Merge pull request #61 from OpenScienceFramework/issue_61

Handle the noBreakHyphen tag

Author: jlward

CHANGELOG

@@ -1,6 +1,9 @@
 
 Changelog
 =========
+* 0.3.11
+    * The non breaking hyphen tag was not correctly being imported. This issue
+      has been fixed.
 * 0.3.10
     * Found and optimized a fairly large performance issue with tables that had
       large amounts of content within a single cell, which includes nested

pydocx/DocxParser.py

@@ -198,6 +198,8 @@ def parse(self, el):
             return self.parse_t(el, parsed)
         elif el.tag == 'tab':
             return self.parse_tab(el, parsed)
+        elif el.tag == 'noBreakHyphen':
+            return self.parse_hyphen(el, parsed)
         elif el.tag == 'br':
             return self.parse_break_tag(el, parsed)
         elif el.tag == 'delText':
@@ -612,6 +614,9 @@ def parse_t(self, el, parsed):
     def parse_tab(self, el, parsed):
         return ' '
 
+    def parse_hyphen(self, el, parsed):
+        return '-'
+
     def parse_break_tag(self, el, parsed):
         return self.break_tag()
 

pydocx/fixtures/no_break_hyphen.docx

@@ -776,6 +776,19 @@ def test_styled_bolding():
     ''')
 
 
+def test_no_break_hyphen():
+    file_path = path.join(
+        path.abspath(path.dirname(__file__)),
+        '..',
+        'fixtures',
+        'no_break_hyphen.docx',
+    )
+    actual_html = convert(file_path)
+    assert_html_equal(actual_html, BASE_HTML % '''
+    <p>AAA-BBB</p>
+    ''')
+
+
 @raises(MalformedDocxException)
 def test_malformed_docx_exception():
     with NamedTemporaryFile(suffix='.docx') as f: