From d5acaf1071564a9997a330315ea99cdc1017bae7 Mon Sep 17 00:00:00 2001
From: Michael Williamson <mike@zwobble.org>
Date: Sun, 1 Dec 2013 11:51:38 +0000
Subject: Move document.xml parsing to separate module

---
 mammoth/docx/__init__.py     | 73 ++----------------------------------------
 mammoth/docx/document_xml.py | 76 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+), 71 deletions(-)
 create mode 100644 mammoth/docx/document_xml.py

(limited to 'mammoth')

diff --git a/mammoth/docx/__init__.py b/mammoth/docx/__init__.py
index de2b8a8..17c90a8 100644
--- a/mammoth/docx/__init__.py
+++ b/mammoth/docx/__init__.py
@@ -3,6 +3,7 @@ import zipfile
 from .. import documents
 from ..results import Result
 from .xmlparser import parse_xml, node_types
+from .document_xml import read_document_xml_element
 
 
 _namespaces = [
@@ -14,75 +15,5 @@ def read(fileobj):
     zip_file = zipfile.ZipFile(fileobj)
     document_fileobj = zip_file.open("word/document.xml")
     document_xml = parse_xml(document_fileobj, _namespaces)
-    return Result(read_xml_element(document_xml), [])
+    return Result(read_document_xml_element(document_xml), [])
 
-
-_handlers = {}
-
-
-def handler(name):
-    def add(func):
-        _handlers[name] = func
-        
-    return add
-
-
-def read_xml_element(element):
-    handler = _handlers.get(element.name)
-    if handler is None:
-        return None
-    else:
-        return handler(element)
-
-
-@handler("w:t")
-def text(element):
-    return documents.Text(_inner_text(element))
-
-
-@handler("w:r")
-def run(element):
-    return documents.Run(_read_xml_elements(element.children))
-
-
-@handler("w:p")
-def paragraph(element):
-    properties = element.find_child_or_null("w:pPr")
-    style_name = properties \
-        .find_child_or_null("w:pStyle") \
-        .attributes.get("w:val")
-    
-    children = _read_xml_elements(element.children)
-    return documents.paragraph(children, style_name)
-
-
-@handler("w:body")
-def body(element):
-    return _read_xml_elements(element.children)
-
-
-@handler("w:document")
-def document(element):
-    body_element = _find_child(element, "w:body")
-    return documents.Document(_read_xml_elements(body_element.children))
-
-
-def _find(predicate, iterable):
-    for item in iterable:
-        if predicate(item):
-            return item
-
-
-def _find_child(element, name):
-    return _find(lambda child: child.name == name, element.children)
-
-
-def _read_xml_elements(elements):
-    return filter(None, map(read_xml_element, elements))
-
-
-def _inner_text(node):
-    if node.node_type == node_types.text:
-        return node.value
-    else:
-        return "".join(_inner_text(child) for child in node.children)
diff --git a/mammoth/docx/document_xml.py b/mammoth/docx/document_xml.py
new file mode 100644
index 0000000..c83c28c
--- /dev/null
+++ b/mammoth/docx/document_xml.py
@@ -0,0 +1,76 @@
+import zipfile
+
+from .. import documents
+from ..results import Result
+from .xmlparser import parse_xml, node_types
+
+
+_handlers = {}
+
+
+def handler(name):
+    def add(func):
+        _handlers[name] = func
+        
+    return add
+
+
+def read_document_xml_element(element):
+    handler = _handlers.get(element.name)
+    if handler is None:
+        return None
+    else:
+        return handler(element)
+
+
+@handler("w:t")
+def text(element):
+    return documents.Text(_inner_text(element))
+
+
+@handler("w:r")
+def run(element):
+    return documents.Run(_read_xml_elements(element.children))
+
+
+@handler("w:p")
+def paragraph(element):
+    properties = element.find_child_or_null("w:pPr")
+    style_name = properties \
+        .find_child_or_null("w:pStyle") \
+        .attributes.get("w:val")
+    
+    children = _read_xml_elements(element.children)
+    return documents.paragraph(children, style_name)
+
+
+@handler("w:body")
+def body(element):
+    return _read_xml_elements(element.children)
+
+
+@handler("w:document")
+def document(element):
+    body_element = _find_child(element, "w:body")
+    return documents.Document(_read_xml_elements(body_element.children))
+
+
+def _find(predicate, iterable):
+    for item in iterable:
+        if predicate(item):
+            return item
+
+
+def _find_child(element, name):
+    return _find(lambda child: child.name == name, element.children)
+
+
+def _read_xml_elements(elements):
+    return filter(None, map(read_document_xml_element, elements))
+
+
+def _inner_text(node):
+    if node.node_type == node_types.text:
+        return node.value
+    else:
+        return "".join(_inner_text(child) for child in node.children)
-- 
cgit v1.2.3