From 5e90d620d4e438a9df81c7dd27d7d50192ebbcac Mon Sep 17 00:00:00 2001
From: Kai Sheng Tai <kst@metamind.io>
Date: Thu, 17 Dec 2015 11:56:09 -0800
Subject: [PATCH] Updated link to GloVe vectors

---
 .gitignore              |  4 ++++
 fetch_and_preprocess.sh |  1 +
 scripts/download.py     | 11 +++--------
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/.gitignore b/.gitignore
index 2a9a0a1..048cbfc 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,3 +4,7 @@ predictions
 trained_models
 *~
 #*#
+*.class
+lib/stanford-parser
+lib/stanford-tagger
+
diff --git a/fetch_and_preprocess.sh b/fetch_and_preprocess.sh
index dd12c13..c0bfda4 100755
--- a/fetch_and_preprocess.sh
+++ b/fetch_and_preprocess.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+set -e
 python2.7 scripts/download.py
 
 CLASSPATH="lib:lib/stanford-parser/stanford-parser.jar:lib/stanford-parser/stanford-parser-3.5.1-models.jar"
diff --git a/scripts/download.py b/scripts/download.py
index a1f81fd..e33647a 100644
--- a/scripts/download.py
+++ b/scripts/download.py
@@ -44,6 +44,7 @@ def download(url, dirpath):
     return filepath
 
 def unzip(filepath):
+    print("Extracting: " + filepath)
     dirpath = os.path.dirname(filepath)
     with zipfile.ZipFile(filepath) as zf:
         zf.extractall(dirpath)
@@ -83,14 +84,8 @@ def download_wordvecs(dirpath):
         return
     else:
         os.makedirs(dirpath)
-    url = 'http://www-nlp.stanford.edu/data/glove.840B.300d.txt.gz'
-    filepath = download(url, dirpath)
-    print('extracting ' + filepath)
-    with gzip.open(filepath, 'rb') as gf:
-        with open(filepath[:-3], 'w') as f:
-            for line in gf:
-                f.write(line)
-    os.remove(filepath)
+    url = 'http://www-nlp.stanford.edu/data/glove.840B.300d.zip'
+    unzip(download(url, dirpath))
 
 def download_sick(dirpath):
     if os.path.exists(dirpath):