r62966 - in /trunk/libhtml-parser-perl/debian: changelog patches/example_selfdocs.patch

Sun Sep 26 00:21:31 UTC 2010

Author: periapt-guest
Date: Sun Sep 26 00:18:31 2010
New Revision: 62966

URL: http://svn.debian.org/wsvn/pkg-perl/?sc=1&rev=62966
Log:
* Added patch to address example issues: (Closes: #584088)
  - Added comments to several scripts in eg directory.
  - Added README to eg directory.
  - Encoding text in certain scripts to ensure clean run on wide chars.
  - Adding rule to examples install

Modified:
    trunk/libhtml-parser-perl/debian/changelog
    trunk/libhtml-parser-perl/debian/patches/example_selfdocs.patch

Modified: trunk/libhtml-parser-perl/debian/changelog
URL: http://svn.debian.org/wsvn/pkg-perl/trunk/libhtml-parser-perl/debian/changelog?rev=62966&op=diff
==============================================================================

--- trunk/libhtml-parser-perl/debian/changelog (original)
+++ trunk/libhtml-parser-perl/debian/changelog Sun Sep 26 00:18:31 2010
@@ -1,17 +1,17 @@
 libhtml-parser-perl (3.68-1) UNRELEASED; urgency=low
 
   [ Salvatore Bonaccorso ]
-  # no need to upload, only changes in POD and 
-  # for specific case of bleadperl 
-  IGNORE-VERSION: 3.68-1
-  
   * New upstream release
   * Bump Standards-Version to 3.9.1.
   * Refresh debian/copyright file.
 
   [ Nicholas Bamber ]
   * Added myself to Uploaders
-  * Started working on #584088
+  * Added patch to address example issues: (Closes: #584088)
+    - Added comments to several scripts in eg directory.
+    - Added README to eg directory.
+    - Encoding text in certain scripts to ensure clean run on wide chars.
+    - Adding rule to examples install
 
  -- Salvatore Bonaccorso <salvatore.bonaccorso at gmail.com>  Thu, 02 Sep 2010 07:49:31 +0200
 

Modified: trunk/libhtml-parser-perl/debian/patches/example_selfdocs.patch
URL: http://svn.debian.org/wsvn/pkg-perl/trunk/libhtml-parser-perl/debian/patches/example_selfdocs.patch?rev=62966&op=diff
==============================================================================
--- trunk/libhtml-parser-perl/debian/patches/example_selfdocs.patch (original)
+++ trunk/libhtml-parser-perl/debian/patches/example_selfdocs.patch Sun Sep 26 00:18:31 2010
@@ -1,3 +1,10 @@
+Author: Nicholas Bamber <nicholas at periapt.co.uk>
+Subject: Fix issues with example scripts
+ - Make sure all the scripts have some explanatory comment
+ - Add a README file in the eg directory
+ - Make sure the scripts run cleanly
+Bug: http://rt.cpan.org/Public/Bug/Display.html?id=58016
+Last-Update: 2010-09-26
 --- a/eg/hanchors
 +++ b/eg/hanchors
 @@ -6,6 +6,7 @@
@@ -19,9 +26,11 @@
      $text =~ s/\s+/ /g;
 --- /dev/null
 +++ b/eg/README
-@@ -0,0 +1,11 @@
-+For all of these scripts if you run them with a file argument, where the file
-+contains some HTML, you should get some output.
+@@ -0,0 +1,23 @@
++For most of these scripts if you run them with a file argument, where the file
++contains some HTML, you should get some output. The 'h*sub' scripts take two
++arguments the first of which is a perl expression and the second an HTML file.
++In any case all of the files have an exlanatory comment.
 +
 +For example try running:
 +
@@ -30,6 +39,16 @@
 +
 +Of course if http://www.debian.org is not your favourite web site you can
 +make the appropriate substitution.
++
++hanchors        - List all anchors in the HTML
++hlc             - Correct any upper case tags to lower case
++hstrip          - Removes deprecated scripting and styling tags and attributes
++htextsub        - Apply arbirary perl expression to all text within HTML
++hrefsub         - Apply arbirary perl expression to all hrefs within HTML
++htitle          - Print title of the HTML document
++hdump           - Output event information whilst parsing HTML document
++hform           - Print analysis of form controls present in HTML
++htext           - Print all the text from the HTML
 +
 --- a/eg/hlc
 +++ b/eg/hlc
@@ -43,3 +62,65 @@
  use strict;
  use HTML::Parser ();
  
+--- a/eg/hstrip
++++ b/eg/hstrip
+@@ -1,6 +1,7 @@
+ #!/usr/bin/perl -w
+ 
+-# This script cleans up an HTML document
++# This script cleans up an HTML document.
++# Specifically it removes deprecated styling and scripting tags.
+ 
+ use strict;
+ use HTML::Parser ();
+--- a/eg/hdump
++++ b/eg/hdump
+@@ -1,5 +1,8 @@
+ #!/usr/bin/perl -w
+ 
++# This script will output event information as it parses the HTML document.
++# This gives the user a "Parser's eye view" of an HTML document.
++
+ use HTML::Parser ();
+ use Data::Dump ();
+ 
+--- a/eg/hform
++++ b/eg/hform
+@@ -1,5 +1,6 @@
+ #!/usr/bin/perl -w
+ 
++# Print information about forms and their controls present in the HTML.
+ # See also HTML::Form module
+ 
+ use HTML::PullParser ();
+--- a/eg/htext
++++ b/eg/htext
+@@ -4,6 +4,7 @@
+ 
+ use strict;
+ use HTML::Parser 3.00 ();
++use Encode;
+ 
+ my %inside;
+ 
+@@ -17,7 +18,7 @@
+ sub text
+ {
+     return if $inside{script} || $inside{style};
+-    print $_[0];
++    print encode('utf8',$_[0]);
+ }
+ 
+ HTML::Parser->new(api_version => 3,
+--- a/eg/htextsub
++++ b/eg/htextsub
+@@ -3,6 +3,9 @@
+ # Shows how to mangle all plain  text in an HTML document, using an arbitrary
+ # Perl expression. Plain text is all text not within a tag declaration, i.e.
+ # not in <p ...>, but possibly between <p> and </p>
++# Example (Reverse 'Debian' in all text) :
++#       lynx -dump -source -raw http://www/debian.org > /tmp/a.txt
++#       ./htextsub '$_ =~ s/Debian/Naibed/gi' /tmp/a.txt
+ 
+ use strict;
+ my $code = shift || usage();


