.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.42) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is >0, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{\ . if \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{\ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" ======================================================================== .\" .IX Title "MediaWiki::DumpFile::Compat::Revisions 3pm" .TH MediaWiki::DumpFile::Compat::Revisions 3pm "2022-06-15" "perl v5.34.0" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" Parse::MediaWikiDump::Revisions \- Object capable of processing dump files with multiple revisions per article .SH "ABOUT" .IX Header "ABOUT" This object is used to access the metadata associated with a MediaWiki instance and provide an iterative interface for extracting the individual article revisions out of the same. To guarantee that there is only a single revision per article use the Parse::MediaWikiDump::Pages object. .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 1 \& use MediaWiki::DumpFile::Compat; \& \& $pmwd = Parse::MediaWikiDump\->new; \& $revisions = $pmwd\->revisions(\*(Aqpages\-articles.xml\*(Aq); \& $revisions = $pmwd\->revisions(\e*FILEHANDLE); \& \& #print the title and id of each article inside the dump file \& while(defined($page = $revisions\->next)) { \& print "title \*(Aq", $page\->title, "\*(Aq id ", $page\->id, "\en"; \& } .Ve .SH "METHODS" .IX Header "METHODS" .ie n .IP "$revisions\->new" 4 .el .IP "\f(CW$revisions\fR\->new" 4 .IX Item "$revisions->new" Open the specified MediaWiki dump file. If the single argument to this method is a string it will be used as the path to the file to open. If the argument is a reference to a filehandle the contents will be read from the filehandle as specified. .ie n .IP "$revisions\->next" 4 .el .IP "\f(CW$revisions\fR\->next" 4 .IX Item "$revisions->next" Returns an instance of the next available Parse::MediaWikiDump::page object or returns undef if there are no more articles left. .ie n .IP "$revisions\->version" 4 .el .IP "\f(CW$revisions\fR\->version" 4 .IX Item "$revisions->version" Returns a plain text string of the dump file format revision number .ie n .IP "$revisions\->sitename" 4 .el .IP "\f(CW$revisions\fR\->sitename" 4 .IX Item "$revisions->sitename" Returns a plain text string that is the name of the MediaWiki instance. .ie n .IP "$revisions\->base" 4 .el .IP "\f(CW$revisions\fR\->base" 4 .IX Item "$revisions->base" Returns the \s-1URL\s0 to the instances main article in the form of a string. .ie n .IP "$revisions\->generator" 4 .el .IP "\f(CW$revisions\fR\->generator" 4 .IX Item "$revisions->generator" Returns a string containing 'MediaWiki' and a version number of the instance that dumped this file. Example: 'MediaWiki 1.14alpha' .ie n .IP "$revisions\->case" 4 .el .IP "\f(CW$revisions\fR\->case" 4 .IX Item "$revisions->case" Returns a string describing the case sensitivity configured in the instance. .ie n .IP "$revisions\->namespaces" 4 .el .IP "\f(CW$revisions\fR\->namespaces" 4 .IX Item "$revisions->namespaces" Returns a reference to an array of references. Each reference is to another array with the first item being the unique identifier of the namespace and the second element containing a string that is the name of the namespace. .ie n .IP "$revisions\->namespaces_names" 4 .el .IP "\f(CW$revisions\fR\->namespaces_names" 4 .IX Item "$revisions->namespaces_names" Returns an array reference the array contains strings of all the namespaces each as an element. .ie n .IP "$revisions\->current_byte" 4 .el .IP "\f(CW$revisions\fR\->current_byte" 4 .IX Item "$revisions->current_byte" Returns the number of bytes that has been processed so far .ie n .IP "$revisions\->size" 4 .el .IP "\f(CW$revisions\fR\->size" 4 .IX Item "$revisions->size" Returns the total size of the dump file in bytes. .SH "EXAMPLE" .IX Header "EXAMPLE" .SS "Extract the article text of each revision of an article using a given title" .IX Subsection "Extract the article text of each revision of an article using a given title" .Vb 1 \& #!/usr/bin/perl \& \& use strict; \& use warnings; \& use MediaWiki::DumpFile::Compat; \& \& my $file = shift(@ARGV) or die "must specify a MediaWiki dump of the current pages"; \& my $title = shift(@ARGV) or die "must specify an article title"; \& my $pmwd = Parse::MediaWikiDump\->new; \& my $dump = $pmwd\->revisions($file); \& my $found = 0; \& \& binmode(STDOUT, \*(Aq:utf8\*(Aq); \& binmode(STDERR, \*(Aq:utf8\*(Aq); \& \& #this is the only currently known value but there could be more in the future \& if ($dump\->case ne \*(Aqfirst\-letter\*(Aq) { \& die "unable to handle any case setting besides \*(Aqfirst\-letter\*(Aq"; \& } \& \& $title = case_fixer($title); \& \& while(my $revision = $dump\->next) { \& if ($revision\->title eq $title) { \& print STDERR "Located text for $title revision ", $revision\->revision_id, "\en"; \& my $text = $revision\->text; \& print $$text; \& \& $found = 1; \& } \& } \& \& print STDERR "Unable to find article text for $title\en" unless $found; \& exit 1; \& \& #removes any case sensativity from the very first letter of the title \& #but not from the optional namespace name \& sub case_fixer { \& my $title = shift; \& \& #check for namespace \& if ($title =~ /^(.+?):(.+)/) { \& $title = $1 . \*(Aq:\*(Aq . ucfirst($2); \& } else { \& $title = ucfirst($title); \& } \& \& return $title; \& } .Ve .SH "LIMITATIONS" .IX Header "LIMITATIONS" .SS "Version 0.4" .IX Subsection "Version 0.4" This class was updated to support version 0.4 dump files from a MediaWiki instance but it does not currently support any of the new information available in those files.