source: ndgCommon/trunk/ndg/common/src/models/Atom.py @ 5767

Subversion URL: http://proj.badc.rl.ac.uk/svn/ndg/ndgCommon/trunk/ndg/common/src/models/Atom.py@5767
Revision 5767, 54.1 KB checked in by aharwood, 11 years ago (diff)

Corrected problem reading content tag

Line 
1'''
2 Class representing data in  atom format - allowing moles data to be stored and accessed in a web feed compatible way
3 
4 @author: C Byrom, Tessella Jun 2008
5'''
6import sys, logging, re, datetime
7from xml.sax.saxutils import escape, unescape
8from xml.etree import cElementTree as ET
9import csml.parser as CsmlParser
10import ndg.common.src.clients.xmldb.eXist.dbconstants as dc
11from ndg.common.src.lib.ETxmlView import et2text
12import ndg.common.src.lib.utilities as utilities
13from ndg.common.src.models.vocabtermdata import VocabTermData as VTD
14from ndg.common.src.models import MolesEntity as ME
15from ndg.common.src.models import Deployment as Deployment
16from ndg.common.src.models import AtomState
17from ndg.common.src.models.ndgObject import ndgObject
18
19class AtomError(Exception):
20    """
21    Exception handling for Atom class.
22    """
23    def __init__(self, msg):
24        logging.error(msg)
25        Exception.__init__(self, msg)
26
27
28class Person(object):
29    '''
30    Class representing atom author type data - with name, uri and role attributes
31    @keyword personType: Type of person to create - specified using the Person.._Type
32    values.  Default is AUTHOR_TYPE.
33    @keyword namespace: a two value array of format, ['short_namespace_name', 'full_namespace_name']
34    - e.g. ['moles', 'http://ndg.nerc.ac.uk/schema/moles2beta']
35    '''
36    AUTHOR_TYPE = 0
37    CONTRIBUTOR_TYPE = 1
38    RESPONSIBLE_PARTY_TYPE = 2
39    ELEMENT_NAMES = ["author", "contributor", "responsibleParty"]
40   
41    def __init__(self, personType = AUTHOR_TYPE, namespace = None):
42        self.type = personType
43        if namespace:
44            self.ns_shortname = namespace[0]
45            self.ns_fullname = namespace[1]
46        else:
47            self.ns_shortname = ""
48            self.ns_fullname = ndgObject.ATOM_NS
49           
50        self.name = ""
51        self.uri = ""
52        self.role = ""
53       
54        # NB, the atom format specifies slightly different data contents
55        self.uriTagName = "email"
56        # NB, responsible party data is always stored in the moles section
57        if self.type == self.RESPONSIBLE_PARTY_TYPE:
58            self.ns_shortname = 'moles'
59            self.ns_fullname = ndgObject.MOLES_NS
60            self.uriTagName = "uri"
61
62    def __str__(self):
63        if self.name or self.uri or self.role:
64            return self.name + " | " + self.uri + " | " + self.role
65        return ""
66
67
68    def hasValue(self):
69        if self.name or self.uri or self.role:
70            return True
71        return False
72   
73    def fromString(self, personString):
74        (self.name, self.uri, self.role) = utilities.getTripleData(personString)
75       
76    def fromETElement(self, personTag):
77        self.name = unescape(personTag.findtext('{%s}name' %self.ns_fullname) or "")
78        self.role = unescape(personTag.findtext('{%s}role' %self.ns_fullname) or "")
79        self.uri = unescape(personTag.findtext('{%s}%s' %(self.ns_fullname, self.uriTagName)) or "")
80        logging.debug("Added name: '%s', role: '%s', %s: '%s'" \
81                      %(self.name, self.role, self.uriTagName, self.uri))
82
83    def toXML(self):
84        prefix = ""
85        if self.ns_shortname:
86            prefix = self.ns_shortname + ':'
87
88        author = ET.Element(prefix + self.ELEMENT_NAMES[self.type])
89
90        if self.name:
91            name = ET.SubElement(author, prefix + "name")
92            name.text = escape(self.name)
93       
94        if self.uri:
95            uri = ET.SubElement(author, prefix + self.uriTagName)
96            uri.text = escape(self.uri)
97       
98        if self.role:
99            role = ET.SubElement(author, prefix + "role")
100            role.text = escape(self.role)
101
102        return author
103   
104    def __cmp__(self, person1):
105        '''
106        Override comparison to allow proper object comparison when checking
107        if Person objects are in an array already - i.e. if person in personArray...
108        '''
109        if not person1:
110            return -1
111       
112        if self is person1:
113            return 0
114        elif self.uri == person1.uri and self.name == person1.name and \
115                self.role == person1.role and self.type == person1.type:
116            return 0
117        return 1
118
119
120class Link(object):
121    '''
122    Class representing an atom link - with href, title and rel attributes
123    '''
124
125    def __init__(self):
126        self.href = ""
127        self.title = ""
128        self.rel = ""
129
130    def fromString(self, linkString):
131        (self.href, self.title, self.rel) = utilities.getTripleData(linkString, doEscape=False)
132        # ensure no funny characters are included on data ingest
133        self.title = utilities.escapeSpecialCharacters(self.title)
134       
135    def fromETElement(self, linkTag):
136        # remove any url quoting when reading in from XML - to avoid need for
137        # correction on display
138        self.href = unescape(linkTag.attrib.get('href') or "")
139        self.rel = unescape(linkTag.attrib.get('rel') or "")
140        self.title = unescape(linkTag.attrib.get('title') or "")
141
142    def toXML(self):
143        # ensure the xml element doesn't contain things like '&' - which will
144        # cause problems when running xqueries
145        link = ET.Element("link")
146        link.attrib["href"] = escape(self.href)
147        link.attrib["title"] = escape(self.title)
148        link.attrib["rel"] = escape(self.rel)
149        return link
150
151    def hasValue(self):
152        # NB, just a rel on its own is meaningless - so ignore
153        if self.href or self.title:
154            return True
155        return False
156   
157    def __str__(self):
158        if self.href or self.title or self.rel:
159            return self.href + " | " + self.title + " | " + self.rel
160        return ""
161   
162    def isChildAtom(self):
163        '''
164        Determines whether the link refers to another atom - e.g. a link to
165        a data granule
166        @return True, if so; False otherwise
167        '''
168        if self.rel.endswith(VTD.GRANULE_TERM) or \
169            self.rel.endswith(VTD.DEPLOYMENT_TERM) or \
170            self.rel.endswith(VTD.ACTIVITY_TERM) or \
171            self.rel.endswith(VTD.DPT_TERM) or \
172            self.rel.endswith(VTD.OBS_TERM):
173            return True
174       
175        return False
176   
177    def __cmp__(self, link1):
178        '''
179        Override comparison to allow proper object comparison when checking
180        if Link objects are in an array already - i.e. if link in linkArray...
181        '''
182        if not link1:
183            return -1
184       
185        if self is link1:
186            return 0
187        elif self.href == link1.href and self.title == link1.title and \
188                self.rel == link1.rel:
189            return 0
190        return 1
191
192
193class Category(object):
194    '''
195    Class representing an atom category - with term, scheme and label attributes
196    '''
197    def __init__(self):
198        self.term = ""
199        self.scheme = ""
200        self.label = ""
201
202    def fromString(self, linkString, escapeSpecialCharacters=True):
203        '''
204        Create Category from triple string of format, 'label | scheme | term'
205        @param linkString: triple string to create category with
206        @keyword escapeSpecialCharacters: if set to True, special characters in
207        triple string are escaped (default)
208        '''
209        (self.label, self.scheme, self.term) = utilities.getTripleData(linkString, \
210            doEscape=escapeSpecialCharacters)
211
212        # also replace any double quotes with single apostrophes - since this data
213        # is stored as an attribute - i.e. already surrounded by double quotes
214        self.label = self.label.replace("\"", "'")
215        self.scheme = self.scheme.replace("\"", "'")
216        self.term = self.term.replace("\"", "'")
217       
218       
219    def fromETElement(self, linkTag):
220        self.term = unescape(linkTag.attrib.get('term') or "")
221        self.label = unescape(linkTag.attrib.get('label') or "")
222        self.scheme = unescape(linkTag.attrib.get('scheme') or "")
223
224    def toXML(self):
225        link = ET.Element("category")
226        link.attrib["term"] = escape(self.term)
227        link.attrib["scheme"] = escape(self.scheme)
228        link.attrib["label"] = escape(self.label)
229        return link
230   
231    def hasValue(self):
232        if self.scheme or self.label or self.term:
233            return True
234        return False
235
236
237class Atom(object):
238
239    # labels for use with the atom categories
240    ATOM_TYPE = "ATOM_TYPE"
241    ATOM_SUBTYPE = "ATOM_SUBTYPE"
242
243    # labels for use with the templates to set/extract specific inputs
244    ONLINE_REF_LABEL = "online_ref"
245    PARAMETER_LABEL = "parameter"
246    ATOM_REF_LABEL = "atom_ref"
247    DELIMITER = "---"
248    REMOVE_LABEL = "remove"
249   
250    # format to use for t1-t2 date range
251    YEAR_FORMAT = '%Y-%m-%d'
252
253    # subtype name, when not defined
254    SUB_TYPE_NOT_DEFINED_NAME = "Not currently defined"
255
256    def __init__(self, atomType = None, vocabTermData = None, ndgObject = None, \
257                 xmlString = None, state = AtomState.WORKING_STATE, **inputs):
258        '''
259        Constructor - initialise the atom variables
260        @keyword atomType: type of atom to set up
261        @keyword vocabTermData: instance of VocabTermData object to use with atom
262        @keywork ndgObject: instance of ndgObject to use with atom
263        @keyword xmlString: XML representation of atom - will be parsed to populate
264        the atom data
265        @keyword state:  AtomState object representing the state of the atom
266        @param inputs: a dict with vals to set directly against the object fields
267        '''
268        logging.info("Initialising atom")
269        if atomType:
270            logging.info(" - of type '%s'" %atomType)
271        self.atomTypeID = atomType
272
273        # some data have further subtypes specified
274        self.subtypeID = None # this should be the termID
275        self.subtype = None # and this should be the fully formed vocab URL
276       
277        self.ndgObject = ndgObject
278
279        self.atomName = None
280        self.files = []
281        self.author = Person()
282        self.contributors = []
283        self.atomAuthors = []
284        self.parameters = []
285        self.spatialData = []
286        self.temporalData = []
287        self.relatedLinks = []
288        self.summary = ""
289        self.content = []
290        # NB, this deployments data duplicates other atom data - and is only used for a
291        # convenient way to collect the info (by lookupAssociatedData()) for use in templates
292        self.deployments = []
293        # ditto for the following field
294        self.dataEntities = []
295           
296        self.csmlFile = None
297        self.cdmlFile = None
298        # general variable to use for setting the atom content - NB, if a csmlFile is specified
299        # (either directly or via a cdmlFile specification), this will be the content by default
300        # for this purpose
301        self.contentFile = None     
302        self.title = None
303        self.datasetID = None        # NB, the dataset id ends up in the atomName - <path><datasetID>.atom
304        self.atomID = None
305   
306        # boundary box info - to replace spatial/temporalData?
307        self.minX = None
308        self.minY = None
309        self.maxX = None
310        self.maxY = None
311        self.t1 = None
312        self.t2 = None
313
314        self.ME = ME.MolesEntity(**inputs)
315       
316        # date when the atom was first ingested
317        self.publishedDate = None
318
319        # last update date
320        self.updatedDate = None
321
322        # assume atom in working state by default - this is used to define what collection
323        # in eXist the atom is stored in
324        self.state = state
325       
326        # additional, non standard atom data can be included in the molesExtra element
327        if vocabTermData:
328            self.VTD = vocabTermData
329        else:
330            self.VTD = VTD()
331       
332        if xmlString:
333            self.fromString(xmlString)
334
335        # retain old title, in case it has changed - NB, this will be done by applying
336        # the inputs dict - and might require other atoms to be updated
337        self.oldTitle = self.title
338           
339        # if inputs passed in as dict, add these now
340        if inputs:
341            logging.info("Adding info to atom from input dict")
342            logging.debug(inputs)
343           
344            # avoid the initial case being caught - i.e. when there is no title at all
345            if inputs.has_key('title'):
346                newTitle = inputs.get('title')
347                if not self.title:
348                    self.oldTitle = newTitle
349                   
350            self.__dict__.update(inputs)
351            self.ME.__dict__.update(inputs)
352           
353            # NB, this doesn't trigger the Content Property, so do this
354            # explicitly, if need be
355            if inputs.has_key('Content'):
356                self.Content = inputs.get('Content')
357            if inputs.has_key('author'):
358                name = inputs.get('author')
359                author = Person()
360                author.fromString(name)
361                self.author = author
362
363        if self.atomTypeID:
364            self.atomTypeName = self.VTD.TERM_DATA[self.atomTypeID].title
365
366        self.deploymentsURL = ""
367        self.dataEntitiesURL = ""
368
369        logging.info("Atom initialised")
370
371
372    def addOnlineReferences(self, links):
373        '''
374        Add online reference data associated with the atom
375        - NB, care needs to be taken here since this data is stored in the atom
376        link elements and these are also used for the various atom associations
377        @param links: a Link or array of Links to add to the relatedLinks attribute
378        '''
379        logging.debug("Adding online references")
380        if not links:
381            return
382       
383        if type(links) is not list:
384            links = [links]
385       
386        # firstly clear out any online refs data from the existing related links
387        newLinks = []
388        for link in self.relatedLinks:
389            if link.isChildAtom():
390                newLinks.append(link)
391       
392        newLinks.extend(links)
393        self.relatedLinks = newLinks
394        logging.debug("Online references added")
395
396
397    def addUniqueRelatedLinks(self, links):
398        '''
399        Add links to relatedLinks array - if they are not already included
400        @param links: a Link or array of Links to add to the relatedLinks attribute
401        '''
402        self.addUniqueLinks(self.relatedLinks, links)
403       
404
405    def removeRelatedLinks(self, linksToDelete):
406        '''
407        Remove any links in the input list from the atom's related links list
408        @param linksToDelete: array of Link objects to remove from atom
409        '''
410        logging.debug("Removing related links from atom")
411        if not linksToDelete:
412            return
413       
414        if type(linksToDelete) is not list:
415            linksToDelete = [linksToDelete]
416       
417        updatedLinks = []
418        for link in self.relatedLinks:
419            if type(link) is not Link:
420                logging.warning("Link is not of 'Link' object type (type='%s') - skipping" %type(link))
421                continue
422            if link in linksToDelete:
423                logging.debug("- found link to remove")
424            else:
425                updatedLinks.append(link)
426
427        self.relatedLinks = updatedLinks
428        logging.debug("Links removed")
429
430    def getPublicationStatePath(self):
431        '''
432        Determine the correct publication state collection for the atom
433        @return collectionPath: collection path for the publication state of the atom
434        '''
435        logging.debug("Getting collection path for atom publication state")
436        collectionPath = dc.ATOM_COLLECTION_PATH + self.state.collectionPath
437        logging.debug("Returning publication state collection, '%s'" %collectionPath)
438        return collectionPath
439       
440
441    def getDefaultEntityCollectionPath(self):
442        '''
443        Determine the correct collection for the entity type of the atom
444        @return entityPath: collection path for the data type of the atom
445        '''
446        logging.debug("Getting collection path for atom entity type")
447        collectionPath = self.getPublicationStatePath()
448       
449        if self.atomTypeID == VTD.DE_TERM:
450            collectionPath += dc.DE_COLLECTION_PATH
451        elif self.atomTypeID == VTD.GRANULE_TERM:
452            collectionPath += dc.GRANULE_COLLECTION_PATH
453        elif self.atomTypeID == VTD.ACTIVITY_TERM and \
454            self.subtypeID == VTD.DEPLOYMENT_TERM:
455            collectionPath += dc.DEPLOYMENTS_COLLECTION_PATH
456        else:
457            collectionPath += dc.DEPLOYMENT_COLLECTION_PATH
458       
459        logging.debug("Returning entity collection, '%s'" %collectionPath)
460        return collectionPath
461       
462
463    def getDefaultCollectionPath(self):
464        '''
465        Determine the correct collection to use for the atom in eXist
466        '''
467        logging.debug("Getting default collection path for atom")
468        collectionPath = self.getDefaultEntityCollectionPath()
469        if not self.ME.providerID:
470            raise AtomError("Error: cannot determine atom collection path because " + \
471                            "the provider ID is not defined")
472           
473        collectionPath += self.ME.providerID + "/"
474        logging.debug("Returning collection, '%s'" %collectionPath)
475        return collectionPath
476
477
478    def __addAtomTypeDataXML(self, root):
479        '''
480        Add the atom type, and subtype data, if available, to atom categories
481        - and lookup and add the appropriate vocab term data
482        '''
483        if self.atomTypeID:
484            logging.info("Adding atom type info to XML output")
485            category = Category()
486            category.label = self.atomTypeID
487            # look up the appropriate vocab term data
488            category.scheme = self.VTD.getTermCurrentVocabURL(self.atomTypeID)
489            category.term = self.ATOM_TYPE
490            root.append(category.toXML())
491
492        if self.subtypeID:
493            logging.info("Adding atom subtype info to XML output")
494            # NB subtypes not all defined, so leave this out for the moment
495            category.label = self.subtypeID
496            # look up the appropriate vocab term data
497            category.scheme = self.VTD.getTermCurrentVocabURL(self.subtypeID)
498            category.term = self.ATOM_SUBTYPE
499            root.append(category.toXML())
500
501
502    def addMolesEntityData(self, abbreviation, provider_id, object_creation_time):
503        '''
504        Add data to include in the moles entity element
505        '''
506        logging.debug('Adding moles entity information')
507        self.ME.abbreviation = abbreviation
508        self.ME.providerID = provider_id
509        self.ME.createdDate = utilities.getISO8601Date(object_creation_time)
510        logging.debug('Moles entity information added')
511
512
513    def addAuthors(self, authors):
514        '''
515        Add author data appropriately to the atom
516        NB, these will overwrite any existing authors of the same type
517        @param authors: list of Person objects with the author data
518        '''
519        logging.debug('Adding authors data to Atom')
520        isFirstAuthor = {}
521        authorArray = None
522        for author in authors:
523            # NB, we're only allowed one atom author
524            if author.type == Person.AUTHOR_TYPE:
525                self.author = author
526                   
527                if isFirstAuthor.has_key(author.type):
528                    raise AtomError("Error: an atom can only have one author specified")
529                isFirstAuthor[author.type] = 1
530                continue
531            elif author.type == Person.CONTRIBUTOR_TYPE:
532                authorArray = self.contributors
533            elif author.type == Person.RESPONSIBLE_PARTY_TYPE:
534                authorArray = self.ME.responsibleParties
535               
536            # check if this is the first addition - if so, clear out the
537            # array in advance
538            if not isFirstAuthor.has_key(author.type):
539                logging.debug("Clearing out author array")
540                # NB, need to be careful to clear the array, not create a ref
541                # to a new array
542                del authorArray[:]
543                isFirstAuthor[author.type] = 1
544
545            if author.hasValue() and author not in authorArray:
546                logging.debug("Adding author (type:'%s', name:'%s', uri:'%s', role:'%s')" \
547                              %(author.type, author.name, author.uri, author.role))
548                authorArray.append(author)
549
550        logging.debug('Finished adding authors data')
551
552
553    def _isNewParameter(self, param):
554        '''
555        Check if a parameter is already specified in the atom, return False if
556        so, otherwise return True
557        '''
558        for p in self.parameters:
559            if p.term == param.term and \
560                p.scheme == param.scheme and \
561                p.label == param.label:
562                return False
563        return True
564
565
566    def addRelatedLinks(self, linkVals):
567        '''
568        Add related links in string format - converting to Link objects
569        NB, only add the link if it is unique
570       
571        @param linkVals: string of format, 'uri | title | vocabServerURL'
572        '''
573        link = self.objectify(linkVals, 'relatedLinks')
574        if link not in self.relatedLinks:
575            self.relatedLinks.append(link)
576
577
578    def addParameters(self, params):
579        '''
580        Add a parameter to list - ensuring it is unique and has been formatted and tidied appropriately
581        @params param: parameter, as string array, to add to atom parameters collection
582        '''
583        # avoid strings being parsed character by character
584        if type(params) is str:
585            params = [params]
586           
587        for param in params:
588            # firstly tidy parameter
589            param = utilities.tidyUpParameters(param)
590            category = Category()
591            # NB, data already tidied up here, so set keyword to avoid this happening again
592            category.fromString(param, escapeSpecialCharacters=False)
593
594            # now check for uniqueness
595            if self._isNewParameter(category):
596                logging.debug("Adding new parameter: %s" %param)
597                self.parameters.append(category)
598   
599   
600    def _linksToXML(self, root):
601        '''
602        Add required links to the input element
603        @param root: element to add links to - NB, should be the root element of the atom
604        '''
605        selfLink = ET.SubElement(root, "link")
606        selfLink.attrib["href"] = self.atomBrowseURL
607        selfLink.attrib["rel"] = "self"
608       
609        for relatedLink in self.relatedLinks:
610            if relatedLink.hasValue():
611                root.append(relatedLink.toXML())
612   
613    def toXML(self):
614        '''
615        Convert the atom into XML representation and return this
616        @return: xml version of atom
617        '''
618        logging.info("Creating formatted XML version of Atom")
619        root = ET.Element("entry")
620        root.attrib["xmlns"] = ndgObject.ATOM_NS
621        root.attrib["xmlns:moles"] = ndgObject.MOLES_NS
622        root.attrib["xmlns:georss"] = ndgObject.GEOSS_NS
623        root.attrib["xmlns:gml"] = ndgObject.GML_NS
624        id = ET.SubElement(root, "id")
625        id.text = self.atomID
626        title = ET.SubElement(root, "title")
627        title.text = escape(self.title or "")
628        self._linksToXML(root)
629
630        if self.author and self.author.hasValue():
631            root.append(self.author.toXML())
632           
633        for contributor in self.contributors:
634            root.append(contributor.toXML())
635
636        # add parameters data
637        for param in self.parameters:
638            if param.hasValue():
639                root.append(param.toXML())
640
641        # add the type and subtype data
642        self.__addAtomTypeDataXML(root)
643                   
644        summary = ET.SubElement(root, "summary")
645        summary.text = escape(self.summary)
646                   
647        # add link to content, if required - NB, can only have one content element in atom
648        # - and this is mandatory
649        content = ET.SubElement(root, "content")
650        contentFile = self.contentFile or self.csmlFile or self.cdmlFile
651        if contentFile:
652            content.attrib["type"] = "application/xml"
653            content.attrib["src"] = contentFile
654        else:
655            content.attrib["type"] = "xhtml"
656            div = ET.SubElement(content, 'xhtml:div')
657            div.attrib["xmlns:xhtml"] = ndgObject.XHTML_NS
658           
659            div.text = self.Content
660       
661        # if there's a published date already defined, assume we're doing an update now
662        # NB, update element is mandatory
663        currentDate = datetime.datetime.today().strftime("%Y-%m-%dT%H:%M:%SZ")
664        if not self.publishedDate:
665            self.publishedDate = currentDate
666
667        updated = ET.SubElement(root, "updated")
668        if not self.updatedDate:
669            self.updatedDate = currentDate
670        updated.text = self.updatedDate
671
672        published = ET.SubElement(root, "published")
673        published.text = self.publishedDate
674
675        # add the moles entity section, if it is required
676        if self.ME:
677            root.append(self.ME.toXML())
678
679        # add temporal range data, if available
680        temporalRange = ET.SubElement(root, "moles:temporalRange")
681        if self.t1:
682            temporalRange.text = escape(self.t1)
683            if self.t2:
684                temporalRange.text += "/" + escape(self.t2)
685
686        # add spatial range data, if available
687        self._addSpatialData(root)
688
689        tree = ET.ElementTree(root)
690        logging.info("XML version of Atom created")
691        return tree
692
693
694    def __getContent(self):
695        logging.debug("Getting content data")
696        contentString = ""
697        # NB, there must be content specified in an atom
698        if not self.content:
699            return "Metadata document"
700       
701        for content_line in self.content:
702            contentString += content_line + "\n"
703
704        return contentString
705
706    def __setContent(self, content):
707        logging.debug("Adding content data")
708        self.content = []
709        if not content:
710            return
711       
712        for content_line in content.split('\n'):
713            self.content.append(content_line)
714           
715    Content = property(fset=__setContent, fget=__getContent, doc="Atom content")
716
717           
718    def fromString(self, xmlString):
719        '''
720        Initialise Atom object using an xmlString
721        @param xmlString: representation of atom as an XML string
722        '''
723        logging.info("Ingesting data from XML string")
724        logging.debug("Create elementtree instance with XML string")
725        tree = ET.fromstring(xmlString)
726        title = tree.findtext('{%s}title' %ndgObject.ATOM_NS)
727        if title:
728            logging.debug("Adding title data")
729            self.title = unescape(title)
730
731        summary = tree.findtext('{%s}summary' %ndgObject.ATOM_NS)
732        if summary:
733            self.summary = unescape(summary)
734
735        authorElement = tree.find('{%s}author' %ndgObject.ATOM_NS)
736        if authorElement:
737            logging.debug("Adding author data")
738            author = Person()
739            author.fromETElement(authorElement)
740            self.author = author
741
742        contributorElements = tree.findall('{%s}contributor' %ndgObject.ATOM_NS)
743        for contributorElement in contributorElements:
744            logging.debug("Adding contributor data")
745            contributor = Person(personType = Person.CONTRIBUTOR_TYPE)
746            contributor.fromETElement(contributorElement)
747            self.contributors.append(contributor)
748
749        molesElement = tree.find('{%s}entity' %ndgObject.MOLES_NS)
750        if molesElement:
751            self.ME.fromET(molesElement)
752               
753        atomID = tree.findtext('{%s}id' %ndgObject.ATOM_NS)
754        self.__parseAtomID(atomID)
755       
756        self._parseCategoryData(tree.findall('{%s}category' %ndgObject.ATOM_NS))
757
758        self._parseLinksData(tree.findall('{%s}link' %ndgObject.ATOM_NS))
759           
760        contentTag = tree.find('{%s}content' %ndgObject.ATOM_NS)
761        if contentTag != None:
762            logging.debug("Found content tag - checking for CSML/CDML file data")
763            file = contentTag.attrib.get('src')
764            if file:
765                # NB, the path will reveal more reliably whether we're dealing with CSML and CDML files
766                if file.upper().find('CSML') > -1:
767                    logging.debug("Adding CSML file data")
768                    self.csmlFile = file
769                elif file.upper().find('CDML') > -1:
770                    logging.debug("Adding CDML file data")
771                    self.cdmlFile = file
772                self.contentFile = file
773            else:
774                logging.debug("No file data - adding contents of element instead")
775                # the div ns is sometimes handled differently - cope with both
776                # options
777               
778                tag = '{%s}div'%ndgObject.XHTML_NS
779                divEl = contentTag.find(tag)
780               
781                if divEl is None:
782                    tag = '{%s}div'%ndgObject.ATOM_NS
783                    divEl = contentTag.find(tag)                                   
784                   
785                if divEl is not None:
786                   
787                    div = divEl.text
788                   
789                    # NB, this can contain xhtml, so check for children
790                    for child in divEl.getchildren():
791                        div += ET.tostring(child)
792   
793                    # NB, Elementtree tends to revert the namespace of the xhtml
794                    # elements to the parent Atom NS - so switch this back
795                    div = div.replace(ndgObject.ATOM_NS, ndgObject.XHTML_NS)
796                    self.Content = div
797       
798        range = tree.findtext('{%s}temporalRange' %ndgObject.MOLES_NS)
799        if range:
800            logging.debug("Adding temporal range data")
801            timeData = range.split('/')
802            self.t1 = unescape(timeData[0])
803            if len(timeData) > 1:
804                self.t2 = unescape(timeData[1])
805       
806        where = tree.find('{%s}where' %ndgObject.GEOSS_NS)
807        if where:
808            # NB, this parser won't mind if we're dealing with Envelope or EnvelopeWithTimePeriod
809            minBBox = where.findall('.//{%s}lowerCorner' %ndgObject.GML_NS)
810            if minBBox:
811                logging.debug("Adding min spatial range data")
812                minBBox = minBBox[0]
813                spatialData = minBBox.text.split()
814                self.minX = unescape(spatialData[0])
815                if len(spatialData) > 1:
816                    self.minY = unescape(spatialData[1])
817           
818            maxBBox = where.findall('.//{%s}upperCorner' %ndgObject.GML_NS)
819            if maxBBox:
820                maxBBox = maxBBox[0]
821                logging.debug("Adding max spatial range data")
822                spatialData = maxBBox.text.split()
823                self.maxX = unescape(spatialData[0])
824                if len(spatialData) > 1:
825                    self.maxY = unescape(spatialData[1])
826               
827        publishedDate = tree.findtext('{%s}published' %ndgObject.ATOM_NS)
828        if publishedDate:
829            logging.debug("Adding published date")
830            self.publishedDate = publishedDate
831               
832        updatedDate = tree.findtext('{%s}updated' %ndgObject.ATOM_NS)
833        if updatedDate:
834            logging.debug("Adding updated date")
835            self.updatedDate = updatedDate
836           
837        logging.info("Completed data ingest")
838   
839   
840    def _parseCategoryData(self, categories):
841        logging.debug("Adding category/parameters data")
842        for category in categories:
843            cat = Category()
844            cat.fromETElement(category)
845           
846            if cat.term == self.ATOM_TYPE:
847                logging.debug("Found atom type data")
848                self.atomTypeID = cat.label
849                self.atomTypeName = self.VTD.TERM_DATA[cat.label].title
850                continue
851            elif cat.term == self.ATOM_SUBTYPE:
852                logging.debug("Found atom subtype data")
853                self.subtypeID = cat.label
854                self.subtype = cat.scheme
855                continue
856
857            self.parameters.append(cat)
858
859
860    def __parseAtomID(self, atomID):
861        '''
862        Given an atom ID, extract the useful bits of info and set these on
863        the relevant atom attributes
864        @param atomID: an atom ID in the 'tag' format
865        '''
866        logging.debug("Extracting atom info from ID, '%s'" %atomID)
867        self.atomID = atomID
868        self.datasetID = atomID.split("__ATOM__")[-1]
869        self._generateAtomName(self.datasetID)
870        logging.debug("- all info extracted")
871   
872
873    def setDatasetID(self, datasetID):
874        '''
875        Set the dataset ID for the atom - and generate an appropriate atom name using this
876        @param datasetID: ID to set for the atom
877        '''
878        self.datasetID = datasetID
879        self._generateAtomName(datasetID) 
880        self.atomID = self.createAtomID(datasetID)
881
882
883    def createAtomID(self, datasetID):
884        '''
885        Create a unique ID, conforming to atom standards, for atom
886        NB, see http://diveintomark.org/archives/2004/05/28/howto-atom-id
887        @param datasetID: ID of atom's dataset
888        @return: unique ID
889        '''
890        logging.info("Creating unique ID for atom")
891        if not self.atomBrowseURL:
892            self._generateAtomName(datasetID)
893        urlBit = self.atomBrowseURL.split('://')[1]
894        urlBit = urlBit.replace('#', '')
895        urlBits = urlBit.split('/')
896        host = urlBits[0].split(':')[0] # avoid the port colon - as this breaks the ID format
897        dateBit = datetime.datetime.today().strftime("%Y-%m-%d")
898       
899        id = "tag:" + host + "," + dateBit + ":/" + "/".join(urlBits[1:])
900        logging.info("- unique ID created for atom")
901        logging.debug(" - '%s'" %id)
902        return id
903       
904       
905    def _generateAtomName(self, datasetID):
906        '''
907        Generate a consistent name for the atom - with full eXist doc path
908        @param datasetID: ID of atom's dataset
909        '''
910        self.atomName = datasetID + ".atom"
911        if not self.ME.providerID:
912            raise ValueError("Provider ID has not been specified for atom - please add this and retry")
913        self.ndgURI = self.ME.providerID + "__ATOM__" + datasetID
914        self.atomBrowseURL = VTD.BROWSE_ROOT_URL + self.ndgURI
915
916
917    def _parseLinksData(self, links):
918        '''
919        Extract links and atom data from array of link elements in the XML representation of the atom
920        @param links: an array of <link> elements
921        '''
922        # firstly, get all data to start with, so we can properly process it afterwards
923        linkData = {}
924        logging.debug("Getting link data")
925        for linkTag in links:
926            link = Link()
927            link.fromETElement(linkTag)
928
929            if not linkData.has_key(link.rel):
930                linkData[link.rel] = []
931           
932            linkData[link.rel].append(link)
933
934        # there should be one self referencing link - which will provide info on the atom itself
935        if not linkData.has_key('self'):
936            errorMessage = "Atom does not have self referencing link - " + \
937                "cannot ascertain datasetID without this - please fix"
938            logging.error(errorMessage)
939            raise ValueError(errorMessage)
940       
941        # this is the link describing the atom itself
942        self.atomBrowseURL = linkData['self'][0].href
943       
944        self.datasetID = self.atomBrowseURL.split("__ATOM__")[-1]
945        self.atomName = self.datasetID + ".atom"
946        # NB, only split on the stem, since the browse host may not be
947        # the same as that defined in VTD
948        self.ndgURI = self.atomBrowseURL.split(VTD.BROWSE_STEM_URL)[-1]
949       
950        # now remove this value and the associated moles doc link
951        del linkData['self']
952        molesDoc = self.atomBrowseURL.replace('ATOM', 'NDG-B1')
953        if linkData.has_key('related'):
954            relatedLinks = []
955            for link in linkData['related']:
956                if link.href != molesDoc:
957                    relatedLinks.append(link)
958           
959            linkData['related'] = relatedLinks
960               
961        # now add the remaining links to the atom
962        for key in linkData:
963            for link in linkData[key]:
964                logging.debug("Adding link data")
965                self.relatedLinks.append(link)
966       
967
968    def _addSpatialData(self, element):
969        '''
970        Add spatial coverage element to an input element
971        @param element: element to add coverage data to
972        '''
973        logging.info("Adding spatial data to Atom")
974        if not self.minX:
975            logging.info("No spatial data specified")
976            return
977        bbox = ET.SubElement(element, "georss:where")
978        envelope = ET.SubElement(bbox, "gml:Envelope")
979        lc = ET.SubElement(envelope, "gml:lowerCorner")
980        lc.text = escape(str(self.minX) + " " + str(self.minY))
981        uc = ET.SubElement(envelope, "gml:upperCorner")
982        uc.text = escape(str(self.maxX) + " " + str(self.maxY))
983
984       
985    def setAttribute(self, attributeName, attributeValue, escapeSpecials = True):
986        '''
987        Set the value of an atom attribute - and do some basic tidying up of the string content
988        - to escape any XML unfriendly characters
989        @param attributeName: name of the attribute whose value to set
990        @param attributeValue: value to set the attribute to 
991        @keyword escapeSpecials: if true, escape any special characters in the attribute
992        content.  Default = True
993        '''
994        logging.debug("Setting attribute, %s, to %s" %(attributeName, attributeValue))
995        origValue = attributeValue
996       
997        # escape any special characters if a value has been specified
998        # NB, need to cope with both single values and arrays
999        isList = True
1000        if attributeValue:
1001            if not isinstance(attributeValue, list):
1002                attributeValue = [attributeValue]
1003                isList = False
1004               
1005            newVals = []
1006            for val in attributeValue:
1007                data = val
1008                if escapeSpecials:
1009                    utilities.escapeSpecialCharacters(val)
1010                newVals.append(self.objectify(data, attributeName))
1011            attributeValue = newVals
1012
1013        # handle the special case of authors; only one author is allowed per atom
1014        # - the others should be treated as contributors
1015        if attributeName == "authors":
1016            setattr(self, "author", attributeValue[0])
1017            if len(attributeValue) > 1:
1018                setattr(self, "contributors", attributeValue[1:])
1019        elif attributeName == "atomAuthors":
1020            self.ME.responsibleParties.extend(attributeValue)
1021        elif attributeName == "files":
1022            self.addUniqueRelatedLinks(attributeValue)
1023        else:
1024            if not isList:
1025                attributeValue = attributeValue[0]
1026            setattr(self, attributeName, attributeValue)
1027
1028
1029    def objectify(self, objectVals, attributeName):
1030        '''
1031        Some inputs are specified as strings but need to be converted into
1032        objects - do this here
1033        @param objectVals: a '|' delimited string of values
1034        @param attributeName: name of attribute the values belong to
1035        '''
1036        obj = None
1037        if type(objectVals) != str:
1038            return objectVals
1039       
1040        if attributeName == "relatedLinks":
1041            obj = Link()
1042        elif attributeName == "atomAuthors":
1043            obj = Person(personType = Person.RESPONSIBLE_PARTY_TYPE)
1044        elif attributeName == "authors":
1045            # NB, ensure there is only one author tag - extra authors are contributors
1046            authorType = Person.AUTHOR_TYPE
1047            if self.author and self.author.hasValue():
1048                authorType= Person.CONTRIBUTOR_TYPE
1049            obj = Person(personType = authorType)
1050        elif attributeName == 'files':
1051            obj = Link()
1052            objectVals = '%s|%s|%s' \
1053                %(self.VTD.getTermCurrentVocabURL(VTD.METADATA_SOURCE_TERM), objectVals, VTD.METADATA_SOURCE_TERM)
1054
1055        if obj:
1056            obj.fromString(objectVals)
1057            # NB, need to set it now, just in case we don't set it before coming back
1058            if attributeName == "authors" and (not self.author or not self.author.hasValue()):
1059                self.author = obj
1060            return obj
1061       
1062        return objectVals
1063
1064
1065    def toPrettyXML(self):
1066        '''
1067        Returns nicely formatted XML as string
1068        '''
1069        atomXML = self.toXML()
1070
1071        # create the string
1072        logging.debug("Converting the elementtree object into a string")
1073        prettyXML = et2text(atomXML.getroot())
1074
1075        # add XML version tag
1076        prettyXML = "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n" + prettyXML
1077        logging.info("Created formatted version of XML object")
1078        return prettyXML
1079
1080
1081    def getLinksOfType(self, termID):
1082        '''
1083        Returns links in the atom related links attribute which match the specified
1084        term ID
1085        @param termID: the termID to look for in the related links - NB, this is
1086        matched to the end of the link.rel value
1087        @return links: array of Link objects with matching term type
1088        '''
1089        logging.debug("Getting atom links of type, '%s'" %termID)
1090        matchingLinks = []
1091        for link in self.relatedLinks:
1092            # firstly, handle special case where we only want the online ref type links
1093            # returned
1094            if termID == self.ONLINE_REF_LABEL:
1095                if not link.isChildAtom():
1096                    logging.debug("- found link with matching term type")
1097                    matchingLinks.append(link)
1098               
1099            elif link and link.rel and link.rel.lower().endswith(termID.lower()):
1100                logging.debug("- found link with matching term type")
1101                matchingLinks.append(link)
1102               
1103        logging.debug("Returning matched links")
1104        return matchingLinks
1105       
1106       
1107    def getLogos(self):
1108        '''
1109        Return related links that are logos
1110        @return: array of Links containing the logos for the atom
1111        '''
1112        logos = []
1113        for link in self.relatedLinks:
1114            if link.rel.lower().endswith(VTD.LOGO_TERM.lower()):
1115                logos.append(link)
1116               
1117        return logos
1118   
1119   
1120    def isGranule(self):
1121        if self.atomTypeID == VTD.GRANULE_TERM:
1122            return True
1123        return False
1124   
1125   
1126    def isDE(self):
1127        if self.atomTypeID == VTD.DE_TERM:
1128            return True
1129        return False
1130   
1131    def isDeployment(self):
1132        if self.subtypeID and self.subtypeID == VTD.DEPLOYMENT_TERM:
1133            return True
1134        return False
1135   
1136    def isDeployable(self):
1137        if (self.atomTypeID == VTD.ACTIVITY_TERM and self.subtypeID != VTD.DEPLOYMENT_TERM) or \
1138            self.atomTypeID == VTD.DPT_TERM or \
1139            self.atomTypeID == VTD.OBS_TERM:
1140            return True
1141        return False
1142   
1143    def isPublished(self):
1144        '''
1145        Check state of atom doc - if published or Published return True,
1146        otherwise return False
1147        '''
1148        return self.state.isPublishedState()
1149       
1150       
1151    def addCSMLData(self, csmlName, csmlContent, aggregateCoverage=False, useCSMLID=False):
1152        '''
1153        Parse CSML data and add extracted info to the atom
1154        @param csmlName: name of the csml file
1155        @param csmlContent: content of the csml file - NB, if this is set to None and the
1156        file, csmlName, is available locally, CsmlParser.Dataset will read in the file
1157        directly
1158        @keyword aggregateCoverage: if set to True, only coverage data that extends the
1159        atom coverage data will be added
1160        @keyword useCSMLID: if True, use the CSML doc ID as the dataset ID - NB,
1161        this should only be True if creating a new atom - e.g. from a granulite
1162        @return csmlDoc: the CsmlParser.Dataset object with the csml data in
1163        '''
1164        logging.info("Creating CSML data model")
1165        self.csmlFile = csmlName
1166        self.contentFile = csmlName
1167        content = csmlContent or csmlName
1168   
1169        csmlDoc = CsmlParser.Dataset(file=content)
1170       
1171        logging.info("Extracting info from CSML file")
1172        logging.debug("Got dataset ID: %s" %csmlDoc.id)
1173        if useCSMLID:
1174            logging.debug(" - using this ID for the atom")
1175            self.setDatasetID(VTD.GRANULE_TERM + '_' + csmlDoc.id)
1176       
1177        title = csmlDoc.name.CONTENT
1178        logging.debug("Got dataset name (title): '%s'" %title)
1179        # NB, if a title is specified (and not as the default value), it automatically is used in
1180        # place of anything in the granulite file
1181        if title and title != "NAME OF DATASET GOES HERE":
1182            logging.info("Title, '%s', extracted from CSML file" %title)
1183            if self.title:
1184                logging.info("- NB, this will override the title specified in the granulite file ('%s')" \
1185                             %self.title)
1186            self.title = title
1187               
1188        bbox1 = csmlDoc.getBoundingBox()
1189        bbox2 = csmlDoc.getCSMLBoundingBox()
1190
1191        time = None
1192        if bbox2:
1193            time = bbox2.getTimeLimits()
1194   
1195        # now check for other parameters to add to granule
1196        # Firstly, extract the bounding envelope
1197        if bbox1:
1198            w, e = utilities.normaliseLongitude(bbox1[0],bbox1[2])
1199            n, s = (bbox1[3], bbox1[1])
1200   
1201            if not aggregateCoverage or (not self.maxY or float(n) > float(self.maxY)):
1202                self.maxY = n
1203               
1204            if not aggregateCoverage or (not self.minY or float(s) < float(self.minY)):
1205                self.minY = s
1206           
1207            if not aggregateCoverage or (not self.minX or float(w) < float(self.minX)):
1208                self.minX = w
1209   
1210            if not aggregateCoverage or (not self.maxX or float(e) > float(self.maxX)):
1211                self.maxX = e
1212           
1213            logging.debug("Got bounding box data from file: (%s, %s) , (%s, %s)" \
1214                          %(w, s, e, n))
1215           
1216            logging.debug("Updated atom bounding box data: (%s, %s) , (%s, %s)" \
1217                          %(self.minX, self.minY, self.maxX, self.maxY))
1218        else:
1219            logging.debug("No valid bounding box data found")
1220   
1221        if time:
1222            t1 = utilities.formatDateYYYYMMDD(time[0])
1223            if not aggregateCoverage or \
1224                (not self.t1 or datetime.datetime.strptime(t1, YEAR_FORMAT) < \
1225                    datetime.datetime.strptime(self.t1, YEAR_FORMAT)):
1226                self.t1 = t1
1227   
1228            t2 = time[1]
1229            if t2 and t2 != 'None':
1230                t2 = utilities.formatDateYYYYMMDD(t2)
1231                if not aggregateCoverage or \
1232                    (not self.t2 or datetime.datetime.strptime(t2, YEAR_FORMAT) > \
1233                        datetime.datetime.strptime(self.t2, YEAR_FORMAT)):
1234                    self.t2 = t2
1235           
1236            logging.debug("Got time range: %s -> %s" %(self.t1, self.t2))
1237        else:
1238            logging.debug("No valid time range data found")
1239   
1240        #create parameter summaries:
1241        #set up list to hold the parameters data
1242        parameters = []
1243        for feature in csmlDoc.featureCollection.featureMembers:
1244            if hasattr(feature.parameter, 'href'):
1245                paramTriple = ""
1246                if hasattr(feature, 'description'):
1247                    paramTriple = feature.description.CONTENT
1248                    paramTriple += " | " + feature.parameter.href
1249                   
1250                    term = ""
1251                    if hasattr(feature, 'name'):
1252                        term = feature.name.CONTENT
1253   
1254                    paramTriple += " | " + term
1255                   
1256                    logging.debug("Got parameter info: %s" %paramTriple)
1257                    parameters.append(paramTriple)
1258       
1259        # update the atom with the extracted parameters
1260        logging.info("Adding CSML parameters to granule atom")
1261        self.addParameters(parameters)
1262        logging.info("Finished adding CSML data")
1263        return csmlDoc
1264
1265
1266    def lookupAssociatedData(self, type, searchClient, lookupIndirectReferences=False):
1267        '''
1268        Check through the atom links and retrieve any associated data of the
1269        specified type
1270        @param type: type of associated data to lookup - currently VTD.DEPLOYMENT_TERM
1271        or VTD.DE_TERM
1272        @param searchClient: Client implementing the AbstractSearchXMLDBClient class
1273        @keyword lookupIndirectReferences: if True, the atom ID is used to search
1274        defined deployments to find those which reference it, otherwise only
1275        deployments data featured in the atom related links are processed
1276        '''
1277        logging.info("Looking up %s info" %type)
1278        self.allActivities = []
1279        self.allObs = []
1280        self.allDpts = []
1281
1282        if type != VTD.DE_TERM and type != VTD.DEPLOYMENT_TERM:
1283            raise ValueError('Unrecognised associated data type: %s' %type)
1284       
1285        # avoid duplicating lookup effort
1286        if (type == VTD.DEPLOYMENT_TERM and self.deployments) or \
1287            (type == VTD.DE_TERM and self.dataEntities):
1288            logging.info("- this info has already been looked up - returning")
1289            return
1290
1291        # firstly, collect all the references to the info required
1292        if lookupIndirectReferences:
1293            logging.info("Looking up indirect references")
1294           
1295            # if we're looking up DE data for deployments data, need to have the
1296            # deployments info looked up first
1297            if type == VTD.DE_TERM and self.isDeployable() and not self.deployments:
1298                self.lookupAssociatedData(VTD.DEPLOYMENT_TERM, searchClient, 
1299                                          lookupIndirectReferences = lookupIndirectReferences)
1300           
1301            logging.info("Looking up references to this atom from other %s" %type)
1302           
1303            # NB, if we're looking up deployments info, we only look up references
1304            # to this atom - if we're looking up DEs, we need to look up references
1305            # to the deployments referenced by this atom
1306            urls = [self.atomBrowseURL]
1307           
1308            if type == VTD.DE_TERM and self.isDeployable():
1309                urls = []
1310                for dep in self.deployments:
1311                    urls.append(dep.browseURL)
1312                   
1313            links = []
1314            for url in urls:
1315                doc = searchClient.getNDGDoc(type, ndgObject.ASSOCIATED_ATOM_DOC_TYPE, url,
1316                                             targetCollection = dc.ATOM_COLLECTION_PATH)
1317                # now need to turn this results set into actual atoms
1318                tree = ET.fromstring(doc)
1319                for atom in tree:
1320                    logging.debug("- found reference in %s" %type)
1321                    links.append(ET.tostring(atom))
1322                   
1323            logging.info("Finished looking up indirect references")
1324        else:
1325            links = self.getLinksOfType(self.VTD.DEPLOYMENT_TERM)
1326
1327        # now retrieve the references and extract the required data
1328        logging.info("Retrieving info from %s references" %type)
1329        if type == VTD.DEPLOYMENT_TERM:
1330            logging.info("Extracting links data to deployment entitites")
1331            self.deployments = []
1332            for link in links:
1333                if lookupIndirectReferences:
1334                    deploymentAtom = link
1335                else:
1336                    localID = link.href.split("__ATOM__")[-1]
1337                    deploymentAtom = searchClient.getNDGDoc('', 
1338                                                            'ATOM', localID, 
1339                                                            targetCollection = dc.ATOM_COLLECTION_PATH)
1340   
1341                deployment = Deployment.Deployment(Atom(xmlString=str(deploymentAtom)))
1342                self.deployments.append(deployment)
1343               
1344                self.addUniqueLinks(self.allActivities, deployment.activities)
1345                self.addUniqueLinks(self.allObs, deployment.obs)
1346                self.addUniqueLinks(self.allDpts, deployment.dpts)
1347        else:
1348            # for DE data, just store the title + link in a Link object
1349            self.dataEntities = []
1350            logging.info("Extracting links data to data entitites")
1351            for data in links:
1352                atom = Atom(xmlString=str(data))
1353                link = Link()
1354                link.title = atom.title
1355                link.href = atom.atomBrowseURL
1356                link.rel = atom.datasetID
1357               
1358                # NB, different deployments may be used by the same DE - so
1359                # avoid duplication
1360                self.addUniqueLinks(self.dataEntities, link)
1361           
1362        logging.info("Finished looking up %s info" %type)
1363
1364
1365    def addUniqueLinks(self, dataArray, links):
1366        '''
1367        Add links to specified array - if they are not already included
1368        @param dataArray: a list, potentially arlready containing links
1369        @param links: a Link or array of Links to add to the dataArray
1370        '''
1371        logging.debug("Adding new links")
1372        if not links:
1373            return
1374       
1375        if type(links) is not list:
1376            links = [links]
1377       
1378        for link in links:
1379            if type(link) is not Link:
1380                logging.warning("Link is not of 'Link' object type (type='%s') - skipping" %type(link))
1381                continue
1382            if link not in dataArray:
1383                logging.debug("- adding unique link")
1384                dataArray.append(link)
1385        logging.debug("Finished adding links")
1386
1387       
1388    def getFullPath(self):
1389        '''
1390        Return full path to atom in eXist, if it exists, or None, otherwise
1391        @return fullPath: string - collection + filename of atom in eXist
1392        '''
1393        # NB, name assigned when atom created in eXist - so if not defined, not
1394        # in eXist
1395        logging.debug("Getting full path to atom")
1396        if self.atomName:
1397            logging.debug("Return full path to atom in eXist")
1398            return self.getDefaultCollectionPath() + self.atomName
1399        logging.debug("Atom doesn't currently exist in eXist - return 'None'")
1400        return None
1401   
1402   
1403    def getSubTypePrettyName(self):
1404        '''
1405        Return the subtype of the atom in a human readable form
1406        @return: sub type of atom as a verbose string
1407        '''
1408        logging.debug("Getting human readable version of atom subtype")
1409        subType = self.SUB_TYPE_NOT_DEFINED_NAME
1410        if self.subtypeID:
1411           subType = self.VTD.tidySubTypeTitle(self.subtypeID)
1412           
1413        logging.debug("- returning subtype: '%s'" %subType)
1414        return subType
Note: See TracBrowser for help on using the repository browser.