Date: Mon, 26 Apr 2004 17:27:24 -0700 (PDT) From: Joe R. Jah To: Gilles Detillieux Cc: "ht://Dig mailing list" Subject: Adding the allow_space_in_url attribute This patch, fileSpace.1, is fileSpace.0 plus corresponding defaults.cc, defaults.xml, and attrs.html entries. I used Gilles' excellent comments in fileSpace.0:) Regards, Joe -- _/ _/_/_/ _/ ____________ __o _/ _/ _/ _/ ______________ _-\<,_ _/ _/ _/_/_/ _/ _/ ......(_)/ (_) _/_/ oe _/ _/. _/_/ ah jjah@cloud.ccsf.cc.ca.us --- htcommon/URL.cc.orig 2003-07-21 07:40:16.000000000 -0500 +++ htcommon/URL.cc 2003-11-13 16:50:03.000000000 -0600 @@ -144,8 +144,26 @@ URL::URL(const String &url, const URL &p _signature(parent._signature), _user(parent._user) { - String temp(url); - temp.remove(" \r\n\t"); + HtConfiguration* config= HtConfiguration::config(); + int allowspace = config->Boolean("allow_space_in_url", 0); + String temp; + const char *urp = url.get(); + while (*urp) + { + if (*urp == ' ' && temp.length() > 0 && allowspace) + { + // Replace space character with %20 if there's more non-space + // characters to come... + const char *s = urp+1; + while (*s && isspace(*s)) + s++; + if (*s) + temp << "%20"; + } + else if (!isspace(*urp)) + temp << *urp; + urp++; + } char* ref = temp; // @@ -314,8 +332,26 @@ void URL::rewrite() // void URL::parse(const String &u) { - String temp(u); - temp.remove(" \t\r\n"); + HtConfiguration* config= HtConfiguration::config(); + int allowspace = config->Boolean("allow_space_in_url", 0); + String temp; + const char *urp = u.get(); + while (*urp) + { + if (*urp == ' ' && temp.length() > 0 && allowspace) + { + // Replace space character with %20 if there's more non-space + // characters to come... + const char *s = urp+1; + while (*s && isspace(*s)) + s++; + if (*s) + temp << "%20"; + } + else if (!isspace(*urp)) + temp << *urp; + urp++; + } char *nurl = temp; // --- htcommon/defaults.cc.orig Sat Nov 8 19:46:34 2003 +++ htcommon/defaults.cc Mon Apr 26 16:07:23 2004 @@ -125,6 +125,19 @@ To disallow digits in words, add the digits to \ valid_punctuation. \ " }, \ +{ "allow_space_in_url", "false", \ + "boolean", "htdig", "", "3.2.0b5", "Indexing:Where", "allow_space_in_url: true", " \ + If set to true, htdig will handle URLs that contain \ + embedded spaces. Technically, this is a violation of \ + RFC 2396, which says spaces should be stripped out \ + (as htdig does by default). However, many web browsers \ + and HTML code generators violate this standard already, \ + so enabling this attribute allows htdig to handle these \ + non-compliant URLs. Even with this attribute set, htdig \ + still strips out all white space (leading, trailing and \ + embedded), except that space characters embedded within \ + the URL will be encoded as %20. +" }, \ { "allow_virtual_hosts", "true", \ "boolean", "htdig", "", "3.0.8b2", "Indexing:Where", "allow_virtual_hosts: false", " \ If set to true, htdig will index virtual web sites as \ --- htcommon/defaults.xml.orig Sat Nov 8 19:46:34 2003 +++ htcommon/defaults.xml Mon Apr 26 17:01:06 2004 @@ -121,6 +121,27 @@ + + false + true + + If set to true, htdig will handle URLs that contain + embedded spaces. Technically, this is a violation of + RFC 2396, which says spaces should be stripped out + (as htdig does by default). However, many web browsers + and HTML code generators violate this standard already, + so enabling this attribute allows htdig to handle these + non-compliant URLs. Even with this attribute set, htdig + still strips out all white space (leading, trailing and + embedded), except that space characters embedded within + the URL will be encoded as %20. + + +

+ + allow_space_in_url +

+ type: +

+ boolean +

+ used by: +

+ htdig +

+ default: +

+ false +

+ block: +

+ Global +

+ version: +

+ 3.2.0b5 +

+ description: +

+ If set to true, htdig will handle URLs that contain + embedded spaces. Technically, this is a violation of + RFC 2396, which says spaces should be stripped out + (as htdig does by default). However, many web browsers + and HTML code generators violate this standard already, + so enabling this attribute allows htdig to handle these + non-compliant URLs. Even with this attribute set, htdig + still strips out all white space (leading, trailing and + embedded), except that space characters embedded within + the URL will be encoded as %20. +

+ example: +

+ + + + + +

+ allow_space_in_url: +

+ true +

allow_virtual_hosts