Don't drop internal links

pydocx/export/html.py

@@ -270,6 +270,8 @@ def get_heading_tag(self, paragraph):
             heading_style.name.lower(),
             self.default_heading_level,
         )
+        if paragraph.bookmark_name:
+            return HtmlTag(tag, id=paragraph.bookmark_name)
         return HtmlTag(tag)
 
     def export_paragraph(self, paragraph):
@@ -507,7 +509,10 @@ def get_hyperlink_tag(self, target_uri):
 
     def export_hyperlink(self, hyperlink):
         results = super(PyDocXHTMLExporter, self).export_hyperlink(hyperlink)
-        tag = self.get_hyperlink_tag(target_uri=hyperlink.target_uri)
+        if not hyperlink.target_uri and hyperlink.anchor:
+            tag = self.get_hyperlink_tag(target_uri='#' + hyperlink.anchor)
+        else:
+            tag = self.get_hyperlink_tag(target_uri=hyperlink.target_uri)
         if tag:
             results = tag.apply(results, allow_empty=False)
 

pydocx/openxml/wordprocessing/__init__.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from pydocx.openxml.wordprocessing.abstract_num import AbstractNum
 from pydocx.openxml.wordprocessing.body import Body
+from pydocx.openxml.wordprocessing.bookmark import Bookmark
 from pydocx.openxml.wordprocessing.br import Break
 from pydocx.openxml.wordprocessing.deleted_run import DeletedRun
 from pydocx.openxml.wordprocessing.deleted_text import DeletedText
@@ -47,6 +48,7 @@
 __all__ = [
     'AbstractNum',
     'Body',
+    'Bookmark',
     'Break',
     'DeletedRun',
     'DeletedText',

pydocx/openxml/wordprocessing/bookmark.py

@@ -0,0 +1,14 @@
+# coding: utf-8
+from __future__ import (
+    absolute_import,
+    print_function,
+    unicode_literals,
+)
+
+from pydocx.models import XmlModel, XmlAttribute
+
+
+class Bookmark(XmlModel):
+    XML_TAG = 'bookmarkStart'
+
+    name = XmlAttribute(name='name')

pydocx/openxml/wordprocessing/paragraph.py

@@ -16,6 +16,7 @@
 from pydocx.openxml.wordprocessing.deleted_run import DeletedRun
 from pydocx.openxml.wordprocessing.sdt_run import SdtRun
 from pydocx.openxml.wordprocessing.simple_field import SimpleField
+from pydocx.openxml.wordprocessing.bookmark import Bookmark
 
 
 class Paragraph(XmlModel):
@@ -31,6 +32,7 @@ class Paragraph(XmlModel):
         DeletedRun,
         SdtRun,
         SimpleField,
+        Bookmark
     )
 
     def __init__(self, **kwargs):
@@ -121,6 +123,12 @@ def runs(self):
             if isinstance(p_child, Run):
                 yield p_child
 
+    @property
+    def bookmark_name(self):
+        for p_child in self.children:
+            if isinstance(p_child, Bookmark):
+                return p_child.name
+
     def get_text(self, tab_char=None):
         '''
         Return a string of all of the contained Text nodes concatenated

tests/export/html/test_heading.py

@@ -744,3 +744,30 @@ def test_single_lvl_list_has_precedence_over_headings(self):
             </ol>
         '''
         self.assert_document_generates_html(document, expected_html)
+
+    def test_heading_with_bookmark(self):
+        document_xml = '''
+            <p>
+              <pPr>
+                <pStyle val="heading1"/>
+              </pPr>
+              <bookmarkStart name="testing"/>
+              <bookmarkEnd/>
+              <r>
+                <t>aaa</t>
+              </r>
+            </p>
+        '''
+
+        style_xml = '''
+            <style styleId="heading1" type="paragraph">
+              <name val="Heading 1"/>
+            </style>
+        '''
+
+        document = WordprocessingDocumentFactory()
+        document.add(StyleDefinitionsPart, style_xml)
+        document.add(MainDocumentPart, document_xml)
+
+        expected_html = '<h1 id="testing">aaa</h1>'
+        self.assert_document_generates_html(document, expected_html)

tests/export/html/test_hyperlink.py

@@ -194,3 +194,21 @@ def test_with_anchor(self):
 
         expected_html = '<p><a href="http://google.com#testing">link</a>.</p>'
         self.assert_document_generates_html(document, expected_html)
+
+    def test_internal_link(self):
+        document_xml = '''
+            <p>
+              <hyperlink anchor="testing">
+                <r>
+                  <t>link</t>
+                </r>
+              </hyperlink>
+            </p>
+        '''
+
+        document = WordprocessingDocumentFactory()
+
+        document.add(MainDocumentPart, document_xml)
+
+        expected_html = '<p><a href="#testing">link</a></p>'
+        self.assert_document_generates_html(document, expected_html)