From: hniksic <devnull@localhost>
Date: Mon, 15 Apr 2002 21:57:10 +0000 (-0700)
Subject: [svn] When downloading recursively, don't ignore rejection of HTML
X-Git-Tag: v1.13~1784
X-Git-Url: http://sjero.net/git/?p=wget;a=commitdiff_plain;h=f8b4b8bd12b0f5c76b7eb6ed908e3cfe0cdc0843

[svn] When downloading recursively, don't ignore rejection of HTML
documents that are themselves leaves of recursion.
---

diff --git a/src/ChangeLog b/src/ChangeLog
index a17ffe8e..d9dd76bd 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,8 @@
+2002-04-15  Hrvoje Niksic  <hniksic@arsdigita.com>
+
+	* recur.c (download_child_p): Don't ignore rejection of HTML
+	documents that are themselves leaves of recursion.
+
 2002-04-15  Ian Abbott  <abbotti@mev.co.uk>
 
 	Makefile.in: Updated several dependencies for object files to take
@@ -16,6 +21,7 @@
 	* utils.c: Don't define `SETJMP()', `run_with_timeout_env' or
 	`abort_run_with_timeout()' when `USE_SIGNAL_TIMEOUT' is undefined.
 
+>>>>>>> 1.395
 2002-04-15  Hrvoje Niksic  <hniksic@arsdigita.com>
 
 	* host.c (getaddrinfo_with_timeout): New function.
diff --git a/src/recur.c b/src/recur.c
index 1d6a6988..da277415 100644
--- a/src/recur.c
+++ b/src/recur.c
@@ -511,23 +511,13 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
   /* 6. */
   {
     /* Check for acceptance/rejection rules.  We ignore these rules
-       for HTML documents because they might lead to other files which
-       need to be downloaded.  Of course, we don't know which
-       documents are HTML before downloading them, so we guess.
-
-       A file is subject to acceptance/rejection rules if:
-
-       * u->file is not "" (i.e. it is not a directory)
-       and either:
-         + there is no file suffix,
-	 + or there is a suffix, but is not "html" or "htm" or similar,
-	 + both:
-	   - recursion is not infinite,
-	   - and we are at its very end. */
-
+       for directories (no file name to match) and for HTML documents,
+       which might lead to other files that do need to be downloaded.
+       That is, unless we've exhausted the recursion depth anyway.  */
     if (u->file[0] != '\0'
-	&& (!has_html_suffix_p (url)
-	    || (opt.reclevel != INFINITE_RECURSION && depth >= opt.reclevel)))
+	&& !(has_html_suffix_p (u->file)
+	     && depth < opt.reclevel - 1
+	     && depth != INFINITE_RECURSION))
       {
 	if (!acceptable (u->file))
 	  {