view release on metacpan or  search on metacpan

lib/Data/Edit/Xml/Reuse.pm  view on Meta::CPAN

#!/usr/bin/perl -I/home/phil/r/salesForce/perl/ -I/home/phil/perl/cpan/DataEditXml/lib  -I/home/phil/perl/cpan/DataTableText/lib -I/home/phil/perl/cpan/DitaGBStandard/lib -I/home/phil/perl/cpan/DataEditXmlToDita/lib -I/home/phil/perl/cpan/DataEditXml...
#-------------------------------------------------------------------------------
# Reuse Xml via Dita conrefs.
# Philip R Brenan at gmail dot com, Appa Apps Ltd Inc, 2019
#-------------------------------------------------------------------------------
# podDocumentation

package Data::Edit::Xml::Reuse;
our $VERSION = 20200503;
use v5.26;
use warnings FATAL => qw(all);
use strict;
use Carp qw(confess cluck);
use Data::Dump qw(dump);
use Data::Edit::Xml;
use Data::Edit::Xml::Xref;
use Data::Table::Text qw(:all);
use Dita::GB::Standard;
use Storable qw(store retrieve);
use Time::HiRes qw(time);
use utf8;

#D1 Reuse Xml                                                                   # Reuse Xml via Dita conrefs.

sub newReuse(%)                                                                 #P Create a new cross reuser.
 {my (%attributes) = @_;                                                        # Attributes

  my $reuse = genHash(__PACKAGE__,                                              # Attributes used by the reuser.
    dictionary                          => undef,                               #I The dictionary file into which to store the duplicate L<Xml>.
    fileExtensions                      => [qw(.dita .ditamap .xml .fodt)],     #I The extensions of the L<Xml> files to examine in the L<inputFolder>.
    getFileUrl => qq(/cgi-bin/uiSelfServiceXref/client.pl?getFile=),            #I An optional url to retrieve a specified file from the server running xref used in generating html reports. The complete url is obtained by appending the fully qualifie...
    htmlFolder                          => undef,                               #I Folder into which to write reports as html.
    inputFiles                          => [],                                  # The files selected from L<inputFolder> for analysis because their extensions matched L<fileExtensions>.
    inputFolder                         => undef,                               #I A folder containing the L<xml> files with extensions named in L<fileExtensions> to be analyzed for reuse.
    matchBlocks                         => [],                                  # [[md5, content]*] blocks of content that match with the confidence level expressed by L<matchSimilarContent>
    matchInBlock                        => {},                                  # {md5 => matchBlocks} : index into L<matchBlocks> by md5 sum.
    matchSimilarTagContent              => 0.5,                                 #I Confidence level between 0 and 1: match content under L<tags> with this level of confidence.
    maximumColumnWidth                  => 180,                                 #I Truncate columns in text reports to this length or allow any width if B<undef>.
    minimumLength                       =>  16,                                 #I The minimum length content must have to be considered for matching.
    minimumReferences                   =>   2,                                 #I The minimum number of references content must have before it can be reused.
    outputFolder                        => undef,                               #I A folder into which to write the deduplicated L<Xml>.
    reportsFolder                       => undef,                               #I A folder into which reports will be written.
    reusableContent                     => {},                                  # {tag}{md5sum}{content}++ potentially reusable content.
    tags                                => {p=>1},                              #I {tag=>1} only consider tags that appear as keys in this hash with truthful values.
    timeEnded                           => undef,                               # Time the run ended.
    timeStart                           => undef,                               # Time the run started.
   );

  loadHash($reuse, @_);                                                         # Load attributes complaining about any invalid ones
 } # newReuse

sub reuse(%)                                                                    # Check Xml for reuse opportunities.
 {my (%attributes) = @_;                                                        # Reuse attributes
  my $reuse = newReuse(%attributes);                                            # Create the reuser

  $reuse->timeStart = time;                                                     # Start time

  for my $attr(qw(inputFolder outputFolder reportsFolder))
   {$reuse->{$attr} or confess "Please supply a value for: $attr";
   }

  $reuse->dictionary //= fpe($reuse->outputFolder, qw(dictionary xml));         # Default dictionary

  lll "Reuse started on input folder:", $reuse->inputFolder;                    # Title

  my @series =                                                                  # Must be done in series at the start
   (q(loadInputFiles),
    q(analyzeInputFiles),
    q(conRef),
   );

  if (1)                                                                        # Perform phases in series that must be run in series
   {my @times;

    for my $phase(@series)                                                      # Each phase in series
     {my $startTime = time;
      lll "Reuse phase $phase";