From tim@nz.eds.com Wed Apr 8 18:28:36 1998 Date: Thu, 9 Apr 1998 10:06:19 +1200 (NZST) From: Tim Frost Reply-To: Tim Frost To: htdig-patches@sol.ccsf.cc.ca.us Cc: Andrew Scherpbier Subject: ht://dig - URL quoting patch - correction In checking the unofficial patch site for ht://dig, I find that an early, broken, version of my fix for handling URL quoting is held on the patch site. The file HTML.cc-h.0, found under the 3.0.8b2 directory, should be deleted, and the following patch should be made available (as HTML.cc.1?). This patch was created against V3.0.8b2 as a unified diff. I can produce a context diff if desired. The original patch attempted to use a new function to do the duplicated work, but this failed because it did not return the (at least) two pointer values that were needed. Tim diff -u htdig-3.0.8b2/htdig/HTML.cc-orig htdig-3.0.8b2/htdig/HTML.cc --- htdig-3.0.8b2/htdig/HTML.cc-orig Sun Dec 7 22:14:40 1997 +++ htdig-3.0.8b2/htdig/HTML.cc Fri Jan 9 21:24:03 1998 @@ -309,7 +309,7 @@ HTML::do_tag(Retriever &retriever, String &tag) { char *position = tag.get() + 1; // Skip the '<' - char *q; + char *q, *t; int which, length; while (isspace(*position)) @@ -358,12 +358,34 @@ position++; while (isspace(*position)) position++; - if (*position == '"') + // + // Allow either single quotes or double quotes + // around the URL itself + // + if (*position == '"'||*position == '\'') { position++; - q = strchr(position, '"'); + q = strchr(position, position[-1]); if (!q) break; + // + // We seem to have matched the opening quote char + // Mark the end of the quotes as our endpoint, so + // that we can continue parsing after the current + // text + // + *q = '\0'; + // + // If a '?' or '#' is present in a quoted URL, + // treat that as the end of the URL, but we skip + // past the quote to parse the rest of the anchor. + // + // Is there a better way of looking for these? + // + if ((t = strchr(position, '#')) != NULL) + *t = '\0'; + if ((t = strchr(position, '?')) != NULL) + *t = '\0'; } else { @@ -374,8 +396,8 @@ *q != '?' && *q != '#') q++; + *q = '\0'; } - *q = '\0'; delete href; href = new URL(position, *base); in_ref = 1; @@ -396,20 +418,42 @@ position++; while (isspace(*position)) position++; - if (*position == '"') + // + // Allow either single quotes or double quotes + // around the URL itself + // + if (*position == '"'||*position == '\'') { position++; - q = strchr(position, '"'); + q = strchr(position, position[-1]); if (!q) break; + // + // We seem to have matched the opening quote char + // Mark the end of the quotes as our endpoint, so + // that we can continue parsing after the current + // text + // + *q = '\0'; + // + // If a '?' or '#' is present in a quoted URL, + // treat that as the end of the URL, but we skip + // past the quote to parse the rest of the anchor. + // + // Is there a better way of looking for these? + // + if ((t = strchr(position, '#')) != NULL) + *t = '\0'; + if ((t = strchr(position, '?')) != NULL) + *t = '\0'; } else { q = position; while (*q && *q != '>' && !isspace(*q)) q++; + *q = '\0'; } - *q = '\0'; retriever.got_anchor(position); position = q + 1; break; @@ -484,20 +528,42 @@ position++; while (isspace(*position)) position++; - if (*position == '"') + // + // Allow either single quotes or double quotes + // around the URL itself + // + if (*position == '"'||*position == '\'') { position++; - q = strchr(position, '"'); + q = strchr(position, position[-1]); if (!q) break; + // + // We seem to have matched the opening quote char + // Mark the end of the quotes as our endpoint, so + // that we can continue parsing after the current + // text + // + *q = '\0'; + // + // If a '?' or '#' is present in a quoted URL, + // treat that as the end of the URL, but we skip + // past the quote to parse the rest of the anchor. + // + // Is there a better way of looking for these? + // + if ((t = strchr(position, '#')) != NULL) + *t = '\0'; + if ((t = strchr(position, '?')) != NULL) + *t = '\0'; } else { q = position; while (*q && *q != '>' && !isspace(*q)) q++; + *q = '\0'; } - *q = '\0'; retriever.got_image(position); break; } @@ -616,12 +682,34 @@ position++; while (isspace(*position)) position++; - if (*position == '"') + // + // Allow either single quotes or double quotes + // around the URL itself + // + if (*position == '"'||*position == '\'') { position++; - q = strchr(position, '"'); + q = strchr(position, position[-1]); if (!q) break; + // + // We seem to have matched the opening quote char + // Mark the end of the quotes as our endpoint, so + // that we can continue parsing after the current + // text + // + *q = '\0'; + // + // If a '?' or '#' is present in a quoted URL, + // treat that as the end of the URL, but we skip + // past the quote to parse the rest of the anchor. + // + // Is there a better way of looking for these? + // + if ((t = strchr(position, '#')) != NULL) + *t = '\0'; + if ((t = strchr(position, '?')) != NULL) + *t = '\0'; } else { @@ -632,8 +720,8 @@ *q != '?' && *q != '#') q++; + *q = '\0'; } - *q = '\0'; delete href; href = new URL(position, *base); if (doindex) @@ -668,12 +756,34 @@ position++; while (isspace(*position)) position++; - if (*position == '"') + // + // Allow either single quotes or double quotes + // around the URL itself + // + if (*position == '"'||*position == '\'') { position++; - q = strchr(position, '"'); + q = strchr(position, position[-1]); if (!q) break; + // + // We seem to have matched the opening quote char + // Mark the end of the quotes as our endpoint, so + // that we can continue parsing after the current + // text + // + *q = '\0'; + // + // If a '?' or '#' is present in a quoted URL, + // treat that as the end of the URL, but we skip + // past the quote to parse the rest of the anchor. + // + // Is there a better way of looking for these? + // + if ((t = strchr(position, '#')) != NULL) + *t = '\0'; + if ((t = strchr(position, '?')) != NULL) + *t = '\0'; } else { @@ -684,8 +794,8 @@ *q != '?' && *q != '#') q++; + *q = '\0'; } - *q = '\0'; delete href; href = new URL(position, *base); if (doindex) @@ -719,12 +829,34 @@ position++; while (isspace(*position)) position++; - if (*position == '"') + // + // Allow either single quotes or double quotes + // around the URL itself + // + if (*position == '"'||*position == '\'') { position++; - q = strchr(position, '"'); + q = strchr(position, position[-1]); if (!q) break; + // + // We seem to have matched the opening quote char + // Mark the end of the quotes as our endpoint, so + // that we can continue parsing after the current + // text + // + *q = '\0'; + // + // If a '?' or '#' is present in a quoted URL, + // treat that as the end of the URL, but we skip + // past the quote to parse the rest of the anchor. + // + // Is there a better way of looking for these? + // + if ((t = strchr(position, '#')) != NULL) + *t = '\0'; + if ((t = strchr(position, '?')) != NULL) + *t = '\0'; } else { @@ -735,8 +867,8 @@ *q != '?' && *q != '#') q++; + *q = '\0'; } - *q = '\0'; URL tempBase(position, *base); *base = tempBase; }