automatically run --gettime, and optimise it for git

* Automatically run --gettime the first time ikiwiki is run on
  a given srcdir.
* Optimise --gettime for git, so it's appropriatly screamingly
  fast. (This could be done for other backends too.)
* However, --gettime for git no longer follows renames.
* Use above to fix up timestamps on docwiki, as well as ensure that
  timestamps on basewiki files shipped in the deb are sane.

9 files changed, 76 insertions, 19 deletions

diff --git a/IkiWiki.pm b/IkiWiki.pm
index 7655dada5..b37b1f344 100644
--- a/IkiWiki.pm
+++ b/IkiWiki.pm
@@ -442,7 +442,6 @@ sub getsetup () {
 	},
 	gettime => {
 		type => "internal",
-		default => 0,
 		description => "running in gettime mode",
 		safe => 0,
 		rebuild => 0,
@@ -1512,6 +1511,7 @@ sub loadindex () {
 			open ($in, "<", "$config{wikistatedir}/indexdb") || return;
 		}
 		else {
+			$config{gettime}=1; # first build
 			return;
 		}
 	}
diff --git a/IkiWiki/Plugin/git.pm b/IkiWiki/Plugin/git.pm
index 86d80186f..aa402c04f 100644
--- a/IkiWiki/Plugin/git.pm
+++ b/IkiWiki/Plugin/git.pm
@@ -616,27 +616,51 @@ sub rcs_diff ($) {
 	}
 }
 
-sub rcs_getctime ($) {
+{
+my %time_cache;
+
+sub findtimes ($$) {
 	my $file=shift;
+	my $id=shift; # 0 = mtime ; 1 = ctime
+
 	# Remove srcdir prefix
 	$file =~ s/^\Q$config{srcdir}\E\/?//;
 
-	my @raw_lines = run_or_die('git', 'log', 
-		'--follow', '--no-merges',
-		'--pretty=raw', '--raw', '--abbrev=40', '--always', '-c',
-		'-r', '--', $file);
-	my @ci;
-	while (my $parsed = parse_diff_tree("", \@raw_lines)) {
-		push @ci, $parsed;
+	if (! keys %time_cache) {
+		my $date;
+		foreach my $line (run_or_die('git', 'log',
+				'--pretty=format:%ct',
+				'--name-only', '--relative')) {
+			if (! defined $date && $line =~ /^(\d+)$/) {
+				$date=$line;
+			}
+			elsif (! length $line) {
+				$date=undef;
+			}
+			else {
+				if (! $time_cache{$line}) {
+					$time_cache{$line}[0]=$date; # mtime
+				}
+				$time_cache{$line}[1]=$date; # ctime
+			}
+		}
 	}
-	my $ctime = $ci[$#ci]->{'author_epoch'};
-	debug("ctime for '$file': ". localtime($ctime));
 
-	return $ctime;
+	return exists $time_cache{$file} ? $time_cache{$file}[$id] : 0;
+}
+
+}
+
+sub rcs_getctime ($) {
+	my $file=shift;
+
+	return findtimes($file, 1);
 }
 
 sub rcs_getmtime ($) {
-	error "rcs_getmtime is not implemented for git\n"; # TODO
+	my $file=shift;
+
+	return findtimes($file, 0);
 }
 
 sub rcs_receive () {
diff --git a/IkiWiki/Render.pm b/IkiWiki/Render.pm
index e1cb68462..a6b0f0617 100644
--- a/IkiWiki/Render.pm
+++ b/IkiWiki/Render.pm
@@ -352,6 +352,8 @@ sub find_new_files ($) {
 	my @new;
 	my @internal_new;
 
+	my $times_noted;
+
 	foreach my $file (@$files) {
 		my $page=pagename($file);
 		if (exists $pagesources{$page} && $pagesources{$page} ne $file) {
@@ -363,7 +365,12 @@ sub find_new_files ($) {
 			if (isinternal($page)) {
 				push @internal_new, $file;
 			}
-			else {
+			elsif ($config{rcs}) {
+				if (! $times_noted) {
+					debug(sprintf(gettext("querying %s for file creation and modification times.."), $config{rcs}));
+					$times_noted=1;
+				}
+
 				push @new, $file;
 				if ($config{gettime} && -e "$config{srcdir}/$file") {
 					eval {
@@ -377,7 +384,7 @@ sub find_new_files ($) {
 					}
 					my $mtime;
 					eval {
-						my $mtime=rcs_getmtime("$config{srcdir}/$file");
+						$mtime=rcs_getmtime("$config{srcdir}/$file");
 					};
 					if ($@) {
 						print STDERR $@;
diff --git a/debian/changelog b/debian/changelog
index 615d5916f..60a67cbe3 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -47,8 +47,15 @@ ikiwiki (3.20100415) UNRELEASED; urgency=low
   * Rename --getctime to --gettime. (The old name still works for
     backwards compatability.)
   * --gettime now also looks up last modification time.
+  * Automatically run --gettime the first time ikiwiki is run on 
+    a given srcdir.
   * Add rcs_getmtime to plugin API; currently only implemented
     for git.
+  * Optimise --gettime for git, so it's appropriatly screamingly
+    fast. (This could be done for other backends too.)
+  * However, --gettime for git no longer follows renames.
+  * Use above to fix up timestamps on docwiki, as well as ensure that
+    timestamps on basewiki files shipped in the deb are sane.
 
  -- Joey Hess <joeyh@debian.org>  Sun, 04 Apr 2010 12:17:11 -0400
 
diff --git a/debian/control b/debian/control
index 87f7d8209..ae06f32b0 100644
--- a/debian/control
+++ b/debian/control
@@ -7,7 +7,7 @@ Build-Depends-Indep: dpkg-dev (>= 1.9.0), libxml-simple-perl,
   libtimedate-perl, libhtml-template-perl,
   libhtml-scrubber-perl, wdg-html-validator,
   libhtml-parser-perl, liburi-perl, perlmagick, po4a (>= 0.34),
-  libfile-chdir-perl
+  libfile-chdir-perl,
 Maintainer: Joey Hess <joeyh@debian.org>
 Uploaders: Josh Triplett <josh@freedesktop.org>
 Standards-Version: 3.8.4
diff --git a/doc/plugins/write.mdwn b/doc/plugins/write.mdwn
index cf7044b2c..0bf6fcf48 100644
--- a/doc/plugins/write.mdwn
+++ b/doc/plugins/write.mdwn
@@ -1085,6 +1085,8 @@ it up in the history.
 
 It's ok if this is not implemented, and throws an error.
 
+If the RCS cannot determine a ctime for the file, return 0.
+
 #### `rcs_getmtime($)`
 
 This is used to get the page modification time for a file from the RCS, by
@@ -1092,6 +1094,8 @@ looking it up in the history.
 
 It's ok if this is not implemented, and throws an error.
 
+If the RCS cannot determine a mtime for the file, return 0.
+
 #### `rcs_receive()`
 
 This is called when ikiwiki is running as a pre-receive hook (or
diff --git a/doc/usage.mdwn b/doc/usage.mdwn
index 553fef01e..2e12517ea 100644
--- a/doc/usage.mdwn
+++ b/doc/usage.mdwn
@@ -320,7 +320,7 @@ also be configured using a setup file.
   intercepted. If you enable this option then you must run at least the 
   CGI portion of ikiwiki over SSL.
 
-* --gettime
+* --gettime, --no-gettime
 
   Extract creation and modification times for each new page from the
   the revision control's log. This is done automatically when building a
diff --git a/docwiki.setup b/docwiki.setup
index 8278b73ea..6bc200066 100644
--- a/docwiki.setup
+++ b/docwiki.setup
@@ -1,6 +1,18 @@
 #!/usr/bin/perl
 # Configuration file for ikiwiki to build its documentation wiki.
 
+# Use git during the build, if it's available and if we're building
+# from a git checkout. This ensures ikiwiki gets the right mtimes and
+# ctimes for files in the doc wiki.
+our $rcs="norcs";
+BEGIN {
+	my $git=`which git 2>&1`;
+	chomp $git;
+	if (-x $git && -d ".git") {
+		$rcs="git";
+	}
+}
+
 use IkiWiki::Setup::Standard {
 	wikiname => "ikiwiki",
 	srcdir => "doc",
@@ -9,7 +21,7 @@ use IkiWiki::Setup::Standard {
 	underlaydirbase => "underlays",
 	underlaydir => "underlays/basewiki",
 	discussion => 0,
-	exclude => qr/\/discussion|bugs\/*|todo\/*|forum\/*/,
+	exclude => qr/\/discussion|bugs\/*|todo\/*|forum\/*/, # save space
 	locale => '',
 	verbose => 1,
 	syslog => 0,
@@ -17,4 +29,7 @@ use IkiWiki::Setup::Standard {
 	usedirs => 0,
 	prefix_directives => 1,
 	add_plugins => [qw{goodstuff version haiku polygen fortune table}],
+	disable_plugins => [qw{recentchanges}], # not appropriate for doc dir
+	rcs => $rcs,
+	gitorigin_branch => '', # don't pull during build
 }
diff --git a/ikiwiki.in b/ikiwiki.in
index 801ff9a0b..acd37f802 100755
--- a/ikiwiki.in
+++ b/ikiwiki.in
@@ -45,7 +45,7 @@ sub getconfig () {
 			"usedirs!" => \$config{usedirs},
 			"prefix-directives!" => \$config{prefix_directives},
 			"getctime" => \$config{gettime},
-			"gettime" => \$config{gettime},
+			"gettime!" => \$config{gettime},
 			"numbacklinks=i" => \$config{numbacklinks},
 			"rcs=s" => \$config{rcs},
 			"no-rcs" => sub { $config{rcs}="" },