diff options
Diffstat (limited to 'contrib/mw-to-git')
| -rw-r--r-- | contrib/mw-to-git/Makefile | 47 | ||||
| -rwxr-xr-x | contrib/mw-to-git/git-remote-mediawiki | 777 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/.gitignore | 4 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/Makefile | 31 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/README | 124 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/install-wiki.sh | 45 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/install-wiki/.gitignore | 1 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/install-wiki/LocalSettings.php | 129 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/install-wiki/db_install.php | 120 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/push-pull-tests.sh | 144 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/t9360-mw-to-git-clone.sh | 257 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh | 24 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh | 321 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh | 198 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/t9364-pull-by-rev.sh | 17 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/test-gitmw-lib.sh | 435 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/test-gitmw.pl | 225 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/test.config | 35 |
18 files changed, 2807 insertions, 127 deletions
diff --git a/contrib/mw-to-git/Makefile b/contrib/mw-to-git/Makefile new file mode 100644 index 0000000000..3ed728b0ef --- /dev/null +++ b/contrib/mw-to-git/Makefile @@ -0,0 +1,47 @@ +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +## Build git-remote-mediawiki + +-include ../../config.mak.autogen +-include ../../config.mak + +ifndef PERL_PATH + PERL_PATH = /usr/bin/perl +endif +ifndef gitexecdir + gitexecdir = $(shell git --exec-path) +endif + +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) +gitexecdir_SQ = $(subst ','\'',$(gitexecdir)) +SCRIPT = git-remote-mediawiki + +.PHONY: install help doc test clean + +help: + @echo 'This is the help target of the Makefile. Current configuration:' + @echo ' gitexecdir = $(gitexecdir_SQ)' + @echo ' PERL_PATH = $(PERL_PATH_SQ)' + @echo 'Run "$(MAKE) install" to install $(SCRIPT) in gitexecdir' + @echo 'Run "$(MAKE) test" to run the testsuite' + +install: + sed -e '1s|#!.*/perl|#!$(PERL_PATH_SQ)|' $(SCRIPT) \ + > '$(gitexecdir_SQ)/$(SCRIPT)' + chmod +x '$(gitexecdir)/$(SCRIPT)' + +doc: + @echo 'Sorry, "make doc" is not implemented yet for $(SCRIPT)' + +test: + $(MAKE) -C t/ test + +clean: + $(RM) '$(gitexecdir)/$(SCRIPT)' + $(MAKE) -C t/ clean diff --git a/contrib/mw-to-git/git-remote-mediawiki b/contrib/mw-to-git/git-remote-mediawiki index c18bfa1f15..68555d4265 100755 --- a/contrib/mw-to-git/git-remote-mediawiki +++ b/contrib/mw-to-git/git-remote-mediawiki @@ -9,40 +9,19 @@ # License: GPL v2 or later # Gateway between Git and MediaWiki. -# https://github.com/Bibzball/Git-Mediawiki/wiki -# -# Known limitations: -# -# - Only wiki pages are managed, no support for [[File:...]] -# attachments. -# -# - Poor performance in the best case: it takes forever to check -# whether we're up-to-date (on fetch or push) or to fetch a few -# revisions from a large wiki, because we use exclusively a -# page-based synchronization. We could switch to a wiki-wide -# synchronization when the synchronization involves few revisions -# but the wiki is large. -# -# - Git renames could be turned into MediaWiki renames (see TODO -# below) -# -# - login/password support requires the user to write the password -# cleartext in a file (see TODO below). -# -# - No way to import "one page, and all pages included in it" -# -# - Multiple remote MediaWikis have not been very well tested. +# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/ use strict; use MediaWiki::API; use DateTime::Format::ISO8601; -use encoding 'utf8'; -# use encoding 'utf8' doesn't change STDERROR -# but we're going to output UTF-8 filenames to STDERR +# By default, use UTF-8 to communicate with Git and the user binmode STDERR, ":utf8"; +binmode STDOUT, ":utf8"; use URI::Escape; +use IPC::Open2; + use warnings; # Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced @@ -59,6 +38,9 @@ use constant EMPTY_CONTENT => "<!-- empty page -->\n"; # used to reflect file creation or deletion in diff. use constant NULL_SHA1 => "0000000000000000000000000000000000000000"; +# Used on Git's side to reflect empty edit messages on the wiki +use constant EMPTY_MESSAGE => '*Empty MediaWiki Message*'; + my $remotename = $ARGV[0]; my $url = $ARGV[1]; @@ -71,10 +53,18 @@ chomp(@tracked_pages); my @tracked_categories = split(/[ \n]/, run_git("config --get-all remote.". $remotename .".categories")); chomp(@tracked_categories); +# Import media files on pull +my $import_media = run_git("config --get --bool remote.". $remotename .".mediaimport"); +chomp($import_media); +$import_media = ($import_media eq "true"); + +# Export media files on push +my $export_media = run_git("config --get --bool remote.". $remotename .".mediaexport"); +chomp($export_media); +$export_media = !($export_media eq "false"); + my $wiki_login = run_git("config --get remote.". $remotename .".mwLogin"); -# TODO: ideally, this should be able to read from keyboard, but we're -# inside a remote helper, so our stdin is connect to git, not to a -# terminal. +# Note: mwPassword is discourraged. Use the credential system instead. my $wiki_passwd = run_git("config --get remote.". $remotename .".mwPassword"); my $wiki_domain = run_git("config --get remote.". $remotename .".mwDomain"); chomp($wiki_login); @@ -86,6 +76,21 @@ my $shallow_import = run_git("config --get --bool remote.". $remotename .".shall chomp($shallow_import); $shallow_import = ($shallow_import eq "true"); +# Fetch (clone and pull) by revisions instead of by pages. This behavior +# is more efficient when we have a wiki with lots of pages and we fetch +# the revisions quite often so that they concern only few pages. +# Possible values: +# - by_rev: perform one query per new revision on the remote wiki +# - by_page: query each tracked page for new revision +my $fetch_strategy = run_git("config --get remote.$remotename.fetchStrategy"); +unless ($fetch_strategy) { + $fetch_strategy = run_git("config --get mediawiki.fetchStrategy"); +} +chomp($fetch_strategy); +unless ($fetch_strategy) { + $fetch_strategy = "by_page"; +} + # Dumb push: don't update notes and mediawiki ref to reflect the last push. # # Configurable with mediawiki.dumbPush, or per-remote with @@ -151,32 +156,152 @@ while (<STDIN>) { ########################## Functions ############################## +## credential API management (generic functions) + +sub credential_read { + my %credential; + my $reader = shift; + my $op = shift; + while (<$reader>) { + my ($key, $value) = /([^=]*)=(.*)/; + if (not defined $key) { + die "ERROR receiving response from git credential $op:\n$_\n"; + } + $credential{$key} = $value; + } + return %credential; +} + +sub credential_write { + my $credential = shift; + my $writer = shift; + # url overwrites other fields, so it must come first + print $writer "url=$credential->{url}\n" if exists $credential->{url}; + while (my ($key, $value) = each(%$credential) ) { + if (length $value && $key ne 'url') { + print $writer "$key=$value\n"; + } + } +} + +sub credential_run { + my $op = shift; + my $credential = shift; + my $pid = open2(my $reader, my $writer, "git credential $op"); + credential_write($credential, $writer); + print $writer "\n"; + close($writer); + + if ($op eq "fill") { + %$credential = credential_read($reader, $op); + } else { + if (<$reader>) { + die "ERROR while running git credential $op:\n$_"; + } + } + close($reader); + waitpid($pid, 0); + my $child_exit_status = $? >> 8; + if ($child_exit_status != 0) { + die "'git credential $op' failed with code $child_exit_status."; + } +} + # MediaWiki API instance, created lazily. my $mediawiki; sub mw_connect_maybe { if ($mediawiki) { - return; + return; } $mediawiki = MediaWiki::API->new; $mediawiki->{config}->{api_url} = "$url/api.php"; if ($wiki_login) { - if (!$mediawiki->login({ - lgname => $wiki_login, - lgpassword => $wiki_passwd, - lgdomain => $wiki_domain, - })) { - print STDERR "Failed to log in mediawiki user \"$wiki_login\" on $url\n"; - print STDERR "(error " . - $mediawiki->{error}->{code} . ': ' . - $mediawiki->{error}->{details} . ")\n"; - exit 1; + my %credential = (url => $url); + $credential{username} = $wiki_login; + $credential{password} = $wiki_passwd; + credential_run("fill", \%credential); + my $request = {lgname => $credential{username}, + lgpassword => $credential{password}, + lgdomain => $wiki_domain}; + if ($mediawiki->login($request)) { + credential_run("approve", \%credential); + print STDERR "Logged in mediawiki user \"$credential{username}\".\n"; } else { - print STDERR "Logged in with user \"$wiki_login\".\n"; + print STDERR "Failed to log in mediawiki user \"$credential{username}\" on $url\n"; + print STDERR " (error " . + $mediawiki->{error}->{code} . ': ' . + $mediawiki->{error}->{details} . ")\n"; + credential_run("reject", \%credential); + exit 1; + } + } +} + +## Functions for listing pages on the remote wiki +sub get_mw_tracked_pages { + my $pages = shift; + get_mw_page_list(\@tracked_pages, $pages); +} + +sub get_mw_page_list { + my $page_list = shift; + my $pages = shift; + my @some_pages = @$page_list; + while (@some_pages) { + my $last = 50; + if ($#some_pages < $last) { + $last = $#some_pages; + } + my @slice = @some_pages[0..$last]; + get_mw_first_pages(\@slice, $pages); + @some_pages = @some_pages[51..$#some_pages]; + } +} + +sub get_mw_tracked_categories { + my $pages = shift; + foreach my $category (@tracked_categories) { + if (index($category, ':') < 0) { + # Mediawiki requires the Category + # prefix, but let's not force the user + # to specify it. + $category = "Category:" . $category; + } + my $mw_pages = $mediawiki->list( { + action => 'query', + list => 'categorymembers', + cmtitle => $category, + cmlimit => 'max' } ) + || die $mediawiki->{error}->{code} . ': ' + . $mediawiki->{error}->{details}; + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; } } } +sub get_mw_all_pages { + my $pages = shift; + # No user-provided list, get the list of pages from the API. + my $mw_pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + aplimit => 'max' + }); + if (!defined($mw_pages)) { + print STDERR "fatal: could not get the list of wiki pages.\n"; + print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; + print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; + exit 1; + } + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } +} + +# queries the wiki for a set of pages. Meant to be used within a loop +# querying the wiki for slices of page list. sub get_mw_first_pages { my $some_pages = shift; my @some_pages = @{$some_pages}; @@ -205,70 +330,45 @@ sub get_mw_first_pages { } } +# Get the list of pages to be fetched according to configuration. sub get_mw_pages { mw_connect_maybe(); + print STDERR "Listing pages on remote wiki...\n"; + my %pages; # hash on page titles to avoid duplicates my $user_defined; if (@tracked_pages) { $user_defined = 1; # The user provided a list of pages titles, but we # still need to query the API to get the page IDs. - - my @some_pages = @tracked_pages; - while (@some_pages) { - my $last = 50; - if ($#some_pages < $last) { - $last = $#some_pages; - } - my @slice = @some_pages[0..$last]; - get_mw_first_pages(\@slice, \%pages); - @some_pages = @some_pages[51..$#some_pages]; - } + get_mw_tracked_pages(\%pages); } if (@tracked_categories) { $user_defined = 1; - foreach my $category (@tracked_categories) { - if (index($category, ':') < 0) { - # Mediawiki requires the Category - # prefix, but let's not force the user - # to specify it. - $category = "Category:" . $category; - } - my $mw_pages = $mediawiki->list( { - action => 'query', - list => 'categorymembers', - cmtitle => $category, - cmlimit => 'max' } ) - || die $mediawiki->{error}->{code} . ': ' . $mediawiki->{error}->{details}; - foreach my $page (@{$mw_pages}) { - $pages{$page->{title}} = $page; - } - } + get_mw_tracked_categories(\%pages); } if (!$user_defined) { - # No user-provided list, get the list of pages from - # the API. - my $mw_pages = $mediawiki->list({ - action => 'query', - list => 'allpages', - aplimit => 500, - }); - if (!defined($mw_pages)) { - print STDERR "fatal: could not get the list of wiki pages.\n"; - print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; - print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; - exit 1; - } - foreach my $page (@{$mw_pages}) { - $pages{$page->{title}} = $page; + get_mw_all_pages(\%pages); + } + if ($import_media) { + print STDERR "Getting media files for selected pages...\n"; + if ($user_defined) { + get_linked_mediafiles(\%pages); + } else { + get_all_mediafiles(\%pages); } } - return values(%pages); + print STDERR (scalar keys %pages) . " pages found.\n"; + return %pages; } +# usage: $out = run_git("command args"); +# $out = run_git("command args", "raw"); # don't interpret output as UTF-8. sub run_git { - open(my $git, "-|:encoding(UTF-8)", "git " . $_[0]); + my $args = shift; + my $encoding = (shift || "encoding(UTF-8)"); + open(my $git, "-|:$encoding", "git " . $args); my $res = do { local $/; <$git> }; close($git); @@ -276,6 +376,123 @@ sub run_git { } +sub get_all_mediafiles { + my $pages = shift; + # Attach list of all pages for media files from the API, + # they are in a different namespace, only one namespace + # can be queried at the same moment + my $mw_pages = $mediawiki->list({ + action => 'query', + list => 'allpages', + apnamespace => get_mw_namespace_id("File"), + aplimit => 'max' + }); + if (!defined($mw_pages)) { + print STDERR "fatal: could not get the list of pages for media files.\n"; + print STDERR "fatal: '$url' does not appear to be a mediawiki\n"; + print STDERR "fatal: make sure '$url/api.php' is a valid page.\n"; + exit 1; + } + foreach my $page (@{$mw_pages}) { + $pages->{$page->{title}} = $page; + } +} + +sub get_linked_mediafiles { + my $pages = shift; + my @titles = map $_->{title}, values(%{$pages}); + + # The query is split in small batches because of the MW API limit of + # the number of links to be returned (500 links max). + my $batch = 10; + while (@titles) { + if ($#titles < $batch) { + $batch = $#titles; + } + my @slice = @titles[0..$batch]; + + # pattern 'page1|page2|...' required by the API + my $mw_titles = join('|', @slice); + + # Media files could be included or linked from + # a page, get all related + my $query = { + action => 'query', + prop => 'links|images', + titles => $mw_titles, + plnamespace => get_mw_namespace_id("File"), + pllimit => 'max' + }; + my $result = $mediawiki->api($query); + + while (my ($id, $page) = each(%{$result->{query}->{pages}})) { + my @media_titles; + if (defined($page->{links})) { + my @link_titles = map $_->{title}, @{$page->{links}}; + push(@media_titles, @link_titles); + } + if (defined($page->{images})) { + my @image_titles = map $_->{title}, @{$page->{images}}; + push(@media_titles, @image_titles); + } + if (@media_titles) { + get_mw_page_list(\@media_titles, $pages); + } + } + + @titles = @titles[($batch+1)..$#titles]; + } +} + +sub get_mw_mediafile_for_page_revision { + # Name of the file on Wiki, with the prefix. + my $filename = shift; + my $timestamp = shift; + my %mediafile; + + # Search if on a media file with given timestamp exists on + # MediaWiki. In that case download the file. + my $query = { + action => 'query', + prop => 'imageinfo', + titles => "File:" . $filename, + iistart => $timestamp, + iiend => $timestamp, + iiprop => 'timestamp|archivename|url', + iilimit => 1 + }; + my $result = $mediawiki->api($query); + + my ($fileid, $file) = each( %{$result->{query}->{pages}} ); + # If not defined it means there is no revision of the file for + # given timestamp. + if (defined($file->{imageinfo})) { + $mediafile{title} = $filename; + + my $fileinfo = pop(@{$file->{imageinfo}}); + $mediafile{timestamp} = $fileinfo->{timestamp}; + # Mediawiki::API's download function doesn't support https URLs + # and can't download old versions of files. + print STDERR "\tDownloading file $mediafile{title}, version $mediafile{timestamp}\n"; + $mediafile{content} = download_mw_mediafile($fileinfo->{url}); + } + return %mediafile; +} + +sub download_mw_mediafile { + my $url = shift; + + my $response = $mediawiki->{ua}->get($url); + if ($response->code == 200) { + return $response->decoded_content; + } else { + print STDERR "Error downloading mediafile from :\n"; + print STDERR "URL: $url\n"; + print STDERR "Server response: " . $response->code . " " . $response->message . "\n"; + exit 1; + } +} + sub get_last_local_revision { # Get note regarding last mediawiki revision my $note = run_git("notes --ref=$remotename/mediawiki show refs/mediawiki/$remotename/master 2>/dev/null"); @@ -297,13 +514,36 @@ sub get_last_local_revision { # Remember the timestamp corresponding to a revision id. my %basetimestamps; +# Get the last remote revision without taking in account which pages are +# tracked or not. This function makes a single request to the wiki thus +# 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(); + + my $query = { + action => 'query', + list => 'recentchanges', + prop => 'revisions', + rclimit => '1', + rcdir => 'older', + }; + my $result = $mediawiki->api($query); + return $result->{query}->{recentchanges}[0]->{revid}; +} + +# Get the last remote revision concerning the tracked pages and the tracked +# categories. sub get_last_remote_revision { mw_connect_maybe(); - my @pages = get_mw_pages(); + my %pages_hash = get_mw_pages(); + my @pages = values(%pages_hash); my $max_rev_num = 0; + print STDERR "Getting last revision id on tracked pages...\n"; + foreach my $page (@pages) { my $id = $page->{pageid}; @@ -379,6 +619,16 @@ sub literal_data { print STDOUT "data ", bytes::length($content), "\n", $content; } +sub literal_data_raw { + # Output possibly binary content. + my ($content) = @_; + # Avoid confusion between size in bytes and in characters + utf8::downgrade($content); + binmode STDOUT, ":raw"; + print STDOUT "data ", bytes::length($content), "\n", $content; + binmode STDOUT, ":utf8"; +} + sub mw_capabilities { # Revisions are imported to the private namespace # refs/mediawiki/$remotename/ by the helper and fetched into @@ -466,6 +716,11 @@ sub import_file_revision { my %commit = %{$commit}; my $full_import = shift; my $n = shift; + my $mediafile = shift; + my %mediafile; + if ($mediafile) { + %mediafile = %{$mediafile}; + } my $title = $commit{title}; my $comment = $commit{comment}; @@ -485,6 +740,10 @@ sub import_file_revision { if ($content ne DELETED_CONTENT) { print STDOUT "M 644 inline $title.mw\n"; literal_data($content); + if (%mediafile) { + print STDOUT "M 644 inline $mediafile{title}\n"; + literal_data_raw($mediafile{content}); + } print STDOUT "\n\n"; } else { print STDOUT "D $title.mw\n"; @@ -547,8 +806,6 @@ sub mw_import_ref { mw_connect_maybe(); - my @pages = get_mw_pages(); - print STDERR "Searching revisions...\n"; my $last_local = get_last_local_revision(); my $fetch_from = $last_local + 1; @@ -557,36 +814,111 @@ sub mw_import_ref { } else { print STDERR ", fetching from here.\n"; } + + my $n = 0; + if ($fetch_strategy eq "by_rev") { + print STDERR "Fetching & writing export data by revs...\n"; + $n = mw_import_ref_by_revs($fetch_from); + } elsif ($fetch_strategy eq "by_page") { + print STDERR "Fetching & writing export data by pages...\n"; + $n = mw_import_ref_by_pages($fetch_from); + } else { + print STDERR "fatal: invalid fetch strategy \"$fetch_strategy\".\n"; + print STDERR "Check your configuration variables remote.$remotename.fetchStrategy and mediawiki.fetchStrategy\n"; + exit 1; + } + + if ($fetch_from == 1 && $n == 0) { + print STDERR "You appear to have cloned an empty MediaWiki.\n"; + # Something has to be done remote-helper side. If nothing is done, an error is + # thrown saying that HEAD is refering to unknown object 0000000000000000000 + # and the clone fails. + } +} + +sub mw_import_ref_by_pages { + + my $fetch_from = shift; + my %pages_hash = get_mw_pages(); + my @pages = values(%pages_hash); + my ($n, @revisions) = fetch_mw_revisions(\@pages, $fetch_from); - # Creation of the fast-import stream - print STDERR "Fetching & writing export data...\n"; + @revisions = sort {$a->{revid} <=> $b->{revid}} @revisions; + my @revision_ids = map $_->{revid}, @revisions; - $n = 0; + return mw_import_revids($fetch_from, \@revision_ids, \%pages_hash); +} + +sub mw_import_ref_by_revs { + + my $fetch_from = shift; + my %pages_hash = get_mw_pages(); + + my $last_remote = get_last_global_remote_rev(); + my @revision_ids = $fetch_from..$last_remote; + return mw_import_revids($fetch_from, \@revision_ids, \%pages_hash); +} + +# Import revisions given in second argument (array of integers). +# Only pages appearing in the third argument (hash indexed by page titles) +# will be imported. +sub mw_import_revids { + my $fetch_from = shift; + my $revision_ids = shift; + my $pages = shift; + + my $n = 0; + my $n_actual = 0; my $last_timestamp = 0; # Placeholer in case $rev->timestamp is undefined - foreach my $pagerevid (sort {$a->{revid} <=> $b->{revid}} @revisions) { + foreach my $pagerevid (@$revision_ids) { + # Count page even if we skip it, since we display + # $n/$total and $total includes skipped pages. + $n++; + # fetch the content of the pages my $query = { action => 'query', prop => 'revisions', rvprop => 'content|timestamp|comment|user|ids', - revids => $pagerevid->{revid}, + revids => $pagerevid, }; my $result = $mediawiki->api($query); - my $rev = pop(@{$result->{query}->{pages}->{$pagerevid->{pageid}}->{revisions}}); + if (!$result) { + die "Failed to retrieve modified page for revision $pagerevid"; + } - $n++; + if (defined($result->{query}->{badrevids}->{$pagerevid})) { + # The revision id does not exist on the remote wiki. + next; + } + + if (!defined($result->{query}->{pages})) { + die "Invalid revision $pagerevid."; + } + + my @result_pages = values(%{$result->{query}->{pages}}); + my $result_page = $result_pages[0]; + my $rev = $result_pages[0]->{revisions}->[0]; + + my $page_title = $result_page->{title}; + + if (!exists($pages->{$page_title})) { + print STDERR "$n/", scalar(@$revision_ids), + ": Skipping revision #$rev->{revid} of $page_title\n"; + next; + } + + $n_actual++; my %commit; $commit{author} = $rev->{user} || 'Anonymous'; - $commit{comment} = $rev->{comment} || '*Empty MediaWiki Message*'; - $commit{title} = mediawiki_smudge_filename( - $result->{query}->{pages}->{$pagerevid->{pageid}}->{title} - ); - $commit{mw_revision} = $pagerevid->{revid}; + $commit{comment} = $rev->{comment} || EMPTY_MESSAGE; + $commit{title} = mediawiki_smudge_filename($page_title); + $commit{mw_revision} = $rev->{revid}; $commit{content} = mediawiki_smudge($rev->{'*'}); if (!defined($rev->{timestamp})) { @@ -596,17 +928,23 @@ sub mw_import_ref { } $commit{date} = DateTime::Format::ISO8601->parse_datetime($last_timestamp); - print STDERR "$n/", scalar(@revisions), ": Revision #$pagerevid->{revid} of $commit{title}\n"; - - import_file_revision(\%commit, ($fetch_from == 1), $n); + # Differentiates classic pages and media files. + my ($namespace, $filename) = $page_title =~ /^([^:]*):(.*)$/; + my %mediafile; + if ($namespace) { + my $id = get_mw_namespace_id($namespace); + if ($id && $id == get_mw_namespace_id("File")) { + %mediafile = get_mw_mediafile_for_page_revision($filename, $rev->{timestamp}); + } + } + # If this is a revision of the media page for new version + # of a file do one common commit for both file and media page. + # Else do commit only for that page. + print STDERR "$n/", scalar(@$revision_ids), ": Revision #$rev->{revid} of $commit{title}\n"; + import_file_revision(\%commit, ($fetch_from == 1), $n_actual, \%mediafile); } - if ($fetch_from == 1 && $n == 0) { - print STDERR "You appear to have cloned an empty MediaWiki.\n"; - # Something has to be done remote-helper side. If nothing is done, an error is - # thrown saying that HEAD is refering to unknown object 0000000000000000000 - # and the clone fails. - } + return $n_actual; } sub error_non_fast_forward { @@ -624,6 +962,63 @@ sub error_non_fast_forward { return 0; } +sub mw_upload_file { + my $complete_file_name = shift; + my $new_sha1 = shift; + my $extension = shift; + my $file_deleted = shift; + my $summary = shift; + my $newrevid; + my $path = "File:" . $complete_file_name; + my %hashFiles = get_allowed_file_extensions(); + if (!exists($hashFiles{$extension})) { + print STDERR "$complete_file_name is not a permitted file on this wiki.\n"; + print STDERR "Check the configuration of file uploads in your mediawiki.\n"; + return $newrevid; + } + # Deleting and uploading a file requires a priviledged user + if ($file_deleted) { + mw_connect_maybe(); + my $query = { + action => 'delete', + title => $path, + reason => $summary + }; + if (!$mediawiki->edit($query)) { + print STDERR "Failed to delete file on remote wiki\n"; + print STDERR "Check your permissions on the remote site. Error code:\n"; + print STDERR $mediawiki->{error}->{code} . ':' . $mediawiki->{error}->{details}; + exit 1; + } + } else { + # 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(); + $mediawiki->{config}->{upload_url} = + "$url/index.php/Special:Upload"; + $mediawiki->edit({ + action => 'upload', + filename => $complete_file_name, + comment => $summary, + file => [undef, + $complete_file_name, + Content => $content], + ignorewarnings => 1, + }, { + skip_encoding => 1 + } ) || die $mediawiki->{error}->{code} . ':' + . $mediawiki->{error}->{details}; + my $last_file_page = $mediawiki->get_page({title => $path}); + $newrevid = $last_file_page->{revid}; + print STDERR "Pushed file: $new_sha1 - $complete_file_name.\n"; + } else { + print STDERR "Empty file $complete_file_name not pushed.\n"; + } + } + return $newrevid; +} + sub mw_push_file { my $diff_info = shift; # $diff_info contains a string in this format: @@ -636,7 +1031,12 @@ sub mw_push_file { my $summary = shift; # MediaWiki revision number. Keep the previous one by default, # in case there's no edit to perform. - my $newrevid = shift; + my $oldrevid = shift; + my $newrevid; + + if ($summary eq EMPTY_MESSAGE) { + $summary = ''; + } my $new_sha1 = $diff_info_split[3]; my $old_sha1 = $diff_info_split[2]; @@ -644,9 +1044,16 @@ sub mw_push_file { my $page_deleted = ($new_sha1 eq NULL_SHA1); $complete_file_name = mediawiki_clean_filename($complete_file_name); - if (substr($complete_file_name,-3) eq ".mw") { - my $title = substr($complete_file_name,0,-3); - + my ($title, $extension) = $complete_file_name =~ /^(.*)\.([^\.]*)$/; + if (!defined($extension)) { + $extension = ""; + } + if ($extension eq "mw") { + my $ns = get_mw_namespace_id_for_page($complete_file_name); + if ($ns && $ns == get_mw_namespace_id("File") && (!$export_media)) { + print STDERR "Ignoring media file related page: $complete_file_name\n"; + return ($oldrevid, "ok"); + } my $file_content; if ($page_deleted) { # Deleting a page usually requires @@ -664,7 +1071,7 @@ sub mw_push_file { action => 'edit', summary => $summary, title => $title, - basetimestamp => $basetimestamps{$newrevid}, + basetimestamp => $basetimestamps{$oldrevid}, text => mediawiki_clean($file_content, $page_created), }, { skip_encoding => 1 # Helps with names with accentuated characters @@ -676,7 +1083,7 @@ sub mw_push_file { $mediawiki->{error}->{code} . ' from mediwiki: ' . $mediawiki->{error}->{details} . ".\n"; - return ($newrevid, "non-fast-forward"); + return ($oldrevid, "non-fast-forward"); } else { # Other errors. Shouldn't happen => just die() die 'Fatal: Error ' . @@ -686,9 +1093,14 @@ sub mw_push_file { } $newrevid = $result->{edit}->{newrevid}; print STDERR "Pushed file: $new_sha1 - $title\n"; + } elsif ($export_media) { + $newrevid = mw_upload_file($complete_file_name, $new_sha1, + $extension, $page_deleted, + $summary); } else { - print STDERR "$complete_file_name not a mediawiki file (Not pushable on this version of git-remote-mediawiki).\n" + print STDERR "Ignoring media file $title\n"; } + $newrevid = ($newrevid or $oldrevid); return ($newrevid, "ok"); } @@ -760,16 +1172,26 @@ sub mw_push_revision { if ($last_local_revid > 0) { my $parsed_sha1 = $remoteorigin_sha1; # Find a path from last MediaWiki commit to pushed commit + print STDERR "Computing path from local to remote ...\n"; + my @local_ancestry = split(/\n/, run_git("rev-list --boundary --parents $local ^$parsed_sha1")); + my %local_ancestry; + foreach my $line (@local_ancestry) { + if (my ($child, $parents) = $line =~ m/^-?([a-f0-9]+) ([a-f0-9 ]+)/) { + foreach my $parent (split(' ', $parents)) { + $local_ancestry{$parent} = $child; + } + } elsif (!$line =~ m/^([a-f0-9]+)/) { + die "Unexpected output from git rev-list: $line"; + } + } while ($parsed_sha1 ne $HEAD_sha1) { - my @commit_info = grep(/^$parsed_sha1/, split(/\n/, run_git("rev-list --children $local"))); - if (!@commit_info) { + my $child = $local_ancestry{$parsed_sha1}; + if (!$child) { + printf STDERR "Cannot find a path in history from remote commit to last commit\n"; return error_non_fast_forward($remote); } - my @commit_info_split = split(/ |\n/, $commit_info[0]); - # $commit_info_split[1] is the sha1 of the commit to export - # $commit_info_split[0] is the sha1 of its direct child - push(@commit_pairs, \@commit_info_split); - $parsed_sha1 = $commit_info_split[1]; + push(@commit_pairs, [$parsed_sha1, $child]); + $parsed_sha1 = $child; } } else { # No remote mediawiki revision. Export the whole @@ -791,8 +1213,8 @@ sub mw_push_revision { # TODO: we could detect rename, and encode them with a #redirect on the wiki. # TODO: for now, it's just a delete+add my @diff_info_list = split(/\0/, $diff_infos); - # Keep the first line of the commit message as mediawiki comment for the revision - my $commit_msg = (split(/\n/, run_git("show --pretty=format:\"%s\" $sha1_commit")))[0]; + # Keep the subject line of the commit message as mediawiki comment for the revision + my $commit_msg = run_git("log --no-walk --format=\"%s\" $sha1_commit"); chomp($commit_msg); # Push every blob while (@diff_info_list) { @@ -817,7 +1239,7 @@ sub mw_push_revision { } } unless ($dumb_push) { - run_git("notes --ref=$remotename/mediawiki add -m \"mediawiki_revision: $mw_revision\" $sha1_commit"); + run_git("notes --ref=$remotename/mediawiki add -f -m \"mediawiki_revision: $mw_revision\" $sha1_commit"); run_git("update-ref -m \"Git-MediaWiki push\" refs/mediawiki/$remotename/master $sha1_commit $sha1_child"); } } @@ -825,3 +1247,104 @@ sub mw_push_revision { print STDOUT "ok $remote\n"; return 1; } + +sub get_allowed_file_extensions { + mw_connect_maybe(); + + my $query = { + action => 'query', + meta => 'siteinfo', + siprop => 'fileextensions' + }; + my $result = $mediawiki->api($query); + my @file_extensions= map $_->{ext},@{$result->{query}->{fileextensions}}; + my %hashFile = map {$_ => 1}@file_extensions; + + return %hashFile; +} + +# In memory cache for MediaWiki namespace ids. +my %namespace_id; + +# Namespaces whose id is cached in the configuration file +# (to avoid duplicates) +my %cached_mw_namespace_id; + +# Return MediaWiki id for a canonical namespace name. +# Ex.: "File", "Project". +sub get_mw_namespace_id { + mw_connect_maybe(); + my $name = shift; + + if (!exists $namespace_id{$name}) { + # Look at configuration file, if the record for that namespace is + # already cached. Namespaces are stored in form: + # "Name_of_namespace:Id_namespace", ex.: "File:6". + my @temp = split(/[\n]/, run_git("config --get-all remote." + . $remotename .".namespaceCache")); + chomp(@temp); + foreach my $ns (@temp) { + my ($n, $id) = split(/:/, $ns); + if ($id eq 'notANameSpace') { + $namespace_id{$n} = {is_namespace => 0}; + } else { + $namespace_id{$n} = {is_namespace => 1, id => $id}; + } + $cached_mw_namespace_id{$n} = 1; + } + } + + if (!exists $namespace_id{$name}) { + print STDERR "Namespace $name not found in cache, querying the wiki ...\n"; + # NS not found => get namespace id from MW and store it in + # configuration file. + my $query = { + action => 'query', + meta => 'siteinfo', + siprop => 'namespaces' + }; + my $result = $mediawiki->api($query); + + while (my ($id, $ns) = each(%{$result->{query}->{namespaces}})) { + if (defined($ns->{id}) && defined($ns->{canonical})) { + $namespace_id{$ns->{canonical}} = {is_namespace => 1, id => $ns->{id}}; + if ($ns->{'*'}) { + # alias (e.g. french Fichier: as alias for canonical File:) + $namespace_id{$ns->{'*'}} = {is_namespace => 1, id => $ns->{id}}; + } + } + } + } + + my $ns = $namespace_id{$name}; + my $id; + + unless (defined $ns) { + print STDERR "No such namespace $name on MediaWiki.\n"; + $ns = {is_namespace => 0}; + $namespace_id{$name} = $ns; + } + + if ($ns->{is_namespace}) { + $id = $ns->{id}; + } + + # Store "notANameSpace" as special value for inexisting namespaces + my $store_id = ($id || 'notANameSpace'); + + # Store explicitely requested namespaces on disk + if (!exists $cached_mw_namespace_id{$name}) { + run_git("config --add remote.". $remotename + .".namespaceCache \"". $name .":". $store_id ."\""); + $cached_mw_namespace_id{$name} = 1; + } + return $id; +} + +sub get_mw_namespace_id_for_page { + if (my ($namespace) = $_[0] =~ /^([^:]*):/) { + return get_mw_namespace_id($namespace); + } else { + return; + } +} diff --git a/contrib/mw-to-git/t/.gitignore b/contrib/mw-to-git/t/.gitignore new file mode 100644 index 0000000000..a7a40b4964 --- /dev/null +++ b/contrib/mw-to-git/t/.gitignore @@ -0,0 +1,4 @@ +WEB/ +wiki/ +trash directory.t*/ +test-results/ diff --git a/contrib/mw-to-git/t/Makefile b/contrib/mw-to-git/t/Makefile new file mode 100644 index 0000000000..f422203fa0 --- /dev/null +++ b/contrib/mw-to-git/t/Makefile @@ -0,0 +1,31 @@ +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +## Test git-remote-mediawiki + +all: test + +-include ../../../config.mak.autogen +-include ../../../config.mak + +T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) + +.PHONY: help test clean all + +help: + @echo 'Run "$(MAKE) test" to launch test scripts' + @echo 'Run "$(MAKE) clean" to remove trash folders' + +test: + @for t in $(T); do \ + echo "$$t"; \ + "./$$t" || exit 1; \ + done + +clean: + $(RM) -r 'trash directory'.* diff --git a/contrib/mw-to-git/t/README b/contrib/mw-to-git/t/README new file mode 100644 index 0000000000..96e97390cf --- /dev/null +++ b/contrib/mw-to-git/t/README @@ -0,0 +1,124 @@ +Tests for Mediawiki-to-Git +========================== + +Introduction +------------ +This manual describes how to install the git-remote-mediawiki test +environment on a machine with git installed on it. + +Prerequisite +------------ + +In order to run this test environment correctly, you will need to +install the following packages (Debian/Ubuntu names, may need to be +adapted for another distribution): + +* lighttpd +* php5 +* php5-cgi +* php5-cli +* php5-curl +* php5-sqlite + +Principles and Technical Choices +-------------------------------- + +The test environment makes it easy to install and manipulate one or +several MediaWiki instances. To allow developers to run the testsuite +easily, the environment does not require root priviledge (except to +install the required packages if needed). It starts a webserver +instance on the user's account (using lighttpd greatly helps for +that), and does not need a separate database daemon (thanks to the use +of sqlite). + +Run the test environment +------------------------ + +Install a new wiki +~~~~~~~~~~~~~~~~~~ + +Once you have all the prerequisite, you need to install a MediaWiki +instance on your machine. If you already have one, it is still +strongly recommended to install one with the script provided. Here's +how to work it: + +a. change directory to contrib/mw-to-git/t/ +b. if needed, edit test.config to choose your installation parameters +c. run `./install-wiki.sh install` +d. check on your favourite web browser if your wiki is correctly + installed. + +Remove an existing wiki +~~~~~~~~~~~~~~~~~~~~~~~ + +Edit the file test.config to fit the wiki you want to delete, and then +execute the command `./install-wiki.sh delete` from the +contrib/mw-to-git/t directory. + +Run the existing tests +~~~~~~~~~~~~~~~~~~~~~~ + +The provided tests are currently in the `contrib/mw-to-git/t` directory. +The files are all the t936[0-9]-*.sh shell scripts. + +a. Run all tests: +To do so, run "make test" from the contrib/mw-to-git/ directory. + +b. Run a specific test: +To run a given test <test_name>, run ./<test_name> from the +contrib/mw-to-git/t directory. + +How to create new tests +----------------------- + +Available functions +~~~~~~~~~~~~~~~~~~~ + +The test environment of git-remote-mediawiki provides some functions +useful to test its behaviour. for more details about the functions' +parameters, please refer to the `test-gitmw-lib.sh` and +`test-gitmw.pl` files. + +** `test_check_wiki_precond`: +Check if the tests must be skipped or not. Please use this function +at the beggining of each new test file. + +** `wiki_getpage`: +Fetch a given page from the wiki and puts its content in the +directory in parameter. + +** `wiki_delete_page`: +Delete a given page from the wiki. + +** `wiki_edit_page`: +Create or modify a given page in the wiki. You can specify several +parameters like a summary for the page edition, or add the page to a +given category. +See test-gitmw.pl for more details. + +** `wiki_getallpage`: +Fetch all pages from the wiki into a given directory. The directory +is created if it does not exists. + +** `test_diff_directories`: +Compare the content of two directories. The content must be the same. +Use this function to compare the content of a git directory and a wiki +one created by wiki_getallpage. + +** `test_contains_N_files`: +Check if the given directory contains a given number of file. + +** `wiki_page_exists`: +Tests if a given page exists on the wiki. + +** `wiki_reset`: +Reset the wiki, i.e. flush the database. Use this function at the +begining of each new test, except if the test re-uses the same wiki +(and history) as the previous test. + +How to write a new test +~~~~~~~~~~~~~~~~~~~~~~~ + +Please, follow the standards given by git. See git/t/README. +New file should be named as t936[0-9]-*.sh. +Be sure to reset your wiki regulary with the function `wiki_reset`. diff --git a/contrib/mw-to-git/t/install-wiki.sh b/contrib/mw-to-git/t/install-wiki.sh new file mode 100755 index 0000000000..c6d6fa3aef --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki.sh @@ -0,0 +1,45 @@ +#!/bin/sh + +# This script installs or deletes a MediaWiki on your computer. +# It requires a web server with PHP and SQLite running. In addition, if you +# do not have MediaWiki sources on your computer, the option 'install' +# downloads them for you. +# Please set the CONFIGURATION VARIABLES in ./test-gitmw-lib.sh + +WIKI_TEST_DIR=$(cd "$(dirname "$0")" && pwd) + +if test -z "$WIKI_TEST_DIR" +then + WIKI_TEST_DIR=. +fi + +. "$WIKI_TEST_DIR"/test-gitmw-lib.sh +usage () { + echo "Usage: " + echo " ./install-wiki.sh <install | delete | --help>" + echo " install | -i : Install a wiki on your computer." + echo " delete | -d : Delete the wiki and all its pages and " + echo " content." +} + + +# Argument: install, delete, --help | -h +case "$1" in + "install" | "-i") + wiki_install + exit 0 + ;; + "delete" | "-d") + wiki_delete + exit 0 + ;; + "--help" | "-h") + usage + exit 0 + ;; + *) + echo "Invalid argument: $1" + usage + exit 1 + ;; +esac diff --git a/contrib/mw-to-git/t/install-wiki/.gitignore b/contrib/mw-to-git/t/install-wiki/.gitignore new file mode 100644 index 0000000000..b5a2a4408c --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki/.gitignore @@ -0,0 +1 @@ +wikidb.sqlite diff --git a/contrib/mw-to-git/t/install-wiki/LocalSettings.php b/contrib/mw-to-git/t/install-wiki/LocalSettings.php new file mode 100644 index 0000000000..29f125116b --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki/LocalSettings.php @@ -0,0 +1,129 @@ +<?php +# This file was automatically generated by the MediaWiki 1.19.0 +# installer. If you make manual changes, please keep track in case you +# need to recreate them later. +# +# See includes/DefaultSettings.php for all configurable settings +# and their default values, but don't forget to make changes in _this_ +# file, not there. +# +# Further documentation for configuration settings may be found at: +# http://www.mediawiki.org/wiki/Manual:Configuration_settings + +# Protect against web entry +if ( !defined( 'MEDIAWIKI' ) ) { + exit; +} + +## Uncomment this to disable output compression +# $wgDisableOutputCompression = true; + +$wgSitename = "Git-MediaWiki-Test"; +$wgMetaNamespace = "Git-MediaWiki-Test"; + +## The URL base path to the directory containing the wiki; +## defaults for all runtime URL paths are based off of this. +## For more information on customizing the URLs please see: +## http://www.mediawiki.org/wiki/Manual:Short_URL +$wgScriptPath = "@WG_SCRIPT_PATH@"; +$wgScriptExtension = ".php"; + +## The protocol and server name to use in fully-qualified URLs +$wgServer = "@WG_SERVER@"; + +## The relative URL path to the skins directory +$wgStylePath = "$wgScriptPath/skins"; + +## The relative URL path to the logo. Make sure you change this from the default, +## or else you'll overwrite your logo when you upgrade! +$wgLogo = "$wgStylePath/common/images/wiki.png"; + +## UPO means: this is also a user preference option + +$wgEnableEmail = true; +$wgEnableUserEmail = true; # UPO + +$wgEmergencyContact = "apache@localhost"; +$wgPasswordSender = "apache@localhost"; + +$wgEnotifUserTalk = false; # UPO +$wgEnotifWatchlist = false; # UPO +$wgEmailAuthentication = true; + +## Database settings +$wgDBtype = "sqlite"; +$wgDBserver = ""; +$wgDBname = "@WG_SQLITE_DATAFILE@"; +$wgDBuser = ""; +$wgDBpassword = ""; + +# SQLite-specific settings +$wgSQLiteDataDir = "@WG_SQLITE_DATADIR@"; + + +## Shared memory settings +$wgMainCacheType = CACHE_NONE; +$wgMemCachedServers = array(); + +## To enable image uploads, make sure the 'images' directory +## is writable, then set this to true: +$wgEnableUploads = true; +$wgUseImageMagick = true; +$wgImageMagickConvertCommand ="@CONVERT@"; +$wgFileExtensions[] = 'txt'; + +# InstantCommons allows wiki to use images from http://commons.wikimedia.org +$wgUseInstantCommons = false; + +## If you use ImageMagick (or any other shell command) on a +## Linux server, this will need to be set to the name of an +## available UTF-8 locale +$wgShellLocale = "en_US.utf8"; + +## If you want to use image uploads under safe mode, +## create the directories images/archive, images/thumb and +## images/temp, and make them all writable. Then uncomment +## this, if it's not already uncommented: +#$wgHashedUploadDirectory = false; + +## Set $wgCacheDirectory to a writable directory on the web server +## to make your wiki go slightly faster. The directory should not +## be publically accessible from the web. +#$wgCacheDirectory = "$IP/cache"; + +# Site language code, should be one of the list in ./languages/Names.php +$wgLanguageCode = "en"; + +$wgSecretKey = "1c912bfe3519fb70f5dc523ecc698111cd43d81a11c585b3eefb28f29c2699b7"; +#$wgSecretKey = "@SECRETKEY@"; + + +# Site upgrade key. Must be set to a string (default provided) to turn on the +# web installer while LocalSettings.php is in place +$wgUpgradeKey = "ddae7dc87cd0a645"; + +## Default skin: you can change the default skin. Use the internal symbolic +## names, ie 'standard', 'nostalgia', 'cologneblue', 'monobook', 'vector': +$wgDefaultSkin = "vector"; + +## For attaching licensing metadata to pages, and displaying an +## appropriate copyright notice / icon. GNU Free Documentation +## License and Creative Commons licenses are supported so far. +$wgRightsPage = ""; # Set to the title of a wiki page that describes your license/copyright +$wgRightsUrl = ""; +$wgRightsText = ""; +$wgRightsIcon = ""; + +# Path to the GNU diff3 utility. Used for conflict resolution. +$wgDiff3 = "/usr/bin/diff3"; + +# Query string length limit for ResourceLoader. You should only set this if +# your web server has a query string length limit (then set it to that limit), +# or if you have suhosin.get.max_value_length set in php.ini (then set it to +# that value) +$wgResourceLoaderMaxQueryLength = -1; + + + +# End of automatically generated settings. +# Add more configuration options below. diff --git a/contrib/mw-to-git/t/install-wiki/db_install.php b/contrib/mw-to-git/t/install-wiki/db_install.php new file mode 100644 index 0000000000..0f3f4e018a --- /dev/null +++ b/contrib/mw-to-git/t/install-wiki/db_install.php @@ -0,0 +1,120 @@ +<?php +/** + * This script generates a SQLite database for a MediaWiki version 1.19.0 + * You must specify the login of the admin (argument 1) and its + * password (argument 2) and the folder where the database file + * is located (absolute path in argument 3). + * It is used by the script install-wiki.sh in order to make easy the + * installation of a MediaWiki. + * + * In order to generate a SQLite database file, MediaWiki ask the user + * to submit some forms in its web browser. This script simulates this + * behavior though the functions <get> and <submit> + * + */ +$argc = $_SERVER['argc']; +$argv = $_SERVER['argv']; + +$login = $argv[2]; +$pass = $argv[3]; +$tmp = $argv[4]; +$port = $argv[5]; + +$url = 'http://localhost:'.$port.'/wiki/mw-config/index.php'; +$db_dir = urlencode($tmp); +$tmp_cookie = tempnam($tmp, "COOKIE_"); +/* + * Fetchs a page with cURL. + */ +function get($page_name = "") { + $curl = curl_init(); + $page_name_add = ""; + if ($page_name != "") { + $page_name_add = '?page='.$page_name; + } + $url = $GLOBALS['url'].$page_name_add; + $tmp_cookie = $GLOBALS['tmp_cookie']; + curl_setopt($curl, CURLOPT_COOKIEJAR, $tmp_cookie); + curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); + curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); + curl_setopt($curl, CURLOPT_COOKIEFILE, $tmp_cookie); + curl_setopt($curl, CURLOPT_HEADER, true); + curl_setopt($curl, CURLOPT_URL, $url); + + $page = curl_exec($curl); + if (!$page) { + die("Could not get page: $url\n"); + } + curl_close($curl); + return $page; +} + +/* + * Submits a form with cURL. + */ +function submit($page_name, $option = "") { + $curl = curl_init(); + $datapost = 'submit-continue=Continue+%E2%86%92'; + if ($option != "") { + $datapost = $option.'&'.$datapost; + } + $url = $GLOBALS['url'].'?page='.$page_name; + $tmp_cookie = $GLOBALS['tmp_cookie']; + curl_setopt($curl, CURLOPT_URL, $url); + curl_setopt($curl, CURLOPT_POST, true); + curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); + curl_setopt($curl, CURLOPT_POSTFIELDS, $datapost); + curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); + curl_setopt($curl, CURLOPT_COOKIEJAR, $tmp_cookie); + curl_setopt($curl, CURLOPT_COOKIEFILE, $tmp_cookie); + + $page = curl_exec($curl); + if (!$page) { + die("Could not get page: $url\n"); + } + curl_close($curl); + return "$page"; +} + +/* + * Here starts this script: simulates the behavior of the user + * submitting forms to generates the database file. + * Note this simulation was made for the MediaWiki version 1.19.0, + * we can't assume it works with other versions. + * + */ + +$page = get(); +if (!preg_match('/input type="hidden" value="([0-9]+)" name="LanguageRequestTime"/', + $page, $matches)) { + echo "Unexpected content for page downloaded:\n"; + echo "$page"; + die; +}; +$timestamp = $matches[1]; +$language = "LanguageRequestTime=$timestamp&uselang=en&ContLang=en"; +$page = submit('Language', $language); + +submit('Welcome'); + +$db_config = 'DBType=sqlite'; +$db_config = $db_config.'&sqlite_wgSQLiteDataDir='.$db_dir; +$db_config = $db_config.'&sqlite_wgDBname='.$argv[1]; +submit('DBConnect', $db_config); + +$wiki_config = 'config_wgSitename=TEST'; +$wiki_config = $wiki_config.'&config__NamespaceType=site-name'; +$wiki_config = $wiki_config.'&config_wgMetaNamespace=MyWiki'; +$wiki_config = $wiki_config.'&config__AdminName='.$login; + +$wiki_config = $wiki_config.'&config__AdminPassword='.$pass; +$wiki_config = $wiki_config.'&config__AdminPassword2='.$pass; + +$wiki_config = $wiki_config.'&wiki__configEmail=email%40email.org'; +$wiki_config = $wiki_config.'&config__SkipOptional=skip'; +submit('Name', $wiki_config); +submit('Install'); +submit('Install'); + +unlink($tmp_cookie); +?> diff --git a/contrib/mw-to-git/t/push-pull-tests.sh b/contrib/mw-to-git/t/push-pull-tests.sh new file mode 100644 index 0000000000..9da2dc5ff0 --- /dev/null +++ b/contrib/mw-to-git/t/push-pull-tests.sh @@ -0,0 +1,144 @@ +test_push_pull () { + + test_expect_success 'Git pull works after adding a new wiki page' ' + wiki_reset && + + git clone mediawiki::'"$WIKI_URL"' mw_dir_1 && + wiki_editpage Foo "page created after the git clone" false && + + ( + cd mw_dir_1 && + git pull + ) && + + wiki_getallpage ref_page_1 && + test_diff_directories mw_dir_1 ref_page_1 + ' + + test_expect_success 'Git pull works after editing a wiki page' ' + wiki_reset && + + wiki_editpage Foo "page created before the git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_2 && + wiki_editpage Foo "new line added on the wiki" true && + + ( + cd mw_dir_2 && + git pull + ) && + + wiki_getallpage ref_page_2 && + test_diff_directories mw_dir_2 ref_page_2 + ' + + test_expect_success 'git pull works on conflict handled by auto-merge' ' + wiki_reset && + + wiki_editpage Foo "1 init +3 +5 + " false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_3 && + + wiki_editpage Foo "1 init +2 content added on wiki after clone +3 +5 + " false && + + ( + cd mw_dir_3 && + echo "1 init +3 +4 content added on git after clone +5 +" >Foo.mw && + git commit -am "conflicting change on foo" && + git pull && + git push + ) + ' + + test_expect_success 'Git push works after adding a file .mw' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_4 && + wiki_getallpage ref_page_4 && + ( + cd mw_dir_4 && + test_path_is_missing Foo.mw && + touch Foo.mw && + echo "hello world" >>Foo.mw && + git add Foo.mw && + git commit -m "Foo" && + git push + ) && + wiki_getallpage ref_page_4 && + test_diff_directories mw_dir_4 ref_page_4 + ' + + test_expect_success 'Git push works after editing a file .mw' ' + wiki_reset && + wiki_editpage "Foo" "page created before the git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_5 && + + ( + cd mw_dir_5 && + echo "new line added in the file Foo.mw" >>Foo.mw && + git commit -am "edit file Foo.mw" && + git push + ) && + + wiki_getallpage ref_page_5 && + test_diff_directories mw_dir_5 ref_page_5 + ' + + test_expect_failure 'Git push works after deleting a file' ' + wiki_reset && + wiki_editpage Foo "wiki page added before git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_6 && + + ( + cd mw_dir_6 && + git rm Foo.mw && + git commit -am "page Foo.mw deleted" && + git push + ) && + + test_must_fail wiki_page_exist Foo + ' + + test_expect_success 'Merge conflict expected and solving it' ' + wiki_reset && + + git clone mediawiki::'"$WIKI_URL"' mw_dir_7 && + wiki_editpage Foo "1 conflict +3 wiki +4" false && + + ( + cd mw_dir_7 && + echo "1 conflict +2 git +4" >Foo.mw && + git add Foo.mw && + git commit -m "conflict created" && + test_must_fail git pull && + "$PERL_PATH" -pi -e "s/[<=>].*//g" Foo.mw && + git commit -am "merge conflict solved" && + git push + ) + ' + + test_expect_failure 'git pull works after deleting a wiki page' ' + wiki_reset && + wiki_editpage Foo "wiki page added before the git clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_8 && + + wiki_delete_page Foo && + ( + cd mw_dir_8 && + git pull && + test_path_is_missing Foo.mw + ) + ' +} diff --git a/contrib/mw-to-git/t/t9360-mw-to-git-clone.sh b/contrib/mw-to-git/t/t9360-mw-to-git-clone.sh new file mode 100755 index 0000000000..811a90c9ae --- /dev/null +++ b/contrib/mw-to-git/t/t9360-mw-to-git-clone.sh @@ -0,0 +1,257 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + + +test_description='Test the Git Mediawiki remote helper: git clone' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + + +test_check_precond + + +test_expect_success 'Git clone creates the expected git log with one file' ' + wiki_reset && + wiki_editpage foo "this is not important" false -c cat -s "this must be the same" && + git clone mediawiki::'"$WIKI_URL"' mw_dir_1 && + ( + cd mw_dir_1 && + git log --format=%s HEAD^..HEAD >log.tmp + ) && + echo "this must be the same" >msg.tmp && + diff -b mw_dir_1/log.tmp msg.tmp +' + + +test_expect_success 'Git clone creates the expected git log with multiple files' ' + wiki_reset && + wiki_editpage daddy "this is not important" false -s="this must be the same" && + wiki_editpage daddy "neither is this" true -s="this must also be the same" && + wiki_editpage daddy "neither is this" true -s="same same same" && + wiki_editpage dj "dont care" false -s="identical" && + wiki_editpage dj "dont care either" true -s="identical too" && + git clone mediawiki::'"$WIKI_URL"' mw_dir_2 && + ( + cd mw_dir_2 && + git log --format=%s Daddy.mw >logDaddy.tmp && + git log --format=%s Dj.mw >logDj.tmp + ) && + echo "same same same" >msgDaddy.tmp && + echo "this must also be the same" >>msgDaddy.tmp && + echo "this must be the same" >>msgDaddy.tmp && + echo "identical too" >msgDj.tmp && + echo "identical" >>msgDj.tmp && + diff -b mw_dir_2/logDaddy.tmp msgDaddy.tmp && + diff -b mw_dir_2/logDj.tmp msgDj.tmp +' + + +test_expect_success 'Git clone creates only Main_Page.mw with an empty wiki' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_3 && + test_contains_N_files mw_dir_3 1 && + test_path_is_file mw_dir_3/Main_Page.mw +' + +test_expect_success 'Git clone does not fetch a deleted page' ' + wiki_reset && + wiki_editpage foo "this page must be deleted before the clone" false && + wiki_delete_page foo && + git clone mediawiki::'"$WIKI_URL"' mw_dir_4 && + test_contains_N_files mw_dir_4 1 && + test_path_is_file mw_dir_4/Main_Page.mw && + test_path_is_missing mw_dir_4/Foo.mw +' + +test_expect_success 'Git clone works with page added' ' + wiki_reset && + wiki_editpage foo " I will be cloned" false && + wiki_editpage bar "I will be cloned" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_5 && + wiki_getallpage ref_page_5 && + test_diff_directories mw_dir_5 ref_page_5 && + wiki_delete_page foo && + wiki_delete_page bar +' + +test_expect_success 'Git clone works with an edited page ' ' + wiki_reset && + wiki_editpage foo "this page will be edited" \ + false -s "first edition of page foo"&& + wiki_editpage foo "this page has been edited and must be on the clone " true && + git clone mediawiki::'"$WIKI_URL"' mw_dir_6 && + test_path_is_file mw_dir_6/Foo.mw && + test_path_is_file mw_dir_6/Main_Page.mw && + wiki_getallpage mw_dir_6/page_ref_6 && + test_diff_directories mw_dir_6 mw_dir_6/page_ref_6 && + ( + cd mw_dir_6 && + git log --format=%s HEAD^ Foo.mw > ../Foo.log + ) && + echo "first edition of page foo" > FooExpect.log && + diff FooExpect.log Foo.log +' + + +test_expect_success 'Git clone works with several pages and some deleted ' ' + wiki_reset && + wiki_editpage foo "this page will not be deleted" false && + wiki_editpage bar "I must not be erased" false && + wiki_editpage namnam "I will not be there at the end" false && + wiki_editpage nyancat "nyan nyan nyan delete me" false && + wiki_delete_page namnam && + wiki_delete_page nyancat && + git clone mediawiki::'"$WIKI_URL"' mw_dir_7 && + test_path_is_file mw_dir_7/Foo.mw && + test_path_is_file mw_dir_7/Bar.mw && + test_path_is_missing mw_dir_7/Namnam.mw && + test_path_is_missing mw_dir_7/Nyancat.mw && + wiki_getallpage mw_dir_7/page_ref_7 && + test_diff_directories mw_dir_7 mw_dir_7/page_ref_7 +' + + +test_expect_success 'Git clone works with one specific page cloned ' ' + wiki_reset && + wiki_editpage foo "I will not be cloned" false && + wiki_editpage bar "Do not clone me" false && + wiki_editpage namnam "I will be cloned :)" false -s="this log must stay" && + wiki_editpage nyancat "nyan nyan nyan you cant clone me" false && + git clone -c remote.origin.pages=namnam \ + mediawiki::'"$WIKI_URL"' mw_dir_8 && + test_contains_N_files mw_dir_8 1 && + test_path_is_file mw_dir_8/Namnam.mw && + test_path_is_missing mw_dir_8/Main_Page.mw && + ( + cd mw_dir_8 && + echo "this log must stay" >msg.tmp && + git log --format=%s >log.tmp && + diff -b msg.tmp log.tmp + ) && + wiki_check_content mw_dir_8/Namnam.mw Namnam +' + +test_expect_success 'Git clone works with multiple specific page cloned ' ' + wiki_reset && + wiki_editpage foo "I will be there" false && + wiki_editpage bar "I will not disapear" false && + wiki_editpage namnam "I be erased" false && + wiki_editpage nyancat "nyan nyan nyan you will not erase me" false && + wiki_delete_page namnam && + git clone -c remote.origin.pages="foo bar nyancat namnam" \ + mediawiki::'"$WIKI_URL"' mw_dir_9 && + test_contains_N_files mw_dir_9 3 && + test_path_is_missing mw_dir_9/Namnam.mw && + test_path_is_file mw_dir_9/Foo.mw && + test_path_is_file mw_dir_9/Nyancat.mw && + test_path_is_file mw_dir_9/Bar.mw && + wiki_check_content mw_dir_9/Foo.mw Foo && + wiki_check_content mw_dir_9/Bar.mw Bar && + wiki_check_content mw_dir_9/Nyancat.mw Nyancat +' + +test_expect_success 'Mediawiki-clone of several specific pages on wiki' ' + wiki_reset && + wiki_editpage foo "foo 1" false && + wiki_editpage bar "bar 1" false && + wiki_editpage dummy "dummy 1" false && + wiki_editpage cloned_1 "cloned_1 1" false && + wiki_editpage cloned_2 "cloned_2 2" false && + wiki_editpage cloned_3 "cloned_3 3" false && + mkdir -p ref_page_10 && + wiki_getpage cloned_1 ref_page_10 && + wiki_getpage cloned_2 ref_page_10 && + wiki_getpage cloned_3 ref_page_10 && + git clone -c remote.origin.pages="cloned_1 cloned_2 cloned_3" \ + mediawiki::'"$WIKI_URL"' mw_dir_10 && + test_diff_directories mw_dir_10 ref_page_10 +' + +test_expect_success 'Git clone works with the shallow option' ' + wiki_reset && + wiki_editpage foo "1st revision, should be cloned" false && + wiki_editpage bar "1st revision, should be cloned" false && + wiki_editpage nyan "1st revision, should not be cloned" false && + wiki_editpage nyan "2nd revision, should be cloned" false && + git -c remote.origin.shallow=true clone \ + mediawiki::'"$WIKI_URL"' mw_dir_11 && + test_contains_N_files mw_dir_11 4 && + test_path_is_file mw_dir_11/Nyan.mw && + test_path_is_file mw_dir_11/Foo.mw && + test_path_is_file mw_dir_11/Bar.mw && + test_path_is_file mw_dir_11/Main_Page.mw && + ( + cd mw_dir_11 && + test `git log --oneline Nyan.mw | wc -l` -eq 1 && + test `git log --oneline Foo.mw | wc -l` -eq 1 && + test `git log --oneline Bar.mw | wc -l` -eq 1 && + test `git log --oneline Main_Page.mw | wc -l ` -eq 1 + ) && + wiki_check_content mw_dir_11/Nyan.mw Nyan && + wiki_check_content mw_dir_11/Foo.mw Foo && + wiki_check_content mw_dir_11/Bar.mw Bar && + wiki_check_content mw_dir_11/Main_Page.mw Main_Page +' + +test_expect_success 'Git clone works with the shallow option with a delete page' ' + wiki_reset && + wiki_editpage foo "1st revision, will be deleted" false && + wiki_editpage bar "1st revision, should be cloned" false && + wiki_editpage nyan "1st revision, should not be cloned" false && + wiki_editpage nyan "2nd revision, should be cloned" false && + wiki_delete_page foo && + git -c remote.origin.shallow=true clone \ + mediawiki::'"$WIKI_URL"' mw_dir_12 && + test_contains_N_files mw_dir_12 3 && + test_path_is_file mw_dir_12/Nyan.mw && + test_path_is_missing mw_dir_12/Foo.mw && + test_path_is_file mw_dir_12/Bar.mw && + test_path_is_file mw_dir_12/Main_Page.mw && + ( + cd mw_dir_12 && + test `git log --oneline Nyan.mw | wc -l` -eq 1 && + test `git log --oneline Bar.mw | wc -l` -eq 1 && + test `git log --oneline Main_Page.mw | wc -l ` -eq 1 + ) && + wiki_check_content mw_dir_12/Nyan.mw Nyan && + wiki_check_content mw_dir_12/Bar.mw Bar && + wiki_check_content mw_dir_12/Main_Page.mw Main_Page +' + +test_expect_success 'Test of fetching a category' ' + wiki_reset && + wiki_editpage Foo "I will be cloned" false -c=Category && + wiki_editpage Bar "Meet me on the repository" false -c=Category && + wiki_editpage Dummy "I will not come" false && + wiki_editpage BarWrong "I will stay online only" false -c=NotCategory && + git clone -c remote.origin.categories="Category" \ + mediawiki::'"$WIKI_URL"' mw_dir_13 && + wiki_getallpage ref_page_13 Category && + test_diff_directories mw_dir_13 ref_page_13 +' + +test_expect_success 'Test of resistance to modification of category on wiki for clone' ' + wiki_reset && + wiki_editpage Tobedeleted "this page will be deleted" false -c=Catone && + wiki_editpage Tobeedited "this page will be modified" false -c=Catone && + wiki_editpage Normalone "this page wont be modified and will be on git" false -c=Catone && + wiki_editpage Notconsidered "this page will not appear on local" false && + wiki_editpage Othercategory "this page will not appear on local" false -c=Cattwo && + wiki_editpage Tobeedited "this page have been modified" true -c=Catone && + wiki_delete_page Tobedeleted + git clone -c remote.origin.categories="Catone" \ + mediawiki::'"$WIKI_URL"' mw_dir_14 && + wiki_getallpage ref_page_14 Catone && + test_diff_directories mw_dir_14 ref_page_14 +' + +test_done diff --git a/contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh b/contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh new file mode 100755 index 0000000000..9ea201459b --- /dev/null +++ b/contrib/mw-to-git/t/t9361-mw-to-git-push-pull.sh @@ -0,0 +1,24 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + +# tests for git-remote-mediawiki + +test_description='Test the Git Mediawiki remote helper: git push and git pull simple test cases' + +. ./test-gitmw-lib.sh +. ./push-pull-tests.sh +. $TEST_DIRECTORY/test-lib.sh + +test_check_precond + +test_push_pull + +test_done diff --git a/contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh b/contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh new file mode 100755 index 0000000000..246d47d8fb --- /dev/null +++ b/contrib/mw-to-git/t/t9362-mw-to-git-utf8.sh @@ -0,0 +1,321 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + +# tests for git-remote-mediawiki + +test_description='Test git-mediawiki with special characters in filenames' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + + +test_check_precond + + +test_expect_success 'Git clone works for a wiki with accents in the page names' ' + wiki_reset && + wiki_editpage féé "This page must be délétéd before clone" false && + wiki_editpage kèè "This page must be deleted before clone" false && + wiki_editpage hàà "This page must be deleted before clone" false && + wiki_editpage kîî "This page must be deleted before clone" false && + wiki_editpage foo "This page must be deleted before clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_1 && + wiki_getallpage ref_page_1 && + test_diff_directories mw_dir_1 ref_page_1 +' + + +test_expect_success 'Git pull works with a wiki with accents in the pages names' ' + wiki_reset && + wiki_editpage kîî "this page must be cloned" false && + wiki_editpage foo "this page must be cloned" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_2 && + wiki_editpage éàîôû "This page must be pulled" false && + ( + cd mw_dir_2 && + git pull + ) && + wiki_getallpage ref_page_2 && + test_diff_directories mw_dir_2 ref_page_2 +' + + +test_expect_success 'Cloning a chosen page works with accents' ' + wiki_reset && + wiki_editpage kîî "this page must be cloned" false && + git clone -c remote.origin.pages=kîî \ + mediawiki::'"$WIKI_URL"' mw_dir_3 && + wiki_check_content mw_dir_3/Kîî.mw Kîî && + test_path_is_file mw_dir_3/Kîî.mw && + rm -rf mw_dir_3 +' + + +test_expect_success 'The shallow option works with accents' ' + wiki_reset && + wiki_editpage néoà "1st revision, should not be cloned" false && + wiki_editpage néoà "2nd revision, should be cloned" false && + git -c remote.origin.shallow=true clone \ + mediawiki::'"$WIKI_URL"' mw_dir_4 && + test_contains_N_files mw_dir_4 2 && + test_path_is_file mw_dir_4/Néoà.mw && + test_path_is_file mw_dir_4/Main_Page.mw && + ( + cd mw_dir_4 && + test `git log --oneline Néoà.mw | wc -l` -eq 1 && + test `git log --oneline Main_Page.mw | wc -l ` -eq 1 + ) && + wiki_check_content mw_dir_4/Néoà.mw Néoà && + wiki_check_content mw_dir_4/Main_Page.mw Main_Page +' + + +test_expect_success 'Cloning works when page name first letter has an accent' ' + wiki_reset && + wiki_editpage îî "this page must be cloned" false && + git clone -c remote.origin.pages=îî \ + mediawiki::'"$WIKI_URL"' mw_dir_5 && + test_path_is_file mw_dir_5/Îî.mw && + wiki_check_content mw_dir_5/Îî.mw Îî +' + + +test_expect_success 'Git push works with a wiki with accents' ' + wiki_reset && + wiki_editpage féé "lots of accents : éèàÖ" false && + wiki_editpage foo "this page must be cloned" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_6 && + ( + cd mw_dir_6 && + echo "A wild Pîkächû appears on the wiki" >Pîkächû.mw && + git add Pîkächû.mw && + git commit -m "A new page appears" && + git push + ) && + wiki_getallpage ref_page_6 && + test_diff_directories mw_dir_6 ref_page_6 +' + +test_expect_success 'Git clone works with accentsand spaces' ' + wiki_reset && + wiki_editpage "é à î" "this page must be délété before the clone" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_7 && + wiki_getallpage ref_page_7 && + test_diff_directories mw_dir_7 ref_page_7 +' + +test_expect_success 'character $ in page name (mw -> git)' ' + wiki_reset && + wiki_editpage file_\$_foo "expect to be called file_$_foo" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_8 && + test_path_is_file mw_dir_8/File_\$_foo.mw && + wiki_getallpage ref_page_8 && + test_diff_directories mw_dir_8 ref_page_8 +' + + + +test_expect_success 'character $ in file name (git -> mw) ' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_9 && + ( + cd mw_dir_9 && + echo "this file is called File_\$_foo.mw" >File_\$_foo.mw && + git add . && + git commit -am "file File_\$_foo.mw" && + git pull && + git push + ) && + wiki_getallpage ref_page_9 && + test_diff_directories mw_dir_9 ref_page_9 +' + + +test_expect_failure 'capital at the begining of file names' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_10 && + ( + cd mw_dir_10 && + echo "my new file foo" >foo.mw && + echo "my new file Foo... Finger crossed" >Foo.mw && + git add . && + git commit -am "file foo.mw" && + git pull && + git push + ) && + wiki_getallpage ref_page_10 && + test_diff_directories mw_dir_10 ref_page_10 +' + + +test_expect_failure 'special character at the begining of file name from mw to git' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_11 && + wiki_editpage {char_1 "expect to be renamed {char_1" false && + wiki_editpage [char_2 "expect to be renamed [char_2" false && + ( + cd mw_dir_11 && + git pull + ) && + test_path_is_file mw_dir_11/{char_1 && + test_path_is_file mw_dir_11/[char_2 +' + +test_expect_success 'Pull page with title containing ":" other than namespace separator' ' + wiki_editpage Foo:Bar content false && + ( + cd mw_dir_11 && + git pull + ) && + test_path_is_file mw_dir_11/Foo:Bar.mw +' + +test_expect_success 'Push page with title containing ":" other than namespace separator' ' + ( + cd mw_dir_11 && + echo content >NotANameSpace:Page.mw && + git add NotANameSpace:Page.mw && + git commit -m "add page with colon" && + git push + ) && + wiki_page_exist NotANameSpace:Page +' + +test_expect_success 'test of correct formating for file name from mw to git' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_12 && + wiki_editpage char_%_7b_1 "expect to be renamed char{_1" false && + wiki_editpage char_%_5b_2 "expect to be renamed char{_2" false && + ( + cd mw_dir_12 && + git pull + ) && + test_path_is_file mw_dir_12/Char\{_1.mw && + test_path_is_file mw_dir_12/Char\[_2.mw && + wiki_getallpage ref_page_12 && + mv ref_page_12/Char_%_7b_1.mw ref_page_12/Char\{_1.mw && + mv ref_page_12/Char_%_5b_2.mw ref_page_12/Char\[_2.mw && + test_diff_directories mw_dir_12 ref_page_12 +' + + +test_expect_failure 'test of correct formating for file name begining with special character' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_13 && + ( + cd mw_dir_13 && + echo "my new file {char_1" >\{char_1.mw && + echo "my new file [char_2" >\[char_2.mw && + git add . && + git commit -am "commiting some exotic file name..." && + git push && + git pull + ) && + wiki_getallpage ref_page_13 && + test_path_is_file ref_page_13/{char_1.mw && + test_path_is_file ref_page_13/[char_2.mw && + test_diff_directories mw_dir_13 ref_page_13 +' + + +test_expect_success 'test of correct formating for file name from git to mw' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_14 && + ( + cd mw_dir_14 && + echo "my new file char{_1" >Char\{_1.mw && + echo "my new file char[_2" >Char\[_2.mw && + git add . && + git commit -m "commiting some exotic file name..." && + git push + ) && + wiki_getallpage ref_page_14 && + mv mw_dir_14/Char\{_1.mw mw_dir_14/Char_%_7b_1.mw && + mv mw_dir_14/Char\[_2.mw mw_dir_14/Char_%_5b_2.mw && + test_diff_directories mw_dir_14 ref_page_14 +' + + +test_expect_success 'git clone with /' ' + wiki_reset && + wiki_editpage \/fo\/o "this is not important" false -c=Deleted && + git clone mediawiki::'"$WIKI_URL"' mw_dir_15 && + test_path_is_file mw_dir_15/%2Ffo%2Fo.mw && + wiki_check_content mw_dir_15/%2Ffo%2Fo.mw \/fo\/o +' + + +test_expect_success 'git push with /' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_16 && + echo "I will be on the wiki" >mw_dir_16/%2Ffo%2Fo.mw && + ( + cd mw_dir_16 && + git add %2Ffo%2Fo.mw && + git commit -m " %2Ffo%2Fo added" && + git push + ) && + wiki_page_exist \/fo\/o && + wiki_check_content mw_dir_16/%2Ffo%2Fo.mw \/fo\/o + +' + + +test_expect_success 'git clone with \' ' + wiki_reset && + wiki_editpage \\ko\\o "this is not important" false -c=Deleted && + git clone mediawiki::'"$WIKI_URL"' mw_dir_17 && + test_path_is_file mw_dir_17/\\ko\\o.mw && + wiki_check_content mw_dir_17/\\ko\\o.mw \\ko\\o +' + + +test_expect_success 'git push with \' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_18 && + echo "I will be on the wiki" >mw_dir_18/\\ko\\o.mw && + ( + cd mw_dir_18 && + git add \\ko\\o.mw && + git commit -m " \\ko\\o added" && + git push + )&& + wiki_page_exist \\ko\\o && + wiki_check_content mw_dir_18/\\ko\\o.mw \\ko\\o + +' + +test_expect_success 'git clone with \ in format control' ' + wiki_reset && + wiki_editpage \\no\\o "this is not important" false && + git clone mediawiki::'"$WIKI_URL"' mw_dir_19 && + test_path_is_file mw_dir_19/\\no\\o.mw && + wiki_check_content mw_dir_19/\\no\\o.mw \\no\\o +' + + +test_expect_success 'git push with \ in format control' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir_20 && + echo "I will be on the wiki" >mw_dir_20/\\fo\\o.mw && + ( + cd mw_dir_20 && + git add \\fo\\o.mw && + git commit -m " \\fo\\o added" && + git push + )&& + wiki_page_exist \\fo\\o && + wiki_check_content mw_dir_20/\\fo\\o.mw \\fo\\o + +' + + +test_done diff --git a/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh b/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh new file mode 100755 index 0000000000..5a0373935f --- /dev/null +++ b/contrib/mw-to-git/t/t9363-mw-to-git-export-import.sh @@ -0,0 +1,198 @@ +#!/bin/sh +# +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# +# License: GPL v2 or later + +# tests for git-remote-mediawiki + +test_description='Test the Git Mediawiki remote helper: git push and git pull simple test cases' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + + +test_check_precond + + +test_git_reimport () { + git -c remote.origin.dumbPush=true push && + git -c remote.origin.mediaImport=true pull --rebase +} + +# Don't bother with permissions, be administrator by default +test_expect_success 'setup config' ' + git config --global remote.origin.mwLogin WikiAdmin && + git config --global remote.origin.mwPassword AdminPass && + test_might_fail git config --global --unset remote.origin.mediaImport +' + +test_expect_success 'git push can upload media (File:) files' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + ( + cd mw_dir && + echo "hello world" >Foo.txt && + git add Foo.txt && + git commit -m "add a text file" && + git push && + "$PERL_PATH" -e "print STDOUT \"binary content: \".chr(255);" >Foo.txt && + git add Foo.txt && + git commit -m "add a text file with binary content" && + git push + ) +' + +test_expect_success 'git clone works on previously created wiki with media files' ' + test_when_finished "rm -rf mw_dir mw_dir_clone" && + git clone -c remote.origin.mediaimport=true \ + mediawiki::'"$WIKI_URL"' mw_dir_clone && + test_cmp mw_dir_clone/Foo.txt mw_dir/Foo.txt && + (cd mw_dir_clone && git checkout HEAD^) && + (cd mw_dir && git checkout HEAD^) && + test_cmp mw_dir_clone/Foo.txt mw_dir/Foo.txt +' + +test_expect_success 'git push & pull work with locally renamed media files' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "A File" >Foo.txt && + git add Foo.txt && + git commit -m "add a file" && + git mv Foo.txt Bar.txt && + git commit -m "Rename a file" && + test_git_reimport && + echo "A File" >expect && + test_cmp expect Bar.txt && + test_path_is_missing Foo.txt + ) +' + +test_expect_success 'git push can propagate local page deletion' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + test_path_is_missing Foo.mw && + echo "hello world" >Foo.mw && + git add Foo.mw && + git commit -m "Add the page Foo" && + git push && + rm -f Foo.mw && + git commit -am "Delete the page Foo" && + test_git_reimport && + test_path_is_missing Foo.mw + ) +' + +test_expect_success 'git push can propagate local media file deletion' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "hello world" >Foo.txt && + git add Foo.txt && + git commit -m "Add the text file Foo" && + git rm Foo.txt && + git commit -m "Delete the file Foo" && + test_git_reimport && + test_path_is_missing Foo.txt + ) +' + +# test failure: the file is correctly uploaded, and then deleted but +# as no page link to it, the import (which looks at page revisions) +# doesn't notice the file deletion on the wiki. We fetch the list of +# files from the wiki, but as the file is deleted, it doesn't appear. +test_expect_failure 'git pull correctly imports media file deletion when no page link to it' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "hello world" >Foo.txt && + git add Foo.txt && + git commit -m "Add the text file Foo" && + git push && + git rm Foo.txt && + git commit -m "Delete the file Foo" && + test_git_reimport && + test_path_is_missing Foo.txt + ) +' + +test_expect_success 'git push properly warns about insufficient permissions' ' + wiki_reset && + git clone mediawiki::'"$WIKI_URL"' mw_dir && + test_when_finished "rm -fr mw_dir" && + ( + cd mw_dir && + echo "A File" >foo.forbidden && + git add foo.forbidden && + git commit -m "add a file" && + git push 2>actual && + test_i18ngrep "foo.forbidden is not a permitted file" actual + ) +' + +test_expect_success 'setup a repository with media files' ' + wiki_reset && + wiki_editpage testpage "I am linking a file [[File:File.txt]]" false && + echo "File content" >File.txt && + wiki_upload_file File.txt && + echo "Another file content" >AnotherFile.txt && + wiki_upload_file AnotherFile.txt +' + +test_expect_success 'git clone works with one specific page cloned and mediaimport=true' ' + git clone -c remote.origin.pages=testpage \ + -c remote.origin.mediaimport=true \ + mediawiki::'"$WIKI_URL"' mw_dir_15 && + test_when_finished "rm -rf mw_dir_15" && + test_contains_N_files mw_dir_15 3 && + test_path_is_file mw_dir_15/Testpage.mw && + test_path_is_file mw_dir_15/File:File.txt.mw && + test_path_is_file mw_dir_15/File.txt && + test_path_is_missing mw_dir_15/Main_Page.mw && + test_path_is_missing mw_dir_15/File:AnotherFile.txt.mw && + test_path_is_missing mw_dir_15/AnothetFile.txt && + wiki_check_content mw_dir_15/Testpage.mw Testpage && + test_cmp mw_dir_15/File.txt File.txt +' + +test_expect_success 'git clone works with one specific page cloned and mediaimport=false' ' + test_when_finished "rm -rf mw_dir_16" && + git clone -c remote.origin.pages=testpage \ + mediawiki::'"$WIKI_URL"' mw_dir_16 && + test_contains_N_files mw_dir_16 1 && + test_path_is_file mw_dir_16/Testpage.mw && + test_path_is_missing mw_dir_16/File:File.txt.mw && + test_path_is_missing mw_dir_16/File.txt && + test_path_is_missing mw_dir_16/Main_Page.mw && + wiki_check_content mw_dir_16/Testpage.mw Testpage +' + +# should behave like mediaimport=false +test_expect_success 'git clone works with one specific page cloned and mediaimport unset' ' + test_when_finished "rm -fr mw_dir_17" && + git clone -c remote.origin.pages=testpage \ + mediawiki::'"$WIKI_URL"' mw_dir_17 && + test_contains_N_files mw_dir_17 1 && + test_path_is_file mw_dir_17/Testpage.mw && + test_path_is_missing mw_dir_17/File:File.txt.mw && + test_path_is_missing mw_dir_17/File.txt && + test_path_is_missing mw_dir_17/Main_Page.mw && + wiki_check_content mw_dir_17/Testpage.mw Testpage +' + +test_done diff --git a/contrib/mw-to-git/t/t9364-pull-by-rev.sh b/contrib/mw-to-git/t/t9364-pull-by-rev.sh new file mode 100755 index 0000000000..5c22457a0b --- /dev/null +++ b/contrib/mw-to-git/t/t9364-pull-by-rev.sh @@ -0,0 +1,17 @@ +#!/bin/sh + +test_description='Test the Git Mediawiki remote helper: git pull by revision' + +. ./test-gitmw-lib.sh +. ./push-pull-tests.sh +. $TEST_DIRECTORY/test-lib.sh + +test_check_precond + +test_expect_success 'configuration' ' + git config --global mediawiki.fetchStrategy by_rev +' + +test_push_pull + +test_done diff --git a/contrib/mw-to-git/t/test-gitmw-lib.sh b/contrib/mw-to-git/t/test-gitmw-lib.sh new file mode 100755 index 0000000000..3b2cfacf51 --- /dev/null +++ b/contrib/mw-to-git/t/test-gitmw-lib.sh @@ -0,0 +1,435 @@ +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# License: GPL v2 or later + +# +# CONFIGURATION VARIABLES +# You might want to change these ones +# + +. ./test.config + +WIKI_URL=http://"$SERVER_ADDR:$PORT/$WIKI_DIR_NAME" +CURR_DIR=$(pwd) +TEST_OUTPUT_DIRECTORY=$(pwd) +TEST_DIRECTORY="$CURR_DIR"/../../../t + +export TEST_OUTPUT_DIRECTORY TEST_DIRECTORY CURR_DIR + +if test "$LIGHTTPD" = "false" ; then + PORT=80 +else + WIKI_DIR_INST="$CURR_DIR/$WEB_WWW" +fi + +wiki_upload_file () { + "$CURR_DIR"/test-gitmw.pl upload_file "$@" +} + +wiki_getpage () { + "$CURR_DIR"/test-gitmw.pl get_page "$@" +} + +wiki_delete_page () { + "$CURR_DIR"/test-gitmw.pl delete_page "$@" +} + +wiki_editpage () { + "$CURR_DIR"/test-gitmw.pl edit_page "$@" +} + +die () { + die_with_status 1 "$@" +} + +die_with_status () { + status=$1 + shift + echo >&2 "$*" + exit "$status" +} + + +# Check the preconditions to run git-remote-mediawiki's tests +test_check_precond () { + if ! test_have_prereq PERL + then + skip_all='skipping gateway git-mw tests, perl not available' + test_done + fi + + if [ ! -f "$GIT_BUILD_DIR"/git-remote-mediawiki ]; + then + echo "No remote mediawiki for git found. Copying it in git" + echo "cp $GIT_BUILD_DIR/contrib/mw-to-git/git-remote-mediawiki $GIT_BUILD_DIR/" + ln -s "$GIT_BUILD_DIR"/contrib/mw-to-git/git-remote-mediawiki "$GIT_BUILD_DIR" + fi + + if [ ! -d "$WIKI_DIR_INST/$WIKI_DIR_NAME" ]; + then + skip_all='skipping gateway git-mw tests, no mediawiki found' + test_done + fi +} + +# test_diff_directories <dir_git> <dir_wiki> +# +# Compare the contents of directories <dir_git> and <dir_wiki> with diff +# and errors if they do not match. The program will +# not look into .git in the process. +# Warning: the first argument MUST be the directory containing the git data +test_diff_directories () { + rm -rf "$1_tmp" + mkdir -p "$1_tmp" + cp "$1"/*.mw "$1_tmp" + diff -r -b "$1_tmp" "$2" +} + +# $1=<dir> +# $2=<N> +# +# Check that <dir> contains exactly <N> files +test_contains_N_files () { + if test `ls -- "$1" | wc -l` -ne "$2"; then + echo "directory $1 sould contain $2 files" + echo "it contains these files:" + ls "$1" + false + fi +} + + +# wiki_check_content <file_name> <page_name> +# +# Compares the contents of the file <file_name> and the wiki page +# <page_name> and exits with error 1 if they do not match. +wiki_check_content () { + mkdir -p wiki_tmp + wiki_getpage "$2" wiki_tmp + # replacement of forbidden character in file name + page_name=$(printf "%s\n" "$2" | sed -e "s/\//%2F/g") + + diff -b "$1" wiki_tmp/"$page_name".mw + if test $? -ne 0 + then + rm -rf wiki_tmp + error "ERROR: file $2 not found on wiki" + fi + rm -rf wiki_tmp +} + +# wiki_page_exist <page_name> +# +# Check the existence of the page <page_name> on the wiki and exits +# with error if it is absent from it. +wiki_page_exist () { + mkdir -p wiki_tmp + wiki_getpage "$1" wiki_tmp + page_name=$(printf "%s\n" "$1" | sed "s/\//%2F/g") + if test -f wiki_tmp/"$page_name".mw ; then + rm -rf wiki_tmp + else + rm -rf wiki_tmp + error "test failed: file $1 not found on wiki" + fi +} + +# wiki_getallpagename +# +# Fetch the name of each page on the wiki. +wiki_getallpagename () { + "$CURR_DIR"/test-gitmw.pl getallpagename +} + +# wiki_getallpagecategory <category> +# +# Fetch the name of each page belonging to <category> on the wiki. +wiki_getallpagecategory () { + "$CURR_DIR"/test-gitmw.pl getallpagename "$@" +} + +# wiki_getallpage <dest_dir> [<category>] +# +# Fetch all the pages from the wiki and place them in the directory +# <dest_dir>. +# If <category> is define, then wiki_getallpage fetch the pages included +# in <category>. +wiki_getallpage () { + if test -z "$2"; + then + wiki_getallpagename + else + wiki_getallpagecategory "$2" + fi + mkdir -p "$1" + while read -r line; do + wiki_getpage "$line" $1; + done < all.txt +} + +# ================= Install part ================= + +error () { + echo "$@" >&2 + exit 1 +} + +# config_lighttpd +# +# Create the configuration files and the folders necessary to start lighttpd. +# Overwrite any existing file. +config_lighttpd () { + mkdir -p $WEB + mkdir -p $WEB_TMP + mkdir -p $WEB_WWW + cat > $WEB/lighttpd.conf <<EOF + server.document-root = "$CURR_DIR/$WEB_WWW" + server.port = $PORT + server.pid-file = "$CURR_DIR/$WEB_TMP/pid" + + server.modules = ( + "mod_rewrite", + "mod_redirect", + "mod_access", + "mod_accesslog", + "mod_fastcgi" + ) + + index-file.names = ("index.php" , "index.html") + + mimetype.assign = ( + ".pdf" => "application/pdf", + ".sig" => "application/pgp-signature", + ".spl" => "application/futuresplash", + ".class" => "application/octet-stream", + ".ps" => "application/postscript", + ".torrent" => "application/x-bittorrent", + ".dvi" => "application/x-dvi", + ".gz" => "application/x-gzip", + ".pac" => "application/x-ns-proxy-autoconfig", + ".swf" => "application/x-shockwave-flash", + ".tar.gz" => "application/x-tgz", + ".tgz" => "application/x-tgz", + ".tar" => "application/x-tar", + ".zip" => "application/zip", + ".mp3" => "audio/mpeg", + ".m3u" => "audio/x-mpegurl", + ".wma" => "audio/x-ms-wma", + ".wax" => "audio/x-ms-wax", + ".ogg" => "application/ogg", + ".wav" => "audio/x-wav", + ".gif" => "image/gif", + ".jpg" => "image/jpeg", + ".jpeg" => "image/jpeg", + ".png" => "image/png", + ".xbm" => "image/x-xbitmap", + ".xpm" => "image/x-xpixmap", + ".xwd" => "image/x-xwindowdump", + ".css" => "text/css", + ".html" => "text/html", + ".htm" => "text/html", + ".js" => "text/javascript", + ".asc" => "text/plain", + ".c" => "text/plain", + ".cpp" => "text/plain", + ".log" => "text/plain", + ".conf" => "text/plain", + ".text" => "text/plain", + ".txt" => "text/plain", + ".dtd" => "text/xml", + ".xml" => "text/xml", + ".mpeg" => "video/mpeg", + ".mpg" => "video/mpeg", + ".mov" => "video/quicktime", + ".qt" => "video/quicktime", + ".avi" => "video/x-msvideo", + ".asf" => "video/x-ms-asf", + ".asx" => "video/x-ms-asf", + ".wmv" => "video/x-ms-wmv", + ".bz2" => "application/x-bzip", + ".tbz" => "application/x-bzip-compressed-tar", + ".tar.bz2" => "application/x-bzip-compressed-tar", + "" => "text/plain" + ) + + fastcgi.server = ( ".php" => + ("localhost" => + ( "socket" => "$CURR_DIR/$WEB_TMP/php.socket", + "bin-path" => "$PHP_DIR/php-cgi -c $CURR_DIR/$WEB/php.ini" + + ) + ) + ) +EOF + + cat > $WEB/php.ini <<EOF + session.save_path ='$CURR_DIR/$WEB_TMP' +EOF +} + +# start_lighttpd +# +# Start or restart daemon lighttpd. If restart, rewrite configuration files. +start_lighttpd () { + if test -f "$WEB_TMP/pid"; then + echo "Instance already running. Restarting..." + stop_lighttpd + fi + config_lighttpd + "$LIGHTTPD_DIR"/lighttpd -f "$WEB"/lighttpd.conf + + if test $? -ne 0 ; then + echo "Could not execute http deamon lighttpd" + exit 1 + fi +} + +# stop_lighttpd +# +# Kill daemon lighttpd and removes files and folders associated. +stop_lighttpd () { + test -f "$WEB_TMP/pid" && kill $(cat "$WEB_TMP/pid") + rm -rf "$WEB" +} + +# Create the SQLite database of the MediaWiki. If the database file already +# exists, it will be deleted. +# This script should be runned from the directory where $FILES_FOLDER is +# located. +create_db () { + rm -f "$TMP/$DB_FILE" + + echo "Generating the SQLite database file. It can take some time ..." + # Run the php script to generate the SQLite database file + # with cURL calls. + php "$FILES_FOLDER/$DB_INSTALL_SCRIPT" $(basename "$DB_FILE" .sqlite) \ + "$WIKI_ADMIN" "$WIKI_PASSW" "$TMP" "$PORT" + + if [ ! -f "$TMP/$DB_FILE" ] ; then + error "Can't create database file $TMP/$DB_FILE. Try to run ./install-wiki.sh delete first." + fi + + # Copy the generated database file into the directory the + # user indicated. + cp "$TMP/$DB_FILE" "$FILES_FOLDER" || + error "Unable to copy $TMP/$DB_FILE to $FILES_FOLDER" +} + +# Install a wiki in your web server directory. +wiki_install () { + if test $LIGHTTPD = "true" ; then + start_lighttpd + fi + + SERVER_ADDR=$SERVER_ADDR:$PORT + # In this part, we change directory to $TMP in order to download, + # unpack and copy the files of MediaWiki + ( + mkdir -p "$WIKI_DIR_INST/$WIKI_DIR_NAME" + if [ ! -d "$WIKI_DIR_INST/$WIKI_DIR_NAME" ] ; then + error "Folder $WIKI_DIR_INST/$WIKI_DIR_NAME doesn't exist. + Please create it and launch the script again." + fi + + # Fetch MediaWiki's archive if not already present in the TMP directory + cd "$TMP" + if [ ! -f "$MW_VERSION.tar.gz" ] ; then + echo "Downloading $MW_VERSION sources ..." + wget "http://download.wikimedia.org/mediawiki/1.19/mediawiki-1.19.0.tar.gz" || + error "Unable to download "\ + "http://download.wikimedia.org/mediawiki/1.19/"\ + "mediawiki-1.19.0.tar.gz. "\ + "Please fix your connection and launch the script again." + echo "$MW_VERSION.tar.gz downloaded in `pwd`. "\ + "You can delete it later if you want." + else + echo "Reusing existing $MW_VERSION.tar.gz downloaded in `pwd`." + fi + archive_abs_path=$(pwd)/"$MW_VERSION.tar.gz" + cd "$WIKI_DIR_INST/$WIKI_DIR_NAME/" || + error "can't cd to $WIKI_DIR_INST/$WIKI_DIR_NAME/" + tar xzf "$archive_abs_path" --strip-components=1 || + error "Unable to extract WikiMedia's files from $archive_abs_path to "\ + "$WIKI_DIR_INST/$WIKI_DIR_NAME" + ) || exit 1 + + create_db + + # Copy the generic LocalSettings.php in the web server's directory + # And modify parameters according to the ones set at the top + # of this script. + # Note that LocalSettings.php is never modified. + if [ ! -f "$FILES_FOLDER/LocalSettings.php" ] ; then + error "Can't find $FILES_FOLDER/LocalSettings.php " \ + "in the current folder. "\ + "Please run the script inside its folder." + fi + cp "$FILES_FOLDER/LocalSettings.php" \ + "$FILES_FOLDER/LocalSettings-tmp.php" || + error "Unable to copy $FILES_FOLDER/LocalSettings.php " \ + "to $FILES_FOLDER/LocalSettings-tmp.php" + + # Parse and set the LocalSettings file of the user according to the + # CONFIGURATION VARIABLES section at the beginning of this script + file_swap="$FILES_FOLDER/LocalSettings-swap.php" + sed "s,@WG_SCRIPT_PATH@,/$WIKI_DIR_NAME," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + sed "s,@WG_SERVER@,http://$SERVER_ADDR," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + sed "s,@WG_SQLITE_DATADIR@,$TMP," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + sed "s,@WG_SQLITE_DATAFILE@,$( basename $DB_FILE .sqlite)," \ + "$FILES_FOLDER/LocalSettings-tmp.php" > "$file_swap" + mv "$file_swap" "$FILES_FOLDER/LocalSettings-tmp.php" + + mv "$FILES_FOLDER/LocalSettings-tmp.php" \ + "$WIKI_DIR_INST/$WIKI_DIR_NAME/LocalSettings.php" || + error "Unable to move $FILES_FOLDER/LocalSettings-tmp.php" \ + "in $WIKI_DIR_INST/$WIKI_DIR_NAME" + echo "File $FILES_FOLDER/LocalSettings.php is set in" \ + " $WIKI_DIR_INST/$WIKI_DIR_NAME" + + echo "Your wiki has been installed. You can check it at + http://$SERVER_ADDR/$WIKI_DIR_NAME" +} + +# Reset the database of the wiki and the password of the admin +# +# Warning: This function must be called only in a subdirectory of t/ directory +wiki_reset () { + # Copy initial database of the wiki + if [ ! -f "../$FILES_FOLDER/$DB_FILE" ] ; then + error "Can't find ../$FILES_FOLDER/$DB_FILE in the current folder." + fi + cp "../$FILES_FOLDER/$DB_FILE" "$TMP" || + error "Can't copy ../$FILES_FOLDER/$DB_FILE in $TMP" + echo "File $FILES_FOLDER/$DB_FILE is set in $TMP" +} + +# Delete the wiki created in the web server's directory and all its content +# saved in the database. +wiki_delete () { + if test $LIGHTTPD = "true"; then + stop_lighttpd + else + # Delete the wiki's directory. + rm -rf "$WIKI_DIR_INST/$WIKI_DIR_NAME" || + error "Wiki's directory $WIKI_DIR_INST/" \ + "$WIKI_DIR_NAME could not be deleted" + # Delete the wiki's SQLite database. + rm -f "$TMP/$DB_FILE" || + error "Database $TMP/$DB_FILE could not be deleted." + fi + + # Delete the wiki's SQLite database + rm -f "$TMP/$DB_FILE" || error "Database $TMP/$DB_FILE could not be deleted." + rm -f "$FILES_FOLDER/$DB_FILE" + rm -rf "$TMP/$MW_VERSION" +} diff --git a/contrib/mw-to-git/t/test-gitmw.pl b/contrib/mw-to-git/t/test-gitmw.pl new file mode 100755 index 0000000000..0ff76259fa --- /dev/null +++ b/contrib/mw-to-git/t/test-gitmw.pl @@ -0,0 +1,225 @@ +#!/usr/bin/perl -w -s +# Copyright (C) 2012 +# Charles Roussel <charles.roussel@ensimag.imag.fr> +# Simon Cathebras <simon.cathebras@ensimag.imag.fr> +# Julien Khayat <julien.khayat@ensimag.imag.fr> +# Guillaume Sasdy <guillaume.sasdy@ensimag.imag.fr> +# Simon Perrat <simon.perrat@ensimag.imag.fr> +# License: GPL v2 or later + +# Usage: +# ./test-gitmw.pl <command> [argument]* +# Execute in terminal using the name of the function to call as first +# parameter, and the function's arguments as following parameters +# +# Example: +# ./test-gitmw.pl "get_page" foo . +# will call <wiki_getpage> with arguments <foo> and <.> +# +# Available functions are: +# "get_page" +# "delete_page" +# "edit_page" +# "getallpagename" + +use MediaWiki::API; +use Getopt::Long; +use encoding 'utf8'; +use DateTime::Format::ISO8601; +use open ':encoding(utf8)'; +use constant SLASH_REPLACEMENT => "%2F"; + +#Parsing of the config file + +my $configfile = "$ENV{'CURR_DIR'}/test.config"; +my %config; +open my $CONFIG, "<", $configfile or die "can't open $configfile: $!"; +while (<$CONFIG>) +{ + chomp; + s/#.*//; + s/^\s+//; + s/\s+$//; + next unless length; + my ($key, $value) = split (/\s*=\s*/,$_, 2); + $config{$key} = $value; + last if ($key eq 'LIGHTTPD' and $value eq 'false'); + last if ($key eq 'PORT'); +} +close $CONFIG or die "can't close $configfile: $!"; + +my $wiki_address = "http://$config{'SERVER_ADDR'}".":"."$config{'PORT'}"; +my $wiki_url = "$wiki_address/$config{'WIKI_DIR_NAME'}/api.php"; +my $wiki_admin = "$config{'WIKI_ADMIN'}"; +my $wiki_admin_pass = "$config{'WIKI_PASSW'}"; +my $mw = MediaWiki::API->new; +$mw->{config}->{api_url} = $wiki_url; + + +# wiki_login <name> <password> +# +# Logs the user with <name> and <password> in the global variable +# of the mediawiki $mw +sub wiki_login { + $mw->login( { lgname => "$_[0]",lgpassword => "$_[1]" } ) + || die "getpage: login failed"; +} + +# wiki_getpage <wiki_page> <dest_path> +# +# fetch a page <wiki_page> from the wiki referenced in the global variable +# $mw and copies its content in directory dest_path +sub wiki_getpage { + my $pagename = $_[0]; + my $destdir = $_[1]; + + my $page = $mw->get_page( { title => $pagename } ); + if (!defined($page)) { + die "getpage: wiki does not exist"; + } + + my $content = $page->{'*'}; + if (!defined($content)) { + die "getpage: page does not exist"; + } + + $pagename=$page->{'title'}; + # Replace spaces by underscore in the page name + $pagename =~ s/ /_/g; + $pagename =~ s/\//%2F/g; + open(my $file, ">$destdir/$pagename.mw"); + print $file "$content"; + close ($file); + +} + +# wiki_delete_page <page_name> +# +# delete the page with name <page_name> from the wiki referenced +# in the global variable $mw +sub wiki_delete_page { + my $pagename = $_[0]; + + my $exist=$mw->get_page({title => $pagename}); + + if (defined($exist->{'*'})){ + $mw->edit({ action => 'delete', + title => $pagename}) + || die $mw->{error}->{code} . ": " . $mw->{error}->{details}; + } else { + die "no page with such name found: $pagename\n"; + } +} + +# wiki_editpage <wiki_page> <wiki_content> <wiki_append> [-c=<category>] [-s=<summary>] +# +# Edit a page named <wiki_page> with content <wiki_content> on the wiki +# referenced with the global variable $mw +# If <wiki_append> == true : append <wiki_content> at the end of the actual +# content of the page <wiki_page> +# If <wik_page> doesn't exist, that page is created with the <wiki_content> +sub wiki_editpage { + my $wiki_page = $_[0]; + my $wiki_content = $_[1]; + my $wiki_append = $_[2]; + my $summary = ""; + my ($summ, $cat) = (); + GetOptions('s=s' => \$summ, 'c=s' => \$cat); + + my $append = 0; + if (defined($wiki_append) && $wiki_append eq 'true') { + $append=1; + } + + my $previous_text =""; + + if ($append) { + my $ref = $mw->get_page( { title => $wiki_page } ); + $previous_text = $ref->{'*'}; + } + + my $text = $wiki_content; + if (defined($previous_text)) { + $text="$previous_text$text"; + } + + # Eventually, add this page to a category. + if (defined($cat)) { + my $category_name="[[Category:$cat]]"; + $text="$text\n $category_name"; + } + if(defined($summ)){ + $summary=$summ; + } + + $mw->edit( { action => 'edit', title => $wiki_page, summary => $summary, text => "$text"} ); +} + +# wiki_getallpagename [<category>] +# +# Fetch all pages of the wiki referenced by the global variable $mw +# and print the names of each one in the file all.txt with a new line +# ("\n") between these. +# If the argument <category> is defined, then this function get only the pages +# belonging to <category>. +sub wiki_getallpagename { + # fetch the pages of the wiki + if (defined($_[0])) { + my $mw_pages = $mw->list ( { action => 'query', + list => 'categorymembers', + cmtitle => "Category:$_[0]", + cmnamespace => 0, + cmlimit => 500 }, + ) + || die $mw->{error}->{code}.": ".$mw->{error}->{details}; + open(my $file, ">all.txt"); + foreach my $page (@{$mw_pages}) { + print $file "$page->{title}\n"; + } + close ($file); + + } else { + my $mw_pages = $mw->list({ + action => 'query', + list => 'allpages', + aplimit => 500, + }) + || die $mw->{error}->{code}.": ".$mw->{error}->{details}; + open(my $file, ">all.txt"); + foreach my $page (@{$mw_pages}) { + print $file "$page->{title}\n"; + } + close ($file); + } +} + +sub wiki_upload_file { + my $file_name = $_[0]; + my $resultat = $mw->edit ( { + action => 'upload', + filename => $file_name, + comment => 'upload a file', + file => [ $file_name ], + ignorewarnings=>1, + }, { + skip_encoding => 1 + } ) || die $mw->{error}->{code} . ' : ' . $mw->{error}->{details}; +} + + + +# Main part of this script: parse the command line arguments +# and select which function to execute +my $fct_to_call = shift; + +wiki_login($wiki_admin, $wiki_admin_pass); + +my %functions_to_call = qw( + upload_file wiki_upload_file + get_page wiki_getpage + delete_page wiki_delete_page + edit_page wiki_editpage + getallpagename wiki_getallpagename +); +die "$0 ERROR: wrong argument" unless exists $functions_to_call{$fct_to_call}; +&{$functions_to_call{$fct_to_call}}(@ARGV); diff --git a/contrib/mw-to-git/t/test.config b/contrib/mw-to-git/t/test.config new file mode 100644 index 0000000000..958b37b4a7 --- /dev/null +++ b/contrib/mw-to-git/t/test.config @@ -0,0 +1,35 @@ +# Name of the web server's directory dedicated to the wiki is WIKI_DIR_NAME +WIKI_DIR_NAME=wiki + +# Login and password of the wiki's admin +WIKI_ADMIN=WikiAdmin +WIKI_PASSW=AdminPass + +# Address of the web server +SERVER_ADDR=localhost + +# SQLite database of the wiki, named DB_FILE, is located in TMP +TMP=/tmp +DB_FILE=wikidb.sqlite + +# If LIGHTTPD is not set to true, the script will use the defaut +# web server running in WIKI_DIR_INST. +WIKI_DIR_INST=/var/www + +# If LIGHTTPD is set to true, the script will use Lighttpd to run +# the wiki. +LIGHTTPD=true + +# The variables below are useful only if LIGHTTPD is set to true. +PORT=1234 +PHP_DIR=/usr/bin +LIGHTTPD_DIR=/usr/sbin +WEB=WEB +WEB_TMP=$WEB/tmp +WEB_WWW=$WEB/www + +# The variables below are used by the script to install a wiki. +# You should not modify these unless you are modifying the script itself. +MW_VERSION=mediawiki-1.19.0 +FILES_FOLDER=install-wiki +DB_INSTALL_SCRIPT=db_install.php |