static HTMLState html_read_line(HTMLParser *parser)
{
gchar buf[HTMLBUFSIZE];
gchar *conv_str;
gint index;
if (fgets(buf, sizeof(buf), parser->fp) == NULL) {
parser->state = HTML_EOF;
return HTML_EOF;
}
conv_str = conv_convert(parser->conv, buf);
if (!conv_str) {
index = parser->bufp - parser->buf->str;
conv_str = conv_utf8todisp(buf, NULL);
g_string_append(parser->buf, conv_str);
g_free(conv_str);
parser->bufp = parser->buf->str + index;
return HTML_CONV_FAILED;
}
index = parser->bufp - parser->buf->str;
g_string_append(parser->buf, conv_str);
g_free(conv_str);
parser->bufp = parser->buf->str + index;
return HTML_NORMAL;
}
static SC_HTMLState sc_html_read_line(SC_HTMLParser *parser)
{
gchar buf[SC_HTMLBUFSIZE];
gchar buf2[SC_HTMLBUFSIZE];
gint index;
if (parser->fp == NULL)
return SC_HTML_EOF;
if (fgets(buf, sizeof(buf), parser->fp) == NULL) {
parser->state = SC_HTML_EOF;
return SC_HTML_EOF;
}
if (conv_convert(parser->conv, buf2, sizeof(buf2), buf) < 0) {
index = parser->bufp - parser->buf->str;
conv_utf8todisp(buf2, sizeof(buf2), buf);
g_string_append(parser->buf, buf2);
parser->bufp = parser->buf->str + index;
return SC_HTML_CONV_FAILED;
}
index = parser->bufp - parser->buf->str;
g_string_append(parser->buf, buf2);
parser->bufp = parser->buf->str + index;
return SC_HTML_NORMAL;
}
static void source_window_append(SourceWindow *sourcewin, const gchar *str)
{
GtkTextView *text = GTK_TEXT_VIEW(sourcewin->text);
GtkTextBuffer *buffer = gtk_text_view_get_buffer(text);
GtkTextIter iter;
gchar *out;
gint len;
len = strlen(str) + 1;
Xalloca(out, len, return);
conv_utf8todisp(out, len, str);
gtk_text_buffer_get_iter_at_offset(buffer, &iter, -1);
gtk_text_buffer_insert(buffer, &iter, out, -1);
}
static SC_HTMLState sc_html_read_line(SC_HTMLParser *parser)
{
gchar buf[SC_HTMLBUFSIZE];
gchar buf2[SC_HTMLBUFSIZE*4];
gint index;
gint n;
if (parser->fp == NULL)
return SC_HTML_EOF;
n = claws_fread(buf, 1, sizeof(buf) - 1, parser->fp);
if (n == 0) {
parser->state = SC_HTML_EOF;
return SC_HTML_EOF;
} else
buf[n] = '\0';
if (conv_convert(parser->conv, buf2, sizeof(buf2), buf) < 0) {
index = parser->bufp - parser->buf->str;
conv_utf8todisp(buf2, sizeof(buf2), buf);
g_string_append(parser->buf, buf2);
parser->bufp = parser->buf->str + index;
return SC_HTML_CONV_FAILED;
}
index = parser->bufp - parser->buf->str;
g_string_append(parser->buf, buf2);
parser->bufp = parser->buf->str + index;
return SC_HTML_NORMAL;
}
gchar *unmime_header(const gchar *encoded_str, gboolean addr_field)
{
const gchar *p = encoded_str;
const gchar *eword_begin_p, *encoding_begin_p, *text_begin_p,
*eword_end_p;
gchar charset[32];
gchar encoding;
gchar *conv_str;
GString *outbuf;
gchar *out_str;
gsize out_len;
int in_quote = FALSE;
outbuf = g_string_sized_new(strlen(encoded_str) * 2);
while (*p != '\0') {
gchar *decoded_text = NULL;
const gchar *quote_p;
gint len;
eword_begin_p = strstr(p, ENCODED_WORD_BEGIN);
if (!eword_begin_p) {
g_string_append(outbuf, p);
break;
}
quote_p = p;
while ((quote_p = strchr(quote_p, '"')) != NULL) {
if (quote_p && quote_p < eword_begin_p) {
/* Found a quote before the encoded word. */
in_quote = !in_quote;
quote_p++;
}
if (quote_p >= eword_begin_p)
break;
}
encoding_begin_p = strchr(eword_begin_p + 2, '?');
if (!encoding_begin_p) {
g_string_append(outbuf, p);
break;
}
text_begin_p = strchr(encoding_begin_p + 1, '?');
if (!text_begin_p) {
g_string_append(outbuf, p);
break;
}
eword_end_p = strstr(text_begin_p + 1, ENCODED_WORD_END);
if (!eword_end_p) {
g_string_append(outbuf, p);
break;
}
if (p == encoded_str) {
g_string_append_len(outbuf, p, eword_begin_p - p);
p = eword_begin_p;
} else {
/* ignore spaces between encoded words */
const gchar *sp;
for (sp = p; sp < eword_begin_p; sp++) {
if (!g_ascii_isspace(*sp)) {
g_string_append_len
(outbuf, p, eword_begin_p - p);
p = eword_begin_p;
break;
}
}
}
len = MIN(sizeof(charset) - 1,
encoding_begin_p - (eword_begin_p + 2));
memcpy(charset, eword_begin_p + 2, len);
charset[len] = '\0';
encoding = g_ascii_toupper(*(encoding_begin_p + 1));
if (encoding == 'B') {
gchar *tmp;
tmp = g_strndup(text_begin_p + 1, eword_end_p - (text_begin_p + 1) + 1);
decoded_text = g_base64_decode(tmp, &out_len);
g_free(tmp);
} else if (encoding == 'Q') {
decoded_text = g_malloc
(eword_end_p - (text_begin_p + 1) + 1);
len = qp_decode_q_encoding
(decoded_text, text_begin_p + 1,
eword_end_p - (text_begin_p + 1));
} else {
g_string_append_len(outbuf, p, eword_end_p + 2 - p);
p = eword_end_p + 2;
continue;
}
/* An encoded word MUST not appear within a quoted string,
* so quoting that word after decoding should be safe.
* We check there are no quotes just to be sure. If there
* are, well, the comma won't pose a problem, probably.
*/
if (addr_field && strchr(decoded_text, ',') && !in_quote &&
!strchr(decoded_text, '"')) {
gchar *tmp = g_strdup_printf("\"%s\"", decoded_text);
g_free(decoded_text);
decoded_text = tmp;
}
/* convert to UTF-8 */
conv_str = conv_codeset_strdup(decoded_text, charset, NULL);
if (!conv_str || !g_utf8_validate(conv_str, -1, NULL)) {
g_free(conv_str);
conv_str = g_malloc(len + 1);
conv_utf8todisp(conv_str, len + 1, decoded_text);
}
g_string_append(outbuf, conv_str);
g_free(conv_str);
g_free(decoded_text);
p = eword_end_p + 2;
}
out_str = outbuf->str;
out_len = outbuf->len;
g_string_free(outbuf, FALSE);
return g_realloc(out_str, out_len + 1);
}
