poliqarpr-corpus 1.0.1

data/README.txt

@@ -0,0 +1,71 @@
+= poliqarpr-corpus
+
+* http://github.com/apohllo/poliqarpr-corpus
+* http://korpus.pl/index.php?page=download
+
+== DESCRIPTION:
+
+Default corpus for poliqarpr (Ruby client for Poliqarp server).
+
+
+== FEATURES/PROBLEMS:
+
+* Default corpus allows to test the poliqarpr Ruby client without need to 
+  manually download or create the corpus.
+
+== SYNOPSIS:
+
+Poliqarpr is Ruby client for Poliqarp corpus server. The default corpus
+for Poliqarpr is used in examples and testing.
+ 
+
+== REQUIREMENTS:
+
+* poliqarpr (sudo gem install poliqarpr)
+* Poliqarp server (only C implementation http://poliqarp.sourceforge.net/)
+
+== INSTALL:
+ 
+You need RubyGems v. 1.2 
+
+* gem -v 
+* 1.2.0 #=> ok
+
+You need the gemcutter.org repository to be added to your sources list:
+
+* gem sources -a http://gemcutter.org
+
+Then you can type:
+
+* sudo gem install poliqarpr-corpus
+
+== BASIC USAGE: 
+
+Require the gem:
+
+  require 'poliaqarpr'
+
+Create the server client and open the default corpus
+
+  client = Poliqarp::Client.new
+  client.open_corpus :default
+
+Query the corpus for given segment
+  
+  result = client.find("kot")
+  result[0].to_s 
+
+Remember to close the client on exit
+  
+  client.close
+
+== LICENSE:
+ 
+The sample corpus ("frek" form
+http://korpus.pl/index.php?page=download) is distributed under
+the GNU GPL license v 2.0
+http://www.gnu.org/licenses/old-licenses/gpl-2.0.html. 
+
+== FEEDBACK
+
+* mailto:apohllo@o2.pl

data/Rakefile

@@ -0,0 +1,23 @@
+task :default => [:install]
+
+$gem_name = "poliqarpr-corpus"
+
+desc "Build the gem"
+task :build do
+  sh "gem build #$gem_name.gemspec"
+end
+
+desc "Install the library at local machnie"
+task :install => :build do 
+  sh "sudo gem install #$gem_name -l"
+end
+
+desc "Uninstall the library from local machnie"
+task :uninstall do
+  sh "sudo gem uninstall #$gem_name"
+end
+
+desc "Clean"
+task :clean do
+  sh "rm #$gem_name*.gem" 
+end

data/corpus/frek.cdf

@@ -0,0 +1,4 @@
+version = 1
+endianness = little-endian
+indices = oda
+index-granularity = 1024

data/corpus/frek.cfg

@@ -0,0 +1,100 @@
+# Config file format for Oasis release
+# Config version 1.0
+
+# The new startup section may contain any command normally accepted by the shell
+
+[ALIASES]
+
+masc = m1|m2|m3
+verb = pact|ppas|winien|praet|bedzie|fin|impt|aglt|ger|imps|inf|pant|pcon
+noun = subst|depr|xxs|ger|ppron12|ppron3
+pron = ppron12|ppron3|siebie
+
+
+[ATTR]
+
+number			= sg pl
+case			= nom gen dat acc inst loc voc
+gender			= m1 m2 m3 f n
+person			= pri sec ter
+degree			= pos comp sup
+aspect			= imperf perf
+negation		= aff neg
+accommodability		= congr rec
+accentability		= akc nakc
+post-prepositionality	= npraep praep
+agglutination		= agl nagl
+vocalicity		= nwok wok
+
+# Parts of speech no longer need forward declarations, this was inconvenient and ugly.
+# Also, any attribute may be optional so a declaration such as:
+# foo = [bar] [froz] fred [wilma]
+# should no longer cause problems and ctags with such attributes now parse correctly regardless
+# of presence or absence of any optional attribute
+
+[POS]
+
+adja	=
+adjp	=
+conj	=
+interp	= 
+pred	=
+xxx	=
+adv	= degree
+imps	= aspect
+inf	= aspect
+pant	= aspect
+pcon	= aspect
+qub	= [vocalicity]
+prep	= case [vocalicity]
+siebie	= case
+subst	= number case gender
+depr	= number case gender
+xxs	= number case gender
+ger	= number case gender aspect negation
+ppron12	= number case gender person [accentability]
+ppron3	= number case gender person [accentability] [post-prepositionality]
+num	= number case gender [accommodability]
+adj	= number case gender degree
+pact	= number case gender aspect negation
+ppas	= number case gender aspect negation
+winien	= number gender aspect
+praet	= number gender aspect [agglutination]
+bedzie	= number person aspect
+fin	= number person aspect
+impt	= number person aspect
+aglt	= number person aspect vocalicity
+ign     =
+
+# Named entities replaced old 'special' attributes, name changed mostly because of
+# unification of 'named-thing' handling code into one named-entity thing
+# Entity aliasing allows for any existing entity to be seen under different name
+#
+# FCQP provides four builtin entities:
+#    entity-current
+#    entity-base
+#    entity-tag
+#    entity-pos
+
+[NAMED-ENTITY]
+
+entity-orth		= orth
+entity-base		= base
+entity-tag		= tag
+entity-pos		= pos
+
+# Old 'aliases' for attribute names
+
+pos			= flex
+number			= numb nmb
+case			= cas
+gender			= gnd gend
+person			= per pers
+degree			= deg degr
+aspect			= asp
+negation		= neg
+accommodability		= acco acom acm
+accentability		= acce acen acn
+post-prepositionality	= ppr ppre
+agglutination		= agg aggl
+vocalicity		= vcl

data/corpus/frek.cfg~

@@ -0,0 +1,100 @@
+# Config file format for Oasis release
+# Config version 1.0
+
+# The new startup section may contain any command normally accepted by the shell
+
+[STARTUP]
+
+/alias masc = m1 m2 m3
+/alias verb = pact ppas winien praet bedzie fin impt aglt ger imps inf pant pcon 
+/alias noun = subst depr xxs ger ppron12 ppron3
+/alias pron = ppron12 ppron3 siebie
+
+
+[ATTR]
+
+number			= sg pl
+case			= nom gen dat acc inst loc voc
+gender			= m1 m2 m3 f n
+person			= pri sec ter
+degree			= pos comp sup
+aspect			= imperf perf
+negation		= aff neg
+accommodability		= congr rec
+accentability		= akc nakc
+post-prepositionality	= npraep praep
+agglutination		= agl nagl
+vocalicity		= nwok wok
+
+# Parts of speech no longer need forward declarations, this was inconvenient and ugly.
+# Also, any attribute may be optional so a declaration such as:
+# foo = [bar] [froz] fred [wilma]
+# should no longer cause problems and ctags with such attributes now parse correctly regardless
+# of presence or absence of any optional attribute
+
+[POS]
+
+adja	=
+adjp	=
+conj	=
+interp	= 
+pred	=
+xxx	=
+adv	= degree
+imps	= aspect
+inf	= aspect
+pant	= aspect
+pcon	= aspect
+qub	= [vocalicity]
+prep	= case [vocalicity]
+siebie	= case
+subst	= number case gender
+depr	= number case gender
+xxs	= number case gender
+ger	= number case gender aspect negation
+ppron12	= number case gender person [accentability]
+ppron3	= number case gender person [accentability] [post-prepositionality]
+num	= number case gender [accommodability]
+adj	= number case gender degree
+pact	= number case gender aspect negation
+ppas	= number case gender aspect negation
+winien	= number gender aspect
+praet	= number gender aspect [agglutination]
+bedzie	= number person aspect
+fin	= number person aspect
+impt	= number person aspect
+aglt	= number person aspect vocalicity
+ign     =
+
+# Named entities replaced old 'special' attributes, name changed mostly because of
+# unification of 'named-thing' handling code into one named-entity thing
+# Entity aliasing allows for any existing entity to be seen under different name
+#
+# FCQP provides four builtin entities:
+#    entity-current
+#    entity-base
+#    entity-tag
+#    entity-pos
+
+[NAMED-ENTITY]
+
+entity-orth		= orth
+entity-base		= base
+entity-tag		= tag
+entity-pos		= pos
+
+# Old 'aliases' for attribute names
+
+pos			= flex
+number			= numb nmb
+case			= cas
+gender			= gnd gend
+person			= per pers
+degree			= deg degr
+aspect			= asp
+negation		= neg
+accommodability		= acco acom acm
+accentability		= acce acen acn
+post-prepositionality	= ppr ppre
+agglutination		= agg aggl
+vocalicity		= vcl

data/corpus/frek.meta.cfg

@@ -0,0 +1 @@
+S sample

data/corpus/frek.meta.lisp

@@ -0,0 +1,4 @@
+(single	"sample"
+        "/cesHeader/fileDesc/(sourceDesc/biblFull/)*sourceDesc/biblStruct/monogr/h.title")
+
+

data/lib/poliqarpr-corpus.rb

@@ -0,0 +1,3 @@
+module Poliqarp
+  DEFAULT_CORPUS = File.join(File.dirname(__FILE__), '..','corpus','frek')
+end

data/poliqarpr-corpus.gemspec

@@ -0,0 +1,17 @@
+Gem::Specification.new do |s|
+  s.name = "poliqarpr-corpus"
+  s.version = "1.0.1"
+  s.date = "2009-12-10"
+  s.summary = "Default corpus for poliqarpr"
+  s.email = "apohllo@o2.pl"
+  s.homepage = "http://www.github.com/apohllo/poliqarpr-corpus"
+  s.description = "Default corpus for Ruby client for Poliqarp (NLP corpus server)"
+  s.authors = ['Aleksander Pohl']
+  s.files = ["Rakefile", "poliqarpr-corpus.gemspec", 'lib/poliqarpr-corpus.rb',
+    "README.txt", ] + Dir.glob("corpus/**/*")
+  s.rdoc_options = ["--main", "README.txt"]
+  s.has_rdoc = true
+  s.extra_rdoc_files = ["README.txt"]
+  s.add_dependency("poliqarpr", [">= 0.0.3"])
+end
+

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification 
+name: poliqarpr-corpus
+version: !ruby/object:Gem::Version 
+  version: 1.0.1
+platform: ruby
+authors: 
+- Aleksander Pohl
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-12-10 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: poliqarpr
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.3
+    version: 
+description: Default corpus for Ruby client for Poliqarp (NLP corpus server)
+email: apohllo@o2.pl
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.txt
+files: 
+- Rakefile
+- poliqarpr-corpus.gemspec
+- lib/poliqarpr-corpus.rb
+- README.txt
+- corpus/frek.poliqarp.base2.offset
+- corpus/frek.poliqarp.subchunk.image
+- corpus/frek.poliqarp.meta-value.image
+- corpus/frek.poliqarp.corpus.image
+- corpus/frek.poliqarp.chunk.image
+- corpus/frek.poliqarp.subpos1.image
+- corpus/frek.poliqarp.subchunk.offset
+- corpus/frek.poliqarp.subpos1.offset
+- corpus/frek.poliqarp.rindex.amb.offset
+- corpus/frek.poliqarp.base1.offset
+- corpus/frek.poliqarp.subpos2.image
+- corpus/frek.poliqarp.tag.image
+- corpus/frek.poliqarp.rindex.orth
+- corpus/frek.cfg~
+- corpus/frek.poliqarp.orth.offset
+- corpus/frek.meta.lisp
+- corpus/frek.cdf
+- corpus/frek.cfg
+- corpus/frek.poliqarp.rindex.disamb
+- corpus/frek.poliqarp.orth.index.alpha
+- corpus/frek.poliqarp.subchunk.item.ch
+- corpus/frek.poliqarp.meta-key.image
+- corpus/frek.poliqarp.meta-value.offset
+- corpus/frek.poliqarp.orth.index.atergo
+- corpus/frek.poliqarp.base1.image
+- corpus/frek.poliqarp.orth.image
+- corpus/frek.poliqarp.meta.image
+- corpus/frek.poliqarp.meta-key.offset
+- corpus/frek.poliqarp.rindex.disamb.offset
+- corpus/frek.poliqarp.rindex.orth.offset
+- corpus/frek.poliqarp.subpos2.offset
+- corpus/frek.poliqarp.rindex.amb
+- corpus/frek.meta.cfg
+- corpus/frek.poliqarp.tag.offset
+- corpus/frek.poliqarp.base2.image
+has_rdoc: true
+homepage: http://www.github.com/apohllo/poliqarpr-corpus
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --main
+- README.txt
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Default corpus for poliqarpr
+test_files: []
+