Lingua-Sentence-1.05/0000755000175000017500000000000012254666223013354 5ustar achimachimLingua-Sentence-1.05/lib/0000755000175000017500000000000012254666223014122 5ustar achimachimLingua-Sentence-1.05/lib/Lingua/0000755000175000017500000000000012254666223015341 5ustar achimachimLingua-Sentence-1.05/lib/Lingua/Sentence.pm0000644000175000017500000002102412254663775017453 0ustar achimachimpackage Lingua::Sentence; use 5.008008; use strict; use warnings; use Carp qw(croak); use File::ShareDir 'dist_dir'; our $VERSION = '1.05'; # Preloaded methods go here. sub new { ref(my $class= shift) and croak "Class name needed"; my $langid = shift; if($langid !~ /^[a-z][a-z]$/) { croak "Invalid language id: $langid"; } my $prefixfile = shift; # Try loading nonbreaking prefix file specified in constructor my $dir = dist_dir('Lingua-Sentence'); if(defined($prefixfile)) { if(!(-e $prefixfile)) { print STDERR "WARNING: Specified prefix file '$prefixfile' does not exist, attempting fall-back to $langid version...\n"; $prefixfile = "$dir/nonbreaking_prefix.$langid"; } } else { $prefixfile = "$dir/nonbreaking_prefix.$langid"; } my %NONBREAKING_PREFIX; #default back to English if we don't have a language-specific prefix file if (!(-e $prefixfile)) { $prefixfile = "$dir/nonbreaking_prefix.en"; print STDERR "WARNING: No known abbreviations for language '$langid', attempting fall-back to English version...\n"; die ("ERROR: No abbreviations files found in $dir\n") unless (-e $prefixfile); } if (-e "$prefixfile") { open(PREFIX, "<:utf8", "$prefixfile"); while () { my $item = $_; chomp($item); if (($item) && (substr($item,0,1) ne "#")) { if ($item =~ /(.*)[\s]+(\#NUMERIC_ONLY\#)/) { $NONBREAKING_PREFIX{$1} = 2; } else { $NONBREAKING_PREFIX{$item} = 1; } } } close(PREFIX); } my $self = { LangID => $langid, Nonbreaking => \%NONBREAKING_PREFIX }; bless $self,$class; return $self; } 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/([?!]) +([\'\"\(\[\¿\¡\p{IsPi}]*[\p{IsUpper}])/$1\n$2/g; #multi-dots followed by sentence starters $text =~ s/(\.[\.]+) +([\'\"\(\[\¿\¡\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}]+) +([\'\"\(\[\¿\¡\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/([?!\.]) +([\'\"\(\[\¿\¡\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] =~ /^([ ]*[\'\"\(\[\¿\¡\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-1.05/t/0000755000175000017500000000000012254666223013617 5ustar achimachimLingua-Sentence-1.05/t/Lingua-Sentence.t0000644000175000017500000001246712103036430016757 0ustar achimachim# Before `make install' is performed this script should be runnable with # `make test'. After `make install' it should work as `perl Lingua-Sentence.t' ######################### # change 'tests => 1' to 'tests => last_test_to_print'; use Test::More tests => 33; BEGIN { use_ok('Lingua::Sentence') }; ######################### # Insert your test code below, the Test::More module is use()ed here so read # its man page ( perldoc Test::More ) for help writing this test script. use Lingua::Sentence; # 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-1.05/t/nonbreaking_prefix.de0000644000175000017500000000335012102557152017774 0ustar achimachim#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-1.05/COPYING0000644000175000017500000001674312103013251014376 0ustar achimachim 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. Lingua-Sentence-1.05/MANIFEST.SKIP0000644000175000017500000000014112102557152015236 0ustar achimachim# Version control files \.svn # Build files ^Makefile$ ^Makefile.old$ ^blib/ # Editor files ~$ Lingua-Sentence-1.05/README0000644000175000017500000000232312254664067014240 0ustar achimachimLingua-Sentence version 1.05 ============================ 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. The module uses punctuation and capitalization clues to split paragraphs into an newline-separated string with one sentence per line. The module provides support for Catalan, English, German, Portuguese, Spanish, Italian, French, Dutch and Greek. Optionally files providing hints for other languages can be provided. INSTALLATION To install this module type the following: perl Makefile.PL make make test make install DEPENDENCIES This module requires these other modules and libraries: Carp; File::ShareDir; Test::More COPYRIGHT AND LICENCE Copyright (C) 2013 by Digital Silk Road Portions Copyright (C) 2005 by Philip Koehn and Josh Schroeder (used with permission) Portuguese nonbreaking prefix file copyright (C) 2009 by Hilário Leal Fontes (used with permission) This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.8.8 or, at your option, any later version of Perl 5 you may have available. Lingua-Sentence-1.05/Makefile.PL0000644000175000017500000000040112102557152015311 0ustar achimachimuse inc::Module::Install; # Define metadata name 'Lingua-Sentence'; all_from 'lib/Lingua/Sentence.pm'; # Dependencies requires 'Carp' => 0; requires 'File::ShareDir' => '1.02'; test_requires 'Test::More' => '0.47'; install_share; WriteAll; Lingua-Sentence-1.05/share/0000755000175000017500000000000012254666223014456 5ustar achimachimLingua-Sentence-1.05/share/nonbreaking_prefix.da0000644000175000017500000001306012254642353020634 0ustar achimachim#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-1.05/share/nonbreaking_prefix.sv0000644000175000017500000000027012103012016020653 0ustar achimachim#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-1.05/share/nonbreaking_prefix.lv0000644000175000017500000000230712103010325020650 0ustar achimachim#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-1.05/share/nonbreaking_prefix.fi0000644000175000017500000000367112254642353020655 0ustar achimachim#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-1.05/share/nonbreaking_prefix.sl0000644000175000017500000000042612103012016020644 0ustar achimachimdr 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-1.05/share/nonbreaking_prefix.is0000644000175000017500000000204312103012004020633 0ustar achimachimno #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-1.05/share/nonbreaking_prefix.ru0000644000175000017500000000436612103012016020663 0ustar achimachim; № №№ 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-1.05/share/nonbreaking_prefix.cs0000644000175000017500000000354512103011774020652 0ustar achimachimBc 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-1.05/share/nonbreaking_prefix.sk0000644000175000017500000000463412103012016020650 0ustar achimachimBc 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-1.05/share/nonbreaking_prefix.nl0000644000175000017500000000305612102557152020657 0ustar achimachim#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-1.05/share/nonbreaking_prefix.it0000644000175000017500000000165312102557152020663 0ustar achimachim#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-1.05/share/nonbreaking_prefix.ca0000644000175000017500000000222212102557152020623 0ustar achimachim#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-1.05/share/nonbreaking_prefix.el0000644000175000017500000004121212254646734020657 0ustar achimachim# 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-1.05/share/nonbreaking_prefix.pl0000644000175000017500000000243712103012014020643 0ustar achimachimadw 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-1.05/share/nonbreaking_prefix.pt0000644000175000017500000000340212102557152020664 0ustar achimachim#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-1.05/share/nonbreaking_prefix.hu0000644000175000017500000000274412103010325020650 0ustar achimachim#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-1.05/share/nonbreaking_prefix.ro0000644000175000017500000000015012103012016020640 0ustar achimachimA 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-1.05/share/nonbreaking_prefix.es0000644000175000017500000000253412102557152020655 0ustar achimachim#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-1.05/share/nonbreaking_prefix.de0000644000175000017500000000335012102557152020633 0ustar achimachim#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-1.05/share/nonbreaking_prefix.en0000644000175000017500000000233112102557152020643 0ustar achimachim#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-1.05/share/nonbreaking_prefix.fr0000644000175000017500000000175712102557152020663 0ustar achimachim#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-1.05/share/nonbreaking_prefix.lt0000644000175000017500000000350312254642353020670 0ustar achimachim#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-1.05/Changes0000644000175000017500000000160212254663611014644 0ustar achimachimRevision history for Perl extension Lingua::Sentence. 1.05 Dec 19, 2013 - added language support for Danish, Finnish, Lithuanian and updated language support for Greek 1.04 Fri Feb 01 15:30:00 2013 - 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 Sat Dec 04 17:40:00 2010 - added language support for Catalan and Dutch - update language support for Spanish 1.02 Wed July 07 11:47:00 2010 - added language support for French, Italian, Spanish - switched to File::ShareDir to access nonbreaking prefix files 1.00 Thu Feb 18 15:07:00 2010 - original version