ slrn-0.9.8.1pl1/src/mime.c 2007-01-15 18:49:38.805345750 +0100
@@ -734,7 +734,7 @@
/* make sure we have a charset available */
if (a->charset==NULL)
{
- a->charset = slrn_safe_strmalloc(ICONV_DEFAULT_CHARSET);
+ a->charset = slrn_safe_strmalloc(Slrn_Fallback_Input_Charset);
}
#endif /* USE_ICONV */
diff -Naur eerst/slrn-0.9.8.1pl1/src/stamp-h1 slrn-0.9.8.1pl1/src/stamp-h1
--- eerst/slrn-0.9.8.1pl1/src/stamp-h1 1970-01-01 01:00:00.000000000 +0100
+++ slrn-0.9.8.1pl1/src/stamp-h1 2007-01-15 18:51:41.310588234 +0100
@@ -0,0 +1 @@
+timestamp for src/config.h
diff -Naur eerst/slrn-0.9.8.1pl1/src/startup.c slrn-0.9.8.1pl1/src/startup.c
--- eerst/slrn-0.9.8.1pl1/src/startup.c 2007-01-15 18:54:23.864352473 +0100
+++ slrn-0.9.8.1pl1/src/startup.c 2007-01-12 22:16:05.556850947 +0100
@@ -699,7 +699,9 @@
},
#if SLRN_HAS_MIME
-# ifndef USE_ICONV /* this is fetched from the current locale */
+# ifdef USE_ICONV
+ {"fallback_charset", &Slrn_Fallback_Input_Charset},
+#else
{"mime_charset", &Slrn_Mime_Display_Charset},
# endif /* USE_ICONV */
{"metamail_command", &Slrn_MetaMail_Cmd},
