X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=perl%2Fdemo%2Fpod.pm;fp=perl%2Fdemo%2Fpod.pm;h=e20e78d52e3bc82426b4f379a1143c4d81cca3e2;hb=af03c4a4f5320b52c7cc5f47bab7c9ad4b3e384d;hp=0000000000000000000000000000000000000000;hpb=54867e37cc72f7a550a15ed77de30e0c1837b57d;p=idzebra-moved-to-github.git

diff --git a/perl/demo/pod.pm b/perl/demo/pod.pm
new file mode 100644
index 0000000..e20e78d
--- /dev/null
+++ b/perl/demo/pod.pm
@@ -0,0 +1,65 @@
+#!/usr/bin/perl
+use strict;
+# ----------------------------------------------------------------------------
+# A dummy example to demonstrate perl filters for zebra. This is going to
+# extract information from the .pm perl module files.
+# ----------------------------------------------------------------------------
+package pod;
+
+use IDZebra::Filter;
+use IDZebra::Data1;
+use Pod::Text;
+our @ISA=qw(IDZebra::Filter);
+1;
+
+
+sub init {
+    # Initialization code may come here
+}
+
+sub process {
+    my ($self, $d1) = @_;
+
+    my $tempfile_in = "/tmp/strucc.in";
+    my $tempfile_out = "/tmp/strucc.out";
+    my $parser = Pod::Text->new (sentence => 0, width => 78);
+
+    my $r1=$d1->mk_root('pod');    
+    my $root=$d1->mk_tag($r1,'pod');
+
+    # This is dirty... Pod::Parser doesn't seems to support 
+    # parsing a string, so we have to write the whole thing out into a 
+    # temporary file
+    open (TMP, ">$tempfile_in");
+    print TMP $self->readall(10240);
+    close (TMP);
+
+    $parser->parse_from_file ($tempfile_in, $tempfile_out);
+
+    my $section;
+    my $data;
+    open (TMP, "$tempfile_out");
+    while(<TMP>) {
+	chomp;
+	if (/^([A-Z]+)\s*$/) {
+	    my $ss = $1;
+	    if ($section) {
+		my $tag = $d1->mk_tag($root,$section);
+		$d1->mk_text($tag,$data) if ($data);
+	    }
+	    $section = $ss;
+	    $data = "";
+	    next;
+	}
+	s/^\s+|\s+$//g;
+	$data.="$_\n";
+    }
+
+    if ($section) { 
+	my $tag = $d1->mk_tag($root,$section);
+	$d1->mk_text($tag,$data) if ($data);
+    }
+    close (TMP);
+    
+    return ($r1);
+}