Merge f34bc53 into c18d959

Vagrantfile

@@ -2,35 +2,35 @@
 # vi: set ft=ruby :
 
 # If there are any problems with the required gems, vagrant
-# has its own ruby environment. To install the gems (iniparse, 
+# has its own ruby environment. To install the gems (iniparse,
 # for example), you need to run:
 #
 # $ vagrant plugin install iniparse
 #
-# For more details, check out: 
+# For more details, check out:
 # https://docs.vagrantup.com/v2/cli/plugin.html
 
 require 'iniparse'
 
 Vagrant.configure("2") do |config|
-  
+
   # preliminaries
   root_dir = File.dirname(__FILE__)
-  
+
   #################################################### VIRTUALBOX PROVIDER SETUP
   # global configuration on the virtualbox provider. for all available
   # options, see http://www.virtualbox.org/manual/ch08.html
   virtualbox_server_name = "dev"
   config.vm.provider :virtualbox do |vb, override_config|
     vb.gui = false
     # http://stackoverflow.com/a/17126363/892506
-    vb.customize ["modifyvm", :id, "--ioapic", "on"] 
+    vb.customize ["modifyvm", :id, "--ioapic", "on"]
     vb.customize ["modifyvm", :id, "--cpus", "2"]
     vb.customize ["modifyvm", :id, "--memory", "2048"]
-    override_config.vm.box = "precise64"
-    override_config.vm.box_url = "http://files.vagrantup.com/precise64.box"
+    override_config.vm.box = "trusty64"
+    override_config.vm.box_url = "https://cloud-images.ubuntu.com/vagrant/trusty/current/trusty-server-cloudimg-amd64-vagrant-disk1.box"
   end
- 
+
   # steps for provisioning so that these provisioning steps are
   # properly executed in this virtual machine and also on travis-ci
   def provision_script(config, script_path)

docs/index.rst

@@ -68,7 +68,7 @@ file types by either mentioning them on the `issue tracker
 
 * ``.ogg`` via `SpeechRecognition`_ and `sox`_
 
-* ``.pdf`` via `pdftotext`_ (default) or `pdfminer`_
+* ``.pdf`` via `pdftotext`_ (default) or `pdfminer.six`_
 
 * ``.png`` via `tesseract-ocr`_
 
@@ -93,7 +93,7 @@ file types by either mentioning them on the `issue tracker
 .. _beautifulsoup4: http://beautiful-soup-4.readthedocs.org/en/latest/
 .. _ebooklib: https://github.com/aerkalov/ebooklib
 .. _msg-extractor: https://github.com/mattgwwalker/msg-extractor
-.. _pdfminer: https://euske.github.io/pdfminer/
+.. _pdfminer.six: https://github.com/goulu/pdfminer
 .. _pdftotext: http://poppler.freedesktop.org/
 .. _ps2text: http://pages.cs.wisc.edu/~ghost/doc/pstotext.htm
 .. _python-docx: https://python-docx.readthedocs.org/en/latest/

docs/installation.rst

@@ -17,7 +17,7 @@ Ubuntu / Debian
 
 There are two steps required to run this package on
 Ubuntu/Debian. First you must install some system packages using the
-`apt-get <https://help.ubuntu.com/12.04/serverguide/apt-get.html>`_
+`apt-get <https://help.ubuntu.com/14.04/serverguide/apt-get.html>`_
 package manager before installing textract from pypi.
 
 .. code-block:: bash

tests/base.py

@@ -159,7 +159,7 @@ def get_standardized_text(self):
             standardized_text = six.b(
                 "the quick brown fox jumps over the lazy dog"
             )
-        return standardized_text.replace(six.b(' '), six.b(''))
+        return six.b('').join(standardized_text.split())
 
     def assertSuccessfulCommand(self, command):
         self.assertEqual(