Move document.xml parsing to separate module

1 files changed, 82 insertions, 0 deletions

diff --git a/tests/docx/document_xml_tests.py b/tests/docx/document_xml_tests.py
new file mode 100644
index 0000000..2771e2c
--- /dev/null
+++ b/tests/docx/document_xml_tests.py
@@ -0,0 +1,82 @@
+from nose.tools import istest, assert_equal
+
+from mammoth import docx, documents
+from mammoth.docx.xmlparser import element as xml_element, text as xml_text
+from mammoth.docx.document_xml import read_document_xml_element
+
+
+@istest
+class ReadXmlElementTests(object):
+    @istest
+    def text_from_text_element_is_read(self):
+        element = _text_element("Hello!")
+        assert_equal(documents.Text("Hello!"), read_document_xml_element(element))
+    
+    @istest
+    def can_read_text_within_run(self):
+        element = _run_element_with_text("Hello!")
+        assert_equal(
+            documents.Run([documents.Text("Hello!")]),
+            read_document_xml_element(element)
+        )
+    
+    @istest
+    def can_read_text_within_paragraph(self):
+        element = _paragraph_element_with_text("Hello!")
+        assert_equal(
+            documents.paragraph([documents.Run([documents.Text("Hello!")])]),
+            read_document_xml_element(element)
+        )
+    
+    @istest
+    def can_read_text_within_document(self):
+        element = _document_element_with_text("Hello!")
+        assert_equal(
+            documents.Document([documents.paragraph([documents.Run([documents.Text("Hello!")])])]),
+            read_document_xml_element(element)
+        )
+        
+    @istest
+    def paragraph_has_no_style_if_it_has_no_properties(self):
+        element = xml_element("w:p")
+        assert_equal(None, read_document_xml_element(element).style_name)
+        
+    @istest
+    def paragraph_has_style_name_read_from_paragraph_properties_if_present(self):
+        style_xml = xml_element("w:pStyle", {"w:val": "Heading1"})
+        properties_xml = xml_element("w:pPr", {}, [style_xml])
+        paragraph_xml = xml_element("w:p", {}, [properties_xml])
+        paragraph = read_document_xml_element(paragraph_xml)
+        assert_equal("Heading1", paragraph.style_name)
+    
+    @istest
+    def unrecognised_elements_are_ignored(self):
+        element = xml_element("w:huh", {}, [])
+        assert_equal(None, read_document_xml_element(element))
+    
+    @istest
+    def unrecognised_children_are_ignored(self):
+        element = xml_element("w:r", {}, [_text_element("Hello!"), xml_element("w:huh", {}, [])])
+        assert_equal(
+            documents.Run([documents.Text("Hello!")]),
+            read_document_xml_element(element)
+        )
+
+
+def _document_element_with_text(text):
+    return xml_element("w:document", {}, [
+        xml_element("w:body", {}, [_paragraph_element_with_text(text)])
+    ])
+
+
+def _paragraph_element_with_text(text):
+    return xml_element("w:p", {}, [_run_element_with_text(text)])
+
+
+def _run_element_with_text(text):
+    return xml_element("w:r", {}, [_text_element(text)])
+
+
+def _text_element(value):
+    return xml_element("w:t", {}, [xml_text(value)])
+