Merge pull request nltk#58 from simonrichard/gh-pages

Add Dolch word list
wzhu2467 · Apr 14, 2017 · e93c1eb · e93c1eb
2 parents 1164703 + 1d6ca44
commit e93c1eb
Show file tree

Hide file tree

Showing 6 changed files with 10 additions and 0 deletions.
diff --git a/collections/all-corpora.xml b/collections/all-corpora.xml
@@ -15,6 +15,7 @@
     <item ref="conll2007"/>
     <item ref="crubadan"/>
     <item ref="dependency_treebank"/>
+    <item ref="dolch"/>
     <item ref="floresta"/>
     <item ref="framenet_v15"/>
     <item ref="framenet_v17"/>

diff --git a/collections/all.xml b/collections/all.xml
@@ -16,6 +16,7 @@
     <item ref="conll2007"/>
     <item ref="crubadan"/>
     <item ref="dependency_treebank"/>
+    <item ref="dolch"/>
     <item ref="europarl_raw"/>
     <item ref="floresta"/>
     <item ref="framenet_v15"/>

diff --git a/index.xml b/index.xml
@@ -20,6 +20,7 @@
     <package checksum="b9015928e35c41f0695525289df5208f" contact="Kepa Sarasola" copyright="Copyright (C) 2007 The University of the Basque Country" id="conll2007" license="Creative Commons Attribution-NonCommercial-NoDerivativeWorks license" name="Dependency Treebanks from CoNLL 2007 (Catalan and Basque Subset)" size="1242958" subdir="corpora" unzip="0" unzipped_size="6399295" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/conll2007.zip" webpage="http://nextens.uvt.nl/depparse-wiki/DataDownload" />
     <package author="Kevin Scannell" checksum="3cc831382dec41b8d9a06d93ef300352" copyright="Copyright (C) 2010 Kevin Scannell" id="crubadan" license="GPLv3" name="Crubadan Corpus" size="5288655" subdir="corpora" unzip="1" unzipped_size="11256183" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/crubadan.zip" webpage="http://borel.slu.edu/crubadan/" />
     <package checksum="631e959acaa42eea718daf04c5cdfa76" copyright="Copyright (C) 1995 University of Pennsylvania" id="dependency_treebank" license="This is a 10% fragment of Penn Treebank, (C) LDC 1995, which has been dependency parsed.  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." name="Dependency Parsed Treebank" sample="True" size="457429" subdir="corpora" unzip="1" unzipped_size="1069540" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/dependency_treebank.zip" />
+    <package checksum="6f9c042774b96366c93fd0f9a9adb697" id="dolch" name="Dolch Word List" size="2116" subdir="corpora" unzip="1" unzipped_size"1917" url="https://en.wikipedia.org/wiki/Dolch_word_list" />
     <package author="Philipp Koehn, University of Edinburgh" checksum="7621d5675990b1decc012c823716ee76" id="europarl_raw" name="Sample European Parliament Proceedings Parallel Corpus" size="12594977" subdir="corpora" unzip="1" unzipped_size="41396100" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/europarl_raw.zip" webpage="http://www.statmt.org/europarl" />
     <package checksum="de5f1df09949f080e0f616f0bc55967d" id="floresta" license="Non-commercial use only" name="Portuguese Treebank" size="1882021" subdir="corpora" unzip="1" unzipped_size="16414136" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/floresta.zip" webpage="http://www.linguateca.pt/Floresta/" />
     <package author="Collin F. Baker" checksum="cf68365950b2f048bcb48619de81f50a" id="framenet_v15" license="May be used for non-commercial purposes." name="FrameNet 1.5" size="69337891" subdir="corpora" unzip="1" unzipped_size="579133737" url="https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/framenet_v15.zip" webpage="http://framenet.icsi.berkeley.edu" />
@@ -128,6 +129,7 @@
       <item ref="conll2007" />
       <item ref="crubadan" />
       <item ref="dependency_treebank" />
+      <item ref="dolch" />
       <item ref="floresta" />
       <item ref="framenet_v15" />
       <item ref="framenet_v17" />
@@ -204,6 +206,7 @@
       <item ref="conll2007" />
       <item ref="crubadan" />
       <item ref="dependency_treebank" />
+      <item ref="dolch" />
       <item ref="europarl_raw" />
       <item ref="floresta" />
       <item ref="framenet_v15" />

diff --git a/packages/corpora/dolch.xml b/packages/corpora/dolch.xml
@@ -0,0 +1,4 @@
+<package id="dolch" name="Dolch Word List"
+         webpage="https://en.wikipedia.org/wiki/Dolch_word_list"
+         unzip="1"
+         />
diff --git a/packages/corpora/dolch.zip b/packages/corpora/dolch.zip
diff --git a/packages/corpora/listing.csv b/packages/corpora/listing.csv
@@ -7,6 +7,7 @@ chat80,chat80,Chat-80 Database,,,chat80.py,University of Pennsylvania,,http://ww
 cmudict,cmudict,Carnegie Mellon Pronouncing Dictionary,,,cmudict.py,,,,,
 conll2000,conll2000,CoNLL 2000 Chunking Corpus,,,conll2000.py,,,,,
 conll2002,conll2002,CoNLL 2002 NER Corpus,Dutch::Spanish,,conll2002.py,,,,,
+dolch,dolch,Dolch Word List,,,,,,,,
 genesis,genesis,Genesis Corpus,,,genesis.py,,,,,
 gutenberg,gutenberg,Project Gutenberg Selections,,,gutenberg.py,,,,,
 ieer,ieer,NIST 1999 Information Extraction ,Entity Recognition Corpus,,ieer.py,,,,,