[Xen-changelog] [xen master] docs/gen-html-index: Extract titles from HTML documents

[patchbot@xxxxxxx]

commit 7782db9260d4c6499458de4e8d9866bc0427e143
Author:     Ian Jackson <ian.jackson@xxxxxxxxxxxxx>
AuthorDate: Fri Apr 6 19:09:02 2018 +0100
Commit:     Ian Jackson <Ian.Jackson@xxxxxxxxxxxxx>
CommitDate: Thu Apr 12 16:13:39 2018 +0100

    docs/gen-html-index: Extract titles from HTML documents
    
    Signed-off-by: Ian Jackson <Ian.Jackson@xxxxxxxxxxxxx>
    Release-acked-by: Juergen Gross <jgross@xxxxxxxx>
    Acked-by: Lars Kurth <lars.kurth@xxxxxxxxxx>
---
 docs/gen-html-index | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/docs/gen-html-index b/docs/gen-html-index
index e9792bf937..5b43b42a8c 100644
--- a/docs/gen-html-index
+++ b/docs/gen-html-index
@@ -10,6 +10,7 @@ use warnings;
 use Getopt::Long;
 use IO::File;
 use File::Basename;
+use HTML::TreeBuilder::XPath;
 
 Getopt::Long::Configure('bundling');
 
@@ -64,6 +65,18 @@ sub make_linktext ($) {
     return "$1($2)" if $l =~ m,^man/(.*)\.([0-9].*)\.html,;
     $l =~ s/.(?:html|txt)$//g;
     return $index{$l} if exists $index{$l};
+
+    my $from_html;
+    eval {
+        my $tree = new HTML::TreeBuilder::XPath;
+        my $f = "$outdir/$l.html";
+        open F, '<', $f or die "$l $f $!";
+        $tree->parse_file(\*F) or die;
+        close F;
+        $from_html = $tree->findvalue("/html/head/title");
+    };
+    return $from_html if $from_html;
+
     return basename($l);
 }
 
--
generated by git-patchbot for /home/xen/git/xen.git#master

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/xen-changelog