def __isLinked(self, ids, map):
query = 'package_node_id:("' + '" OR "'.join(ids) + '")'
req = SearchRequest(query)
req.setParam("fq", 'recordtype:"master"')
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "9999")
out = ByteArrayOutputStream()
self.__indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
currentList = []
for doc in result.getJsonList("response/docs"):
currentList.extend(doc.getList("package_node_id"))
if type(map).__name__ == "LinkedHashMap":
for author in map.keySet():
authorDocs = map.get(author)
for doc in authorDocs:
if doc.get("id") in currentList:
doc.set("linked", "true")
else:
for author in map.keys():
authorList = map[author]
for count in authorList:
doc = authorList[count]
if doc.get("id") in currentList:
doc.set("linked", "true")
class QueuesData:
def __init__(self):
pass
def __activate__(self, context):
self.request = context["request"]
self.response = context["response"]
self.formData = context["formData"]
if self.request.isXHR():
print " **** formData: %s" % self.formData
queue = self.formData.get("queueName")
msg = self.formData.get("queueMessage")
self.queueMessage(queue, msg);
out = self.response.getPrintWriter("text/plain")
out.println(self.formData)
out.close()
self.config = JsonConfigHelper(JsonConfig.getSystemFile())
self.threads = self.config.getJsonList("messaging/threads")
def getDescription(self, queue):
for thread in self.threads:
name = thread.get("config/name")
if name == queue:
return thread.get("description")
def queueMessage(self, queue, msg):
ms = MessagingServices.getInstance()
ms.queueMessage(queue, msg);
ms.release()
def search_solr(self):
query = "(rootUri:"
if self.rootUriList:
query += "(" + " OR ".join(self.rootUriList) + ")"
else:
query += "\"" + self.rootUri + "\""
if self.type:
query += " AND type:\"" + self.type + "\""
query += ")"
#print "**********", query
req = SearchRequest(query)
req.setParam("facet", "false")
req.setParam("rows", str(99999))
req.setParam("sort", "dateCreated asc")
req.setParam("start", str(0))
#security_roles = page.authentication.get_roles_list();
#security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
#req.addParam("fq", security_query)
out = ByteArrayOutputStream()
Services.indexer.annotateSearch(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
result = result.getJsonList("response/docs")
# Every annotation for this URI
if self.type == "http://www.purl.org/anotar/ns/type/0.1#Tag":
return self.process_tags(result)
else:
return self.process_response(result)
def getSuggestedNames(self):
# search common forms
lookupNames = []
surname = self.__metadata.getList("surname").get(0)
firstName = self.__metadata.getList("firstName").get(0)
firstInitial = firstName[0].upper()
secondName = self.__metadata.getList("secondName")
if not secondName.isEmpty():
secondName = secondName.get(0)
if secondName and secondName != "":
secondInitial = secondName[0].upper()
lookupNames.append("%s, %s. %s." % (surname, firstInitial, secondInitial))
lookupNames.append("%s, %s %s." % (surname, firstName, secondInitial))
lookupNames.append("%s, %s %s" % (surname, firstName, secondName))
lookupNames.append("%s %s %s" % (firstName, secondName, surname))
lookupNames.append("%s, %s." % (surname, firstInitial))
lookupNames.append("%s, %s" % (surname, firstName))
lookupNames.append("%s %s" % (firstName, surname))
query = '" OR dc_title:"'.join(lookupNames)
# general word search from each part of the name
parts = [p for p in self.getPackageTitle().split(" ") if len(p) > 0]
query2 = " OR dc_title:".join(parts)
req = SearchRequest('(dc_title:"%s")^2.5 OR (dc_title:%s)^0.5' % (query, query2))
self.log.info("suggestedNames query={}", req.query)
req.setParam("fq", 'recordtype:"author"')
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "9999")
req.setParam("fl", "score")
req.setParam("sort", "score desc")
# Make sure 'fq' has already been set in the session
##security_roles = self.authentication.get_roles_list();
##security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
##req.addParam("fq", security_query)
out = ByteArrayOutputStream()
indexer = self.services.getIndexer()
indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
# self.log.info("result={}", result.toString())
docs = result.getJsonList("response/docs")
map = LinkedHashMap()
for doc in docs:
authorName = doc.getList("dc_title").get(0)
if map.containsKey(authorName):
authorDocs = map.get(authorName)
else:
authorDocs = ArrayList()
map.put(authorName, authorDocs)
authorDocs.add(doc)
self.__maxScore = max(1.0, float(result.get("response/maxScore")))
return map
class Queues:
def __init__(self):
self.config = JsonConfigHelper(JsonConfig.getSystemFile())
self.threads = self.config.getJsonList("messaging/threads")
def getDescription(self, queue):
for thread in self.threads:
name = thread.get("config/name")
if name == queue:
return thread.get("description")
def __getMetadata(self, oid):
req = SearchRequest('id:%s' % oid)
req.setParam("fq", 'item_type:"object"')
# Make sure 'fq' has already been set in the session
##security_roles = self.authentication.get_roles_list();
##security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
##req.addParam("fq", security_query)
out = ByteArrayOutputStream()
self.__indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
#self.log.info("result={}", result.toString())
return result.getJsonList("response/docs").get(0)
def __getAuthorDetails(self, citationIds):
query = " OR id:".join(citationIds)
req = SearchRequest('id:%s' % query)
req.setParam("fq", 'recordtype:"author"')
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "9999")
# Make sure 'fq' has already been set in the session
##security_roles = self.authentication.get_roles_list();
##security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
##req.addParam("fq", security_query)
out = ByteArrayOutputStream()
self.__indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
return result.getJsonList("response/docs")
def __init__(self):
responseType = "text/html; charset=UTF-8"
responseMsg = ""
func = formData.get("func")
if func == "placeName":
try:
placeName = formData.get("q")
url = "http://ws.geonames.org/searchJSON?fuzzy=0.7&q=" + placeName
client = BasicHttpClient(url)
get = GetMethod(url)
statusInt = client.executeMethod(get)
r = str(statusInt)
jsonConfigHelper = JsonConfigHelper(get.getResponseBodyAsString().strip())
for geoName in jsonConfigHelper.getJsonList("geonames"):
responseMsg += "%s, %s|%s \n" % (geoName.get("name"), geoName.get("countryName"), geoName.get("geonameId"))
except Exception, e:
print "exception: ", str(e)
r = str(e), None
responseType = "text/plain; charset=UTF-8"
def getAuthorities(self):
req = SearchRequest('package_node_id:%s' % self.metadata.get("id"))
req.setParam("fq", 'recordtype:"master"')
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "9999")
# Make sure 'fq' has already been set in the session
##security_roles = self.authentication.get_roles_list();
##security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
##req.addParam("fq", security_query)
out = ByteArrayOutputStream()
indexer = self.services.getIndexer()
indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
docs = result.getJsonList("response/docs")
return docs
def __searchNames(self, searchText):
# search common forms
lookupNames = []
req = SearchRequest('(dc_title:"%s")^2.5' % searchText)
self.log.info("searchNames query={}", req.query)
req.setParam("fq", 'recordtype:"author"')
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "9999")
req.setParam("fl", "score")
req.setParam("sort", "score desc")
out = ByteArrayOutputStream()
self.__indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
docs = result.getJsonList("response/docs")
#Using this map because velocity gave error if LinkHashedMap is used
map={}
idList = []
count = 0
for doc in docs:
authorName = str(doc.getList("dc_title").get(0))
idList.append(doc.get("id"))
if map.has_key(authorName):
docsDic = map.get(authorName)
else:
docsDic = {}
map[authorName] = docsDic
#hash storageId and authorName
doc.set("authorHash", self.getHash(authorName))
doc.set("storageHash", self.getHash(doc.get("storage_id")))
doc.set("affiliation", self.getCitationAffiliation(doc))
##doc.set("linked", Boolean.toString(linked))
docsDic["%s" % count] = doc
count +=1
if idList:
self.__isLinked(idList, map)
return map
def process_tags(self, result):
tags = []
tagsDict = {}
# Build a dictionary of the tags
for doc in result:
doc = JsonConfigHelper(doc.get("jsonString"))
tag = doc.get("content/literal")
locs = doc.getJsonList("annotates/locators").size()
if locs == 0:
if tag in tagsDict:
d = tagsDict[tag]
d.set("tagCount", str(int(d.get("tagCount")) + 1))
else:
doc.set("tagCount", str(1))
tagsDict[tag] = doc
else:
tags.append(doc.toString())
for tag in tagsDict:
tags.append(tagsDict[tag].toString())
return "[" + ",".join(tags) + "]"
def getSearchTerms(self):
searchTerms = []
prefix = self.getSuggestionPrefix()
query = '%(prefix)s OR %(prefix)s*' % { "prefix" : prefix }
req = SearchRequest(query)
req.addParam("fq", self.page.getPortal().getQuery())
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "50")
req.setParam("fl", "score,id,dc_title")
req.setParam("sort", "score desc")
out = ByteArrayOutputStream()
indexer = self.services.getIndexer()
indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
docs = result.getJsonList("response/docs")
for doc in docs:
dc_title = doc.getList("dc_title").get(0)
searchTerms.append(dc_title)
return '", "'.join(searchTerms)
def __getSolrData(self):
prefix = self.getSearchTerms()
print "prefix='%s'" % prefix
if prefix:
query = "dc_title:%(prefix)s OR dc_title:%(prefix)s*" % {"prefix": prefix}
query += " OR f_dc_identifier:%(ns)s%(prefix)s OR f_dc_identifier:%(ns)s%(prefix)s*" % {
"prefix": prefix,
"ns": "http\://example.com/arc/",
}
else:
query = "*:*"
portal = self.services.portalManager.get(self.portalId)
if portal.searchQuery != "*:*" and portal.searchQuery != "":
query = query + " AND " + portal.searchQuery
req = SearchRequest(query)
req.setParam("fq", 'item_type:"object"')
if portal.query:
req.addParam("fq", portal.query)
req.setParam("fl", "score")
req.setParam("sort", "score desc")
req.setParam("start", self.getStartIndex())
req.setParam("rows", self.getItemsPerPage())
req.setParam("facet", "true")
req.setParam("facet.field", "repository_name")
req.setParam("facet.mincount", "1")
ns = self.getNamespace()
level = self.getFormData("level", None)
if level and level != "top":
req.addParam("fq", 'repository_name:"%s"' % level.replace(ns, ""))
try:
out = ByteArrayOutputStream()
indexer = self.services.getIndexer()
indexer.search(req, out)
results = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
if level == "top":
narrowerMap = {}
for doc in results.getJsonList("response/docs"):
value = doc.getList("repository_name").get(0)
hash = md5.md5(value).hexdigest()
if not narrowerMap.has_key(hash):
# print value, hash
narrowerMap[hash] = []
narrowerMap[hash].append(doc.get("id"))
docs = ArrayList()
facets = results.getList("facet_counts/facet_fields/repository_name")
for i in range(0, len(facets), 2):
value = facets[i]
hash = md5.md5(value).hexdigest()
# print value,hash
doc = JsonConfigHelper()
doc.set("score", "1")
doc.set("dc_identifier", "%s%s" % (ns, value))
doc.set("skos_inScheme", ns)
doc.set("skos_broader", "%s%s" % (ns, value))
doc.set("skos_narrower", '", "'.join(narrowerMap[hash]))
doc.set("skos_prefLabel", value)
docs.add(doc)
results.removePath("response/docs")
results.setJsonList("response/docs", docs)
return results
except Exception, e:
self.log.error("Failed to lookup '{}': {}", prefix, str(e))
def getSuggestedNames(self):
# search common forms
lookupNames = []
surname = self.__metadata.getList("surname").get(0)
firstName = self.__metadata.getList("firstName").get(0)
firstInitial = firstName[0].upper()
secondName = self.__metadata.getList("secondName")
if not secondName.isEmpty():
secondName = secondName.get(0)
if secondName and secondName != "":
secondInitial = secondName[0].upper()
lookupNames.append("%s, %s. %s." % (surname, firstInitial, secondInitial))
lookupNames.append("%s, %s %s." % (surname, firstName, secondInitial))
lookupNames.append("%s, %s %s" % (surname, firstName, secondName))
lookupNames.append("%s %s %s" % (firstName, secondName, surname))
lookupNames.append("%s, %s." % (surname, firstInitial))
lookupNames.append("%s, %s" % (surname, firstName))
lookupNames.append("%s %s" % (firstName, surname))
query = '" OR dc_title:"'.join(lookupNames)
# general word search from each part of the name
parts = [p for p in self.getPackageTitle().split(" ") if len(p) > 0]
query2 = " OR dc_title:".join(parts)
#filter out the linked citation
linkedCitations = self.__manifest.getList("//children//id")
query3 = ""
if linkedCitations:
query3 = " OR ".join(linkedCitations)
query3 = " AND -id:(%s)" % query3
req = SearchRequest('(dc_title:"%s")^2.5 OR (dc_title:%s)^0.5%s' % (query, query2, query3))
self.log.info("suggestedNames query={}", req.query)
req.setParam("fq", 'recordtype:"author"')
req.addParam("fq", 'item_type:"object"')
req.setParam("rows", "9999")
req.setParam("fl", "score")
req.setParam("sort", "score desc")
# Make sure 'fq' has already been set in the session
##security_roles = self.authentication.get_roles_list();
##security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
##req.addParam("fq", security_query)
out = ByteArrayOutputStream()
self.__indexer.search(req, out)
result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
#self.log.info("result={}", result.toString())
docs = result.getJsonList("response/docs")
exactMatchRecords = LinkedHashMap()
map = LinkedHashMap()
idList = []
for doc in docs:
authorName = doc.getList("dc_title").get(0)
rank = self.getRank(doc.getList("score").get(0))
id = doc.get("id")
idList.append(id)
#try to do automatch
if float(rank) == 100.00 and self.isModified() == "false":
if exactMatchRecords.containsKey(authorName):
authorMatchDocs = exactMatchRecords.get(authorName)
else:
authorMatchDocs = ArrayList()
exactMatchRecords.put(authorName, authorMatchDocs)
authorMatchDocs.add(doc)
elif id not in linkedCitations:
if map.containsKey(authorName):
authorDocs = map.get(authorName)
else:
authorDocs = ArrayList()
map.put(authorName, authorDocs)
authorDocs.add(doc)
self.__maxScore = max(1.0, float(result.get("response/maxScore")))
if idList:
self.__isLinked(idList, map)
# Do not auto save if record is live
if self.__workflowMetadata.get("modified") == "false":
self.__autoSaveExactRecord(exactMatchRecords)
return map
class DetailData:
def __init__(self):
self.userAgreement = AgreementData(bindings)
def __activate__(self, context):
self.velocityContext = context
self.services = context["Services"]
self.request = context["request"]
self.response = context["response"]
self.contextPath = context["contextPath"]
self.formData = context["formData"]
self.page = context["page"]
self.uaActivated = False
useDownload = Boolean.parseBoolean(self.formData.get("download", "true"))
self.__isPreview = Boolean.parseBoolean(self.formData.get("preview", "false"))
self.__previewPid = None
self.__hasPid = False
uri = URLDecoder.decode(self.request.getAttribute("RequestURI"))
matches = re.match("^(.*?)/(.*?)/(?:(.*?)/)?(.*)$", uri)
if matches and matches.group(3):
oid = matches.group(3)
pid = matches.group(4)
self.__metadata = JsonConfigHelper()
self.__object = self.__getObject(oid)
self.__oid = oid
# If we have a PID
if pid:
self.__hasPid = True
if useDownload:
# Download the payload to support relative links
download = DownloadData()
download.__activate__(context)
else:
# Render the detail screen with the alternative preview
self.__readMetadata(oid)
self.__previewPid = pid
# Otherwise, render the detail screen
else:
self.__readMetadata(oid)
self.__previewPid = self.getPreview()
if self.__previewPid:
self.__previewPid = URLEncoder.encode(self.__previewPid, "UTF-8")
else:
# require trailing slash for relative paths
q = ""
if self.__isPreview:
q = "?preview=true"
self.response.sendRedirect("%s/%s/%s" % (self.contextPath, uri, q))
def getAllowedRoles(self):
metadata = self.getMetadata()
if metadata is not None:
return metadata.getList("security_filter")
else:
return []
def getAllPreviews(self):
list = self.getAltPreviews()
preview = self.getPreview()
if not list.contains(preview):
list.add(preview)
return list
def getAltPreviews(self):
return self.__metadata.getList("altpreview")
def getFileName(self):
return self.getObject().getSourceId()
def getFileNameSplit(self, index):
return os.path.splitext(self.getFileName())[index]
def getFriendlyName(self, name):
if name.startswith("dc_"):
name = name[3:]
if name.startswith("meta_"):
name = name[5:]
return name.replace("_", " ").capitalize()
def getMetadata(self):
return self.__metadata
def getMetadataMap(self):
return self.__metadataMap
def getObject(self):
return self.__object
def getOid(self):
return self.__oid
def getPreview(self):
return self.__metadata.get("preview")
def getPreviewPid(self):
return self.__previewPid
def getProperty(self, field):
return self.getObject().getMetadata().getProperty(field)
def getUserAgreement(self):
if not self.uaActivated:
self.userAgreement.__activate__(self.velocityContext, self.getMetadata())
self.uaActivated = True
return self.userAgreement
def hasLocalFile(self):
# get original file.path from object properties
filePath = self.getProperty("file.path")
return filePath and os.path.exists(filePath)
def hasPid(self):
return self.__hasPid
def isAccessDenied(self):
myRoles = self.page.authentication.get_roles_list()
allowedRoles = self.getAllowedRoles()
for role in myRoles:
if role in allowedRoles:
return False
return True
def isDetail(self):
return not (self.request.isXHR() or self.__isPreview)
def isIndexed(self):
return self.__getNumFound() == 1
def isPending(self):
meta = self.getObject().getMetadata()
status = meta.get("render-pending")
return Boolean.parseBoolean(status)
def setStatus(self, status):
self.response.setStatus(status)
def __getNumFound(self):
return int(self.__solrData.get("response/numFound"))
def __getObject(self, oid):
obj = None
try:
storage = self.services.getStorage()
try:
obj = storage.getObject(oid)
except StorageException:
sid = self.__getStorageId(oid)
if sid is not None:
obj = storage.getObject(sid)
print "Object not found: oid='%s', trying sid='%s'" % (oid, sid)
except StorageException:
print "Object not found: oid='%s'" % oid
return obj
def __getStorageId(self, oid):
return self.__metadata.get("storage_id")
def __loadSolrData(self, oid):
portal = self.page.getPortal()
query = 'id:"%s"' % oid
if self.isDetail() and portal.getSearchQuery():
query += " AND " + portal.getSearchQuery()
req = SearchRequest(query)
req.addParam("fq", 'item_type:"object"')
if self.isDetail():
req.addParam("fq", portal.getQuery())
out = ByteArrayOutputStream()
self.services.getIndexer().search(req, out)
self.__solrData = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
def __readMetadata(self, oid):
self.__loadSolrData(oid)
if self.isIndexed():
self.__metadata = self.__solrData.getJsonList("response/docs").get(0)
if self.__object is None:
# Try again, indexed records might have a special storage_id
self.__object = self.__getObject(oid)
# Just a more usable instance of metadata
self.__json = JsonConfigHelper(self.__solrData.getList("response/docs").get(0))
self.__metadataMap = TreeMap(self.__json.getMap("/"))
else:
self.__metadata.set("id", oid)
def __search(self):
requireEscape = False
recordsPerPage = self.__portal.recordsPerPage
uri = URLDecoder.decode(self.request.getAttribute("RequestURI"))
query = None
pagePath = self.__portal.getName() + "/" + self.pageName
if query is None or query == "":
query = self.formData.get("query")
requireEscape = True
if query is None or query == "":
query = "*:*"
if query == "*:*":
self.__query = ""
else:
self.__query = query
if requireEscape:
query = self.__escapeQuery(query)
query = "%s:%s" % (self.__searchField, query)
self.sessionState.set("query", self.__query)
# find objects with annotations matching the query
if query != "*:*":
anotarQuery = self.__query
if requireEscape:
anotarQuery = self.__escapeQuery(anotarQuery)
annoReq = SearchRequest(anotarQuery)
annoReq.setParam("facet", "false")
annoReq.setParam("rows", str(99999))
annoReq.setParam("sort", "dateCreated asc")
annoReq.setParam("start", str(0))
anotarOut = ByteArrayOutputStream()
self.services.indexer.annotateSearch(annoReq, anotarOut)
resultForAnotar = JsonConfigHelper(ByteArrayInputStream(anotarOut.toByteArray()))
resultForAnotar = resultForAnotar.getJsonList("response/docs")
ids = HashSet()
for annoDoc in resultForAnotar:
annotatesUri = annoDoc.get("annotatesUri")
ids.add(annotatesUri)
print "Found annotation for %s" % annotatesUri
# add annotation ids to query
query += ' OR id:("' + '" OR "'.join(ids) + '")'
portalSearchQuery = self.__portal.searchQuery
if portalSearchQuery == "":
portalSearchQuery = query
else:
if query != "*:*":
query += " AND " + portalSearchQuery
else:
query = portalSearchQuery
req = SearchRequest(query)
req.setParam("facet", "true")
req.setParam("rows", str(recordsPerPage))
req.setParam("facet.field", self.__portal.facetFieldList)
req.setParam("facet.sort", Boolean.toString(self.__portal.getFacetSort()))
req.setParam("facet.limit", str(self.__portal.facetCount))
req.setParam("sort", self.__sortBy)
# setup facets
if self.__useSessionNavigation:
action = self.formData.get("verb")
value = self.formData.get("value")
fq = self.sessionState.get("fq")
if fq is not None:
self.__pageNum = 1
req.setParam("fq", fq)
if action == "add_fq":
self.__pageNum = 1
req.addParam("fq", URLDecoder.decode(value, "UTF-8"))
elif action == "remove_fq":
self.__pageNum = 1
req.removeParam("fq", URLDecoder.decode(value, "UTF-8"))
elif action == "clear_fq":
self.__pageNum = 1
req.removeParam("fq")
elif action == "select-page":
self.__pageNum = int(value)
else:
navUri = uri[len(pagePath) :]
self.__pageNum, fq, self.__fqParts = self.__parseUri(navUri)
savedfq = self.sessionState.get("savedfq")
limits = []
if savedfq:
limits.extend(savedfq)
if fq:
limits.extend(fq)
self.sessionState.set("savedfq", limits)
for q in fq:
req.addParam("fq", URLDecoder.decode(q, "UTF-8"))
portalQuery = self.__portal.query
if portalQuery:
req.addParam("fq", portalQuery)
req.addParam("fq", 'item_type:"object"')
if req.getParams("fq"):
self.__selected = ArrayList(req.getParams("fq"))
if self.__useSessionNavigation:
self.sessionState.set("fq", self.__selected)
self.sessionState.set("searchQuery", portalSearchQuery)
self.sessionState.set("pageNum", self.__pageNum)
# Make sure 'fq' has already been set in the session
if not self.page.authentication.is_admin():
current_user = self.page.authentication.get_username()
security_roles = self.page.authentication.get_roles_list()
security_filter = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
security_exceptions = 'security_exception:"' + current_user + '"'
owner_query = 'owner:"' + current_user + '"'
security_query = "(" + security_filter + ") OR (" + security_exceptions + ") OR (" + owner_query + ")"
req.addParam("fq", security_query)
req.setParam("start", str((self.__pageNum - 1) * recordsPerPage))
print " * search.py:", req.toString(), self.__pageNum
out = ByteArrayOutputStream()
self.services.indexer.search(req, out)
self.__result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
if self.__result is not None:
self.__paging = Pagination(
self.__pageNum, int(self.__result.get("response/numFound")), self.__portal.recordsPerPage
)
def __search(self):
recordsPerPage = self.__portal.recordsPerPage
uri = URLDecoder.decode(request.getAttribute("RequestURI"))
query = None
pagePath = portalId + "/" + pageName
if uri != pagePath:
query = uri[len(pagePath)+1:]
if query is None or query == "":
query = formData.get("query")
if query is None or query == "":
query = "*:*"
if query == "*:*":
self.__query = ""
else:
self.__query = query
sessionState.set("query", self.__query)
# find objects with annotations matching the query
if query != "*:*":
anotarQuery = self.__query
annoReq = SearchRequest(anotarQuery)
annoReq.setParam("facet", "false")
annoReq.setParam("rows", str(99999))
annoReq.setParam("sort", "dateCreated asc")
annoReq.setParam("start", str(0))
anotarOut = ByteArrayOutputStream()
Services.indexer.annotateSearch(annoReq, anotarOut)
resultForAnotar = JsonConfigHelper(ByteArrayInputStream(anotarOut.toByteArray()))
resultForAnotar = resultForAnotar.getJsonList("response/docs")
ids = HashSet()
for annoDoc in resultForAnotar:
annotatesUri = annoDoc.get("annotatesUri")
ids.add(annotatesUri)
print "Found annotation for %s" % annotatesUri
# add annotation ids to query
query += ' OR id:("' + '" OR "'.join(ids) + '")'
portalSearchQuery = self.__portal.searchQuery
if portalSearchQuery == "":
portalSearchQuery = query
else:
if query != "*:*":
query += " AND " + portalSearchQuery
else:
query = portalSearchQuery
req = SearchRequest(query)
req.setParam("facet", "true")
req.setParam("rows", str(recordsPerPage))
req.setParam("facet.field", self.__portal.facetFieldList)
req.setParam("facet.sort", "true")
req.setParam("facet.limit", str(self.__portal.facetCount))
req.setParam("sort", "f_dc_title asc")
# setup facets
action = formData.get("verb")
value = formData.get("value")
fq = sessionState.get("fq")
if fq is not None:
self.__pageNum = 1
req.setParam("fq", fq)
if action == "add_fq":
self.__pageNum = 1
name = formData.get("name")
print " * add_fq: %s" % value
req.addParam("fq", URLDecoder.decode(value, "UTF-8"))
elif action == "remove_fq":
self.__pageNum = 1
req.removeParam("fq", URLDecoder.decode(value, "UTF-8"))
elif action == "clear_fq":
self.__pageNum = 1
req.removeParam("fq")
elif action == "select-page":
self.__pageNum = int(value)
req.addParam("fq", 'item_type:"object"')
portalQuery = self.__portal.query
print " * portalQuery=%s" % portalQuery
if portalQuery:
req.addParam("fq", portalQuery)
self.__selected = list(req.getParams("fq"))
sessionState.set("fq", self.__selected)
sessionState.set("searchQuery", portalSearchQuery)
sessionState.set("pageNum", self.__pageNum)
# Make sure 'fq' has already been set in the session
if not page.authentication.is_admin():
security_roles = page.authentication.get_roles_list()
security_query = 'security_filter:("' + '" OR "'.join(security_roles) + '")'
current_user = page.authentication.get_username()
owner_query = 'owner:"' + current_user + '"'
req.addParam("fq", "(" + security_query + ") OR (" + owner_query + ")")
req.setParam("start", str((self.__pageNum - 1) * recordsPerPage))
print " * search.py:", req.toString(), self.__pageNum
out = ByteArrayOutputStream()
Services.indexer.search(req, out)
self.__result = JsonConfigHelper(ByteArrayInputStream(out.toByteArray()))
if self.__result is not None:
self.__paging = Pagination(self.__pageNum,
int(self.__result.get("response/numFound")),
self.__portal.recordsPerPage)
def __workflow(self):
# Workflow data
WORKFLOW_ID = "packaging"
wfChanged = False
workflow_security = []
self.message_list = None
try:
wfPayload = self.object.getPayload("workflow.metadata")
wfMeta = JsonConfigHelper(wfPayload.open())
wfPayload.close()
# Are we indexing because of a workflow progression?
targetStep = wfMeta.get("targetStep")
if targetStep is not None and targetStep != wfMeta.get("step"):
wfChanged = True
# Step change
wfMeta.set("step", targetStep)
wfMeta.removePath("targetStep")
# This must be a re-index then
else:
targetStep = wfMeta.get("step")
# Security change
stages = self.config.getJsonList("stages")
for stage in stages:
if stage.get("name") == targetStep:
wfMeta.set("label", stage.get("label"))
self.item_security = stage.getList("visibility")
workflow_security = stage.getList("security")
if wfChanged == True:
self.message_list = stage.getList("message")
# Form processing
formData = wfMeta.getJsonList("formData")
if formData.size() > 0:
formData = formData[0]
else:
formData = None
coreFields = ["title", "creator", "contributor", "description", "format", "creationDate"]
if formData is not None:
# Core fields
title = formData.getList("title")
if title:
self.titleList = title
creator = formData.getList("creator")
if creator:
self.creatorList = creator
contributor = formData.getList("contributor")
if contributor:
self.contributorList = contributor
description = formData.getList("description")
if description:
self.descriptionList = description
format = formData.getList("format")
if format:
self.formatList = format
creation = formData.getList("creationDate")
if creation:
self.creationDate = creation
# Non-core fields
data = formData.getMap("/")
for field in data.keySet():
if field not in coreFields:
self.customFields[field] = formData.getList(field)
except StorageException, e:
# No workflow payload, time to create
wfChanged = True
wfMeta = JsonConfigHelper()
wfMeta.set("id", WORKFLOW_ID)
wfMeta.set("step", "pending")
wfMeta.set("pageTitle", "Uploaded Files - Management")
stages = self.config.getJsonList("stages")
for stage in stages:
if stage.get("name") == "pending":
wfMeta.set("label", stage.get("label"))
self.item_security = stage.getList("visibility")
workflow_security = stage.getList("security")
self.message_list = stage.getList("message")
# Step change
wfMeta.set("step", targetStep)
wfMeta.removePath("targetStep")
# This must be a re-index then
else:
targetStep = wfMeta.get("step")
# Security change
stages = jsonConfig.getJsonList("stages")
for stage in stages:
if stage.get("name") == targetStep:
item_security = stage.getList("visibility")
workflow_security = stage.getList("security")
# Form processing
formData = wfMeta.getJsonList("formData")
if formData.size() > 0:
formData = formData[0]
else:
formData = None
coreFields = ["title", "creator", "contributor", "description", "format", "creationDate"]
if formData is not None:
# Core fields
title = formData.getList("title")
if title is not None and title.size() > 0:
titleList = title
creator = formData.getList("creator")
if creator is not None and creator.size() > 0:
creatorList = creator
contributor = formData.getList("contributor")
if contributor is not None and contributor.size() > 0:
def __init__(self):
print "formData=%s" % formData
func = formData.get("func")
result = "{}"
resultType = "text/plain; charset=UTF-8"
oid = formData.get("oid")
portalId = formData.get("portalId")
portalManager = Services.getPortalManager()
if func == "reharvest":
if oid:
print "Reharvesting single object: %s" % oid
portalManager.reharvest(oid)
result = '{ status: "ok" }'
elif portalId:
portal = portalManager.get(portalId)
print " Reharvesting portal: %s" % portal.getName()
indexer = Services.getIndexer()
# TODO security filter
# TODO this should loop through the whole portal,
# not just the first page of results
if portal.getQuery() == "":
searchRequest = SearchRequest("item_type:object")
else:
searchRequest = SearchRequest(portal.getQuery())
result = ByteArrayOutputStream();
Services.getIndexer().search(searchRequest, result)
json = JsonConfigHelper(ByteArrayInputStream(result.toByteArray()))
objectIds = HashSet()
for doc in json.getJsonList("response/docs"):
objectIds.add(doc.get("id"))
if not objectIds.isEmpty():
portalManager.reharvest(objectIds)
result = '{ status: "ok" }'
else:
result = '{ status: "failed" }'
elif func == "get-state":
result = '{ running: "%s", lastResult: "%s" }' % \
(sessionState.get("reharvest/running"),
sessionState.get("reharvest/lastResult"))
elif func == "get-log":
context = LoggerFactory.getILoggerFactory()
logger = context.getLogger("au.edu.usq.fascinator.HarvestClient")
appender = logger.getAppender("CYCLIC")
layout = HTMLLayout()
layout.setContext(context)
layout.setPattern("%d%msg")
layout.setTitle("Reharvest log")
layout.start()
result = "<table>"
count = appender.getLength()
if count == -1:
result += "<tr><td>Failed</td></tr>"
elif count == 0:
result += "<tr><td>No logging events</td></tr>"
else:
for i in range(0, count):
event = appender.get(i)
result += layout.doLayout(event)
result += "</table>"
resultType = "text/html; charset=UTF-8"
writer = response.getPrintWriter(resultType)
writer.println(result)
writer.close()
