[PATCH/RFC V2 0/4] git-remote-mediawiki: new tool to preview local changes without pushing

@@ -0,0 +1,24 @@
+package GitMediawiki;
+
+use 5.008;
+use strict;
+use Git;
+
+BEGIN {
+
+our ($VERSION, @ISA, @EXPORT, @EXPORT_OK);
+
+# Totally unstable API.
+$VERSION = '0.01';
+
+require Exporter;
+
+@ISA = qw(Exporter);
+
+@EXPORT = ();
+
+# Methods which can be called as standalone functions as well:
+@EXPORT_OK = ();
+}
+
+1; # Famous last words

@@ -4,14 +4,29 @@
 #
 ## Build git-remote-mediawiki
 
+GIT_MEDIAWIKI_PM=GitMediawiki.pm
 SCRIPT_PERL=git-remote-mediawiki.perl
 GIT_ROOT_DIR=../..
 HERE=contrib/mw-to-git/
 
 SCRIPT_PERL_FULL=$(patsubst %,$(HERE)/%,$(SCRIPT_PERL))
+INSTLIBDIR=$(shell $(MAKE) -C $(GIT_ROOT_DIR)/perl \
+                -s --no-print-directory instlibdir)
 
 all: build
 
-build install clean:
+install_pm:
+	cp $(GIT_MEDIAWIKI_PM) $(INSTLIBDIR)
+
+build:
+	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \
+                build-perl-script
+
+install: install_pm
+	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \
+                install-perl-script
+
+clean:
 	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \
-                $@-perl-script
+                clean-perl-script
+	rm $(INSTLIBDIR)/$(GIT_MEDIAWIKI_PM)

@@ -18,7 +18,77 @@ require Exporter;
 @EXPORT = ();
 
 # Methods which can be called as standalone functions as well:
-@EXPORT_OK = ();
+@EXPORT_OK = qw(clean_filename smudge_filename connect_maybe);
+}
+
+# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced
+use constant SLASH_REPLACEMENT => '%2F';
+
+sub clean_filename {
+	my $filename = shift;
+	$filename =~ s{@{[SLASH_REPLACEMENT]}}{/}g;
+	# [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded.
+	# Do a variant of URL-encoding, i.e. looks like URL-encoding,
+	# but with _ added to prevent MediaWiki from thinking this is
+	# an actual special character.
+	$filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge;
+	# If we use the uri escape before
+	# we should unescape here, before anything
+
+	return $filename;
+}
+
+sub smudge_filename {
+	my $filename = shift;
+	$filename =~ s{/}{@{[SLASH_REPLACEMENT]}}g;
+	$filename =~ s/ /_/g;
+	# Decode forbidden characters encoded in clean_filename
+	$filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf('%c', hex($1))/ge;
+	return $filename;
+}
+
+sub connect_maybe {
+	my $wiki = shift;
+	if ($wiki) {
+		return $wiki;
+	}
+
+	my $remote_name = shift;
+	my $remote_url = shift;
+	my ($wiki_login, $wiki_password, $wiki_domain);
+
+	git_cmd_try {
+		$wiki_login = Git::config("remote.${remote_name}.mwLogin");
+		$wiki_password = Git::config("remote.${remote_name}.mwPassword");
+		$wiki_domain = Git::config("remote.${remote_name}.mwDomain");}
+		"%s failed w/ code %d";
+
+	$wiki = MediaWiki::API->new;
+	$wiki->{config}->{api_url} = "${remote_url}/api.php";
+	if ($wiki_login) {
+		my %credential = (
+			'url' => $remote_url,
+			'username' => $wiki_login,
+			'password' => $wiki_password
+		);
+		Git::credential(\%credential);
+		my $request = {lgname => $credential{username},
+			       lgpassword => $credential{password},
+			       lgdomain => $wiki_domain};
+		if ($wiki->login($request)) {
+			Git::credential(\%credential, 'approve');
+			print {*STDERR} qq(Logged in mediawiki user "$credential{username}".\n);
+		} else {
+			print {*STDERR} qq(Failed to log in mediawiki user "$credential{username}" on ${remote_url}\n);
+			print {*STDERR} '  (error ' .
+				$wiki->{error}->{code} . ': ' .
+				$wiki->{error}->{details} . ")\n";
+			Git::credential(\%credential, 'reject');
+			exit 1;
+		}
+	}
+
+	return $wiki;
 }
 
 1; # Famous last words

@@ -13,6 +13,8 @@
 
 use strict;
 use MediaWiki::API;
+use Git;
+use GitMediawiki qw(clean_filename smudge_filename connect_maybe);
 use DateTime::Format::ISO8601;
 
 # By default, use UTF-8 to communicate with Git and the user

@@ -24,9 +26,6 @@ use IPC::Open2;
 
 use warnings;
 
-# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced
-use constant SLASH_REPLACEMENT => "%2F";
-
 # It's not always possible to delete pages (may require some
 # privileges). Deleted pages are replaced with this content.
 use constant DELETED_CONTENT => "[[Category:Deleted]]\n";

@@ -159,36 +158,6 @@ while (<STDIN>) {
 # MediaWiki API instance, created lazily.
 my $mediawiki;
 
-sub mw_connect_maybe {
-	if ($mediawiki) {
-		return;
-	}
-	$mediawiki = MediaWiki::API->new;
-	$mediawiki->{config}->{api_url} = "$url/api.php";
-	if ($wiki_login) {
-		my %credential = (
-			'url' => $url,
-			'username' => $wiki_login,
-			'password' => $wiki_passwd
-		);
-		Git::credential(\%credential);
-		my $request = {lgname => $credential{username},
-			       lgpassword => $credential{password},
-			       lgdomain => $wiki_domain};
-		if ($mediawiki->login($request)) {
-			Git::credential(\%credential, 'approve');
-			print STDERR "Logged in mediawiki user \"$credential{username}\".\n";
-		} else {
-			print STDERR "Failed to log in mediawiki user \"$credential{username}\" on $url\n";
-			print STDERR "  (error " .
-				$mediawiki->{error}->{code} . ': ' .
-				$mediawiki->{error}->{details} . ")\n";
-			Git::credential(\%credential, 'reject');
-			exit 1;
-		}
-	}
-}
-
 sub fatal_mw_error {
 	my $action = shift;
 	print STDERR "fatal: could not $action.\n";

@@ -293,7 +262,7 @@ sub get_mw_first_pages {
 
 # Get the list of pages to be fetched according to configuration.
 sub get_mw_pages {
-	mw_connect_maybe();
+	$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 
 	print STDERR "Listing pages on remote wiki...\n";
 

@@ -480,7 +449,7 @@ my %basetimestamps;
 # avoid a loop onto all tracked pages. This is useful for the fetch-by-rev
 # option.
 sub get_last_global_remote_rev {
-	mw_connect_maybe();
+	$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 
 	my $query = {
 		action => 'query',

@@ -496,7 +465,7 @@ sub get_last_global_remote_rev {
 # Get the last remote revision concerning the tracked pages and the tracked
 # categories.
 sub get_last_remote_revision {
-	mw_connect_maybe();
+	$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 
 	my %pages_hash = get_mw_pages();
 	my @pages = values(%pages_hash);

@@ -552,29 +521,6 @@ sub mediawiki_smudge {
 	return $string."\n";
 }
 
-sub mediawiki_clean_filename {
-	my $filename = shift;
-	$filename =~ s/@{[SLASH_REPLACEMENT]}/\//g;
-	# [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded.
-	# Do a variant of URL-encoding, i.e. looks like URL-encoding,
-	# but with _ added to prevent MediaWiki from thinking this is
-	# an actual special character.
-	$filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge;
-	# If we use the uri escape before
-	# we should unescape here, before anything
-
-	return $filename;
-}
-
-sub mediawiki_smudge_filename {
-	my $filename = shift;
-	$filename =~ s/\//@{[SLASH_REPLACEMENT]}/g;
-	$filename =~ s/ /_/g;
-	# Decode forbidden characters encoded in mediawiki_clean_filename
-	$filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf("%c", hex($1))/ge;
-	return $filename;
-}
-
 sub literal_data {
 	my ($content) = @_;
 	print STDOUT "data ", bytes::length($content), "\n", $content;

@@ -775,7 +721,7 @@ sub mw_import_ref {
 		return;
 	}
 
-	mw_connect_maybe();
+	$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 
 	print STDERR "Searching revisions...\n";
 	my $last_local = get_last_local_revision();

@@ -888,7 +834,7 @@ sub mw_import_revids {
 		my %commit;
 		$commit{author} = $rev->{user} || 'Anonymous';
 		$commit{comment} = $rev->{comment} || EMPTY_MESSAGE;
-		$commit{title} = mediawiki_smudge_filename($page_title);
+		$commit{title} = smudge_filename($page_title);
 		$commit{mw_revision} = $rev->{revid};
 		$commit{content} = mediawiki_smudge($rev->{'*'});
 

@@ -949,7 +895,7 @@ sub mw_upload_file {
 	}
 	# Deleting and uploading a file requires a priviledged user
 	if ($file_deleted) {
-		mw_connect_maybe();
+		$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 		my $query = {
 			action => 'delete',
 			title => $path,

@@ -965,7 +911,7 @@ sub mw_upload_file {
 		# Don't let perl try to interpret file content as UTF-8 => use "raw"
 		my $content = run_git("cat-file blob $new_sha1", "raw");
 		if ($content ne "") {
-			mw_connect_maybe();
+			$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 			$mediawiki->{config}->{upload_url} =
 				"$url/index.php/Special:Upload";
 			$mediawiki->edit({

@@ -1013,7 +959,7 @@ sub mw_push_file {
 	my $old_sha1 = $diff_info_split[2];
 	my $page_created = ($old_sha1 eq NULL_SHA1);
 	my $page_deleted = ($new_sha1 eq NULL_SHA1);
-	$complete_file_name = mediawiki_clean_filename($complete_file_name);
+	$complete_file_name = clean_filename($complete_file_name);
 
 	my ($title, $extension) = $complete_file_name =~ /^(.*)\.([^\.]*)$/;
 	if (!defined($extension)) {

@@ -1036,7 +982,7 @@ sub mw_push_file {
 			$file_content = run_git("cat-file blob $new_sha1");
 		}
 
-		mw_connect_maybe();
+		$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 
 		my $result = $mediawiki->edit( {
 			action => 'edit',

@@ -1220,7 +1166,7 @@ sub mw_push_revision {
 }
 
 sub get_allowed_file_extensions {
-	mw_connect_maybe();
+	$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 
 	my $query = {
 		action => 'query',

@@ -1244,7 +1190,7 @@ my %cached_mw_namespace_id;
 # Return MediaWiki id for a canonical namespace name.
 # Ex.: "File", "Project".
 sub get_mw_namespace_id {
-	mw_connect_maybe();
+	$mediawiki = connect_maybe($mediawiki, $remotename, $url);
 	my $name = shift;
 
 	if (!exists $namespace_id{$name}) {

@@ -6,6 +6,7 @@
 
 GIT_MEDIAWIKI_PM=GitMediawiki.pm
 SCRIPT_PERL=git-remote-mediawiki.perl
+SCRIPT_PERL+=git-mw.perl
 GIT_ROOT_DIR=../..
 HERE=contrib/mw-to-git/
 

@@ -19,14 +20,14 @@ install_pm:
 	cp $(GIT_MEDIAWIKI_PM) $(INSTLIBDIR)
 
 build:
-	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \
+	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \
                 build-perl-script
 
 install: install_pm
-	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \
+	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \
                 install-perl-script
 
 clean:
-	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \
+	$(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \
                 clean-perl-script
 	rm $(INSTLIBDIR)/$(GIT_MEDIAWIKI_PM)

@@ -0,0 +1,46 @@
+#!/usr/bin/perl
+
+# Copyright (C) 2013
+#     Benoit Person <benoit.person@ensimag.imag.fr>
+#     Celestin Matte <celestin.matte@ensimag.imag.fr>
+# License: GPL v2 or later
+
+# Set of tools for git repo with a mediawiki remote.
+# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/
+
+use strict;
+use warnings;
+
+use Getopt::Long;
+
+my %commands = (
+	'help' =>
+		[\&help, {}, \&help]
+);
+
+# Search for sub-command
+my $cmd = $commands{'help'};
+for (my $i = 0; $i < @ARGV; $i++) {
+	if (defined $commands{$ARGV[$i]}) {
+		$cmd = $commands{$ARGV[$i]};
+		splice @ARGV, $i, 1;
+		last;
+	}
+};
+GetOptions( %{$cmd->[1]},
+	'help|h' => \&{$cmd->[2]});
+
+# Launch command
+&{$cmd->[0]};
+
+############################## Help Functions ##################################
+
+sub help {
+	print <<'END';
+usage: git mw <command> <args>
+
+git mw commands are:
+    Help        Display help information about git mw
+END
+	exit;
+}

@@ -12,10 +12,37 @@ use strict;
 use warnings;
 
 use Getopt::Long;
+use URI::URL qw(url);
+use IO::File;
+use LWP::Simple;
+use HTML::TreeBuilder;
+
+use Git;
+use MediaWiki::API;
+use GitMediawiki qw(smudge_filename connect_maybe);
+
+#preview parameters
+my $file_name;
+my $remote_name = '';
+my $preview_file_name = '';
+my $autoload = 0;
+my $blob = 0;
+sub file {
+	$file_name = shift;
+	return $file_name;
+}
 
 my %commands = (
 	'help' =>
-		[\&help, {}, \&help]
+		[\&help, {}, \&help],
+	'preview' =>
+		[\&preview, {
+			'<>' => \&file,
+			'output|o=s' => \$preview_file_name,
+			'remote|r=s' => \$remote_name,
+			'autoload|a' => \$autoload,
+			'blob|b' => \$blob
+		}, \&preview_help]
 );
 
 # Search for sub-command

@@ -33,6 +60,179 @@ GetOptions( %{$cmd->[1]},
 # Launch command
 &{$cmd->[0]};
 
+############################# Preview Functions ################################
+
+sub preview_help {
+	print <<'END';
+usage: git mw preview [--remote|-r <remote name>] [--autoload|-a]
+                      [--output|-o <output filename>] <filename>
+
+    -r, --remote    Specify which mediawiki should be used
+    -o, --output    Name of the output file
+    -a, --autoload  Autoload the page in your default web browser
+END
+	exit;
+}
+
+sub preview {
+	my $wiki;
+	my ($remote_url, $wiki_page_name);
+	my ($content, $content_tree, $template, $html_tree, $mw_content_text);
+	my $file_content;
+
+	# file_name argumeent is mandatory
+	if (! defined $file_name) {
+		die "File not set, see `git mw help` \n";
+	}
+
+	if ($blob) { # blob mode
+		$blob = $file_name;
+		if ($blob =~ /(.+):(.+)/) {
+			$file_name = $2;
+		}
+	} else { # file mode
+		if (! -e $file_name) {
+			die "File $file_name does not exists \n";
+		}
+	}
+
+	# Default preview_file_name is file_name with .html ext
+	if ($preview_file_name eq '') {
+		$preview_file_name = $file_name;
+		$preview_file_name =~ s/\.[^.]+$/.html/;
+	}
+
+	# Transform file_name into a mediawiki page name
+	$wiki_page_name = smudge_filename($file_name);
+	$wiki_page_name =~ s/\.[^.]+$//;
+
+	if ($remote_name eq '') {
+		# Search current branch upstream branch remote
+		$remote_name = git_cmd_try {
+			my $current_branch = 
+				Git::command_oneline('symbolic-ref', '--short', 'HEAD');
+			Git::config("branch.$current_branch.remote") }
+			"%s failed w/ code %d";
+
+		if ($remote_name) {
+			$remote_url = mediawiki_remote_url_maybe($remote_name);
+		}
+
+		# Search all possibles mediawiki remotes
+		if (! $remote_url) {
+			my @remotes = git_cmd_try {
+				Git::command('remote'); }
+				"%s failed w/ code%d";
+
+			my @valid_remotes = ();
+			foreach my $remote (@remotes) {
+				$remote_url = mediawiki_remote_url_maybe($remote);
+				if ($remote_url) {
+					push(@valid_remotes, $remote);
+				}
+			}
+
+			if ($#valid_remotes == 0) {
+				print "Can not find any mediawiki remote in this repo. \n";
+				exit 1;
+			} else {
+				print "There are multiple mediawiki remotes, which of:\n";
+				foreach my $remote (@remotes) {
+					print "\t$remote\n";
+				}
+				print "do you want ? Use the -r option to specify the remote\n";
+			}
+
+			exit 0;
+		}
+	} else {
+		# Check remote name
+		my @remotes = git_cmd_try {
+			Git::command('remote') }
+			"%s failed w/ code %d";
+		grep { $_ eq $remote_name } @remotes
+			or die "$remote_name is not a remote";
+	
+		# Find remote url
+		$remote_url = mediawiki_remote_url_maybe($remote_name);
+		if (! $remote_url) {
+			die "the remote you selected is not a mediawiki remote";
+		}
+	}
+
+	# Create and connect to the wiki if necessary
+	$wiki = connect_maybe($wiki, $remote_name, $remote_url);
+
+	# Read file content
+	if ($blob) {
+		$file_content = git_cmd_try {
+			Git::command('cat-file', 'blob', $blob); }
+			"%s failed w/ code %d";
+	} else {
+		open my $read_fh, "<", $file_name
+			or die "could not open $file_name: $!";
+		$file_content = do { local $/ = undef; <$read_fh> };
+		close $read_fh;
+	}
+
+	# Load template page
+	$template = get("$remote_url/index.php?title=$wiki_page_name")
+		or die "You need to create $wiki_page_name before previewing it";
+	$html_tree = HTML::TreeBuilder->new;
+	$html_tree->parse($template);
+
+	# Load new content
+	$content = $wiki->api({
+		action => 'parse',
+		text => $file_content,
+		title => $wiki_page_name
+	}) or die 'No response from distant mediawiki';
+	$content = $content->{'parse'}->{'text'}->{'*'};
+	$content_tree = HTML::TreeBuilder->new;
+	$content_tree->parse($content);
+
+	# Replace old content with new one
+	$mw_content_text = $html_tree->look_down('id', 'mw-content-text');
+	$mw_content_text->delete_content();
+	$mw_content_text->push_content($content_tree);
+
+	# Transform relative links into absolute ones
+	for (@{ $html_tree->extract_links() }) {
+		my ($link, $element, $attr) = @$_;
+		my $url = url($link)->canonical;
+		$element->attr($attr, URI->new_abs($url, $remote_url));
+	}
+
+	# Save the preview file
+	my $save_fh = IO::File->new($preview_file_name, 'w')
+		or die "Could not open: $!";
+	$save_fh->print($html_tree->as_HTML);
+
+	# Auto-loading in browser
+	if ($autoload) {
+		system('git', 'web--browse', $preview_file_name);
+	} else {
+		print "preview file saved as: $preview_file_name\n";
+	}
+
+	exit;
+}
+
+sub mediawiki_remote_url_maybe {
+	my $remote = shift;
+
+	# Find remote url
+	my $remote_url = git_cmd_try {
+		Git::config("remote.$remote.url") }
+		"%s failed w/ code %d";
+	if ($remote_url =~ s/mediawiki::(.*)/$1/) {
+		return url($remote_url)->canonical;
+	} else {
+		return undef;
+	}
+
+}
+
 ############################## Help Functions ##################################
 
 sub help {

@@ -41,6 +241,7 @@ usage: git mw <command> <args>
 
 git mw commands are:
     Help        Display help information about git mw
+    Preview 	Parse and render local file into HTML
 END
 	exit;
 }