- Streamlined namespace support by simulating namespace prefixes

for makeelement()
- Initial work on adding images (doesn't work yet)

Author: mikemaccana

README.markdown

@@ -3,7 +3,7 @@ Python docx
 
 ## Introduction
 
-The docx module reads and writes Microsoft Office Word 2007 docx files.
+The docx module creates, reads and writes Microsoft Office Word 2007 docx files.
 
 These are referred to as 'WordML', 'Office Open XML' and 'Open XML' by Microsoft.
 

docx.py

@@ -11,8 +11,10 @@
 import re
 import time
 
-# Namespaces used for the test (document.xml)
-docns = {
+# All Word prefixes / namespace matches used in document.xml & core.xml
+# LXML doesn't actually use prefixes (just the real namespace) , but these
+# make it easier to copy Word output more easily. 
+nsprefixes = {
     'mv':'urn:schemas-microsoft-com:mac:vml',
     'mo':'http://schemas.microsoft.com/office/mac/office/2008/main',
     've':'http://schemas.openxmlformats.org/markup-compatibility/2006',
@@ -26,21 +28,13 @@
     'wp':'http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing',
     'a':'http://schemas.openxmlformats.org/drawingml/2006/main',
     'pic':'http://schemas.openxmlformats.org/drawingml/2006/picture',
-    }
-
-# Namespaces used for document properties (core.xml)
-propns={
     'cp':"http://schemas.openxmlformats.org/package/2006/metadata/core-properties", 
     'dc':"http://purl.org/dc/elements/1.1/", 
     'dcterms':"http://purl.org/dc/terms/",
     'dcmitype':"http://purl.org/dc/dcmitype/",
     'xsi':"http://www.w3.org/2001/XMLSchema-instance",
     }
 
-def getns(nsdict,prefix):
-    '''Given a dict to search, a namespace prefix to look for, return a formatted namespace'''
-    return '{'+nsdict[prefix]+'}'
-
 def opendocx(file):
     '''Open a docx file, return a document XML tree'''
     mydoc = zipfile.ZipFile(file)
@@ -53,14 +47,15 @@ def newdocument():
     document.append(makeelement('body'))
     return document
 
-def makeelement(tagname,tagtext=None,tagnamespace=getns(docns,'w'),tagattributes=None,attributenamespace=None):
-    '''Create an element & return it'''  
-    newelement = etree.Element(tagnamespace+tagname)
+def makeelement(tagname,tagtext=None,nsprefix='w',tagattributes=None,attributenamespace=None):
+    '''Create an element & return it''' 
+    namespace = '{'+nsprefixes[nsprefix]+'}'
+    newelement = etree.Element(namespace+tagname)
     # Add attributes with namespaces
     if tagattributes:
         # If they haven't bothered setting attribute namespace, use the same one as the tag
         if not attributenamespace:
-            attributenamespace = tagnamespace    
+            attributenamespace = namespace    
         for tagattribute in tagattributes:
             newelement.set(attributenamespace+tagattribute, tagattributes[tagattribute])
     if tagtext:
@@ -193,26 +188,100 @@ def table(contents):
         table.append(row)   
     return table                 
 
-def picture(filename):
+def picture():
     '''Create a pragraph containing an image - FIXME - not implemented yet'''
     # Word uses paragraphs to contain images
     # http://openxmldeveloper.org/articles/462.aspx
-    resourceid = rId5
-    newrelationship = makeelement('Relationship',tagattributes={'Id':resourceid,'Type':'http://schemas.openxmlformats.org/officeDocument/2006/relationships/image'},Target=filename)
-    newpara = makeelement('deleteme',style='BodyText')
+    #resourceid = rId5
+    #newrelationship = makeelement('Relationship',tagattributes={'Id':resourceid,'Type':'http://schemas.openxmlformats.org/officeDocument/2006/relationships/image'},Target=filename)
+    
+    # Now make drawing element
+    #newpara = makeelement('deleteme',style='BodyText')
+
+    
+    blipfill = makeelement('blipFill',nsprefix='a')
+    blipfill.append(makeelement('blip',nsprefix='a',tagattributes={'embed':'rId5'}))
+    stretch = makeelement('stretch',nsprefix='a')
+    stretch.append(makeelement('fillRect',nsprefix='a'))
+    blipfill.append(stretch)
+
+    sppr = makeelement('spPr',nsprefix='pic')
+    xfrm = makeelement('xfrm',nsprefix='a')
+    xfrm.append(makeelement('off',nsprefix='a',tagattributes={'x':'0','y':'0'}))
+    xfrm.append(makeelement('ext',nsprefix='a',tagattributes={'cx':'5486400','cy':'3429000'}))
+    prstgeom = makeelement('prstGeom',nsprefix='a',tagattributes={'prst':'rect'})
+    prstgeom.append(makeelement('avLst',nsprefix='a'))
+    sppr.append(xfrm)
+    sppr.append(prstgeom)
+
+    nvpicpr = makeelement('nvPicPr',nsprefix='a')
+    cnvpr = makeelement('cNvPr',nsprefix='a',tagattributes={'id':'0','name':'aero_glow_v2_1920x1200.png'})
+    cnvpicpr = makeelement('cNvPicPr')
+    nvpicpr.append(cnvpicpr)
+    nvpicpr.append(cnvpr)
+    
+    pic = makeelement('pic',nsprefix='pic')
+    pic.append(blipfill)
+    pic.append(sppr)
+    pic.append(nvpicpr)
+
+
+    graphicdata = makeelement('graphicData',nsprefix='a',tagattributes={'uri':'http://schemas.openxmlformats.org/drawingml/2006/picture'})
+    graphicdata.append(pic)
+
+    graphic = makeelement('graphic',nsprefix='a')
+    graphic.append(graphicdata)
+
+    framepr = makeelement('cNvGraphicFramePr',nsprefix='a')
+    framelocks = makeelement('graphicFrameLocks',nsprefix='a',tagattributes={'noChangeAspect':'1'})
+    framepr.append(framelocks)
+
     makeelement('drawing')
-    makeelement('inline',tagattributes={'distT':"0",'distB':"0",'distL':"0",'distR':"0"},tagnamespace=getns(docns,'wp'))
-    makeelement('graphic',tagnamespace=getns(docns,'a'))
-    makeelement('graphicData',tagnamespace=getns(docns,'a'))
-    makeelement('pic',tagnamespace=getns(docns,'a'))
-                          
+    inline = makeelement('inline',tagattributes={'distT':"0",'distB':"0",'distL':"0",'distR':"0"},nsprefix='wp')
+    extent = makeelement('extent',nsprefix='a',tagattributes={'cx':'5486400','cy':'3429000'})
+    effectextent = makeelement('effectExtent',nsprefix='a',tagattributes={'l':'25400','t':'0','r':'0','b':'0'})
+    docpr = makeelement('docPr',nsprefix='a',tagattributes={'id':'1','name':'Picture 0','descr':'aero_glow_v2_1920x1200.png'})
+    inline.append(extent)
+    inline.append(effectextent)
+    inline.append(docpr)
+    inline.append(framepr)
+    inline.append(graphic)
+    drawing = makeelement('drawing')
+    drawing.append(inline)
+    return drawing
+    '''
+    <w:drawing>
+    	<wp:inline distT="0" distB="0" distL="0" distR="0">
+    		<wp:extent cx="5486400" cy="3429000"/>
+    		<wp:effectExtent l="25400" t="0" r="0" b="0"/>
+    		<wp:docPr id="1" name="Picture 0" descr="aero_glow_v2_1920x1200.png"/>
+    		<wp:cNvGraphicFramePr>
+    			<a:graphicFrameLocks xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" noChangeAspect="1"/>
+    		<a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main">
+    			<a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/picture">
+    				<pic:pic xmlns:pic="http://schemas.openxmlformats.org/drawingml/2006/picture">
+    					<pic:nvPicPr>
+    						<pic:cNvPr id="0" name="aero_glow_v2_1920x1200.png"/>
+    						<pic:cNvPicPr/>
+    					<pic:blipFill>
+    						<a:blip r:embed="rId5"/>
+    						<a:stretch>
+    							<a:fillRect/>
+    					<pic:spPr>
+    						<a:xfrm>
+    							<a:off x="0" y="0"/>
+    							<a:ext cx="5486400" cy="3429000"/>
+    						<a:prstGeom prst="rect">
+    							<a:avLst/>
+    '''
+
 
 def search(document,search):
     '''Search a document for a regex, return '''
     results = False
     searchre = re.compile(search)
     for element in document.iter():
-        if element.tag == getns(docns,'w')+'t':
+        if element.tag == 'w'+'t':
             if element.text:
                 if searchre.match(element.text):
                     results = True
@@ -223,7 +292,7 @@ def replace(document,search,replace):
     newdocument = document
     searchre = re.compile(search)
     for element in newdocument.iter():
-        if element.tag == getns(docns,'w')+'t':
+        if element.tag == 'w'+'t':
             if element.text:
                 if searchre.search(element.text):
                     element.text = re.sub(search,replace,element.text)
@@ -238,7 +307,7 @@ def getdocumenttext(document):
     paralist = []
     for element in document.iter():
         # Find p (paragraph) elements
-        if element.tag == getns(docns,'w')+'p':
+        if element.tag == 'w'+'p':
             paralist.append(element)
 
     # Since a single sentence might be spread over multiple text elements, iterate through each 
@@ -248,7 +317,7 @@ def getdocumenttext(document):
         # Loop through each paragraph
         for element in para.iter():
             # Find t (text) elements
-            if element.tag == getns(docns,'w')+'t':
+            if element.tag == 'w'+'t':
                 if element.text:
                     paratext = paratext+element.text
 
@@ -260,27 +329,27 @@ def getdocumenttext(document):
 def docproperties(title,subject,creator,keywords,lastmodifiedby=None):
     '''Makes document properties. '''
     # OpenXML uses the term 'core' to refer to the 'Dublin Core' specification used to make the properties.  
-    docprops = makeelement('coreProperties',tagnamespace=getns(propns,'cp'))    
-    docprops.append(makeelement('title',tagtext=title,tagnamespace=getns(propns,'dc')))
-    docprops.append(makeelement('subject',tagtext=subject,tagnamespace=getns(propns,'dc')))
-    docprops.append(makeelement('creator',tagtext=creator,tagnamespace=getns(propns,'dc')))
-    docprops.append(makeelement('keywords',tagtext=','.join(keywords),tagnamespace=getns(propns,'cp')))    
+    docprops = makeelement('coreProperties',nsprefix='cp')    
+    docprops.append(makeelement('title',tagtext=title,nsprefix='dc'))
+    docprops.append(makeelement('subject',tagtext=subject,nsprefix='dc'))
+    docprops.append(makeelement('creator',tagtext=creator,nsprefix='dc'))
+    docprops.append(makeelement('keywords',tagtext=','.join(keywords),nsprefix='cp'))    
     if not lastmodifiedby:
         lastmodifiedby = creator
-    docprops.append(makeelement('lastModifiedBy',tagtext=lastmodifiedby,tagnamespace=getns(propns,'cp')))
-    docprops.append(makeelement('revision',tagtext='1',tagnamespace=getns(propns,'cp')))
-    docprops.append(makeelement('category',tagtext='Examples',tagnamespace=getns(propns,'cp')))
-    docprops.append(makeelement('description',tagtext='Examples',tagnamespace=getns(propns,'dc')))
+    docprops.append(makeelement('lastModifiedBy',tagtext=lastmodifiedby,nsprefix='cp'))
+    docprops.append(makeelement('revision',tagtext='1',nsprefix='cp'))
+    docprops.append(makeelement('category',tagtext='Examples',nsprefix='cp'))
+    docprops.append(makeelement('description',tagtext='Examples',nsprefix='dc'))
     currenttime = time.strftime('%Y-%m-%dT-%H:%M:%SZ')
     # FIXME - creating these items manually fails - but we can live without them for now.
     '''	What we're going for:
     <dcterms:created xsi:type="dcterms:W3CDTF">2010-01-01T21:07:00Z</dcterms:created>
     <dcterms:modified xsi:type="dcterms:W3CDTF">2010-01-01T21:20:00Z</dcterms:modified>
     currenttime'''
-    #docprops.append(makeelement('created',tagnamespace=getns(propns,'dcterms'),
-    #tagattributes={'type':'dcterms:W3CDTF'},tagtext='2010-01-01T21:07:00Z',attributenamespace=getns(propns,'xsi')))
-    #docprops.append(makeelement('modified',tagnamespace=getns(propns,'dcterms'),
-    #tagattributes={'type':'dcterms:W3CDTF'},tagtext='2010-01-01T21:07:00Z',attributenamespace=getns(propns,'xsi')))
+    #docprops.append(makeelement('created',nsprefix='dcterms',
+    #tagattributes={'type':'dcterms:W3CDTF'},tagtext='2010-01-01T21:07:00Z',attributenamespace='xsi'))
+    #docprops.append(makeelement('modified',nsprefix='dcterms',
+    #tagattributes={'type':'dcterms:W3CDTF'},tagtext='2010-01-01T21:07:00Z',attributenamespace='xsi'))
     return docprops
 
 
@@ -306,6 +375,7 @@ def savedocx(document,properties,newfilename):
     'word/numbering.xml',
     'word/theme/',
     'word/theme/theme1.xml',
+    #'word/media/image1.png',
     'word/settings.xml',
     'word/fontTable.xml']:
         newfile.write('template/'+xmlfile,xmlfile)

example-makedocument.py

@@ -14,7 +14,7 @@
     document = newdocument()
 
     # This xpath location is where most interesting content lives 
-    docbody = document.xpath('/w:document/w:body', namespaces=docns)[0]
+    docbody = document.xpath('/w:document/w:body', namespaces=nsprefixes)[0]
 
     # Append two headings and a paragraph
     docbody.append(heading('''Welcome to Python's docx module''',1)  )   
@@ -41,6 +41,9 @@
     docbody.append(paragraph('Thanks to the awesomeness of the lxml module, we can:'))
     for point in ['Search and replace','Extract plain text of document','Add and delete items anywhere within the document']:
         docbody.append(paragraph(point,style='ListBullet'))
+        
+    # Add an image (beta)
+    #docbody.append(picture())
 
     # Search and replace 
     document = replace(document,'the','the goshdarned')

template/word/_rels/document.xml.rels

@@ -1,2 +1,2 @@
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme" Target="theme/theme1.xml"/><Relationship Id="rId4" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/webSettings" Target="webSettings.xml"/><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering" Target="numbering.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/><Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings" Target="settings.xml"/><Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/fontTable" Target="fontTable.xml"/></Relationships>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId4" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/webSettings" Target="webSettings.xml"/><Relationship Id="rId5" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="media/image1.png"/><Relationship Id="rId7" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme" Target="theme/theme1.xml"/><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering" Target="numbering.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/><Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings" Target="settings.xml"/><Relationship Id="rId6" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/fontTable" Target="fontTable.xml"/></Relationships>