When converting <A> tags, don't omit the change to

[citadel.git] / webcit / html2html.c

diff --git a/webcit/html2html.c b/webcit/html2html.c
index ca8804c1aa6d707699863bbf91785d12c9ad984e..72356c700bf539566f5baee2cd92b3c74e7372a9 100644 (file)
--- a/webcit/html2html.c
+++ b/webcit/html2html.c
@@ -59,6 +59,18 @@ void extract_charset_from_meta(char *charset, char *meta_http_equiv, char *meta_
        striplt(buf);
        if (!strncasecmp(buf, "charset=", 8)) {
                strcpy(charset, &buf[8]);
+
+               /*
+                * The brain-damaged webmail program in Microsoft Exchange declares
+                * a charset of "unicode" when they really mean "UTF-8".  GNU iconv
+                * treats "unicode" as an alias for "UTF-16" so we have to manually
+                * fix this here, otherwise messages generated in Exchange webmail
+                * show up as a big pile of weird characters.
+                */
+               if (!strcasecmp(charset, "unicode")) {
+                       strcpy(charset, "UTF-8");
+               }
+
        }
 }
 
@@ -77,6 +89,7 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
        char *msgstart;
        char *msgend;
        char *converted_msg;
+       size_t converted_alloc = 0;
        int buffer_length = 1;
        int line_length = 0;
        int content_length = 0;
@@ -251,7 +264,13 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
         */
 
        /** Now go through the message, parsing tags as necessary. */
-       converted_msg = malloc(content_length);
+       converted_alloc = content_length + 8192;
+       converted_msg = malloc(converted_alloc);
+       if (converted_msg == NULL) {
+               wprintf("Error %d: %s<br />%s:%s", errno, strerror(errno), __FILE__, __LINE__);
+               goto BAIL;
+       }
+
        strcpy(converted_msg, "");
        ptr = msg;
        msgend = strchr(msg, 0);
@@ -265,7 +284,13 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
                 */
                if (!strncasecmp(ptr, "<a href=\"mailto:", 16)) {
                        content_length += 64;
-                       converted_msg = realloc(converted_msg, content_length);
+                       if (content_length >= converted_alloc) {
+                               converted_alloc += 8192;
+                               converted_msg = realloc(converted_msg, converted_alloc);
+                               if (converted_msg == NULL) {
+                                       abort();
+                               }
+                       }
                        sprintf(&converted_msg[output_length],
                                "<a href=\"display_enter"
                                "?force_room=_MAIL_&recp=");
@@ -281,14 +306,26 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
                             ) {
                                /* open external links to new window */
                                content_length += 64;
-                               converted_msg = realloc(converted_msg, content_length);
+                               if (content_length >= converted_alloc) {
+                                       converted_alloc += 8192;
+                                       converted_msg = realloc(converted_msg, converted_alloc);
+                                       if (converted_msg == NULL) {
+                                               abort();
+                                       }
+                               }
                                sprintf(&converted_msg[output_length], new_window);
                                output_length += strlen(new_window);
                                ptr = &ptr[8];
                        }
                        else if ( (treat_as_wiki) && (strncasecmp(ptr, "<a href=\"wiki?", 14)) ) {
                                content_length += 64;
-                               converted_msg = realloc(converted_msg, content_length);
+                               if (content_length >= converted_alloc) {
+                                       converted_alloc += 8192;
+                                       converted_msg = realloc(converted_msg, converted_alloc);
+                                       if (converted_msg == NULL) {
+                                               abort();
+                                       }
+                               }
                                sprintf(&converted_msg[output_length], "<a href=\"wiki?page=");
                                output_length += 19;
                                ptr = &ptr[9];
@@ -323,7 +360,13 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
                                }
                                if (linklen > 0) {
                                        content_length += (32 + linklen);
-                                       converted_msg = realloc(converted_msg, content_length);
+                                       if (content_length >= converted_alloc) {
+                                               converted_alloc += 8192;
+                                               converted_msg = realloc(converted_msg, converted_alloc);
+                                               if (converted_msg == NULL) {
+                                                       abort();
+                                               }
+                                       }
                                        sprintf(&converted_msg[output_length], new_window);
                                        output_length += strlen(new_window);
                                        converted_msg[output_length] = '\"';
@@ -343,17 +386,17 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
                                }
                }
                else {
-                       /**
-                        * We need to know when we're inside a tag,
-                        * so we don't turn things that look like URL's into
-                        * links, when they're already links - or image sources.
-                        */
-                       if (*ptr == '<') ++brak;
-                       if (*ptr == '>') --brak;
-                       if (!strncasecmp(ptr, "</A>", 3)) --alevel;
                        converted_msg[output_length] = *ptr++;
                        converted_msg[++output_length] = 0;
                }
+               /**
+                * We need to know when we're inside a tag,
+                * so we don't turn things that look like URL's into
+                * links, when they're already links - or image sources.
+                */
+               if (*ptr == '<') ++brak;
+               if (*ptr == '>') --brak;
+               if (!strncasecmp(ptr, "</A>", 3)) --alevel;
        }
 
        /**     uncomment these two lines to override conversion        */
@@ -363,12 +406,12 @@ void output_html(char *supplied_charset, int treat_as_wiki) {
        /** Output our big pile of markup */
        client_write(converted_msg, output_length);
 
-       /** A little trailing vertical whitespace... */
+BAIL:  /** A little trailing vertical whitespace... */
        wprintf("<br /><br />\n");
 
        /** Now give back the memory */
-       free(converted_msg);
-       free(msg);
+       if (converted_msg != NULL) free(converted_msg);
+       if (msg != NULL) free(msg);
 }
 
 /*@}*/