Re: [gnumeric-list][PATCH - new version] handle unicode and codepagesfor Import/Export of Excel files

[gnumeric-list-admin gnome org]

It is too close to a release to try something like this.
I need more time to consider and test it.  Possibly after release.

On Tue, Mar 13, 2001 at 05:02:50PM +0400, gnumeric-list-admin gnome org wrote:
> @@ -587,12 +594,23 @@
>               ans->hidden = MS_BIFF_H_VISIBLE;
>               break;
>       }
> +#if 0
>       if (ver == MS_BIFF_V8) {
> -             int slen = MS_OLE_GET_GUINT16 (q->data + 6);
> +             int slen = MS_OLE_GET_GUINT16 (q->data + 6);            
>               ans->name = biff_get_text (q->data + 8, slen, NULL);
> -     } else {
> +     } else 
> +#endif
> +     { 
> +             /* 
> +              * there are test files produced by non-latin1 Excel (e.g. 
> +              * russian version) that prove that branch above is 
> +              * incorrect. It seems test files that insured author of branch
> +              * above were produced by latin1 version of Excel - 
> +              * in that case q->data[7] is always 0, so it can be attributed
> +              * to length of sheet name or to the string header.
> +              *                      - Vlad Harchev <hvv hippo ru>
> +              */
>               int slen = MS_OLE_GET_GUINT8 (q->data + 6);
> -
>               ans->name = biff_get_text (q->data + 7, slen, NULL);
>       }
This is one of the few areas that the XL file format docs are very
clear on.  I'll need to study this in more detail before it can go
in.
 
> +static char*
> +get_locale_charset_name()
> +{
> +#ifndef HAVE_ICONV
> +     return "";
> +#else
> +     static char* charset = NULL;
> +
> +     if (charset)
> +             return charset;
> +             
> +#ifdef _NL_CTYPE_CODESET_NAME
> +     charset = nl_langinfo (_NL_CTYPE_CODESET_NAME);
> +#elif defined(CODESET)
> +     charset = nl_langinfo (CODESET);
> +#elif
#else
> +     {
> +             char* locale = setlocale(LC_CTYPE,NULL);
> +             char* tmp = strchr(locale,'.');
> +             if (tmp)
> +                     charset = tmp+1;
> +     }
> +#endif  
> +     if (!charset)
> +             charset = "ISO-8859-1";
> +     charset = g_strdup(charset);
> +     return charset;
^^^^^
This seems like a recipe for problems.
Is the caller is responsible for freeing the string ?  What ensures
that the value will be valid ?  If that is the case then the
!HAVE_ICONV case will fail.
> +#endif
> +}

> +guint
> +excel_iconv_win_codepage()
> +{
> +     char* lang = NULL;
> +     static guint codepage = 0;
> +     char* env_lang;
> +     
> +     if (codepage)
> +             return codepage;
> +             
> +     /* the code below is executed only once */
If it is called only once why leak ?
> +     if (env_lang = getenv("WINDOWS_LANGUAGE"))
> +             lang = env_lang; /* just for flexibility */
> +     else {
> +             char* locale = setlocale(LC_CTYPE,NULL);
> +             char* lang_sep = strchr(locale,'_');
> +             if (lang_sep)
> +                     lang = g_strndup(locale,lang_sep-locale);
> +             else
> +                     lang = locale;
> +     }
> +     lang = g_strdup(lang);