Merge pull request #213 from nltk/pickle-patch

Convert the pickle tagsets dictionary to json

collections/all-nltk.xml

@@ -92,6 +92,7 @@
   <item ref="swadesh" />
   <item ref="switchboard" />
   <item ref="tagsets" />
+  <item ref="tagsets_json" />
   <item ref="timit" />
   <item ref="toolbox" />
   <item ref="treebank" />

collections/all.xml

@@ -92,6 +92,7 @@
   <item ref="swadesh" />
   <item ref="switchboard" />
   <item ref="tagsets" />
+  <item ref="tagsets_json" />
   <item ref="timit" />
   <item ref="toolbox" />
   <item ref="treebank" />

index.xml

@@ -95,6 +95,7 @@
     <package id="swadesh" name="Swadesh Wordlists" webpage="http://en.wiktionary.org/wiki/Appendix:Swadesh_list" license="GNU Free Documentation License" unzip="1" unzipped_size="39998" size="22828" checksum="6612ccb71f327e85780dc7813dee40f6" subdir="corpora" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/swadesh.zip" />
     <package id="switchboard" name="Switchboard Corpus Sample" sample="True" license="Permission is granted for use of this material in accordance with the Open Content License [http://opencontent.org/opl.shtml].  This corpus contains transcripts and annotations for 36 calls from the Switchboard Corpus [http://www.ldc.upenn.edu/Catalog/LDC93S7.html]." unzip="1" unzipped_size="2541179" size="791161" checksum="878df010a9f2c2d0a6546a8365f10595" subdir="corpora" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/switchboard.zip" />
     <package id="tagsets" name="Help on Tagsets" author="UCREL, Lancaster University" languages="English" unzip="1" unzipped_size="79723" size="34531" checksum="e15834e0dd89b107925af6bb11a8eaa4" subdir="help" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/help/tagsets.zip" />
+    <package id="tagsets_json" name="Help on Tagsets" author="UCREL, Lancaster University" languages="English" unzip="1" unzipped_size="0" size="742" checksum="bc2b6c611e9a20c43f4b204edcf4e2ad" subdir="help" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/help/tagsets_json.zip" />
     <package id="timit" name="TIMIT Corpus Sample" sample="True" license="This corpus sample is Copyright 1993 Linguistic Data Consortium, and is distributed under the terms of the Creative Commons Attribution, Non-Commercial, ShareAlike license.  http://creativecommons.org/" webpage="http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC93S1" unzip="1" unzipped_size="31932925" size="22251869" checksum="34c047c4749a811287f2c652104d7849" subdir="corpora" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/timit.zip" />
     <package id="toolbox" name="Toolbox Sample Files" unzip="1" unzipped_size="829593" size="250616" checksum="26657c1b8b5f5afdc3d5d754393a9216" subdir="corpora" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/toolbox.zip" />
     <package id="treebank" name="Penn Treebank Sample" sample="True" copyright="Copyright (C) 1995 University of Pennsylvania" license="This is a 10% fragment of Penn Treebank, (C) LDC 1995.  It is made available under fair use for the purposes of illustrating NLTK tools for tokenizing, tagging, chunking and parsing.  This data is for non-commercial use only." unzip="1" unzipped_size="5963497" size="1740034" checksum="78c24a97940c2504d0ad35dd3f8a560b" subdir="corpora" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/treebank.zip" />
@@ -213,6 +214,7 @@
       <item ref="swadesh" />
       <item ref="switchboard" />
       <item ref="tagsets" />
+      <item ref="tagsets_json" />
       <item ref="timit" />
       <item ref="toolbox" />
       <item ref="treebank" />
@@ -423,6 +425,7 @@
       <item ref="swadesh" />
       <item ref="switchboard" />
       <item ref="tagsets" />
+      <item ref="tagsets_json" />
       <item ref="timit" />
       <item ref="toolbox" />
       <item ref="treebank" />