Changeset 3191

Timestamp:

12/23/07 18:14:00

Author:

pvanhoof

Message:

• • • • Ported a patch for the rfc2047 decoder from Jacky gtkdict at yahoo.com.cn
        

Files:

• trunk/ChangeLog (modified) (1 diff)
• trunk/libtinymail-camel/camel-lite/camel/camel-mime-utils.c (modified) (4 diffs)
• trunk/libtinymail-camel/camel-lite/libedataserver/e-iconv.c (modified) (1 diff)

trunk/ChangeLog

@@ -4 +4 @@
-        two libs are not going to be supported in Tinymail 1.0
-        * Improvements to the NAMESPACE, LIST and LSUB things
+        * Ported a patch for the rfc2047 decoder from Jacky gtkdict at yahoo.com.cn
-
-2007-12-22  Philip Van Hoof <pvanhoof@gnome.org>

trunk/libtinymail-camel/camel-lite/camel/camel-mime-utils.c

@@ -822 +822 @@
-}
-
+static void
+print_hex (unsigned char *data, size_t len)
+{
+        size_t i, x;
+        unsigned char *p = data;
+        char high, low;
+
+        x = 0;
+        printf ("%04u    ", x);
+        for (i = 0; i < len; i++) {
+                high = *p >> 4;
+                high = (high<10) ? high + '0' : high + 'a' - 10;
+
+                low = *p & 0x0f;
+                low = (low<10) ? low + '0' : low + 'a' - 10;
+
+                printf ("0x%c%c  ", high, low);
+
+                p++;
+                x++;
+                if (i % 8 == 7) {
+                        printf ("\n%04u    ", x);
+                }
+        }
+        printf ("\n");
+}
+
+static size_t
+conv_to_utf8 (const char *encname, char *in, size_t inlen, char *out, size_t outlen)
+{
+        char *charset, *inbuf, *outbuf;
+        iconv_t ic;
+        size_t inbuf_len, outbuf_len, ret;
+
+        charset = (char *) e_iconv_charset_name (encname);
+
+        ic = e_iconv_open ("UTF-8", charset);
+        if (ic == (iconv_t) -1) {
+                printf ("e_iconv_open() error\n");
+                return (size_t)-1;
+        }
+
+        inbuf = in;
+        inbuf_len = inlen;
+
+        outbuf = out;
+        outbuf_len = outlen;
+
+        ret = e_iconv (ic, (const char **) &inbuf, &inbuf_len, &outbuf, &outbuf_len);
+        if (ret == (size_t)-1) {
+                printf ("e_iconv() error! source charset is %s, target charset is %s\n", charset, "UTF-8");
+                printf ("converted %u bytes, but last %u bytes can't convert!!\n", inlen - inbuf_len, inbuf_len);
+                printf ("source data:\n");
+                print_hex (in, inlen);
+
+                *outbuf = '\0';
+                printf ("target string is \"%s\"\n", out);
+
+                return (size_t)-1;
+        }
+
+        ret = outlen - outbuf_len;
+        out[ret] = '\0';
+
+        e_iconv_close (ic);
+
+        return ret;
+}
+
-/* decode rfc 2047 encoded string segment */
+#define DECWORD_LEN 1024
+#define UTF8_DECWORD_LEN 2048
+
-static char *
-rfc2047_decode_word(const char *in, size_t len)
-{
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
-
-        d(printf("rfc2047: decoding '%.*s'\n", len, in));
-
+        prev_charset[0] = curr_charset[0] = '\0';
+
+        decword_ptr = decword;
+        utf8_decword_ptr = utf8_decword;
+
-        /* quick check to see if this could possibly be a real encoded word */
-
-
+
+
+
-                d(printf("invalid\n"));
-                return NULL;
-        }
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
-                inptr++;
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                case 'Q':
-
+
+
-                        break;
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
-                        break;
-                }
-                default:
-                        /* uhhh, unknown encoding type - probably an invalid encoded word string */
@@ -876 +1001 @@
-                d(printf("The encoded length = %d\n", inlen));
-                if (inlen > 0) {
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-}
-
@@ -1015 +1097 @@
-}
-
+typedef enum {
+        BEGIN,
+        BEGIN_SPACE,
+        NOENCODED_WORD,
+        ENCODED_WORD_CHARSET,
+        ENCODED_WORD_ENCODED_TEXT,
+        ENCODED_WORD_END,
+        ENCODED_WORD_END_SPACE,
+        END
+} StatsType;
+
-/* decodes a simple text, rfc822 + rfc2047 */
-static char *
@@ -1020 +1113 @@
-{
-        GString *out;
-const char *inptr, *inend, *start, *chunk, *locale_charset
-GString *(* append) (GString *, const char *, gssize)
+StatsType stats
+const char *inptr, *inend, *start, *locale_charset;
-        char *dword = NULL;
-        guint32 mask;
-
-        locale_charset = e_iconv_locale_charset ();
-
-        if (ctext) {
-                mask = (CAMEL_MIME_IS_SPECIAL | CAMEL_MIME_IS_SPACE | CAMEL_MIME_IS_CTRL);
-                append = append_quoted_pair;
-        } else {
-                mask = (CAMEL_MIME_IS_LWSP);
-                append = g_string_append_len;
-        }
-
-        out = g_string_new ("");
-        inptr = in;
-        inend = inptr + inlen;
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                        break;
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-        }
-

trunk/libtinymail-camel/camel-lite/libedataserver/e-iconv.c

@@ -144 +144 @@
-        { "5601",           "EUC-KR"     },
-        { "zh_TW-euc",      "EUC-TW"     },
-gb2312
+GBK
-        { "zh_TW-big5",     "BIG5"       },
-gb2312
+GBK
-        { "big5-0",         "BIG5"       },
-        { "big5.eten-0",    "BIG5"       },
-        { "big5hkscs-0",    "BIG5HKSCS"  },
-
-
-
+
+
+
+
-        { "gb18030-0",      "gb18030"    },
-        { "gbk-0",          "GBK"        },