Changeset 35409 for lang/perl/MSWord-ExtractContent

Timestamp:

09/17/09 16:58:57 (4 years ago)

Author:

dayflower

Message:

CLX をきちんとハンドリングするように修正した。

Location:

lang/perl/MSWord-ExtractContent/trunk

Files:

• lib/File/Extract/MSWord.pm (modified) (1 diff)
• lib/MSWord/ExtractContent.pm (modified) (3 diffs)
• t/97_podspell.t (modified) (1 diff)

lang/perl/MSWord-ExtractContent/trunk/lib/File/Extract/MSWord.pm

@@ -30 +30 @@
 __END__
 
-=encoding utf-8
-
-=for stopwords
-MSWord
-
 =head1 NAME
 

lang/perl/MSWord-ExtractContent/trunk/lib/MSWord/ExtractContent.pm

@@ -300 +300 @@
         = substr $self->_table_stream, $self->{_fcClx}, $self->{_lcbClx};
 
-    $self->{_prm_encoding} = ord(substr $clx, 0, 1, q{});
+    while (length $clx > 0) {
+        my $clxt = ord(substr $clx, 0, 1, q{});
+
+        last  if $clxt == 2;    # plcfpcd
+
+        if ($clxt == 1) {       # grpprl => SKIP
+            my $skip = _get_short(substr $clx, 0, 2, q{});
+
+            substr $clx, 0, $skip, q{};
+        }
+        else {
+            croak "Unknown CLX block.";
+        }
+    }
+    croak "PCDs not found"  if length $clx <= 0;
+
 
     my $length = _get_long(substr $clx, 0, 4, q{});
-    if ($length != length $clx) {
-        carp "Unmatched PCD length.";
-    }
-
-    my $n = ( length($clx) - $LENGTH_CP )  /  ( $LENGTH_CP + $LENGTH_PCD );
+
+    my $n = ( $length - $LENGTH_CP )  /  ( $LENGTH_CP + $LENGTH_PCD );
     printf {*STDERR} "number of PCDs: %d\n", $n  if $DEBUG;
 
@@ -501 +513 @@
 1;
 __END__
-
-=encoding utf-8
-
-=for stopwords
-functionalities
-utf
-msword
-CHP CHaracter PAP PAragraph
 
 =head1 NAME
@@ -609 +613 @@
 =head1 LIMITATIONS
 
+Only support Microsoft Word binary document.
+Does not support Microsoft Word XML document (.docx).
+
 This module does not handle PAP (PAragraph Properties) and CHP (CHaracter
 Properties), that define paragraphs and characters style.

lang/perl/MSWord-ExtractContent/trunk/t/97_podspell.t

@@ -11 +11 @@
 Nobuaki
 ITO
+functionalities
 utf
+docx
+msword
+CHP
+CHaracter
+PAP
+PAragraph