opener-constituent-parser-nl 1.1.0 → 1.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6fb4abe6d9ba20a847991088e724f976c1c0f513
-  data.tar.gz: 630fdefa1e52a567c48e2cd9faf2302e0bcf4a2e
+  metadata.gz: 819a202f5bb0bc6e8eb8b653056b3921eb4973c5
+  data.tar.gz: 7b07ac07c45bfcd877112e61b2aceff684eaeec4
 SHA512:
-  metadata.gz: f3436a9fd712446d68970d135bc04eb4dafd5df0e8d87c3c91104a250d6f150a5ce61cc290192acb545ff7d216102ddc14744fd7f0f3284e0471a799a3d4a723
-  data.tar.gz: 27212605333aca1981b600b345a4daad8a1ed2a1bdef2aaac4943caab91eaaa721444c83f47d037552a6a7b8dd32a794e58b9b37a21c72d0a51e3ca3547024b0
+  metadata.gz: 614fbe0ebca264c3348f836911c7ef29d9bff17a9a89951ca4adef52dd5e878e77d9ea66122ad047080b036588c1675e9876de9b2be167fcaec03295f30583ca
+  data.tar.gz: 514153a51bcb96f689ddbf7fb705c9f0570f759d068540ee1e19910dd29c99013e138b2da269cca7fc71d583490d98ed52c208e1ba2ee6962d14fa2fd38fd58a

data/README.md

@@ -1,5 +1,3 @@
-[![Build Status](https://drone.io/github.com/opener-project/constituent-parser-nl/status.png)](https://drone.io/github.com/opener-project/constituent-parser-nl/latest)
-
 Constituent-parser-nl
 =======
 
@@ -38,4 +36,4 @@ Contact
 ------
 * Ruben Izquierdo
 * Vrije University of Amsterdam
-* ruben.izquierdobevia@vu.nl
+* ruben.izquierdobevia@vu.nl

data/core/alpino_parser.py

@@ -32,6 +32,8 @@ this_name = 'alpino kaf constituency parser'
 this_layer = 'constituents'
 
 #### SET THIS VARIABLE TO YOUR LOCAL FOLDER OF ALPINO
+os.environ['SP_CTYPE']='utf8'
+os.environ['SP_CSETLEN']='212'
 ALPINO_HOME = os.environ['ALPINO_HOME']
 
 logging.basicConfig(stream=sys.stderr,format='%(asctime)s - %(levelname)s - %(message)s',level=logging.DEBUG)
@@ -73,6 +75,7 @@ def xml_to_penn(filename):
   ## to iso-8859-1, but the real encoding is UTF-8. So we need to force to use this encoding
   
   parser = etree.XMLParser(encoding='UTF-8')
+  #parser = etree.XMLParser(encoding='ISO-8859-1')
   tree = etree.parse(filename,parser)
   
   str = node_to_penn(tree.find('node'))
@@ -159,7 +162,6 @@ for sentence in sentences:
     token = token.replace('[','\[')
     token = token.replace(']','\]')
     token = token.replace('|','\|')
-    #print>>sys.stderr,token.encode('utf-8'),
     alpino_pro.stdin.write(token.encode('utf-8')+' ')
   alpino_pro.stdin.write('\n')
   #print>>sys.stderr

data/lib/opener/constituent_parsers/nl.rb

@@ -49,7 +49,7 @@ module Opener
 
         raise stderr unless process.success?
 
-        return stdout
+        return stdout.strip
       end
 
       protected

data/lib/opener/constituent_parsers/nl/version.rb

@@ -1,7 +1,7 @@
 module Opener
   module ConstituentParsers
     class NL
-      VERSION = "1.1.0"
+      VERSION = "1.1.1"
     end
   end
 end

data/task/requirements.rake

@@ -4,5 +4,5 @@ task :requirements do
 
   Cliver.detect!('make')
   Cliver.detect!('python', '~> 2.6')
-  Cliver.detect!('pip', '~> 1.3')
+  Cliver.detect!('pip', '>= 1.3')
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: opener-constituent-parser-nl
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.1.1
 platform: ruby
 authors:
 - development@olery.com
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-25 00:00:00.000000000 Z
+date: 2015-01-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake