Lingua-Sentence-1.100/0000755000076500000240000000000013054657247014364 5ustar cwhitenerstaffLingua-Sentence-1.100/Changes0000644000076500000240000000244313054657247015662 0ustar cwhitenerstaffRevision history for Lingua-Sentence 1.100 2017-02-26 - Moved to Dist::Zilla - Moved to ExtUtils::MakeMaker - Tidied the code to get rid of the tabs and spaces problem - Removed use of non-ASCII characters in the regular expressions. Use the \x{} syntax instead. - Un-escaped several regular expressions non-metacharacters - Removed usage of two-arg open - Removed bareword file handles - Use File::Spec and Path::Tiny to slurp files 1.05 2013-12-19 - added language support for Danish, Finnish, Lithuanian and updated language support for Greek 1.04 2013-02-01 - added language support for Czech, Hungarian, Icelandic, Latvian, Polish, Romanian, Russian, Slovak, Slovenian and Swedish - changed license to LGPLv3 because language support files come under this license - fixed RT issue #82069: Sentences with more than one trailing whitespace not split - removed use of Exporter as this is object-oriented module 1.03 2010-12-04 - added language support for Catalan and Dutch - update language support for Spanish 1.02 2010-07-07 - added language support for French, Italian, Spanish - switched to File::ShareDir to access nonbreaking prefix files 1.00 2010-02-18 - original version Lingua-Sentence-1.100/CONTRIBUTING.md0000644000076500000240000001020413054657247016612 0ustar cwhitenerstaff# HOW TO CONTRIBUTE Thank you for considering contributing to this distribution. This file contains instructions that will help you work with the source code. The distribution is managed with [Dist::Zilla](https://metacpan.org/pod/Dist::Zilla). This means that many of the usual files you might expect are not in the repository, but are generated at release time. Some generated files are kept in the repository as a convenience (e.g. Build.PL/Makefile.PL and META.json). Generally, **you do not need Dist::Zilla to contribute patches**. You may need Dist::Zilla to create a tarball. See below for guidance. ## Getting dependencies If you have App::cpanminus 1.6 or later installed, you can use [cpanm](https://metacpan.org/pod/cpanm) to satisfy dependencies like this: $ cpanm --installdeps --with-develop . You can also run this command (or any other cpanm command) without installing App::cpanminus first, using the fatpacked `cpanm` script via curl or wget: $ curl -L https://cpanmin.us | perl - --installdeps --with-develop . $ wget -qO - https://cpanmin.us | perl - --installdeps --with-develop . Otherwise, look for either a `cpanfile` or `META.json` file for a list of dependencies to satisfy. ## Running tests You can run tests directly using the `prove` tool: $ prove -l $ prove -lv t/some_test_file.t For most of my distributions, `prove` is entirely sufficient for you to test any patches you have. I use `prove` for 99% of my testing during development. ## Code style and tidying Please try to match any existing coding style. If there is a `.perltidyrc` file, please install Perl::Tidy and use perltidy before submitting patches. ## Installing and using Dist::Zilla [Dist::Zilla](https://metacpan.org/pod/Dist::Zilla) is a very powerful authoring tool, optimized for maintaining a large number of distributions with a high degree of automation, but it has a large dependency chain, a bit of a learning curve and requires a number of author-specific plugins. To install it from CPAN, I recommend one of the following approaches for the quickest installation: # using CPAN.pm, but bypassing non-functional pod tests $ cpan TAP::Harness::Restricted $ PERL_MM_USE_DEFAULT=1 HARNESS_CLASS=TAP::Harness::Restricted cpan Dist::Zilla # using cpanm, bypassing *all* tests $ cpanm -n Dist::Zilla In either case, it's probably going to take about 10 minutes. Go for a walk, go get a cup of your favorite beverage, take a bathroom break, or whatever. When you get back, Dist::Zilla should be ready for you. Then you need to install any plugins specific to this distribution: $ dzil authordeps --missing | cpanm You can use Dist::Zilla to install the distribution's dependencies if you haven't already installed them with cpanm: $ dzil listdeps --missing --develop | cpanm Once everything is installed, here are some dzil commands you might try: $ dzil build $ dzil test $ dzil regenerate You can learn more about Dist::Zilla at http://dzil.org/ ## Other notes This distribution maintains the generated `META.json` and either `Makefile.PL` or `Build.PL` in the repository. This allows two things: [Travis CI](https://travis-ci.org/) can build and test the distribution without requiring Dist::Zilla, and the distribution can be installed directly from Github or a local git repository using `cpanm` for testing (again, not requiring Dist::Zilla). $ cpanm git://github.com/Author/Distribution-Name.git $ cd Distribution-Name; cpanm . Contributions are preferred in the form of a Github pull request. See [Using pull requests](https://help.github.com/articles/using-pull-requests/) for further information. You can use the Github issue tracker to report issues without an accompanying patch. # CREDITS This file was adapted from an initial `CONTRIBUTING.mkdn` file from David Golden under the terms of the Apache 2 license, with inspiration from the contributing documents from [Dist::Zilla::Plugin::Author::KENTNL::CONTRIBUTING](https://metacpan.org/pod/Dist::Zilla::Plugin::Author::KENTNL::CONTRIBUTING) and [Dist::Zilla::PluginBundle::Author::ETHER](https://metacpan.org/pod/Dist::Zilla::PluginBundle::Author::ETHER). Lingua-Sentence-1.100/cpanfile0000644000076500000240000000112513054657247016067 0ustar cwhitenerstaffon 'configure' => sub { requires 'ExtUtils::MakeMaker'; }; on 'runtime' => sub { requires 'perl' => '5.008001'; requires 'strict'; requires 'warnings'; requires 'Carp'; requires 'File::ShareDir' => '1.02'; requires 'File::Spec'; requires 'Path::Tiny'; }; on 'test' => sub { requires 'Test::More'; }; on 'develop' => sub { requires 'Test::CheckManifest' => '1.29'; requires 'Test::CPAN::Changes' => '0.4'; requires 'Test::CPAN::Meta'; requires 'Test::Kwalitee' => '1.22'; requires 'Test::Pod::Spelling::CommonMistakes' => '1.000'; }; Lingua-Sentence-1.100/dist.ini0000644000076500000240000000270613054657247016035 0ustar cwhitenerstaffname = Lingua-Sentence author = Achim Ruopp license = LGPL_3_0 copyright_holder = Philip Koehn, Josh Schroeder, and Digital Silk Road copyright_year = 2005 version = 1.100 [Git::GatherDir] exclude_filename = Makefile.PL exclude_filename = META.json exclude_filename = README.md exclude_filename = LICENSE [@Starter] -remove = GatherDir revision = 1 ReadmeAnyFromPod.source_filename = lib/Lingua/Sentence.pm [PkgVersion] [ReadmeAnyFromPod / Markdown_Readme] type = markdown filename = README.md location = root [Prereqs::FromCPANfile] [MetaProvides::Package] [NextRelease] format = %-9v %{yyyy-MM-dd}d [Git::Contributors] [GithubMeta] issues = 1 user = achimr [@Git] [Test::CleanNamespaces] ; TODO [Test::NoTabs] ; TODO [Test::EOL] [MetaTests] [CheckChangeLog] [CheckChangesHasContent] [Test::ChangesHasContent] [Test::Kwalitee] [Test::Version] ; [MojibakeTests] [Test::MinimumVersion] [Test::Pod::Coverage::Configurable] [Test::PodSpelling] wordlist = Pod::Wordlist spell_cmd = aspell list stopword = CPAN stopword = Bas stopword = Europarl stopword = Fontes stopword = Gim stopword = Hil stopword = Jes stopword = Kathrin stopword = Leal stopword = MERCHANTABILITY stopword = Nonbreaking stopword = Philipp stopword = Rozema stopword = nez stopword = nonbreaking stopword = preceeding stopword = rio stopword = splitter [CopyFilesFromBuild] copy = Makefile.PL copy = META.json copy = LICENSE Lingua-Sentence-1.100/lib/0000755000076500000240000000000013054657247015132 5ustar cwhitenerstaffLingua-Sentence-1.100/lib/Lingua/0000755000076500000240000000000013054657247016351 5ustar cwhitenerstaffLingua-Sentence-1.100/lib/Lingua/Sentence.pm0000644000076500000240000002253413054657247020461 0ustar cwhitenerstaffpackage Lingua::Sentence; use strict; use warnings; use Carp (); use File::ShareDir (); use File::Spec (); use Path::Tiny (); our $VERSION = '1.100'; $VERSION = eval $VERSION; sub new { my ($class, $lang_id, $prefix_file) = @_; Carp::croak("Invalid language id: $lang_id") unless ($lang_id && $lang_id =~ /^[a-z][a-z]$/i); # Try loading nonbreaking prefix file specified in constructor my $dir = File::ShareDir::dist_dir('Lingua-Sentence'); my $fallback = File::Spec->catfile($dir, 'nonbreaking_prefix.' . $lang_id); my $fallback_en = File::Spec->catfile($dir, 'nonbreaking_prefix.en'); if (defined($prefix_file)) { unless (-e $prefix_file) { warn "WARNING: Specified prefix file '$prefix_file' does not exist, attempting fall-back to $lang_id version...\n"; $prefix_file = $fallback; } } else { $prefix_file = $fallback; } #default back to English if we don't have a language-specific prefix file unless (-e $prefix_file) { $prefix_file = $fallback_en; warn "WARNING: No known abbreviations for language '$lang_id', attempting fall-back to English version...\n"; } # grab all non-breaking prefixes and store them in a hashref my $nb_prefix = {}; my $pt = Path::Tiny::path($prefix_file); if ($pt->is_file) { for my $line ($pt->lines_utf8({chomp => 1})) { next unless $line; next if substr($line, 0, 1) eq '#'; if ($line =~ /^(.*?)\s+#NUMERIC_ONLY#/) { $nb_prefix->{$1} = 2; } else { $nb_prefix->{$line} = 1; } } } else { die("ERROR: No abbreviations files found in $dir\n"); } return bless {LangID => $lang_id, Nonbreaking => $nb_prefix,}, $class; } sub split { my $self = shift; if (!ref $self) { return "Unnamed $self"; } my $text = shift; if (!$text) { return ''; } return _preprocess($self, $text); } sub split_array { my $self = shift; if (!ref $self) { return "Unnamed $self"; } my $text = shift; if (!$text) { return (); } my $splittext = _preprocess($self, $text); chomp $splittext; return split(/\n/, $splittext); } sub _preprocess { my ($self, $text) = @_; #####add sentence breaks as needed##### #non-period end of sentence markers (?!) followed by sentence starters. $text =~ s/([?!]) +(['"([\x{00bf}\x{00A1}\p{IsPi}]*[\p{IsUpper}])/$1\n$2/g; #multi-dots followed by sentence starters $text =~ s/(\.[\.]+) +(['"([\x{00bf}\x{00A1}\p{IsPi}]*[\p{IsUpper}])/$1\n$2/g; # add breaks for sentences that end with some sort of punctuation inside a quote or parenthetical and are followed by a possible sentence starter punctuation and upper case $text =~ s/([?!\.][\ ]*['")\]\p{IsPf}]+) +(['"([\x{00bf}\x{00A1}\p{IsPi}]*[\ ]*[\p{IsUpper}])/$1\n$2/g; # add breaks for sentences that end with some sort of punctuation are followed by a sentence starter punctuation and upper case $text =~ s/([?!\.]) +(['"([\x{00bf}\x{00A1}\p{IsPi}]+[\ ]*[\p{IsUpper}])/$1\n$2/g; # special punctuation cases are covered. Check all remaining periods. my $word; my $i; my @words = split(/ +/, $text); $text = ""; for ($i = 0; $i < (scalar(@words) - 1); $i++) { if ($words[$i] =~ /([\p{IsAlnum}\.\-]*)([\'\"\)\]\%\p{IsPf}]*)(\.+)$/) { #check if $1 is a known honorific and $2 is empty, never break my $prefix = $1; my $starting_punct = $2; if ( $prefix && $self->{Nonbreaking}{$prefix} && $self->{Nonbreaking}{$prefix} == 1 && !$starting_punct) { #not breaking; } elsif ($words[$i] =~ /(\.)[\p{IsUpper}\-]+(\.+)$/) { #not breaking - upper case acronym } elsif ($words[$i + 1] =~ /^([ ]*['"([\x{00bf}\x{00A1}\p{IsPi}]*[ ]*[\p{IsUpper}0-9])/) { #the next word has a bunch of initial quotes, maybe a space, then either upper case or a number $words[$i] = $words[$i] . "\n" unless ($prefix && $self->{Nonbreaking}{$prefix} && $self->{Nonbreaking}{$prefix} == 2 && !$starting_punct && ($words[$i + 1] =~ /^[0-9]+/)); #we always add a return for these unless we have a numeric non-breaker and a number start } } $text = $text . $words[$i] . " "; } #we stopped one token from the end to allow for easy look-ahead. Append it now. $text = $text . $words[$i]; # clean up spaces at head and tail of each line as well as any double-spacing $text =~ s/ +/ /g; $text =~ s/\n /\n/g; $text =~ s/ \n/\n/g; $text =~ s/^ //g; $text =~ s/ $//g; #add trailing break $text .= "\n" unless $text =~ /\n$/; return $text; } 1; __END__ =head1 NAME Lingua::Sentence - Perl extension for breaking text paragraphs into sentences =head1 SYNOPSIS use Lingua::Sentence; my $splitter = Lingua::Sentence->new("en"); my $text = 'This is a paragraph. It contains several sentences. "But why," you ask?'; print $splitter->split($text); =head1 DESCRIPTION This module allows splitting of text paragraphs into sentences. It is based on scripts developed by Philipp Koehn and Josh Schroeder for processing the Europarl corpus (L). The module uses punctuation and capitalization clues to split paragraphs into an newline-separated string with one sentence per line. For example: This is a paragraph. It contains several sentences. "But why," you ask? goes to: This is a paragraph. It contains several sentences. "But why," you ask? Languages currently supported by the module are: =over =item Catalan =item Czech =item Dutch =item English =item French =item German =item Greek =item Hungarian =item Icelandic =item Italian =item Latvian =item Polish =item Portuguese =item Russian =item Spanish =item Slovak =item Slovenian =item Swedish =back =head2 Nonbreaking Prefixes Files Nonbreaking prefixes are loosely defined as any word ending in a period that does NOT indicate an end of sentence marker. A basic example is Mr. and Ms. in English. The sentence splitter module uses the nonbreaking prefix files included in this distribution. To add a file for other languages, follow the naming convention nonbreaking_prefix.?? and use the two-letter language code you intend to use when creating a Lingua::Sentence object. The sentence splitter module will first look for a file for the language it is processing, and fall back to English if a file for that language is not found. For the splitter, normally a period followed by an uppercase word results in a sentence split. If the word preceeding the period is a nonbreaking prefix, this line break is not inserted. A special case of prefixes, NUMERIC_ONLY, is included for special cases where the prefix should be handled ONLY when before numbers. For example, "Article No. 24 states this." the No. is a nonbreaking prefix. However, in "No. It is not true." No functions as a word. See the example prefix files included in the distribution for more examples. =head3 CREDITS Thanks for the following individuals for supplying nonbreaking prefix files: Bas Rozema (Dutch), HilErio Leal Fontes (Portuguese), JesEs GimEnez (Catalan & Spanish), Anne-Kathrin Schumann (Russian) =head2 EXPORT =over =item new($lang_id) Instantiate an object to split sentences in language $lang_id. If the language is not supported, a splitter object for English will be instantiated. =item new($lang_id,$nonbreaking_prefix_file) Instantiate an object to split sentences in language $lang_id and the nonbreaking prefix file $nonbreaking_prefix_file. If the file does not exist, a splitter object for English will be instantiated. =item split($text) Split sentences in $text by inserting newline characters at the sentence breaks. The resulting string is also terminated with a newline. =item split_array($text) Split sentences in $text into an array of sentences. =back =head1 SUPPORT Bugs should always be submitted via the project hosting bug tracker L For other issues, contact the maintainer. =head1 SEE ALSO L, L, L, L =head1 AUTHOR Achim Ruopp, Eachimru@gmail.comE =head1 COPYRIGHT AND LICENSE Copyright (C) 2010 by Digital Silk Road Portions Copyright (C) 2005 by Philip Koehn and Josh Schroeder (used with permission) This program is free software: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with this program. If not, see . =cut Lingua-Sentence-1.100/LICENSE0000644000076500000240000012407113054657247015376 0ustar cwhitenerstaffThis software is Copyright (c) 2005 by Philip Koehn, Josh Schroeder, and Digital Silk Road. This is free software, licensed under: The GNU Lesser General Public License, Version 3, June 2007 GNU LESSER GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. This version of the GNU Lesser General Public License incorporates the terms and conditions of version 3 of the GNU General Public License, supplemented by the additional permissions listed below. 0. Additional Definitions. As used herein, "this License" refers to version 3 of the GNU Lesser General Public License, and the "GNU GPL" refers to version 3 of the GNU General Public License. "The Library" refers to a covered work governed by this License, other than an Application or a Combined Work as defined below. An "Application" is any work that makes use of an interface provided by the Library, but which is not otherwise based on the Library. Defining a subclass of a class defined by the Library is deemed a mode of using an interface provided by the Library. A "Combined Work" is a work produced by combining or linking an Application with the Library. The particular version of the Library with which the Combined Work was made is also called the "Linked Version". The "Minimal Corresponding Source" for a Combined Work means the Corresponding Source for the Combined Work, excluding any source code for portions of the Combined Work that, considered in isolation, are based on the Application, and not on the Linked Version. The "Corresponding Application Code" for a Combined Work means the object code and/or source code for the Application, including any data and utility programs needed for reproducing the Combined Work from the Application, but excluding the System Libraries of the Combined Work. 1. Exception to Section 3 of the GNU GPL. You may convey a covered work under sections 3 and 4 of this License without being bound by section 3 of the GNU GPL. 2. Conveying Modified Versions. If you modify a copy of the Library, and, in your modifications, a facility refers to a function or data to be supplied by an Application that uses the facility (other than as an argument passed when the facility is invoked), then you may convey a copy of the modified version: a) under this License, provided that you make a good faith effort to ensure that, in the event an Application does not supply the function or data, the facility still operates, and performs whatever part of its purpose remains meaningful, or b) under the GNU GPL, with none of the additional permissions of this License applicable to that copy. 3. Object Code Incorporating Material from Library Header Files. The object code form of an Application may incorporate material from a header file that is part of the Library. You may convey such object code under terms of your choice, provided that, if the incorporated material is not limited to numerical parameters, data structure layouts and accessors, or small macros, inline functions and templates (ten or fewer lines in length), you do both of the following: a) Give prominent notice with each copy of the object code that the Library is used in it and that the Library and its use are covered by this License. b) Accompany the object code with a copy of the GNU GPL and this license document. 4. Combined Works. You may convey a Combined Work under terms of your choice that, taken together, effectively do not restrict modification of the portions of the Library contained in the Combined Work and reverse engineering for debugging such modifications, if you also do each of the following: a) Give prominent notice with each copy of the Combined Work that the Library is used in it and that the Library and its use are covered by this License. b) Accompany the Combined Work with a copy of the GNU GPL and this license document. c) For a Combined Work that displays copyright notices during execution, include the copyright notice for the Library among these notices, as well as a reference directing the user to the copies of the GNU GPL and this license document. d) Do one of the following: 0) Convey the Minimal Corresponding Source under the terms of this License, and the Corresponding Application Code in a form suitable for, and under terms that permit, the user to recombine or relink the Application with a modified version of the Linked Version to produce a modified Combined Work, in the manner specified by section 6 of the GNU GPL for conveying Corresponding Source. 1) Use a suitable shared library mechanism for linking with the Library. A suitable mechanism is one that (a) uses at run time a copy of the Library already present on the user's computer system, and (b) will operate properly with a modified version of the Library that is interface-compatible with the Linked Version. e) Provide Installation Information, but only if you would otherwise be required to provide such information under section 6 of the GNU GPL, and only to the extent that such information is necessary to install and execute a modified version of the Combined Work produced by recombining or relinking the Application with a modified version of the Linked Version. (If you use option 4d0, the Installation Information must accompany the Minimal Corresponding Source and Corresponding Application Code. If you use option 4d1, you must provide the Installation Information in the manner specified by section 6 of the GNU GPL for conveying Corresponding Source.) 5. Combined Libraries. You may place library facilities that are a work based on the Library side by side in a single library together with other library facilities that are not Applications and are not covered by this License, and convey such a combined library under terms of your choice, if you do both of the following: a) Accompany the combined library with a copy of the same work based on the Library, uncombined with any other library facilities, conveyed under the terms of this License. b) Give prominent notice with the combined library that part of it is a work based on the Library, and explaining where to find the accompanying uncombined form of the same work. 6. Revised Versions of the GNU Lesser General Public License. The Free Software Foundation may publish revised and/or new versions of the GNU Lesser 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 Library as you received it specifies that a certain numbered version of the GNU Lesser General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that published version or of any later version published by the Free Software Foundation. If the Library as you received it does not specify a version number of the GNU Lesser General Public License, you may choose any version of the GNU Lesser General Public License ever published by the Free Software Foundation. If the Library as you received it specifies that a proxy can decide whether future versions of the GNU Lesser General Public License shall apply, that proxy's public statement of acceptance of any version is permanent authorization for you to choose that version for the Library. ------------------------------------------------------------------------------- GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The GNU General Public License is a free, copyleft license for software and other kinds of works. The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users. We, the Free Software Foundation, use the GNU General Public License for most of our software; it applies also to any other work released this way by its authors. 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 them 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 prevent others from denying you these rights or asking you to surrender the rights. Therefore, you have certain responsibilities if you distribute copies of the software, or if you modify it: responsibilities to respect the freedom of others. For example, if you distribute copies of such a program, whether gratis or for a fee, you must pass on to the recipients the same freedoms that you received. 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. Developers that use the GNU GPL protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License giving you legal permission to copy, distribute and/or modify it. For the developers' and authors' protection, the GPL clearly explains that there is no warranty for this free software. For both users' and authors' sake, the GPL requires that modified versions be marked as changed, so that their problems will not be attributed erroneously to authors of previous versions. Some devices are designed to deny users access to install or run modified versions of the software inside them, although the manufacturer can do so. This is fundamentally incompatible with the aim of protecting users' freedom to change the software. The systematic pattern of such abuse occurs in the area of products for individuals to use, which is precisely where it is most unacceptable. Therefore, we have designed this version of the GPL to prohibit the practice for those products. If such problems arise substantially in other domains, we stand ready to extend this provision to those domains in future versions of the GPL, as needed to protect the freedom of users. Finally, every program is threatened constantly by software patents. States should not allow patents to restrict development and use of software on general-purpose computers, but in those that do, we wish to avoid the special danger that patents applied to a free program could make it effectively proprietary. To prevent this, the GPL assures that patents cannot be used to render the program non-free. The precise terms and conditions for copying, distribution and modification follow. TERMS AND CONDITIONS 0. Definitions. "This License" refers to version 3 of the GNU General Public License. "Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks. "The Program" refers to any copyrightable work licensed under this License. Each licensee is addressed as "you". "Licensees" and "recipients" may be individuals or organizations. To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work. A "covered work" means either the unmodified Program or a work based on the Program. To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well. To "convey" a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying. An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion. 1. Source Code. The "source code" for a work means the preferred form of the work for making modifications to it. "Object code" means any non-source form of a work. A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language. The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it. The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those subprograms and other parts of the work. The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source. The Corresponding Source for a work in source code form is that same work. 2. Basic Permissions. All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law. You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you. Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary. 3. Protecting Users' Legal Rights From Anti-Circumvention Law. No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures. When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures. 4. Conveying Verbatim Copies. You may convey 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; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program. You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee. 5. Conveying Modified Source Versions. You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions: a) The work must carry prominent notices stating that you modified it, and giving a relevant date. b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to "keep intact all notices". c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it. d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so. A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate. 6. Conveying Non-Source Forms. You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways: a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange. b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge. c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b. d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements. e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d. A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work. A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product. "Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made. If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM). The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network. Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying. 7. Additional Terms. "Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions. When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission. Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms: a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or d) Limiting the use for publicity purposes of names of licensors or authors of the material; or e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors. All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying. If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms. Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way. 8. Termination. You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11). However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation. Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice. Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10. 9. Acceptance Not Required for Having Copies. You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so. 10. Automatic Licensing of Downstream Recipients. Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License. An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts. You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it. 11. Patents. A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's "contributor version". A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License. Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version. In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party. If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent license to downstream recipients. "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid. If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it. A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007. Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law. 12. No Surrender of Others' Freedom. If 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 convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program. 13. Use with the GNU Affero General Public License. Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the special requirements of the GNU Affero General Public License, section 13, concerning interaction through a network will apply to the combination as such. 14. Revised Versions of this License. The Free Software Foundation may publish revised and/or new versions of the GNU 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 that a certain numbered version of the GNU General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU General Public License, you may choose any version ever published by the Free Software Foundation. If the Program specifies that a proxy can decide which future versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program. Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version. 15. Disclaimer of Warranty. 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. 16. Limitation of Liability. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 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. 17. Interpretation of Sections 15 and 16. If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . Also add information on how to contact you by electronic and paper mail. If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode: Copyright (C) This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, your program's commands might be different; for a GUI interface, you would use an "about box". You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU GPL, see . The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, please read . Lingua-Sentence-1.100/Makefile.PL0000644000076500000240000000313413054657247016337 0ustar cwhitenerstaff# This file was automatically generated by Dist::Zilla::Plugin::MakeMaker v6.008. use strict; use warnings; use 5.008001; use ExtUtils::MakeMaker; use File::ShareDir::Install; $File::ShareDir::Install::INCLUDE_DOTFILES = 1; $File::ShareDir::Install::INCLUDE_DOTDIRS = 1; install_share dist => "share"; my %WriteMakefileArgs = ( "ABSTRACT" => "Perl extension for breaking text paragraphs into sentences", "AUTHOR" => "Achim Ruopp ", "CONFIGURE_REQUIRES" => { "ExtUtils::MakeMaker" => 0, "File::ShareDir::Install" => "0.06" }, "DISTNAME" => "Lingua-Sentence", "LICENSE" => "lgpl", "MIN_PERL_VERSION" => "5.008001", "NAME" => "Lingua::Sentence", "PREREQ_PM" => { "Carp" => 0, "File::ShareDir" => "1.02", "File::Spec" => 0, "Path::Tiny" => 0, "strict" => 0, "warnings" => 0 }, "TEST_REQUIRES" => { "ExtUtils::MakeMaker" => 0, "File::Spec" => 0, "Test::More" => 0 }, "VERSION" => "1.100", "test" => { "TESTS" => "t/*.t" } ); my %FallbackPrereqs = ( "Carp" => 0, "ExtUtils::MakeMaker" => 0, "File::ShareDir" => "1.02", "File::Spec" => 0, "Path::Tiny" => 0, "Test::More" => 0, "strict" => 0, "warnings" => 0 ); unless ( eval { ExtUtils::MakeMaker->VERSION(6.63_03) } ) { delete $WriteMakefileArgs{TEST_REQUIRES}; delete $WriteMakefileArgs{BUILD_REQUIRES}; $WriteMakefileArgs{PREREQ_PM} = \%FallbackPrereqs; } delete $WriteMakefileArgs{CONFIGURE_REQUIRES} unless eval { ExtUtils::MakeMaker->VERSION(6.52) }; WriteMakefile(%WriteMakefileArgs); { package MY; use File::ShareDir::Install qw(postamble); } Lingua-Sentence-1.100/MANIFEST0000644000076500000240000000225313054657247015517 0ustar cwhitenerstaff# This file was automatically generated by Dist::Zilla::Plugin::Manifest v6.008. CONTRIBUTING.md Changes LICENSE MANIFEST META.json META.yml Makefile.PL README cpanfile dist.ini lib/Lingua/Sentence.pm share/nonbreaking_prefix.ca share/nonbreaking_prefix.cs share/nonbreaking_prefix.da share/nonbreaking_prefix.de share/nonbreaking_prefix.el share/nonbreaking_prefix.en share/nonbreaking_prefix.es share/nonbreaking_prefix.fi share/nonbreaking_prefix.fr share/nonbreaking_prefix.hu share/nonbreaking_prefix.is share/nonbreaking_prefix.it share/nonbreaking_prefix.lt share/nonbreaking_prefix.lv share/nonbreaking_prefix.nl share/nonbreaking_prefix.pl share/nonbreaking_prefix.pt share/nonbreaking_prefix.ro share/nonbreaking_prefix.ru share/nonbreaking_prefix.sk share/nonbreaking_prefix.sl share/nonbreaking_prefix.sv t/00-report-prereqs.dd t/00-report-prereqs.t t/Lingua-Sentence.t t/nonbreaking_prefix.de xt/author/00-compile.t xt/author/clean-namespaces.t xt/author/eol.t xt/author/no-tabs.t xt/author/pod-coverage.t xt/author/pod-spell.t xt/author/pod-syntax.t xt/author/test-version.t xt/release/changes_has_content.t xt/release/distmeta.t xt/release/kwalitee.t xt/release/minimum-version.t Lingua-Sentence-1.100/META.json0000644000076500000240000005003613054657247016011 0ustar cwhitenerstaff{ "abstract" : "Perl extension for breaking text paragraphs into sentences", "author" : [ "Achim Ruopp " ], "dynamic_config" : 0, "generated_by" : "Dist::Zilla version 6.008, CPAN::Meta::Converter version 2.150005", "license" : [ "lgpl_3_0" ], "meta-spec" : { "url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec", "version" : 2 }, "name" : "Lingua-Sentence", "no_index" : { "directory" : [ "eg", "examples", "inc", "share", "t", "xt" ] }, "prereqs" : { "configure" : { "requires" : { "ExtUtils::MakeMaker" : "0", "File::ShareDir::Install" : "0.06" } }, "develop" : { "requires" : { "File::Spec" : "0", "IO::Handle" : "0", "IPC::Open3" : "0", "Pod::Coverage::TrustPod" : "0", "Test::CPAN::Changes" : "0.4", "Test::CPAN::Meta" : "0", "Test::CheckManifest" : "1.29", "Test::CleanNamespaces" : "0.15", "Test::EOL" : "0", "Test::Kwalitee" : "1.22", "Test::MinimumVersion" : "0", "Test::More" : "0.88", "Test::NoTabs" : "0", "Test::Pod" : "1.41", "Test::Pod::Coverage" : "1.08", "Test::Pod::Spelling::CommonMistakes" : "1.000", "Test::Spelling" : "0.12", "Test::Version" : "1" } }, "runtime" : { "requires" : { "Carp" : "0", "File::ShareDir" : "1.02", "File::Spec" : "0", "Path::Tiny" : "0", "perl" : "5.008001", "strict" : "0", "warnings" : "0" } }, "test" : { "recommends" : { "CPAN::Meta" : "2.120900" }, "requires" : { "ExtUtils::MakeMaker" : "0", "File::Spec" : "0", "Test::More" : "0" } } }, "provides" : { "Lingua::Sentence" : { "file" : "lib/Lingua/Sentence.pm", "version" : "1.100" } }, "release_status" : "stable", "resources" : { "bugtracker" : { "web" : "https://github.com/achimr/corpus-tools/issues" }, "homepage" : "https://github.com/achimr/corpus-tools", "repository" : { "type" : "git", "url" : "https://github.com/achimr/corpus-tools.git", "web" : "https://github.com/achimr/corpus-tools" } }, "version" : "1.100", "x_Dist_Zilla" : { "perl" : { "version" : "5.024000" }, "plugins" : [ { "class" : "Dist::Zilla::Plugin::Git::GatherDir", "config" : { "Dist::Zilla::Plugin::GatherDir" : { "exclude_filename" : [ "LICENSE", "META.json", "Makefile.PL", "README.md" ], "exclude_match" : [], "follow_symlinks" : 0, "include_dotfiles" : 0, "prefix" : "", "prune_directory" : [], "root" : "." }, "Dist::Zilla::Plugin::Git::GatherDir" : { "include_untracked" : 0 } }, "name" : "Git::GatherDir", "version" : "2.041" }, { "class" : "Dist::Zilla::Plugin::PruneCruft", "name" : "@Starter/PruneCruft", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::ManifestSkip", "name" : "@Starter/ManifestSkip", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::MetaConfig", "name" : "@Starter/MetaConfig", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::MetaProvides::Package", "config" : { "Dist::Zilla::Plugin::MetaProvides::Package" : { "finder_objects" : [ { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : "@Starter/MetaProvides::Package/AUTOVIV/:InstallModulesPM", "version" : "6.008" } ], "include_underscores" : 0 }, "Dist::Zilla::Role::MetaProvider::Provider" : { "$Dist::Zilla::Role::MetaProvider::Provider::VERSION" : "2.002003", "inherit_missing" : "1", "inherit_version" : "1", "meta_noindex" : "1" }, "Dist::Zilla::Role::ModuleMetadata" : { "Module::Metadata" : "1.000031", "version" : "0.004" } }, "name" : "@Starter/MetaProvides::Package", "version" : "2.004002" }, { "class" : "Dist::Zilla::Plugin::MetaNoIndex", "name" : "@Starter/MetaNoIndex", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::MetaYAML", "name" : "@Starter/MetaYAML", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::MetaJSON", "name" : "@Starter/MetaJSON", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::License", "name" : "@Starter/License", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::ReadmeAnyFromPod", "config" : { "Dist::Zilla::Role::FileWatcher" : { "version" : "0.006" } }, "name" : "@Starter/ReadmeAnyFromPod", "version" : "0.163250" }, { "class" : "Dist::Zilla::Plugin::ExecDir", "name" : "@Starter/ExecDir", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::ShareDir", "name" : "@Starter/ShareDir", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::PodSyntaxTests", "name" : "@Starter/PodSyntaxTests", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::Test::ReportPrereqs", "name" : "@Starter/Test::ReportPrereqs", "version" : "0.025" }, { "class" : "Dist::Zilla::Plugin::Test::Compile", "config" : { "Dist::Zilla::Plugin::Test::Compile" : { "bail_out_on_fail" : "0", "fail_on_warning" : "author", "fake_home" : 0, "filename" : "xt/author/00-compile.t", "module_finder" : [ ":InstallModules" ], "needs_display" : 0, "phase" : "develop", "script_finder" : [ ":PerlExecFiles" ], "skips" : [], "switch" : [] } }, "name" : "@Starter/Test::Compile", "version" : "2.056" }, { "class" : "Dist::Zilla::Plugin::MakeMaker", "config" : { "Dist::Zilla::Role::TestRunner" : { "default_jobs" : 1 } }, "name" : "@Starter/MakeMaker", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::Manifest", "name" : "@Starter/Manifest", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::TestRelease", "name" : "@Starter/TestRelease", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::RunExtraTests", "config" : { "Dist::Zilla::Role::TestRunner" : { "default_jobs" : 1 } }, "name" : "@Starter/RunExtraTests", "version" : "0.029" }, { "class" : "Dist::Zilla::Plugin::ConfirmRelease", "name" : "@Starter/ConfirmRelease", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::UploadToCPAN", "name" : "@Starter/UploadToCPAN", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::PkgVersion", "name" : "PkgVersion", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::ReadmeAnyFromPod", "config" : { "Dist::Zilla::Role::FileWatcher" : { "version" : "0.006" } }, "name" : "Markdown_Readme", "version" : "0.163250" }, { "class" : "Dist::Zilla::Plugin::Prereqs::FromCPANfile", "name" : "Prereqs::FromCPANfile", "version" : "0.08" }, { "class" : "Dist::Zilla::Plugin::MetaProvides::Package", "config" : { "Dist::Zilla::Plugin::MetaProvides::Package" : { "finder_objects" : [ { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : "MetaProvides::Package/AUTOVIV/:InstallModulesPM", "version" : "6.008" } ], "include_underscores" : 0 }, "Dist::Zilla::Role::MetaProvider::Provider" : { "$Dist::Zilla::Role::MetaProvider::Provider::VERSION" : "2.002003", "inherit_missing" : "1", "inherit_version" : "1", "meta_noindex" : "1" }, "Dist::Zilla::Role::ModuleMetadata" : { "Module::Metadata" : "1.000031", "version" : "0.004" } }, "name" : "MetaProvides::Package", "version" : "2.004002" }, { "class" : "Dist::Zilla::Plugin::NextRelease", "name" : "NextRelease", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::Git::Contributors", "config" : { "Dist::Zilla::Plugin::Git::Contributors" : { "git --version" : "2.10.1 (Apple Git-78)", "include_authors" : 0, "include_releaser" : 1, "order_by" : "name", "paths" : [] } }, "name" : "Git::Contributors", "version" : "0.029" }, { "class" : "Dist::Zilla::Plugin::GithubMeta", "name" : "GithubMeta", "version" : "0.54" }, { "class" : "Dist::Zilla::Plugin::Git::Check", "config" : { "Dist::Zilla::Plugin::Git::Check" : { "untracked_files" : "die" }, "Dist::Zilla::Role::Git::DirtyFiles" : { "allow_dirty" : [ "Changes", "dist.ini" ], "allow_dirty_match" : [], "changelog" : "Changes" }, "Dist::Zilla::Role::Git::Repo" : { "git --version" : "2.10.1 (Apple Git-78)", "repo_root" : "." } }, "name" : "@Git/Check", "version" : "2.041" }, { "class" : "Dist::Zilla::Plugin::Git::Commit", "config" : { "Dist::Zilla::Plugin::Git::Commit" : { "add_files_in" : [], "commit_msg" : "v%v%n%n%c" }, "Dist::Zilla::Role::Git::DirtyFiles" : { "allow_dirty" : [ "Changes", "dist.ini" ], "allow_dirty_match" : [], "changelog" : "Changes" }, "Dist::Zilla::Role::Git::Repo" : { "git --version" : "2.10.1 (Apple Git-78)", "repo_root" : "." }, "Dist::Zilla::Role::Git::StringFormatter" : { "time_zone" : "local" } }, "name" : "@Git/Commit", "version" : "2.041" }, { "class" : "Dist::Zilla::Plugin::Git::Tag", "config" : { "Dist::Zilla::Plugin::Git::Tag" : { "branch" : null, "changelog" : "Changes", "signed" : 0, "tag" : "v1.100", "tag_format" : "v%v", "tag_message" : "v%v" }, "Dist::Zilla::Role::Git::Repo" : { "git --version" : "2.10.1 (Apple Git-78)", "repo_root" : "." }, "Dist::Zilla::Role::Git::StringFormatter" : { "time_zone" : "local" } }, "name" : "@Git/Tag", "version" : "2.041" }, { "class" : "Dist::Zilla::Plugin::Git::Push", "config" : { "Dist::Zilla::Plugin::Git::Push" : { "push_to" : [ "origin" ], "remotes_must_exist" : 1 }, "Dist::Zilla::Role::Git::Repo" : { "git --version" : "2.10.1 (Apple Git-78)", "repo_root" : "." } }, "name" : "@Git/Push", "version" : "2.041" }, { "class" : "Dist::Zilla::Plugin::Test::CleanNamespaces", "config" : { "Dist::Zilla::Plugin::Test::CleanNamespaces" : { "filename" : "xt/author/clean-namespaces.t", "skips" : [] } }, "name" : "Test::CleanNamespaces", "version" : "0.006" }, { "class" : "Dist::Zilla::Plugin::Test::NoTabs", "config" : { "Dist::Zilla::Plugin::Test::NoTabs" : { "filename" : "xt/author/no-tabs.t", "finder" : [ ":InstallModules", ":ExecFiles", ":TestFiles" ] } }, "name" : "Test::NoTabs", "version" : "0.15" }, { "class" : "Dist::Zilla::Plugin::Test::EOL", "config" : { "Dist::Zilla::Plugin::Test::EOL" : { "filename" : "xt/author/eol.t", "finder" : [ ":ExecFiles", ":InstallModules", ":TestFiles" ], "trailing_whitespace" : 1 } }, "name" : "Test::EOL", "version" : "0.19" }, { "class" : "Dist::Zilla::Plugin::MetaTests", "name" : "MetaTests", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::CheckChangeLog", "name" : "CheckChangeLog", "version" : "0.02" }, { "class" : "Dist::Zilla::Plugin::CheckChangesHasContent", "name" : "CheckChangesHasContent", "version" : "0.010" }, { "class" : "Dist::Zilla::Plugin::Test::ChangesHasContent", "name" : "Test::ChangesHasContent", "version" : "0.010" }, { "class" : "Dist::Zilla::Plugin::Test::Kwalitee", "config" : { "Dist::Zilla::Plugin::Test::Kwalitee" : { "filename" : "xt/release/kwalitee.t", "skiptest" : [] } }, "name" : "Test::Kwalitee", "version" : "2.12" }, { "class" : "Dist::Zilla::Plugin::Test::Version", "name" : "Test::Version", "version" : "1.09" }, { "class" : "Dist::Zilla::Plugin::Test::MinimumVersion", "name" : "Test::MinimumVersion", "version" : "2.000007" }, { "class" : "Dist::Zilla::Plugin::Test::Pod::Coverage::Configurable", "name" : "Test::Pod::Coverage::Configurable", "version" : "0.06" }, { "class" : "Dist::Zilla::Plugin::Test::PodSpelling", "config" : { "Dist::Zilla::Plugin::Test::PodSpelling" : { "directories" : [ "bin", "lib" ], "spell_cmd" : "aspell list", "stopwords" : [ "Bas", "CPAN", "Europarl", "Fontes", "Gim", "Hil", "Jes", "Kathrin", "Leal", "MERCHANTABILITY", "Nonbreaking", "Philipp", "Rozema", "nez", "nonbreaking", "preceeding", "rio", "splitter" ], "wordlist" : "Pod::Wordlist" } }, "name" : "Test::PodSpelling", "version" : "2.007004" }, { "class" : "Dist::Zilla::Plugin::CopyFilesFromBuild", "name" : "CopyFilesFromBuild", "version" : "0.163040" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":InstallModules", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":IncModules", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":TestFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":ExtraTestFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":ExecFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":PerlExecFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":ShareFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":MainModule", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":AllFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : ":NoFiles", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : "@Starter/MetaProvides::Package/AUTOVIV/:InstallModulesPM", "version" : "6.008" }, { "class" : "Dist::Zilla::Plugin::FinderCode", "name" : "MetaProvides::Package/AUTOVIV/:InstallModulesPM", "version" : "6.008" } ], "zilla" : { "class" : "Dist::Zilla::Dist::Builder", "config" : { "is_trial" : "0" }, "version" : "6.008" } }, "x_contributors" : [ "Chase Whitener " ], "x_serialization_backend" : "Cpanel::JSON::XS version 3.0225" } Lingua-Sentence-1.100/META.yml0000644000076500000240000003103113054657247015633 0ustar cwhitenerstaff--- abstract: 'Perl extension for breaking text paragraphs into sentences' author: - 'Achim Ruopp ' build_requires: ExtUtils::MakeMaker: '0' File::Spec: '0' Test::More: '0' configure_requires: ExtUtils::MakeMaker: '0' File::ShareDir::Install: '0.06' dynamic_config: 0 generated_by: 'Dist::Zilla version 6.008, CPAN::Meta::Converter version 2.150005' license: lgpl meta-spec: url: http://module-build.sourceforge.net/META-spec-v1.4.html version: '1.4' name: Lingua-Sentence no_index: directory: - eg - examples - inc - share - t - xt provides: Lingua::Sentence: file: lib/Lingua/Sentence.pm version: '1.100' requires: Carp: '0' File::ShareDir: '1.02' File::Spec: '0' Path::Tiny: '0' perl: '5.008001' strict: '0' warnings: '0' resources: bugtracker: https://github.com/achimr/corpus-tools/issues homepage: https://github.com/achimr/corpus-tools repository: https://github.com/achimr/corpus-tools.git version: '1.100' x_Dist_Zilla: perl: version: '5.024000' plugins: - class: Dist::Zilla::Plugin::Git::GatherDir config: Dist::Zilla::Plugin::GatherDir: exclude_filename: - LICENSE - META.json - Makefile.PL - README.md exclude_match: [] follow_symlinks: 0 include_dotfiles: 0 prefix: '' prune_directory: [] root: . Dist::Zilla::Plugin::Git::GatherDir: include_untracked: 0 name: Git::GatherDir version: '2.041' - class: Dist::Zilla::Plugin::PruneCruft name: '@Starter/PruneCruft' version: '6.008' - class: Dist::Zilla::Plugin::ManifestSkip name: '@Starter/ManifestSkip' version: '6.008' - class: Dist::Zilla::Plugin::MetaConfig name: '@Starter/MetaConfig' version: '6.008' - class: Dist::Zilla::Plugin::MetaProvides::Package config: Dist::Zilla::Plugin::MetaProvides::Package: finder_objects: - class: Dist::Zilla::Plugin::FinderCode name: '@Starter/MetaProvides::Package/AUTOVIV/:InstallModulesPM' version: '6.008' include_underscores: 0 Dist::Zilla::Role::MetaProvider::Provider: $Dist::Zilla::Role::MetaProvider::Provider::VERSION: '2.002003' inherit_missing: '1' inherit_version: '1' meta_noindex: '1' Dist::Zilla::Role::ModuleMetadata: Module::Metadata: '1.000031' version: '0.004' name: '@Starter/MetaProvides::Package' version: '2.004002' - class: Dist::Zilla::Plugin::MetaNoIndex name: '@Starter/MetaNoIndex' version: '6.008' - class: Dist::Zilla::Plugin::MetaYAML name: '@Starter/MetaYAML' version: '6.008' - class: Dist::Zilla::Plugin::MetaJSON name: '@Starter/MetaJSON' version: '6.008' - class: Dist::Zilla::Plugin::License name: '@Starter/License' version: '6.008' - class: Dist::Zilla::Plugin::ReadmeAnyFromPod config: Dist::Zilla::Role::FileWatcher: version: '0.006' name: '@Starter/ReadmeAnyFromPod' version: '0.163250' - class: Dist::Zilla::Plugin::ExecDir name: '@Starter/ExecDir' version: '6.008' - class: Dist::Zilla::Plugin::ShareDir name: '@Starter/ShareDir' version: '6.008' - class: Dist::Zilla::Plugin::PodSyntaxTests name: '@Starter/PodSyntaxTests' version: '6.008' - class: Dist::Zilla::Plugin::Test::ReportPrereqs name: '@Starter/Test::ReportPrereqs' version: '0.025' - class: Dist::Zilla::Plugin::Test::Compile config: Dist::Zilla::Plugin::Test::Compile: bail_out_on_fail: '0' fail_on_warning: author fake_home: 0 filename: xt/author/00-compile.t module_finder: - ':InstallModules' needs_display: 0 phase: develop script_finder: - ':PerlExecFiles' skips: [] switch: [] name: '@Starter/Test::Compile' version: '2.056' - class: Dist::Zilla::Plugin::MakeMaker config: Dist::Zilla::Role::TestRunner: default_jobs: 1 name: '@Starter/MakeMaker' version: '6.008' - class: Dist::Zilla::Plugin::Manifest name: '@Starter/Manifest' version: '6.008' - class: Dist::Zilla::Plugin::TestRelease name: '@Starter/TestRelease' version: '6.008' - class: Dist::Zilla::Plugin::RunExtraTests config: Dist::Zilla::Role::TestRunner: default_jobs: 1 name: '@Starter/RunExtraTests' version: '0.029' - class: Dist::Zilla::Plugin::ConfirmRelease name: '@Starter/ConfirmRelease' version: '6.008' - class: Dist::Zilla::Plugin::UploadToCPAN name: '@Starter/UploadToCPAN' version: '6.008' - class: Dist::Zilla::Plugin::PkgVersion name: PkgVersion version: '6.008' - class: Dist::Zilla::Plugin::ReadmeAnyFromPod config: Dist::Zilla::Role::FileWatcher: version: '0.006' name: Markdown_Readme version: '0.163250' - class: Dist::Zilla::Plugin::Prereqs::FromCPANfile name: Prereqs::FromCPANfile version: '0.08' - class: Dist::Zilla::Plugin::MetaProvides::Package config: Dist::Zilla::Plugin::MetaProvides::Package: finder_objects: - class: Dist::Zilla::Plugin::FinderCode name: MetaProvides::Package/AUTOVIV/:InstallModulesPM version: '6.008' include_underscores: 0 Dist::Zilla::Role::MetaProvider::Provider: $Dist::Zilla::Role::MetaProvider::Provider::VERSION: '2.002003' inherit_missing: '1' inherit_version: '1' meta_noindex: '1' Dist::Zilla::Role::ModuleMetadata: Module::Metadata: '1.000031' version: '0.004' name: MetaProvides::Package version: '2.004002' - class: Dist::Zilla::Plugin::NextRelease name: NextRelease version: '6.008' - class: Dist::Zilla::Plugin::Git::Contributors config: Dist::Zilla::Plugin::Git::Contributors: 'git --version': '2.10.1 (Apple Git-78)' include_authors: 0 include_releaser: 1 order_by: name paths: [] name: Git::Contributors version: '0.029' - class: Dist::Zilla::Plugin::GithubMeta name: GithubMeta version: '0.54' - class: Dist::Zilla::Plugin::Git::Check config: Dist::Zilla::Plugin::Git::Check: untracked_files: die Dist::Zilla::Role::Git::DirtyFiles: allow_dirty: - Changes - dist.ini allow_dirty_match: [] changelog: Changes Dist::Zilla::Role::Git::Repo: 'git --version': '2.10.1 (Apple Git-78)' repo_root: . name: '@Git/Check' version: '2.041' - class: Dist::Zilla::Plugin::Git::Commit config: Dist::Zilla::Plugin::Git::Commit: add_files_in: [] commit_msg: v%v%n%n%c Dist::Zilla::Role::Git::DirtyFiles: allow_dirty: - Changes - dist.ini allow_dirty_match: [] changelog: Changes Dist::Zilla::Role::Git::Repo: 'git --version': '2.10.1 (Apple Git-78)' repo_root: . Dist::Zilla::Role::Git::StringFormatter: time_zone: local name: '@Git/Commit' version: '2.041' - class: Dist::Zilla::Plugin::Git::Tag config: Dist::Zilla::Plugin::Git::Tag: branch: ~ changelog: Changes signed: 0 tag: v1.100 tag_format: v%v tag_message: v%v Dist::Zilla::Role::Git::Repo: 'git --version': '2.10.1 (Apple Git-78)' repo_root: . Dist::Zilla::Role::Git::StringFormatter: time_zone: local name: '@Git/Tag' version: '2.041' - class: Dist::Zilla::Plugin::Git::Push config: Dist::Zilla::Plugin::Git::Push: push_to: - origin remotes_must_exist: 1 Dist::Zilla::Role::Git::Repo: 'git --version': '2.10.1 (Apple Git-78)' repo_root: . name: '@Git/Push' version: '2.041' - class: Dist::Zilla::Plugin::Test::CleanNamespaces config: Dist::Zilla::Plugin::Test::CleanNamespaces: filename: xt/author/clean-namespaces.t skips: [] name: Test::CleanNamespaces version: '0.006' - class: Dist::Zilla::Plugin::Test::NoTabs config: Dist::Zilla::Plugin::Test::NoTabs: filename: xt/author/no-tabs.t finder: - ':InstallModules' - ':ExecFiles' - ':TestFiles' name: Test::NoTabs version: '0.15' - class: Dist::Zilla::Plugin::Test::EOL config: Dist::Zilla::Plugin::Test::EOL: filename: xt/author/eol.t finder: - ':ExecFiles' - ':InstallModules' - ':TestFiles' trailing_whitespace: 1 name: Test::EOL version: '0.19' - class: Dist::Zilla::Plugin::MetaTests name: MetaTests version: '6.008' - class: Dist::Zilla::Plugin::CheckChangeLog name: CheckChangeLog version: '0.02' - class: Dist::Zilla::Plugin::CheckChangesHasContent name: CheckChangesHasContent version: '0.010' - class: Dist::Zilla::Plugin::Test::ChangesHasContent name: Test::ChangesHasContent version: '0.010' - class: Dist::Zilla::Plugin::Test::Kwalitee config: Dist::Zilla::Plugin::Test::Kwalitee: filename: xt/release/kwalitee.t skiptest: [] name: Test::Kwalitee version: '2.12' - class: Dist::Zilla::Plugin::Test::Version name: Test::Version version: '1.09' - class: Dist::Zilla::Plugin::Test::MinimumVersion name: Test::MinimumVersion version: '2.000007' - class: Dist::Zilla::Plugin::Test::Pod::Coverage::Configurable name: Test::Pod::Coverage::Configurable version: '0.06' - class: Dist::Zilla::Plugin::Test::PodSpelling config: Dist::Zilla::Plugin::Test::PodSpelling: directories: - bin - lib spell_cmd: 'aspell list' stopwords: - Bas - CPAN - Europarl - Fontes - Gim - Hil - Jes - Kathrin - Leal - MERCHANTABILITY - Nonbreaking - Philipp - Rozema - nez - nonbreaking - preceeding - rio - splitter wordlist: Pod::Wordlist name: Test::PodSpelling version: '2.007004' - class: Dist::Zilla::Plugin::CopyFilesFromBuild name: CopyFilesFromBuild version: '0.163040' - class: Dist::Zilla::Plugin::FinderCode name: ':InstallModules' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':IncModules' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':TestFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':ExtraTestFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':ExecFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':PerlExecFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':ShareFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':MainModule' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':AllFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: ':NoFiles' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: '@Starter/MetaProvides::Package/AUTOVIV/:InstallModulesPM' version: '6.008' - class: Dist::Zilla::Plugin::FinderCode name: MetaProvides::Package/AUTOVIV/:InstallModulesPM version: '6.008' zilla: class: Dist::Zilla::Dist::Builder config: is_trial: '0' version: '6.008' x_contributors: - 'Chase Whitener ' x_serialization_backend: 'YAML::Tiny version 1.69' Lingua-Sentence-1.100/README0000644000076500000240000001075713054657247015256 0ustar cwhitenerstaffNAME Lingua::Sentence - Perl extension for breaking text paragraphs into sentences SYNOPSIS use Lingua::Sentence; my $splitter = Lingua::Sentence->new("en"); my $text = 'This is a paragraph. It contains several sentences. "But why," you ask?'; print $splitter->split($text); DESCRIPTION This module allows splitting of text paragraphs into sentences. It is based on scripts developed by Philipp Koehn and Josh Schroeder for processing the Europarl corpus (http://www.statmt.org/europarl/). The module uses punctuation and capitalization clues to split paragraphs into an newline-separated string with one sentence per line. For example: This is a paragraph. It contains several sentences. "But why," you ask? goes to: This is a paragraph. It contains several sentences. "But why," you ask? Languages currently supported by the module are: Catalan Czech Dutch English French German Greek Hungarian Icelandic Italian Latvian Polish Portuguese Russian Spanish Slovak Slovenian Swedish Nonbreaking Prefixes Files Nonbreaking prefixes are loosely defined as any word ending in a period that does NOT indicate an end of sentence marker. A basic example is Mr. and Ms. in English. The sentence splitter module uses the nonbreaking prefix files included in this distribution. To add a file for other languages, follow the naming convention nonbreaking_prefix.?? and use the two-letter language code you intend to use when creating a Lingua::Sentence object. The sentence splitter module will first look for a file for the language it is processing, and fall back to English if a file for that language is not found. For the splitter, normally a period followed by an uppercase word results in a sentence split. If the word preceeding the period is a nonbreaking prefix, this line break is not inserted. A special case of prefixes, NUMERIC_ONLY, is included for special cases where the prefix should be handled ONLY when before numbers. For example, "Article No. 24 states this." the No. is a nonbreaking prefix. However, in "No. It is not true." No functions as a word. See the example prefix files included in the distribution for more examples. CREDITS Thanks for the following individuals for supplying nonbreaking prefix files: Bas Rozema (Dutch), Hilário Leal Fontes (Portuguese), Jesús Giménez (Catalan & Spanish), Anne-Kathrin Schumann (Russian) EXPORT new($lang_id) Instantiate an object to split sentences in language $lang_id. If the language is not supported, a splitter object for English will be instantiated. new($lang_id,$nonbreaking_prefix_file) Instantiate an object to split sentences in language $lang_id and the nonbreaking prefix file $nonbreaking_prefix_file. If the file does not exist, a splitter object for English will be instantiated. split($text) Split sentences in $text by inserting newline characters at the sentence breaks. The resulting string is also terminated with a newline. split_array($text) Split sentences in $text into an array of sentences. SUPPORT Bugs should always be submitted via the project hosting bug tracker http://code.google.com/p/corpus-tools/issues/list For other issues, contact the maintainer. SEE ALSO Text::Sentence, Lingua::EN::Sentence, Lingua::DE::Sentence, Lingua::HE::Sentence AUTHOR Achim Ruopp, COPYRIGHT AND LICENSE Copyright (C) 2010 by Digital Silk Road Portions Copyright (C) 2005 by Philip Koehn and Josh Schroeder (used with permission) This program is free software: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with this program. If not, see . Lingua-Sentence-1.100/share/0000755000076500000240000000000013054657247015466 5ustar cwhitenerstaffLingua-Sentence-1.100/share/nonbreaking_prefix.ca0000644000076500000240000000222213054657247021643 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A B C D E F G H I J K L M N O P Q R S T U V W X Y Z #Abbreviations aa abrev adj adm admón afma afmas afmo afmos ag am ap apdo art arts assn atte av bros bv cap caps cg cgo cia cía cit cl cm co col corp cos cta cte ctra cts dcha dept dg dl dm doc docs dpt dpto dr dra dras dres dto dupdo ed ej emma emmas emmo emmos entlo entpo esp etc ex excm excma excmas excmo excmos fasc fdo fig figs fol fra gral ha hnos hz ib ibid ibíd id íd ilm ilma ilmas ilmo ilmos iltre inc intr ít izq izqda izqdo jr kc kcal kg khz kl km kw lám lda ldo lib lim ltd ma máx mg mhz min mín mm mr mrs mtro ntra ntro núm ob op pág págs pd ph pje pl plc pm pp pral prof pról prov ps pta ptas pte pts pza ref rr rte sec seg sig sr sra sras sres srta ss sust tech tel teléf tít ud uds vda vdo vid vol vols vra vro vta Lingua-Sentence-1.100/share/nonbreaking_prefix.cs0000644000076500000240000000354513054657247021676 0ustar cwhitenerstaffBc BcA Ing Ing.arch MUDr MVDr MgA Mgr JUDr PhDr RNDr PharmDr ThLic ThDr Ph.D Th.D prof doc CSc DrSc dr. h. c PaedDr Dr PhMr DiS abt ad a.i aj angl anon apod atd atp aut bd biogr b.m b.p b.r cca cit cizojaz c.k col čes čín čj ed facs fasc fol fot franc h.c hist hl hrsg ibid il ind inv.č jap jhdt jv koed kol korej kl krit lat lit m.a maď mj mp násl např nepubl něm no nr n.s okr odd odp obr opr orig phil pl pokrač pol port pozn př.kr př.n.l přel přeprac příl pseud pt red repr resp revid rkp roč roz rozš samost sect sest seš sign sl srv stol sv šk šk.ro špan tab t.č tis tj tř tzv univ uspoř vol vl.jm vs vyd vyobr zal zejm zkr zprac zvl n.p např než MUDr abl absol adj adv ak ak. sl akt alch amer anat angl anglosas arab arch archit arg astr astrol att bás belg bibl biol boh bot bulh círk csl č čas čes dat děj dep dět dial dór dopr dosl ekon epic etnonym eufem f fam fem fil film form fot fr fut fyz gen geogr geol geom germ gram hebr herald hist hl hovor hud hut chcsl chem ie imp impf ind indoevr inf instr interj ión iron it kanad katalán klas kniž komp konj konkr kř kuch lat lék les lid lit liturg lok log m mat meteor metr mod ms mysl n náb námoř neklas něm nesklon nom ob obch obyč ojed opt part pas pejor pers pf pl plpf práv prep předl přivl r rcsl refl reg rkp ř řec s samohl sg sl souhl spec srov stfr střv stsl subj subst superl sv sz táz tech telev teol trans typogr var vedl verb vl. jm voj vok vůb vulg výtv vztaž zahr zájm zast zejm zeměd zkr zř mj dl atp sport Mgr horn MVDr JUDr RSDr Bc PhDr ThDr Ing aj apod PharmDr pomn ev slang nprap odp dop pol st stol p. n. l před n. l n. l př. Kr po Kr př. n. l odd RNDr tzv atd tzn resp tj p br č. j čj č. p čp a. s s. r. o spol. s r. o p. o s. p v. o. s k. s o. p. s o. s v. r v z ml vč kr mld hod popř ap event rus slov rum švýc P. T zvl hor dol S.O.S Lingua-Sentence-1.100/share/nonbreaking_prefix.da0000644000076500000240000001306013054657247021646 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single letter followed by a period is not a sentence ender A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Æ Ø Å a b c d e f g h i j k l m n o p q r s t u v w x y z æ ø å # Abbreviations A.st Act Adj Adm Adr Adv Afb Afd Afg Afl Afr Afrik Afs Afsn Agro Akad Akk Al Alm Almh Am Amer Amp Amr Anf.st Ang Ank Anm Ann Antikv Anv Apr Arab Arb Arr Art Art.nr Ass Att Aug Aut Autorisationsnr Av Bd Bdt Beg Bek Belg Besl Best Bet Bf Bfr Bibl Biol Bkg Bl Bl.a Bot Boul Br Brit Brom Bto Bulg Bull Ca Cand Cf Chir Cirk Cit Civiling Co Containernr D.kr Da Dagl Dat Dav Deb Dec Def Den Dept Dg Dhrr Dial Dif Din Dir Disp Distr Div Dkr Dl Dlr Dm Do Dr Dronn Ds Dupl Dvs E.kr Eftf Eftm Egl Egtl Eks Ekskl Eksp Ekspl El El.lign Elektr Elektron Ell Em Endv Eng Ent Esc Etc Eur Evt Exam F.eks F.kr Fa Fagl Fam Farm Feb Fec Fem Ff Ffr Fg Fhv Fi Fig Fk Fl Flg Flgd Flt Fm Fmd Fo Fol Forb Foreg Forf Fork Form Forordn Forr Fors Forsk Forts Forv Foræld Fp Fr Frk Fuldm Fung Fut Fys Fær Følg Gd Gen Geogr Geol Geom Gg Gl Gld Gldgs Gn Gnsn Gnsntl Gr Gram Grdl Gymn Hdl Henh Henv Hft Hhv Hist Hj Holl Hort Hpl Hr Hrs Hum Ib Ibid If Ifl Iflg Iht Ikr Ill Imp Impf Ind Indb Indv Inf Ing Inkl Insp Instr Interj Intern Is Isl Istf It Ital Itk J.nr Jan Jap Jf Jfr Jr Jun Jur Jvf Kal Kap Kat Kbh Kem Kgl Kgs Kin Kirk Kl Kld Km/t Knsp Komm Komp Konj Kons Korr Kp Kr Kst Kt Ktr Kv Lab Lact Lat Lb Lb.mtr Lbs Lejl Lev Lgd Lic Lign Lin Ling Ling.merc Litt Ll Loc.cit Lok Lrs Ltr M.fl M.fl.st M/sek Mag Maks Mar Mask Mat Matr Matr.nr Max Md Mdl Mdr Mdtl Med Med.vet Medd Medflg Medl Merc Merk Met Mezz Mf Mfl Mgl Mht Mia Mill Min Mio Ml Mod Mods Modsv Modt Mr Mrk Mrs Ms Mul Mv N.br Nat Nb Ndf Ndr Ned Nedenn Nedenst Nederl Neds Nedsæt Ngt Nkr Nl Nml No Nom Nord Nov Nr Nto Ntr Nuv Nuvær O.fl O.fl.st O.s.fr Obj Obl Obs Odont Oecon Off Ofl Okt Omg Omk Omkr Omr Omtr Op.cit Opg Opl Opr Org Orig Ors Osfr Osv Ovenn Ovenst Overf Overs Ovf Oz Pag Par Partc Pct Pd Pens Perf Pers Pf Pg Pga Pgl Pharm Phil Pinx Pk Pkt Pl Plur Pluskv Polit Polyt Pop Port Portug Pos Pr Prc Prod Prof Pron Præp Præs Præt Psych Psyk Pt Pta Ptas Ptc Pts Påg Pæd Rad Rb Red Ref Refl Reg Reg.nr Regn Rel Rep Repr Resp Rk Russ S.br Sa Sb Sc Sch Schw Scient Scient.pol Scient.soc Scil Sculps Sdr Sek Sekr Sen Sept Sfr Sfrs Sg Sh Sign Silv Sing Sj Sjæld Sk Skr Skt Slutn Sml Smp Sms Smst Soc Soc.dem Sort Sovj Sp Spec Spm Spr Spskf Spøg St Stat Sth Stk Str Stud Subj Sup Suppl Sv Såk Sædv T.eks Tab Td Tdr Techn Tekn Temp Teol Teoret Th Theol Tidl Tilf Tilh Till Tilsv Tjek Tjg Tlf Tlgr Toldpos Tr Trb Trp Tskf Tv Ty Typ Tyrk Uafh Ubf Udb Udd Udg Uds Udv Uegl Ugtl Ulin Ult Undert Undt Ung Univ V.lgd Var Vb Vedk Vedl Vedr Vejl Vet Vetr Vha Vidensk Vol Vsa Vulg Vær Zo Zool Årg Årh Årl Æstet Ø.lgd Økon Østr Øv Øvr a.st act adj adm adr adv afb afd afg afl afr afrik afs afsn agro akad akk al alm almh am amer amp amr anf.st ang ank anm ann antikv anv apr arab arb arr art art.nr ass att aug aut autorisationsnr av bd bdt beg bek belg besl best bet bf bfr bibl biol bkg bl bl.a bot boul br brit brom bto bulg bull ca cand cf chir cirk cit civiling co containernr d.kr da dagl dat dav deb dec def den dept dg dhrr dial dif din dir disp distr div dkr dl dlr dm do dr dronn ds dupl dvs e.kr eftf eftm egl egtl eks ekskl eksp ekspl el el.lign elektr elektron ell em endv eng ent esc etc eur evt exam f.eks f.kr fa fagl fam farm feb fec fem ff ffr fg fhv fi fig fk fl flg flgd flt fm fmd fo fol forb foreg forf fork form forordn forr fors forsk forts forv foræld fp fr frk fuldm fung fut fys fær følg gd gen geogr geol geom gg gl gld gldgs gn gnsn gnsntl gr gram grdl gymn hdl henh henv hft hhv hist hj holl hort hpl hr hrs hum ib ibid if ifl iflg iht ikr ill imp impf ind indb indv inf ing inkl insp instr interj intern is isl istf it ital itk j.nr jan jap jf jfr jr jun jur jvf kal kap kat kbh kem kgl kgs kin kirk kl kld km/t knsp komm komp konj kons korr kp kr kst kt ktr kv lab lact lat lb lb.mtr lbs lejl lev lgd lic lign lin ling ling.merc litt ll loc.cit lok lrs ltr m.fl m.fl.st m/sek mag maks mar mask mat matr matr.nr max md mdl mdr mdtl med med.vet medd medflg medl merc merk met mezz mf mfl mgl mht mia mill min mio ml mod mods modsv modt mr mrk mrs ms mul mv n.br nat nb ndf ndr ned nedenn nedenst nederl neds nedsæt ngt nkr nl nml no nom nord nov nr nto ntr nuv nuvær o.fl o.fl.st o.s.fr obj obl obs odont oecon off ofl okt omg omk omkr omr omtr op.cit opg opl opr org orig ors osfr osv ovenn ovenst overf overs ovf oz pag par partc pct pd pens perf pers pf pg pga pgl pharm phil pinx pk pkt pl plur pluskv polit polyt pop port portug pos pr prc prod prof pron præp præs præt psych psyk pt pta ptas ptc pts påg pæd rad rb red ref refl reg reg.nr regn rel rep repr resp rk russ s.br sa sb sc sch schw scient scient.pol scient.soc scil sculps sdr sek sekr sen sept sfr sfrs sg sh sign silv sing sj sjæld sk skr skt slutn sml smp sms smst soc soc.dem sort sovj sp spec spm spr spskf spøg st stat sth stk str stud subj sup suppl sv såk sædv t.eks tab td tdr techn tekn temp teol teoret th theol tidl tilf tilh till tilsv tjek tjg tlf tlgr toldpos tr trb trp tskf tv ty typ tyrk uafh ubf udb udd udg uds udv uegl ugtl ulin ult undert undt ung univ v.lgd var vb vedk vedl vedr vejl vet vetr vha vidensk vol vsa vulg vær zo zool årg årh årl æstet ø.lgd økon østr øv øvr #Number indicators # add #NUMERIC_ONLY# after the word if it should ONLY be non-breaking when a 0-9 digit follows it Lingua-Sentence-1.100/share/nonbreaking_prefix.de0000644000076500000240000000335013054657247021653 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name #no german words end in single lower-case letters, so we throw those in too. A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z #Roman Numerals. A dot after one of these is not a sentence break in German. I II III IV V VI VII VIII IX X XI XII XIII XIV XV XVI XVII XVIII XIX XX i ii iii iv v vi vii viii ix x xi xii xiii xiv xv xvi xvii xviii xix xx #Titles and Honorifics Adj Adm Adv Asst Bart Bldg Brig Bros Capt Cmdr Col Comdr Con Corp Cpl DR Dr Ens Gen Gov Hon Hosp Insp Lt MM MR MRS MS Maj Messrs Mlle Mme Mr Mrs Ms Msgr Op Ord Pfc Ph Prof Pvt Rep Reps Res Rev Rt Sen Sens Sfc Sgt Sr St Supt Surg #Misc symbols Mio Mrd bzw v vs usw d.h z.B u.a etc Mrd MwSt ggf d.J D.h m.E vgl I.F z.T sogen ff u.E g.U g.g.A c.-à-d Buchst u.s.w sog u.ä Std evtl Zt Chr u.U o.ä Ltd b.A z.Zt spp sen SA k.o jun i.H.v dgl dergl Co zzt usf s.p.a Dkr Corp bzgl BSE #Number indicators # add #NUMERIC_ONLY# after the word if it should ONLY be non-breaking when a 0-9 digit follows it No Nos Art Nr pp ca Ca #Ordinals are done with . in German - "1." = "1st" in English 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 Lingua-Sentence-1.100/share/nonbreaking_prefix.el0000644000076500000240000004121213054657247021662 0ustar cwhitenerstaff# Sigle letters in upper-case are usually abbreviations of names Α Β Γ Δ Ε Ζ Η Θ Ι Κ Λ Μ Ν Ξ Ο Π Ρ Σ Τ Υ Φ Χ Ψ Ω # Includes abbreviations for the Greek language compiled from various sources (Greek grammar books, Greek language related web content). Άθαν Έγχρ Έκθ Έσδ Έφ Όμ Α΄Έσδρ Α΄Έσδ Α΄Βασ Α΄Θεσ Α΄Ιω Α΄Κορινθ Α΄Κορ Α΄Μακκ Α΄Μακ Α΄Πέτρ Α΄Πέτ Α΄Παραλ Α΄Πε Α΄Σαμ Α΄Τιμ Α΄Χρον Α΄Χρ Α.Β.Α Α.Β Α.Ε Α.Κ.Τ.Ο Αέθλ Αέτ Αίλ.Δ Αίλ.Τακτ Αίσ Αββακ Αβυδ Αβ Αγάκλ Αγάπ Αγάπ.Αμαρτ.Σ Αγάπ.Γεωπ Αγαθάγγ Αγαθήμ Αγαθιν Αγαθοκλ Αγαθρχ Αγαθ Αγαθ.Ιστ Αγαλλ Αγαπητ Αγγ Αγησ Αγλ Αγορ.Κ Αγρο.Κωδ Αγρ.Εξ Αγρ.Κ Αγ.Γρ Αδριαν Αδρ Αετ Αθάν Αθήν Αθήν.Επιγρ Αθήν.Επιτ Αθήν.Ιατρ Αθήν.Μηχ Αθανάσ Αθαν Αθηνί Αθηναγ Αθηνόδ Αθ Αθ.Αρχ Αιλ Αιλ.Επιστ Αιλ.ΖΙ Αιλ.ΠΙ Αιλ.απ Αιμιλ Αιν.Γαζ Αιν.Τακτ Αισχίν Αισχίν.Επιστ Αισχ Αισχ.Αγαμ Αισχ.Αγ Αισχ.Αλ Αισχ.Ελεγ Αισχ.Επτ.Θ Αισχ.Ευμ Αισχ.Ικέτ Αισχ.Ικ Αισχ.Περσ Αισχ.Προμ.Δεσμ Αισχ.Πρ Αισχ.Χοηφ Αισχ.Χο Αισχ.απ ΑιτΕ Αιτ Αλκ Αλχιας Αμ.Π.Ο Αμβ Αμμών Αμ. Αν.Πειθ.Συμβ.Δικ Ανακρ Ανακ Αναμν.Τόμ Αναπλ Ανδ Ανθλγος Ανθστης Αντισθ Ανχης Αν Αποκ Απρ Απόδ Απόφ Απόφ.Νομ Απ Απ.Δαπ Απ.Διατ Απ.Επιστ Αριθ Αριστοτ Αριστοφ Αριστοφ.Όρν Αριστοφ.Αχ Αριστοφ.Βάτρ Αριστοφ.Ειρ Αριστοφ.Εκκλ Αριστοφ.Θεσμ Αριστοφ.Ιππ Αριστοφ.Λυσ Αριστοφ.Νεφ Αριστοφ.Πλ Αριστοφ.Σφ Αριστ Αριστ.Αθ.Πολ Αριστ.Αισθ Αριστ.Αν.Πρ Αριστ.Ζ.Ι Αριστ.Ηθ.Ευδ Αριστ.Ηθ.Νικ Αριστ.Κατ Αριστ.Μετ Αριστ.Πολ Αριστ.Φυσιογν Αριστ.Φυσ Αριστ.Ψυχ Αριστ.Ρητ Αρμεν Αρμ Αρχ.Εκ.Καν.Δ Αρχ.Ευβ.Μελ Αρχ.Ιδ.Δ Αρχ.Νομ Αρχ.Ν Αρχ.Π.Ε Αρ Αρ.Φορ.Μητρ Ασμ Ασμ.ασμ Αστ.Δ Αστ.Χρον Ασ Ατομ.Γνωμ Αυγ Αφρ Αχ.Νομ Α Α.Εγχ.Π Α.Κ.΄Υδρας Β΄Έσδρ Β΄Έσδ Β΄Βασ Β΄Θεσ Β΄Ιω Β΄Κορινθ Β΄Κορ Β΄Μακκ Β΄Μακ Β΄Πέτρ Β΄Πέτ Β΄Πέ Β΄Παραλ Β΄Σαμ Β΄Τιμ Β΄Χρον Β΄Χρ Β.Ι.Π.Ε Β.Κ.Τ Β.Κ.Ψ.Β Β.Μ Β.Ο.Α.Κ Β.Ο.Α Β.Ο.Δ Βίβλ Βαρ ΒεΘ Βι.Περ Βιπερ Βιργ Βλγ Βούλ Βρ Γ΄Βασ Γ΄Μακκ ΓΕΝμλ Γέν Γαλ Γεν Γλ Γν.Ν.Σ.Κρ Γνωμ Γν Γράμμ Γρηγ.Ναζ Γρηγ.Νύσ Γ Νοσ Γ' Ογκολ Γ.Ν Δ΄Βασ Δ.Β Δ.Δίκη Δ.Δίκ Δ.Ε.Σ Δ.Ε.Φ.Α Δ.Ε.Φ Δ.Εργ.Ν Δαμ Δαμ.μνημ.έργ Δαν Δασ.Κ Δεκ Δελτ.Δικ.Ε.Τ.Ε Δελτ.Νομ Δελτ.Συνδ.Α.Ε Δερμ Δευτ Δεύτ Δημοσθ Δημόκρ Δι.Δικ Διάτ Διαιτ.Απ Διαιτ Διαρκ.Στρατ Δικ Διοίκ.Πρωτ ΔιοικΔνη Διοικ.Εφ Διον.Αρ Διόρθ.Λαθ Δ.κ.Π Δνη Δν Δογμ.Όρος Δρ Δ.τ.Α Δτ ΔωδΝομ Δ.Περ Δ.Στρ ΕΔΠολ ΕΕυρΚ ΕΙΣ ΕΝαυτΔ ΕΣΑμΕΑ ΕΣΘ ΕΣυγκΔ ΕΤρΑξΧρΔ Ε.Φ.Ε.Τ Ε.Φ.Ι Ε.Φ.Ο.Επ.Α Εβδ Εβρ Εγκύκλ.Επιστ Εγκ Εε.Αιγ Εθν.Κ.Τ Εθν Ειδ.Δικ.Αγ.Κακ Εικ Ειρ.Αθ Ειρην.Αθ Ειρην Έλεγχ Ειρ Εισ.Α.Π Εισ.Ε Εισ.Ν.Α.Κ Εισ.Ν.Κ.Πολ.Δ Εισ.Πρωτ Εισηγ.Έκθ Εισ Εκκλ Εκκ Εκ Ελλ.Δνη Εν.Ε Εξ Επ.Αν Επ.Εργ.Δ Επ.Εφ Επ.Κυπ.Δ Επ.Μεσ.Αρχ Επ.Νομ Επίκτ Επίκ Επι.Δ.Ε Επιθ.Ναυτ.Δικ Επικ Επισκ.Ε.Δ Επισκ.Εμπ.Δικ Επιστ.Επετ.Αρμ Επιστ.Επετ Επιστ.Ιερ Επιτρ.Προστ.Συνδ.Στελ Επιφάν Επτ.Εφ Επ.Ιρ Επ.Ι Εργ.Ασφ.Νομ Ερμ.Α.Κ Ερμη.Σ Εσθ Εσπερ Ετρ.Δ Ευκλ Ευρ.Δ.Δ.Α Ευρ.Σ.Δ.Α Ευρ.ΣτΕ Ευρατόμ Ευρ.Άλκ Ευρ.Ανδρομ Ευρ.Βάκχ Ευρ.Εκ Ευρ.Ελ Ευρ.Ηλ Ευρ.Ηρακ Ευρ.Ηρ Ευρ.Ηρ.Μαιν Ευρ.Ικέτ Ευρ.Ιππόλ Ευρ.Ιφ.Α Ευρ.Ιφ.Τ Ευρ.Ι.Τ Ευρ.Κύκλ Ευρ.Μήδ Ευρ.Ορ Ευρ.Ρήσ Ευρ.Τρωάδ Ευρ.Φοίν Εφ.Αθ Εφ.Εν Εφ.Επ Εφ.Θρ Εφ.Θ Εφ.Ι Εφ.Κερ Εφ.Κρ Εφ.Λ Εφ.Ν Εφ.Πατ Εφ.Πειρ Εφαρμ.Δ.Δ Εφαρμ Εφεσ Εφημ Εφ Ζαχ Ζιγ Ζυ Ζχ ΗΕ.Δ Ημερ Ηράκλ Ηροδ Ησίοδ Ησ Η.Ε.Γ ΘΗΣ ΘΡ Θαλ Θεοδ Θεοφ Θεσ Θεόδ.Μοψ Θεόκρ Θεόφιλ Θουκ Θρ Θρ.Ε Θρ.Ιερ Θρ.Ιρ Ιακ Ιαν Ιβ Ιδθ Ιδ Ιεζ Ιερ Ιζ Ιησ Ιησ.Ν Ικ Ιλ Ιν Ιουδ Ιουστ Ιούδα Ιούλ Ιούν Ιπποκρ Ιππόλ Ιρ Ισίδ.Πηλ Ισοκρ Ισ.Ν Ιωβ Ιωλ Ιων Ιω ΚΟΣ ΚΟ.ΜΕ.ΚΟΝ ΚΠοινΔ ΚΠολΔ ΚαΒ Καλ Καλ.Τέχν ΚανΒ Καν.Διαδ Κατάργ Κλ ΚοινΔ Κολσ Κολ Κον Κορ Κος ΚριτΕπιθ ΚριτΕ Κριτ Κρ ΚτΒ ΚτΕ ΚτΠ Κυβ Κυπρ Κύριλ.Αλεξ Κύριλ.Ιερ Λεβ Λεξ.Σουίδα Λευϊτ Λευ Λκ Λογ ΛουκΑμ Λουκιαν Λουκ.Έρωτ Λουκ.Ενάλ.Διάλ Λουκ.Ερμ Λουκ.Εταιρ.Διάλ Λουκ.Ε.Δ Λουκ.Θε.Δ Λουκ.Ικ. Λουκ.Ιππ Λουκ.Λεξιφ Λουκ.Μεν Λουκ.Μισθ.Συν Λουκ.Ορχ Λουκ.Περ Λουκ.Συρ Λουκ.Τοξ Λουκ.Τυρ Λουκ.Φιλοψ Λουκ.Φιλ Λουκ.Χάρ Λουκ. Λουκ.Αλ Λοχ Λυδ Λυκ Λυσ Λωζ Λ1 Λ2 ΜΟΕφ Μάρκ Μέν Μαλ Ματθ Μα Μιχ Μκ Μλ Μμ Μον.Δ.Π Μον.Πρωτ Μον Μρ Μτ Μχ Μ.Βασ Μ.Πλ ΝΑ Ναυτ.Χρον Να Νδικ Νεεμ Νε Νικ ΝκΦ Νμ ΝοΒ Νομ.Δελτ.Τρ.Ελ Νομ.Δελτ Νομ.Σ.Κ Νομ.Χρ Νομ Νομ.Διεύθ Νοσ Ντ Νόσων Ν1 Ν2 Ν3 Ν4 Νtot Ξενοφ Ξεν Ξεν.Ανάβ Ξεν.Απολ Ξεν.Απομν Ξεν.Απομ Ξεν.Ελλ Ξεν.Ιέρ Ξεν.Ιππαρχ Ξεν.Ιππ Ξεν.Κυρ.Αν Ξεν.Κύρ.Παιδ Ξεν.Κ.Π Ξεν.Λακ.Πολ Ξεν.Οικ Ξεν.Προσ Ξεν.Συμπόσ Ξεν.Συμπ Ο΄ Οβδ Οβ ΟικΕ Οικ Οικ.Πατρ Οικ.Σύν.Βατ Ολομ Ολ Ολ.Α.Π Ομ.Ιλ Ομ.Οδ ΟπΤοιχ Οράτ Ορθ ΠΡΟ.ΠΟ Πίνδ Πίνδ.Ι Πίνδ.Νεμ Πίνδ.Ν Πίνδ.Ολ Πίνδ.Παθ Πίνδ.Πυθ Πίνδ.Π ΠαγΝμλγ Παν Παρμ Παροιμ Παρ Παυσ Πειθ.Συμβ ΠειρΝ Πελ ΠεντΣτρ Πεντ Πεντ.Εφ ΠερΔικ Περ.Γεν.Νοσ Πετ Πλάτ Πλάτ.Αλκ Πλάτ.Αντ Πλάτ.Αξίοχ Πλάτ.Απόλ Πλάτ.Γοργ Πλάτ.Ευθ Πλάτ.Θεαίτ Πλάτ.Κρατ Πλάτ.Κριτ Πλάτ.Λύσ Πλάτ.Μεν Πλάτ.Νόμ Πλάτ.Πολιτ Πλάτ.Πολ Πλάτ.Πρωτ Πλάτ.Σοφ. Πλάτ.Συμπ Πλάτ.Τίμ Πλάτ.Φαίδρ Πλάτ.Φιλ Πλημ Πλούτ Πλούτ.Άρατ Πλούτ.Αιμ Πλούτ.Αλέξ Πλούτ.Αλκ Πλούτ.Αντ Πλούτ.Αρτ Πλούτ.Ηθ Πλούτ.Θεμ Πλούτ.Κάμ Πλούτ.Καίσ Πλούτ.Κικ Πλούτ.Κράσ Πλούτ.Κ Πλούτ.Λυκ Πλούτ.Μάρκ Πλούτ.Μάρ Πλούτ.Περ Πλούτ.Ρωμ Πλούτ.Σύλλ Πλούτ.Φλαμ Πλ Ποιν.Δικ Ποιν.Δ Ποιν.Ν Ποιν.Χρον Ποιν.Χρ Πολ.Δ Πολ.Πρωτ Πολ Πολ.Μηχ Πολ.Μ Πρακτ.Αναθ Πρακτ.Ολ Πραξ Πρμ Πρξ Πρωτ Πρ Πρ.Αν Πρ.Λογ Πταισμ Πυρ.Καλ Πόλη Π.Δ Π.Δ.Άσμ ΡΜ.Ε Ρθ Ρμ Ρωμ ΣΠλημ Σαπφ Σειρ Σολ Σοφ Σοφ.Αντιγ Σοφ.Αντ Σοφ.Αποσ Σοφ.Απ Σοφ.Ηλέκ Σοφ.Ηλ Σοφ.Οιδ.Κολ Σοφ.Οιδ.Τύρ Σοφ.Ο.Τ Σοφ.Σειρ Σοφ.Σολ Σοφ.Τραχ Σοφ.Φιλοκτ Σρ Σ.τ.Ε Σ.τ.Π Στρ.Π.Κ Στ.Ευρ Συζήτ Συλλ.Νομολ Συλ.Νομ ΣυμβΕπιθ Συμπ.Ν Συνθ.Αμ Συνθ.Ε.Ε Συνθ.Ε.Κ Συνθ.Ν Σφν Σφ Σφ.Σλ Σχ.Πολ.Δ Σχ.Συντ.Ε Σωσ Σύντ Σ.Πληρ ΤΘ ΤΣ.Δ Τίτ Τβ Τελ.Ενημ Τελ.Κ Τερτυλ Τιμ Τοπ.Α Τρ.Ο Τριμ Τριμ.Πλ Τρ.Πλημ Τρ.Π.Δ Τ.τ.Ε Ττ Τωβ Υγ Υπερ Υπ Υ.Γ Φιλήμ Φιλιπ Φιλ Φλμ Φλ Φορ.Β Φορ.Δ.Ε Φορ.Δνη Φορ.Δ Φορ.Επ Φώτ Χρ.Ι.Δ Χρ.Ιδ.Δ Χρ.Ο Χρυσ Ψήφ Ψαλμ Ψαλ Ψλ Ωριγ Ωσ Ω.Ρ.Λ άγν άγν.ετυμολ άγ άκλ άνθρ άπ άρθρ άρν άρ άτ άψ ά έκδ έκφρ έμψ ένθ.αν έτ έ.α ίδ αβεστ αβησσ αγγλ αγγ αδημ αεροναυτ αερον αεροπ αθλητ αθλ αθροιστ αιγυπτ αιγ αιτιολ αιτ αι ακαδ ακκαδ αλβ αλλ αλφαβητ αμα αμερικ αμερ αμετάβ αμτβ αμφιβ αμφισβ αμφ αμ ανάλ ανάπτ ανάτ αναβ αναδαν αναδιπλασ αναδιπλ αναδρ αναλ αναν ανασυλλ ανατολ ανατομ ανατυπ ανατ αναφορ αναφ ανα.ε ανδρων ανθρωπολ ανθρωπ ανθ ανομ αντίτ αντδ αντιγρ αντιθ αντικ αντιμετάθ αντων αντ ανωτ ανόργ ανών αορ απαρέμφ απαρφ απαρχ απαρ απλολ απλοπ αποβ αποηχηροπ αποθ αποκρυφ αποφ απρμφ απρφ απρόσ απόδ απόλ απόσπ απόφ αραβοτουρκ αραβ αραμ αρβαν αργκ αριθμτ αριθμ αριθ αρκτικόλ αρκ αρμεν αρμ αρνητ αρσ αρχαιολ αρχιτεκτ αρχιτ αρχκ αρχ αρωμουν αρωμ αρ αρ.μετρ αρ.φ ασσυρ αστρολ αστροναυτ αστρον αττ αυστραλ αυτοπ αυτ αφγαν αφηρ αφομ αφρικ αχώρ αόρ α.α α/α α0 βαθμ βαθ βαπτ βασκ βεβαιωτ βεβ βεδ βενετ βεν βερβερ βιβλγρ βιολ βιομ βιοχημ βιοχ βλάχ βλ βλ.λ βοταν βοτ βουλγαρ βουλγ βούλ βραζιλ βρετον βόρ γαλλ γενικότ γενοβ γεν γερμαν γερμ γεωγρ γεωλ γεωμετρ γεωμ γεωπ γεωργ γλυπτ γλωσσολ γλωσσ γλ γνμδ γνμ γνωμ γοτθ γραμμ γραμ γρμ γρ γυμν δίδες δίκ δίφθ δαν δεικτ δεκατ δηλ δημογρ δημοτ δημώδ δημ διάγρ διάκρ διάλεξ διάλ διάσπ διαλεκτ διατρ διαφ διαχ διδα διεθν διεθ δικον διστ δισύλλ δισ διφθογγοπ δογμ δολ δοτ δρμ δρχ δρ(α) δωρ δ εβρ εγκλπ εδ εθνολ εθν ειδικότ ειδ ειδ.β εικ ειρ εισ εκατοστμ εκατοστ εκατστ.2 εκατστ.3 εκατ εκδ εκκλησ εκκλ εκ ελλην ελλ ελνστ ελπ εμβ εμφ εναλλ ενδ ενεργ ενεστ ενικ ενν εν εξέλ εξακολ εξομάλ εξ εο επέκτ επίδρ επίθ επίρρ επίσ επαγγελμ επανάλ επανέκδ επιθ επικ επιμ επιρρ επιστ επιτατ επιφ επών επ εργ ερμ ερρινοπ ερωτ ετρουσκ ετυμ ετ ευφ ευχετ εφ εύχρ ε.α ε/υ ε0 ζωγρ ζωολ ηθικ ηθ ηλεκτρολ ηλεκτρον ηλεκτρ ημίτ ημίφ ημιφ ηχηροπ ηχηρ ηχομιμ ηχ η θέατρ θεολ θετ θηλ θρακ θρησκειολ θρησκ θ ιαπων ιατρ ιδιωμ ιδ ινδ ιραν ισπαν ιστορ ιστ ισχυροπ ιταλ ιχθυολ ιων κάτ καθ κακοσ καν καρ κατάλ κατατ κατωτ κατ κα κελτ κεφ κινεζ κινημ κλητ κλιτ κλπ κλ κν κοινωνιολ κοινων κοπτ κουτσοβλαχ κουτσοβλ κπ κρ.γν κτγ κτην κτητ κτλ κτ κυριολ κυρ κύρ κ κ.ά κ.ά.π κ.α κ.εξ κ.επ κ.ε κ.λπ κ.λ.π κ.ού.κ κ.ο.κ κ.τ.λ κ.τ.τ κ.τ.ό λέξ λαογρ λαπ λατιν λατ λαϊκότρ λαϊκ λετ λιθ λογιστ λογοτ λογ λουβ λυδ λόγ λ λ.χ μέλλ μέσ μαθημ μαθ μαιευτ μαλαισ μαλτ μαμμων μεγεθ μεε μειωτ μελ μεξ μεσν μεσογ μεσοπαθ μεσοφ μετάθ μεταβτ μεταβ μετακ μεταπλ μεταπτωτ μεταρ μεταφορ μετβ μετεπιθ μετεπιρρ μετεωρολ μετεωρ μετον μετουσ μετοχ μετρ μετ μητρων μηχανολ μηχ μικροβιολ μογγολ μορφολ μουσ μπενελούξ μσνλατ μσν μτβ μτγν μτγ μτφρδ μτφρ μτφ μτχ μυθ μυκην μυκ μφ μ μ.ε μ.μ μ.π.ε μ.π.π μ0 ναυτ νεοελλ νεολατιν νεολατ νεολ νεότ νλατ νομ νορβ νοσ νότ ν ξ.λ οικοδ οικολ οικον οικ ολλανδ ολλ ομηρ ομόρρ ονομ ον οπτ ορθογρ ορθ οριστ ορυκτολ ορυκτ ορ οσετ οσκ ουαλ ουγγρ ουδ ουσιαστικοπ ουσιαστ ουσ πίν παθητ παθολ παθ παιδ παλαιοντ παλαιότ παλ παππων παράγρ παράγ παράλλ παράλ παραγ παρακ παραλ παραπ παρατ παρβ παρετυμ παροξ παρων παρωχ παρ παρ.φρ πατριδων πατρων πβ περιθ περιλ περιφρ περσ περ πιθ πληθ πληροφ ποδ ποιητ πολιτ πολλαπλ πολ πορτογαλ πορτ ποσ πρακριτ πρβλ πρβ πργ πρκμ πρκ πρλ προέλ προβηγκ προελλ προηγ προθεμ προπαραλ προπαροξ προπερισπ προσαρμ προσηγορ προσταχτ προστ προσφών προσ προτακτ προτ.Εισ προφ προχωρ πρτ πρόθ πρόσθ πρόσ πρότ πρ πρ.Εφ πτ πυ π π.Χ π.μ π.χ ρήμ ρίζ ρηματ ρητορ ριν ρουμ ρωμ ρωσ ρ σανσκρ σαξ σελ σερβοκρ σερβ σημασιολ σημδ σημειολ σημερ σημιτ σημ σκανδ σκυθ σκωπτ σλαβ σλοβ σουηδ σουμερ σουπ σπάν σπανιότ σπ σσ στατ στερ στιγμ στιχ στρέμ στρατιωτ στρατ στ συγγ συγκρ συγκ συμπερ συμπλεκτ συμπλ συμπροφ συμφυρ συμφ συνήθ συνίζ συναίρ συναισθ συνδετ συνδ συνεκδ συνηρ συνθετ συνθ συνοπτ συντελ συντομογρ συντ συν συρ σχημ σχ σύγκρ σύμπλ σύμφ σύνδ σύνθ σύντμ σύντ σ σ.π σ/β τακτ τελ τετρ τετρ.μ τεχνλ τεχνολ τεχν τεύχ τηλεπικ τηλεόρ τιμ τιμ.τομ τοΣ τον τοπογρ τοπων τοπ τοσκ τουρκ τοχ τριτοπρόσ τροποπ τροπ τσεχ τσιγγ ττ τυπ τόμ τόνν τ τ.μ τ.χλμ υβρ υπερθ υπερσ υπερ υπεύθ υποθ υποκορ υποκ υποσημ υποτ υποφ υποχωρ υπόλ υπόχρ υπ υστλατ υψόμ υψ φάκ φαρμακολ φαρμ φιλολ φιλοσ φιλοτ φινλ φοινικ φράγκ φρανκον φριζ φρ φυλλ φυσιολ φυσ φωνηεντ φωνητ φωνολ φων φωτογρ φ φ.τ.μ χαμιτ χαρτόσ χαρτ χασμ χαϊδ χγφ χειλ χεττ χημ χιλ χλγρ χλγ χλμ χλμ.2 χλμ.3 χλσγρ χλστγρ χλστμ χλστμ.2 χλστμ.3 χλ χργρ χρημ χρον χρ χφ χ.ε χ.κ χ.ο χ.σ χ.τ χ.χ ψευδ ψυχαν ψυχιατρ ψυχολ ψυχ ωκεαν όμ όν όπ.παρ όπ.π ό.π ύψ 1Βσ 1Εσ 1Θσ 1Ιν 1Κρ 1Μκ 1Πρ 1Πτ 1Τμ 2Βσ 2Εσ 2Θσ 2Ιν 2Κρ 2Μκ 2Πρ 2Πτ 2Τμ 3Βσ 3Ιν 3Μκ 4Βσ Lingua-Sentence-1.100/share/nonbreaking_prefix.en0000644000076500000240000000233113054657247021663 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A B C D E F G H I J K L M N O P Q R S T U V W X Y Z #List of titles. These are often followed by upper-case names, but do not indicate sentence breaks Adj Adm Adv Asst Bart Bldg Brig Bros Capt Cmdr Col Comdr Con Corp Cpl DR Dr Drs Ens Gen Gov Hon Hr Hosp Insp Lt MM MR MRS MS Maj Messrs Mlle Mme Mr Mrs Ms Msgr Op Ord Pfc Ph Prof Pvt Rep Reps Res Rev Rt Sen Sens Sfc Sgt Sr St Supt Surg #misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence) v vs i.e rev e.g #Numbers only. These should only induce breaks when followed by a numeric sequence # add NUMERIC_ONLY after the word for this function #This case is mostly for the english "No." which can either be a sentence of its own, or #if followed by a number, a non-breaking prefix No #NUMERIC_ONLY# Nos Art #NUMERIC_ONLY# Nr pp #NUMERIC_ONLY# Lingua-Sentence-1.100/share/nonbreaking_prefix.es0000644000076500000240000000253413054657247021675 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A B C D E F G H I J K L M N O P Q R S T U V W X Y Z #Abbreviations a.c aa.rr abrev adj adm admón afma afmas afmo afmos ag am ap apdo art arts arz arzbpo assn atte av avda bros bv cap caps cg cgo cia cit cl cm co col corp cos cta cte ctra cts cía cía d.c dcha dept depto dg dl dm doc docs dpt dpto dr dra dras dres dto dupdo ed ee.uu ej emma emmas emmo emmos entlo entpo esp etc ex excm excma excmas excmo excmos fasc fdo fig figs fil fol fra gr grs gral ha hnos hros hz ib ibid ibíd id ilm ilma ilmas ilmo ilmos iltre inc intr izq izqda izqdo jr kc kcal kg khz kl km kw lda ldo lib lic lim loc ltd ltda lám ma mg mhz min mm mons mr mrs ms mss mtro máx mín ntra ntro núm ob obpo op pd ph pje pl plc pm pp ppal pral prof prov pról ps pta ptas pte pts pza pág págs párr rda rdo ref reg rel rev revda revdo rma rmo rte s sa sdad sec secret seg sg sig smo sr sra sras sres srs srta ss.mm sta sto sust tech tel telf teléf ten tfono tlf t.v.e tít ud uds vda vdo vid vol vols vra vro vta íd ít Lingua-Sentence-1.100/share/nonbreaking_prefix.fi0000644000076500000240000000367113054657247021667 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. # Any single letter followed by a period is not a sentence ender A B C D E F G H I J K L M N O P Q R S T U V X Y Z Å Ä Ö a b c d e f g h i j k l m n o p q r s t u v x y z å ä ö # Abbreviations Alav Ao Arv Asiak Ay Britt Dem Dipl Dos Em Ent Esim Et Ev.Lut Fil Geol Harj Henk Hp Hra Hum Huom Ilt Inc It Jap Jne Joht Kand Kk Ko Kok Ks Kät Leht Lib Lis Lopull Luot Lut Lyh Länt Lääk Lääket M.m Maat Mahd Maist Mat Met Metsät Milj Min Mm Mol Muist Myöh Nim Nimim Nk Ns Nyk O.s Oik Ok Ol Op Os Ovh P.r Pat Per.sop Perj Pion Pit Pk Pl Po Pohj Pos Posit Pros Puh Puol Pys Pääll Rad Rak Raut Rek Rek.n:o Rek.nro Room.kat Ruots Rva S.o Sal Sar Sd Sit Siv Skand Sm So Sop Sos Sot Sp Spp Ss Subj Suom Säv Tait Tal Tarj Tav Tekn Tekst Teol Teoll Teor Tied Tiet Til Tms Tn Tod Toht Toim Torst Tp Tri Ts Tuom Tv Täyd Ugr Usk Vak Valt Valtiot Vanh Var Vars Vast Virk Vm Vnp Voim Vpj Vrt Vs Vv Yht Yks Yksit Yl Ylim Ym Yo Yp Yst alav ao arv asiak ay britt dem dipl dos em ent esim et ev.Lut fil geol harj henk hp hra hum huom ilt inc it jap jne joht kand kk ko kok ks kät leht lib lis lopull luot lut lyh länt lääk lääket m.m maat mahd maist mat met metsät milj min mm mol muist myöh nim nimim nk ns nyk o.s oik ok ol op os ovh p.r pat per.sop perj pion pit pk pl po pohj pos posit pros puh puol pys pääll rad rak raut rek rek.n:o rek.nro room.kat ruots rva s.o sal sar sd sit siv skand sm so sop sos sot sp spp ss subj suom säv tait tal tarj tav tekn tekst teol teoll teor tied tiet til tms tn tod toht toim torst tp tri ts tuom tv täyd ugr usk vak valt valtiot vanh var vars vast virk vm vnp voim vpj vrt vs vv yht yks yksit yl ylim ym yo yp yst #Number indicators # add #NUMERIC_ONLY# after the word if it should ONLY be non-breaking when a 0-9 digit follows it Lingua-Sentence-1.100/share/nonbreaking_prefix.fr0000644000076500000240000000175713054657247021703 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender #usually upper case letters are initials in a name #no French words end in single lower-case letters, so we throw those in too? A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z # Period-final abbreviation list for French A.C.N A.M art ann apr av auj lib B.P boul ca c.-à-d cf ch.-l chap contr C.P.I C.Q.F.D C.N C.N.S C.S dir éd e.g env al etc E.V ex fasc fém fig fr hab ibid id i.e inf LL.AA LL.AA.II LL.AA.RR LL.AA.SS L.D LL.EE LL.MM LL.MM.II.RR loc.cit masc MM ms N.B N.D.A N.D.L.R N.D.T n/réf NN.SS N.S N.D N.P.A.I p.c.c pl pp p.ex p.j P.S R.A.S R.-V R.P R.I.P SS S.S S.A S.A.I S.A.R S.A.S S.E sec sect sing S.M S.M.I.R sq sqq suiv sup suppl tél T.S.V.P vb vol vs X.O Z.I Lingua-Sentence-1.100/share/nonbreaking_prefix.hu0000644000076500000240000000274413054657247021705 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Á É Í Ó Ö Ő Ú Ü Ű #List of titles. These are often followed by upper-case names, but do not indicate sentence breaks Dr dr kb Kb vö Vö pl Pl ca Ca min Min max Max ún Ún prof Prof de De du Du Szt St #Numbers only. These should only induce breaks when followed by a numeric sequence # add NUMERIC_ONLY after the word for this function #This case is mostly for the english "No." which can either be a sentence of its own, or #if followed by a number, a non-breaking prefix # Month name abbreviations jan #NUMERIC_ONLY# Jan #NUMERIC_ONLY# Feb #NUMERIC_ONLY# feb #NUMERIC_ONLY# márc #NUMERIC_ONLY# Márc #NUMERIC_ONLY# ápr #NUMERIC_ONLY# Ápr #NUMERIC_ONLY# máj #NUMERIC_ONLY# Máj #NUMERIC_ONLY# jún #NUMERIC_ONLY# Jún #NUMERIC_ONLY# Júl #NUMERIC_ONLY# júl #NUMERIC_ONLY# aug #NUMERIC_ONLY# Aug #NUMERIC_ONLY# Szept #NUMERIC_ONLY# szept #NUMERIC_ONLY# okt #NUMERIC_ONLY# Okt #NUMERIC_ONLY# nov #NUMERIC_ONLY# Nov #NUMERIC_ONLY# dec #NUMERIC_ONLY# Dec #NUMERIC_ONLY# # Other abbreviations tel #NUMERIC_ONLY# Tel #NUMERIC_ONLY# Fax #NUMERIC_ONLY# fax #NUMERIC_ONLY# Lingua-Sentence-1.100/share/nonbreaking_prefix.is0000644000076500000240000000204313054657247021674 0ustar cwhitenerstaffno #NUMERIC_ONLY# No #NUMERIC_ONLY# nr #NUMERIC_ONLY# Nr #NUMERIC_ONLY# nR #NUMERIC_ONLY# NR #NUMERIC_ONLY# a b c d e f g h i j k l m n o p q r s t u v w x y z ^ í á ó æ A B C D E F G H I J K L M N O P Q R S T U V W X Y Z ab.fn a.fn afs al alm alg andh ath aths atr ao au aukaf áfn áhrl.s áhrs ákv.gr ákv bh bls dr e.Kr et ef efn ennfr eink end e.st erl fél fskj fh f.hl físl fl fn fo forl frb frl frh frt fsl fsh fs fsk fst f.Kr ft fv fyrrn fyrrv germ gm gr hdl hdr hf hl hlsk hljsk hljv hljóðv hr hv hvk holl Hos höf hk hrl ísl kaf kap Khöfn kk kg kk km kl klst kr kt kgúrsk kvk leturbr lh lh.nt lh.þt lo ltr mlja mljó millj mm mms m.fl miðm mgr mst mín nf nh nhm nl nk nmgr no núv nt o.áfr o.m.fl ohf o.fl o.s.frv ófn ób óákv.gr óákv pfn PR pr Ritstj Rvík Rvk samb samhlj samn samn sbr sek sérn sf sfn sh sfn sh s.hl sk skv sl sn so ss.us s.st samþ sbr shlj sign skál st st.s stk sþ teg tbl tfn tl tvíhlj tvt till to umr uh us uppl útg vb Vf vh vkf Vl vl vlf vmf 8vo vsk vth þt þf þjs þgf þlt þolm þm þml þýð Lingua-Sentence-1.100/share/nonbreaking_prefix.it0000644000076500000240000000165313054657247021703 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender #usually upper case letters are initials in a name #no Italian words end in single lower-case letters, so we throw those in too? A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z # Period-final abbreviation list from http://www.chass.utoronto.ca/~ngargano/corsi/corrisp/abbreviazioni.html a.c es all Amn Arch Avv Bcc c.a C.A.P Cc banc post c.c.p c.m Co c.p C.P corr c.s c.v Dott Dr ecc Egr e.p.c fatt Geom gg Id Ing int lett Mo Mons N.B ogg on pp p.c p.c p.c.c p.es p.f p.r P.S p.v P.T Prof racc Rag Rev ric Rif RP RSVP S.A acc S.B.F seg sgg ss Sig Sigg s.n.c Soc S.p.A Spett S.P.M S.r.l tel u.s V.P v.r v.s Lingua-Sentence-1.100/share/nonbreaking_prefix.lt0000644000076500000240000000350313054657247021702 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. # Any single letter followed by a period is not a sentence ender A Ą B C Č D E Ę Ė F G H I Į Y J K L M N O P R S Š T U Ų Ū V Z Ž a ą b c č d e ę ė f g h i į y j k l m n o p r s š t u ų ū v z ž # Abbreviations J.j J.em Nr Vt A.k A.s Adv Akad Aklg Akt Al Aps Apskr Apyg Asist Asmv Atsak Aut Avd B.k Biol Bkl Bot Bt Buv Chem Dail Dek Dir Dirig Doc Dr Drp Dėst Dš E.p Egz Eil Ekon El.p El.pšt Ež Fak Faks Filol Filos Gen Geol Gerb Gim Gv Gyd Insp Inž Istor K.a Kand Kat Kl Kln Kn Koresp Kpt Kr Kun Kyš L.e.p Ltn M.e M.m Mat Med Mgnt Mgr Min Mjr Mln Mlrd Mok Moksl Mokyt Mot Mst Mstl Nkt Ntk P.d P.m.e Pav Pavad Pirm Pl Plg Plk Pr Pr.Kr Prof Prok Prot Pss Pvz Pšt Red Rš Sav Saviv Sek Sekr Sen Sk Skg Skv Skyr Sp Spec Sr St Str Stud Sąs T.p T.y Techn Tel Teol Tūkst Up Upl Vad Ved Vet Virš Vlsč Vtv Vv Vyr Vyresn Zool Įn Įl Šv Š.m Šnek Šv Ž.ū Žml Žr j.j j.em nr vt a.k a.s adv akad aklg akt al aps apskr apyg asist asmv atsak aut avd b.k biol bkl bot bt buv chem dail dek dir dirig doc dr drp dėst dš e.p egz eil ekon el.p el.pšt ež fak faks filol filos gen geol gerb gim gv gyd insp inž istor k.a kand kat kl kln kn koresp kpt kr kun kyš l.e.p ltn m.e m.m mat med mgnt mgr min mjr mln mlrd mok moksl mokyt mot mst mstl nkt ntk p.d p.m.e pav pavad pirm pl plg plk pr pr.Kr prof prok prot pss pvz pšt red rš sav saviv sek sekr sen sk skg skv skyr sp spec sr st str stud sąs t.p t.y techn tel teol tūkst up upl vad ved vet virš vlsč vtv vv vyr vyresn zool Įn įl Šv š.m šnek šv ž.ū žml žr #Number indicators # add #NUMERIC_ONLY# after the word if it should ONLY be non-breaking when a 0-9 digit follows it Lingua-Sentence-1.100/share/nonbreaking_prefix.lv0000644000076500000240000000230713054657247021705 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A Ā B C Č D E Ē F G Ģ H I Ī J K Ķ L Ļ M N Ņ O P Q R S Š T U Ū V W X Y Z Ž #List of titles. These are often followed by upper-case names, but do not indicate sentence breaks dr Dr med prof Prof inž Inž ist.loc Ist.loc kor.loc Kor.loc v.i vietn Vietn #misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence) a.l t.p pārb Pārb vec Vec inv Inv sk Sk spec Spec vienk Vienk virz Virz māksl Māksl mūz Mūz akad Akad soc Soc galv Galv vad Vad sertif Sertif folkl Folkl hum Hum #Numbers only. These should only induce breaks when followed by a numeric sequence # add NUMERIC_ONLY after the word for this function #This case is mostly for the english "No." which can either be a sentence of its own, or #if followed by a number, a non-breaking prefix Nr #NUMERIC_ONLY# Lingua-Sentence-1.100/share/nonbreaking_prefix.nl0000644000076500000240000000305613054657247021677 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #Sources: http://nl.wikipedia.org/wiki/Lijst_van_afkortingen # http://nl.wikipedia.org/wiki/Aanspreekvorm # http://nl.wikipedia.org/wiki/Titulatuur_in_het_Nederlands_hoger_onderwijs #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A B C D E F G H I J K L M N O P Q R S T U V W X Y Z #List of titles. These are often followed by upper-case names, but do not indicate sentence breaks bacc bc bgen c.i dhr dr dr.h.c drs drs ds eint fa Fa fam gen genm ing ir jhr jkvr jr kand kol lgen lkol Lt maj Mej mevr Mme mr mr Mw o.b.s plv prof ritm tint Vz Z.D Z.D.H Z.E Z.Em Z.H Z.K.H Z.K.M Z.M z.v #misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence) #we seem to have a lot of these in dutch i.e.: i.p.v - in plaats van (in stead of) never ends a sentence a.g.v bijv bijz bv d.w.z e.c e.g e.k ev i.p.v i.s.m i.t.t i.v.m m.a.w m.b.t m.b.v m.h.o m.i m.i.v v.w.t #Numbers only. These should only induce breaks when followed by a numeric sequence # add NUMERIC_ONLY after the word for this function #This case is mostly for the english "No." which can either be a sentence of its own, or #if followed by a number, a non-breaking prefix Nr #NUMERIC_ONLY# Nrs nrs nr #NUMERIC_ONLY# Lingua-Sentence-1.100/share/nonbreaking_prefix.pl0000644000076500000240000000243713054657247021703 0ustar cwhitenerstaffadw afr akad al Al am amer arch art Art artyst astr austr bałt bdb bł bm br bryg bryt centr ces chem chiń chir c.k c.o cyg cyw cyt czes czw cd Cd czyt ćw ćwicz daw dcn dekl demokr det diec dł dn dot dol dop dost dosł h.c ds dst duszp dypl egz ekol ekon elektr em ew fab farm fot fr gat gastr geogr geol gimn głęb gm godz górn gosp gr gram hist hiszp hr Hr hot id in im iron jn kard kat katol k.k kk kol kl k.p.a kpc k.p.c kpt kr k.r krak k.r.o kryt kult laic łac niem woj nb np Nb Np pol pow m.in pt ps Pt Ps cdn jw ryc rys Ryc Rys tj tzw Tzw tzn zob ang ub ul pw pn pl al k n nr #NUMERIC_ONLY# Nr #NUMERIC_ONLY# ww wł ur zm żyd żarg żyw wył bp bp wyst tow Tow o sp Sp st spółdz Spółdz społ spółgł stoł stow Stoł Stow zn zew zewn zdr zazw zast zaw zał zal zam zak zakł zagr zach adw Adw lek Lek med mec Mec doc Doc dyw dyr Dyw Dyr inż Inż mgr Mgr dh dr Dh Dr p P red Red prof prok Prof Prok hab płk Płk nadkom Nadkom podkom Podkom ks Ks gen Gen por Por reż Reż przyp Przyp śp św śW Śp Św ŚW szer Szer pkt #NUMERIC_ONLY# str #NUMERIC_ONLY# tab #NUMERIC_ONLY# Tab #NUMERIC_ONLY# tel ust #NUMERIC_ONLY# par #NUMERIC_ONLY# poz pok oo oO Oo OO r #NUMERIC_ONLY# l #NUMERIC_ONLY# s #NUMERIC_ONLY# najśw Najśw A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Ś Ć Ż Ź Dz Lingua-Sentence-1.100/share/nonbreaking_prefix.pt0000644000076500000240000000340213054657247021704 0ustar cwhitenerstaff#File adapted for PT by H. Leal Fontes from the EN & DE versions published with moses-2009-04-13. Last update: 10.11.2009. #Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z #Roman Numerals. A dot after one of these is not a sentence break in Portuguese. I II III IV V VI VII VIII IX X XI XII XIII XIV XV XVI XVII XVIII XIX XX i ii iii iv v vi vii viii ix x xi xii xiii xiv xv xvi xvii xviii xix xx #List of titles. These are often followed by upper-case names, but do not indicate sentence breaks Adj Adm Adv Art Ca Capt Cmdr Col Comdr Con Corp Cpl DR DRA Dr Dra Dras Drs Eng Enga Engas Engos Ex Exo Exmo Fig Gen Hosp Insp Lda MM MR MRS MS Maj Mrs Ms Msgr Op Ord Pfc Ph Prof Pvt Rep Reps Res Rev Rt Sen Sens Sfc Sgt Sr Sra Sras Srs Sto Supt Surg adj adm adv art cit col con corp cpl dr dra dras drs eng enga engas engos ex exo exmo fig op prof sr sra sras srs sto #misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence) v vs i.e rev e.g #Numbers only. These should only induce breaks when followed by a numeric sequence # add NUMERIC_ONLY after the word for this function #This case is mostly for the english "No." which can either be a sentence of its own, or #if followed by a number, a non-breaking prefix No #NUMERIC_ONLY# Nos Art #NUMERIC_ONLY# Nr p #NUMERIC_ONLY# pp #NUMERIC_ONLY# Lingua-Sentence-1.100/share/nonbreaking_prefix.ro0000644000076500000240000000015013054657247021676 0ustar cwhitenerstaffA B C D E F G H I J K L M N O P Q R S T U V W X Y Z dpdv etc șamd M.Ap.N dl Dl d-na D-na dvs Dvs pt Pt Lingua-Sentence-1.100/share/nonbreaking_prefix.ru0000644000076500000240000000436613054657247021721 0ustar cwhitenerstaff; № №№ 0г 0га 0гг 0дм 0кг 0км 0л 0м 0мг 0мм 0см 0т 10-ый 11-ый 12-ый 1г 1га 1гг 1дм 1кг 1км 1л 1м 1мг 1мм 1см 1т 1-ый 2г 2га 2гг 2дм 2кг 2км 2л 2м 2мг 2мм 2-ой 2см 2т 3г 3га 3гг 3дм 3-ий 3кг 3км 3л 3м 3мг 3мм 3см 3т 4г 4га 4гг 4дм 4кг 4км 4л 4м 4мг 4мм 4см 4т 4-ый 5г 5га 5гг 5дм 5кг 5км 5л 5м 5мг 5мм 5см 5т 5-ый 6г 6га 6гг 6дм 6кг 6км 6л 6м 6мг 6мм 6-ой 6см 6т 7г 7га 7гг 7дм 7кг 7км 7л 7м 7мг 7мм 7-ой 7см 7т 8г 8га 8гг 8дм 8кг 8км 8л 8м 8мг 8мм 8-ой 8см 8т 9г 9га 9гг 9дм 9кг 9км 9л 9м 9мг 9мм 9см 9т 9-ый A B C Cв Cвв D E F G H I Iв Iвв J K L Lв Lвв M Mв Mвв N O P Q R S T U V Vв Vвв W X Xв Xвв Y Z А Б б/г б.г б/м б.м бн/о бомж Бр. Бтто. б/у б.у бульв в В вв вкл вм в/о вт в т. ч в/ч в.ч г Г га газ. гвтч гг г-жа гл гл. обр гм гн г-н гос грн д Д да дал дг дм до н. э до н.э доп до Р. Хр др д-р е Е ед Ё Ж ж/д ж. д З зав зам Зам и И и др им инд и.о И.О и пр исп Исп и т.д и т.п Й к К кал кап кв кг кит кл км км/час кол комн коп куб л Л лиц лл лм л. с л.с м М макс Мб м. б м.б мг мин мк мл млн Млн млрд Млрд мм м. пр н Н наб напр нач неуд ном нпр Н-то Нтто н. э н.э о о/ О обл обр общ ок ост отл п П п/г п.г пгт п. г. т пер Пер перераб пл п/м п. м пос пп п/пр пр приб просп Просп проф Проф п.т.ч р Р ред руб Руб с С сб св с/г с. г с.г сек сл. обр см См с/м см/сек соч ср ст стр Стр с/ч с.ч с.ш т Т табл Табл т/г т.г т. е т.е тел Тел тех т. к т.к т/м т.м т.н т. наз т. о т. обр тов тт туп тыс Тыс У уд у. е ул уст уч Ф физ Ф.И.О. фр х Х хор Ц ч Ч чел ч. п Ч. П ч. т. д Ш шт Щ Ы Ь э Э экз Ю Я Lingua-Sentence-1.100/share/nonbreaking_prefix.sk0000644000076500000240000000463413054657247021706 0ustar cwhitenerstaffBc Mgr RNDr PharmDr PhDr JUDr PaedDr ThDr Ing MUDr MDDr MVDr Dr ThLic PhD ArtD ThDr Dr DrSc CSs prof obr Obr Č č absol adj admin adr Adr adv advok afr ak akad akc akuz et al alch amer anat angl Angl anglosas anorg ap apod arch archeol archit arg art astr astrol astron atp atď austr Austr aut belg Belg bibl Bibl biol bot bud bás býv cest chem cirk csl čs Čs dat dep det dial diaľ dipl distrib dokl dosl dopr dram duš dv dvojčl dór ekol ekon el elektr elektrotech energet epic est etc etonym eufem európ Európ ev evid expr fa fam farm fem feud fil filat filoz fi fon form fot fr Fr franc Franc fraz fut fyz fyziol garb gen genet genpor geod geogr geol geom germ gr Gr gréc Gréc gréckokat hebr herald hist hlav hosp hromad hud hypok ident i.e ident imp impf indoeur inf inform instr int interj inšt inštr iron jap Jap jaz jedn juhoamer juhových juhozáp juž kanad Kanad kanc kapit kpt kart katastr knih kniž komp konj konkr kozmet krajč kresť kt kuch lat latinskoamer lek lex lingv lit litur log lok max Max maď Maď medzinár mest metr mil Mil min Min miner ml mld mn mod mytol napr nar Nar nasl nedok neg negat neklas nem Nem neodb neos neskl nesklon nespis nespráv neved než niekt niž nom náb nákl námor nár obch obj obv obyč obč občian odb odd ods ojed okr Okr opt opyt org os osob ot ovoc par part pejor pers pf Pf P.f p.f pl Plk pod podst pokl polit politol polygr pomn popl por porad porov posch potrav použ poz pozit poľ poľno poľnohosp poľov pošt pož prac predl pren prep preuk priezv Priezv privl prof práv príd príj prík príp prír prísl príslov príč psych publ pís písm pôv refl reg rep resp rozk rozlič rozpráv roč Roč ryb rádiotech rím samohl semest sev severoamer severových severozáp sg skr skup sl Sloven soc soch sociol sp spol Spol spoloč spoluhl správ spôs st star starogréc starorím s.r.o stol stor str stredoamer stredoškol subj subst superl sv sz súkr súp súvzť tal Tal tech tel Tel telef teles telev teol trans turist tuzem typogr tzn tzv ukaz ul Ul umel univ ust ved vedľ verb veter vin viď vl vod vodohosp pnl vulg vyj vys vysokoškol vzťaž vôb vých výd výrob výsk výsl výtv výtvar význ včel vš všeob zahr zar zariad zast zastar zastaráv zb zdravot združ zjemn zlat zn Zn zool zr zried zv záhr zák zákl zám záp západoeur zázn územ účt čast čes Čes čl čísl živ pr fak Kr p.n.l A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Lingua-Sentence-1.100/share/nonbreaking_prefix.sl0000644000076500000240000000042613054657247021702 0ustar cwhitenerstaffdr Dr itd itn št #NUMERIC_ONLY# Št #NUMERIC_ONLY# d jan Jan feb Feb mar Mar apr Apr jun Jun jul Jul avg Avg sept Sept sep Sep okt Okt nov Nov dec Dec tj Tj npr Npr sl Sl op Op gl Gl oz Oz prev dipl ing prim Prim cf Cf gl Gl A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Lingua-Sentence-1.100/share/nonbreaking_prefix.sv0000644000076500000240000000027013054657247021711 0ustar cwhitenerstaff#single upper case letter are usually initials A B C D E F G H I J K L M N O P Q R S T U V W X Y Z #misc abbreviations AB G VG dvs etc from iaf jfr kl kr mao mfl mm osv pga tex tom vs Lingua-Sentence-1.100/t/0000755000076500000240000000000013054657247014627 5ustar cwhitenerstaffLingua-Sentence-1.100/t/00-report-prereqs.dd0000644000076500000240000000501213054657247020345 0ustar cwhitenerstaffdo { my $x = { 'configure' => { 'requires' => { 'ExtUtils::MakeMaker' => '0', 'File::ShareDir::Install' => '0.06' } }, 'develop' => { 'requires' => { 'File::Spec' => '0', 'IO::Handle' => '0', 'IPC::Open3' => '0', 'Pod::Coverage::TrustPod' => '0', 'Test::CPAN::Changes' => '0.4', 'Test::CPAN::Meta' => '0', 'Test::CheckManifest' => '1.29', 'Test::CleanNamespaces' => '0.15', 'Test::EOL' => '0', 'Test::Kwalitee' => '1.22', 'Test::MinimumVersion' => '0', 'Test::More' => '0.88', 'Test::NoTabs' => '0', 'Test::Pod' => '1.41', 'Test::Pod::Coverage' => '1.08', 'Test::Pod::Spelling::CommonMistakes' => '1.000', 'Test::Spelling' => '0.12', 'Test::Version' => '1' } }, 'runtime' => { 'requires' => { 'Carp' => '0', 'File::ShareDir' => '1.02', 'File::Spec' => '0', 'Path::Tiny' => '0', 'perl' => '5.008001', 'strict' => '0', 'warnings' => '0' } }, 'test' => { 'recommends' => { 'CPAN::Meta' => '2.120900' }, 'requires' => { 'ExtUtils::MakeMaker' => '0', 'File::Spec' => '0', 'Test::More' => '0' } } }; $x; }Lingua-Sentence-1.100/t/00-report-prereqs.t0000644000076500000240000001271413054657247020230 0ustar cwhitenerstaff#!perl use strict; use warnings; # This test was generated by Dist::Zilla::Plugin::Test::ReportPrereqs 0.025 use Test::More tests => 1; use ExtUtils::MakeMaker; use File::Spec; # from $version::LAX my $lax_version_re = qr/(?: undef | (?: (?:[0-9]+) (?: \. | (?:\.[0-9]+) (?:_[0-9]+)? )? | (?:\.[0-9]+) (?:_[0-9]+)? ) | (?: v (?:[0-9]+) (?: (?:\.[0-9]+)+ (?:_[0-9]+)? )? | (?:[0-9]+)? (?:\.[0-9]+){2,} (?:_[0-9]+)? ) )/x; # hide optional CPAN::Meta modules from prereq scanner # and check if they are available my $cpan_meta = "CPAN::Meta"; my $cpan_meta_pre = "CPAN::Meta::Prereqs"; my $HAS_CPAN_META = eval "require $cpan_meta; $cpan_meta->VERSION('2.120900')" && eval "require $cpan_meta_pre"; ## no critic # Verify requirements? my $DO_VERIFY_PREREQS = 1; sub _max { my $max = shift; $max = ( $_ > $max ) ? $_ : $max for @_; return $max; } sub _merge_prereqs { my ($collector, $prereqs) = @_; # CPAN::Meta::Prereqs object if (ref $collector eq $cpan_meta_pre) { return $collector->with_merged_prereqs( CPAN::Meta::Prereqs->new( $prereqs ) ); } # Raw hashrefs for my $phase ( keys %$prereqs ) { for my $type ( keys %{ $prereqs->{$phase} } ) { for my $module ( keys %{ $prereqs->{$phase}{$type} } ) { $collector->{$phase}{$type}{$module} = $prereqs->{$phase}{$type}{$module}; } } } return $collector; } my @include = qw( ); my @exclude = qw( ); # Add static prereqs to the included modules list my $static_prereqs = do 't/00-report-prereqs.dd'; # Merge all prereqs (either with ::Prereqs or a hashref) my $full_prereqs = _merge_prereqs( ( $HAS_CPAN_META ? $cpan_meta_pre->new : {} ), $static_prereqs ); # Add dynamic prereqs to the included modules list (if we can) my ($source) = grep { -f } 'MYMETA.json', 'MYMETA.yml'; if ( $source && $HAS_CPAN_META && (my $meta = eval { CPAN::Meta->load_file($source) } ) ) { $full_prereqs = _merge_prereqs($full_prereqs, $meta->prereqs); } else { $source = 'static metadata'; } my @full_reports; my @dep_errors; my $req_hash = $HAS_CPAN_META ? $full_prereqs->as_string_hash : $full_prereqs; # Add static includes into a fake section for my $mod (@include) { $req_hash->{other}{modules}{$mod} = 0; } for my $phase ( qw(configure build test runtime develop other) ) { next unless $req_hash->{$phase}; next if ($phase eq 'develop' and not $ENV{AUTHOR_TESTING}); for my $type ( qw(requires recommends suggests conflicts modules) ) { next unless $req_hash->{$phase}{$type}; my $title = ucfirst($phase).' '.ucfirst($type); my @reports = [qw/Module Want Have/]; for my $mod ( sort keys %{ $req_hash->{$phase}{$type} } ) { next if $mod eq 'perl'; next if grep { $_ eq $mod } @exclude; my $file = $mod; $file =~ s{::}{/}g; $file .= ".pm"; my ($prefix) = grep { -e File::Spec->catfile($_, $file) } @INC; my $want = $req_hash->{$phase}{$type}{$mod}; $want = "undef" unless defined $want; $want = "any" if !$want && $want == 0; my $req_string = $want eq 'any' ? 'any version required' : "version '$want' required"; if ($prefix) { my $have = MM->parse_version( File::Spec->catfile($prefix, $file) ); $have = "undef" unless defined $have; push @reports, [$mod, $want, $have]; if ( $DO_VERIFY_PREREQS && $HAS_CPAN_META && $type eq 'requires' ) { if ( $have !~ /\A$lax_version_re\z/ ) { push @dep_errors, "$mod version '$have' cannot be parsed ($req_string)"; } elsif ( ! $full_prereqs->requirements_for( $phase, $type )->accepts_module( $mod => $have ) ) { push @dep_errors, "$mod version '$have' is not in required range '$want'"; } } } else { push @reports, [$mod, $want, "missing"]; if ( $DO_VERIFY_PREREQS && $type eq 'requires' ) { push @dep_errors, "$mod is not installed ($req_string)"; } } } if ( @reports ) { push @full_reports, "=== $title ===\n\n"; my $ml = _max( map { length $_->[0] } @reports ); my $wl = _max( map { length $_->[1] } @reports ); my $hl = _max( map { length $_->[2] } @reports ); if ($type eq 'modules') { splice @reports, 1, 0, ["-" x $ml, "", "-" x $hl]; push @full_reports, map { sprintf(" %*s %*s\n", -$ml, $_->[0], $hl, $_->[2]) } @reports; } else { splice @reports, 1, 0, ["-" x $ml, "-" x $wl, "-" x $hl]; push @full_reports, map { sprintf(" %*s %*s %*s\n", -$ml, $_->[0], $wl, $_->[1], $hl, $_->[2]) } @reports; } push @full_reports, "\n"; } } } if ( @full_reports ) { diag "\nVersions for all modules listed in $source (including optional ones):\n\n", @full_reports; } if ( @dep_errors ) { diag join("\n", "\n*** WARNING WARNING WARNING WARNING WARNING WARNING WARNING WARNING ***\n", "The following REQUIRED prerequisites were not satisfied:\n", @dep_errors, "\n" ); } pass; # vim: ts=4 sts=4 sw=4 et: Lingua-Sentence-1.100/t/Lingua-Sentence.t0000644000076500000240000001161213054657247017776 0ustar cwhitenerstaffuse strict; use warnings; use Lingua::Sentence; use Test::More tests => 32; # English split test string and array results my $splitter = Lingua::Sentence->new("en"); isa_ok($splitter,'Lingua::Sentence'); is($splitter->split('Foo'),"Foo\n",'Line break appended to single word'); is($splitter->split('This is a paragraph. It contains several sentences. "But why," you ask?'),"This is a paragraph.\nIt contains several sentences.\n\"But why,\" you ask?\n", 'Three test sentences split'); my @split = $splitter->split_array('This is a paragraph. It contains several sentences. "But why," you ask?'); is(@split,3,'Three elements in split array'); is($split[0],'This is a paragraph.','First array element correct'); is($split[1],'It contains several sentences.','Second array element correct'); is($split[2],'"But why," you ask?','Third array element correct'); @split = $splitter->split_array('Hey! Now.'); is(@split,2,'Two elements in split array'); is($split[0],'Hey!','First array element correct'); is($split[1],'Now.','Second array element correct'); @split = $splitter->split_array('Hey... Now.'); is(@split,2,'Two elements in split array'); is($split[0],'Hey...','First array element correct'); is($split[1],'Now.','Second array element correct'); @split = $splitter->split_array('Hey. Now.'); is(@split,2,'Two elements in split array'); is($split[0],'Hey.','First array element correct'); is($split[1],'Now.','Second array element correct'); @split = $splitter->split_array('Hey. Now.'); is(@split,2,'Two elements in split array'); is($split[0],'Hey.','First array element correct'); is($split[1],'Now.','Second array element correct'); # Create splitter for language that does not exist in current ISO 639-2 list my $xo_splitter = Lingua::Sentence->new("xo"); isa_ok($xo_splitter,'Lingua::Sentence'); is($xo_splitter->split('This is a paragraph. It contains several sentences. "But why," you ask?'),"This is a paragraph.\nIt contains several sentences.\n\"But why,\" you ask?\n", 'Three test sentences split'); # Once a member variable for the language code is defined this could be checked here # German split test my $de_splitter = Lingua::Sentence->new("de"); isa_ok($de_splitter,'Lingua::Sentence'); is($de_splitter->split('Nie hätte das passieren sollen. Dr. Soltan sagte: "Der Fluxcompensator war doch kalibriert!".'),"Nie hätte das passieren sollen.\nDr. Soltan sagte: \"Der Fluxcompensator war doch kalibriert!\".\n","German split test"); # Greek split test my $el_splitter = Lingua::Sentence->new("el"); isa_ok($el_splitter,'Lingua::Sentence'); is($el_splitter->split('Όλα τα συστήματα ανώτατης εκπαίδευσης σχεδιάζονται σε εθνικό επίπεδο. Η ΕΕ αναλαμβάνει κυρίως να συμβάλει στη βελτίωση της συγκρισιμότητας μεταξύ των διάφορων συστημάτων και να βοηθά φοιτητές και καθηγητές να μετακινούνται με ευκολία μεταξύ των συστημάτων των κρατών μελών.'),"Όλα τα συστήματα ανώτατης εκπαίδευσης σχεδιάζονται σε εθνικό επίπεδο.\nΗ ΕΕ αναλαμβάνει κυρίως να συμβάλει στη βελτίωση της συγκρισιμότητας μεταξύ των διάφορων συστημάτων και να βοηθά φοιτητές και καθηγητές να μετακινούνται με ευκολία μεταξύ των συστημάτων των κρατών μελών.\n","Greek split test"); # Portuguese split test my $pt_splitter = Lingua::Sentence->new("pt"); isa_ok($pt_splitter,'Lingua::Sentence'); is($pt_splitter->split('Isto é um parágrafo. Contém várias frases. «Mas porquê,» perguntas tu?'),"Isto é um parágrafo.\nContém várias frases.\n«Mas porquê,» perguntas tu?\n","Portuguese split test"); # Spanish split test my $es_splitter = Lingua::Sentence->new("es"); isa_ok($es_splitter,'Lingua::Sentence'); is($es_splitter->split('La UE ofrece una gran variedad de empleos en un entorno multinacional y multilingüe. La Oficina Europea de Selección de Personal (EPSO) se ocupa de la contratación, sobre todo mediante oposiciones generales.'),"La UE ofrece una gran variedad de empleos en un entorno multinacional y multilingüe.\nLa Oficina Europea de Selección de Personal (EPSO) se ocupa de la contratación, sobre todo mediante oposiciones generales.\n","Spanish split test"); # Split test with custom prefix file ok( -e 't/nonbreaking_prefix.de'); my $de_custom_splitter = Lingua::Sentence->new("de","t/nonbreaking_prefix.de"); isa_ok($de_custom_splitter,'Lingua::Sentence'); is($de_custom_splitter->split('Nie hätte das passieren sollen. Dr. Soltan sagte: "Der Fluxcompensator war doch kalibriert!".'),"Nie hätte das passieren sollen.\nDr. Soltan sagte: \"Der Fluxcompensator war doch kalibriert!\".\n","German split test"); Lingua-Sentence-1.100/t/nonbreaking_prefix.de0000644000076500000240000000335013054657247021014 0ustar cwhitenerstaff#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker. #Special cases are included for prefixes that ONLY appear before 0-9 numbers. #any single upper case letter followed by a period is not a sentence ender (excluding I occasionally, but we leave it in) #usually upper case letters are initials in a name #no german words end in single lower-case letters, so we throw those in too. A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z #Roman Numerals. A dot after one of these is not a sentence break in German. I II III IV V VI VII VIII IX X XI XII XIII XIV XV XVI XVII XVIII XIX XX i ii iii iv v vi vii viii ix x xi xii xiii xiv xv xvi xvii xviii xix xx #Titles and Honorifics Adj Adm Adv Asst Bart Bldg Brig Bros Capt Cmdr Col Comdr Con Corp Cpl DR Dr Ens Gen Gov Hon Hosp Insp Lt MM MR MRS MS Maj Messrs Mlle Mme Mr Mrs Ms Msgr Op Ord Pfc Ph Prof Pvt Rep Reps Res Rev Rt Sen Sens Sfc Sgt Sr St Supt Surg #Misc symbols Mio Mrd bzw v vs usw d.h z.B u.a etc Mrd MwSt ggf d.J D.h m.E vgl I.F z.T sogen ff u.E g.U g.g.A c.-à-d Buchst u.s.w sog u.ä Std evtl Zt Chr u.U o.ä Ltd b.A z.Zt spp sen SA k.o jun i.H.v dgl dergl Co zzt usf s.p.a Dkr Corp bzgl BSE #Number indicators # add #NUMERIC_ONLY# after the word if it should ONLY be non-breaking when a 0-9 digit follows it No Nos Art Nr pp ca Ca #Ordinals are done with . in German - "1." = "1st" in English 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 Lingua-Sentence-1.100/xt/0000755000076500000240000000000013054657247015017 5ustar cwhitenerstaffLingua-Sentence-1.100/xt/author/0000755000076500000240000000000013054657247016321 5ustar cwhitenerstaffLingua-Sentence-1.100/xt/author/00-compile.t0000644000076500000240000000254613054657247020362 0ustar cwhitenerstaffuse 5.006; use strict; use warnings; # this test was generated with Dist::Zilla::Plugin::Test::Compile 2.056 use Test::More; plan tests => 2; my @module_files = ( 'Lingua/Sentence.pm' ); # no fake home requested my @switches = ( -d 'blib' ? '-Mblib' : '-Ilib', ); use File::Spec; use IPC::Open3; use IO::Handle; open my $stdin, '<', File::Spec->devnull or die "can't open devnull: $!"; my @warnings; for my $lib (@module_files) { # see L my $stderr = IO::Handle->new; diag('Running: ', join(', ', map { my $str = $_; $str =~ s/'/\\'/g; q{'} . $str . q{'} } $^X, @switches, '-e', "require q[$lib]")) if $ENV{PERL_COMPILE_TEST_DEBUG}; my $pid = open3($stdin, '>&STDERR', $stderr, $^X, @switches, '-e', "require q[$lib]"); binmode $stderr, ':crlf' if $^O eq 'MSWin32'; my @_warnings = <$stderr>; waitpid($pid, 0); is($?, 0, "$lib loaded ok"); shift @_warnings if @_warnings and $_warnings[0] =~ /^Using .*\bblib/ and not eval { require blib; blib->VERSION('1.01') }; if (@_warnings) { warn @_warnings; push @warnings, @_warnings; } } is(scalar(@warnings), 0, 'no warnings found') or diag 'got warnings: ', ( Test::More->can('explain') ? Test::More::explain(\@warnings) : join("\n", '', @warnings) ); Lingua-Sentence-1.100/xt/author/clean-namespaces.t0000644000076500000240000000036113054657247021705 0ustar cwhitenerstaffuse strict; use warnings; # this test was generated with Dist::Zilla::Plugin::Test::CleanNamespaces 0.006 use Test::More 0.94; use Test::CleanNamespaces 0.15; subtest all_namespaces_clean => sub { all_namespaces_clean() }; done_testing; Lingua-Sentence-1.100/xt/author/eol.t0000644000076500000240000000056413054657247017272 0ustar cwhitenerstaffuse strict; use warnings; # this test was generated with Dist::Zilla::Plugin::Test::EOL 0.19 use Test::More 0.88; use Test::EOL; my @files = ( 'lib/Lingua/Sentence.pm', 't/00-report-prereqs.dd', 't/00-report-prereqs.t', 't/Lingua-Sentence.t', 't/nonbreaking_prefix.de' ); eol_unix_ok($_, { trailing_whitespace => 1 }) foreach @files; done_testing; Lingua-Sentence-1.100/xt/author/no-tabs.t0000644000076500000240000000053213054657247020051 0ustar cwhitenerstaffuse strict; use warnings; # this test was generated with Dist::Zilla::Plugin::Test::NoTabs 0.15 use Test::More 0.88; use Test::NoTabs; my @files = ( 'lib/Lingua/Sentence.pm', 't/00-report-prereqs.dd', 't/00-report-prereqs.t', 't/Lingua-Sentence.t', 't/nonbreaking_prefix.de' ); notabs_ok($_) foreach @files; done_testing; Lingua-Sentence-1.100/xt/author/pod-coverage.t0000644000076500000240000000171313054657247021063 0ustar cwhitenerstaff#!perl # This file was automatically generated by Dist::Zilla::Plugin::Test::Pod::Coverage::Configurable. use Test::Pod::Coverage 1.08; use Test::More 0.88; BEGIN { if ( $] <= 5.008008 ) { plan skip_all => 'These tests require Pod::Coverage::TrustPod, which only works with Perl 5.8.9+'; } } use Pod::Coverage::TrustPod; my %skip = map { $_ => 1 } qw( ); my @modules; for my $module ( all_modules() ) { next if $skip{$module}; push @modules, $module; } plan skip_all => 'All the modules we found were excluded from POD coverage test.' unless @modules; plan tests => scalar @modules; my %trustme = (); my @also_private; for my $module ( sort @modules ) { pod_coverage_ok( $module, { coverage_class => 'Pod::Coverage::TrustPod', also_private => \@also_private, trustme => $trustme{$module} || [], }, "pod coverage for $module" ); } done_testing(); Lingua-Sentence-1.100/xt/author/pod-spell.t0000644000076500000240000000077113054657247020412 0ustar cwhitenerstaffuse strict; use warnings; use Test::More; # generated by Dist::Zilla::Plugin::Test::PodSpelling 2.007004 use Test::Spelling 0.12; use Pod::Wordlist; set_spell_cmd('aspell list'); add_stopwords(); all_pod_files_spelling_ok( qw( bin lib ) ); __DATA__ Achim Bas CPAN Chase Digital Europarl Fontes Gim Hil Jes Josh Kathrin Koehn Leal Lingua MERCHANTABILITY Nonbreaking Philip Philipp Road Rozema Ruopp Schroeder Sentence Silk Whitener achimru and capoeirab lib nez nonbreaking preceeding rio splitter Lingua-Sentence-1.100/xt/author/pod-syntax.t0000644000076500000240000000025213054657247020613 0ustar cwhitenerstaff#!perl # This file was automatically generated by Dist::Zilla::Plugin::PodSyntaxTests. use strict; use warnings; use Test::More; use Test::Pod 1.41; all_pod_files_ok(); Lingua-Sentence-1.100/xt/author/test-version.t0000644000076500000240000000063713054657247021156 0ustar cwhitenerstaffuse strict; use warnings; use Test::More; # generated by Dist::Zilla::Plugin::Test::Version 1.09 use Test::Version; my @imports = qw( version_all_ok ); my $params = { is_strict => 0, has_version => 1, multiple => 0, }; push @imports, $params if version->parse( $Test::Version::VERSION ) >= version->parse('1.002'); Test::Version->import(@imports); version_all_ok; done_testing; Lingua-Sentence-1.100/xt/release/0000755000076500000240000000000013054657247016437 5ustar cwhitenerstaffLingua-Sentence-1.100/xt/release/changes_has_content.t0000644000076500000240000000201113054657247022613 0ustar cwhitenerstaff#!perl use Test::More tests => 2; note 'Checking Changes'; my $changes_file = 'Changes'; my $newver = '1.100'; my $trial_token = '-TRIAL'; SKIP: { ok(-e $changes_file, "$changes_file file exists") or skip 'Changes is missing', 1; ok(_get_changes($newver), "$changes_file has content for $newver"); } done_testing; # _get_changes copied and adapted from Dist::Zilla::Plugin::Git::Commit # by Jerome Quelin sub _get_changes { my $newver = shift; # parse changelog to find commit message open(my $fh, '<', $changes_file) or die "cannot open $changes_file: $!"; my $changelog = join('', <$fh>); close $fh; my @content = grep { /^$newver(?:$trial_token)?(?:\s+|$)/ ... /^\S/ } # from newver to un-indented split /\n/, $changelog; shift @content; # drop the version line # drop unindented last line and trailing blank lines pop @content while ( @content && $content[-1] =~ /^(?:\S|\s*$)/ ); # return number of non-blank lines return scalar @content; } Lingua-Sentence-1.100/xt/release/distmeta.t0000644000076500000240000000017213054657247020436 0ustar cwhitenerstaff#!perl # This file was automatically generated by Dist::Zilla::Plugin::MetaTests. use Test::CPAN::Meta; meta_yaml_ok(); Lingua-Sentence-1.100/xt/release/kwalitee.t0000644000076500000240000000027513054657247020435 0ustar cwhitenerstaff# this test was generated with Dist::Zilla::Plugin::Test::Kwalitee 2.12 use strict; use warnings; use Test::More 0.88; use Test::Kwalitee 1.21 'kwalitee_ok'; kwalitee_ok(); done_testing; Lingua-Sentence-1.100/xt/release/minimum-version.t0000644000076500000240000000027013054657247021761 0ustar cwhitenerstaff#!perl use Test::More; eval "use Test::MinimumVersion"; plan skip_all => "Test::MinimumVersion required for testing minimum versions" if $@; all_minimum_version_from_metayml_ok();