Merge branch 'master' of ssh://git.cy55.de/home/git/cybertools

docgen/README.txt

@@ -8,3 +8,52 @@ docgen - Document Generation from Result Sets and XML Structures
   >>> from cybertools.docgen.base import WordDocument
   >>> doc = WordDocument(None, TestRequest)
 
+
+Working with MHT Files
+======================
+
+  >>> import os
+  >>> basePath = os.path.join(os.path.dirname(__file__), 'testing')
+
+  >>> path = os.path.join(basePath, 'test_doc.mht')
+  >>> f = open(path, 'rt')
+  >>> data = f.read()
+  >>> f.close()
+
+  >>> xbody = '''<div class="WordSection1">
+  ... <v:shape id="Grafik_x0020_2" o:spid="_x0000_i1025" type="#_x0000_t75"
+  ...     style="width:320pt;height:240pt;visibility:visible;mso-wrap-style:square">
+  ...   <v:imagedata src="FB-Besprechungsprotokoll-Dateien/image002.jpg" o:title=""/>
+  ... </v:shape>
+  ... </div>
+  ... '''
+
+  >>> body = '''<div class="WordSection1">
+  ... <img src="files/test_image.jpg" />
+  ... </div>
+  ... '''
+
+  >>> from cybertools.docgen.mht import MHTFile
+  >>> document = MHTFile(data, body)
+
+  >>> imageRefs = document.htmlDoc.getImageRefs()
+  >>> for path in imageRefs:
+  ...     imagePath = os.path.join(basePath, os.path.basename(path))
+  ...     f = open(imagePath, 'rt')
+  ...     imageData = f.read()
+  ...     f.close()
+  ...     document.addImage(imageData, path)
+
+  >>> document.insertBody()
+
+  >>> output = document.asString()
+  >>> len(data), len(output)
+  (294996, 336140)
+
+  >>> outPath = os.path.join(basePath, 'out_doc.mht')
+  >>> #f = open(outPath, 'wt')
+  >>> #f.write(document.asString())
+  >>> #f.close()
+
+  >>> #os.unlink(outPath)
+

docgen/mht.py

@@ -0,0 +1,131 @@
+#
+#  Copyright (c) 2012 Helmut Merz helmutm@cy55.de
+#
+#  This program is free software; you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation; either version 2 of the License, or
+#  (at your option) any later version.
+#
+#  This program is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+#
+
+"""
+Working with MHT Files.
+"""
+
+import base64
+from cStringIO import StringIO
+import email
+import Image
+import mimetypes
+import os
+
+from cybertools.text.lib.BeautifulSoup import BeautifulSoup, Tag
+
+
+class MHTFile(object):
+
+    #encoding = 'UTF-8'
+    #encoding = 'ISO8859-15'
+    encoding = 'Windows-1252'
+    bodyMarker = 'lxdoc_body'
+    foldernameSuffix = 'Dateien'
+    indexes = dict(body=2, filelist=-2)
+
+    path = documentName = None
+
+    imageTemplate = ('\n'
+        'Content-Location: %(path)s/%(docname)s-%(suffix)s/%(imgname)s\n'
+        'Content-Transfer-Encoding: base64\n'
+        'Content-Type: %(ctype)s\n\n%(imgdata)s\n\n')
+
+    filelistItemTemplate = ' <o:File HRef=3D"%s"/>\n'
+    filelistPattern =' <o:File HRef=3D"filelist.xml"/>'
+
+    def __init__(self, data, body):
+        self.data = data
+        self.msg = email.message_from_string(data)
+        self.boundary = self.msg.get_boundary()
+        self.parts = data.split(self.boundary)
+        self.body = body
+        self.htmlDoc = HTMLDoc(body)
+        self.lastImageNum = 0
+        self.imageMappings = {}
+        for idx, part in enumerate(self.msg.walk()):
+            docPath = part['Content-Location']
+            contentType = part.get_content_type()
+            #print '***', idx, docPath, contentType 
+            if idx == self.indexes['body'] - 1:
+                self.path, docname = os.path.split(docPath)
+                self.documentName, ext = os.path.splitext(docname)
+            if contentType.startswith('image/'):
+                self.lastImageNum += 1
+        #print '###', self.path, self.documentName, self.lastImageNum
+
+    def getImageRefs(self):
+        return self.htmlDoc.getImageRefs()
+
+    def addImage(self, imageData, path):
+        image = Image.open(StringIO(imageData))
+        width, height = image.size
+        contentType, enc = mimetypes.guess_type(path)
+        bp, ext = os.path.splitext(path)
+        self.lastImageNum += 1
+        name = 'image%03i%s' % (self.lastImageNum, ext)
+        self.imageMappings[path] = (name, width, height)
+        flpos = self.indexes['filelist']
+        vars = dict(path=self.path, docname=self.documentName,  
+                    suffix=self.foldernameSuffix,
+                    imgname=name, ctype=contentType,
+                    imgdata=base64.encodestring(imageData))
+        content = self. imageTemplate % vars
+        self.parts.insert(flpos, str(content))
+        filelistRep = (self.filelistItemTemplate % name) + self.filelistPattern
+        filelist = self.parts[flpos]
+        self.parts[flpos] = str(filelist.replace(self.filelistPattern, filelistRep))
+
+
+    def insertBody(self):
+        path = '-'.join((self.documentName, self.foldernameSuffix))
+        self.htmlDoc.updateImageRefs(self.imageMappings, path)
+        content = self.htmlDoc.doc.renderContents(self.encoding)
+        bodyIndex = self.indexes['body']
+        baseDocument = self.parts[bodyIndex]
+        self.parts[bodyIndex] =  baseDocument.replace(self.bodyMarker, 
+                                        self.quopri(content))
+
+    def asString(self):
+        return self.boundary.join(self.parts)
+
+    def quopri(self, s):
+        return s.replace('="', '=3D"')
+
+
+class HTMLDoc(object):
+
+    def __init__(self, data):
+        self.data = data
+        self.doc = BeautifulSoup(data)
+
+    def getImageRefs(self):
+        return [img['src'] for img in self.doc('img')]
+
+    def updateImageRefs(self, mappings, path=''):
+        for img in self.doc('img'):
+            name, width, height = mappings[img['src']]
+            imgdata = Tag(self.doc, 'v:imagedata')
+            imgdata['src'] = '/'.join((path, name))
+            imgdata.isSelfClosing = True
+            img.append(imgdata)
+            del img['src']
+            img['style'] = 'width:%spt;height:%spt' % (width, height)
+            img.isSelfClosing = False
+            img.name='v:shape'
+

integrator/filesystem.py

@@ -1,5 +1,5 @@
 #
-#  Copyright (c) 2008 Helmut Merz helmutm@cy55.de
+#  Copyright (c) 2012 Helmut Merz helmutm@cy55.de
 #
 #  This program is free software; you can redistribute it and/or modify
 #  it under the terms of the GNU General Public License as published by
@@ -18,8 +18,6 @@
 
 """
 Access to objects in the file system.
-
-$Id$
 """
 
 import os, stat
@@ -40,7 +38,7 @@ class ReadContainer(ReadContainer):
 
     factoryName = 'filesystem'
 
-    @Lazy
+    @property
     def filenames(self):
         return os.listdir(self.address)
 
@@ -86,7 +84,7 @@ class File(File):
     data = None
 
     def getData(self, num=-1):
-        f = open(self.address, 'r')
+        f = open(self.address, 'rb')
         data = f.read(num)
         f.close()
         return data
@@ -115,10 +113,13 @@ class ContainerFactory(ContainerFactory):
 
 class FileFactory(FileFactory):
 
+    proxyClass = File
+    imageClass = Image
+
     def __call__(self, address, **kw):
         contentType = kw.pop('contentType', None)
         width = height = 0
-        obj = File(address, contentType, **kw)
+        obj = self.proxyClass(address, contentType, **kw)
         if not contentType:
             data = obj.getData(50)
             contentType, width, height = getImageInfo(data)
@@ -126,7 +127,7 @@ class FileFactory(FileFactory):
             name = os.path.basename(address)
             contentType, encoding = guess_content_type(name, data, '')
         if contentType.startswith('image/'):
-            return Image(address, contentType=contentType,
+            return self.imageClass(address, contentType=contentType,
                          width=width, height=height, **kw)
         else:
             obj.contentType = contentType

organize/work.py

@@ -80,6 +80,7 @@ def workItemStates():
         State('planned_x', 'planned', (), color='red'),
         State('accepted_x', 'accepted', (), color='yellow'),
         State('done_x', 'done', (), color='lightgreen'),
+        State('finished_x', 'finished', (), color='green'),
         # transitions:
         Transition('plan', 'plan', 'planned'),
         Transition('accept', 'accept', 'accepted'),
@@ -131,13 +132,16 @@ class WorkItemType(object):
     """
 
     def __init__(self, name, title, description=u'', 
-                 actions=None, fields=None, indicator=None):
+                 actions=None, fields=None, indicator=None,
+                 delegatedState='delegated', prefillDate=True):
         self.name = name
         self.title = title
         self.description = description
         self.actions = actions or list(editingRules)
         self.fields = fields or ('deadline', 'start-end', 'duration-effort')
         self.indicator = indicator
+        self.delegatedState = delegatedState
+        self.prefillDate = prefillDate
 
 workItemTypes = Jeep((
     WorkItemType('work', u'Unit of Work', indicator='work_work'),
@@ -150,7 +154,13 @@ workItemTypes = Jeep((
         actions=('plan', 'accept', 'finish', 'cancel', 
                  'modify', 'delegate', 'move', 'close', 'reopen'),
         fields =('deadline',),
-        indicator='work_deadline')
+        indicator='work_deadline'),
+    WorkItemType('checkup', u'Check-up',
+        actions=('accept', 'finish', 'cancel', 
+                 'modify', 'delegate', 'close', 'reopen'),
+        fields =('deadline', 'start-end',),
+        indicator='work_checkup',
+        delegatedState='closed', prefillDate=False),
 ))
 
 
@@ -182,7 +192,7 @@ class WorkItem(Stateful, Track):
 
     def getWorkItemType(self):
         name = self.workItemType
-        return name and workItemTypes[name] or None
+        return name and workItemTypes[name] or workItemTypes['work']
 
     @property
     def party(self):
@@ -259,7 +269,7 @@ class WorkItem(Stateful, Track):
             xkw = dict(kw)
             xkw.pop('party', None)
             delegated = self.createNew('delegate', userName, **xkw)
-        delegated.state = 'delegated'
+        delegated.state = self.getWorkItemType().delegatedState
         delegated.reindex('state')
         new = delegated.createNew('plan', userName, runId=0, **kw)
         new.data['source'] = delegated.name
@@ -284,7 +294,8 @@ class WorkItem(Stateful, Track):
         new.state = self.state
         new.reindex()
         moved.data['target'] = new.name
-        if self.state in ('planned', 'accepted', 'delegated', 'moved', 'done'):
+        if self.state in ('planned', 'accepted', 'delegated', 'moved', 
+                          'done', 'finished'):
             self.state = self.state + '_x'
             self.reindex('state')
         return new