Text-Phonetic

 view release on metacpan or  search on metacpan

Changes  view on Meta::CPAN

Revision history for Perl module Text::Phonetic


2.09 Wed May 31 2017
    - Fix Koeln algorithm (rt123300)

2.08 Wed May 31 2017
    - Makefile fix for perl 5.26

2.07 Sat Apr 2 2016
    - Fix tests
    - Declare dependencies

2.06 Wed Sep 23 2015
    - Moose -> Moo (implemented by Miquel Ruiz)
    - Update Phonix to match WAIS (implemented by olsgaard)
    - Fix typo (implemented by Dmitri Tikhonov)
    - Remove mymenta.* from dist (implemented by Sandro Cazzaniga)

2.05 Mon Jan 27 2014
    - Update POD
    - Dist housekeeping
    - Use Class::Load instead of Class::MOP to load classes

2.04 Sat Nov 17 2012
    - Fix failing tests
    - Check predicates only once
    - Dist housekeeping
    - Update documentation

2.02 Sat Oct 30 2009
    - Fix failing tests

2.01 Mon Oct 26 2009
    - Use Moose' extend instead of parent

2.00 Sun Oct 25 2009
    - Use Moose
    - Implement new constructor
    - Add optional attributes to soundex algorithm
    - Remove soundexnara algorithm (now in Soundex)
    - New API
    - Move author tests to xt/
    - Update makefile: Text::* modukes are optional, generate readme, add github repo
    - Fix linebreaks

1.07 Thu Oct 20 2008
    - Fixed warnings on empty strings (reported by Jürgen Peters)
    - Returns undef on empty strings

1.06 Thu Jul 16 2008
    - Fixed rule bug in T::P::Phonix (reported by Bart Massey)

1.05 Thu Jul 16 2008
    - More tests
    - Test coverage 94.8%
    - Fixed compare bugs
    - Pod encoding

1.04 Sun Apr 13 2008
    - Fixed Text::Phonetic::Phonix
    - Switched to Module::Install
    
1.03 Fri Apr 13 2008
    - Makefile not executable
    - Documentation
    - Added Text::Phonetic::Phonem

1.02 Sun Dec 12 2007
    - Corrected depenedicies in Makefile and META.yml, so that cpantesters tests don't fail
    
1.01 Sun Dec 10 2007
    - Corrected depenedicies in Makefile and META.yml, so that cpantesters tests don't fail
    
1.00 Sun Nov 11 2007
    - original version; created by ExtUtils::ModuleMaker 0.49

LICENSE  view on Meta::CPAN

Terms of Perl itself

a) the GNU General Public License as published by the Free
   Software Foundation; either version 1, or (at your option) any
   later version, or
b) the "Artistic License"

---------------------------------------------------------------------------

The General Public License (GPL)
Version 2, June 1991

Copyright (C) 1989, 1991 Free Software Foundation, Inc. 675 Mass Ave,
Cambridge, MA 02139, USA. Everyone is permitted to copy and distribute
verbatim copies of this license document, but changing it is not allowed.

Preamble

The licenses for most software are designed to take away your freedom to share
and change it. By contrast, the GNU General Public License is intended to
guarantee your freedom to share and change free software--to make sure the
software is free for all its users. This General Public License applies to most of
the Free Software Foundation's software and to any other program whose
authors commit to using it. (Some other Free Software Foundation software is
covered by the GNU Library General Public License instead.) You can apply it to
your programs, too.

When we speak of free software, we are referring to freedom, not price. Our
General Public Licenses are designed to make sure that you have the freedom
to distribute copies of free software (and charge for this service if you wish), that
you receive source code or can get it if you want it, that you can change the
software or use pieces of it in new free programs; and that you know you can do
these things.

To protect your rights, we need to make restrictions that forbid anyone to deny
you these rights or to ask you to surrender the rights. These restrictions
translate to certain responsibilities for you if you distribute copies of the
software, or if you modify it.

For example, if you distribute copies of such a program, whether gratis or for a
fee, you must give the recipients all the rights that you have. You must make
sure that they, too, receive or can get the source code. And you must show
them these terms so they know their rights.

We protect your rights with two steps: (1) copyright the software, and (2) offer
you this license which gives you legal permission to copy, distribute and/or
modify the software.

Also, for each author's protection and ours, we want to make certain that
everyone understands that there is no warranty for this free software. If the
software is modified by someone else and passed on, we want its recipients to
know that what they have is not the original, so that any problems introduced by
others will not reflect on the original authors' reputations.

Finally, any free program is threatened constantly by software patents. We wish
to avoid the danger that redistributors of a free program will individually obtain
patent licenses, in effect making the program proprietary. To prevent this, we
have made it clear that any patent must be licensed for everyone's free use or
not licensed at all.

The precise terms and conditions for copying, distribution and modification
follow.

GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND
MODIFICATION

0. This License applies to any program or other work which contains a notice
placed by the copyright holder saying it may be distributed under the terms of
this General Public License. The "Program", below, refers to any such program
or work, and a "work based on the Program" means either the Program or any
derivative work under copyright law: that is to say, a work containing the
Program or a portion of it, either verbatim or with modifications and/or translated
into another language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".

Activities other than copying, distribution and modification are not covered by
this License; they are outside its scope. The act of running the Program is not
restricted, and the output from the Program is covered only if its contents
constitute a work based on the Program (independent of having been made by
running the Program). Whether that is true depends on what the Program does.

1. You may copy and distribute verbatim copies of the Program's source code as
you receive it, in any medium, provided that you conspicuously and appropriately
publish on each copy an appropriate copyright notice and disclaimer of warranty;
keep intact all the notices that refer to this License and to the absence of any
warranty; and give any other recipients of the Program a copy of this License
along with the Program.

You may charge a fee for the physical act of transferring a copy, and you may at
your option offer warranty protection in exchange for a fee.

2. You may modify your copy or copies of the Program or any portion of it, thus
forming a work based on the Program, and copy and distribute such
modifications or work under the terms of Section 1 above, provided that you also
meet all of these conditions:

a) You must cause the modified files to carry prominent notices stating that you
changed the files and the date of any change.

b) You must cause any work that you distribute or publish, that in whole or in
part contains or is derived from the Program or any part thereof, to be licensed
as a whole at no charge to all third parties under the terms of this License.

c) If the modified program normally reads commands interactively when run, you
must cause it, when started running for such interactive use in the most ordinary
way, to print or display an announcement including an appropriate copyright
notice and a notice that there is no warranty (or else, saying that you provide a
warranty) and that users may redistribute the program under these conditions,
and telling the user how to view a copy of this License. (Exception: if the
Program itself is interactive but does not normally print such an announcement,
your work based on the Program is not required to print an announcement.)

These requirements apply to the modified work as a whole. If identifiable
sections of that work are not derived from the Program, and can be reasonably
considered independent and separate works in themselves, then this License,
and its terms, do not apply to those sections when you distribute them as
separate works. But when you distribute the same sections as part of a whole
which is a work based on the Program, the distribution of the whole must be on
the terms of this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.

Thus, it is not the intent of this section to claim rights or contest your rights to
work written entirely by you; rather, the intent is to exercise the right to control
the distribution of derivative or collective works based on the Program.

In addition, mere aggregation of another work not based on the Program with the
Program (or with a work based on the Program) on a volume of a storage or
distribution medium does not bring the other work under the scope of this
License.

3. You may copy and distribute the Program (or a work based on it, under
Section 2) in object code or executable form under the terms of Sections 1 and 2
above provided that you also do one of the following:

a) Accompany it with the complete corresponding machine-readable source
code, which must be distributed under the terms of Sections 1 and 2 above on a
medium customarily used for software interchange; or,

b) Accompany it with a written offer, valid for at least three years, to give any
third party, for a charge no more than your cost of physically performing source
distribution, a complete machine-readable copy of the corresponding source
code, to be distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,

c) Accompany it with the information you received as to the offer to distribute
corresponding source code. (This alternative is allowed only for noncommercial
distribution and only if you received the program in object code or executable
form with such an offer, in accord with Subsection b above.)

The source code for a work means the preferred form of the work for making
modifications to it. For an executable work, complete source code means all the
source code for all modules it contains, plus any associated interface definition
files, plus the scripts used to control compilation and installation of the
executable. However, as a special exception, the source code distributed need
not include anything that is normally distributed (in either source or binary form)
with the major components (compiler, kernel, and so on) of the operating system
on which the executable runs, unless that component itself accompanies the
executable.

If distribution of executable or object code is made by offering access to copy
from a designated place, then offering equivalent access to copy the source
code from the same place counts as distribution of the source code, even though
third parties are not compelled to copy the source along with the object code.

4. You may not copy, modify, sublicense, or distribute the Program except as
expressly provided under this License. Any attempt otherwise to copy, modify,
sublicense or distribute the Program is void, and will automatically terminate
your rights under this License. However, parties who have received copies, or
rights, from you under this License will not have their licenses terminated so long
as such parties remain in full compliance.

5. You are not required to accept this License, since you have not signed it.
However, nothing else grants you permission to modify or distribute the Program
or its derivative works. These actions are prohibited by law if you do not accept
this License. Therefore, by modifying or distributing the Program (or any work
based on the Program), you indicate your acceptance of this License to do so,
and all its terms and conditions for copying, distributing or modifying the
Program or works based on it.

6. Each time you redistribute the Program (or any work based on the Program),
the recipient automatically receives a license from the original licensor to copy,
distribute or modify the Program subject to these terms and conditions. You
may not impose any further restrictions on the recipients' exercise of the rights
granted herein. You are not responsible for enforcing compliance by third parties
to this License.

7. If, as a consequence of a court judgment or allegation of patent infringement
or for any other reason (not limited to patent issues), conditions are imposed on
you (whether by court order, agreement or otherwise) that contradict the
conditions of this License, they do not excuse you from the conditions of this
License. If you cannot distribute so as to satisfy simultaneously your obligations
under this License and any other pertinent obligations, then as a consequence
you may not distribute the Program at all. For example, if a patent license would
not permit royalty-free redistribution of the Program by all those who receive
copies directly or indirectly through you, then the only way you could satisfy
both it and this License would be to refrain entirely from distribution of the
Program.

If any portion of this section is held invalid or unenforceable under any particular
circumstance, the balance of the section is intended to apply and the section as
a whole is intended to apply in other circumstances.

It is not the purpose of this section to induce you to infringe any patents or other
property right claims or to contest validity of any such claims; this section has
the sole purpose of protecting the integrity of the free software distribution
system, which is implemented by public license practices. Many people have
made generous contributions to the wide range of software distributed through
that system in reliance on consistent application of that system; it is up to the
author/donor to decide if he or she is willing to distribute software through any
other system and a licensee cannot impose that choice.

This section is intended to make thoroughly clear what is believed to be a
consequence of the rest of this License.

8. If the distribution and/or use of the Program is restricted in certain countries
either by patents or by copyrighted interfaces, the original copyright holder who
places the Program under this License may add an explicit geographical
distribution limitation excluding those countries, so that distribution is permitted
only in or among countries not thus excluded. In such case, this License
incorporates the limitation as if written in the body of this License.

9. The Free Software Foundation may publish revised and/or new versions of the
General Public License from time to time. Such new versions will be similar in
spirit to the present version, but may differ in detail to address new problems or
concerns.

Each version is given a distinguishing version number. If the Program specifies a
version number of this License which applies to it and "any later version", you
have the option of following the terms and conditions either of that version or of
any later version published by the Free Software Foundation. If the Program does
not specify a version number of this License, you may choose any version ever
published by the Free Software Foundation.

10. If you wish to incorporate parts of the Program into other free programs
whose distribution conditions are different, write to the author to ask for
permission. For software which is copyrighted by the Free Software Foundation,
write to the Free Software Foundation; we sometimes make exceptions for this.
Our decision will be guided by the two goals of preserving the free status of all
derivatives of our free software and of promoting the sharing and reuse of
software generally.

NO WARRANTY

11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS
NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE
COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM
"AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR
IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE
ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE,
YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR
CORRECTION.

12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED
TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY
WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS
PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES
ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM
(INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY
OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS
BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.

END OF TERMS AND CONDITIONS


---------------------------------------------------------------------------

The Artistic License

Preamble

The intent of this document is to state the conditions under which a Package
may be copied, such that the Copyright Holder maintains some semblance of
artistic control over the development of the package, while giving the users of the
package the right to use and distribute the Package in a more-or-less customary
fashion, plus the right to make reasonable modifications.

Definitions:

-    "Package" refers to the collection of files distributed by the Copyright
     Holder, and derivatives of that collection of files created through textual
     modification. 
-    "Standard Version" refers to such a Package if it has not been modified,
     or has been modified in accordance with the wishes of the Copyright
     Holder. 
-    "Copyright Holder" is whoever is named in the copyright or copyrights for
     the package. 
-    "You" is you, if you're thinking about copying or distributing this Package.
-    "Reasonable copying fee" is whatever you can justify on the basis of
     media cost, duplication charges, time of people involved, and so on. (You
     will not be required to justify it to the Copyright Holder, but only to the
     computing community at large as a market that must bear the fee.) 
-    "Freely Available" means that no fee is charged for the item itself, though
     there may be fees involved in handling the item. It also means that
     recipients of the item may redistribute it under the same conditions they
     received it. 

1. You may make and give away verbatim copies of the source form of the
Standard Version of this Package without restriction, provided that you duplicate
all of the original copyright notices and associated disclaimers.

2. You may apply bug fixes, portability fixes and other modifications derived from
the Public Domain or from the Copyright Holder. A Package modified in such a
way shall still be considered the Standard Version.

3. You may otherwise modify your copy of this Package in any way, provided
that you insert a prominent notice in each changed file stating how and when
you changed that file, and provided that you do at least ONE of the following:

     a) place your modifications in the Public Domain or otherwise
     make them Freely Available, such as by posting said modifications
     to Usenet or an equivalent medium, or placing the modifications on
     a major archive site such as ftp.uu.net, or by allowing the
     Copyright Holder to include your modifications in the Standard
     Version of the Package.

     b) use the modified Package only within your corporation or
     organization.

     c) rename any non-standard executables so the names do not
     conflict with standard executables, which must also be provided,
     and provide a separate manual page for each non-standard
     executable that clearly documents how it differs from the Standard
     Version.

     d) make other distribution arrangements with the Copyright Holder.

4. You may distribute the programs of this Package in object code or executable
form, provided that you do at least ONE of the following:

     a) distribute a Standard Version of the executables and library
     files, together with instructions (in the manual page or equivalent)
     on where to get the Standard Version.

     b) accompany the distribution with the machine-readable source of
     the Package with your modifications.

     c) accompany any non-standard executables with their
     corresponding Standard Version executables, giving the
     non-standard executables non-standard names, and clearly
     documenting the differences in manual pages (or equivalent),
     together with instructions on where to get the Standard Version.

     d) make other distribution arrangements with the Copyright Holder.

5. You may charge a reasonable copying fee for any distribution of this Package.
You may charge any fee you choose for support of this Package. You may not
charge a fee for this Package itself. However, you may distribute this Package in
aggregate with other (possibly commercial) programs as part of a larger
(possibly commercial) software distribution provided that you do not advertise
this Package as a product of your own.

6. The scripts and library files supplied as input to or produced as output from
the programs of this Package do not automatically fall under the copyright of this
Package, but belong to whomever generated them, and may be sold
commercially, and may be aggregated with this Package.

7. C or perl subroutines supplied by you and linked into this Package shall not
be considered part of this Package.

8. Aggregation of this Package with a commercial distribution is always permitted
provided that the use of this Package is embedded; that is, when no overt attempt
is made to make this Package's interfaces visible to the end user of the
commercial distribution. Such use shall not be construed as a distribution of
this Package.

9. The name of the Copyright Holder may not be used to endorse or promote
products derived from this software without specific prior written permission.

10. THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR
IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR
PURPOSE.

The End


MANIFEST  view on Meta::CPAN

Changes
inc/Module/Install.pm
inc/Module/Install/AuthorRequires.pm
inc/Module/Install/Base.pm
inc/Module/Install/Can.pm
inc/Module/Install/Fetch.pm
inc/Module/Install/Makefile.pm
inc/Module/Install/Metadata.pm
inc/Module/Install/ReadmeFromPod.pm
inc/Module/Install/Win32.pm
inc/Module/Install/WriteAll.pm
lib/Text/Phonetic.pm
lib/Text/Phonetic/DaitchMokotoff.pm
lib/Text/Phonetic/DoubleMetaphone.pm
lib/Text/Phonetic/Koeln.pm
lib/Text/Phonetic/Metaphone.pm
lib/Text/Phonetic/Phonem.pm
lib/Text/Phonetic/Phonix.pm
lib/Text/Phonetic/Soundex.pm
LICENSE
Makefile.PL
MANIFEST			This list of files
META.yml
README
t/001_load.t
t/002_general.t
t/003_interface.t
t/004_wrapper.t
t/005_koeln.t
t/006_daitchmokotoff.t
t/007_phonix.t
t/008_phonem.t
t/009_empty.t
t/010_predicate.t
t/global.pl
t/lib/Text/Phonetic/Fake.pm
t/lib/Text/Phonetic/Real.pm
t/lib/Text/SomePhoneticAlgorithm.pm
Todo
xt/perlcritic.t
xt/pod.t
xt/podcoverage.t
xt/podstyle.t

META.yml  view on Meta::CPAN

---
abstract: 'A base class for phonetic algorithms'
author:
  - 'Maroš Kollár'
build_requires:
  ExtUtils::MakeMaker: 6.59
  Test::Most: 0
  Test::NoWarnings: 0
configure_requires:
  ExtUtils::MakeMaker: 6.59
distribution_type: module
dynamic_config: 1
generated_by: 'Module::Install version 1.18'
license: perl
meta-spec:
  url: http://module-build.sourceforge.net/META-spec-v1.4.html
  version: 1.4
name: Text-Phonetic
no_index:
  directory:
    - inc
    - t
    - xt
recommends:
  Text::DoubleMetaphone: 0
  Text::Metaphone: 0
requires:
  Class::Load: 0
  Module::Find: '0.11'
  Moo: '1.001000'
  Text::Soundex: '3.03'
  Text::Unidecode: 0
  perl: 5.8.0
resources:
  license: http://dev.perl.org/licenses/
  repository: git://github.com/maros/Text-Phonetic.git
version: '2.08'

Makefile.PL  view on Meta::CPAN

# Load the Module::Install bundled in ./inc/
use lib ".";
use strict;
use warnings;
use inc::Module::Install 1.05;

my $from = 'lib/Text/Phonetic.pm';

# Define metadata
name            'Text-Phonetic';
all_from        $from;
readme_from     $from;

perl_version    '5.008';

# Specific dependencies
requires        'Moo'                   => '1.001000';
requires        'Module::Find'          => '0.11';
requires        'Text::Unidecode'       => 0;
requires        'Text::Soundex'         => '3.03';
requires        'Class::Load'           => 0;

recommends      'Text::Metaphone'       => 0;
recommends      'Text::DoubleMetaphone' => 0;

feature 'Soundex support',
    -default   => 1,
    'Text::Soundex' => '3.03';

feature 'Metaphone support',
    -default   => 1,
    'Text::Metaphone' => 0;

feature 'DoubleMetaphone support',
    -default   => 1,
    'Text::DoubleMetaphone' => 0;

build_requires  'Test::Most'            => 0;
build_requires  'Test::NoWarnings'      => 0;

author_requires 'Test::Pod'             => '1.14';
author_requires 'Test::Pod::Coverage'   => '1.04';
author_requires 'Test::Perl::Critic'    => 0;
author_requires 'Module::Install::ReadmeFromPod'        => 0;

repository 'git://github.com/maros/Text-Phonetic.git';

WriteAll;

README  view on Meta::CPAN

NAME
    Text::Phonetic - A base class for phonetic algorithms

SYNOPSIS
      use Text::Phonetic::Metaphone;
  
      my $phonetic = Text::Phonetic::Metaphone->new();
      $encoded_string = $phonetic->encode($string);
      @encoded_list = $phonetic->encode(@list);
  
      my $same = $phonetic->compare($string1,$string2);

    Or

      use Text::Phonetic;
      my $phonetic = Text::Phonetic->load( algorithm => 'Phonix' );
      $encoded_string = $phonetic->encode($string);

    This module provides an easy and convinient way to encode names with
    various phonetic algorithms. It acts as a wrapper around other phonetic
    algorithm modules like Text::Metaphone, Text::DoubleMetaphone,
    Text::Soundex and also implements some other algorithms such as
    Text::Phonetic::DaitchMokotoff, Text::Phonetic::Koeln,
    Text::Phonetic::Phonem and Text::Phonetic::Phonix.

    This module can easily be subclassed.

DESCRIPTION
  Constructors
   new
     $obj = Text::Phonetic::SUBCLASS->new(%PARAMETERS)

    You can pass arbitrary attributes to the constructor. The only global
    attribute is "unidecode" which defaults to 1 if not set. This attribute
    controls if non-latin characters should be transliterated to A-Z (see
    also Text::Unidecode).

    Additional attributes may be defined by the various implementation
    classes.

   load
     $obj = Text::Phonetic->load(algorithm => $algorithm, %PARAMETERS)

    Alternative constructor which also loads the requested algorithm
    subclass.

  Methods
   encode
     $RETURN_STRING = $obj->encode($STRING);
     OR
     @RETURN_LIST = $obj->encode(@LIST);
     OR
     $RETURN_LIST_REF = $obj->encode(@LIST);

    Encodes the given string or list of strings. Returns a single value,
    array or array reference depending on the caller context and parameters.

    Returns undef on an empty/undefined/whitespace only string.

   compare
     $RETURN_CODE = $obj->compare($STRING1,$STRING2);

    The return code is an integer between 100 and 0 indicating the
    likelihood that the to results are the same. 100 means that the strings
    are completely identical. 99 means that the strings match after all
    non-latin characters have been transliterated. Values in between 98 and
    1 usually mean that the given strings match. 0 means that the used
    alogorithm couldn't match the two strings at all. "compare" is a
    shortcut to the "$obj->_do_compare($CODE1,$CODE2)" method.

  Class Methods
   available_algorithms
     my @available = Text::Phonetic->available_algorithms;

    Returns a list of all available/installed algorithms

SUBLCASSING
    You can easily subclass Text::Phonetic and add your own phonetic
    algorithm. All subclasses must use Text::Phonetic as their base class,
    reside in the Text::Phonetic namespace, and implement the following
    methods:

  _do_encode
     $RESULT = $obj->_do_encode($STRING);

    This method does the actual encoding. It should return either a string
    or an array reference.

  _do_compare
     $RETURN_STRING = $obj->_do_compare($RESULT1,$RESULT2);

    If your "_do_encode" method doesn't return a single scalar value you
    also might need to implement a comparison method. It takes two results
    as returned by "_do_encode" and returns an integer value between 98 and
    0 (see "compare").

  _predicates
    Third party modules can be marked as predicates by adding the
    "_predicates" method which should return al list of package names. All
    predicates will be loaded if installed. If missing an exception will be
    thrown.

  Object structure
    Text::Phonetic uses Moo to declare attributes.

  Helper class methods
   _compare_list
     Text::Phonetic::_compare_list($LIST1_REF,$LIST2_REF);

    Compares the two arrays and returns true if at least one element is
    equal (ignoring the position) in both lists.

  Example class
     package Text::Phonetic::MyAlgorithm;
     use Moo;
     extends qw(Text::Phonetic);
 
     has someattribute => (
        is  => 'rw',
     );
 
     sub _do_encode {
         my ($self,$string) = @_;
         # Do something
         return $phonetic_representation;
     }
 
     __PACKAGE__->meta->make_immutable;
     no Moo;
     1;

SEE ALSO
    DBIx::Class::PhoneticSearch (Build phonetic indices via DBIx::Class),
    Text::Phonetic::VideoGame (Phonetic encoding for video game titles)

SUPPORT
    Please report any bugs or feature requests to
    "text-phonetic@rt.cpan.org", or through the web interface at
    <http://rt.cpan.org/Public/Bug/Report.html?Queue=Text::Phonetic>. I will
    be notified, and then you'll automatically be notified of progress on
    your report as I make changes.

AUTHOR
        Maroš Kollár
        CPAN ID: MAROS
        maros [at] k-1.com
    
        http://www.k-1.com

COPYRIGHT
    Text::Phonetic is Copyright (c) 2006-2012 Maroš Kollár -
    <http://www.k-1.com>

LICENCE
    This library is free software, you can redistribute it and/or modify it
    under the same terms as Perl itself.

Todo  view on Meta::CPAN

TODO list for Perl module Text::Phonetic

- Phonix compare algorithm


inc/Module/Install.pm  view on Meta::CPAN

#line 1
package Module::Install;

# For any maintainers:
# The load order for Module::Install is a bit magic.
# It goes something like this...
#
# IF ( host has Module::Install installed, creating author mode ) {
#     1. Makefile.PL calls "use inc::Module::Install"
#     2. $INC{inc/Module/Install.pm} set to installed version of inc::Module::Install
#     3. The installed version of inc::Module::Install loads
#     4. inc::Module::Install calls "require Module::Install"
#     5. The ./inc/ version of Module::Install loads
# } ELSE {
#     1. Makefile.PL calls "use inc::Module::Install"
#     2. $INC{inc/Module/Install.pm} set to ./inc/ version of Module::Install
#     3. The ./inc/ version of Module::Install loads
# }

use 5.006;
use strict 'vars';
use Cwd        ();
use File::Find ();
use File::Path ();

use vars qw{$VERSION $MAIN};
BEGIN {
	# All Module::Install core packages now require synchronised versions.
	# This will be used to ensure we don't accidentally load old or
	# different versions of modules.
	# This is not enforced yet, but will be some time in the next few
	# releases once we can make sure it won't clash with custom
	# Module::Install extensions.
	$VERSION = '1.18';

	# Storage for the pseudo-singleton
	$MAIN    = undef;

	*inc::Module::Install::VERSION = *VERSION;
	@inc::Module::Install::ISA     = __PACKAGE__;

}

sub import {
	my $class = shift;
	my $self  = $class->new(@_);
	my $who   = $self->_caller;

	#-------------------------------------------------------------
	# all of the following checks should be included in import(),
	# to allow "eval 'require Module::Install; 1' to test
	# installation of Module::Install. (RT #51267)
	#-------------------------------------------------------------

	# Whether or not inc::Module::Install is actually loaded, the
	# $INC{inc/Module/Install.pm} is what will still get set as long as
	# the caller loaded module this in the documented manner.
	# If not set, the caller may NOT have loaded the bundled version, and thus
	# they may not have a MI version that works with the Makefile.PL. This would
	# result in false errors or unexpected behaviour. And we don't want that.
	my $file = join( '/', 'inc', split /::/, __PACKAGE__ ) . '.pm';
	unless ( $INC{$file} ) { die <<"END_DIE" }

Please invoke ${\__PACKAGE__} with:

	use inc::${\__PACKAGE__};

not:

	use ${\__PACKAGE__};

END_DIE

	# This reportedly fixes a rare Win32 UTC file time issue, but
	# as this is a non-cross-platform XS module not in the core,
	# we shouldn't really depend on it. See RT #24194 for detail.
	# (Also, this module only supports Perl 5.6 and above).
	eval "use Win32::UTCFileTime" if $^O eq 'MSWin32' && $] >= 5.006;

	# If the script that is loading Module::Install is from the future,
	# then make will detect this and cause it to re-run over and over
	# again. This is bad. Rather than taking action to touch it (which
	# is unreliable on some platforms and requires write permissions)
	# for now we should catch this and refuse to run.
	if ( -f $0 ) {
		my $s = (stat($0))[9];

		# If the modification time is only slightly in the future,
		# sleep briefly to remove the problem.
		my $a = $s - time;
		if ( $a > 0 and $a < 5 ) { sleep 5 }

		# Too far in the future, throw an error.
		my $t = time;
		if ( $s > $t ) { die <<"END_DIE" }

Your installer $0 has a modification time in the future ($s > $t).

This is known to create infinite loops in make.

Please correct this, then run $0 again.

END_DIE
	}


	# Build.PL was formerly supported, but no longer is due to excessive
	# difficulty in implementing every single feature twice.
	if ( $0 =~ /Build.PL$/i ) { die <<"END_DIE" }

Module::Install no longer supports Build.PL.

It was impossible to maintain duel backends, and has been deprecated.

Please remove all Build.PL files and only use the Makefile.PL installer.

END_DIE

	#-------------------------------------------------------------

	# To save some more typing in Module::Install installers, every...
	# use inc::Module::Install
	# ...also acts as an implicit use strict.
	$^H |= strict::bits(qw(refs subs vars));

	#-------------------------------------------------------------

	unless ( -f $self->{file} ) {
		foreach my $key (keys %INC) {
			delete $INC{$key} if $key =~ /Module\/Install/;
		}

		local $^W;
		require "$self->{path}/$self->{dispatch}.pm";
		File::Path::mkpath("$self->{prefix}/$self->{author}");
		$self->{admin} = "$self->{name}::$self->{dispatch}"->new( _top => $self );
		$self->{admin}->init;
		@_ = ($class, _self => $self);
		goto &{"$self->{name}::import"};
	}

	local $^W;
	*{"${who}::AUTOLOAD"} = $self->autoload;
	$self->preload;

	# Unregister loader and worker packages so subdirs can use them again
	delete $INC{'inc/Module/Install.pm'};
	delete $INC{'Module/Install.pm'};

	# Save to the singleton
	$MAIN = $self;

	return 1;
}

sub autoload {
	my $self = shift;
	my $who  = $self->_caller;
	my $cwd  = Cwd::getcwd();
	my $sym  = "${who}::AUTOLOAD";
	$sym->{$cwd} = sub {
		my $pwd = Cwd::getcwd();
		if ( my $code = $sym->{$pwd} ) {
			# Delegate back to parent dirs
			goto &$code unless $cwd eq $pwd;
		}
		unless ($$sym =~ s/([^:]+)$//) {
			# XXX: it looks like we can't retrieve the missing function
			# via $$sym (usually $main::AUTOLOAD) in this case.
			# I'm still wondering if we should slurp Makefile.PL to
			# get some context or not ...
			my ($package, $file, $line) = caller;
			die <<"EOT";
Unknown function is found at $file line $line.
Execution of $file aborted due to runtime errors.

If you're a contributor to a project, you may need to install
some Module::Install extensions from CPAN (or other repository).
If you're a user of a module, please contact the author.
EOT
		}
		my $method = $1;
		if ( uc($method) eq $method ) {
			# Do nothing
			return;
		} elsif ( $method =~ /^_/ and $self->can($method) ) {
			# Dispatch to the root M:I class
			return $self->$method(@_);
		}

		# Dispatch to the appropriate plugin
		unshift @_, ( $self, $1 );
		goto &{$self->can('call')};
	};
}

sub preload {
	my $self = shift;
	unless ( $self->{extensions} ) {
		$self->load_extensions(
			"$self->{prefix}/$self->{path}", $self
		);
	}

	my @exts = @{$self->{extensions}};
	unless ( @exts ) {
		@exts = $self->{admin}->load_all_extensions;
	}

	my %seen;
	foreach my $obj ( @exts ) {
		while (my ($method, $glob) = each %{ref($obj) . '::'}) {
			next unless $obj->can($method);
			next if $method =~ /^_/;
			next if $method eq uc($method);
			$seen{$method}++;
		}
	}

	my $who = $self->_caller;
	foreach my $name ( sort keys %seen ) {
		local $^W;
		*{"${who}::$name"} = sub {
			${"${who}::AUTOLOAD"} = "${who}::$name";
			goto &{"${who}::AUTOLOAD"};
		};
	}
}

sub new {
	my ($class, %args) = @_;

	delete $INC{'FindBin.pm'};
	{
		# to suppress the redefine warning
		local $SIG{__WARN__} = sub {};
		require FindBin;
	}

	# ignore the prefix on extension modules built from top level.
	my $base_path = Cwd::abs_path($FindBin::Bin);
	unless ( Cwd::abs_path(Cwd::getcwd()) eq $base_path ) {
		delete $args{prefix};
	}
	return $args{_self} if $args{_self};

	$base_path = VMS::Filespec::unixify($base_path) if $^O eq 'VMS';

	$args{dispatch} ||= 'Admin';
	$args{prefix}   ||= 'inc';
	$args{author}   ||= ($^O eq 'VMS' ? '_author' : '.author');
	$args{bundle}   ||= 'inc/BUNDLES';
	$args{base}     ||= $base_path;
	$class =~ s/^\Q$args{prefix}\E:://;
	$args{name}     ||= $class;
	$args{version}  ||= $class->VERSION;
	unless ( $args{path} ) {
		$args{path}  = $args{name};
		$args{path}  =~ s!::!/!g;
	}
	$args{file}     ||= "$args{base}/$args{prefix}/$args{path}.pm";
	$args{wrote}      = 0;

	bless( \%args, $class );
}

sub call {
	my ($self, $method) = @_;
	my $obj = $self->load($method) or return;
        splice(@_, 0, 2, $obj);
	goto &{$obj->can($method)};
}

sub load {
	my ($self, $method) = @_;

	$self->load_extensions(
		"$self->{prefix}/$self->{path}", $self
	) unless $self->{extensions};

	foreach my $obj (@{$self->{extensions}}) {
		return $obj if $obj->can($method);
	}

	my $admin = $self->{admin} or die <<"END_DIE";
The '$method' method does not exist in the '$self->{prefix}' path!
Please remove the '$self->{prefix}' directory and run $0 again to load it.
END_DIE

	my $obj = $admin->load($method, 1);
	push @{$self->{extensions}}, $obj;

	$obj;
}

sub load_extensions {
	my ($self, $path, $top) = @_;

	my $should_reload = 0;
	unless ( grep { ! ref $_ and lc $_ eq lc $self->{prefix} } @INC ) {
		unshift @INC, $self->{prefix};
		$should_reload = 1;
	}

	foreach my $rv ( $self->find_extensions($path) ) {
		my ($file, $pkg) = @{$rv};
		next if $self->{pathnames}{$pkg};

		local $@;
		my $new = eval { local $^W; require $file; $pkg->can('new') };
		unless ( $new ) {
			warn $@ if $@;
			next;
		}
		$self->{pathnames}{$pkg} =
			$should_reload ? delete $INC{$file} : $INC{$file};
		push @{$self->{extensions}}, &{$new}($pkg, _top => $top );
	}

	$self->{extensions} ||= [];
}

sub find_extensions {
	my ($self, $path) = @_;

	my @found;
	File::Find::find( {no_chdir => 1, wanted => sub {
		my $file = $File::Find::name;
		return unless $file =~ m!^\Q$path\E/(.+)\.pm\Z!is;
		my $subpath = $1;
		return if lc($subpath) eq lc($self->{dispatch});

		$file = "$self->{path}/$subpath.pm";
		my $pkg = "$self->{name}::$subpath";
		$pkg =~ s!/!::!g;

		# If we have a mixed-case package name, assume case has been preserved
		# correctly.  Otherwise, root through the file to locate the case-preserved
		# version of the package name.
		if ( $subpath eq lc($subpath) || $subpath eq uc($subpath) ) {
			my $content = Module::Install::_read($File::Find::name);
			my $in_pod  = 0;
			foreach ( split /\n/, $content ) {
				$in_pod = 1 if /^=\w/;
				$in_pod = 0 if /^=cut/;
				next if ($in_pod || /^=cut/);  # skip pod text
				next if /^\s*#/;               # and comments
				if ( m/^\s*package\s+($pkg)\s*;/i ) {
					$pkg = $1;
					last;
				}
			}
		}

		push @found, [ $file, $pkg ];
	}}, $path ) if -d $path;

	@found;
}





#####################################################################
# Common Utility Functions

sub _caller {
	my $depth = 0;
	my $call  = caller($depth);
	while ( $call eq __PACKAGE__ ) {
		$depth++;
		$call = caller($depth);
	}
	return $call;
}

sub _read {
	local *FH;
	open( FH, '<', $_[0] ) or die "open($_[0]): $!";
	binmode FH;
	my $string = do { local $/; <FH> };
	close FH or die "close($_[0]): $!";
	return $string;
}

sub _readperl {
	my $string = Module::Install::_read($_[0]);
	$string =~ s/(?:\015{1,2}\012|\015|\012)/\n/sg;
	$string =~ s/(\n)\n*__(?:DATA|END)__\b.*\z/$1/s;
	$string =~ s/\n\n=\w+.+?\n\n=cut\b.+?\n+/\n\n/sg;
	return $string;
}

sub _readpod {
	my $string = Module::Install::_read($_[0]);
	$string =~ s/(?:\015{1,2}\012|\015|\012)/\n/sg;
	return $string if $_[0] =~ /\.pod\z/;
	$string =~ s/(^|\n=cut\b.+?\n+)[^=\s].+?\n(\n=\w+|\z)/$1$2/sg;
	$string =~ s/\n*=pod\b[^\n]*\n+/\n\n/sg;
	$string =~ s/\n*=cut\b[^\n]*\n+/\n\n/sg;
	$string =~ s/^\n+//s;
	return $string;
}

sub _write {
	local *FH;
	open( FH, '>', $_[0] ) or die "open($_[0]): $!";
	binmode FH;
	foreach ( 1 .. $#_ ) {
		print FH $_[$_] or die "print($_[0]): $!";
	}
	close FH or die "close($_[0]): $!";
}

# _version is for processing module versions (eg, 1.03_05) not
# Perl versions (eg, 5.8.1).
sub _version {
	my $s = shift || 0;
	my $d =()= $s =~ /(\.)/g;
	if ( $d >= 2 ) {
		# Normalise multipart versions
		$s =~ s/(\.)(\d{1,3})/sprintf("$1%03d",$2)/eg;
	}
	$s =~ s/^(\d+)\.?//;
	my $l = $1 || 0;
	my @v = map {
		$_ . '0' x (3 - length $_)
	} $s =~ /(\d{1,3})\D?/g;
	$l = $l . '.' . join '', @v if @v;
	return $l + 0;
}

sub _cmp {
	_version($_[1]) <=> _version($_[2]);
}

# Cloned from Params::Util::_CLASS
sub _CLASS {
	(
		defined $_[0]
		and
		! ref $_[0]
		and
		$_[0] =~ m/^[^\W\d]\w*(?:::\w+)*\z/s
	) ? $_[0] : undef;
}

1;

# Copyright 2008 - 2012 Adam Kennedy.

inc/Module/Install/AuthorRequires.pm  view on Meta::CPAN

#line 1
use strict;
use warnings;

package Module::Install::AuthorRequires;

use base 'Module::Install::Base';

# cargo cult
BEGIN {
    our $VERSION = '0.02';
    our $ISCORE  = 1;
}

sub author_requires {
    my $self = shift;

    return $self->{values}->{author_requires}
        unless @_;

    my @added;
    while (@_) {
        my $mod = shift or last;
        my $version = shift || 0;
        push @added, [$mod => $version];
    }

    push @{ $self->{values}->{author_requires} }, @added;
    $self->admin->author_requires(@added);

    return map { @$_ } @added;
}

1;

__END__

#line 92

inc/Module/Install/Base.pm  view on Meta::CPAN

#line 1
package Module::Install::Base;

use strict 'vars';
use vars qw{$VERSION};
BEGIN {
	$VERSION = '1.18';
}

# Suspend handler for "redefined" warnings
BEGIN {
	my $w = $SIG{__WARN__};
	$SIG{__WARN__} = sub { $w };
}

#line 42

sub new {
	my $class = shift;
	unless ( defined &{"${class}::call"} ) {
		*{"${class}::call"} = sub { shift->_top->call(@_) };
	}
	unless ( defined &{"${class}::load"} ) {
		*{"${class}::load"} = sub { shift->_top->load(@_) };
	}
	bless { @_ }, $class;
}

#line 61

sub AUTOLOAD {
	local $@;
	my $func = eval { shift->_top->autoload } or return;
	goto &$func;
}

#line 75

sub _top {
	$_[0]->{_top};
}

#line 90

sub admin {
	$_[0]->_top->{admin}
	or
	Module::Install::Base::FakeAdmin->new;
}

#line 106

sub is_admin {
	! $_[0]->admin->isa('Module::Install::Base::FakeAdmin');
}

sub DESTROY {}

package Module::Install::Base::FakeAdmin;

use vars qw{$VERSION};
BEGIN {
	$VERSION = $Module::Install::Base::VERSION;
}

my $fake;

sub new {
	$fake ||= bless(\@_, $_[0]);
}

sub AUTOLOAD {}

sub DESTROY {}

# Restore warning handler
BEGIN {
	$SIG{__WARN__} = $SIG{__WARN__}->();
}

1;

#line 159

inc/Module/Install/Can.pm  view on Meta::CPAN

#line 1
package Module::Install::Can;

use strict;
use Config                ();
use ExtUtils::MakeMaker   ();
use Module::Install::Base ();

use vars qw{$VERSION @ISA $ISCORE};
BEGIN {
	$VERSION = '1.18';
	@ISA     = 'Module::Install::Base';
	$ISCORE  = 1;
}

# check if we can load some module
### Upgrade this to not have to load the module if possible
sub can_use {
	my ($self, $mod, $ver) = @_;
	$mod =~ s{::|\\}{/}g;
	$mod .= '.pm' unless $mod =~ /\.pm$/i;

	my $pkg = $mod;
	$pkg =~ s{/}{::}g;
	$pkg =~ s{\.pm$}{}i;

	local $@;
	eval { require $mod; $pkg->VERSION($ver || 0); 1 };
}

# Check if we can run some command
sub can_run {
	my ($self, $cmd) = @_;

	my $_cmd = $cmd;
	return $_cmd if (-x $_cmd or $_cmd = MM->maybe_command($_cmd));

	for my $dir ((split /$Config::Config{path_sep}/, $ENV{PATH}), '.') {
		next if $dir eq '';
		require File::Spec;
		my $abs = File::Spec->catfile($dir, $cmd);
		return $abs if (-x $abs or $abs = MM->maybe_command($abs));
	}

	return;
}

# Can our C compiler environment build XS files
sub can_xs {
	my $self = shift;

	# Ensure we have the CBuilder module
	$self->configure_requires( 'ExtUtils::CBuilder' => 0.27 );

	# Do we have the configure_requires checker?
	local $@;
	eval "require ExtUtils::CBuilder;";
	if ( $@ ) {
		# They don't obey configure_requires, so it is
		# someone old and delicate. Try to avoid hurting
		# them by falling back to an older simpler test.
		return $self->can_cc();
	}

	# Do we have a working C compiler
	my $builder = ExtUtils::CBuilder->new(
		quiet => 1,
	);
	unless ( $builder->have_compiler ) {
		# No working C compiler
		return 0;
	}

	# Write a C file representative of what XS becomes
	require File::Temp;
	my ( $FH, $tmpfile ) = File::Temp::tempfile(
		"compilexs-XXXXX",
		SUFFIX => '.c',
	);
	binmode $FH;
	print $FH <<'END_C';
#include "EXTERN.h"
#include "perl.h"
#include "XSUB.h"

int main(int argc, char **argv) {
    return 0;
}

int boot_sanexs() {
    return 1;
}

END_C
	close $FH;

	# Can the C compiler access the same headers XS does
	my @libs   = ();
	my $object = undef;
	eval {
		local $^W = 0;
		$object = $builder->compile(
			source => $tmpfile,
		);
		@libs = $builder->link(
			objects     => $object,
			module_name => 'sanexs',
		);
	};
	my $result = $@ ? 0 : 1;

	# Clean up all the build files
	foreach ( $tmpfile, $object, @libs ) {
		next unless defined $_;
		1 while unlink;
	}

	return $result;
}

# Can we locate a (the) C compiler
sub can_cc {
	my $self   = shift;

	if ($^O eq 'VMS') {
		require ExtUtils::CBuilder;
		my $builder = ExtUtils::CBuilder->new(
		quiet => 1,
		);
		return $builder->have_compiler;
	}

	my @chunks = split(/ /, $Config::Config{cc}) or return;

	# $Config{cc} may contain args; try to find out the program part
	while (@chunks) {
		return $self->can_run("@chunks") || (pop(@chunks), next);
	}

	return;
}

# Fix Cygwin bug on maybe_command();
if ( $^O eq 'cygwin' ) {
	require ExtUtils::MM_Cygwin;
	require ExtUtils::MM_Win32;
	if ( ! defined(&ExtUtils::MM_Cygwin::maybe_command) ) {
		*ExtUtils::MM_Cygwin::maybe_command = sub {
			my ($self, $file) = @_;
			if ($file =~ m{^/cygdrive/}i and ExtUtils::MM_Win32->can('maybe_command')) {
				ExtUtils::MM_Win32->maybe_command($file);
			} else {
				ExtUtils::MM_Unix->maybe_command($file);
			}
		}
	}
}

1;

__END__

#line 245

inc/Module/Install/Fetch.pm  view on Meta::CPAN

#line 1
package Module::Install::Fetch;

use strict;
use Module::Install::Base ();

use vars qw{$VERSION @ISA $ISCORE};
BEGIN {
	$VERSION = '1.18';
	@ISA     = 'Module::Install::Base';
	$ISCORE  = 1;
}

sub get_file {
    my ($self, %args) = @_;
    my ($scheme, $host, $path, $file) =
        $args{url} =~ m|^(\w+)://([^/]+)(.+)/(.+)| or return;

    if ( $scheme eq 'http' and ! eval { require LWP::Simple; 1 } ) {
        $args{url} = $args{ftp_url}
            or (warn("LWP support unavailable!\n"), return);
        ($scheme, $host, $path, $file) =
            $args{url} =~ m|^(\w+)://([^/]+)(.+)/(.+)| or return;
    }

    $|++;
    print "Fetching '$file' from $host... ";

    unless (eval { require Socket; Socket::inet_aton($host) }) {
        warn "'$host' resolve failed!\n";
        return;
    }

    return unless $scheme eq 'ftp' or $scheme eq 'http';

    require Cwd;
    my $dir = Cwd::getcwd();
    chdir $args{local_dir} or return if exists $args{local_dir};

    if (eval { require LWP::Simple; 1 }) {
        LWP::Simple::mirror($args{url}, $file);
    }
    elsif (eval { require Net::FTP; 1 }) { eval {
        # use Net::FTP to get past firewall
        my $ftp = Net::FTP->new($host, Passive => 1, Timeout => 600);
        $ftp->login("anonymous", 'anonymous@example.com');
        $ftp->cwd($path);
        $ftp->binary;
        $ftp->get($file) or (warn("$!\n"), return);
        $ftp->quit;
    } }
    elsif (my $ftp = $self->can_run('ftp')) { eval {
        # no Net::FTP, fallback to ftp.exe
        require FileHandle;
        my $fh = FileHandle->new;

        local $SIG{CHLD} = 'IGNORE';
        unless ($fh->open("|$ftp -n")) {
            warn "Couldn't open ftp: $!\n";
            chdir $dir; return;
        }

        my @dialog = split(/\n/, <<"END_FTP");
open $host
user anonymous anonymous\@example.com
cd $path
binary
get $file $file
quit
END_FTP
        foreach (@dialog) { $fh->print("$_\n") }
        $fh->close;
    } }
    else {
        warn "No working 'ftp' program available!\n";
        chdir $dir; return;
    }

    unless (-f $file) {
        warn "Fetching failed: $@\n";
        chdir $dir; return;
    }

    return if exists $args{size} and -s $file != $args{size};
    system($args{run}) if exists $args{run};
    unlink($file) if $args{remove};

    print(((!exists $args{check_for} or -e $args{check_for})
        ? "done!" : "failed! ($!)"), "\n");
    chdir $dir; return !$?;
}

1;

inc/Module/Install/Makefile.pm  view on Meta::CPAN

#line 1
package Module::Install::Makefile;

use strict 'vars';
use ExtUtils::MakeMaker   ();
use Module::Install::Base ();
use Fcntl qw/:flock :seek/;

use vars qw{$VERSION @ISA $ISCORE};
BEGIN {
	$VERSION = '1.18';
	@ISA     = 'Module::Install::Base';
	$ISCORE  = 1;
}

sub Makefile { $_[0] }

my %seen = ();

sub prompt {
	shift;

	# Infinite loop protection
	my @c = caller();
	if ( ++$seen{"$c[1]|$c[2]|$_[0]"} > 3 ) {
		die "Caught an potential prompt infinite loop ($c[1]|$c[2]|$_[0])";
	}

	# In automated testing or non-interactive session, always use defaults
	if ( ($ENV{AUTOMATED_TESTING} or -! -t STDIN) and ! $ENV{PERL_MM_USE_DEFAULT} ) {
		local $ENV{PERL_MM_USE_DEFAULT} = 1;
		goto &ExtUtils::MakeMaker::prompt;
	} else {
		goto &ExtUtils::MakeMaker::prompt;
	}
}

# Store a cleaned up version of the MakeMaker version,
# since we need to behave differently in a variety of
# ways based on the MM version.
my $makemaker = eval $ExtUtils::MakeMaker::VERSION;

# If we are passed a param, do a "newer than" comparison.
# Otherwise, just return the MakeMaker version.
sub makemaker {
	( @_ < 2 or $makemaker >= eval($_[1]) ) ? $makemaker : 0
}

# Ripped from ExtUtils::MakeMaker 6.56, and slightly modified
# as we only need to know here whether the attribute is an array
# or a hash or something else (which may or may not be appendable).
my %makemaker_argtype = (
 C                  => 'ARRAY',
 CONFIG             => 'ARRAY',
# CONFIGURE          => 'CODE', # ignore
 DIR                => 'ARRAY',
 DL_FUNCS           => 'HASH',
 DL_VARS            => 'ARRAY',
 EXCLUDE_EXT        => 'ARRAY',
 EXE_FILES          => 'ARRAY',
 FUNCLIST           => 'ARRAY',
 H                  => 'ARRAY',
 IMPORTS            => 'HASH',
 INCLUDE_EXT        => 'ARRAY',
 LIBS               => 'ARRAY', # ignore ''
 MAN1PODS           => 'HASH',
 MAN3PODS           => 'HASH',
 META_ADD           => 'HASH',
 META_MERGE         => 'HASH',
 PL_FILES           => 'HASH',
 PM                 => 'HASH',
 PMLIBDIRS          => 'ARRAY',
 PMLIBPARENTDIRS    => 'ARRAY',
 PREREQ_PM          => 'HASH',
 CONFIGURE_REQUIRES => 'HASH',
 SKIP               => 'ARRAY',
 TYPEMAPS           => 'ARRAY',
 XS                 => 'HASH',
# VERSION            => ['version',''],  # ignore
# _KEEP_AFTER_FLUSH  => '',

 clean      => 'HASH',
 depend     => 'HASH',
 dist       => 'HASH',
 dynamic_lib=> 'HASH',
 linkext    => 'HASH',
 macro      => 'HASH',
 postamble  => 'HASH',
 realclean  => 'HASH',
 test       => 'HASH',
 tool_autosplit => 'HASH',

 # special cases where you can use makemaker_append
 CCFLAGS   => 'APPENDABLE',
 DEFINE    => 'APPENDABLE',
 INC       => 'APPENDABLE',
 LDDLFLAGS => 'APPENDABLE',
 LDFROM    => 'APPENDABLE',
);

sub makemaker_args {
	my ($self, %new_args) = @_;
	my $args = ( $self->{makemaker_args} ||= {} );
	foreach my $key (keys %new_args) {
		if ($makemaker_argtype{$key}) {
			if ($makemaker_argtype{$key} eq 'ARRAY') {
				$args->{$key} = [] unless defined $args->{$key};
				unless (ref $args->{$key} eq 'ARRAY') {
					$args->{$key} = [$args->{$key}]
				}
				push @{$args->{$key}},
					ref $new_args{$key} eq 'ARRAY'
						? @{$new_args{$key}}
						: $new_args{$key};
			}
			elsif ($makemaker_argtype{$key} eq 'HASH') {
				$args->{$key} = {} unless defined $args->{$key};
				foreach my $skey (keys %{ $new_args{$key} }) {
					$args->{$key}{$skey} = $new_args{$key}{$skey};
				}
			}
			elsif ($makemaker_argtype{$key} eq 'APPENDABLE') {
				$self->makemaker_append($key => $new_args{$key});
			}
		}
		else {
			if (defined $args->{$key}) {
				warn qq{MakeMaker attribute "$key" is overriden; use "makemaker_append" to append values\n};
			}
			$args->{$key} = $new_args{$key};
		}
	}
	return $args;
}

# For mm args that take multiple space-separated args,
# append an argument to the current list.
sub makemaker_append {
	my $self = shift;
	my $name = shift;
	my $args = $self->makemaker_args;
	$args->{$name} = defined $args->{$name}
		? join( ' ', $args->{$name}, @_ )
		: join( ' ', @_ );
}

sub build_subdirs {
	my $self    = shift;
	my $subdirs = $self->makemaker_args->{DIR} ||= [];
	for my $subdir (@_) {
		push @$subdirs, $subdir;
	}
}

sub clean_files {
	my $self  = shift;
	my $clean = $self->makemaker_args->{clean} ||= {};
	  %$clean = (
		%$clean,
		FILES => join ' ', grep { length $_ } ($clean->{FILES} || (), @_),
	);
}

sub realclean_files {
	my $self      = shift;
	my $realclean = $self->makemaker_args->{realclean} ||= {};
	  %$realclean = (
		%$realclean,
		FILES => join ' ', grep { length $_ } ($realclean->{FILES} || (), @_),
	);
}

sub libs {
	my $self = shift;
	my $libs = ref $_[0] ? shift : [ shift ];
	$self->makemaker_args( LIBS => $libs );
}

sub inc {
	my $self = shift;
	$self->makemaker_args( INC => shift );
}

sub _wanted_t {
}

sub tests_recursive {
	my $self = shift;
	my $dir = shift || 't';
	unless ( -d $dir ) {
		die "tests_recursive dir '$dir' does not exist";
	}
	my %tests = map { $_ => 1 } split / /, ($self->tests || '');
	require File::Find;
	File::Find::find(
        sub { /\.t$/ and -f $_ and $tests{"$File::Find::dir/*.t"} = 1 },
        $dir
    );
	$self->tests( join ' ', sort keys %tests );
}

sub write {
	my $self = shift;
	die "&Makefile->write() takes no arguments\n" if @_;

	# Check the current Perl version
	my $perl_version = $self->perl_version;
	if ( $perl_version ) {
		eval "use $perl_version; 1"
			or die "ERROR: perl: Version $] is installed, "
			. "but we need version >= $perl_version";
	}

	# Make sure we have a new enough MakeMaker
	require ExtUtils::MakeMaker;

	if ( $perl_version and $self->_cmp($perl_version, '5.006') >= 0 ) {
		# This previous attempted to inherit the version of
		# ExtUtils::MakeMaker in use by the module author, but this
		# was found to be untenable as some authors build releases
		# using future dev versions of EU:MM that nobody else has.
		# Instead, #toolchain suggests we use 6.59 which is the most
		# stable version on CPAN at time of writing and is, to quote
		# ribasushi, "not terminally fucked, > and tested enough".
		# TODO: We will now need to maintain this over time to push
		# the version up as new versions are released.
		$self->build_requires(     'ExtUtils::MakeMaker' => 6.59 );
		$self->configure_requires( 'ExtUtils::MakeMaker' => 6.59 );
	} else {
		# Allow legacy-compatibility with 5.005 by depending on the
		# most recent EU:MM that supported 5.005.
		$self->build_requires(     'ExtUtils::MakeMaker' => 6.36 );
		$self->configure_requires( 'ExtUtils::MakeMaker' => 6.36 );
	}

	# Generate the MakeMaker params
	my $args = $self->makemaker_args;
	$args->{DISTNAME} = $self->name;
	$args->{NAME}     = $self->module_name || $self->name;
	$args->{NAME}     =~ s/-/::/g;
	$args->{VERSION}  = $self->version or die <<'EOT';
ERROR: Can't determine distribution version. Please specify it
explicitly via 'version' in Makefile.PL, or set a valid $VERSION
in a module, and provide its file path via 'version_from' (or
'all_from' if you prefer) in Makefile.PL.
EOT

	if ( $self->tests ) {
		my @tests = split ' ', $self->tests;
		my %seen;
		$args->{test} = {
			TESTS => (join ' ', grep {!$seen{$_}++} @tests),
		};
    } elsif ( $Module::Install::ExtraTests::use_extratests ) {
        # Module::Install::ExtraTests doesn't set $self->tests and does its own tests via harness.
        # So, just ignore our xt tests here.
	} elsif ( -d 'xt' and ($Module::Install::AUTHOR or $ENV{RELEASE_TESTING}) ) {
		$args->{test} = {
			TESTS => join( ' ', map { "$_/*.t" } grep { -d $_ } qw{ t xt } ),
		};
	}
	if ( $] >= 5.005 ) {
		$args->{ABSTRACT} = $self->abstract;
		$args->{AUTHOR}   = join ', ', @{$self->author || []};
	}
	if ( $self->makemaker(6.10) ) {
		$args->{NO_META}   = 1;
		#$args->{NO_MYMETA} = 1;
	}
	if ( $self->makemaker(6.17) and $self->sign ) {
		$args->{SIGN} = 1;
	}
	unless ( $self->is_admin ) {
		delete $args->{SIGN};
	}
	if ( $self->makemaker(6.31) and $self->license ) {
		$args->{LICENSE} = $self->license;
	}

	my $prereq = ($args->{PREREQ_PM} ||= {});
	%$prereq = ( %$prereq,
		map { @$_ } # flatten [module => version]
		map { @$_ }
		grep $_,
		($self->requires)
	);

	# Remove any reference to perl, PREREQ_PM doesn't support it
	delete $args->{PREREQ_PM}->{perl};

	# Merge both kinds of requires into BUILD_REQUIRES
	my $build_prereq = ($args->{BUILD_REQUIRES} ||= {});
	%$build_prereq = ( %$build_prereq,
		map { @$_ } # flatten [module => version]
		map { @$_ }
		grep $_,
		($self->configure_requires, $self->build_requires)
	);

	# Remove any reference to perl, BUILD_REQUIRES doesn't support it
	delete $args->{BUILD_REQUIRES}->{perl};

	# Delete bundled dists from prereq_pm, add it to Makefile DIR
	my $subdirs = ($args->{DIR} || []);
	if ($self->bundles) {
		my %processed;
		foreach my $bundle (@{ $self->bundles }) {
			my ($mod_name, $dist_dir) = @$bundle;
			delete $prereq->{$mod_name};
			$dist_dir = File::Basename::basename($dist_dir); # dir for building this module
			if (not exists $processed{$dist_dir}) {
				if (-d $dist_dir) {
					# List as sub-directory to be processed by make
					push @$subdirs, $dist_dir;
				}
				# Else do nothing: the module is already present on the system
				$processed{$dist_dir} = undef;
			}
		}
	}

	unless ( $self->makemaker('6.55_03') ) {
		%$prereq = (%$prereq,%$build_prereq);
		delete $args->{BUILD_REQUIRES};
	}

	if ( my $perl_version = $self->perl_version ) {
		eval "use $perl_version; 1"
			or die "ERROR: perl: Version $] is installed, "
			. "but we need version >= $perl_version";

		if ( $self->makemaker(6.48) ) {
			$args->{MIN_PERL_VERSION} = $perl_version;
		}
	}

	if ($self->installdirs) {
		warn qq{old INSTALLDIRS (probably set by makemaker_args) is overriden by installdirs\n} if $args->{INSTALLDIRS};
		$args->{INSTALLDIRS} = $self->installdirs;
	}

	my %args = map {
		( $_ => $args->{$_} ) } grep {defined($args->{$_} )
	} keys %$args;

	my $user_preop = delete $args{dist}->{PREOP};
	if ( my $preop = $self->admin->preop($user_preop) ) {
		foreach my $key ( keys %$preop ) {
			$args{dist}->{$key} = $preop->{$key};
		}
	}

	my $mm = ExtUtils::MakeMaker::WriteMakefile(%args);
	$self->fix_up_makefile($mm->{FIRST_MAKEFILE} || 'Makefile');
}

sub fix_up_makefile {
	my $self          = shift;
	my $makefile_name = shift;
	my $top_class     = ref($self->_top) || '';
	my $top_version   = $self->_top->VERSION || '';

	my $preamble = $self->preamble
		? "# Preamble by $top_class $top_version\n"
			. $self->preamble
		: '';
	my $postamble = "# Postamble by $top_class $top_version\n"
		. ($self->postamble || '');

	local *MAKEFILE;
	open MAKEFILE, "+< $makefile_name" or die "fix_up_makefile: Couldn't open $makefile_name: $!";
	eval { flock MAKEFILE, LOCK_EX };
	my $makefile = do { local $/; <MAKEFILE> };

	$makefile =~ s/\b(test_harness\(\$\(TEST_VERBOSE\), )/$1'inc', /;
	$makefile =~ s/( -I\$\(INST_ARCHLIB\))/ -Iinc$1/g;
	$makefile =~ s/( "-I\$\(INST_LIB\)")/ "-Iinc"$1/g;
	$makefile =~ s/^(FULLPERL = .*)/$1 "-Iinc"/m;
	$makefile =~ s/^(PERL = .*)/$1 "-Iinc"/m;

	# Module::Install will never be used to build the Core Perl
	# Sometimes PERL_LIB and PERL_ARCHLIB get written anyway, which breaks
	# PREFIX/PERL5LIB, and thus, install_share. Blank them if they exist
	$makefile =~ s/^PERL_LIB = .+/PERL_LIB =/m;
	#$makefile =~ s/^PERL_ARCHLIB = .+/PERL_ARCHLIB =/m;

	# Perl 5.005 mentions PERL_LIB explicitly, so we have to remove that as well.
	$makefile =~ s/(\"?)-I\$\(PERL_LIB\)\1//g;

	# XXX - This is currently unused; not sure if it breaks other MM-users
	# $makefile =~ s/^pm_to_blib\s+:\s+/pm_to_blib :: /mg;

	seek MAKEFILE, 0, SEEK_SET;
	truncate MAKEFILE, 0;
	print MAKEFILE  "$preamble$makefile$postamble" or die $!;
	close MAKEFILE  or die $!;

	1;
}

sub preamble {
	my ($self, $text) = @_;
	$self->{preamble} = $text . $self->{preamble} if defined $text;
	$self->{preamble};
}

sub postamble {
	my ($self, $text) = @_;
	$self->{postamble} ||= $self->admin->postamble;
	$self->{postamble} .= $text if defined $text;
	$self->{postamble}
}

1;

__END__

#line 544

inc/Module/Install/Metadata.pm  view on Meta::CPAN

#line 1
package Module::Install::Metadata;

use strict 'vars';
use Module::Install::Base ();

use vars qw{$VERSION @ISA $ISCORE};
BEGIN {
	$VERSION = '1.18';
	@ISA     = 'Module::Install::Base';
	$ISCORE  = 1;
}

my @boolean_keys = qw{
	sign
};

my @scalar_keys = qw{
	name
	module_name
	abstract
	version
	distribution_type
	tests
	installdirs
};

my @tuple_keys = qw{
	configure_requires
	build_requires
	requires
	recommends
	bundles
	resources
};

my @resource_keys = qw{
	homepage
	bugtracker
	repository
};

my @array_keys = qw{
	keywords
	author
};

*authors = \&author;

sub Meta              { shift          }
sub Meta_BooleanKeys  { @boolean_keys  }
sub Meta_ScalarKeys   { @scalar_keys   }
sub Meta_TupleKeys    { @tuple_keys    }
sub Meta_ResourceKeys { @resource_keys }
sub Meta_ArrayKeys    { @array_keys    }

foreach my $key ( @boolean_keys ) {
	*$key = sub {
		my $self = shift;
		if ( defined wantarray and not @_ ) {
			return $self->{values}->{$key};
		}
		$self->{values}->{$key} = ( @_ ? $_[0] : 1 );
		return $self;
	};
}

foreach my $key ( @scalar_keys ) {
	*$key = sub {
		my $self = shift;
		return $self->{values}->{$key} if defined wantarray and !@_;
		$self->{values}->{$key} = shift;
		return $self;
	};
}

foreach my $key ( @array_keys ) {
	*$key = sub {
		my $self = shift;
		return $self->{values}->{$key} if defined wantarray and !@_;
		$self->{values}->{$key} ||= [];
		push @{$self->{values}->{$key}}, @_;
		return $self;
	};
}

foreach my $key ( @resource_keys ) {
	*$key = sub {
		my $self = shift;
		unless ( @_ ) {
			return () unless $self->{values}->{resources};
			return map  { $_->[1] }
			       grep { $_->[0] eq $key }
			       @{ $self->{values}->{resources} };
		}
		return $self->{values}->{resources}->{$key} unless @_;
		my $uri = shift or die(
			"Did not provide a value to $key()"
		);
		$self->resources( $key => $uri );
		return 1;
	};
}

foreach my $key ( grep { $_ ne "resources" } @tuple_keys) {
	*$key = sub {
		my $self = shift;
		return $self->{values}->{$key} unless @_;
		my @added;
		while ( @_ ) {
			my $module  = shift or last;
			my $version = shift || 0;
			push @added, [ $module, $version ];
		}
		push @{ $self->{values}->{$key} }, @added;
		return map {@$_} @added;
	};
}

# Resource handling
my %lc_resource = map { $_ => 1 } qw{
	homepage
	license
	bugtracker
	repository
};

sub resources {
	my $self = shift;
	while ( @_ ) {
		my $name  = shift or last;
		my $value = shift or next;
		if ( $name eq lc $name and ! $lc_resource{$name} ) {
			die("Unsupported reserved lowercase resource '$name'");
		}
		$self->{values}->{resources} ||= [];
		push @{ $self->{values}->{resources} }, [ $name, $value ];
	}
	$self->{values}->{resources};
}

# Aliases for build_requires that will have alternative
# meanings in some future version of META.yml.
sub test_requires     { shift->build_requires(@_) }
sub install_requires  { shift->build_requires(@_) }

# Aliases for installdirs options
sub install_as_core   { $_[0]->installdirs('perl')   }
sub install_as_cpan   { $_[0]->installdirs('site')   }
sub install_as_site   { $_[0]->installdirs('site')   }
sub install_as_vendor { $_[0]->installdirs('vendor') }

sub dynamic_config {
	my $self  = shift;
	my $value = @_ ? shift : 1;
	if ( $self->{values}->{dynamic_config} ) {
		# Once dynamic we never change to static, for safety
		return 0;
	}
	$self->{values}->{dynamic_config} = $value ? 1 : 0;
	return 1;
}

# Convenience command
sub static_config {
	shift->dynamic_config(0);
}

sub perl_version {
	my $self = shift;
	return $self->{values}->{perl_version} unless @_;
	my $version = shift or die(
		"Did not provide a value to perl_version()"
	);

	# Normalize the version
	$version = $self->_perl_version($version);

	# We don't support the really old versions
	unless ( $version >= 5.005 ) {
		die "Module::Install only supports 5.005 or newer (use ExtUtils::MakeMaker)\n";
	}

	$self->{values}->{perl_version} = $version;
}

sub all_from {
	my ( $self, $file ) = @_;

	unless ( defined($file) ) {
		my $name = $self->name or die(
			"all_from called with no args without setting name() first"
		);
		$file = join('/', 'lib', split(/-/, $name)) . '.pm';
		$file =~ s{.*/}{} unless -e $file;
		unless ( -e $file ) {
			die("all_from cannot find $file from $name");
		}
	}
	unless ( -f $file ) {
		die("The path '$file' does not exist, or is not a file");
	}

	$self->{values}{all_from} = $file;

	# Some methods pull from POD instead of code.
	# If there is a matching .pod, use that instead
	my $pod = $file;
	$pod =~ s/\.pm$/.pod/i;
	$pod = $file unless -e $pod;

	# Pull the different values
	$self->name_from($file)         unless $self->name;
	$self->version_from($file)      unless $self->version;
	$self->perl_version_from($file) unless $self->perl_version;
	$self->author_from($pod)        unless @{$self->author || []};
	$self->license_from($pod)       unless $self->license;
	$self->abstract_from($pod)      unless $self->abstract;

	return 1;
}

sub provides {
	my $self     = shift;
	my $provides = ( $self->{values}->{provides} ||= {} );
	%$provides = (%$provides, @_) if @_;
	return $provides;
}

sub auto_provides {
	my $self = shift;
	return $self unless $self->is_admin;
	unless (-e 'MANIFEST') {
		warn "Cannot deduce auto_provides without a MANIFEST, skipping\n";
		return $self;
	}
	# Avoid spurious warnings as we are not checking manifest here.
	local $SIG{__WARN__} = sub {1};
	require ExtUtils::Manifest;
	local *ExtUtils::Manifest::manicheck = sub { return };

	require Module::Build;
	my $build = Module::Build->new(
		dist_name    => $self->name,
		dist_version => $self->version,
		license      => $self->license,
	);
	$self->provides( %{ $build->find_dist_packages || {} } );
}

sub feature {
	my $self     = shift;
	my $name     = shift;
	my $features = ( $self->{values}->{features} ||= [] );
	my $mods;

	if ( @_ == 1 and ref( $_[0] ) ) {
		# The user used ->feature like ->features by passing in the second
		# argument as a reference.  Accomodate for that.
		$mods = $_[0];
	} else {
		$mods = \@_;
	}

	my $count = 0;
	push @$features, (
		$name => [
			map {
				ref($_) ? ( ref($_) eq 'HASH' ) ? %$_ : @$_ : $_
			} @$mods
		]
	);

	return @$features;
}

sub features {
	my $self = shift;
	while ( my ( $name, $mods ) = splice( @_, 0, 2 ) ) {
		$self->feature( $name, @$mods );
	}
	return $self->{values}->{features}
		? @{ $self->{values}->{features} }
		: ();
}

sub no_index {
	my $self = shift;
	my $type = shift;
	push @{ $self->{values}->{no_index}->{$type} }, @_ if $type;
	return $self->{values}->{no_index};
}

sub read {
	my $self = shift;
	$self->include_deps( 'YAML::Tiny', 0 );

	require YAML::Tiny;
	my $data = YAML::Tiny::LoadFile('META.yml');

	# Call methods explicitly in case user has already set some values.
	while ( my ( $key, $value ) = each %$data ) {
		next unless $self->can($key);
		if ( ref $value eq 'HASH' ) {
			while ( my ( $module, $version ) = each %$value ) {
				$self->can($key)->($self, $module => $version );
			}
		} else {
			$self->can($key)->($self, $value);
		}
	}
	return $self;
}

sub write {
	my $self = shift;
	return $self unless $self->is_admin;
	$self->admin->write_meta;
	return $self;
}

sub version_from {
	require ExtUtils::MM_Unix;
	my ( $self, $file ) = @_;
	$self->version( ExtUtils::MM_Unix->parse_version($file) );

	# for version integrity check
	$self->makemaker_args( VERSION_FROM => $file );
}

sub abstract_from {
	require ExtUtils::MM_Unix;
	my ( $self, $file ) = @_;
	$self->abstract(
		bless(
			{ DISTNAME => $self->name },
			'ExtUtils::MM_Unix'
		)->parse_abstract($file)
	);
}

# Add both distribution and module name
sub name_from {
	my ($self, $file) = @_;
	if (
		Module::Install::_read($file) =~ m/
		^ \s*
		package \s*
		([\w:]+)
		[\s|;]*
		/ixms
	) {
		my ($name, $module_name) = ($1, $1);
		$name =~ s{::}{-}g;
		$self->name($name);
		unless ( $self->module_name ) {
			$self->module_name($module_name);
		}
	} else {
		die("Cannot determine name from $file\n");
	}
}

sub _extract_perl_version {
	if (
		$_[0] =~ m/
		^\s*
		(?:use|require) \s*
		v?
		([\d_\.]+)
		\s* ;
		/ixms
	) {
		my $perl_version = $1;
		$perl_version =~ s{_}{}g;
		return $perl_version;
	} else {
		return;
	}
}

sub perl_version_from {
	my $self = shift;
	my $perl_version=_extract_perl_version(Module::Install::_read($_[0]));
	if ($perl_version) {
		$self->perl_version($perl_version);
	} else {
		warn "Cannot determine perl version info from $_[0]\n";
		return;
	}
}

sub author_from {
	my $self    = shift;
	my $content = Module::Install::_read($_[0]);
	if ($content =~ m/
		=head \d \s+ (?:authors?)\b \s*
		([^\n]*)
		|
		=head \d \s+ (?:licen[cs]e|licensing|copyright|legal)\b \s*
		.*? copyright .*? \d\d\d[\d.]+ \s* (?:\bby\b)? \s*
		([^\n]*)
	/ixms) {
		my $author = $1 || $2;

		# XXX: ugly but should work anyway...
		if (eval "require Pod::Escapes; 1") {
			# Pod::Escapes has a mapping table.
			# It's in core of perl >= 5.9.3, and should be installed
			# as one of the Pod::Simple's prereqs, which is a prereq
			# of Pod::Text 3.x (see also below).
			$author =~ s{ E<( (\d+) | ([A-Za-z]+) )> }
			{
				defined $2
				? chr($2)
				: defined $Pod::Escapes::Name2character_number{$1}
				? chr($Pod::Escapes::Name2character_number{$1})
				: do {
					warn "Unknown escape: E<$1>";
					"E<$1>";
				};
			}gex;
		}
		elsif (eval "require Pod::Text; 1" && $Pod::Text::VERSION < 3) {
			# Pod::Text < 3.0 has yet another mapping table,
			# though the table name of 2.x and 1.x are different.
			# (1.x is in core of Perl < 5.6, 2.x is in core of
			# Perl < 5.9.3)
			my $mapping = ($Pod::Text::VERSION < 2)
				? \%Pod::Text::HTML_Escapes
				: \%Pod::Text::ESCAPES;
			$author =~ s{ E<( (\d+) | ([A-Za-z]+) )> }
			{
				defined $2
				? chr($2)
				: defined $mapping->{$1}
				? $mapping->{$1}
				: do {
					warn "Unknown escape: E<$1>";
					"E<$1>";
				};
			}gex;
		}
		else {
			$author =~ s{E<lt>}{<}g;
			$author =~ s{E<gt>}{>}g;
		}
		$self->author($author);
	} else {
		warn "Cannot determine author info from $_[0]\n";
	}
}

#Stolen from M::B
my %license_urls = (
    perl         => 'http://dev.perl.org/licenses/',
    apache       => 'http://apache.org/licenses/LICENSE-2.0',
    apache_1_1   => 'http://apache.org/licenses/LICENSE-1.1',
    artistic     => 'http://opensource.org/licenses/artistic-license.php',
    artistic_2   => 'http://opensource.org/licenses/artistic-license-2.0.php',
    lgpl         => 'http://opensource.org/licenses/lgpl-license.php',
    lgpl2        => 'http://opensource.org/licenses/lgpl-2.1.php',
    lgpl3        => 'http://opensource.org/licenses/lgpl-3.0.html',
    bsd          => 'http://opensource.org/licenses/bsd-license.php',
    gpl          => 'http://opensource.org/licenses/gpl-license.php',
    gpl2         => 'http://opensource.org/licenses/gpl-2.0.php',
    gpl3         => 'http://opensource.org/licenses/gpl-3.0.html',
    mit          => 'http://opensource.org/licenses/mit-license.php',
    mozilla      => 'http://opensource.org/licenses/mozilla1.1.php',
    open_source  => undef,
    unrestricted => undef,
    restrictive  => undef,
    unknown      => undef,
);

sub license {
	my $self = shift;
	return $self->{values}->{license} unless @_;
	my $license = shift or die(
		'Did not provide a value to license()'
	);
	$license = __extract_license($license) || lc $license;
	$self->{values}->{license} = $license;

	# Automatically fill in license URLs
	if ( $license_urls{$license} ) {
		$self->resources( license => $license_urls{$license} );
	}

	return 1;
}

sub _extract_license {
	my $pod = shift;
	my $matched;
	return __extract_license(
		($matched) = $pod =~ m/
			(=head \d \s+ L(?i:ICEN[CS]E|ICENSING)\b.*?)
			(=head \d.*|=cut.*|)\z
		/xms
	) || __extract_license(
		($matched) = $pod =~ m/
			(=head \d \s+ (?:C(?i:OPYRIGHTS?)|L(?i:EGAL))\b.*?)
			(=head \d.*|=cut.*|)\z
		/xms
	);
}

sub __extract_license {
	my $license_text = shift or return;
	my @phrases      = (
		'(?:under )?the same (?:terms|license) as (?:perl|the perl (?:\d )?programming language)' => 'perl', 1,
		'(?:under )?the terms of (?:perl|the perl programming language) itself' => 'perl', 1,
		'Artistic and GPL'                   => 'perl',         1,
		'GNU general public license'         => 'gpl',          1,
		'GNU public license'                 => 'gpl',          1,
		'GNU lesser general public license'  => 'lgpl',         1,
		'GNU lesser public license'          => 'lgpl',         1,
		'GNU library general public license' => 'lgpl',         1,
		'GNU library public license'         => 'lgpl',         1,
		'GNU Free Documentation license'     => 'unrestricted', 1,
		'GNU Affero General Public License'  => 'open_source',  1,
		'(?:Free)?BSD license'               => 'bsd',          1,
		'Artistic license 2\.0'              => 'artistic_2',   1,
		'Artistic license'                   => 'artistic',     1,
		'Apache (?:Software )?license'       => 'apache',       1,
		'GPL'                                => 'gpl',          1,
		'LGPL'                               => 'lgpl',         1,
		'BSD'                                => 'bsd',          1,
		'Artistic'                           => 'artistic',     1,
		'MIT'                                => 'mit',          1,
		'Mozilla Public License'             => 'mozilla',      1,
		'Q Public License'                   => 'open_source',  1,
		'OpenSSL License'                    => 'unrestricted', 1,
		'SSLeay License'                     => 'unrestricted', 1,
		'zlib License'                       => 'open_source',  1,
		'proprietary'                        => 'proprietary',  0,
	);
	while ( my ($pattern, $license, $osi) = splice(@phrases, 0, 3) ) {
		$pattern =~ s#\s+#\\s+#gs;
		if ( $license_text =~ /\b$pattern\b/i ) {
			return $license;
		}
	}
	return '';
}

sub license_from {
	my $self = shift;
	if (my $license=_extract_license(Module::Install::_read($_[0]))) {
		$self->license($license);
	} else {
		warn "Cannot determine license info from $_[0]\n";
		return 'unknown';
	}
}

sub _extract_bugtracker {
	my @links   = $_[0] =~ m#L<(
	 https?\Q://rt.cpan.org/\E[^>]+|
	 https?\Q://github.com/\E[\w_]+/[\w_]+/issues|
	 https?\Q://code.google.com/p/\E[\w_\-]+/issues/list
	 )>#gx;
	my %links;
	@links{@links}=();
	@links=keys %links;
	return @links;
}

sub bugtracker_from {
	my $self    = shift;
	my $content = Module::Install::_read($_[0]);
	my @links   = _extract_bugtracker($content);
	unless ( @links ) {
		warn "Cannot determine bugtracker info from $_[0]\n";
		return 0;
	}
	if ( @links > 1 ) {
		warn "Found more than one bugtracker link in $_[0]\n";
		return 0;
	}

	# Set the bugtracker
	bugtracker( $links[0] );
	return 1;
}

sub requires_from {
	my $self     = shift;
	my $content  = Module::Install::_readperl($_[0]);
	my @requires = $content =~ m/^use\s+([^\W\d]\w*(?:::\w+)*)\s+(v?[\d\.]+)/mg;
	while ( @requires ) {
		my $module  = shift @requires;
		my $version = shift @requires;
		$self->requires( $module => $version );
	}
}

sub test_requires_from {
	my $self     = shift;
	my $content  = Module::Install::_readperl($_[0]);
	my @requires = $content =~ m/^use\s+([^\W\d]\w*(?:::\w+)*)\s+([\d\.]+)/mg;
	while ( @requires ) {
		my $module  = shift @requires;
		my $version = shift @requires;
		$self->test_requires( $module => $version );
	}
}

# Convert triple-part versions (eg, 5.6.1 or 5.8.9) to
# numbers (eg, 5.006001 or 5.008009).
# Also, convert double-part versions (eg, 5.8)
sub _perl_version {
	my $v = $_[-1];
	$v =~ s/^([1-9])\.([1-9]\d?\d?)$/sprintf("%d.%03d",$1,$2)/e;
	$v =~ s/^([1-9])\.([1-9]\d?\d?)\.(0|[1-9]\d?\d?)$/sprintf("%d.%03d%03d",$1,$2,$3 || 0)/e;
	$v =~ s/(\.\d\d\d)000$/$1/;
	$v =~ s/_.+$//;
	if ( ref($v) ) {
		# Numify
		$v = $v + 0;
	}
	return $v;
}

sub add_metadata {
    my $self = shift;
    my %hash = @_;
    for my $key (keys %hash) {
        warn "add_metadata: $key is not prefixed with 'x_'.\n" .
             "Use appopriate function to add non-private metadata.\n" unless $key =~ /^x_/;
        $self->{values}->{$key} = $hash{$key};
    }
}


######################################################################
# MYMETA Support

sub WriteMyMeta {
	die "WriteMyMeta has been deprecated";
}

sub write_mymeta_yaml {
	my $self = shift;

	# We need YAML::Tiny to write the MYMETA.yml file
	unless ( eval { require YAML::Tiny; 1; } ) {
		return 1;
	}

	# Generate the data
	my $meta = $self->_write_mymeta_data or return 1;

	# Save as the MYMETA.yml file
	print "Writing MYMETA.yml\n";
	YAML::Tiny::DumpFile('MYMETA.yml', $meta);
}

sub write_mymeta_json {
	my $self = shift;

	# We need JSON to write the MYMETA.json file
	unless ( eval { require JSON; 1; } ) {
		return 1;
	}

	# Generate the data
	my $meta = $self->_write_mymeta_data or return 1;

	# Save as the MYMETA.yml file
	print "Writing MYMETA.json\n";
	Module::Install::_write(
		'MYMETA.json',
		JSON->new->pretty(1)->canonical->encode($meta),
	);
}

sub _write_mymeta_data {
	my $self = shift;

	# If there's no existing META.yml there is nothing we can do
	return undef unless -f 'META.yml';

	# We need Parse::CPAN::Meta to load the file
	unless ( eval { require Parse::CPAN::Meta; 1; } ) {
		return undef;
	}

	# Merge the perl version into the dependencies
	my $val  = $self->Meta->{values};
	my $perl = delete $val->{perl_version};
	if ( $perl ) {
		$val->{requires} ||= [];
		my $requires = $val->{requires};

		# Canonize to three-dot version after Perl 5.6
		if ( $perl >= 5.006 ) {
			$perl =~ s{^(\d+)\.(\d\d\d)(\d*)}{join('.', $1, int($2||0), int($3||0))}e
		}
		unshift @$requires, [ perl => $perl ];
	}

	# Load the advisory META.yml file
	my @yaml = Parse::CPAN::Meta::LoadFile('META.yml');
	my $meta = $yaml[0];

	# Overwrite the non-configure dependency hashes
	delete $meta->{requires};
	delete $meta->{build_requires};
	delete $meta->{recommends};
	if ( exists $val->{requires} ) {
		$meta->{requires} = { map { @$_ } @{ $val->{requires} } };
	}
	if ( exists $val->{build_requires} ) {
		$meta->{build_requires} = { map { @$_ } @{ $val->{build_requires} } };
	}

	return $meta;
}

1;

inc/Module/Install/ReadmeFromPod.pm  view on Meta::CPAN

#line 1
package Module::Install::ReadmeFromPod;

use 5.006;
use strict;
use warnings;
use base qw(Module::Install::Base);
use vars qw($VERSION);

$VERSION = '0.26';

{

    # these aren't defined until after _require_admin is run, so
    # define them so prototypes are available during compilation.
    sub io;
    sub capture(&;@);

#line 28

    my $done = 0;

    sub _require_admin {

	# do this once to avoid redefinition warnings from IO::All
	return if $done;

	require IO::All;
	IO::All->import( '-binary' );

	require Capture::Tiny;
	Capture::Tiny->import ( 'capture' );

	return;
    }

}

sub readme_from {
  my $self = shift;
  return unless $self->is_admin;

  _require_admin;

  # Input file
  my $in_file  = shift || $self->_all_from
    or die "Can't determine file to make readme_from";

  # Get optional arguments
  my ($clean, $format, $out_file, $options);
  my $args = shift;
  if ( ref $args ) {
    # Arguments are in a hashref
    if ( ref($args) ne 'HASH' ) {
      die "Expected a hashref but got a ".ref($args)."\n";
    } else {
      $clean    = $args->{'clean'};
      $format   = $args->{'format'};
      $out_file = $args->{'output_file'};
      $options  = $args->{'options'};
    }
  } else {
    # Arguments are in a list
    $clean    = $args;
    $format   = shift;
    $out_file = shift;
    $options  = \@_;
  }

  # Default values;
  $clean  ||= 0;
  $format ||= 'txt';

  # Generate README
  print "readme_from $in_file to $format\n";
  if ($format =~ m/te?xt/) {
    $out_file = $self->_readme_txt($in_file, $out_file, $options);
  } elsif ($format =~ m/html?/) {
    $out_file = $self->_readme_htm($in_file, $out_file, $options);
  } elsif ($format eq 'man') {
    $out_file = $self->_readme_man($in_file, $out_file, $options);
  } elsif ($format eq 'md') {
    $out_file = $self->_readme_md($in_file, $out_file, $options);
  } elsif ($format eq 'pdf') {
    $out_file = $self->_readme_pdf($in_file, $out_file, $options);
  }

  if ($clean) {
    $self->clean_files($out_file);
  }

  return 1;
}


sub _readme_txt {
  my ($self, $in_file, $out_file, $options) = @_;
  $out_file ||= 'README';
  require Pod::Text;
  my $parser = Pod::Text->new( @$options );
  my $io = io->file($out_file)->open(">");
  my $out_fh = $io->io_handle;
  $parser->output_fh( *$out_fh );
  $parser->parse_file( $in_file );
  return $out_file;
}


sub _readme_htm {
  my ($self, $in_file, $out_file, $options) = @_;
  $out_file ||= 'README.htm';
  require Pod::Html;
  my ($o) = capture {
    Pod::Html::pod2html(
      "--infile=$in_file",
      "--outfile=-",
      @$options,
    );
  };
  io->file($out_file)->print($o);
  # Remove temporary files if needed
  for my $file ('pod2htmd.tmp', 'pod2htmi.tmp') {
    if (-e $file) {
      unlink $file or warn "Warning: Could not remove file '$file'.\n$!\n";
    }
  }
  return $out_file;
}


sub _readme_man {
  my ($self, $in_file, $out_file, $options) = @_;
  $out_file ||= 'README.1';
  require Pod::Man;
  my $parser = Pod::Man->new( @$options );
  my $io = io->file($out_file)->open(">");
  my $out_fh = $io->io_handle;
  $parser->output_fh( *$out_fh );
  $parser->parse_file( $in_file );
  return $out_file;
}


sub _readme_pdf {
  my ($self, $in_file, $out_file, $options) = @_;
  $out_file ||= 'README.pdf';
  eval { require App::pod2pdf; }
    or die "Could not generate $out_file because pod2pdf could not be found\n";
  my $parser = App::pod2pdf->new( @$options );
  $parser->parse_from_file($in_file);
  my ($o) = capture { $parser->output };
  io->file($out_file)->print($o);
  return $out_file;
}

sub _readme_md {
  my ($self, $in_file, $out_file, $options) = @_;
  $out_file ||= 'README.md';
  require Pod::Markdown;
  my $parser = Pod::Markdown->new( @$options );
  my $io = io->file($out_file)->open(">");
  my $out_fh = $io->io_handle;
  $parser->output_fh( *$out_fh );
  $parser->parse_file( $in_file );
  return $out_file;
}


sub _all_from {
  my $self = shift;
  return unless $self->admin->{extensions};
  my ($metadata) = grep {
    ref($_) eq 'Module::Install::Metadata';
  } @{$self->admin->{extensions}};
  return unless $metadata;
  return $metadata->{values}{all_from} || '';
}

'Readme!';

__END__

#line 316

inc/Module/Install/Win32.pm  view on Meta::CPAN

#line 1
package Module::Install::Win32;

use strict;
use Module::Install::Base ();

use vars qw{$VERSION @ISA $ISCORE};
BEGIN {
	$VERSION = '1.18';
	@ISA     = 'Module::Install::Base';
	$ISCORE  = 1;
}

# determine if the user needs nmake, and download it if needed
sub check_nmake {
	my $self = shift;
	$self->load('can_run');
	$self->load('get_file');

	require Config;
	return unless (
		$^O eq 'MSWin32'                     and
		$Config::Config{make}                and
		$Config::Config{make} =~ /^nmake\b/i and
		! $self->can_run('nmake')
	);

	print "The required 'nmake' executable not found, fetching it...\n";

	require File::Basename;
	my $rv = $self->get_file(
		url       => 'http://download.microsoft.com/download/vc15/Patch/1.52/W95/EN-US/Nmake15.exe',
		ftp_url   => 'ftp://ftp.microsoft.com/Softlib/MSLFILES/Nmake15.exe',
		local_dir => File::Basename::dirname($^X),
		size      => 51928,
		run       => 'Nmake15.exe /o > nul',
		check_for => 'Nmake.exe',
		remove    => 1,
	);

	die <<'END_MESSAGE' unless $rv;

-------------------------------------------------------------------------------

Since you are using Microsoft Windows, you will need the 'nmake' utility
before installation. It's available at:

  http://download.microsoft.com/download/vc15/Patch/1.52/W95/EN-US/Nmake15.exe
      or
  ftp://ftp.microsoft.com/Softlib/MSLFILES/Nmake15.exe

Please download the file manually, save it to a directory in %PATH% (e.g.
C:\WINDOWS\COMMAND\), then launch the MS-DOS command line shell, "cd" to
that directory, and run "Nmake15.exe" from there; that will create the
'nmake.exe' file needed by this module.

You may then resume the installation process described in README.

-------------------------------------------------------------------------------
END_MESSAGE

}

1;

inc/Module/Install/WriteAll.pm  view on Meta::CPAN

#line 1
package Module::Install::WriteAll;

use strict;
use Module::Install::Base ();

use vars qw{$VERSION @ISA $ISCORE};
BEGIN {
	$VERSION = '1.18';
	@ISA     = qw{Module::Install::Base};
	$ISCORE  = 1;
}

sub WriteAll {
	my $self = shift;
	my %args = (
		meta        => 1,
		sign        => 0,
		inline      => 0,
		check_nmake => 1,
		@_,
	);

	$self->sign(1)                if $args{sign};
	$self->admin->WriteAll(%args) if $self->is_admin;

	$self->check_nmake if $args{check_nmake};
	unless ( $self->makemaker_args->{PL_FILES} ) {
		# XXX: This still may be a bit over-defensive...
		unless ($self->makemaker(6.25)) {
			$self->makemaker_args( PL_FILES => {} ) if -f 'Build.PL';
		}
	}

	# Until ExtUtils::MakeMaker support MYMETA.yml, make sure
	# we clean it up properly ourself.
	$self->realclean_files('MYMETA.yml');

	if ( $args{inline} ) {
		$self->Inline->write;
	} else {
		$self->Makefile->write;
	}

	# The Makefile write process adds a couple of dependencies,
	# so write the META.yml files after the Makefile.
	if ( $args{meta} ) {
		$self->Meta->write;
	}

	# Experimental support for MYMETA
	if ( $ENV{X_MYMETA} ) {
		if ( $ENV{X_MYMETA} eq 'JSON' ) {
			$self->Meta->write_mymeta_json;
		} else {
			$self->Meta->write_mymeta_yaml;
		}
	}

	return 1;
}

1;

lib/Text/Phonetic.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic;
# ============================================================================
use Moo;
use utf8;

use Text::Unidecode qw();
use Carp;
use Module::Find;
use Class::Load;

our $AUTHORITY = 'cpan:MAROS';
our $VERSION = "2.09";

use 5.008000;

our $DEFAULT_ALGORITHM = 'Phonix';
our @PREDICATES_CHECKED;
our @AVAILABLE_ALGORITHMS = grep
    { s/^Text::Phonetic::(.+)$/$1/x }
    findsubmod Text::Phonetic;

has 'unidecode' => (
    is              => 'rw',
    default         => 1,
    required        => 1,
    documentation   => q[Transliterate strings to ASCII before processing]
);

after 'BUILDARGS' => sub {
    my ($class) = @_;
    return $class->check_predicates;
};

# ----------------------------------------------------------------------------
# Class methods

sub available_algorithms {
    return @AVAILABLE_ALGORITHMS;
}

sub register_algorithm {
    my ($class,$algorithm) = @_;
    push @AVAILABLE_ALGORITHMS,$algorithm
        unless grep { $algorithm eq $_ } @AVAILABLE_ALGORITHMS;
    return $algorithm;
}

sub check_predicates {
    my ($class) = @_;

    if ($class->can('_predicates')
        && ! grep { $class eq $_ } @PREDICATES_CHECKED) {
        my @predicates = $class->_predicates;
        foreach my $predicate (@predicates) {
            my $ok = Class::Load::try_load_class($predicate);
            unless ($ok) {
                croak("Could not load '$class' phonetic algorithm: Predicate '$predicate' is missing")
            } else {
                push(@PREDICATES_CHECKED,$class);
            }
        }
    }
    return;
}

# ----------------------------------------------------------------------------
# Constructor (new provided by Moo)

sub load {
    my $self = shift;
    my $params = (scalar @_ == 1 && ref($_[0]) eq 'HASH') ? shift : { @_ };

    my $algorithm = delete($params->{algorithm}) || $DEFAULT_ALGORITHM;
    my $class = __PACKAGE__.'::'.$algorithm;

    unless (grep { $algorithm eq $_ } @AVAILABLE_ALGORITHMS) {
        croak("Could not load '$algorithm' phonetic algorithm: Algorithm not available");
    }

    unless (Class::Load::is_class_loaded($class)) {
        my ($ok,$error) = Class::Load::try_load_class($class);
        unless ($ok) {
            croak("Could not load '$algorithm' phonetic algorithm: $error")
        }
    }

    $class->check_predicates;

    return $class->new($params);
}

# ----------------------------------------------------------------------------
# Public methods

sub encode {
    my $self = shift;

    # Single value
    if (scalar(@_) == 1) {
        my $string = shift;
        $string = Text::Unidecode::unidecode($string)
            if ($self->unidecode);
        return
            unless defined $string && $string !~ /^\s*$/;
        return $self->_do_encode($string);
    # Expand list
    } elsif (scalar(@_) > 1) {
        my @result_list;
        foreach my $string (@_) {
            push @result_list,$self->encode($string);
        }
        return wantarray ? @result_list : \@result_list;
    }
    # Fallback
    return;
}


sub compare {
    my ($self,$string1,$string2) = @_;

    return 0 unless defined $string1 && $string1 !~ /^\s*$/;
    return 0 unless defined $string2 && $string2 !~ /^\s*$/;

    # Extremely rare case ;-)
    return 100 if ($string1 eq $string2);

    if ($self->unidecode) {
        $string1 = Text::Unidecode::unidecode($string1);
        $string2 = Text::Unidecode::unidecode($string2);

        # Also not very likely, but has to be checked
        return 99 if ($string1 eq $string2);
    }

    my $value1 = $self->_do_encode($string1);
    my $value2 = $self->_do_encode($string2);

    return 0 unless (defined $value1 && defined $value2);

    return $self->_do_compare($self->_do_encode($string1),$self->_do_encode($string2));
}

sub _do_compare {
    my ($self,$result1,$result2) = @_;

    return 50 if ($result1 eq $result2);
    return 0;
}

sub _do_encode {
    carp('_do_encode is an abstract method!');
}

# ----------------------------------------------------------------------------
# Utility functions

sub _is_inlist {
    my $string = shift;
    return 0 unless defined $string;
    my $list = (scalar @_ == 1 && ref($_[0]) eq 'ARRAY') ? shift : \@_;

    return 1 if grep {$string eq $_ } @$list;
    return 0;
}

sub _compare_list {
    my ($list1,$list2) = @_;

    return 0 unless ref($list1) eq 'ARRAY' && ref($list2) eq 'ARRAY';

    foreach my $element1 (@$list1) {
        next unless defined $element1;
        foreach my $element2 (@$list2) {
            next unless defined $element2;
            return 1
                if $element1 eq $element2;
        }
    }

    return 0;
}

"Schmitt ~ Smith ~ Schmitz";

=encoding utf8

=pod

=head1 NAME

Text::Phonetic - A base class for phonetic algorithms

=head1 SYNOPSIS

  use Text::Phonetic::Metaphone;

  my $phonetic = Text::Phonetic::Metaphone->new();
  $encoded_string = $phonetic->encode($string);
  @encoded_list = $phonetic->encode(@list);

  my $same = $phonetic->compare($string1,$string2);

Or

  use Text::Phonetic;
  my $phonetic = Text::Phonetic->load( algorithm => 'Phonix' );
  $encoded_string = $phonetic->encode($string);

This module provides an easy and convinient way to encode names with various
phonetic algorithms. It acts as a wrapper around other phonetic algorithm
modules like L<Text::Metaphone>, L<Text::DoubleMetaphone>, L<Text::Soundex>
and also implements some other algorithms such as
L<Text::Phonetic::DaitchMokotoff>, L<Text::Phonetic::Koeln>,
L<Text::Phonetic::Phonem> and L<Text::Phonetic::Phonix>.

This module can easily be subclassed.

=head1 DESCRIPTION

=head2 Constructors

=head3 new

 $obj = Text::Phonetic::SUBCLASS->new(%PARAMETERS)

You can pass arbitrary attributes to the constructor. The only global
attribute is C<unidecode> which defaults to 1 if not set. This attribute
controls if non-latin characters should be transliterated to A-Z
(see also L<Text::Unidecode>).

Additional attributes may be defined by the various implementation classes.

=head3 load

 $obj = Text::Phonetic->load(algorithm => $algorithm, %PARAMETERS)

Alternative constructor which also loads the requested algorithm subclass.

=head2 Methods

=head3 encode

 $RETURN_STRING = $obj->encode($STRING);
 OR
 @RETURN_LIST = $obj->encode(@LIST);
 OR
 $RETURN_LIST_REF = $obj->encode(@LIST);

Encodes the given string or list of strings. Returns a single value, array or
array reference depending on the caller context and parameters.

Returns undef on an empty/undefined/whitespace only string.

=head3 compare

 $RETURN_CODE = $obj->compare($STRING1,$STRING2);

The return code is an integer between 100 and 0 indicating the likelihood that
the to results are the same. 100  means that the strings are completely
identical. 99 means that the strings match after all non-latin characters
have been transliterated. Values in between 98 and 1 usually mean that the
given strings match. 0 means that the used alogorithm couldn't match the two
strings at all.
C<compare> is a shortcut to the C<$obj-E<gt>_do_compare($CODE1,$CODE2)> method.

=head2 Class Methods

=head3 available_algorithms

 my @available = Text::Phonetic->available_algorithms;

Returns a list of all available/installed algorithms

=head1 SUBLCASSING

You can easily subclass Text::Phonetic and add your own phonetic algorithm.
All subclasses must use Text::Phonetic as their base class, reside in
the Text::Phonetic namespace, and implement the following methods:

=head2 _do_encode

 $RESULT = $obj->_do_encode($STRING);

This method does the actual encoding. It should return either a string or
an array reference.

=head2 _do_compare

 $RETURN_STRING = $obj->_do_compare($RESULT1,$RESULT2);

If your C<_do_encode> method doesn't return a single scalar value you also
might need to implement a comparison method. It takes two results as returned
by C<_do_encode> and returns an integer value between 98 and 0
(see L<"compare">).

=head2 _predicates

Third party modules can be marked as predicates by adding the C<_predicates>
method which should return al list of package names. All predicates will be
loaded if installed. If missing an exception will be thrown.

=head2 Object structure

Text::Phonetic uses L<Moo> to declare attributes.

=head2 Helper class methods

=head3 _compare_list

 Text::Phonetic::_compare_list($LIST1_REF,$LIST2_REF);

Compares the two arrays and returns true if at least one element is equal
(ignoring the position) in both lists.

=head2 Example class

 package Text::Phonetic::MyAlgorithm;
 use Moo;
 extends qw(Text::Phonetic);

 has someattribute => (
    is  => 'rw',
 );

 sub _do_encode {
     my ($self,$string) = @_;
     # Do something
     return $phonetic_representation;
 }

 __PACKAGE__->meta->make_immutable;
 no Moo;
 1;

=head1 SEE ALSO

L<DBIx::Class::PhoneticSearch> (Build phonetic indices via DBIx::Class),
L<Text::Phonetic::VideoGame> (Phonetic encoding for video game titles)

=head1 SUPPORT

Please report any bugs or feature requests to C<text-phonetic@rt.cpan.org>, or
through the web interface at
L<http://rt.cpan.org/Public/Bug/Report.html?Queue=Text::Phonetic>.
I will be notified, and then you'll automatically be notified of progress on
your report as I make changes.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com

    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic is Copyright (c) 2006-2012 Maroš Kollár
- L<http://www.k-1.com>

=head1 LICENCE

This library is free software, you can redistribute it and/or modify
it under the same terms as Perl itself.

=cut

lib/Text/Phonetic/DaitchMokotoff.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::DaitchMokotoff;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

our $VERSION = $Text::Phonetic::VERSION;

our @RULES = (
    ["SCHTSCH", 2, 4, 4],
    ["SCHTSH", 2, 4, 4],
    ["SCHTCH", 2, 4, 4],
    ["SHTCH", 2, 4, 4],
    ["SHTSH", 2, 4, 4],
    ["STSCH", 2, 4, 4],
    ["TTSCH", 4, 4, 4],
    ["ZHDZH", 2, 4, 4],
    ["SHCH", 2, 4, 4],
    ["SCHT", 2, 43, 43],
    ["SCHD", 2, 43, 43],
    ["STCH", 2, 4, 4],
    ["STRZ", 2, 4, 4],
    ["STRS", 2, 4, 4],
    ["STSH", 2, 4, 4],
    ["SZCZ", 2, 4, 4],
    ["SZCS", 2, 4, 4],
    ["TTCH", 4, 4, 4],
    ["TSCH", 4, 4, 4],
    ["TTSZ", 4, 4, 4],
    ["ZDZH", 2, 4, 4],
    ["ZSCH", 4, 4, 4],
    ["CHS", 5, 54, 54],
    ["CSZ", 4, 4, 4],
    ["CZS", 4, 4, 4],
    ["DRZ", 4, 4, 4],
    ["DRS", 4, 4, 4],
    ["DSH", 4, 4, 4],
    ["DSZ", 4, 4, 4],
    ["DZH", 4, 4, 4],
    ["DZS", 4, 4, 4],
    ["SCH", 4, 4, 4],
    ["SHT", 2, 43, 43],
    ["SZT", 2, 43, 43],
    ["SHD", 2, 43, 43],
    ["SZD", 2, 43, 43],
    ["TCH", 4, 4, 4],
    ["TRZ", 4, 4, 4],
    ["TRS", 4, 4, 4],
    ["TSH", 4, 4, 4],
    ["TTS", 4, 4, 4],
    ["TTZ", 4, 4, 4],
    ["TZS", 4, 4, 4],
    ["TSZ", 4, 4, 4],
    ["ZDZ", 2, 4, 4],
    ["ZHD", 2, 43, 43],
    ["ZSH", 4, 4, 4],
    ["AI", 0, 1, undef],
    ["AJ", 0, 1, undef],
    ["AY", 0, 1, undef],
    ["AU", 0, 7, undef],
    ["CZ", 4, 4, 4],
    ["CS", 4, 4, 4],
    ["DS", 4, 4, 4],
    ["DZ", 4, 4, 4],
    ["DT", 3, 3, 3],
    ["EI", 0, 1, undef],
    ["EJ", 0, 1, undef],
    ["EY", 0, 1, undef],
    ["EU", 1, 1, undef],
    ["IA", 1, undef, undef],
    ["IE", 1, undef, undef],
    ["IO", 1, undef, undef],
    ["IU", 1, undef, undef],
    ["KS", 5, 54, 54],
    ["KH", 5, 5, 5],
    ["MN", 66, 66, 66],
    ["NM", 66, 66, 66],
    ["OI", 0, 1, undef],
    ["OJ", 0, 1, undef],
    ["OY", 0, 1, undef],
    ["PF", 7, 7, 7],
    ["PH", 7, 7, 7],
    ["SH", 4, 4, 4],
    ["SC", 2, 4, 4],
    ["ST", 2, 43, 43],
    ["SD", 2, 43, 43],
    ["SZ", 4, 4, 4],
    ["TH", 3, 3, 3],
    ["TS", 4, 4, 4],
    ["TC", 4, 4, 4],
    ["TZ", 4, 4, 4],
    ["UI", 0, 1, undef],
    ["UJ", 0, 1, undef],
    ["UY", 0, 1, undef],
    ["UE", 0, 1, undef],
    ["ZD", 2, 43, 43],
    ["ZH", 4, 4, 4],
    ["ZS", 4, 4, 4],
    ["RZ", [94,4], [94,4], [94,4]],
    ["CH", [5,4], [5,4], [5,4]],
    ["CK", [4,45], [4,45], [4,45]],
    ["RS", [94,4], [94,4], [94,4]],
    ["FB", 7, 7, 7],
    ["A", 0, undef, undef],
    ["B", 7, 7, 7],
    ["D", 3, 3, 3],
    ["E", 0, undef, undef],
    ["F", 7, 7, 7],
    ["G", 5, 5, 5],
    ["H", 5, 5, undef],
    ["I", 0, undef, undef],
    ["K", 5, 5, 5],
    ["L", 8, 8, 8],
    ["M", 6, 6, 6],
    ["N", 6, 6, 6],
    ["O", 0, undef, undef],
    ["P", 7, 7, 7],
    ["Q", 5, 5, 5],
    ["R", 9, 9, 9],
    ["S", 4, 4, 4],
    ["T", 3, 3, 3],
    ["U", 0, undef, undef],
    ["V", 7, 7, 7],
    ["W", 7, 7, 7],
    ["X", 5, 54, 54],
    ["Y", 1, undef, undef],
    ["Z", 4, 4, 4],
    ["C", [5,4], [5,4], [5,4]],
    ["J", [1,4], [4,undef], [4,undef]],
);

sub _do_compare {
    my ($self,$result1,$result2) = @_;

    return 50
       if Text::Phonetic::_compare_list($result1,$result2);

    return 0;
}

sub _do_encode {
    my ($self,$string) = @_;

    my $match_index;
    my $last_match;
    my $result_list = [''];

    $string = uc($string);
    $string =~ tr/A-Z//cd;

    while (length($string)) {
        # Loop all rules
        RULES: foreach my $rule (@RULES) {

            # Check if rule matches
            #if ($string =~ s/^([AEIOUJY]{2})([AEIOU])//i) {

            if ($string =~ s/^$rule->[0]//) {
                # Is Start of a string?
                if ($result_list->[0] eq '') {
                    $match_index = 1;
                # Before a vowel?
                } elsif (Text::Phonetic::_is_inlist(substr($string,0,1),qw(A E I O U)))  {
                    $match_index = 2;
                # Other situation
                } else{
                    $match_index = 3;
                }
                unless (defined $rule->[$match_index]) {
                    undef $last_match;
                    last RULES;
                }
                last RULES if (defined($last_match) && $last_match eq $rule->[$match_index]);
                $last_match = $rule->[$match_index];
                $result_list = _add_result($result_list,$rule->[$match_index]);
                last RULES;
            }
        }
    }

    foreach my $result (@$result_list) {
        $result .= '0'  x (6-length $result);
        $result = substr($result,0,6);
    }

    return $result_list;
}

sub _add_result {
    my $result = shift;
    my $rule = shift;

    return $result unless defined $rule;

    if (ref($rule) eq 'ARRAY') {
        my $newresult = [];
        foreach my $result_string (@$result) {
            foreach my $rule_string (@$rule) {
                push @$newresult,$result_string.$rule_string;
            }
        }
        return $newresult;
    } else {
        foreach my $result_string (@$result) {
            $result_string .= $rule;
        }
        return $result;
    }
}

1;

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::DaitchMokotoff - Daitch-Mokotoff algorithm

=head1 DESCRIPTION

Daitch-Mokotoff Soundex (D-M Soundex) is a phonetic algorithm invented in 1985
by genealogist Gary Mokotoff, and later improved by Randy Daitch, both of the
Jewish Genealogical Society. It is a refinement of the Russell and American
Soundex algorithms designed to allow matching of Slavic and Yiddish surnames
with similar pronunciation but differences in spelling. (Wikipedia, 2007)

Some strings in the Daitch-Mokotoff algorithm produce ambigous results.
Therefore the results are always returned as Array references, even if there
is only a single result.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic::Metaphone is Copyright (c) 2006,2007 Maroš. Kollár.
All rights reserved.

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO

Description of the algorithm can be found at
L<http://en.wikipedia.org/wiki/Daitch-Mokotoff_Soundex>

L<Text::Metaphone>

=cut

lib/Text/Phonetic/DoubleMetaphone.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::DoubleMetaphone;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

our $VERSION = $Text::Phonetic::VERSION;

sub _predicates {
    return 'Text::DoubleMetaphone';
}

sub _do_compare {
    my ($self,$result1,$result2) = @_;

    return 50
       if Text::Phonetic::_compare_list($result1,$result2);

    return 0;
}

sub _do_encode {
    my ($self,$string) = @_;

    my($code1, $code2) = Text::DoubleMetaphone::double_metaphone($string);
    return [$code1,$code2];
}

1;

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::DoubleMetaphone - DoubleMetaphone algorithm

=head1 DESCRIPTION

The Double Metaphone search algorithm is a phonetic algorithm written by
Lawrence Philips and is the second generation of his Metaphone algorithm.
(Wikipedia, 2007)

The Result is always an array ref containing two (mostly, but not always)
identical elements.

This module is a thin wrapper around L<Text::DoubleMetaphone>.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic::DoubleMetaphone is Copyright (c) 2006,2007 Maroš. Kollár.
All rights reserved.

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO

Description of the algorithm can be found at
L<http://en.wikipedia.org/wiki/Double_Metaphone>

L<Text::DoubleMetaphone>

=cut

lib/Text/Phonetic/Koeln.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::Koeln;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

our $VERSION = $Text::Phonetic::VERSION;

sub _do_encode {
    my ($self,$string) = @_;

    my (@character_list,$result,$last_match);

    $string = uc($string);

    # Replace umlaut
    $string =~ s/ß/S/g;
    $string =~ s/Ä/AE/g;
    $string =~ s/Ö/OE/g;
    $string =~ s/Ü/UE/g;

    # Replace double consonants
    #$string =~ s/([BCDFGHJKLMNPQRSTVWXZ])\1+/$1/g;

    # Convert string to array
    @character_list = split //,$string;
    $result = '';

    # Handle initial sounds
    if ($character_list[0] eq 'C') {
        if (Text::Phonetic::_is_inlist($character_list[1],qw(A H K L O Q R U X))) {
            $result .= 4;
        } else {
            $result .= 8;
        }
        $last_match = shift @character_list;
    }

    # Loop all characters
    while (scalar(@character_list)) {
        # A,E,I,J,O,U,Y => 0
        if (Text::Phonetic::_is_inlist($character_list[0],qw(A E I J Y O U))) {
            $result .= 0;
            $last_match = shift @character_list;
        # B => 1
        } elsif ($character_list[0] eq 'B') {
            $result .= 1;
            $last_match = shift @character_list;
        # P in front of H => 1
        # P => 3
        } elsif ($character_list[0] eq 'P') {
            if (defined($character_list[1])
                && $character_list[1] eq 'H') {
                $result .= 3;
            } else {
                $result .= 1;
            }
            $last_match = shift @character_list;
        # D,T in front of C,S,Z => 8
        # D,T => 2
        } elsif (Text::Phonetic::_is_inlist($character_list[0],qw(D T))) {
            if (defined($character_list[1]) && $character_list[1] =~ m/[CSZ]/) {
                $result .= 8;
            } else {
                $result .= 2;
            }
            $last_match = shift @character_list;
        # F,V,W => 3
        } elsif (Text::Phonetic::_is_inlist($character_list[0],qw(F V W))) {
            $result .= 3;
            $last_match = shift @character_list;
        # C in front of A,H,K,O,Q,U,X => 4
        # C after S,Z => 8
        } elsif ($character_list[0] eq 'C') {
            if (Text::Phonetic::_is_inlist($last_match,qw(S Z))) {
                $result .= 8;
            } elsif (defined($character_list[1])
                && Text::Phonetic::_is_inlist($character_list[1],qw(A H K O Q U X))) {
                $result .= 4;
            } else {
                $result .= 8;
            }
            $last_match = shift @character_list;
        # G,K,Q => 4
        } elsif (Text::Phonetic::_is_inlist($character_list[0],qw(G Q K))) {
            $result .= 4;
            $last_match = shift @character_list;
        # X not after C,K,Q => 48
        # X after C,K,Q => 8
        } elsif ($character_list[0] eq 'X') {
            if (Text::Phonetic::_is_inlist($last_match,qw(C K Q))) {
                $result .= 8;
            } else {
                $result .= 48;
            }
            $last_match = shift @character_list;
        # L => 5
        } elsif ($character_list[0] eq 'L') {
            $result .= 5;
            $last_match = shift @character_list;
        # M,N => 6
        } elsif (Text::Phonetic::_is_inlist($character_list[0],qw(M N))) {
            $result .= 6;
            $last_match = shift @character_list;
        # R => 7
        } elsif ($character_list[0] eq 'R') {
            $result .= 7;
            $last_match = shift @character_list;
        # S,Z => 8
        } elsif (Text::Phonetic::_is_inlist($character_list[0],qw(S Z))) {
            $result .= 8;
            $last_match = shift @character_list;
        # No rule matched
        } else {
            $last_match = shift @character_list;
        }

    }

    # Replace consecutive codes
    $result =~ s/(\d)\1+/$1/g;

    # Replace zero code (except for first position)
    $result =~ s/([1-9])0+/$1/g;

    return $result
}


1;

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::Koeln - Kölner Phonetik algorithm

=head1 DESCRIPTION

The "Kölner Phonetik" is a phonetic algorithm for indexing names by sound, as
pronounced in German. The goal is for names with the same pronunciation to be
encoded to the same representation so that they can be matched despite minor
differences in spelling.

In contrast to Soundex this algorithm is suitable for long names since the
length of the encoded result is not limited. This algorithm is able to find
allmost all ortographic variations in names, but also produces many false
positives.

The result is always a sequence of numbers. Special characters and whitespaces
are ignored. If your text might contain non-latin characters (except for
German umlaute and 'ß') you should unaccent it prior to creating a phonetic
code.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic::Koeln is Copyright (c) 2006,2007 Maroš. Kollár.
All rights reserved.

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO

Description of the algorithm can be found at
L<http://de.wikipedia.org/wiki/K%C3%B6lner_Phonetik>

Hans Joachim Postel: Die Kölner Phonetik. Ein Verfahren zur Identifizierung
von Personennamen auf der Grundlage der Gestaltanalyse. in: IBM-Nachrichten,
19. Jahrgang, 1969, S. 925-931

=cut

lib/Text/Phonetic/Metaphone.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::Metaphone;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

has 'max_length'=> (
    is              => 'rw',
    isa             => sub {
        die 'max_length must be an int' unless shift =~ /\d/
    },
    documentation   => q[Limit the length of the encoded string],
    default         => 0,
);

our $VERSION = $Text::Phonetic::VERSION;

sub _predicates {
    return 'Text::Metaphone';
}

sub _do_encode {
    my ($self,$string) = @_;

    return Text::Metaphone::Metaphone($string,$self->max_length);
}

1;

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::Metaphone - Metaphone algorithm

=head1 DESCRIPTION

Metaphone was developed by Lawrence Philips as a response to deficiencies in
the Soundex algorithm. It is more accurate than Soundex because it uses a
larger set of rules for English pronunciation. (Wikipedia, 2007)

This module is a thin wrapper around L<Text::Metaphone>.

The parameter C<max_length> can be set to limit the length of the encoded
string.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic::Metaphone is Copyright (c) 2006,2007 Maroš. Kollár.
All rights reserved.

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO

Description of the algorithm can be found at
L<http://en.wikipedia.org/wiki/Metaphone>

L<Text::Metaphone>

=cut

lib/Text/Phonetic/Phonem.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::Phonem;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

our $VERSION = $Text::Phonetic::VERSION;

our %DOUBLECHARS = (
    SC  =>'C',
    SZ  =>'C',
    CZ  =>'C',
    TZ  =>'C',
    SZ  =>'C',
    TS  =>'C',
    KS  =>'X',
    PF  =>'V',
    QU  =>'KW',
    PH  =>'V',
    UE  =>'Y',
    AE  =>'E',
    OE  =>'Ö',
    EI  =>'AY',
    EY  =>'AY',
    EU  =>'OY',
    AU  =>'A§',
    OU  =>'§ '
);

sub _do_encode {
    my ($self,$string) = @_;

    $string = uc($string);
    $string =~ tr/A-Z//cd;

    # Iterate over two character substitutions
    foreach my $index (0..((length $string)-2)) {
        if ($DOUBLECHARS{substr $string,$index,2}) {
            substr ($string,$index,2) = $DOUBLECHARS{substr $string,$index,2};
        }
    }

    # Single character substitutions via tr
    $string =~tr/ZKGQIJFWPT§/CCCCYYVBDUA/;

    #delete forbidden characters
    $string =~tr/ABCDLMNORSUVWXY//cd;

    #remove double chars
    $string =~tr/ABCDLMNORSUVWXY//s;

    return $string;
}

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::Phonem - Phonem algorithm

=head1 DESCRIPTION

The PHONEM algorithm is a simple substitution algorithm that was originally
implemented in dBase.

Implementation of the PHONEM substitutions, as described in Georg Wilde and
Carsten Meyer, "Doppelgaenger gesucht - Ein Programm fuer kontextsensitive
phonetische Textumwandlung" from ct Magazin fuer Computer & Technik 25/1999.

The original variant was implemented as X86-Assembler-Funktion. This
implementation does not try to mimic the original code, though it should
achieve equal results. As the original software used for building the original
implementation was not available, there was no testing for correctness, other
than the examples given in the article.

The Perl implementation was written by Martin Wilz
(L<http://wilz.de/view/Themen/MagisterArbeit>)

=head1 AUTHOR

    Martin Wilz
    http://wilz.de/view/Themen/MagisterArbeit

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO


=cut

1;

lib/Text/Phonetic/Phonix.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::Phonix;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

our $VERSION = $Text::Phonetic::VERSION;

our $VOVEL = '[AEIOU]';
our $VOVEL_WITHY = '[AEIOUY]';
our $CONSONANT = '[BCDFGHJLMNPQRSTVXZXY]';

our @VALUES = (
    [qr/[AEIOUHWY]/,0],
    [qr/[BP]/,1],
    [qr/[CGJKQ]/,2],
    [qr/[DT]/,3],
    [qr/L/,4],
    [qr/[MN]/,5],
    [qr/R/,6],
    [qr/[FV]/,7],
    [qr/[SXZ]/,8],
);

our @RULES = (
    [qr/DG/,'G'],
    [qr/C([OAU])/,'K1'],
    [qr/C[YI]/,'SI'],
    [qr/CE/,'SE'],
    [qr/^CL($VOVEL)/,'KL1'],
    [qr/CK/,'K'],
    [qr/[GJ]C$/,'K'],
    [qr/^CH?R($VOVEL)/,'KR1'],
    [qr/^WR/,'R'],
    [qr/NC/,'NK'],
    [qr/CT/,'KT'],
    [qr/PH/,'F'],
    [qr/AA/,'AR'], #neu
    [qr/SCH/,'SH'],
    [qr/BTL/,'TL'],
    [qr/GHT/,'T'],
    [qr/AUGH/,'ARF'],
    [qr/($VOVEL)LJ($VOVEL)/,'1LD2'],
    [qr/LOUGH/,'LOW'],
    [qr/^Q/,'KW'],
    [qr/^KN/,'N'],
    [qr/GN$/,'N'],
    [qr/GHN/,'N'],
    [qr/GNE$/,'N'],
    [qr/GHNE/,'NE'],
    [qr/GNES$/,'NS'],
    [qr/^GN/,'N'],
    [qr/(\w)GN($CONSONANT)/,'1N2'],
    [qr/^PS/,'S'],
    [qr/^PT/,'T'],
    [qr/^CZ/,'C'],
    [qr/($VOVEL)WZ(\w)/,'1Z2'],
    [qr/(\w)CZ(\w)/,'1CH2'],
    [qr/LZ/,'LSH'],
    [qr/RZ/,'RSH'],
    [qr/(\w)Z($VOVEL)/,'1S2'],
    [qr/ZZ/,'TS'],
    [qr/($CONSONANT)Z(\w)/,'1TS2'],
    [qr/HROUGH/,'REW'],
    [qr/OUGH/,'OF'],
    [qr/($VOVEL)Q($VOVEL)/,'1KW2'],
    [qr/($VOVEL)J($VOVEL)/,'1Y2'],
    [qr/^YJ($VOVEL)/,'Y1'],
    [qr/^GH/,'G'],
    [qr/($VOVEL)E$/,'1GH'],
    [qr/^CY/,'S'],
    [qr/NX/,'NKS'],
    [qr/^PF/,'F'],
    [qr/DT$/,'T'],
    [qr/(T|D)L$/,'1IL'],
    [qr/YTH/,'ITH'],
    [qr/^TS?J($VOVEL)/,'CH1'],
    [qr/^TS($VOVEL)/,'T1'],
    [qr/TCH/,'CH'], # old che
    [qr/($VOVEL)WSK/,'1VSIKE'],
    [qr/^[PM]N($VOVEL)/,'N1'],
    [qr/($VOVEL)STL/,'1SL'],
    [qr/TNT$/,'ENT'],
    [qr/EAUX$/,'OH'],
    [qr/EXCI/,'ECS'],
    [qr/X/,'ECS'],
    [qr/NED$/,'ND'],
    [qr/JR/,'DR'],
    [qr/EE$/,'EA'],
    [qr/ZS/,'S'],
    [qr/($VOVEL)H?R($CONSONANT)/,'1AH2'],
    [qr/($VOVEL)HR$/,'1AH'],
    [qr/RE$/,'AR'],
    [qr/($VOVEL)R$/,'1AH'],
    [qr/LLE/,'LE'],
    [qr/($CONSONANT)LE(S?)$/,'1ILE2'],
    [qr/E$/,''],
    [qr/ES$/,'S'],
    [qr/($VOVEL)SS/,'1AS'],
    [qr/($VOVEL)MB$/,'1M'],
    [qr/MPTS/,'MPS'],
    [qr/MPS/,'MS'],
    [qr/MPT/,'MT'],

);

#sub _do_compare {
#	my $obj = shift;
#	my $result1 = shift;
#	my $result2 = shift;
#
#	# Main values are different
#	return 0 unless ($result1->[0] eq $result2->[0]);
#
#	# Ending values the same
#	return 75 if ($result1->[1] eq $result2->[1]);
#
#	# Ending values differ in length, and are same for the shorter
#	my $length1 = length $result1->[1];
#	my $length2 = length $result2->[1];
#	if ($length1 > $length2
#		&& $length1 - $length2 == 1) {
#		return 50 if (substr($result1->[1],0,$length2) eq $result2->[1]);
#	 }elsif ($length2 > $length1
#		&& $length2 - $length1 == 1) {
#		return 50 if (substr($result2->[1],0,$length1) eq $result1->[1]);
#	}
#
#	return 25;
#}
#The algorithm always returns either a scalar value or an array reference with
#two elements. The fist element represents the sound of the name without the
#ending sound, and the second element represents the ending sound. To get a
#full representation of the name you need to concat the two elements.
#
#If you want to compare two names the following rules apply:
#
#=over
#
#=item * If the ending sound values of an entered name and a retrieved name are
#the same, the retrieved name is a LIKELY candidate.
#
#=item * If an entered name has an ending-sound value, and the retrieved name
#does not, then the retrieved name is a LEAST-LIKELY candidate.
#
#=item * If the two ending-sound values are the same for the length of the
#shorter, and the difference in length between the two ending-sound is one
#digit only, then the retrieved name isa LESS-LIKELY candidate.
#
#=item * All other cases result in LEAST-LIKELY candidates.
#
#=back

sub _do_encode {
    my ($self,$string) = @_;

    my ($original_string, $first_char);
    $original_string = $string;

    # To uppercase and remove other characters
    $string = uc($string);
    $string =~ tr/A-Z//cd;

    # RULE 1: Replcace rule
    foreach my $rule (@RULES) {
        my $regexp = $rule->[0];
        my $replace = $rule->[1];
        $string =~ s/$regexp/_replace($replace,$1,$2)/ge;
    }

    # RULE 2: Fetch first character
    $first_char = substr($string,0,1,'');

    # RULE 3: Exceptions for first character rule
    if (grep { $first_char eq $_ } qw(A E I O U Y)) {
        $first_char = 'v';
        $string =~ s/^$VOVEL_WITHY//;
    } elsif ($first_char eq 'W' || $first_char eq 'H') {
        #$string =~ s/^[WH]//;
    }

    # RULE 4
    $string =~ s/ES$/S/;
    # RULE 5
    $string =~ s/($VOVEL_WITHY)$/$1E/;
    # RULE 6
    #$string =~ s/\w$//; # This rule seems kind of strict
    # RULE 7-8
#   if ($string =~ s/($VOVEL_WITHY)([A-Z]+)$/$2/) {
#       # RULE 13
#       $last_string = _transform($2);
#   }

    # RULE 9-11
    $string = _transform($string);

    # RULE 12
    $string = $first_char.$string;

    #$string .= $last_string if (defined $last_string);
    $string .= '0'  x (8-length $string);
    $string = substr($string,0,8);

    return $string;
}

sub _transform {
    my $string = shift;
    return unless defined $string;

    # RULE 9
    $string =~ s/([AEIOUYHW])//g;
    # RULE 10
    $string =~ s/($CONSONANT+)\1/$1/g;
    # RULE 11
    foreach my $value (@VALUES) {
        my $regexp = $value->[0];
        $string =~ s/$regexp/$value->[1]/g;
    }
    return $string;
}

sub _replace {
    my $replace = shift;
    my $pos1 = shift;
    my $pos2 = shift;

    $replace =~ s/1/$pos1/ if (defined $pos1);
    $replace =~ s/2/$pos2/ if (defined $pos2);

    return $replace;
}

1;

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::Phonix - Phonix algorithm

=head1 DESCRIPTION

Phonix is an improved version of Soundex, developed by T.N. Gadd. Phonix
has been incorporated into a number of WAIS implementations, including
freeWAIS.

There seem to be two variants of the Phonix algorithm. One which also includes
the first letter in the numeric code, and one that doesn't. This module is
using the later variant.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic::Phonix is Copyright (c) 2006,2007 Maroš. Kollár.
All rights reserved.

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO


=cut

lib/Text/Phonetic/Soundex.pm  view on Meta::CPAN

# ============================================================================
package Text::Phonetic::Soundex;
# ============================================================================
use utf8;

use Moo;
extends qw(Text::Phonetic);

has 'nara'=> (
    is              => 'rw',
    documentation   => q[Use the soundex variant maintained by the National Archives and Records Administration (NARA)],
    default         => 0,
);

has 'nocode'=> (
    is              => 'rw',
    documentation   => q[Redefine the value that will be returned if the input string contains no identifiable sounds within it],
    predicate       => 'has_nocode',
);

our $VERSION = $Text::Phonetic::VERSION;

sub _predicates {
    return 'Text::Soundex';
}

sub _do_encode {
    my ($self,$string) = @_;

    if ($self->has_nocode) {
        $Text::Soundex::nocode = $self->nocode;
    }

    if ($self->nara) {
        return Text::Soundex::soundex_nara($string);
    } else {
        return Text::Soundex::soundex($string);
    }
}

1;

=encoding utf8

=pod

=head1 NAME

Text::Phonetic::Soundex - Soundex algorithm

=head1 DESCRIPTION

Soundex is a phonetic algorithm for indexing names by sound, as pronounced in
English. Soundex is the most widely known of all phonetic algorithms.
Improvements to Soundex are the basis for many modern phonetic algorithms.
(Wikipedia, 2007)

If the parameter C<nara> is set to a true value, a variant of the soundex
algorithm maintained by the National Archives and Records Administration
(NARA) will be used.

If the parameter C<nocode> redefines the value that will be returned if the
input string contains no identifiable sounds within it.

This module is a thin wrapper around L<Text::Soundex>.

=head1 AUTHOR

    Maroš Kollár
    CPAN ID: MAROS
    maros [at] k-1.com
    http://www.k-1.com

=head1 COPYRIGHT

Text::Phonetic::Soundex is Copyright (c) 2006,2007 Maroš. Kollár.
All rights reserved.

This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.

The full text of the license can be found in the
LICENSE file included with this module.

=head1 SEE ALSO

Description of the algorithm can be found at
L<http://en.wikipedia.org/wiki/Soundex>

L<Text::Soundex>

=cut

t/001_load.t  view on Meta::CPAN

# -*- perl -*-

# t/001_load.t - check module loading

use Test::Most tests => 8+1;
use Test::NoWarnings;

require "t/global.pl";

use_ok( 'Text::Phonetic' );
use_ok( 'Text::Phonetic::Koeln' );
use_ok( 'Text::Phonetic::DaitchMokotoff' );
use_ok( 'Text::Phonetic::Phonix' );
use_ok( 'Text::Phonetic::Phonem' );

load_conditional('Text::Phonetic::Metaphone','Text::Metaphone');
load_conditional('Text::Phonetic::DoubleMetaphone','Text::DoubleMetaphone');
load_conditional('Text::Phonetic::Soundex','Text::Soundex');
#load_conditional('Text::Phonetic::MultiPhone','Text::MultiPhone');

t/002_general.t  view on Meta::CPAN

# -*- perl -*-

# t/002_load.t - some general checks

use Test::Most tests => 8+1;
use Test::NoWarnings;

use_ok( 'Text::Phonetic' );

my @list = Text::Phonetic->available_algorithms();

explain('Found '.scalar @list);
ok(scalar @list >= 7,'Found at least 7 installed algorithms');
ok((grep { $_ eq 'Soundex'} @list),'Found soundex algorithm');

ok(Text::Phonetic::_is_inlist('hase','baer','hase','luchs'),'Helper function ok');
ok(! Text::Phonetic::_is_inlist('hase','baer','ratte','luchs'),'Helper function ok');
ok(Text::Phonetic::_is_inlist('hase',['baer','hase','luchs']),'Helper function ok');

ok(Text::Phonetic::_compare_list(['hase','baer'],['luchs','ratte','hase']),'Helper function ok');
ok(! Text::Phonetic::_compare_list(['hase','baer'],['luchs','ratte']),'Helper function ok');

t/003_interface.t  view on Meta::CPAN

# -*- perl -*-

# t/002_load.t - check interface

use Test::Most tests => 16+1;
use Test::NoWarnings;

use_ok( 'Text::Phonetic' );


my $t1 = Text::Phonetic->load();

isa_ok($t1,'Text::Phonetic::Phonix');
is($t1->encode('schneider'),'S5300000','Object works');

my $t2 = Text::Phonetic->load(algorithm => 'Phonem');
isa_ok($t2,'Text::Phonetic::Phonem');
is($t2->encode('schneider'),'CNAYDR','Object works');

my $t3 = Text::Phonetic::Phonix->new();
isa_ok($t3,'Text::Phonetic::Phonix');
is($t3->encode('schneider'),'S5300000','Object works');

local @Text::Phonetic::AVAILABLE_ALGORITHMS;
push @Text::Phonetic::AVAILABLE_ALGORITHMS,'Test';

{
    package Text::Phonetic::Test;
    use Moo;
    extends qw(Text::Phonetic);

    has 'attribute' => (
        is  => 'rw',
        required => 1,
    );

    sub _do_encode {
        my ($self,$sting) = @_;
        return $self->attribute;
    }
}

my $t4 = Text::Phonetic::Test->new(attribute => 'test');
isa_ok($t4,'Text::Phonetic::Test');
is($t4->encode('schneider'),'test','Object works');
is($t4->encode('attribute'),'test','Attribute is set');

my $t5 = Text::Phonetic->load(attribute => 'test', algorithm => 'Test');
isa_ok($t5,'Text::Phonetic::Test');
is($t5->encode('schneider'),'test','Object works');
is($t5->encode('attribute'),'test','Attribute is set');

my $t6 = Text::Phonetic->load({attribute => 'test', algorithm => 'Test'});
isa_ok($t6,'Text::Phonetic::Test');
is($t6->encode('schneider'),'test','Object works');
is($t6->encode('attribute'),'test','Attribute is set');

t/004_wrapper.t  view on Meta::CPAN

# -*- perl -*-

# t/004_wrapper.t - check wrapped modules

use utf8;
use Test::Most tests=>33+1;
use Test::NoWarnings;

use_ok('Text::Phonetic');

require "t/global.pl";

if (run_conditional('Text::Soundex','19')) {
    my $soundex = Text::Phonetic->load(
        algorithm   => 'Soundex',
    );

    isa_ok($soundex,'Text::Phonetic::Soundex');
    test_encode($soundex,"Euler","E460");
    test_encode($soundex,"Gauss","G200");
    test_encode($soundex,"Hilbert","H416");
    test_encode($soundex,"Knuth","K530");
    test_encode($soundex,"Lloydi","L300");
    test_encode($soundex,"Lukasiewicz","L222");
    test_encode($soundex,"Ashcraft","A226");

    is($soundex->compare('Alexander','Alieksandr'),50,'Compare soundex');
    is($soundex->compare('Alexander','Barbara'),0,'Compare soundex');
    is($soundex->compare('Alexander','Alexander'),100,'Compare soundex');
    is($soundex->compare('Alexander','Alexandér'),99,'Compare soundex');

    # Multi tests
    my @rlist = $soundex->encode('Alexander','Alieksandr','Euler');
    my $rlist = $soundex->encode('Alexander','Alieksandr','Euler');
    is(scalar(@rlist),3,'Soundex list');
    is(scalar(@$rlist),3,'Soundex list');
    is($rlist[2],'E460','Soundex list');
    is($rlist->[2],'E460','Soundex list');

    my $soundexnara = Text::Phonetic->load(
        algorithm   => 'Soundex',
        nara        => 1,
    );
    isa_ok($soundexnara,'Text::Phonetic::Soundex');
    test_encode($soundexnara,"Ashcraft","A261");

    my $soundexnocode = Text::Phonetic->load(
        algorithm   => 'Soundex',
        nocode      => 'Z0000',
    );
    test_encode($soundexnocode,"_","Z0000");
}

if (run_conditional('Text::Metaphone','8')) {
    my $metaphone = Text::Phonetic->load(
        algorithm   => 'Metaphone'
    );
    isa_ok($metaphone,'Text::Phonetic::Metaphone');
    test_encode($metaphone,"recrudescence","RKRTSNS");
    test_encode($metaphone,"moist","MST");
    test_encode($metaphone,"Gutenberg","KTNBRK");

    my $metaphone_length = Text::Phonetic->load(
        algorithm   => 'Metaphone',
        max_length  => 4
    );
    isa_ok($metaphone_length,'Text::Phonetic::Metaphone');
    test_encode($metaphone_length,"recrudescence","RKRT");
    test_encode($metaphone_length,"Gutenberg","KTNB");

    is($metaphone->compare('Gutenberg','Gutnbaerg'),50,'Compare Metaphone');
}

if (run_conditional('Text::DoubleMetaphone','5')) {
    my $doublemetaphone = Text::Phonetic->load(
        algorithm   => 'DoubleMetaphone'
    );
    isa_ok($doublemetaphone,'Text::Phonetic::DoubleMetaphone');
    is($doublemetaphone->compare('Alexander','Alieksandr'),50,'Compare DoubleMetaphone');
    is($doublemetaphone->compare('Alexander','Barbara'),0,'Compare DoubleMetaphone');
    is($doublemetaphone->compare('Alexander','Alexander'),100,'Compare DoubleMetaphone');
    is($doublemetaphone->compare('Alexander','Alexandér'),99,'Compare DoubleMetaphone');
}


t/005_koeln.t  view on Meta::CPAN

# -*- perl -*-

# t/005_koeln.t - Test koelner phonetik

use Test::Most tests=>82+1;
use Test::NoWarnings;
use utf8;

use Text::Phonetic::Koeln;

my $cologne = Text::Phonetic::Koeln->new();

require "t/global.pl";

my %TEST = (
    'wikipedia'             => '3412',
    'müller-lüdenscheidt'   => '65752682',
    'breschnew'             => '17863',
    'müller'                => '657',
    'schmidt'               => '862', # or 8628?
    'schneider'             => '8627',
    'fischer'               => '387',
    'auerbach'              => '0714',
    'ohrbach'               => '0714',
    'moskowitz'             => '68438',
    'moskovitsch'           => '68438',
    'ceniow'                => '863',
    'tsenyuv'               => '863',
    'weber'                 => '317',
    'beier'                 => '17',
    'maier'                 => '67',
    'major'                 => '67',
    'meyer'                 => '67',
    'wagner'                => '3467', # or 367?
    'schulz'                => '858', # or 85?
    'becker'                => '147',
    'hoffmann'              => '0366',
    'schäfer'               => '837',
    'cater'                 => '427',
    'axel'                  => '0485',

    # C as initial sound before A, H, K, L, O, Q, R, U, X = '4'
    'ca'                    => '4',
    'ch'                    => '4',
    'ck'                    => '4',
    'cl'                    => '45',
    'co'                    => '4',
    'cq'                    => '4',
    'cr'                    => '47',
    'cu'                    => '4',
    'cx'                    => '48',

    # Ca as initial sound NOT before A, H, K, L, O, Q, R, U, X = '8'
    'cb'                    => '81',
    'cc'                    => '8',
    'cd'                    => '82',
    'ce'                    => '8',
    'cf'                    => '83',
    'cg'                    => '84',
    'ci'                    => '8',
    'cj'                    => '8',
    'cm'                    => '86',
    'cn'                    => '86',
    'cp'                    => '81',
    'cs'                    => '8',
    'ct'                    => '82',
    'cv'                    => '83',
    'cw'                    => '83',
    'cy'                    => '8',
    'cz'                    => '8',
    # C after S, Z = '8'
    'sc'                    => '8',
    'zc'                    => '8',
    'scx'                   => '8',
    'zcx'                   => '8',

    # C before A, H, K, O, Q, U, X but NOT after S, Z = '4'
    'bca',                  => '14',
    'bch',                  => '14',
    'bck',                  => '14',
    'bco',                  => '14',
    'bcq',                  => '14',
    'bcu',                  => '14',
    'bcx',                  => '148',
    # c notb efore a, h, k, o, q, u, x = '8'
    'bcb',                  => '181',
    'bcc',                  => '18',
    'bcd',                  => '182',
    'bce',                  => '18',
    'bcf',                  => '183',
    'bcg',                  => '184',
    'bci',                  => '18',
    'bcj',                  => '18',
    'bcl',                  => '185',
    'bcm',                  => '186',
    'bcn',                  => '186',
    'bcp',                  => '181',
    'bcr',                  => '187',
    'bcs',                  => '18',
    'bct',                  => '182',
    'bcv',                  => '183',
    'bcw',                  => '183',
    'bcy',                  => '18',
    'bcz',                  => '18',
);

isa_ok($cologne,'Text::Phonetic::Koeln');
while (my($key,$value) = each(%TEST)) {
    test_encode($cologne,$key,$value);
}







( run in 0.633 second using v1.01-cache-2.11-cpan-8780591d54d )