source: collective.imstransport/trunk/collective/imstransport/utilities/imsinterchange.py @ 202

Revision 202, 10.7 KB checked in by brent, 4 years ago (diff)

Refactored CC writer.
Line 
1from Products.CMFCore.interfaces import ISiteRoot
2from collective.imstransport import IMSTransportMessageFactory as _
3from zope.interface import implements
4from collective.imstransport.utilities.interfaces import IIMSManifestReader, IIMSManifestWriter
5import md5
6from zope.component import getUtility
7import re
8
9class IMSReader(object):
10    """ Base class for IMS reader objects. """
11
12    implements(IIMSManifestReader)
13
14    def getPackageName(self):
15        """ Return the desciptive name of the package type. """
16        return None
17
18    def readPackage(self, file, context):
19        """ Read IMS manifest. Override this to read specific package info. """
20
21    # Helper functions for readPackage
22
23    def createIdFromFile(self, file):
24        """ Get Id from file path """
25        return file.split('/')[-1]
26
27    def createPathFromFile(self, file):
28        """ Get folder path from file path """
29        return '/'.join(file.split('/')[:-1])
30
31    def determineType(self, item, fn):
32        result = 'File'
33        docmimetypes = ['text/html', 'text/htm' 'text/plain' 'text/x-rst', 'text/structured']
34
35        if item.has_key('type'):
36            result = type
37        elif item.has_key('Format') and item['Format'] in docmimetypes:
38            result = 'Document'
39        elif item.has_key('Format') and 'image' in item['Format']:
40            result = 'Image'
41        else:
42            """ Determine the file mimetype """
43            site = getUtility(ISiteRoot)
44            mtr = site.mimetypes_registry
45            mimetype = mtr.lookupExtension(filename)
46           
47            if mimetype in docmimetypes:
48                result = 'Document'
49            elif 'image' in mimetype:
50                result = 'Image'
51        return result                   
52
53
54class IMSWriter(object):
55    """ Base class for IMS writer objects. """
56
57    implements(IIMSManifestWriter)
58
59    def _writeObjectData(self, obj, path):
60        """ Write file data to the destination object. """
61        if type(obj) == type(''):
62            data = obj       
63        else:
64            format = ''
65            if hasattr(obj.aq_explicit, 'Format'):
66                format = obj.Format()
67            if obj.Type() in ['File', 'Image'] and hasattr(obj.aq_explicit, 'data'):
68                    data = obj.data
69            elif 'text/html' == format and hasattr(obj.aq_explicit, 'getText'):
70                    data = obj.getText()
71            elif format in ['text/plain', 'text/x-rst', 'text/structured'] and hasattr(obj.aq_explicit, 'getRawText'):
72                    data = obj.getRawText()
73            else:
74                data = ''
75
76        if self.destination:
77            self.destination.writeFile(path, data)
78
79    def _getAllObjects(self, context):
80        """ Get all sub objects. """
81        objects = [obj.getObject() for obj in context.portal_catalog.searchResults(path={'query':('/'.join(context.getPhysicalPath())+'/'),'depth':-1})]
82        return [object for object in objects if not object.isPrincipiaFolderish or getattr(object.aq_explicit, 'getText', None)]
83
84    def _getChildrenObjects(self, parent, objects):
85        """ Get objects in current folder """
86        parentpath = '/'.join(parent.getPhysicalPath())
87        children = []
88        for object in objects:
89            rpath = '/'.join(object.getPhysicalPath()).replace(parentpath, '')
90
91            if len(rpath.split('/')) == 1:
92                children.append(object)
93                       
94        return children
95
96    def _getObjectPath(self, obj, context):
97        """ Get the path of an object. """
98
99        root_path = context.aq_explicit.virtual_url_path()
100        obj_path = obj.aq_explicit.virtual_url_path()
101
102        if obj_path.find(root_path) != 0:
103            return ''
104
105        # Remove the path of the folder object
106        path = obj_path.replace(root_path, '')
107        if path and path[0] == '/':
108            path = path[1:]
109
110        if not path:
111            return ''
112
113        if hasattr(obj.aq_explicit, 'Format'):
114            if 'text/html' == obj.Format() and obj.isPrincipiaFolderish:
115                path += '.html'
116
117        return path
118
119    def _createPathId(self, path, pre='RES'):
120        """ Create a unique id given a path """
121        return pre + str(md5.md5(path).hexdigest())
122
123    def _getCopyrightString(self, copyright, rights_holder, rights_holder_email):
124        cp = ''
125        if copyright:
126            cp += copyright
127        if rights_holder:
128            if cp:
129                cp += ', '
130            cp += rights_holder
131        if rights_holder_email:
132            if cp:
133                cp += ', '
134            cp += rights_holder_email
135        return cp
136 
137    def getObjSize(self, object):
138        """ Retrieves the correct size of the object"""
139        return '%d' %object.get_size()
140
141    def writeCustomMetadata(self, object):
142        """ Write the custom metdata for the package. Overridden at lower levels. """
143
144        return
145   
146
147   
148
149
150class IMSInterchangeReader(object):
151
152    implements(IIMSManifestReader)
153    name = _(u'IMS Interchange Reader')
154
155    def determineType(self, context, hashref, objDict, filename):
156        """ Determine the type of the incoming object """
157
158        if objDict[hashref].has_key('type') and objDict[hashref]['type']:
159            return objDict[hashref]['type']
160        elif objDict[hashref].has_key('Format') and objDict[hashref]['Format'] in ['text/html', 'text/htm' 'text/plain' 'text/x-rst', 'text/structured']:
161            return 'Document'
162        elif objDict[hashref].has_key('Format') and re.match('^image', objDict[hashref]['Format']):
163            return 'Image'
164        else:
165            return self.determineFileMimetype(filename, context)
166           
167    def createIdFromFile(self, file):
168        """ Get Id from file path """
169        return file.split('/')[-1]
170
171    def createPathFromFile(self, file):
172        """ Get folder path from file path """
173        return '/'.join(file.split('/')[:-1])
174
175
176    def determineFileMimetype(self, name, context):
177        """ Determine the file mimetype """
178        portal = context.portal_url.getPortalObject()
179        registry = portal.mimetypes_registry
180        mimetype = registry.lookupExtension(name)
181
182        if mimetype and mimetype.major() == 'text' and mimetype.minor() == 'html':
183            return 'Document'
184        elif mimetype and mimetype.major() == 'image':
185            return 'Image'
186        else:
187            return 'File'
188
189    def parseFile(self, context, file, objDict, hashref, id, path):
190        """ parse a file object and add data to it """
191        objDict[hashref]['file'] = file
192        objDict[hashref]['id'] = id
193        objDict[hashref]['path'] = path
194        objDict[hashref]['type'] = self.determineType(context, hashref, objDict, file)
195
196
197    def parseResourceMetadata(self, resourcereader, resourceid, context):
198        """ Read the resource metadata """
199
200        resourcereader.readGeneral()
201        resourcereader.readLifecycle()
202        resourcereader.readMetaMetadata()
203        resourcereader.readTechnical()
204        resourcereader.readRights()
205        customnode = resourcereader.getCustomData('', '')
206        if customnode:
207            metadict = resourcereader.readCustomMetadata(customnode)
208            resourcereader.appendCustomData(metadict)
209        return resourcereader.processResourceMetadata()
210       
211    def readCustomData(self, context, prefix, ns, location):
212        """
213        Hook for reading custom metadata for additional metadata requirements.
214        Should return a dictionary of values representing attribute name and value.
215        """
216
217        return {}
218
219    def getObjectDictionary(self):
220        """ Return the object dictionary """
221        return self.objdict
222
223
224    def getPackageName(self):
225
226        return self.name
227
228
229class IMSInterchangeWriter(object):
230
231    implements(IIMSManifestWriter)
232    name = _(u'IMS Interchange Writer') 
233
234
235    def _writeObjectData(self, obj, path):
236        """ Write file data to the destination object. """
237        if type(obj) == type(''):
238            data = obj       
239        else:
240            format = ''
241            if hasattr(obj.aq_explicit, 'Format'):
242                format = obj.Format()
243            if obj.Type() in ['File', 'Image'] and hasattr(obj.aq_explicit, 'data'):
244                    data = obj.data
245            elif 'text/html' == format and hasattr(obj.aq_explicit, 'getText'):
246                    data = obj.getText()
247            elif format in ['text/plain', 'text/x-rst', 'text/structured'] and hasattr(obj.aq_explicit, 'getRawText'):
248                    data = obj.getRawText()
249            else:
250                data = ''
251
252        if self.destination:
253            self.destination.writeFile(path, data)
254
255    def _getAllObjects(self, context):
256        """ Get all sub objects. """
257        objects = [obj.getObject() for obj in context.portal_catalog.searchResults(path={'query':('/'.join(context.getPhysicalPath())+'/'),'depth':-1})]
258        return [object for object in objects if not object.isPrincipiaFolderish or getattr(object.aq_explicit, 'getText', None)]
259
260    def _getChildrenObjects(self, parent, objects):
261        """ Get objects in current folder """
262        parentpath = '/'.join(parent.getPhysicalPath())
263        children = []
264        for object in objects:
265            rpath = '/'.join(object.getPhysicalPath()).replace(parentpath, '')
266
267            if len(rpath.split('/')) == 1:
268                children.append(object)
269                       
270        return children
271
272    def _getObjectPath(self, obj, context):
273        """ Get the path of an object. """
274
275        root_path = context.aq_explicit.virtual_url_path()
276        obj_path = obj.aq_explicit.virtual_url_path()
277
278        if obj_path.find(root_path) != 0:
279            return ''
280
281        # Remove the path of the folder object
282        path = obj_path.replace(root_path, '')
283        if path and path[0] == '/':
284            path = path[1:]
285
286        if not path:
287            return ''
288
289        if hasattr(obj.aq_explicit, 'Format'):
290            if 'text/html' == obj.Format() and obj.isPrincipiaFolderish:
291                path += '.html'
292
293        return path
294
295    def _createPathId(self, path, pre='RES'):
296        """ Create a unique id given a path """
297        return pre + str(md5.md5(path).hexdigest())
298
299    def _getCopyrightString(self, copyright, rights_holder, rights_holder_email):
300        cp = ''
301        if copyright:
302            cp += copyright
303        if rights_holder:
304            if cp:
305                cp += ', '
306            cp += rights_holder
307        if rights_holder_email:
308            if cp:
309                cp += ', '
310            cp += rights_holder_email
311        return cp
312 
313    def getObjSize(self, object):
314        """ Retrieves the correct size of the object"""
315        return '%d' %object.get_size()
316
317    def writeCustomMetadata(self, object):
318        """ Write the custom metdata for the package. Overridden at lower levels. """
319
320        return
321   
Note: See TracBrowser for help on using the repository browser.