Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Browse files

prepare v0.02

  • Loading branch information...
commit 7b6590899e9872f120a4e2ddea2f6dbfa740799a 1 parent 0109a1e
@patch authored
View
9 Build.PL
@@ -7,11 +7,12 @@ my $builder = Module::Build->new(
license => 'perl',
create_readme => 1,
configure_requires => {
- 'Module::Build' => 0.36,
+ 'Module::Build' => '0.36',
},
build_requires => {
- 'String::Dump' => 0.05,
- 'Test::More' => 0.82, # note()
+ 'Pod::Man' => '2.04',
+ 'String::Dump' => '0.05',
+ 'Test::More' => '0.82',
},
requires => {
'perl' => '5.8.0', # minimum Unicode support
@@ -21,7 +22,7 @@ my $builder = Module::Build->new(
'utf8' => 0,
'warnings' => 0,
'Carp' => 0,
- 'Moo' => 1.000000,
+ 'Moo' => '1.000000',
'Unicode::CaseFold' => 0,
'Unicode::Normalize' => 0,
},
View
8 Changes
@@ -1,11 +1,11 @@
Revision history for Perl module Lingua::Stem::UniNE
-v0.02 XXX
- - Added 50K generated Bulgarian and Persian tests
+v0.02 2013-04-08
+ - First public release to CPAN
+ - Significantly improved test coverage
- Fixed Persian bugs discovered by new tests
- - The 50K tests per language are now included in the repo only, not the distro
v0.01 2013-04-04
- First release
- Languages supported: Bulgarian (bg), Czech (cs), Persian (fa)
- - Code tested and reviewed by Kurt Starsinic
+ - Code reviewed and tested by Kurt Starsinic
View
3  MANIFEST
@@ -11,9 +11,10 @@ META.json
META.yml
README
t/00-load.t
+t/01-stemmer.t
t/bg.t
t/cs.t
-t/stemmer.t
+t/fa.t
xt/author/changes.t
xt/author/kwalitee.t
xt/author/pod-coverage.t
View
2  MANIFEST.SKIP
@@ -17,7 +17,7 @@
# Avoid files from the repository not intended for distribution
^README.pod$
^src\b
-^t/[a-z]{2}-50k.t$
+^t/exhaustive\b
^TODO$
# Avoid other random files
View
5 README.pod
@@ -6,7 +6,7 @@ Lingua::Stem::UniNE - University of Neuchâtel stemmers
=head1 VERSION
-This document describes Lingua::Stem::UniNE v0.01.
+This document describes Lingua::Stem::UniNE v0.02.
=head1 SYNOPSIS
@@ -112,9 +112,6 @@ L<Lingua::Stem::Snowball> provides alternate stemming algorithms for Finnish,
French, German, Hungarian, Italian, Portuguese, Russian, Spanish, and Swedish,
as well as other languages.
-L<Lingua::Stem::Any> provides a consistent unified interface for
-Lingua::Stem::UniNE, Lingua::Stem::Snowball, and other stemming modules on CPAN.
-
=head1 ACKNOWLEDGEMENTS
L<Jacques Savoy|http://members.unine.ch/jacques.savoy/> and Ljiljana Dolamic of
View
9 TODO
@@ -1,14 +1,9 @@
Lingua::Stem::UniNE to-do list
* Additional languages:
- * Semitic: Arabic, Persian
* Eastern: Bengali, Hindi, Marathi
* Uralic: Finnish, Hungarian
* Italic: French, Italian, Portuguese, Spanish
- * Others: German, Russian, Swedish
+ * Others: Arabic, German, Russian, Swedish
* Add aggressive option: Czech
-* Design API
-* More tests
-* Should it be Lingua::Stem::UniNE or ::Savoy? (contact Jacques Savoy)
-* Change to grapheme-level instead of codepoint-level
-* Add caching option? (see Lingua::Stem)
+* Add caching option
View
7 lib/Lingua/Stem/UniNE.pm
@@ -5,7 +5,7 @@ use utf8;
use Moo;
use Carp;
-our $VERSION = '0.01';
+our $VERSION = '0.02';
my @languages = qw( bg cs fa );
my %is_language = map { $_ => 1 } @languages;
@@ -62,7 +62,7 @@ Lingua::Stem::UniNE - University of Neuchâtel stemmers
=head1 VERSION
-This document describes Lingua::Stem::UniNE v0.01.
+This document describes Lingua::Stem::UniNE v0.02.
=head1 SYNOPSIS
@@ -168,9 +168,6 @@ L<Lingua::Stem::Snowball> provides alternate stemming algorithms for Finnish,
French, German, Hungarian, Italian, Portuguese, Russian, Spanish, and Swedish,
as well as other languages.
-L<Lingua::Stem::Any> provides a consistent unified interface for
-Lingua::Stem::UniNE, Lingua::Stem::Snowball, and other stemming modules on CPAN.
-
=head1 ACKNOWLEDGEMENTS
L<Jacques Savoy|http://members.unine.ch/jacques.savoy/> and Ljiljana Dolamic of
View
11 lib/Lingua/Stem/UniNE/BG.pm
@@ -8,7 +8,7 @@ use parent 'Exporter';
use Unicode::CaseFold qw( fc );
use Unicode::Normalize qw( NFC );
-our $VERSION = '0.01';
+our $VERSION = '0.02';
our @EXPORT_OK = qw( stem stem_bg );
*stem_bg = \&stem;
@@ -125,7 +125,7 @@ Lingua::Stem::UniNE::BG - Bulgarian stemmer
=head1 VERSION
-This document describes Lingua::Stem::UniNE::BG v0.01.
+This document describes Lingua::Stem::UniNE::BG v0.02.
=head1 SYNOPSIS
@@ -140,10 +140,15 @@ This document describes Lingua::Stem::UniNE::BG v0.01.
A stemmer for the Bulgarian language.
+This module provides the C<stem> and C<stem_bg> functions, which are synonymous
+and can optionally be exported. They accept a single word and return a single
+stem.
+
=head1 SEE ALSO
L<Lingua::Stem::UniNE> provides a stemming object with access to all of the
-implemented University of Neuchâtel stemmers including this one.
+implemented University of Neuchâtel stemmers including this one. It has
+additional features like stemming lists or array references of words.
This stemming algorithm was defined in
L<Searching Strategies for the Bulgarian Language|http://dl.acm.org/citation.cfm?id=1298736>
View
11 lib/Lingua/Stem/UniNE/CS.pm
@@ -8,7 +8,7 @@ use parent 'Exporter';
use Unicode::CaseFold qw( fc );
use Unicode::Normalize qw( NFC );
-our $VERSION = '0.01';
+our $VERSION = '0.02';
our @EXPORT_OK = qw( stem stem_cs );
*stem_cs = \&stem;
@@ -132,7 +132,7 @@ Lingua::Stem::UniNE::CS - Czech stemmer
=head1 VERSION
-This document describes Lingua::Stem::UniNE::CS v0.01.
+This document describes Lingua::Stem::UniNE::CS v0.02.
=head1 SYNOPSIS
@@ -149,10 +149,15 @@ A light stemmer for the Czech language that removes case endings from nouns and
adjectives, possessive adjective endings from names, and takes care of
palatalization.
+This module provides the C<stem> and C<stem_cs> functions, which are synonymous
+and can optionally be exported. They accept a single word and return a single
+stem.
+
=head1 SEE ALSO
L<Lingua::Stem::UniNE> provides a stemming object with access to all of the
-implemented University of Neuchâtel stemmers including this one.
+implemented University of Neuchâtel stemmers including this one. It has
+additional features like stemming lists or array references of words.
This stemming algorithm was defined in
L<Indexing and stemming approaches for the Czech language|http://dl.acm.org/citation.cfm?id=1598600>
View
11 lib/Lingua/Stem/UniNE/FA.pm
@@ -9,7 +9,7 @@ use parent 'Exporter';
use Unicode::CaseFold qw( fc );
use Unicode::Normalize qw( NFC );
-our $VERSION = '0.01';
+our $VERSION = '0.02';
our @EXPORT_OK = qw( stem stem_fa );
*stem_fa = \&stem;
@@ -101,7 +101,7 @@ Lingua::Stem::UniNE::FA - Persian stemmer
=head1 VERSION
-This document describes Lingua::Stem::UniNE::FA v0.01.
+This document describes Lingua::Stem::UniNE::FA v0.02.
=head1 SYNOPSIS
@@ -116,10 +116,15 @@ This document describes Lingua::Stem::UniNE::FA v0.01.
A stemmer for the Persian (Farsi) language.
+This module provides the C<stem> and C<stem_fa> functions, which are synonymous
+and can optionally be exported. They accept a single word and return a single
+stem.
+
=head1 SEE ALSO
L<Lingua::Stem::UniNE> provides a stemming object with access to all of the
-implemented University of Neuchâtel stemmers including this one.
+implemented University of Neuchâtel stemmers including this one. It has
+additional features like stemming lists or array references of words.
This stemming algorithm was originally implemented by Ljiljana Dolamic in
L<Java|http://members.unine.ch/jacques.savoy/clef/persianStemmerUnicode.txt>.
View
0  t/stemmer.t → t/01-stemmer.t
File renamed without changes
View
0  t/bg-50k.t → t/exhaustive/bg-50k.t
File renamed without changes
View
0  t/cs-50k.t → t/exhaustive/cs-50k.t
File renamed without changes
View
0  t/fa-50k.t → t/exhaustive/fa-50k.t
File renamed without changes
Please sign in to comment.
Something went wrong with that request. Please try again.