From pe@iki.fi Tue Aug  5 16:53:41 1997
Date: Tue, 5 Aug 1997 16:53:35 +0300 (EEST)
From: Pasi Eronen <pe@iki.fi>
To: HTDig mailing list <htdig@sdsu.edu>
Subject: Patches for local home directories


Hi!

Few days ago, I posted patches for local filesystem access
to HTDig. Since then, I've received a request for supporting
user home directory URLs (like http://www.my.com/~user/foo.html),
and made a patch for that, too.

The syntax of the new configuration file option is:

  local_user_urls: prefix1=[path1],dir1 ...

If you leave the "path" part out, it looks up the user's home
directory in /etc/passwd (or NIS or whatever). For example, 
to map  "http://www.my.org/~joe/foo/bar.html" to 
"/home/joe/www/foo/bar.html" you would say:

  local_user_urls: http://www.my.org/=/home/,/www/

The default behaviour of many WWW servers is approximately:

  local_user_urls: http://www.my.org/=,/public_html/

(NOTE: All the slashes in these examples are REQUIRED!)

This patch is a bit large, so I won't post it here. Instead,
it's available from <http://www.iki.fi/pe/htdig/>. I'm not
indexing any home directories myself, so comments are very
welcome.  (Tip: you can see what local filename it's trying
to use if you specify options '-v -v' to htdig.)

Thanks to Geoff Hutchison for testing this patch.

Best regards,
Pasi

---
Pasi Eronen <pe@iki.fi>, +358-50-5123499

*** htcommon/defaults.cc.orig	Mon Aug  4 18:14:48 1997
--- htcommon/defaults.cc	Mon Aug  4 18:15:10 1997
***************
*** 65,68 ****
--- 65,69 ----
      {"locale",				"iso_8859_1"},
      {"local_urls",			""},
+     {"local_user_urls",			""},
      {"maintainer",			"andrew@contigo.com"},
      {"match_method",			"or"},
*** htdig/Retriever.h.orig	Mon Aug  4 18:12:20 1997
--- htdig/Retriever.h	Mon Aug  4 18:12:38 1997
***************
*** 117,120 ****
--- 117,121 ----
      int			IsValidURL(char *url);
      String *            IsLocal(char *url);
+     String *            IsLocalUser(char *url);
      void		RetrievedDocument(Document &, char *url, DocumentRef *ref);
      void		parse_url(URLRef &urlRef);
*** htdig/Retriever.cc.orig	Mon Aug  4 18:12:27 1997
--- htdig/Retriever.cc	Mon Aug  4 18:13:30 1997
***************
*** 27,30 ****
--- 27,31 ----
  #include "Document.h"
  #include <StringList.h>
+ #include <pwd.h>
  
  static WordList	words;
***************
*** 261,265 ****
      // Retrive document, first trying local file access if possible.
      Document::DocStatus status;
!     String *local_filename = IsLocal(url.get());
      if (local_filename)
      {  
--- 262,268 ----
      // Retrive document, first trying local file access if possible.
      Document::DocStatus status;
!     String *local_filename = IsLocalUser(url.get());
!     if (!local_filename)
!         local_filename = IsLocal(url.get());
      if (local_filename)
      {  
***************
*** 538,541 ****
--- 541,548 ----
      }
  
+     // This shouldn't happen, but check anyway...
+     if (strstr(url, ".."))
+         return 0;
+     
      String *prefix, *path;
      prefixes->Start_Get();
***************
*** 556,559 ****
--- 563,665 ----
  
  
+ //*****************************************************************************
+ // String* Retriever::IsLocalUser(char *url)
+ //   If the URL has ~user part, returns a string containing the
+ //   (possible) local filename of the given url, or 0 if it's
+ //   definitely not local.
+ //   THE CALLER MUST FREE THE STRING AFTER USE!
+ //
+ String*
+ Retriever::IsLocalUser(char *url)
+ {
+     static StringList *prefixes = 0, *paths = 0, *dirs = 0;
+     static Dictionary home_cache;
+ 
+     //
+     // Initialize prefix/path list if this is the first time.
+     // The list is given in format "prefix1=path1,dir1 ..."
+     // If path is zero-length, user's home directory is looked up. 
+     //
+     if (!prefixes)
+     {
+         prefixes = new StringList();
+ 	paths = new StringList();
+ 	dirs = new StringList();
+ 	String t = config["local_user_urls"];
+ 	char *p = strtok(t, " \t");
+ 	while (p)
+ 	{
+ 	    char *path = strchr(p, '=');
+ 	    if (!path)
+ 	        continue;
+ 	    *path++ = '\0';
+ 	    char *dir = strchr(path, ',');
+ 	    if (!dir)
+ 	        continue;
+ 	    *dir++ = '\0';
+ 	    prefixes->Add(p);
+ 	    paths->Add(path);
+ 	    dirs->Add(dir);
+ 	    p = strtok(0, " \t");
+ 	}
+     }
+ 
+     // Can we do anything about this?
+     if (!strchr(url, '~') || !prefixes->Count() || strstr(url, ".."))
+         return 0;
+ 
+     // Split the URL to components
+     String tmp = url;
+     char *name = strchr(tmp, '~');
+     *name++ = '\0';
+     char *rest = strchr(name, '/');
+     if (!rest || (rest-name <= 1) || (rest-name > 32))
+         return 0;
+     *rest++ = '\0';
+ 
+     // Look it up in the prefix/path/dir table
+     prefixes->Start_Get();
+     paths->Start_Get();
+     dirs->Start_Get();
+     String *prefix, *path, *dir;
+     while (prefix = (String*) prefixes->Get_Next())
+     {
+         path = (String*) paths->Get_Next();
+ 	dir = (String*) dirs->Get_Next();
+         if (strcasecmp(*prefix, tmp) != 0)
+   	    continue;
+ 
+ 	String *local = new String;
+ 	// No path, look up home directory
+ 	if (path->length() == 0)
+ 	{
+ 	    String *home = (String*) home_cache[name];
+ 	    if (!home)
+ 	    {
+ 	        struct passwd *passwd = getpwnam(name);
+ 		if (passwd)
+ 		{
+ 		    home = new String(passwd->pw_dir);
+ 		    home_cache.Add(name, home);
+ 		}
+ 	    }
+ 	    if (home)
+ 	        *local += *home;
+ 	    else
+ 	        return 0;
+ 	}
+ 	else
+ 	{
+ 	    *local += *path;
+ 	    *local += name;
+ 	}
+ 	*local += *dir;
+ 	*local += rest;
+ 	return local;
+     }
+     return 0;
+ }
+ 
+  
  //*****************************************************************************
  // DocumentRef *Retriever::GetRef(char *u)