Make cleanup of encodings, moving webpac closer to having

[webpac2] / lib / WebPAC / Input.pm

diff --git a/lib/WebPAC/Input.pm b/lib/WebPAC/Input.pm
index 37d5166..218a969 100644 (file)
--- a/lib/WebPAC/Input.pm
+++ b/lib/WebPAC/Input.pm
@@ -8,19 +8,15 @@ use blib;
 use WebPAC::Common;
 use base qw/WebPAC::Common/;
 use Data::Dump qw/dump/;
-use Encode qw/from_to/;
+use Encode qw/decode from_to/;
 
 =head1 NAME
 
 WebPAC::Input - read different file formats into WebPAC
 
-=head1 VERSION
-
-Version 0.18
-
 =cut
 
-our $VERSION = '0.18';
+our $VERSION = '0.19';
 
 =head1 SYNOPSIS
 
@@ -61,7 +57,6 @@ Create new input database object.
 
   my $db = new WebPAC::Input(
        module => 'WebPAC::Input::MARC',
-       encoding => 'ISO-8859-2',
        recode => 'char pairs',
        no_progress_bar => 1,
        input_config => {
@@ -72,10 +67,6 @@ Create new input database object.
 C<module> is low-level file format module. See L<WebPAC::Input::ISIS> and
 L<WebPAC::Input::MARC>.
 
-Optional parametar C<encoding> specify application code page (which will be
-used internally). This should probably be your terminal encoding, and by
-default, it C<ISO-8859-2>.
-
 C<recode> is optional string constisting of character or words pairs that
 should be replaced in input stream.
 
@@ -93,9 +84,10 @@ sub new {
 
        my $log = $self->_get_logger;
 
-       $log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup});
-       $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup});
-       $log->logconfess("low_mem argument is not suppored any more. rewrite it to load_row and save_row") if ($self->{low_mem});
+       $log->logconfess("code_page argument is not suppored any more.") if $self->{code_page};
+       $log->logconfess("encoding argument is not suppored any more.") if $self->{encoding};
+       $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if $self->{lookup};
+       $log->logconfess("low_mem argument is not suppored any more. rewrite it to load_row and save_row") if $self->{low_mem};
 
        $log->logconfess("specify low-level file format module") unless ($self->{module});
        my $module_path = $self->{module};
@@ -105,8 +97,6 @@ sub new {
 
        require $module_path;
 
-       $self->{'encoding'} ||= 'ISO-8859-2';
-
        $self ? return $self : return undef;
 }
 
@@ -118,7 +108,8 @@ This function will read whole database in memory and produce lookups.
 
  $input->open(
        path => '/path/to/database/file',
-       code_page => 'cp852',
+       input_encoding => 'cp852',
+       strict_encoding => 0,
        limit => 500,
        offset => 6000,
        stats => 1,
@@ -143,7 +134,7 @@ This function will read whole database in memory and produce lookups.
 
  );
 
-By default, C<code_page> is assumed to be C<cp852>.
+By default, C<input_encoding> is assumed to be C<cp852>.
 
 C<offset> is optional parametar to position at some offset before reading from database.
 
@@ -164,6 +155,8 @@ overrides C<modify_records> if both exists for same input.
 C<save_row> and C<load_row> are low-level implementation of store engine. Calling convention
 is documented in example above.
 
+C<strict_encoding> should really default to 1, but it doesn't for now.
+
 Returns size of database, regardless of C<offset> and C<limit>
 parametars, see also C<size>.
 
@@ -174,7 +167,10 @@ sub open {
        my $arg = {@_};
 
        my $log = $self->_get_logger();
+       $log->debug( "arguments: ",dump( $arg ));
 
+       $log->logconfess("encoding argument is not suppored any more.") if $self->{encoding};
+       $log->logconfess("code_page argument is not suppored any more.") if $self->{code_page};
        $log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup});
        $log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef}))
                if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE');
@@ -182,10 +178,9 @@ sub open {
        $log->debug( $arg->{lookup_coderef} ? '' : 'not ', "using lookup_coderef");
 
        $log->logcroak("need path") if (! $arg->{'path'});
-       my $code_page = $arg->{'code_page'} || 'cp852';
+       my $input_encoding = $arg->{'input_encoding'} || $self->{'input_encoding'} || 'cp852';
 
        # store data in object
-       $self->{'input_code_page'} = $code_page;
        foreach my $v (qw/path offset limit/) {
                $self->{$v} = $arg->{$v} if ($arg->{$v});
        }
@@ -240,7 +235,7 @@ sub open {
 #              filter => sub {
 #                      my ($l,$f_nr) = @_;
 #                      return unless defined($l);
-#                      from_to($l, $code_page, $self->{'encoding'});
+#                      $l = decode($input_encoding, $l);
 #                      $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
 #                      return $l;
 #              },
@@ -278,7 +273,12 @@ sub open {
        # store size for later
        $self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
 
-       $log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{encoding}", $self->{stats} ? ' [stats]' : '');
+       my $strict_encoding = $arg->{strict_encoding} || $self->{strict_encoding}; ## FIXME should be 1 really
+
+       $log->info("processing $self->{size}/$size records [$from_rec-$to_rec]",
+               " encoding $input_encoding ", $strict_encoding ? ' [strict]' : '',
+               $self->{stats} ? ' [stats]' : '',
+       );
 
        # read database
        for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
@@ -296,7 +296,8 @@ sub open {
                                $log->debug("-=> $f_nr ## $l");
 
                                # codepage conversion and recode_regex
-                               from_to($l, $code_page, $self->{'encoding'});
+#                              $l = decode($input_encoding, $l, 1);
+                               from_to( $l, $input_encoding, 'utf-8', 1 );
                                $l =~ s/($recode_regex)/$recode_map->{$1}/g if ($recode_regex && $recode_map);
 
                                # apply regexps