Merge pull request #29 from OpenScienceFramework/issue_29

Stop overriding the handlers in the test cases

Author: jlward

README.md

@@ -166,10 +166,10 @@ OR, let's say FOO is your new favorite markup language. Simply customize your ow
 
 The base parser `Docx2Html` relies on certain css class being set for certain behaviour to occur. Currently these include:
 
-* class `insert` -> Turns the text green.
-* class `delete` -> Turns the text red and draws a line through the text.
-* class `center` -> Aligns the text to the center.
-* class `right` -> Aligns the text to the right.
-* class `left` -> Aligns the text to the left.
-* class `comment` -> Turns the text blue.
+* class `pydocx-insert` -> Turns the text green.
+* class `pydocx-delete` -> Turns the text red and draws a line through the text.
+* class `pydocx-center` -> Aligns the text to the center.
+* class `pydocx-right` -> Aligns the text to the right.
+* class `pydocx-left` -> Aligns the text to the left.
+* class `pydocx-comment` -> Turns the text blue.
 * class `pydocx-underline` -> Underlines the text.

pydocx/parsers/Docx2Html.py

@@ -1,7 +1,6 @@
 from pydocx.DocxParser import DocxParser
 
 import xml.sax.saxutils
-import textwrap
 
 
 class Docx2Html(DocxParser):
@@ -21,16 +20,22 @@ def head(self):
         }
 
     def style(self):
-        return textwrap.dedent('''<style>.insert{{color:red}}.delete
-        {{color:red; text-decoration:line-through}}.center
-        {{text-align:center}}.right{{text-align:right}}
-        .left{{text-align:left}} .comment{{color:blue}}
-        .pydocx-underline {text-decoration: underline;}
-        body{{width:%(width)spx; margin:0px auto;
-        }}</style>''') % {
+        result = (
+            '<style>'
+            '.pydocx-insert {color:green;}'
+            '.pydocx-delete {color:red;text-decoration:line-through;}'
+            '.pydocx-center {text-align:center;}'
+            '.pydocx-right {text-align:right;}'
+            '.pydocx-left {text-align:left;}'
+            '.pydocx-comment {color:blue;}'
+            '.pydocx-underline {text-decoration: underline;}'
+            'body {width:%(width)spx;margin:0px auto;}'
+            '</style>'
+        ) % {
+            #multiple by (4/3) to get to px
             'width': (self.page_width * (4 / 3)),
         }
-        #multiple by (4/3) to get to px
+        return result
 
     def escape(self, text):
         return xml.sax.saxutils.quoteattr(text)[1:-1]
@@ -49,7 +54,7 @@ def heading(self, text, heading_value):
 
     def insertion(self, text, author, date):
         return (
-            "<span class='insert' author='%(author)s' "
+            "<span class='pydocx-insert' author='%(author)s' "
             "date='%(date)s'>%(text)s</span>"
         ) % {
             'author': author,
@@ -83,7 +88,7 @@ def image(self, path, x, y):
 
     def deletion(self, text, author, date):
         return (
-            "<span class='delete' author='%(author)s' "
+            "<span class='pydocx-delete' author='%(author)s' "
             "date='%(date)s'>%(text)s</span>"
         ) % {
             'author': author,
@@ -97,8 +102,9 @@ def list_element(self, text):
         }
 
     def ordered_list(self, text, list_style):
-        return "<ol>%(text)s</ol>" % {
+        return '<ol list-style-type="%(list_style)s">%(text)s</ol>' % {
             'text': text,
+            'list_style': list_style,
         }
 
     def unordered_list(self, text):
@@ -121,7 +127,7 @@ def tab(self):
         return '&nbsp&nbsp&nbsp&nbsp'
 
     def table(self, text):
-        return '<table border=1>' + text + '</table>'
+        return '<table border="1">' + text + '</table>'
 
     def table_row(self, text):
         return '<tr>' + text + '</tr>'
@@ -145,7 +151,7 @@ def page_break(self):
     def indent(self, text, just='', firstLine='', left='', right=''):
         slug = '<div'
         if just:
-            slug += " class='%(just)s'"
+            slug += " class='pydocx-%(just)s'"
         if firstLine or left or right:
             slug += " style='"
             if firstLine:

pydocx/tests/__init__.py

@@ -11,6 +11,28 @@
 )
 from unittest import TestCase
 
+STYLE = (
+    '<style>'
+    '.pydocx-insert {color:green;}'
+    '.pydocx-delete {color:red;text-decoration:line-through;}'
+    '.pydocx-center {text-align:center;}'
+    '.pydocx-right {text-align:right;}'
+    '.pydocx-left {text-align:left;}'
+    '.pydocx-comment {color:blue;}'
+    '.pydocx-underline {text-decoration: underline;}'
+    'body {width:612px;margin:0px auto;}'
+    '</style>'
+)
+
+BASE_HTML = '''
+<html>
+    <head>
+    %s
+    </head>
+    <body>%%s</body>
+</html>
+''' % STYLE
+
 
 def assert_html_equal(actual_html, expected_html):
     assert collapse_html(
@@ -78,6 +100,10 @@ def _build_data(
                 remove_namespaces(document_xml),
             )
 
+        # This is the standard page width for a word document, Also the page
+        # width that we are looking for in the test.
+        self.page_width = 612
+
     def _parse_rels_root(self, *args, **kwargs):
         if self._test_rels_dict is None:
             return {}
@@ -92,38 +118,15 @@ def get_list_style(self, num_id, ilvl):
     def _parse_styles(self):
         return {}
 
-    def head(self):
-        return ''
-
-    def table(self, text):
-        return '<table>' + text + '</table>'
-
-    def ordered_list(self, text, list_style):
-        list_type_conversions = {
-            'decimal': 'decimal',
-            'decimalZero': 'decimal-leading-zero',
-            'upperRoman': 'upper-roman',
-            'lowerRoman': 'lower-roman',
-            'upperLetter': 'upper-alpha',
-            'lowerLetter': 'lower-alpha',
-            'ordinal': 'decimal',
-            'cardinalText': 'decimal',
-            'ordinalText': 'decimal',
-        }
-        return '<ol data-list-type="{list_style}">{text}</ol>'.format(
-            list_style=list_type_conversions.get(list_style, 'decimal'),
-            text=text,
-        )
-
 
 DEFAULT_NUMBERING_DICT = {
     '1': {
         '0': 'decimal',
         '1': 'decimal',
     },
     '2': {
-        '0': 'none',
-        '1': 'none',
+        '0': 'lowerLetter',
+        '1': 'lowerLetter',
     },
 }
 
@@ -159,4 +162,4 @@ def test_expected_output(self):
             numbering_dict=self.numbering_dict,
         ).parsed
 
-        assert_html_equal(html, self.expected_output)
+        assert_html_equal(html, BASE_HTML % self.expected_output)