diff options
author | Jeffrey Stedfast <fejj@ximian.com> | 2001-07-20 08:08:50 +0800 |
---|---|---|
committer | Jeffrey Stedfast <fejj@src.gnome.org> | 2001-07-20 08:08:50 +0800 |
commit | 25ea76f3a782b2cd0a9ed65216203b7d7472ef57 (patch) | |
tree | b9fbdc13ea42b51c99ec31c54b883c78eaff132d /camel/camel-mime-utils.c | |
parent | 0ce3b207745b7094c31a4713f8bc08cbe926b425 (diff) | |
download | gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.tar gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.tar.gz gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.tar.bz2 gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.tar.lz gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.tar.xz gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.tar.zst gsoc2013-evolution-25ea76f3a782b2cd0a9ed65216203b7d7472ef57.zip |
Convert to the iconv-friendly charset names.
2001-07-19 Jeffrey Stedfast <fejj@ximian.com>
* camel-mime-filter-charset.c
(camel_mime_filter_charset_new_convert): Convert to the
iconv-friendly charset names.
* providers/imap/camel-imap-store.c (create_folder): Fixed a
compiler warning about returning without a value in a non-void
function. Blah.
* camel-mime-part.c (process_header): Pass the locale charset as
the default_charset to header_decode_string().
* camel-folder-summary.c (camel_folder_summary_format_string):
Pass the locale charset as the default_charset to
header_decode_string().
(content_info_new): Same.
* camel-mime-message.c (process_header): Pass the locale charset
as the default_charset to header_decode_string().
* camel-mime-utils.c (append_8bit): New helper function who's
purpose is similar to append_latin1() but for 8bit text that we
are assuming is not latin1.
(header_decode_text): Now takes a default_charset parameter and
calls append_8bit when appropriate.
(header_decode_string): Also takes a default_charset parameter
now.
(header_decode_mailbox): Pass NULL as the default_charset to
header_decode_string().
svn path=/trunk/; revision=11250
Diffstat (limited to 'camel/camel-mime-utils.c')
-rw-r--r-- | camel/camel-mime-utils.c | 122 |
1 files changed, 64 insertions, 58 deletions
diff --git a/camel/camel-mime-utils.c b/camel/camel-mime-utils.c index ba704b19dc..594c1de05e 100644 --- a/camel/camel-mime-utils.c +++ b/camel/camel-mime-utils.c @@ -1004,32 +1004,63 @@ g_string_append_len(GString *st, const char *s, int l) according to the rfc's. Anyway, since the conversion to utf-8 is trivial, just do it here without iconv */ static GString * -append_latin1(GString *out, const char *in, int len) +append_latin1 (GString *out, const char *in, int len) { unsigned int c; - + while (len) { c = (unsigned int)*in++; len--; if (c & 0x80) { - out = g_string_append_c(out, 0xc0 | ((c>>6) & 0x3)); /* 110000xx */ - out = g_string_append_c(out, 0x80 | (c&0x3f)); /* 10xxxxxx */ + out = g_string_append_c (out, 0xc0 | ((c >> 6) & 0x3)); /* 110000xx */ + out = g_string_append_c (out, 0x80 | (c & 0x3f)); /* 10xxxxxx */ } else { - out = g_string_append_c(out, c); + out = g_string_append_c (out, c); } } return out; } +static void +append_8bit (GString *out, const char *inbuf, int inlen, const char *default_charset) +{ + char *outbase, *outbuf; + int outlen; + iconv_t ic; + + ic = iconv_open ("UTF-8", default_charset); + if (ic != (iconv_t) -1) { + int ret; + + outlen = inlen * 6 + 16; + outbuf = outbase = g_malloc (outlen); + + ret = iconv (ic, &inbuf, &inlen, &outbuf, &outlen); + if (ret >= 0) { + iconv (ic, NULL, 0, &outbuf, &outlen); + *outbuf = '\0'; + } + + iconv_close (ic); + + /* FIXME: is outlen == strlen (outbuf) ?? */ + g_string_append_len (out, outbase, strlen (outbase)); + } else { + /* bah, completely broken...just append as raw text */ + g_string_append_len (out, inbuf, inlen); + } +} + /* decodes a simple text, rfc822 */ static char * -header_decode_text (const char *in, int inlen) +header_decode_text (const char *in, int inlen, const char *default_charset) { GString *out; char *inptr, *inend, *start, *word_start; char *decoded; gboolean wasdword = FALSE; gboolean wasspace = FALSE; + gboolean islatin1 = FALSE; out = g_string_new (""); start = inptr = (char *) in; @@ -1056,8 +1087,12 @@ header_decode_text (const char *in, int inlen) g_string_append (out, dword); g_free (dword); wasdword = TRUE; + } else if (islatin1 || !default_charset) { + /* append_latin1 is safe for 7bit ascii too */ + append_latin1 (out, start, inptr - start - 1); + wasdword = FALSE; } else { - out = append_latin1 (out, start, inptr - start - 1); + append_8bit (out, start, inptr - start - 1, default_charset); wasdword = FALSE; } @@ -1068,6 +1103,11 @@ header_decode_text (const char *in, int inlen) wasspace = FALSE; if (!word_start) word_start = inptr - 1; + + if (c & 0x80 || c <= 127) + islatin1 = TRUE; + else + islatin1 = FALSE; } } @@ -1087,8 +1127,11 @@ header_decode_text (const char *in, int inlen) g_string_append (out, dword); g_free (dword); + } else if (islatin1 || !default_charset) { + /* append_latin1 is safe for 7bit ascii too */ + append_latin1 (out, start, inptr - start); } else { - out = append_latin1 (out, start, inptr - start); + append_8bit (out, start, inptr - start, default_charset); } } @@ -1098,49 +1141,12 @@ header_decode_text (const char *in, int inlen) return decoded; } -#if 0 /* This is broken */ - -/* so in what way is it broken? */ - -/* decodes a simple text, rfc822 */ -static char * -header_decode_text(const char *in, int inlen) -{ - GString *out; - const char *inptr = in; - const char *inend = in+inlen; - char *encstart, *encend; - char *decword; - - out = g_string_new(""); - while ( (encstart = strstr(inptr, "=?")) - && (encend = strstr(encstart+2, "?=")) ) { - - decword = rfc2047_decode_word(encstart, encend-encstart+2); - if (decword) { - out = g_string_append_len(out, inptr, encstart-inptr); - out = g_string_append_len(out, decword, strlen(decword)); - g_free (decword); - } else { - out = append_latin1(out, inptr, encend-inptr+2); - } - inptr = encend+2; - } - out = append_latin1(out, inptr, inend-inptr); - - encstart = out->str; - g_string_free(out, FALSE); - - return encstart; -} -#endif - char * -header_decode_string(const char *in) +header_decode_string (const char *in, const char *default_charset) { if (in == NULL) return NULL; - return header_decode_text(in, strlen(in)); + return header_decode_text (in, strlen (in), default_charset); } /* how long a sequence of pre-encoded words should be less than, to attempt to @@ -2248,13 +2254,13 @@ header_decode_mailbox(const char **in) header_decode_lwsp(&inptr); if (!(*inptr == '.' || *inptr == '@' || *inptr==',' || *inptr=='\0')) { /* ',' and '\0' required incase it is a simple address, no @ domain part (buggy writer) */ - name = g_string_new(""); + name = g_string_new (""); while (pre) { char *text, *last; /* perform internationalised decoding, and append */ - text = header_decode_string(pre); - name = g_string_append(name, text); + text = header_decode_string (pre, NULL); + g_string_append (name, text); last = pre; g_free(text); @@ -2362,19 +2368,19 @@ header_decode_mailbox(const char **in) if (comend > comstart) { d(printf(" looking at subset '%.*s'\n", comend-comstart, comstart)); - tmp = g_strndup(comstart, comend-comstart); - text = header_decode_string(tmp); - name = g_string_new(text); - g_free(tmp); - g_free(text); + tmp = g_strndup (comstart, comend-comstart); + text = header_decode_string (tmp, NULL); + name = g_string_new (text); + g_free (tmp); + g_free (text); } } } - + *in = inptr; - + if (addr->len > 0) { - address = header_address_new_name(name?name->str:"", addr->str); + address = header_address_new_name(name ? name->str : "", addr->str); } g_string_free(addr, TRUE); |