", 0, "'s Yahoo! Profile", 0, NULL, + gaim_markup_extract_info_field(url_text, buf, "<title>", 0, "'s Yahoo! Profile", 0, NULL, _("If you wish to view this profile, you will need to visit this link in your web browser"), 1, YAHOO_PROFILE_URL); strcat(buf, "</body></html>\n"); @@ -2439,7 +2438,7 @@ url_buffer = g_strdup(url_text); - /* strip_html() doesn't strip out character entities like and · + /* gaim_markup_strip_html() doesn't strip out character entities like and · */ while ((p = strstr(url_buffer, " ")) != NULL) { memmove(p, p + 6, strlen(p + 6)); @@ -2457,45 +2456,45 @@ } /* nuke the html, it's easier than trying to parse the horrid stuff */ - stripped = strip_html(url_buffer); + stripped = gaim_markup_strip_html(url_buffer); /* gonna re-use the memory we've already got for url_buffer */ strcpy(url_buffer, "<html><body>\n"); /* extract their Yahoo! ID and put it in */ - info_extract_field(stripped, url_buffer, "Yahoo! ID:", 2, "\n", 0, + gaim_markup_extract_info_field(stripped, url_buffer, "Yahoo! ID:", 2, "\n", 0, NULL, _("Yahoo! ID"), 0, NULL); /* extract their Email address and put it in */ - info_extract_field(stripped, url_buffer, "My Email", 5, "\n", 0, + gaim_markup_extract_info_field(stripped, url_buffer, "My Email", 5, "\n", 0, "Private", _("Email"), 0, NULL); /* extract the Nickname if it exists */ - info_extract_field(stripped, url_buffer, "Nickname:", 1, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Nickname:", 1, "\n", '\n', NULL, _("Nickname"), 0, NULL); /* extract their RealName and put it in */ - info_extract_field(stripped, url_buffer, "RealName:", 1, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "RealName:", 1, "\n", '\n', NULL, _("Realname"), 0, NULL); /* extract their Location and put it in */ - info_extract_field(stripped, url_buffer, "Location:", 2, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Location:", 2, "\n", '\n', NULL, _("Location"), 0, NULL); /* extract their Age and put it in */ - info_extract_field(stripped, url_buffer, "Age:", 3, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Age:", 3, "\n", '\n', NULL, _("Age"), 0, NULL); /* extract their MaritalStatus and put it in */ - info_extract_field(stripped, url_buffer, "MaritalStatus:", 3, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "MaritalStatus:", 3, "\n", '\n', "No Answer", _("Marital Status"), 0, NULL); /* extract their Gender and put it in */ - info_extract_field(stripped, url_buffer, "Gender:", 3, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Gender:", 3, "\n", '\n', "No Answer", _("Gender"), 0, NULL); /* extract their Occupation and put it in */ - info_extract_field(stripped, url_buffer, "Occupation:", 2, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Occupation:", 2, "\n", '\n', NULL, _("Occupation"), 0, NULL); /* Hobbies, Latest News, and Favorite Quote are a bit different, since the @@ -2505,24 +2504,24 @@ * looking for the 'Links' heading, which is the next thing to follow this * bunch. */ - if (!info_extract_field(stripped, url_buffer, "Hobbies:", 1, "Latest News", + if (!gaim_markup_extract_info_field(stripped, url_buffer, "Hobbies:", 1, "Latest News", '\n', NULL, _("Hobbies"), 0, NULL)) - if (!info_extract_field(stripped, url_buffer, "Hobbies:", 1, "Favorite Quote", + if (!gaim_markup_extract_info_field(stripped, url_buffer, "Hobbies:", 1, "Favorite Quote", '\n', NULL, _("Hobbies"), 0, NULL)) - info_extract_field(stripped, url_buffer, "Hobbies:", 1, "Links", + gaim_markup_extract_info_field(stripped, url_buffer, "Hobbies:", 1, "Links", '\n', NULL, _("Hobbies"), 0, NULL); - if (!info_extract_field(stripped, url_buffer, "Latest News:", 1, "Favorite Quote", + if (!gaim_markup_extract_info_field(stripped, url_buffer, "Latest News:", 1, "Favorite Quote", '\n', NULL, _("Latest News"), 0, NULL)) - info_extract_field(stripped, url_buffer, "Latest News:", 1, "Links", + gaim_markup_extract_info_field(stripped, url_buffer, "Latest News:", 1, "Links", '\n', NULL, _("Latest News"), 0, NULL); - info_extract_field(stripped, url_buffer, "Favorite Quote:", 0, "Links", + gaim_markup_extract_info_field(stripped, url_buffer, "Favorite Quote:", 0, "Links", '\n', NULL, _("Favorite Quote"), 0, NULL); /* Home Page will either be "No home page specified", * or "Home Page: " and a link. */ p = strstr(stripped, "No home page specified"); if (!p) - info_extract_field(stripped, url_buffer, "Home Page:", 1, " ", 0, NULL, + gaim_markup_extract_info_field(stripped, url_buffer, "Home Page:", 1, " ", 0, NULL, _("Home Page"), 1, NULL); /* Cool Link {1,2,3} is also different. If "No cool link specified" exists, @@ -2532,19 +2531,19 @@ */ p = strstr(stripped,"No cool link specified"); if (!p) - if (info_extract_field(stripped, url_buffer, "Cool Link 1:", 1, " ", 0, NULL, + if (gaim_markup_extract_info_field(stripped, url_buffer, "Cool Link 1:", 1, " ", 0, NULL, _("Cool Link 1"), 1, NULL)) - if (info_extract_field(stripped, url_buffer, "Cool Link 2:", 1, " ", 0, NULL, + if (gaim_markup_extract_info_field(stripped, url_buffer, "Cool Link 2:", 1, " ", 0, NULL, _("Cool Link 2"), 1, NULL)) - info_extract_field(stripped, url_buffer, "Cool Link 3:", 1, " ", 0, NULL, + gaim_markup_extract_info_field(stripped, url_buffer, "Cool Link 3:", 1, " ", 0, NULL, _("Cool Link 3"), 1, NULL); /* see if Member Since is there, and if so, extract it. */ - info_extract_field(stripped, url_buffer, "Member Since:", 1, "Last Updated:", + gaim_markup_extract_info_field(stripped, url_buffer, "Member Since:", 1, "Last Updated:", '\n', NULL, _("Member Since"), 0, NULL); /* extract the Last Updated date and put it in */ - info_extract_field(stripped, url_buffer, "Last Updated:", 1, "\n", '\n', NULL, + gaim_markup_extract_info_field(stripped, url_buffer, "Last Updated:", 1, "\n", '\n', NULL, _("Last Updated"), 0, NULL); /* finish off the html */ diff -r 2343c3aa1dec -r c8bf2da398e3 src/util.c --- a/src/util.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/util.c Wed Oct 01 03:43:18 2003 +0000 @@ -2,8 +2,9 @@ * @file util.h Utility Functions * @ingroup core * - * Copyright (C) 1998-1999, Mark Spencer <markster@marko.net> - * Copyright (C) 2003 Christian Hammond <chipx86@gnupdate.org> + * Copyright (C) 1998-1999 Mark Spencer <markster@marko.net> + * 2003 Christian Hammond <chipx86@gnupdate.org> + * 2003 Nathan Walp <faceprint@faceprint.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -1169,6 +1170,448 @@ } gboolean +gaim_markup_extract_info_field(const char *str, char *dest_buffer, + const char *start_token, int skip, + const char *end_token, char check_value, + const char *no_value_token, + const char *display_name, gboolean is_link, + const char *link_prefix) +{ + const char *p, *q; + char buf[1024]; + + g_return_val_if_fail(str != NULL, FALSE); + g_return_val_if_fail(dest_buffer != NULL, FALSE); + g_return_val_if_fail(start_token != NULL, FALSE); + g_return_val_if_fail(end_token != NULL, FALSE); + g_return_val_if_fail(display_name != NULL, FALSE); + + p = strstr(str, start_token); + + if (p == NULL) + return FALSE; + + p += strlen(start_token) + skip; + + if (check_value != '\0' && *p == check_value) + return FALSE; + + q = strstr(p, end_token); + + if (q != NULL && (!no_value_token || + (no_value_token && strncmp(p, no_value_token, + strlen(no_value_token))))) + { + strcat(dest_buffer, ""); + strcat(dest_buffer, display_name); + strcat(dest_buffer, ": "); + + if (is_link) + { + strcat(dest_buffer, " <a href=\""); + memcpy(buf, p, q - p); + buf[q - p] = '\0'; + + if (link_prefix) + strcat(dest_buffer, link_prefix); + + strcat(dest_buffer, buf); + strcat(dest_buffer, "\">"); + + if (link_prefix) + strcat(dest_buffer, link_prefix); + + strcat(dest_buffer, buf); + strcat(dest_buffer, "</a>"); + } + else + { + memcpy(buf, p, q - p); + buf[q - p] = '\0'; + strcat(dest_buffer, buf); + } + + strcat(dest_buffer, " \n"); + + return TRUE; + } + + return FALSE; +} + +struct gaim_parse_tag { + char *src_tag; + char *dest_tag; +}; + +#define ALLOW_TAG_ALT(x, y) if(!g_ascii_strncasecmp(c, "<" x " ", strlen("<" x " "))) { \ + const char *o = c + strlen("<" x); \ + const char *p = NULL, *q = NULL, *r = NULL; \ + GString *innards = g_string_new(""); \ + while(o && *o) { \ + if(!q && (*o == '\"' || *o == '\'') ) { \ + q = o; \ + } else if(q) { \ + if(*o == *q) { \ + char *unescaped = g_strndup(q+1, o-q-1); \ + char *escaped = g_markup_escape_text(unescaped, -1); \ + g_string_append_printf(innards, "%c%s%c", *q, escaped, *q); \ + g_free(unescaped); \ + g_free(escaped); \ + q = NULL; \ + } else if(*c == '\\') { \ + o++; \ + } \ + } else if(*o == '<') { \ + r = o; \ + } else if(*o == '>') { \ + p = o; \ + break; \ + } else { \ + innards = g_string_append_c(innards, *o); \ + } \ + o++; \ + } \ + if(p && !r) { \ + if(*(p-1) != '/') { \ + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); \ + pt->src_tag = x; \ + pt->dest_tag = y; \ + tags = g_list_prepend(tags, pt); \ + } \ + xhtml = g_string_append(xhtml, "<" y); \ + c += strlen("<" x ); \ + xhtml = g_string_append(xhtml, innards->str); \ + xhtml = g_string_append_c(xhtml, '>'); \ + c = p + 1; \ + } else { \ + xhtml = g_string_append(xhtml, "<"); \ + plain = g_string_append_c(plain, '<'); \ + c++; \ + } \ + g_string_free(innards, TRUE); \ + continue; \ + } \ + if(!g_ascii_strncasecmp(c, "<" x, strlen("<" x)) && \ + (*(c+strlen("<" x)) == '>' || \ + !g_ascii_strncasecmp(c+strlen("<" x), "/>", 2))) { \ + xhtml = g_string_append(xhtml, "<" y); \ + c += strlen("<" x); \ + if(*c != '/') { \ + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); \ + pt->src_tag = x; \ + pt->dest_tag = y; \ + tags = g_list_prepend(tags, pt); \ + xhtml = g_string_append_c(xhtml, '>'); \ + } else { \ + xhtml = g_string_append(xhtml, "/>");\ + } \ + c = strchr(c, '>') + 1; \ + continue; \ + } +#define ALLOW_TAG(x) ALLOW_TAG_ALT(x, x) +void +gaim_markup_html_to_xhtml(const char *html, char **xhtml_out, + char **plain_out) +{ + GString *xhtml = g_string_new(""); + GString *plain = g_string_new(""); + GList *tags = NULL, *tag; + const char *c = html; + + while(c && *c) { + if(*c == '<') { + if(*(c+1) == '/') { /* closing tag */ + tag = tags; + while(tag) { + struct gaim_parse_tag *pt = tag->data; + if(!g_ascii_strncasecmp((c+2), pt->src_tag, strlen(pt->src_tag)) && *(c+strlen(pt->src_tag)+2) == '>') { + c += strlen(pt->src_tag) + 3; + break; + } + tag = tag->next; + } + if(tag) { + while(tags) { + struct gaim_parse_tag *pt = tags->data; + g_string_append_printf(xhtml, "</%s>", pt->dest_tag); + if(tags == tag) + break; + tags = g_list_remove(tags, pt); + g_free(pt); + } + g_free(tag->data); + tags = g_list_remove(tags, tag->data); + } else { + /* we tried to close a tag we never opened! escape it + * and move on */ + xhtml = g_string_append(xhtml, "<"); + plain = g_string_append_c(plain, '<'); + c++; + } + } else { /* opening tag */ + ALLOW_TAG("a"); + ALLOW_TAG_ALT("b", "strong"); + ALLOW_TAG("blockquote"); + ALLOW_TAG_ALT("bold", "strong"); + ALLOW_TAG("cite"); + ALLOW_TAG("div"); + ALLOW_TAG("em"); + ALLOW_TAG("h1"); + ALLOW_TAG("h2"); + ALLOW_TAG("h3"); + ALLOW_TAG("h4"); + ALLOW_TAG("h5"); + ALLOW_TAG("h6"); + /* we only allow html to start the message */ + if(c == html) + ALLOW_TAG("html"); + ALLOW_TAG_ALT("i", "em"); + ALLOW_TAG_ALT("italic", "em"); + ALLOW_TAG("li"); + ALLOW_TAG("ol"); + ALLOW_TAG("p"); + ALLOW_TAG("pre"); + ALLOW_TAG("q"); + ALLOW_TAG("span"); + ALLOW_TAG("strong"); + ALLOW_TAG("ul"); + + /* we skip <HR> because it's not legal in XHTML-IM. However, + * we still want to send something sensible, so we put a + * linebreak in its place. also needs special handling + * because putting a to close it would just be dumb. */ + if((!g_ascii_strncasecmp(c, "<br", 3) + || !g_ascii_strncasecmp(c, "<hr", 3)) + && (*(c+3) == '>' || + !g_ascii_strncasecmp(c+3, "/>", 2) || + !g_ascii_strncasecmp(c+3, " />", 3))) { + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, " "); + if(*c != '\n') + plain = g_string_append_c(plain, '\n'); + continue; + } + if(!g_ascii_strncasecmp(c, "", 3) || !g_ascii_strncasecmp(c, "<underline>", strlen("<underline>"))) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = *(c+2) == '>' ? "u" : "underline"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "<s>", 3) || !g_ascii_strncasecmp(c, "<strike>", strlen("<strike>"))) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = *(c+2) == '>' ? "s" : "strike"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "", 5)) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = "sub"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "", 5)) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = "sup"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "<font", 5) && (*(c+5) == '>' || *(c+5) == ' ')) { + const char *p = c; + GString *style = g_string_new(""); + struct gaim_parse_tag *pt; + while(*p && *p != '>') { + if(!g_ascii_strncasecmp(p, "color=", strlen("color="))) { + const char *q = p + strlen("color="); + GString *color = g_string_new(""); + if(*q == '\'' || *q == '\"') + q++; + while(*q && *q != '\"' && *q != '\'' && *q != ' ') { + color = g_string_append_c(color, *q); + q++; + } + g_string_append_printf(style, "color: %s; ", color->str); + g_string_free(color, TRUE); + p = q; + } else if(!g_ascii_strncasecmp(p, "face=", strlen("face="))) { + const char *q = p + strlen("face="); + gboolean space_allowed = FALSE; + GString *face = g_string_new(""); + if(*q == '\'' || *q == '\"') { + space_allowed = TRUE; + q++; + } + while(*q && *q != '\"' && *q != '\'' && (space_allowed || *q != ' ')) { + face = g_string_append_c(face, *q); + q++; + } + g_string_append_printf(style, "font-family: %s; ", face->str); + g_string_free(face, TRUE); + p = q; + } else if(!g_ascii_strncasecmp(p, "size=", strlen("size="))) { + const char *q = p + strlen("size="); + int sz; + const char *size = "medium"; + if(*q == '\'' || *q == '\"') + q++; + sz = atoi(q); + if(sz < 3) + size = "smaller"; + else if(sz > 3) + size = "larger"; + g_string_append_printf(style, "font-size: %s; ", size); + p = q; + } + p++; + } + c = strchr(c, '>') + 1; + pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = "font"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + xhtml = g_string_append(xhtml, "<span"); + if(style->len) + g_string_append_printf(xhtml, " style='%s'", style->str); + xhtml = g_string_append_c(xhtml, '>'); + g_string_free(style, TRUE); + continue; + } + if(!g_ascii_strncasecmp(c, "<body ", 6)) { + const char *p = c; + gboolean did_something = FALSE; + while(*p && *p != '>') { + if(!g_ascii_strncasecmp(p, "bgcolor=", strlen("bgcolor="))) { + const char *q = p + strlen("bgcolor="); + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + GString *color = g_string_new(""); + if(*q == '\'' || *q == '\"') + q++; + while(*q && *q != '\"' && *q != '\'' && *q != ' ') { + color = g_string_append_c(color, *q); + q++; + } + g_string_append_printf(xhtml, "", color->str); + g_string_free(color, TRUE); + c = strchr(c, '>') + 1; + pt->src_tag = "body"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + did_something = TRUE; + break; + } + p++; + } + if(did_something) continue; + } + /* this has to come after the special case for bgcolor */ + ALLOW_TAG("body"); + if(!g_ascii_strncasecmp(c, ""); + if(p) { + xhtml = g_string_append(xhtml, "<!--"); + c += strlen("<!--"); + continue; + } + } + + xhtml = g_string_append(xhtml, "<"); + plain = g_string_append_c(plain, '<'); + c++; + } + } else { + xhtml = g_string_append_c(xhtml, *c); + plain = g_string_append_c(plain, *c); + c++; + } + } + tag = tags; + while(tag) { + g_string_append_printf(xhtml, "</%s>", (char *)tag->data); + tag = tag->next; + } + g_list_free(tags); + if(xhtml_out) + *xhtml_out = g_strdup(xhtml->str); + if(plain_out) + *plain_out = g_strdup(plain->str); + g_string_free(xhtml, TRUE); + g_string_free(plain, TRUE); +} + +char * +gaim_markup_strip_html(const char *str) +{ + int i, j, k; + gboolean visible = TRUE; + gchar *str2; + + g_return_val_if_fail(str != NULL, NULL); + + str2 = g_strdup(str); + + for (i = 0, j = 0; str2[i]; i++) + { + if (str2[i] == '<') + { + k = i + 1; + + if(g_ascii_isspace(str2[k])) + visible = TRUE; + else + { + while (str2[k]) + { + if (str2[k] == '<') + { + visible = TRUE; + break; + } + + if (str2[k] == '>') + { + visible = FALSE; + break; + } + + k++; + } + } + } + else if (str2[i] == '>' && !visible) + { + visible = TRUE; + continue; + } + + if (str2[i] == '&' && strncasecmp(str2 + i, """, 6) == 0) + { + str2[j++] = '\"'; + i = i + 5; + continue; + } + + if (visible) + str2[j++] = str2[i]; + } + + str2[j] = '\0'; + + return str2; +} + +gboolean gaim_url_parse(const char *url, char **ret_host, int *ret_port, char **ret_path) { diff -r 2343c3aa1dec -r c8bf2da398e3 src/util.h --- a/src/util.h Wed Oct 01 03:01:25 2003 +0000 +++ b/src/util.h Wed Oct 01 03:43:18 2003 +0000 @@ -350,6 +350,55 @@ GData **attributes); /** + * Extracts a field of data from HTML. + * + * This is a scary function. See protocols/msn/msn.c and + * protocols/yahoo/yahoo.c for example usage. + * + * @param str The string to parse. + * @param dest_buffer The destination buffer to append the new + * field info to. + * @param start_token The beginning token. + * @param skip The number of characters to skip after the + * start token. + * @param end_token The ending token. + * @param check_value The value that the last character must meet. + * @param no_value_token The token indicating no value is given. + * @param display_name The short descriptive name to display for this token. + * @param is_link TRUE if this should be a link, or FALSE otherwise. + * @param link_prefix The prefix for the link. + * + * @return TRUE if successful, or FALSE otherwise. + */ +gboolean gaim_markup_extract_info_field(const char *str, char *dest_buffer, + const char *start_token, int skip, + const char *end_token, + char check_value, + const char *no_value_token, + const char *display_name, + gboolean is_link, + const char *link_prefix); + +/** + * Converts HTML markup to XHTML. + * + * @param html The HTML markup. + * @param dest_xhtml The destination XHTML output. + * @param dest_plain The destination plain-text output. + */ +void gaim_markup_html_to_xhtml(const char *html, char **dest_xhtml, + char **dest_plain); + +/** + * Strips HTML tags from a string. + * + * @param str The string to strip HTML from. + * + * @return The new string without HTML. This must be freed. + */ +char *gaim_markup_strip_html(const char *str); + +/** * Parses a URL, returning its host, port, and file path. * * The returned data must be freed.

# HG changeset patch # User Christian Hammond # Date 1064979798 0 # Node ID c8bf2da398e3290f52ea284cf4ab83cb089ed281 # Parent 2343c3aa1decd0f3af372c0f6b435f853c644fe3 [gaim-migrate @ 7660] html.[ch] is gone. Everything inside was namespaced and put in util.[ch]. One less ugly part of gaim in the tree. committer: Tailor Script diff -r 2343c3aa1dec -r c8bf2da398e3 src/Makefile.am --- a/src/Makefile.am Wed Oct 01 03:01:25 2003 +0000 +++ b/src/Makefile.am Wed Oct 01 03:43:18 2003 +0000 @@ -64,8 +64,6 @@ debug.h \ ft.c \ ft.h \ - html.c \ - html.h \ imgstore.c \ imgstore.h \ md5.c \ diff -r 2343c3aa1dec -r c8bf2da398e3 src/gtkconv.c --- a/src/gtkconv.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/gtkconv.c Wed Oct 01 03:43:18 2003 +0000 @@ -33,7 +33,6 @@ #include #include "debug.h" -#include "html.h" #include "imgstore.h" #include "log.h" #include "multi.h" @@ -4388,7 +4387,7 @@ gtk_imhtml_append_text_with_images(GTK_IMHTML(gtkconv->imhtml), buf2, 0, images); if (gaim_prefs_get_bool("/gaim/gtk/logging/strip_html")) { - char *t1 = strip_html(buf); + char *t1 = gaim_markup_strip_html(buf); conv->history = g_string_append(conv->history, t1); conv->history = g_string_append(conv->history, "\n"); @@ -4406,7 +4405,7 @@ char nm[256]; if (gaim_prefs_get_bool("/gaim/gtk/logging/strip_html")) - t1 = strip_html(buf); + t1 = gaim_markup_strip_html(buf); else t1 = buf; @@ -4544,8 +4543,8 @@ if (gaim_prefs_get_bool("/gaim/gtk/logging/strip_html")) { char *t1, *t2; - t1 = strip_html(buf); - t2 = strip_html(new_message); + t1 = gaim_markup_strip_html(buf); + t2 = gaim_markup_strip_html(new_message); conv->history = g_string_append(conv->history, t1); conv->history = g_string_append(conv->history, t2); @@ -4581,8 +4580,8 @@ strncpy(nm, gaim_conversation_get_name(conv), sizeof(nm)); if (gaim_prefs_get_bool("/gaim/gtk/logging/strip_html")) { - t1 = strip_html(buf); - t2 = strip_html(with_font_tag); + t1 = gaim_markup_strip_html(buf); + t2 = gaim_markup_strip_html(with_font_tag); } else { t1 = html_logize(buf); diff -r 2343c3aa1dec -r c8bf2da398e3 src/gtkprefs.c --- a/src/gtkprefs.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/gtkprefs.c Wed Oct 01 03:43:18 2003 +0000 @@ -24,7 +24,6 @@ #include "gtkinternal.h" #include "debug.h" -#include "html.h" #include "notify.h" #include "prefs.h" #include "proxy.h" diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/jabber/jabber.c --- a/src/protocols/jabber/jabber.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/jabber/jabber.c Wed Oct 01 03:43:18 2003 +0000 @@ -34,13 +34,13 @@ #include "account.h" #include "accountopt.h" #include "debug.h" -#include "html.h" #include "message.h" #include "multi.h" #include "notify.h" #include "prpl.h" #include "request.h" #include "server.h" +#include "util.h" #include "auth.h" #include "buddy.h" @@ -777,7 +777,9 @@ } else if(jb && !GAIM_BUDDY_IS_ONLINE(b) && jb->error_msg) { ret = g_strdup(jb->error_msg); } else { - char *stripped = strip_html(jabber_buddy_get_status_msg(jb)); + char *stripped; + + stripped = gaim_markup_strip_html(jabber_buddy_get_status_msg(jb)); if(!stripped && b->uc & UC_UNAVAILABLE) stripped = g_strdup(jabber_get_state_string(b->uc)); @@ -802,7 +804,7 @@ char *text = NULL; if(jbr->status) { char *stripped; - stripped = strip_html(jbr->status); + stripped = gaim_markup_strip_html(jbr->status); text = g_markup_escape_text(stripped, -1); g_free(stripped); } diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/jabber/message.c --- a/src/protocols/jabber/message.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/jabber/message.c Wed Oct 01 03:43:18 2003 +0000 @@ -21,9 +21,9 @@ #include "internal.h" #include "debug.h" -#include "html.h" #include "notify.h" #include "server.h" +#include "util.h" #include "buddy.h" #include "chat.h" @@ -348,7 +348,7 @@ buf = g_strdup_printf("%s", msg); - html_to_xhtml(buf, &xhtml, &plain); + gaim_markup_html_to_xhtml(buf, &xhtml, &plain); g_free(buf); jm->body = plain; @@ -378,7 +378,7 @@ jm->type = JABBER_MESSAGE_CHAT; jm->to = g_strdup_printf("%s@%s", chat->room, chat->server); - html_to_xhtml(message, NULL, &jm->body); + gaim_markup_html_to_xhtml(message, NULL, &jm->body); jabber_message_send(jm); jabber_message_free(jm); diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/jabber/presence.c --- a/src/protocols/jabber/presence.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/jabber/presence.c Wed Oct 01 03:43:18 2003 +0000 @@ -21,10 +21,10 @@ #include "internal.h" #include "debug.h" -#include "html.h" #include "notify.h" #include "request.h" #include "server.h" +#include "util.h" #include "buddy.h" #include "chat.h" @@ -54,7 +54,7 @@ char *stripped = NULL; if(msg) { - html_to_xhtml(msg, NULL, &stripped); + gaim_markup_html_to_xhtml(msg, NULL, &stripped); } else { stripped = g_strdup(""); } diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/msn/msn.c --- a/src/protocols/msn/msn.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/msn/msn.c Wed Oct 01 03:43:18 2003 +0000 @@ -30,7 +30,7 @@ #include "state.h" #include "utils.h" #include "multi.h" -#include "html.h" +#include "util.h" #define BUDDY_ALIAS_MAXLEN 388 @@ -1236,7 +1236,7 @@ url_buffer = g_strdup(url_text); /* If they have a homepage link, MSN masks it such that we need to - * fetch the url out before strip_html() nukes it */ + * fetch the url out before gaim_markup_strip_html() nukes it */ if ((p = strstr(url_text, "Take a look at my \n"); /* Extract their Name and put it in */ - info_extract_field(stripped, url_buffer, "\tName", 0, "\t", '\n', - "Undisclosed", _("Name"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, "\tName", 0, "\t", + '\n', "Undisclosed", _("Name"), 0, NULL); /* Extract their Age and put it in */ - info_extract_field(stripped, url_buffer, "\tAge", 0, "\t", '\n', - "Undisclosed", _("Age"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, "\tAge", 0, "\t", + '\n', "Undisclosed", _("Age"), 0, NULL); /* Extract their Gender and put it in */ - info_extract_field(stripped, url_buffer, "\tGender", 6, "\t", '\n', - "Undisclosed", _("Gender"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, "\tGender", 6, "\t", + '\n', "Undisclosed", _("Gender"), 0, NULL); /* Extract their MaritalStatus and put it in */ - info_extract_field(stripped, url_buffer, "\tMaritalStatus", 0, "\t", '\n', - "Undisclosed", _("Marital Status"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, "\tMaritalStatus", + 0, "\t", '\n', "Undisclosed", + _("Marital Status"), 0, NULL); /* Extract their Location and put it in */ - info_extract_field(stripped, url_buffer, "\tLocation", 0, "\t", '\n', - "Undisclosed", _("Location"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, "\tLocation", 0, + "\t", '\n', "Undisclosed", _("Location"), + 0, NULL); /* Extract their Occupation and put it in */ - info_extract_field(stripped, url_buffer, "\t Occupation", 6, "\t", '\n', - "Undisclosed", _("Occupation"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, "\t Occupation", 6, + "\t", '\n', "Undisclosed", _("Occupation"), + 0, NULL); /* * The fields, 'A Little About Me', 'Favorite Things', 'Hobbies @@ -1316,102 +1319,99 @@ */ /* Check if they have A Little About Me */ - found = info_extract_field(stripped, url_buffer, "\tA Little About Me", - 1, "Favorite Things", '\n', NULL, - _("A Little About Me"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "\tA Little About Me", 1, "Favorite Things", '\n', NULL, + _("A Little About Me"), 0, NULL); if (!found) { - found = info_extract_field(stripped, url_buffer, - "\tA Little About Me", 1, - "Hobbies and Interests", '\n', NULL, - _("A Little About Me"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "\tA Little About Me", 1, "Hobbies and Interests", '\n', + NULL, _("A Little About Me"), 0, NULL); + } + + if (!found) + { + found = gaim_markup_extract_info_field(stripped, url_buffer, + "\tA Little About Me", 1, "Favorite Quote", '\n', NULL, + _("A Little About Me"), 0, NULL); } if (!found) { - found = info_extract_field(stripped, url_buffer, - "\tA Little About Me", 1, - "Favorite Quote", '\n', NULL, - _("A Little About Me"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "\tA Little About Me", 1, "My Homepage\tTake a look", '\n', + NULL, _("A Little About Me"), 0, NULL); } if (!found) { - found = info_extract_field(stripped, url_buffer, - "\tA Little About Me", 1, - "My Homepage\tTake a look", '\n', NULL, - _("A Little About Me"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, + "\tA Little About Me", 1, "last updated", '\n', NULL, + _("A Little About Me"), 0, NULL); + } + + /* Check if they have Favorite Things */ + found = gaim_markup_extract_info_field(stripped, url_buffer, + "Favorite Things", 1, "Hobbies and Interests", '\n', NULL, + _("Favorite Things"), 0, NULL); + + if (!found) + { + found = gaim_markup_extract_info_field(stripped, url_buffer, + "Favorite Things", 1, "Favorite Quote", '\n', NULL, + "Favorite Things", 0, NULL); } if (!found) { - info_extract_field(stripped, url_buffer, "\tA Little About Me", 1, - "last updated", '\n', - NULL, _("A Little About Me"), 0, NULL); - } - - /* Check if they have Favorite Things */ - found = info_extract_field(stripped, url_buffer, "Favorite Things", 1, - "Hobbies and Interests", '\n', NULL, - _("Favorite Things"), 0, NULL); - - if (!found) - { - found = info_extract_field(stripped, url_buffer, "Favorite Things", 1, - "Favorite Quote", '\n', NULL, - "Favorite Things", 0, NULL); - } - - if (!found) - { - found = info_extract_field(stripped, url_buffer, "Favorite Things", 1, - "My Homepage\tTake a look", '\n', NULL, - _("Favorite Things"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "Favorite Things", 1, "My Homepage\tTake a look", '\n', NULL, + _("Favorite Things"), 0, NULL); } if (!found) { - info_extract_field(stripped, url_buffer, "Favorite Things", 1, - "last updated", '\n', NULL, - _("Favorite Things"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, + "Favorite Things", 1, "last updated", '\n', NULL, + _("Favorite Things"), 0, NULL); } /* Check if they have Hobbies and Interests */ - found = info_extract_field(stripped, url_buffer, "Hobbies and Interests", - 1, "Favorite Quote", '\n', NULL, - _("Hobbies and Interests"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "Hobbies and Interests", 1, "Favorite Quote", '\n', NULL, + _("Hobbies and Interests"), 0, NULL); if (!found) { - found = info_extract_field(stripped, url_buffer, - "Hobbies and Interests", 1, - "My Homepage\tTake a look", '\n', NULL, - _("Hobbies and Interests"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "Hobbies and Interests", 1, "My Homepage\tTake a look", + '\n', NULL, _("Hobbies and Interests"), 0, NULL); } if (!found) { - info_extract_field(stripped, url_buffer, "Hobbies and Interests", - 1, "last updated", '\n', NULL, - _("Hobbies and Interests"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, + "Hobbies and Interests", 1, "last updated", '\n', NULL, + _("Hobbies and Interests"), 0, NULL); } /* Check if they have Favorite Quote */ - found = info_extract_field(stripped, url_buffer, "Favorite Quote", 1, - "My Homepage\tTake a look", '\n', NULL, - _("Favorite Quote"), 0, NULL); + found = gaim_markup_extract_info_field(stripped, url_buffer, + "Favorite Quote", 1, "My Homepage\tTake a look", '\n', NULL, + _("Favorite Quote"), 0, NULL); if (!found) { - info_extract_field(stripped, url_buffer, "Favorite Quote", 1, - "last updated", '\n', NULL, - _("Favorite Quote"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, + "Favorite Quote", 1, "last updated", '\n', NULL, + _("Favorite Quote"), 0, NULL); } /* Extract the last updated date and put it in */ - info_extract_field(stripped, url_buffer, "\tlast updated:", 1, "\n", '\n', - NULL, _("Last Updated"), 0, NULL); + gaim_markup_extract_info_field(stripped, url_buffer, + "\tlast updated:", 1, "\n", '\n', NULL, _("Last Updated"), + 0, NULL); /* If we were able to fetch a homepage url earlier, stick it in there */ if (user_url != NULL) diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/oscar/oscar.c --- a/src/protocols/oscar/oscar.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/oscar/oscar.c Wed Oct 01 03:43:18 2003 +0000 @@ -41,7 +41,6 @@ #include "proxy.h" #include "request.h" #include "util.h" -#include "html.h" #include "aim.h" #include "md5.h" @@ -5279,7 +5278,7 @@ if (strlen(buf) > c->maxlen) return -E2BIG; - buf2 = strip_html(buf); + buf2 = gaim_markup_strip_html(buf); if (strlen(buf2) > c->maxvis) { g_free(buf2); return -E2BIG; @@ -5418,7 +5417,7 @@ if (away_utf8 != NULL) { gchar *tmp1, *tmp2; tmp1 = gaim_strreplace(away_utf8, "
", "\n"); - tmp2 = strip_html(tmp1); + tmp2 = gaim_markup_strip_html(tmp1); g_free(tmp1); tmp1 = away_subs(tmp2, gaim_connection_get_display_name(gc)); g_free(tmp2); diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/toc/toc.c --- a/src/protocols/toc/toc.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/toc/toc.c Wed Oct 01 03:43:18 2003 +0000 @@ -30,7 +30,6 @@ #include "proxy.h" #include "request.h" #include "util.h" -#include "html.h" static GaimPlugin *my_protocol = NULL; diff -r 2343c3aa1dec -r c8bf2da398e3 src/protocols/yahoo/yahoo.c --- a/src/protocols/yahoo/yahoo.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/protocols/yahoo/yahoo.c Wed Oct 01 03:43:18 2003 +0000 @@ -33,7 +33,6 @@ #include "request.h" #include "server.h" #include "util.h" -#include "html.h" #include "sha.h" #include "yahoo.h" @@ -1919,7 +1918,7 @@ case YAHOO_STATUS_CUSTOM: if (!f->msg) return NULL; - stripped = strip_html(f->msg); + stripped = gaim_markup_strip_html(f->msg); if (stripped) { char *ret = g_markup_escape_text(stripped, strlen(stripped)); g_free(stripped); @@ -1953,7 +1952,7 @@ case YAHOO_STATUS_CUSTOM: if (!f->msg) return NULL; - status = strip_html(f->msg); + status = gaim_markup_strip_html(f->msg); break; default: status = g_strdup(yahoo_get_status_string(f->status)); @@ -2411,7 +2410,7 @@ p = strstr(url_text, "Adult Profiles Warning Message"); if (p) { strcpy(buf, _("Sorry, profiles marked as containing adult content are not supported at this time.

\n")); - info_extract_field(url_text, buf, ".idname=", 0, "%26", 0, NULL, + gaim_markup_extract_info_field(url_text, buf, ".idname=", 0, "%26", 0, NULL, _("If you wish to view this profile, you will need to visit this link in your web browser"), 1, YAHOO_PROFILE_URL); strcat(buf, "\n"); @@ -2428,7 +2427,7 @@ p = strstr(url_text, "Last Updated:"); if (!p) { strcpy(buf, _("Sorry, non-English profiles are not supported at this time.

\n")); - info_extract_field(url_text, buf, "", 0, "'s Yahoo! Profile", 0, NULL, + gaim_markup_extract_info_field(url_text, buf, "<title>", 0, "'s Yahoo! Profile", 0, NULL, _("If you wish to view this profile, you will need to visit this link in your web browser"), 1, YAHOO_PROFILE_URL); strcat(buf, "</body></html>\n"); @@ -2439,7 +2438,7 @@ url_buffer = g_strdup(url_text); - /* strip_html() doesn't strip out character entities like and · + /* gaim_markup_strip_html() doesn't strip out character entities like and · */ while ((p = strstr(url_buffer, " ")) != NULL) { memmove(p, p + 6, strlen(p + 6)); @@ -2457,45 +2456,45 @@ } /* nuke the html, it's easier than trying to parse the horrid stuff */ - stripped = strip_html(url_buffer); + stripped = gaim_markup_strip_html(url_buffer); /* gonna re-use the memory we've already got for url_buffer */ strcpy(url_buffer, "<html><body>\n"); /* extract their Yahoo! ID and put it in */ - info_extract_field(stripped, url_buffer, "Yahoo! ID:", 2, "\n", 0, + gaim_markup_extract_info_field(stripped, url_buffer, "Yahoo! ID:", 2, "\n", 0, NULL, _("Yahoo! ID"), 0, NULL); /* extract their Email address and put it in */ - info_extract_field(stripped, url_buffer, "My Email", 5, "\n", 0, + gaim_markup_extract_info_field(stripped, url_buffer, "My Email", 5, "\n", 0, "Private", _("Email"), 0, NULL); /* extract the Nickname if it exists */ - info_extract_field(stripped, url_buffer, "Nickname:", 1, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Nickname:", 1, "\n", '\n', NULL, _("Nickname"), 0, NULL); /* extract their RealName and put it in */ - info_extract_field(stripped, url_buffer, "RealName:", 1, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "RealName:", 1, "\n", '\n', NULL, _("Realname"), 0, NULL); /* extract their Location and put it in */ - info_extract_field(stripped, url_buffer, "Location:", 2, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Location:", 2, "\n", '\n', NULL, _("Location"), 0, NULL); /* extract their Age and put it in */ - info_extract_field(stripped, url_buffer, "Age:", 3, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Age:", 3, "\n", '\n', NULL, _("Age"), 0, NULL); /* extract their MaritalStatus and put it in */ - info_extract_field(stripped, url_buffer, "MaritalStatus:", 3, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "MaritalStatus:", 3, "\n", '\n', "No Answer", _("Marital Status"), 0, NULL); /* extract their Gender and put it in */ - info_extract_field(stripped, url_buffer, "Gender:", 3, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Gender:", 3, "\n", '\n', "No Answer", _("Gender"), 0, NULL); /* extract their Occupation and put it in */ - info_extract_field(stripped, url_buffer, "Occupation:", 2, "\n", '\n', + gaim_markup_extract_info_field(stripped, url_buffer, "Occupation:", 2, "\n", '\n', NULL, _("Occupation"), 0, NULL); /* Hobbies, Latest News, and Favorite Quote are a bit different, since the @@ -2505,24 +2504,24 @@ * looking for the 'Links' heading, which is the next thing to follow this * bunch. */ - if (!info_extract_field(stripped, url_buffer, "Hobbies:", 1, "Latest News", + if (!gaim_markup_extract_info_field(stripped, url_buffer, "Hobbies:", 1, "Latest News", '\n', NULL, _("Hobbies"), 0, NULL)) - if (!info_extract_field(stripped, url_buffer, "Hobbies:", 1, "Favorite Quote", + if (!gaim_markup_extract_info_field(stripped, url_buffer, "Hobbies:", 1, "Favorite Quote", '\n', NULL, _("Hobbies"), 0, NULL)) - info_extract_field(stripped, url_buffer, "Hobbies:", 1, "Links", + gaim_markup_extract_info_field(stripped, url_buffer, "Hobbies:", 1, "Links", '\n', NULL, _("Hobbies"), 0, NULL); - if (!info_extract_field(stripped, url_buffer, "Latest News:", 1, "Favorite Quote", + if (!gaim_markup_extract_info_field(stripped, url_buffer, "Latest News:", 1, "Favorite Quote", '\n', NULL, _("Latest News"), 0, NULL)) - info_extract_field(stripped, url_buffer, "Latest News:", 1, "Links", + gaim_markup_extract_info_field(stripped, url_buffer, "Latest News:", 1, "Links", '\n', NULL, _("Latest News"), 0, NULL); - info_extract_field(stripped, url_buffer, "Favorite Quote:", 0, "Links", + gaim_markup_extract_info_field(stripped, url_buffer, "Favorite Quote:", 0, "Links", '\n', NULL, _("Favorite Quote"), 0, NULL); /* Home Page will either be "No home page specified", * or "Home Page: " and a link. */ p = strstr(stripped, "No home page specified"); if (!p) - info_extract_field(stripped, url_buffer, "Home Page:", 1, " ", 0, NULL, + gaim_markup_extract_info_field(stripped, url_buffer, "Home Page:", 1, " ", 0, NULL, _("Home Page"), 1, NULL); /* Cool Link {1,2,3} is also different. If "No cool link specified" exists, @@ -2532,19 +2531,19 @@ */ p = strstr(stripped,"No cool link specified"); if (!p) - if (info_extract_field(stripped, url_buffer, "Cool Link 1:", 1, " ", 0, NULL, + if (gaim_markup_extract_info_field(stripped, url_buffer, "Cool Link 1:", 1, " ", 0, NULL, _("Cool Link 1"), 1, NULL)) - if (info_extract_field(stripped, url_buffer, "Cool Link 2:", 1, " ", 0, NULL, + if (gaim_markup_extract_info_field(stripped, url_buffer, "Cool Link 2:", 1, " ", 0, NULL, _("Cool Link 2"), 1, NULL)) - info_extract_field(stripped, url_buffer, "Cool Link 3:", 1, " ", 0, NULL, + gaim_markup_extract_info_field(stripped, url_buffer, "Cool Link 3:", 1, " ", 0, NULL, _("Cool Link 3"), 1, NULL); /* see if Member Since is there, and if so, extract it. */ - info_extract_field(stripped, url_buffer, "Member Since:", 1, "Last Updated:", + gaim_markup_extract_info_field(stripped, url_buffer, "Member Since:", 1, "Last Updated:", '\n', NULL, _("Member Since"), 0, NULL); /* extract the Last Updated date and put it in */ - info_extract_field(stripped, url_buffer, "Last Updated:", 1, "\n", '\n', NULL, + gaim_markup_extract_info_field(stripped, url_buffer, "Last Updated:", 1, "\n", '\n', NULL, _("Last Updated"), 0, NULL); /* finish off the html */ diff -r 2343c3aa1dec -r c8bf2da398e3 src/util.c --- a/src/util.c Wed Oct 01 03:01:25 2003 +0000 +++ b/src/util.c Wed Oct 01 03:43:18 2003 +0000 @@ -2,8 +2,9 @@ * @file util.h Utility Functions * @ingroup core * - * Copyright (C) 1998-1999, Mark Spencer <markster@marko.net> - * Copyright (C) 2003 Christian Hammond <chipx86@gnupdate.org> + * Copyright (C) 1998-1999 Mark Spencer <markster@marko.net> + * 2003 Christian Hammond <chipx86@gnupdate.org> + * 2003 Nathan Walp <faceprint@faceprint.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -1169,6 +1170,448 @@ } gboolean +gaim_markup_extract_info_field(const char *str, char *dest_buffer, + const char *start_token, int skip, + const char *end_token, char check_value, + const char *no_value_token, + const char *display_name, gboolean is_link, + const char *link_prefix) +{ + const char *p, *q; + char buf[1024]; + + g_return_val_if_fail(str != NULL, FALSE); + g_return_val_if_fail(dest_buffer != NULL, FALSE); + g_return_val_if_fail(start_token != NULL, FALSE); + g_return_val_if_fail(end_token != NULL, FALSE); + g_return_val_if_fail(display_name != NULL, FALSE); + + p = strstr(str, start_token); + + if (p == NULL) + return FALSE; + + p += strlen(start_token) + skip; + + if (check_value != '\0' && *p == check_value) + return FALSE; + + q = strstr(p, end_token); + + if (q != NULL && (!no_value_token || + (no_value_token && strncmp(p, no_value_token, + strlen(no_value_token))))) + { + strcat(dest_buffer, ""); + strcat(dest_buffer, display_name); + strcat(dest_buffer, ": "); + + if (is_link) + { + strcat(dest_buffer, " <a href=\""); + memcpy(buf, p, q - p); + buf[q - p] = '\0'; + + if (link_prefix) + strcat(dest_buffer, link_prefix); + + strcat(dest_buffer, buf); + strcat(dest_buffer, "\">"); + + if (link_prefix) + strcat(dest_buffer, link_prefix); + + strcat(dest_buffer, buf); + strcat(dest_buffer, "</a>"); + } + else + { + memcpy(buf, p, q - p); + buf[q - p] = '\0'; + strcat(dest_buffer, buf); + } + + strcat(dest_buffer, " \n"); + + return TRUE; + } + + return FALSE; +} + +struct gaim_parse_tag { + char *src_tag; + char *dest_tag; +}; + +#define ALLOW_TAG_ALT(x, y) if(!g_ascii_strncasecmp(c, "<" x " ", strlen("<" x " "))) { \ + const char *o = c + strlen("<" x); \ + const char *p = NULL, *q = NULL, *r = NULL; \ + GString *innards = g_string_new(""); \ + while(o && *o) { \ + if(!q && (*o == '\"' || *o == '\'') ) { \ + q = o; \ + } else if(q) { \ + if(*o == *q) { \ + char *unescaped = g_strndup(q+1, o-q-1); \ + char *escaped = g_markup_escape_text(unescaped, -1); \ + g_string_append_printf(innards, "%c%s%c", *q, escaped, *q); \ + g_free(unescaped); \ + g_free(escaped); \ + q = NULL; \ + } else if(*c == '\\') { \ + o++; \ + } \ + } else if(*o == '<') { \ + r = o; \ + } else if(*o == '>') { \ + p = o; \ + break; \ + } else { \ + innards = g_string_append_c(innards, *o); \ + } \ + o++; \ + } \ + if(p && !r) { \ + if(*(p-1) != '/') { \ + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); \ + pt->src_tag = x; \ + pt->dest_tag = y; \ + tags = g_list_prepend(tags, pt); \ + } \ + xhtml = g_string_append(xhtml, "<" y); \ + c += strlen("<" x ); \ + xhtml = g_string_append(xhtml, innards->str); \ + xhtml = g_string_append_c(xhtml, '>'); \ + c = p + 1; \ + } else { \ + xhtml = g_string_append(xhtml, "<"); \ + plain = g_string_append_c(plain, '<'); \ + c++; \ + } \ + g_string_free(innards, TRUE); \ + continue; \ + } \ + if(!g_ascii_strncasecmp(c, "<" x, strlen("<" x)) && \ + (*(c+strlen("<" x)) == '>' || \ + !g_ascii_strncasecmp(c+strlen("<" x), "/>", 2))) { \ + xhtml = g_string_append(xhtml, "<" y); \ + c += strlen("<" x); \ + if(*c != '/') { \ + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); \ + pt->src_tag = x; \ + pt->dest_tag = y; \ + tags = g_list_prepend(tags, pt); \ + xhtml = g_string_append_c(xhtml, '>'); \ + } else { \ + xhtml = g_string_append(xhtml, "/>");\ + } \ + c = strchr(c, '>') + 1; \ + continue; \ + } +#define ALLOW_TAG(x) ALLOW_TAG_ALT(x, x) +void +gaim_markup_html_to_xhtml(const char *html, char **xhtml_out, + char **plain_out) +{ + GString *xhtml = g_string_new(""); + GString *plain = g_string_new(""); + GList *tags = NULL, *tag; + const char *c = html; + + while(c && *c) { + if(*c == '<') { + if(*(c+1) == '/') { /* closing tag */ + tag = tags; + while(tag) { + struct gaim_parse_tag *pt = tag->data; + if(!g_ascii_strncasecmp((c+2), pt->src_tag, strlen(pt->src_tag)) && *(c+strlen(pt->src_tag)+2) == '>') { + c += strlen(pt->src_tag) + 3; + break; + } + tag = tag->next; + } + if(tag) { + while(tags) { + struct gaim_parse_tag *pt = tags->data; + g_string_append_printf(xhtml, "</%s>", pt->dest_tag); + if(tags == tag) + break; + tags = g_list_remove(tags, pt); + g_free(pt); + } + g_free(tag->data); + tags = g_list_remove(tags, tag->data); + } else { + /* we tried to close a tag we never opened! escape it + * and move on */ + xhtml = g_string_append(xhtml, "<"); + plain = g_string_append_c(plain, '<'); + c++; + } + } else { /* opening tag */ + ALLOW_TAG("a"); + ALLOW_TAG_ALT("b", "strong"); + ALLOW_TAG("blockquote"); + ALLOW_TAG_ALT("bold", "strong"); + ALLOW_TAG("cite"); + ALLOW_TAG("div"); + ALLOW_TAG("em"); + ALLOW_TAG("h1"); + ALLOW_TAG("h2"); + ALLOW_TAG("h3"); + ALLOW_TAG("h4"); + ALLOW_TAG("h5"); + ALLOW_TAG("h6"); + /* we only allow html to start the message */ + if(c == html) + ALLOW_TAG("html"); + ALLOW_TAG_ALT("i", "em"); + ALLOW_TAG_ALT("italic", "em"); + ALLOW_TAG("li"); + ALLOW_TAG("ol"); + ALLOW_TAG("p"); + ALLOW_TAG("pre"); + ALLOW_TAG("q"); + ALLOW_TAG("span"); + ALLOW_TAG("strong"); + ALLOW_TAG("ul"); + + /* we skip <HR> because it's not legal in XHTML-IM. However, + * we still want to send something sensible, so we put a + * linebreak in its place. also needs special handling + * because putting a to close it would just be dumb. */ + if((!g_ascii_strncasecmp(c, "<br", 3) + || !g_ascii_strncasecmp(c, "<hr", 3)) + && (*(c+3) == '>' || + !g_ascii_strncasecmp(c+3, "/>", 2) || + !g_ascii_strncasecmp(c+3, " />", 3))) { + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, " "); + if(*c != '\n') + plain = g_string_append_c(plain, '\n'); + continue; + } + if(!g_ascii_strncasecmp(c, "", 3) || !g_ascii_strncasecmp(c, "<underline>", strlen("<underline>"))) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = *(c+2) == '>' ? "u" : "underline"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "<s>", 3) || !g_ascii_strncasecmp(c, "<strike>", strlen("<strike>"))) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = *(c+2) == '>' ? "s" : "strike"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "", 5)) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = "sub"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "", 5)) { + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = "sup"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + c = strchr(c, '>') + 1; + xhtml = g_string_append(xhtml, ""); + continue; + } + if(!g_ascii_strncasecmp(c, "<font", 5) && (*(c+5) == '>' || *(c+5) == ' ')) { + const char *p = c; + GString *style = g_string_new(""); + struct gaim_parse_tag *pt; + while(*p && *p != '>') { + if(!g_ascii_strncasecmp(p, "color=", strlen("color="))) { + const char *q = p + strlen("color="); + GString *color = g_string_new(""); + if(*q == '\'' || *q == '\"') + q++; + while(*q && *q != '\"' && *q != '\'' && *q != ' ') { + color = g_string_append_c(color, *q); + q++; + } + g_string_append_printf(style, "color: %s; ", color->str); + g_string_free(color, TRUE); + p = q; + } else if(!g_ascii_strncasecmp(p, "face=", strlen("face="))) { + const char *q = p + strlen("face="); + gboolean space_allowed = FALSE; + GString *face = g_string_new(""); + if(*q == '\'' || *q == '\"') { + space_allowed = TRUE; + q++; + } + while(*q && *q != '\"' && *q != '\'' && (space_allowed || *q != ' ')) { + face = g_string_append_c(face, *q); + q++; + } + g_string_append_printf(style, "font-family: %s; ", face->str); + g_string_free(face, TRUE); + p = q; + } else if(!g_ascii_strncasecmp(p, "size=", strlen("size="))) { + const char *q = p + strlen("size="); + int sz; + const char *size = "medium"; + if(*q == '\'' || *q == '\"') + q++; + sz = atoi(q); + if(sz < 3) + size = "smaller"; + else if(sz > 3) + size = "larger"; + g_string_append_printf(style, "font-size: %s; ", size); + p = q; + } + p++; + } + c = strchr(c, '>') + 1; + pt = g_new0(struct gaim_parse_tag, 1); + pt->src_tag = "font"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + xhtml = g_string_append(xhtml, "<span"); + if(style->len) + g_string_append_printf(xhtml, " style='%s'", style->str); + xhtml = g_string_append_c(xhtml, '>'); + g_string_free(style, TRUE); + continue; + } + if(!g_ascii_strncasecmp(c, "<body ", 6)) { + const char *p = c; + gboolean did_something = FALSE; + while(*p && *p != '>') { + if(!g_ascii_strncasecmp(p, "bgcolor=", strlen("bgcolor="))) { + const char *q = p + strlen("bgcolor="); + struct gaim_parse_tag *pt = g_new0(struct gaim_parse_tag, 1); + GString *color = g_string_new(""); + if(*q == '\'' || *q == '\"') + q++; + while(*q && *q != '\"' && *q != '\'' && *q != ' ') { + color = g_string_append_c(color, *q); + q++; + } + g_string_append_printf(xhtml, "", color->str); + g_string_free(color, TRUE); + c = strchr(c, '>') + 1; + pt->src_tag = "body"; + pt->dest_tag = "span"; + tags = g_list_prepend(tags, pt); + did_something = TRUE; + break; + } + p++; + } + if(did_something) continue; + } + /* this has to come after the special case for bgcolor */ + ALLOW_TAG("body"); + if(!g_ascii_strncasecmp(c, ""); + if(p) { + xhtml = g_string_append(xhtml, "<!--"); + c += strlen("<!--"); + continue; + } + } + + xhtml = g_string_append(xhtml, "<"); + plain = g_string_append_c(plain, '<'); + c++; + } + } else { + xhtml = g_string_append_c(xhtml, *c); + plain = g_string_append_c(plain, *c); + c++; + } + } + tag = tags; + while(tag) { + g_string_append_printf(xhtml, "</%s>", (char *)tag->data); + tag = tag->next; + } + g_list_free(tags); + if(xhtml_out) + *xhtml_out = g_strdup(xhtml->str); + if(plain_out) + *plain_out = g_strdup(plain->str); + g_string_free(xhtml, TRUE); + g_string_free(plain, TRUE); +} + +char * +gaim_markup_strip_html(const char *str) +{ + int i, j, k; + gboolean visible = TRUE; + gchar *str2; + + g_return_val_if_fail(str != NULL, NULL); + + str2 = g_strdup(str); + + for (i = 0, j = 0; str2[i]; i++) + { + if (str2[i] == '<') + { + k = i + 1; + + if(g_ascii_isspace(str2[k])) + visible = TRUE; + else + { + while (str2[k]) + { + if (str2[k] == '<') + { + visible = TRUE; + break; + } + + if (str2[k] == '>') + { + visible = FALSE; + break; + } + + k++; + } + } + } + else if (str2[i] == '>' && !visible) + { + visible = TRUE; + continue; + } + + if (str2[i] == '&' && strncasecmp(str2 + i, """, 6) == 0) + { + str2[j++] = '\"'; + i = i + 5; + continue; + } + + if (visible) + str2[j++] = str2[i]; + } + + str2[j] = '\0'; + + return str2; +} + +gboolean gaim_url_parse(const char *url, char **ret_host, int *ret_port, char **ret_path) { diff -r 2343c3aa1dec -r c8bf2da398e3 src/util.h --- a/src/util.h Wed Oct 01 03:01:25 2003 +0000 +++ b/src/util.h Wed Oct 01 03:43:18 2003 +0000 @@ -350,6 +350,55 @@ GData **attributes); /** + * Extracts a field of data from HTML. + * + * This is a scary function. See protocols/msn/msn.c and + * protocols/yahoo/yahoo.c for example usage. + * + * @param str The string to parse. + * @param dest_buffer The destination buffer to append the new + * field info to. + * @param start_token The beginning token. + * @param skip The number of characters to skip after the + * start token. + * @param end_token The ending token. + * @param check_value The value that the last character must meet. + * @param no_value_token The token indicating no value is given. + * @param display_name The short descriptive name to display for this token. + * @param is_link TRUE if this should be a link, or FALSE otherwise. + * @param link_prefix The prefix for the link. + * + * @return TRUE if successful, or FALSE otherwise. + */ +gboolean gaim_markup_extract_info_field(const char *str, char *dest_buffer, + const char *start_token, int skip, + const char *end_token, + char check_value, + const char *no_value_token, + const char *display_name, + gboolean is_link, + const char *link_prefix); + +/** + * Converts HTML markup to XHTML. + * + * @param html The HTML markup. + * @param dest_xhtml The destination XHTML output. + * @param dest_plain The destination plain-text output. + */ +void gaim_markup_html_to_xhtml(const char *html, char **dest_xhtml, + char **dest_plain); + +/** + * Strips HTML tags from a string. + * + * @param str The string to strip HTML from. + * + * @return The new string without HTML. This must be freed. + */ +char *gaim_markup_strip_html(const char *str); + +/** * Parses a URL, returning its host, port, and file path. * * The returned data must be freed.