Changeset 2734

Timestamp:

2001-09-10T10:55:01+12:00 (23 years ago)

Author:

sjboddie

Message:

Chinese text segmentation is now done whenever language="zh" instead of
just when encoding="gb"

File:

• trunk/gsdl/perllib/plugins/BasPlug.pm (modified) (3 diffs)

trunk/gsdl/perllib/plugins/BasPlug.pm

@@ -291 +291 @@
     # read in file ($text will be in utf8)
     my $text = "";
-    $self->read_file ($filename, $encoding, \$text);
+    $self->read_file ($filename, $encoding, $language, \$text);
 
     if (!length ($text)) {
@@ -333 +333 @@
 sub read_file {
     my $self = shift (@_);
-    my ($filename, $encoding, $textref) = @_;
+    my ($filename, $encoding, $language, $textref) = @_;
 
     if (!-r $filename)
@@ -356 +356 @@
     $reader->read_file ($textref);
 
-    if ($encoding eq "gb") {
+    if ($language eq "zh") {
         # segment the Chinese words
         $$textref = &cnseg::segment($$textref);