Merge pull request #150 from lyncode/DS-1415

DS-1415: Harvesting configurations added [master]

dspace/config/modules/oai.cfg

@@ -23,3 +23,81 @@ cache.enabled = true
 
 # Base Cache Directory
 cache.dir = ${dspace.dir}/var/oai
+
+#---------------------------------------------------------------#
+#--------------OAI HARVESTING CONFIGURATIONS--------------------#
+#---------------------------------------------------------------#
+# These configs are only used by the OAI-ORE related functions  #
+#---------------------------------------------------------------#
+
+### Harvester settings
+
+# Crosswalk settings; the {name} value must correspond to a declated ingestion crosswalk
+# harvester.oai.metadataformats.{name} = {namespace},{optional display name}
+# The display name is only used in the xmlui for the jspui there are entries in the
+# Messages.properties in the form jsp.tools.edit-collection.form.label21.select.{name}
+harvester.oai.metadataformats.dc = http://www.openarchives.org/OAI/2.0/oai_dc/, Simple Dublin Core
+harvester.oai.metadataformats.qdc = http://purl.org/dc/terms/, Qualified Dublin Core
+harvester.oai.metadataformats.dim = http://www.dspace.org/xmlns/dspace/dim, DSpace Intermediate Metadata
+
+# This field works in much the same way as harvester.oai.metadataformats.PluginName
+# The {name} must correspond to a declared ingestion crosswalk, while the
+# {namespace} must be supported by the target OAI-PMH provider when harvesting content.
+# harvester.oai.oreSerializationFormat.{name} = {namespace}
+
+# Determines whether the harvester scheduling process should be started
+# automatically when the DSpace webapp is deployed.
+# default: false
+harvester.autoStart=false
+
+# Amount of time subtracted from the from argument of the PMH request to account
+# for the time taken to negotiate a connection. Measured in seconds. Default value is 120.
+#harvester.timePadding = 120
+
+# How frequently the harvest scheduler checks the remote provider for updates,
+# messured in minutes. The default vaule is 12 hours (or 720 minutes)
+#harvester.harvestFrequency = 720
+
+# The heartbeat is the frequency at which the harvest scheduler queries the local
+# database to determine if any collections are due for a harvest cycle (based on
+# the harvestFrequency) value. The scheduler is optimized to then sleep until the
+# next collection is actually ready to be harvested. The minHeartbeat and
+# maxHeartbeat are the lower and upper bounds on this timeframe. Measured in seconds.
+# Default minHeartbeat is 30.  Default maxHeartbeat is 3600.
+#harvester.minHeartbeat = 30
+#harvester.maxHeartbeat = 3600
+
+# How many harvest process threads the scheduler can spool up at once. Default value is 3.
+#harvester.maxThreads = 3
+
+# How much time passess before a harvest thread is terminated. The termination process
+# waits for the current item to complete ingest and saves progress made up to that point.
+# Measured in hours. Default value is 24.
+#harvester.threadTimeout = 24
+
+# When harvesting an item that contains an unknown schema or field within a schema what
+# should the harvester do? Either add a new registry item for the field or schema, ignore
+# the specific field or schema (importing everything else about the item), or fail with
+# an error. The default value if undefined is: fail.
+# Possible values: 'fail', 'add', or 'ignore'
+harvester.unknownField  = add
+harvester.unknownSchema = fail
+
+# The webapp responsible for minting the URIs for ORE Resource Maps.
+# If using oai, the dspace.oai.uri config value must be set.
+# The URIs generated for ORE ReMs follow the following convention for both cases.
+# format: [baseURI]/metadata/handle/[theHandle]/ore.xml
+# Default value is oai
+#ore.authoritative.source = oai
+
+# A harvest process will attempt to scan the metadata of the incoming items
+# (dc.identifier.uri field, to be exact) to see if it looks like a handle.
+# If so, it matches the pattern against the values of this parameter.
+# If there is a match the new item is assigned the handle from the metadata value
+# instead of minting a new one. Default value: hdl.handle.net
+#harvester.acceptedHandleServer = hdl.handle.net, handle.myu.edu
+
+# Pattern to reject as an invalid handle prefix (known test string, for example)
+# when attempting to find the handle of harvested items. If there is a match with
+# this config parameter, a new handle will be minted instead. Default value: 123456789.
+#harvester.rejectedHandlePrefix = 123456789, myTestHandle