Alvis-Convert

 view release on metacpan or  search on metacpan

lib/Alvis/Convert.pm  view on Meta::CPAN

package Alvis::Convert;

$Alvis::Convert::VERSION = '0.4';

########################################################################
#
# A general "set of document files in some format" -> 
# "set of files in ALVIS format" converter.
#
#   -- Kimmo Valtonen
#
########################################################################

use strict;
use warnings;

use Carp;
use Data::Dumper;
use Encode;
use XML::LibXML;

use Alvis::Canonical;
use Alvis::Document;
use Alvis::Document::Encoding;
use Alvis::Document::Meta;
use Alvis::Document::Links;
use Alvis::Document::Type;
use Alvis::AinoDump;
use Alvis::Wikipedia::XMLDump;


############################################################################
#
#  Global variables
#
############################################################################

# Types of documents handled
our ($UNKNOWN_FILE_TYPE,$DIR,$META,$HTML,$NEWS_XML,$AINODUMP,
     $WIKIPEDIA_XML_DUMP)=(0..6);
my %RecognizedEntryTypeDescs=($UNKNOWN_FILE_TYPE=>"Guess the file type",
			      $DIR=>"Directory",
			      $META=>"Meta information",
			      $HTML=>"HTML",
			      $NEWS_XML=>
			      "XML information about a news article",
			      $AINODUMP=>"ainodump",
			      $WIKIPEDIA_XML_DUMP=>"Wikipedia XML dump");

############################################################################
#
#  Error message stuff
#
############################################################################

my ($ERR_OK,
    $ERR_CANONICAL,
    $ERR_ASSEMBLER,
    $ERR_CANDOC_CONV,
    $ERR_META,
    $ERR_LINKS,
    $ERR_LINK_ADD,
    $ERR_ASSEMBLE,
    $ERR_NO_NEWS_XML_TEXT,
    $ERR_XML_PARSER,
    $ERR_XML_PARSE,
    $ERR_NO_URL,
    $ERR_ENCODING_WIZARD,
    $ERR_UTF8_CONV,
    $ERR_ENCODING_CONV,
    $ERR_TYPE_SUFFIX,
    $ERR_READ_HTML,
    $ERR_READ_NEWS_XML,
    $ERR_ALVIS_CONV,
    $ERR_ALVIS_SUFFIX,
    $ERR_NO_OUTPUT_ROOT_DIR,
    $ERR_WRITING_OUTPUT,
    $ERR_DIR_CONV,



( run in 0.817 second using v1.01-cache-2.11-cpan-39bf76dae61 )