diff options
Diffstat (limited to 'contrib/mw-to-git')
| -rw-r--r-- | contrib/mw-to-git/.gitignore | 1 | ||||
| -rw-r--r-- | contrib/mw-to-git/Git/Mediawiki.pm | 78 | ||||
| -rw-r--r-- | contrib/mw-to-git/Makefile | 23 | ||||
| -rwxr-xr-x | contrib/mw-to-git/bin-wrapper/git | 14 | ||||
| -rwxr-xr-x | contrib/mw-to-git/git-mw.perl | 368 | ||||
| -rwxr-xr-x | contrib/mw-to-git/git-remote-mediawiki.perl | 109 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/t9365-continuing-queries.sh | 23 | ||||
| -rwxr-xr-x | contrib/mw-to-git/t/test-gitmw-lib.sh | 10 | ||||
| -rw-r--r-- | contrib/mw-to-git/t/test.config | 2 |
9 files changed, 537 insertions, 91 deletions
diff --git a/contrib/mw-to-git/.gitignore b/contrib/mw-to-git/.gitignore index b9196555e5..ae545b013d 100644 --- a/contrib/mw-to-git/.gitignore +++ b/contrib/mw-to-git/.gitignore @@ -1 +1,2 @@ git-remote-mediawiki +git-mw diff --git a/contrib/mw-to-git/Git/Mediawiki.pm b/contrib/mw-to-git/Git/Mediawiki.pm index 805f42a49e..d13c4dfa7d 100644 --- a/contrib/mw-to-git/Git/Mediawiki.pm +++ b/contrib/mw-to-git/Git/Mediawiki.pm @@ -18,7 +18,83 @@ require Exporter; @EXPORT = (); # Methods which can be called as standalone functions as well: -@EXPORT_OK = (); +@EXPORT_OK = qw(clean_filename smudge_filename connect_maybe + EMPTY HTTP_CODE_OK HTTP_CODE_PAGE_NOT_FOUND); +} + +# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced +use constant SLASH_REPLACEMENT => '%2F'; + +# Used to test for empty strings +use constant EMPTY => q{}; + +# HTTP codes +use constant HTTP_CODE_OK => 200; +use constant HTTP_CODE_PAGE_NOT_FOUND => 404; + +sub clean_filename { + my $filename = shift; + $filename =~ s{@{[SLASH_REPLACEMENT]}}{/}g; + # [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded. + # Do a variant of URL-encoding, i.e. looks like URL-encoding, + # but with _ added to prevent MediaWiki from thinking this is + # an actual special character. + $filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge; + # If we use the uri escape before + # we should unescape here, before anything + + return $filename; +} + +sub smudge_filename { + my $filename = shift; + $filename =~ s{/}{@{[SLASH_REPLACEMENT]}}g; + $filename =~ s/ /_/g; + # Decode forbidden characters encoded in clean_filename + $filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf('%c', hex($1))/ge; + return $filename; +} + +sub connect_maybe { + my $wiki = shift; + if ($wiki) { + return $wiki; + } + + my $remote_name = shift; + my $remote_url = shift; + my ($wiki_login, $wiki_password, $wiki_domain); + + $wiki_login = Git::config("remote.${remote_name}.mwLogin"); + $wiki_password = Git::config("remote.${remote_name}.mwPassword"); + $wiki_domain = Git::config("remote.${remote_name}.mwDomain"); + + $wiki = MediaWiki::API->new; + $wiki->{config}->{api_url} = "${remote_url}/api.php"; + if ($wiki_login) { + my %credential = ( + 'url' => $remote_url, + 'username' => $wiki_login, + 'password' => $wiki_password + ); + Git::credential(\%credential); + my $request = {lgname => $credential{username}, + lgpassword => $credential{password}, + lgdomain => $wiki_domain}; + if ($wiki->login($request)) { + Git::credential(\%credential, 'approve'); + print {*STDERR} qq(Logged in mediawiki user "$credential{username}".\n); + } else { + print {*STDERR} qq(Failed to log in mediawiki user "$credential{username}" on ${remote_url}\n); + print {*STDERR} ' (error ' . + $wiki->{error}->{code} . ': ' . + $wiki->{error}->{details} . ")\n"; + Git::credential(\%credential, 'reject'); + exit 1; + } + } + + return $wiki; } 1; # Famous last words diff --git a/contrib/mw-to-git/Makefile b/contrib/mw-to-git/Makefile index 37b68e2571..a4b6f7a2cd 100644 --- a/contrib/mw-to-git/Makefile +++ b/contrib/mw-to-git/Makefile @@ -2,12 +2,19 @@ # Copyright (C) 2013 # Matthieu Moy <Matthieu.Moy@imag.fr> # +# To build and test: +# +# make +# bin-wrapper/git mw preview Some_page.mw +# bin-wrapper/git clone mediawiki::http://example.com/wiki/ +# # To install, run Git's toplevel 'make install' then run: # # make install GIT_MEDIAWIKI_PM=Git/Mediawiki.pm SCRIPT_PERL=git-remote-mediawiki.perl +SCRIPT_PERL+=git-mw.perl GIT_ROOT_DIR=../.. HERE=contrib/mw-to-git/ @@ -21,22 +28,30 @@ INSTLIBDIR_SQ = $(subst ','\'',$(INSTLIBDIR)) all: build +test: all + $(MAKE) -C t + +check: perlcritic test + install_pm: $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(INSTLIBDIR_SQ)/Git' $(INSTALL) -m 644 $(GIT_MEDIAWIKI_PM) \ '$(DESTDIR_SQ)$(INSTLIBDIR_SQ)/$(GIT_MEDIAWIKI_PM)' build: - $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \ + $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \ build-perl-script install: install_pm - $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \ + $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \ install-perl-script clean: - $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL=$(SCRIPT_PERL_FULL) \ + $(MAKE) -C $(GIT_ROOT_DIR) SCRIPT_PERL="$(SCRIPT_PERL_FULL)" \ clean-perl-script perlcritic: - perlcritic -2 *.perl + perlcritic -5 $(SCRIPT_PERL) + -perlcritic -2 $(SCRIPT_PERL) + +.PHONY: all test check install_pm install clean perlcritic diff --git a/contrib/mw-to-git/bin-wrapper/git b/contrib/mw-to-git/bin-wrapper/git new file mode 100755 index 0000000000..6663ae57e8 --- /dev/null +++ b/contrib/mw-to-git/bin-wrapper/git @@ -0,0 +1,14 @@ +#!/bin/sh + +# git executable wrapper script for Git-Mediawiki to run tests without +# installing all the scripts and perl packages. + +GIT_ROOT_DIR=../../.. +GIT_EXEC_PATH=$(cd "$(dirname "$0")" && cd ${GIT_ROOT_DIR} && pwd) + +GITPERLLIB="$GIT_EXEC_PATH"'/contrib/mw-to-git'"${GITPERLLIB:+:$GITPERLLIB}" +PATH="$GIT_EXEC_PATH"'/contrib/mw-to-git:'"$PATH" + +export GITPERLLIB PATH + +exec "${GIT_EXEC_PATH}/bin-wrappers/git" "$@" diff --git a/contrib/mw-to-git/git-mw.perl b/contrib/mw-to-git/git-mw.perl new file mode 100755 index 0000000000..28df3ee321 --- /dev/null +++ b/contrib/mw-to-git/git-mw.perl @@ -0,0 +1,368 @@ +#!/usr/bin/perl + +# Copyright (C) 2013 +# Benoit Person <benoit.person@ensimag.imag.fr> +# Celestin Matte <celestin.matte@ensimag.imag.fr> +# License: GPL v2 or later + +# Set of tools for git repo with a mediawiki remote. +# Documentation & bugtracker: https://github.com/moy/Git-Mediawiki/ + +use strict; +use warnings; + +use Getopt::Long; +use URI::URL qw(url); +use LWP::UserAgent; +use HTML::TreeBuilder; + +use Git; +use MediaWiki::API; +use Git::Mediawiki qw(clean_filename connect_maybe + EMPTY HTTP_CODE_PAGE_NOT_FOUND); + +# By default, use UTF-8 to communicate with Git and the user +binmode STDERR, ':encoding(UTF-8)'; +binmode STDOUT, ':encoding(UTF-8)'; + +# Global parameters +my $verbose = 0; +sub v_print { + if ($verbose) { + return print {*STDERR} @_; + } + return; +} + +# Preview parameters +my $file_name = EMPTY; +my $remote_name = EMPTY; +my $preview_file_name = EMPTY; +my $autoload = 0; +sub file { + $file_name = shift; + return $file_name; +} + +my %commands = ( + 'help' => + [\&help, {}, \&help], + 'preview' => + [\&preview, { + '<>' => \&file, + 'output|o=s' => \$preview_file_name, + 'remote|r=s' => \$remote_name, + 'autoload|a' => \$autoload + }, \&preview_help] +); + +# Search for sub-command +my $cmd = $commands{'help'}; +for (0..@ARGV-1) { + if (defined $commands{$ARGV[$_]}) { + $cmd = $commands{$ARGV[$_]}; + splice @ARGV, $_, 1; + last; + } +}; +GetOptions( %{$cmd->[1]}, + 'help|h' => \&{$cmd->[2]}, + 'verbose|v' => \$verbose); + +# Launch command +&{$cmd->[0]}; + +############################# Preview Functions ################################ + +sub preview_help { + print {*STDOUT} <<'END'; +USAGE: git mw preview [--remote|-r <remote name>] [--autoload|-a] + [--output|-o <output filename>] [--verbose|-v] + <blob> | <filename> + +DESCRIPTION: +Preview is an utiliy to preview local content of a mediawiki repo as if it was +pushed on the remote. + +For that, preview searches for the remote name of the current branch's +upstream if --remote is not set. If that remote is not found or if it +is not a mediawiki, it lists all mediawiki remotes configured and asks +you to replay your command with the --remote option set properly. + +Then, it searches for a file named 'filename'. If it's not found in +the current dir, it will assume it's a blob. + +The content retrieved in the file (or in the blob) will then be parsed +by the remote mediawiki and combined with a template retrieved from +the mediawiki. + +Finally, preview will save the HTML result in a file. and autoload it +in your default web browser if the option --autoload is present. + +OPTIONS: + -r <remote name>, --remote <remote name> + If the remote is a mediawiki, the template and the parse engine + used for the preview will be those of that remote. + If not, a list of valid remotes will be shown. + + -a, --autoload + Try to load the HTML output in a new tab (or new window) of your + default web browser. + + -o <output filename>, --output <output filename> + Change the HTML output filename. Default filename is based on the + input filename with its extension replaced by '.html'. + + -v, --verbose + Show more information on what's going on under the hood. +END + exit; +} + +sub preview { + my $wiki; + my ($remote_url, $wiki_page_name); + my ($new_content, $template); + my $file_content; + + if ($file_name eq EMPTY) { + die "Missing file argument, see `git mw help`\n"; + } + + v_print("### Selecting remote\n"); + if ($remote_name eq EMPTY) { + $remote_name = find_upstream_remote_name(); + if ($remote_name) { + $remote_url = mediawiki_remote_url_maybe($remote_name); + } + + if (! $remote_url) { + my @valid_remotes = find_mediawiki_remotes(); + + if ($#valid_remotes == 0) { + print {*STDERR} "No mediawiki remote in this repo. \n"; + exit 1; + } else { + my $remotes_list = join("\n\t", @valid_remotes); + print {*STDERR} <<"MESSAGE"; +There are multiple mediawiki remotes, which of: + ${remotes_list} +do you want ? Use the -r option to specify the remote. +MESSAGE + } + + exit 1; + } + } else { + if (!is_valid_remote($remote_name)) { + die "${remote_name} is not a remote\n"; + } + + $remote_url = mediawiki_remote_url_maybe($remote_name); + if (! $remote_url) { + die "${remote_name} is not a mediawiki remote\n"; + } + } + v_print("selected remote:\n\tname: ${remote_name}\n\turl: ${remote_url}\n"); + + $wiki = connect_maybe($wiki, $remote_name, $remote_url); + + # Read file content + if (! -e $file_name) { + $file_content = git_cmd_try { + Git::command('cat-file', 'blob', $file_name); } + "%s failed w/ code %d"; + + if ($file_name =~ /(.+):(.+)/) { + $file_name = $2; + } + } else { + open my $read_fh, "<", $file_name + or die "could not open ${file_name}: $!\n"; + $file_content = do { local $/ = undef; <$read_fh> }; + close $read_fh + or die "unable to close: $!\n"; + } + + v_print("### Retrieving template\n"); + ($wiki_page_name = clean_filename($file_name)) =~ s/\.[^.]+$//; + $template = get_template($remote_url, $wiki_page_name); + + v_print("### Parsing local content\n"); + $new_content = $wiki->api({ + action => 'parse', + text => $file_content, + title => $wiki_page_name + }, { + skip_encoding => 1 + }) or die "No response from remote mediawiki\n"; + $new_content = $new_content->{'parse'}->{'text'}->{'*'}; + + v_print("### Merging contents\n"); + if ($preview_file_name eq EMPTY) { + ($preview_file_name = $file_name) =~ s/\.[^.]+$/.html/; + } + open(my $save_fh, '>:encoding(UTF-8)', $preview_file_name) + or die "Could not open: $!\n"; + print {$save_fh} merge_contents($template, $new_content, $remote_url); + close($save_fh) + or die "Could not close: $!\n"; + + v_print("### Results\n"); + if ($autoload) { + v_print("Launching browser w/ file: ${preview_file_name}"); + system('git', 'web--browse', $preview_file_name); + } else { + print {*STDERR} "Preview file saved as: ${preview_file_name}\n"; + } + + exit; +} + +# uses global scope variable: $remote_name +sub merge_contents { + my $template = shift; + my $content = shift; + my $remote_url = shift; + my ($content_tree, $html_tree, $mw_content_text); + my $template_content_id = 'bodyContent'; + + $html_tree = HTML::TreeBuilder->new; + $html_tree->parse($template); + + $content_tree = HTML::TreeBuilder->new; + $content_tree->parse($content); + + $template_content_id = Git::config("remote.${remote_name}.mwIDcontent") + || $template_content_id; + v_print("Using '${template_content_id}' as the content ID\n"); + + $mw_content_text = $html_tree->look_down('id', $template_content_id); + if (!defined $mw_content_text) { + print {*STDERR} <<"CONFIG"; +Could not combine the new content with the template. You might want to +configure `mediawiki.IDContent` in your config: + git config --add remote.${remote_name}.mwIDcontent <id> +and re-run the command afterward. +CONFIG + exit 1; + } + $mw_content_text->delete_content(); + $mw_content_text->push_content($content_tree); + + make_links_absolute($html_tree, $remote_url); + + return $html_tree->as_HTML; +} + +sub make_links_absolute { + my $html_tree = shift; + my $remote_url = shift; + for (@{ $html_tree->extract_links() }) { + my ($link, $element, $attr) = @{ $_ }; + my $url = url($link)->canonical; + if ($url !~ /#/) { + $element->attr($attr, URI->new_abs($url, $remote_url)); + } + } + return $html_tree; +} + +sub is_valid_remote { + my $remote = shift; + my @remotes = git_cmd_try { + Git::command('remote') } + "%s failed w/ code %d"; + my $found_remote = 0; + foreach my $remote (@remotes) { + if ($remote eq $remote) { + $found_remote = 1; + last; + } + } + return $found_remote; +} + +sub find_mediawiki_remotes { + my @remotes = git_cmd_try { + Git::command('remote'); } + "%s failed w/ code %d"; + my $remote_url; + my @valid_remotes = (); + foreach my $remote (@remotes) { + $remote_url = mediawiki_remote_url_maybe($remote); + if ($remote_url) { + push(@valid_remotes, $remote); + } + } + return @valid_remotes; +} + +sub find_upstream_remote_name { + my $current_branch = git_cmd_try { + Git::command_oneline('symbolic-ref', '--short', 'HEAD') } + "%s failed w/ code %d"; + return Git::config("branch.${current_branch}.remote"); +} + +sub mediawiki_remote_url_maybe { + my $remote = shift; + + # Find remote url + my $remote_url = Git::config("remote.${remote}.url"); + if ($remote_url =~ s/mediawiki::(.*)/$1/) { + return url($remote_url)->canonical; + } + + return; +} + +sub get_template { + my $url = shift; + my $page_name = shift; + my ($req, $res, $code, $url_after); + + $req = LWP::UserAgent->new; + if ($verbose) { + $req->show_progress(1); + } + + $res = $req->get("${url}/index.php?title=${page_name}"); + if (!$res->is_success) { + $code = $res->code; + $url_after = $res->request()->uri(); # resolve all redirections + if ($code == HTTP_CODE_PAGE_NOT_FOUND) { + if ($verbose) { + print {*STDERR} <<"WARNING"; +Warning: Failed to retrieve '$page_name'. Create it on the mediawiki if you want +all the links to work properly. +Trying to use the mediawiki homepage as a fallback template ... +WARNING + } + + # LWP automatically redirects GET request + $res = $req->get("${url}/index.php"); + if (!$res->is_success) { + $url_after = $res->request()->uri(); # resolve all redirections + die "Failed to get homepage @ ${url_after} w/ code ${code}\n"; + } + } else { + die "Failed to get '${page_name}' @ ${url_after} w/ code ${code}\n"; + } + } + + return $res->decoded_content; +} + +############################## Help Functions ################################## + +sub help { + print {*STDOUT} <<'END'; +usage: git mw <command> <args> + +git mw commands are: + help Display help information about git mw + preview Parse and render local file into HTML +END + exit; +} diff --git a/contrib/mw-to-git/git-remote-mediawiki.perl b/contrib/mw-to-git/git-remote-mediawiki.perl index 71baf8ace8..3f8d993afa 100755 --- a/contrib/mw-to-git/git-remote-mediawiki.perl +++ b/contrib/mw-to-git/git-remote-mediawiki.perl @@ -14,6 +14,8 @@ use strict; use MediaWiki::API; use Git; +use Git::Mediawiki qw(clean_filename smudge_filename connect_maybe + EMPTY HTTP_CODE_OK); use DateTime::Format::ISO8601; use warnings; @@ -23,9 +25,6 @@ binmode STDOUT, ':encoding(UTF-8)'; use URI::Escape; -# Mediawiki filenames can contain forward slashes. This variable decides by which pattern they should be replaced -use constant SLASH_REPLACEMENT => '%2F'; - # It's not always possible to delete pages (may require some # privileges). Deleted pages are replaced with this content. use constant DELETED_CONTENT => "[[Category:Deleted]]\n"; @@ -40,8 +39,6 @@ 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*'; -use constant EMPTY => q{}; - # Number of pages taken into account at once in submodule get_mw_page_list use constant SLICE_SIZE => 50; @@ -50,8 +47,6 @@ use constant SLICE_SIZE => 50; # the number of links to be returned (500 links max). use constant BATCH_SIZE => 10; -use constant HTTP_CODE_OK => 200; - if (@ARGV != 2) { exit_error_usage(); } @@ -199,37 +194,6 @@ sub parse_command { # MediaWiki API instance, created lazily. my $mediawiki; -sub mw_connect_maybe { - if ($mediawiki) { - return; - } - $mediawiki = MediaWiki::API->new; - $mediawiki->{config}->{api_url} = "${url}/api.php"; - if ($wiki_login) { - my %credential = ( - 'url' => $url, - 'username' => $wiki_login, - 'password' => $wiki_passwd - ); - Git::credential(\%credential); - my $request = {lgname => $credential{username}, - lgpassword => $credential{password}, - lgdomain => $wiki_domain}; - if ($mediawiki->login($request)) { - Git::credential(\%credential, 'approve'); - print {*STDERR} qq(Logged in mediawiki user "$credential{username}".\n); - } else { - print {*STDERR} qq(Failed to log in mediawiki user "$credential{username}" on ${url}\n); - print {*STDERR} ' (error ' . - $mediawiki->{error}->{code} . ': ' . - $mediawiki->{error}->{details} . ")\n"; - Git::credential(\%credential, 'reject'); - exit 1; - } - } - return; -} - sub fatal_mw_error { my $action = shift; print STDERR "fatal: could not $action.\n"; @@ -339,7 +303,7 @@ sub get_mw_first_pages { # Get the list of pages to be fetched according to configuration. sub get_mw_pages { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); print {*STDERR} "Listing pages on remote wiki...\n"; @@ -529,7 +493,7 @@ sub get_last_local_revision { # avoid a loop onto all tracked pages. This is useful for the fetch-by-rev # option. sub get_last_global_remote_rev { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); my $query = { action => 'query', @@ -545,7 +509,7 @@ sub get_last_global_remote_rev { # Get the last remote revision concerning the tracked pages and the tracked # categories. sub get_last_remote_revision { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); my %pages_hash = get_mw_pages(); my @pages = values(%pages_hash); @@ -601,29 +565,6 @@ sub mediawiki_smudge { return "${string}\n"; } -sub mediawiki_clean_filename { - my $filename = shift; - $filename =~ s{@{[SLASH_REPLACEMENT]}}{/}g; - # [, ], |, {, and } are forbidden by MediaWiki, even URL-encoded. - # Do a variant of URL-encoding, i.e. looks like URL-encoding, - # but with _ added to prevent MediaWiki from thinking this is - # an actual special character. - $filename =~ s/[\[\]\{\}\|]/sprintf("_%%_%x", ord($&))/ge; - # If we use the uri escape before - # we should unescape here, before anything - - return $filename; -} - -sub mediawiki_smudge_filename { - my $filename = shift; - $filename =~ s{/}{@{[SLASH_REPLACEMENT]}}g; - $filename =~ s/ /_/g; - # Decode forbidden characters encoded in mediawiki_clean_filename - $filename =~ s/_%_([0-9a-fA-F][0-9a-fA-F])/sprintf('%c', hex($1))/ge; - return $filename; -} - sub literal_data { my ($content) = @_; print {*STDOUT} 'data ', bytes::length($content), "\n", $content; @@ -635,9 +576,9 @@ sub literal_data_raw { my ($content) = @_; # Avoid confusion between size in bytes and in characters utf8::downgrade($content); - binmode {*STDOUT}, ':raw'; + binmode STDOUT, ':raw'; print {*STDOUT} 'data ', bytes::length($content), "\n", $content; - binmode {*STDOUT}, ':encoding(UTF-8)'; + binmode STDOUT, ':encoding(UTF-8)'; return; } @@ -649,6 +590,9 @@ sub mw_capabilities { print {*STDOUT} "import\n"; print {*STDOUT} "list\n"; print {*STDOUT} "push\n"; + if ($dumb_push) { + print {*STDOUT} "no-private-update\n"; + } print {*STDOUT} "\n"; return; } @@ -681,6 +625,9 @@ sub fetch_mw_revisions_for_page { rvstartid => $fetch_from, rvlimit => 500, pageids => $id, + + # Let MediaWiki know that we support the latest API. + continue => '', }; my $revnum = 0; @@ -696,8 +643,15 @@ sub fetch_mw_revisions_for_page { push(@page_revs, $page_rev_ids); $revnum++; } - last if (!$result->{'query-continue'}); - $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid}; + + if ($result->{'query-continue'}) { # For legacy APIs + $query->{rvstartid} = $result->{'query-continue'}->{revisions}->{rvstartid}; + } elsif ($result->{continue}) { # For newer APIs + $query->{rvstartid} = $result->{continue}->{rvcontinue}; + $query->{continue} = $result->{continue}->{continue}; + } else { + last; + } } if ($shallow_import && @page_revs) { print {*STDERR} " Found 1 revision (shallow import).\n"; @@ -831,7 +785,7 @@ sub mw_import_ref { return; } - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); print {*STDERR} "Searching revisions...\n"; my $last_local = get_last_local_revision(); @@ -945,7 +899,7 @@ sub mw_import_revids { my %commit; $commit{author} = $rev->{user} || 'Anonymous'; $commit{comment} = $rev->{comment} || EMPTY_MESSAGE; - $commit{title} = mediawiki_smudge_filename($page_title); + $commit{title} = smudge_filename($page_title); $commit{mw_revision} = $rev->{revid}; $commit{content} = mediawiki_smudge($rev->{'*'}); @@ -1006,7 +960,7 @@ sub mw_upload_file { } # Deleting and uploading a file requires a priviledged user if ($file_deleted) { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); my $query = { action => 'delete', title => $path, @@ -1022,7 +976,7 @@ sub mw_upload_file { # Don't let perl try to interpret file content as UTF-8 => use "raw" my $content = run_git("cat-file blob ${new_sha1}", 'raw'); if ($content ne EMPTY) { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); $mediawiki->{config}->{upload_url} = "${url}/index.php/Special:Upload"; $mediawiki->edit({ @@ -1070,7 +1024,7 @@ sub mw_push_file { my $old_sha1 = $diff_info_split[2]; my $page_created = ($old_sha1 eq NULL_SHA1); my $page_deleted = ($new_sha1 eq NULL_SHA1); - $complete_file_name = mediawiki_clean_filename($complete_file_name); + $complete_file_name = clean_filename($complete_file_name); my ($title, $extension) = $complete_file_name =~ /^(.*)\.([^\.]*)$/; if (!defined($extension)) { @@ -1093,7 +1047,7 @@ sub mw_push_file { $file_content = run_git("cat-file blob ${new_sha1}"); } - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); my $result = $mediawiki->edit( { action => 'edit', @@ -1270,7 +1224,6 @@ sub mw_push_revision { } if (!$dumb_push) { run_git(qq(notes --ref=${remotename}/mediawiki add -f -m "mediawiki_revision: ${mw_revision}" ${sha1_commit})); - run_git(qq(update-ref -m "Git-MediaWiki push" refs/mediawiki/${remotename}/master ${sha1_commit} ${sha1_child})); } } @@ -1279,7 +1232,7 @@ sub mw_push_revision { } sub get_allowed_file_extensions { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); my $query = { action => 'query', @@ -1303,7 +1256,7 @@ my %cached_mw_namespace_id; # Return MediaWiki id for a canonical namespace name. # Ex.: "File", "Project". sub get_mw_namespace_id { - mw_connect_maybe(); + $mediawiki = connect_maybe($mediawiki, $remotename, $url); my $name = shift; if (!exists $namespace_id{$name}) { @@ -1362,7 +1315,7 @@ sub get_mw_namespace_id { # Store "notANameSpace" as special value for inexisting namespaces my $store_id = ($id || 'notANameSpace'); - # Store explicitely requested namespaces on disk + # Store explicitly requested namespaces on disk if (!exists $cached_mw_namespace_id{$name}) { run_git(qq(config --add remote.${remotename}.namespaceCache "${name}:${store_id}")); $cached_mw_namespace_id{$name} = 1; diff --git a/contrib/mw-to-git/t/t9365-continuing-queries.sh b/contrib/mw-to-git/t/t9365-continuing-queries.sh new file mode 100755 index 0000000000..27e267f532 --- /dev/null +++ b/contrib/mw-to-git/t/t9365-continuing-queries.sh @@ -0,0 +1,23 @@ +#!/bin/sh + +test_description='Test the Git Mediawiki remote helper: queries w/ more than 500 results' + +. ./test-gitmw-lib.sh +. $TEST_DIRECTORY/test-lib.sh + +test_check_precond + +test_expect_success 'creating page w/ >500 revisions' ' + wiki_reset && + for i in `test_seq 501` + do + echo "creating revision $i" && + wiki_editpage foo "revision $i<br/>" true + done +' + +test_expect_success 'cloning page w/ >500 revisions' ' + git clone mediawiki::'"$WIKI_URL"' mw_dir +' + +test_done diff --git a/contrib/mw-to-git/t/test-gitmw-lib.sh b/contrib/mw-to-git/t/test-gitmw-lib.sh index bb76cee379..3372b2af34 100755 --- a/contrib/mw-to-git/t/test-gitmw-lib.sh +++ b/contrib/mw-to-git/t/test-gitmw-lib.sh @@ -62,12 +62,8 @@ test_check_precond () { 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 "$GIT_BUILD_DIR" - fi + GIT_EXEC_PATH=$(cd "$(dirname "$0")" && cd "../.." && pwd) + PATH="$GIT_EXEC_PATH"'/bin-wrapper:'"$PATH" if [ ! -d "$WIKI_DIR_INST/$WIKI_DIR_NAME" ]; then @@ -95,7 +91,7 @@ test_diff_directories () { # 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 "directory $1 should contain $2 files" echo "it contains these files:" ls "$1" false diff --git a/contrib/mw-to-git/t/test.config b/contrib/mw-to-git/t/test.config index 4cfebe9c69..5ba0684162 100644 --- a/contrib/mw-to-git/t/test.config +++ b/contrib/mw-to-git/t/test.config @@ -12,7 +12,7 @@ SERVER_ADDR=localhost TMP=/tmp DB_FILE=wikidb.sqlite -# If LIGHTTPD is not set to true, the script will use the defaut +# If LIGHTTPD is not set to true, the script will use the default # web server running in WIKI_DIR_INST. WIKI_DIR_INST=/var/www |