User:ImplSearchBot/Code: Difference between revisions

Line 1:

<lang perl>#!/usr/bin/perl -w

use strict;

use MediaWiki::Bot;

use JSON qw/to_json from_json/;

use Data::Dumper;

# Handles interaction with the wiki.

Line 20:

Line 19:

defined $password

or die $usage;

#my $json = new JSON;

#$json->allow_blessed(1);

#$json->convert_blessed(1);

my $posttosite = shift @ARGV;

Line 29:

Line 32:

my $editor = MediaWiki::Bot->new('ImpleSearchBot');

$editor->{debug} = 1;

sub sanitizenamefs

{

my $pagename = shift;

$pagename =~ tr/:\//__/;

return $pagename;

}

sub postpage

Line 41:

Line 51:

unless( defined $posttosite )

{

$pagename =~ ~~tr/:\//_-/~~;

$pagename = &sanitizenamefs($pagename);

$pagename .= ".wikitxt";

Line 60:

Line 70:

or warn "Failed to post page: " . $editor->{'errstr'};

}

sub getcacheddata

{

my $dataname = shift;

my $filename = &sanitizenamefs("cache_" . $dataname . ".json");

open my $infile, '<', $filename

or warn "Failed to load cached data $filename: $!";

return undef unless defined $infile;

my $jsondata;

$jsondata .= $_ while <$infile>;

close $infile;

return from_json($jsondata);

}

# Not doing anything with this yet. It's intended to allow us to compare site state between now and when we

# last ran, so that we can learn to avoid doing unnecessary work. (Server resources and bloated edit statistics...)

# Also, I plan on publishing the cache files in a version control system like SVN or Git, to allow multiple bots

# to share the data and to provide history. (It's the public target that necessitates using JSON instead of Data::Dumper)

# SVN has the advantage that I already know how to use it. Git has the advantage in that I can use GitHub and not tax

# my Slice with Git traffic, and I don't have to punch a hole in the firewall to access more services.

sub cachedata

{

my $dataname = shift;

my $data = shift;

my $filename = &sanitizenamefs("cache_" . $dataname . ".json");

open my $outfile, '>', $filename

or warn "Failed to cache $filename: $!";

return unless defined $outfile;

print "Caching $filename:" . scalar $data . "\n";

print $outfile to_json($data);

close $outfile;

}

sub getcategory

{

my $categoryname = shift;

my @categorycontents = $editor->get_pages_in_category($categoryname);

&cachedata($categoryname, \@categorycontents);

return @categorycontents;

}

Line 73:

Line 130:

# No, it's not the "(expr) or die" syntax. This will be clearer

# for most folks who read the code.

die "Unable to login: " . ~~Dumper~~($editor);

die "Unable to login: " . from_json($editor);

}

# Get a complete listing of the tasks.

print "Getting tasks\n";

my @alltasks = ~~$editor->get_pages_in_category~~('Category:Programming Tasks');

my @alltasks = &getcategory('Category:Programming Tasks');

# Get a complete listing of the languages.

print "Getting the languages.\n";

my @alllanguages = ~~$editor->get_pages_in_category~~('Category:Programming Languages');

my @alllanguages = &getcategory('Category:Programming Languages');

# We want the language name, not the fully-qualified wiki name.

Line 89:

Line 146:

# Get a list of the languages for which we've already provided bodies for the related omit categories.

# Store it as a hash, so the lookup will be faster.

my %createdomitcategories = map {$_, 1} ~~$editor->get_pages_in_category~~('Category:Maintenance/OmitCategoriesCreated');

my %createdomitcategories = map {$_, 1} &getcategory('Category:Maintenance/OmitCategoriesCreated');

print "Identifying implemented and omitted languages\n";

foreach my $language (@alllanguages)

{

my %implemented = map {$_, 1} ~~$editor->get_pages_in_category~~("Category:$language");

my %implemented = map {$_, 1} &getcategory("Category:$language");

my %omitted = map {$_, 1} ~~$editor->get_pages_in_category~~("Category:$language/Omit");

my %omitted = map {$_, 1} &getcategory("Category:$language/Omit");

my $omitcount = scalar keys %omitted;