Annotation Tools: Add helper functions and fixed pep8/pylint errors

Small plugin fixes

common/lib/xmodule/xmodule/annotator_mixin.py

@@ -0,0 +1,45 @@
+"""
+Annotations Tool Mixin
+This file contains global variables and functions used in the various Annotation Tools.
+"""
+from pkg_resources import resource_string
+from lxml import etree
+from urlparse import urlparse
+from os.path import splitext, basename
+from HTMLParser import HTMLParser
+
+def get_instructions(xmltree):
+    """ Removes <instructions> from the xmltree and returns them as a string, otherwise None. """
+    instructions = xmltree.find('instructions')
+    if instructions is not None:
+        instructions.tag = 'div'
+        xmltree.remove(instructions)
+        return etree.tostring(instructions, encoding='unicode')
+    return None
+
+def get_extension(srcurl):
+    ''' get the extension of a given url '''
+    if 'youtu' in srcurl:
+        return 'video/youtube'
+    else:
+        disassembled = urlparse(srcurl)
+        file_ext = splitext(basename(disassembled.path))[1]
+        return 'video/' + file_ext.replace('.', '')
+
+class MLStripper(HTMLParser):
+    "helper function for html_to_text below"
+    def __init__(self):
+        self.reset()
+        self.fed = []
+    def handle_data(self, d):
+        self.fed.append(d)
+    def handle_entityref(self, name):
+        self.fed.append('&%s;' % name)
+    def get_data(self):
+        return ''.join(self.fed)
+
+def html_to_text(html):
+    "strips the html tags off of the text to return plaintext"
+    s = MLStripper()
+    s.feed(html)
+    return s.get_data()

common/lib/xmodule/xmodule/annotator_token.py

@@ -23,8 +23,8 @@ def retrieve_token(userid, secret):
     dtnow = datetime.datetime.now()
     dtutcnow = datetime.datetime.utcnow()
     delta = dtnow - dtutcnow
-    newhour, newmin = divmod((delta.days * 24 * 60 * 60 + delta.seconds + 30) // 60, 60)
-    newtime = "%s%+02d:%02d" % (dtnow.isoformat(), newhour, newmin)
+    newhour, newmin = divmod((delta.days * 24 * 60 * 60 + delta.seconds + 30) // 60, 60)  # pylint: disable=E1103
+    newtime = "%s%+02d:%02d" % (dtnow.isoformat(), newhour, newmin)  # pylint: disable=E1103
     # uses the issued time (UTC plus timezone), the consumer key and the user's email to maintain a 
     # federated system in the annotation backend server
     custom_data = {"issuedAt": newtime, "consumerKey": secret, "userId": userid, "ttl": 86400}

common/lib/xmodule/xmodule/tests/test_annotator_mixin.py

@@ -0,0 +1,52 @@
+"""
+This test will run for annotator_mixin.py
+"""
+
+import unittest
+from lxml import etree
+
+from xmodule.annotator_mixin import get_instructions, get_extension, html_to_text
+
+class HelperFunctionTest(unittest.TestCase):
+    """
+    Tests to ensure that the following helper functions work for the annotation tool
+    """
+    sample_xml = '''
+        <annotatable>
+            <instructions><p>Helper Test Instructions.</p></instructions>
+        </annotatable>
+    '''
+    sample_sourceurl = "http://video-js.zencoder.com/oceans-clip.mp4"
+    sample_youtubeurl = "http://www.youtube.com/watch?v=yxLIu-scR9Y"
+    sample_html = '<p><b>Testing here</b> and not bolded here</p>'
+
+    def test_get_instructions(self):
+        """
+        Function takes in an input of a specific xml string with surrounding instructions tags and returns a valid html string.
+        """
+        xmltree = etree.fromstring(self.sample_xml)
+
+        expected_xml = u"<div><p>Helper Test Instructions.</p></div>"
+        actual_xml = get_instructions(xmltree)  # pylint: disable=W0212
+        self.assertIsNotNone(actual_xml)
+        self.assertEqual(expected_xml.strip(), actual_xml.strip())
+
+        xmltree = etree.fromstring('<annotatable>foo</annotatable>')
+        actual = get_instructions(xmltree)  # pylint: disable=W0212
+        self.assertIsNone(actual)
+
+    def test_get_extension(self):
+        """
+        Tests whether given a url if the video will return a youtube source or extension
+        """
+        expectedyoutube = 'video/youtube'
+        expectednotyoutube = 'video/mp4'
+        result1 = get_extension(self.sample_sourceurl)  # pylint: disable=W0212
+        result2 = get_extension(self.sample_youtubeurl)  # pylint: disable=W0212
+        self.assertEqual(expectedyoutube, result2)
+        self.assertEqual(expectednotyoutube, result1)
+
+    def test_html_to_text(self):
+        expectedText = "Testing here and not bolded here"
+        result = html_to_text(self.sample_html)
+        self.assertEqual(expectedText, result)

common/lib/xmodule/xmodule/tests/test_annotator_token.py

@@ -12,9 +12,9 @@ class TokenRetriever(unittest.TestCase):
     """
     def test_token(self):
         """
-        Test for the token generator. Give an a random username and secret token, it should create the properly encoded string of text. 
+        Test for the token generator. Give an a random username and secret token, it should create the properly encoded string of text.
         """
         expected = "eyJhbGciOiAiSFMyNTYiLCAidHlwIjogIkpXVCJ9.eyJpc3N1ZWRBdCI6ICIyMDE0LTAyLTI3VDE3OjAwOjQyLjQwNjQ0MSswOjAwIiwgImNvbnN1bWVyS2V5IjogImZha2Vfc2VjcmV0IiwgInVzZXJJZCI6ICJ1c2VybmFtZSIsICJ0dGwiOiA4NjQwMH0.Dx1PoF-7mqBOOSGDMZ9R_s3oaaLRPnn6CJgGGF2A5CQ"
         response = retrieve_token("username", "fake_secret")
         self.assertEqual(expected.split('.')[0], response.split('.')[0])
-        self.assertNotEqual(expected.split('.')[2], response.split('.')[2])
+        self.assertNotEqual(expected.split('.')[2], response.split('.')[2])

common/lib/xmodule/xmodule/tests/test_videoannotation.py

@@ -66,6 +66,6 @@ class VideoAnnotationModuleTestCase(unittest.TestCase):
         """
         Tests to make sure variables passed in truly exist within the html once it is all rendered.
         """
-        context = self.mod.get_html() # pylint: disable=W0212
+        context = self.mod.get_html()  # pylint: disable=W0212
         for key in ['display_name', 'instructions_html', 'sourceUrl', 'typeSource', 'poster', 'annotation_storage']:
             self.assertIn(key, context)

common/lib/xmodule/xmodule/textannotation_module.py

@@ -6,6 +6,7 @@ from pkg_resources import resource_string
 from xmodule.x_module import XModule
 from xmodule.raw_module import RawDescriptor
 from xblock.core import Scope, String
+from xmodule.annotator_mixin import get_instructions
 from xmodule.annotator_token import retrieve_token
 
 import textwrap
@@ -70,12 +71,7 @@ class TextAnnotationModule(AnnotatableFields, XModule):
 
     def _extract_instructions(self, xmltree):
         """ Removes <instructions> from the xmltree and returns them as a string, otherwise None. """
-        instructions = xmltree.find('instructions')
-        if instructions is not None:
-            instructions.tag = 'div'
-            xmltree.remove(instructions)
-            return etree.tostring(instructions, encoding='unicode')
-        return None
+        return get_instructions(xmltree)
 
     def get_html(self):
         """ Renders parameters to template. """

common/lib/xmodule/xmodule/videoannotation_module.py

@@ -7,6 +7,7 @@ from pkg_resources import resource_string
 from xmodule.x_module import XModule
 from xmodule.raw_module import RawDescriptor
 from xblock.core import Scope, String
+from xmodule.annotator_mixin import get_instructions, get_extension
 from xmodule.annotator_token import retrieve_token
 
 import textwrap
@@ -65,24 +66,11 @@ class VideoAnnotationModule(AnnotatableFields, XModule):
 
     def _extract_instructions(self, xmltree):
         """ Removes <instructions> from the xmltree and returns them as a string, otherwise None. """
-        instructions = xmltree.find('instructions')
-        if instructions is not None:
-            instructions.tag = 'div'
-            xmltree.remove(instructions)
-            return etree.tostring(instructions, encoding='unicode')
-        return None
+        return get_instructions(xmltree)
 
     def _get_extension(self, srcurl):
         ''' get the extension of a given url '''
-        if 'youtu' in srcurl:
-            return 'video/youtube'
-        else:
-            spliturl = srcurl.split(".")
-            extensionplus1 = spliturl[len(spliturl) - 1]
-            spliturl = extensionplus1.split("?")
-            extensionplus2 = spliturl[0]
-            spliturl = extensionplus2.split("#")
-            return 'video/' + spliturl[0]
+        return get_extension(srcurl)
 
     def get_html(self):
         """ Renders parameters to template. """