From 32f024e3829b02bed1c456fccb09d192f27d755c Mon Sep 17 00:00:00 2001
From: kohleman <kohleman>
Date: Mon, 25 Jun 2012 13:23:24 +0000
Subject: [PATCH] updated to V2 drop box syntax
SVN: 25850
---
.../create-flowcell-dropbox.py | 220 ++++++++++--------
.../create-flowcell-dropbox/plugin.properties | 4 +-
.../plugin.properties | 4 +-
.../register-flowcell-dropbox.py | 76 +++---
4 files changed, 172 insertions(+), 132 deletions(-)
diff --git a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/create-flowcell-dropbox.py b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/create-flowcell-dropbox.py
index e092beacec5..9b7f600f561 100755
--- a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/create-flowcell-dropbox.py
+++ b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/create-flowcell-dropbox.py
@@ -1,9 +1,33 @@
'''
-expected incoming Name for HiSeq2000 runs: 110715_SN792_0054_BC035RACXX
+@copyright:
+2012 ETH Zuerich, CISD
+
+@license:
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+@description:
+Parses the two Illumina provided files 'runParameters.xml' and 'RunInfo.xml'
+and creates one Sample of type 'ILLUMINA_FLOW_CELL' and sets Sample properties
+from those two XML files. Additionally the number of lanes are read out and
+are created as contained samples of type 'ILLUMINA_FLOW_LANE'.
+
+@note:
+print statements go to: <openBIS_HOME>/datastore_server/log/startup_log.txt
+expected incoming Name for HiSeq runs: 110715_SN792_0054_BC035RACXX
expected incoming Name for GAII runs: 110812_6353WAAXX
-Note:
-print statements go to: ~openbis/sprint/datastore_server/log/startup_log.txt
+@author:
+Manuel Kohler
'''
import os
@@ -69,107 +93,103 @@ def create_openbis_timestamp ():
# -----------------------------------------------------------------------------
-# Create a "transaction" -- a way of grouping operations together so they all
-# happen or none of them do.
-transaction = service.transaction()
-
-incomingPath = incoming.getAbsolutePath()
-print(incomingPath)
-
-# Get the incoming name
-name = incoming.getName()
-
-split=name.split("_")
-if (len(split) == 4):
- IS_HISEQ_RUN=True
-if (len(split) == 2):
- pass
-
-# Search for the sample and check if there is already sample with this name
-search_service = transaction.getSearchService()
-sc = SearchCriteria()
-sc.addMatchClause(SearchCriteria.MatchClause.createAttributeMatch(SearchCriteria.MatchClauseAttribute.CODE, name));
-foundSamples = search_service.searchForSamples(sc)
-if foundSamples.size() > 0:
- raise NameError('Already found a Flow Cell with the following name: '+ name)
-
-# Parse the RunInfo.xml file
-runInfo = parseXmlFile(incomingPath + '/' + RUNINFO)
-print(runInfo)
-
-# Create a new Flow Cell and set the experiment
-project = transaction.getProject(FLOWCELL_PROJECT_ID)
-if project == None:
- space = transaction.getSpace(FLOWCELL_SPACE)
- if space == None:
- space = transaction.createNewSpace(FLOWCELL_SPACE, None)
- space.setDescription("A test space")
- project = transaction.createNewProject(FLOWCELL_PROJECT_ID)
- project.setDescription("A demo project")
-expID = FLOWCELL_PROJECT_ID + '/' + datetime.now().strftime("%Y.%m")
-exp = transaction.getExperiment(expID)
-if exp == None:
- exp = transaction.createNewExperiment(expID, EXPERIMENT_TYPE_CODE)
-newFlowCell = transaction.createNewSample('/' + FLOWCELL_SPACE + '/' + name, "ILLUMINA_FLOW_CELL")
-newFlowCell.setExperiment(exp)
-
-if IS_HISEQ_RUN:
- run = runInfo.getAllchildren('Run')[0].attrib
- if (run['Id'] != name):
- raise NameError('Flowcell names do not match between directory name '+ name +
- ' and ' + RUNINFO + 'property file: ' + run['Id'])
-
- # The HiSeq is providing more infos, which we will parse here:
- runParameters = parseXmlFile(incomingPath + '/' + RUNPARAMETERS)
-
- newFlowCell.setPropertyValue("ILLUMINA_PIPELINE_VERSION", runParameters.getXmlElement(RUNPARAMETERS_XML['RTAVERSION']))
- newFlowCell.setPropertyValue("FLOWCELLTYPE", runParameters.getXmlElement(RUNPARAMETERS_XML['FLOWCELL']))
- newFlowCell.setPropertyValue("CONTROL_LANE", runParameters.getXmlElement(RUNPARAMETERS_XML['CONTROLLANE']))
- newFlowCell.setPropertyValue("SBS_KIT", runParameters.getXmlElement(RUNPARAMETERS_XML['SBS']))
-
- read1 = runParameters.getAllchildren('Read1')
- newFlowCell.setPropertyValue("CYCLES_REQUESTED_BY_CUSTOMER", read1[0].text)
-
- read2 = runParameters.getAllchildren('Read2')
- if (str(read2[0].text) == '0'):
- newFlowCell.setPropertyValue("END_TYPE", "SINGLE_READ")
- else:
- newFlowCell.setPropertyValue("END_TYPE", "PAIRED_END")
- newFlowCell.setPropertyValue("PAIRED_END_KIT", runParameters.getXmlElement(RUNPARAMETERS_XML['PE']))
-
- indexRead1 = runParameters.getAllchildren('IndexRead1')
- newFlowCell.setPropertyValue("INDEXREAD", indexRead1[0].text)
-
- indexRead2 = runParameters.getAllchildren('IndexRead2')
- newFlowCell.setPropertyValue("INDEXREAD2", indexRead2[0].text)
-
- def setFcProperty(searchId, dict):
- children = runInfo.getAllchildren(searchId)
- for element in (dict):
- if (element <> '') and (dict[element] <> ''):
- newFlowCell.setPropertyValue(element, children[0].attrib[dict[element]])
-
- setFcProperty('FlowcellLayout', RUNINFO_XML)
-
-
-sequencer = runInfo.getAllchildren('Instrument')
-newFlowCell.setPropertyValue("SEQUENCER", INSTRUMENT[sequencer[0].text])
-
-newFlowCell.setPropertyValue("FLOW_CELL_SEQUENCED_ON", create_openbis_timestamp())
-if IS_HISEQ_RUN:
- maxLanes = runInfo.getAllchildren('FlowcellLayout')[0].attrib[RUNINFO_XML['LANECOUNT']]
-else:
- maxLanes = len(runInfo.getAllchildren('Tiles')[0])
-
-# -----------------------------------------------------------------------------
-
-def registerFlowLane(a_lane):
+def registerFlowLane(transaction, a_lane, name, newFlowCell):
'''
Registers a new Flow lane
'''
newFlowLane = transaction.createNewSample('/' + FLOWCELL_SPACE + '/' + name + ':' + str(a_lane), "ILLUMINA_FLOW_LANE")
newFlowLane.setContainer(newFlowCell)
+
+# -----------------------------------------------------------------------------
+
+def process(transaction):
+
+ incoming = transaction.getIncoming()
+ incomingPath = incoming.getAbsolutePath()
+
+ # Get the incoming name
+ name = incoming.getName()
+
+ split=name.split("_")
+ if (len(split) == 4):
+ IS_HISEQ_RUN=True
+ if (len(split) == 2):
+ pass
+
+ # Search for the sample and check if there is already sample with this name
+ search_service = transaction.getSearchService()
+ sc = SearchCriteria()
+ sc.addMatchClause(SearchCriteria.MatchClause.createAttributeMatch(SearchCriteria.MatchClauseAttribute.CODE, name));
+ foundSamples = search_service.searchForSamples(sc)
+ if foundSamples.size() > 0:
+ raise NameError('Already found a Flow Cell with the following name: '+ name)
+
+ # Parse the RunInfo.xml file
+ runInfo = parseXmlFile(incomingPath + '/' + RUNINFO)
+
+ # Create a new Flow Cell and set the experiment
+ project = transaction.getProject(FLOWCELL_PROJECT_ID)
+ if project == None:
+ space = transaction.getSpace(FLOWCELL_SPACE)
+ if space == None:
+ space = transaction.createNewSpace(FLOWCELL_SPACE, None)
+ space.setDescription("A test space")
+ project = transaction.createNewProject(FLOWCELL_PROJECT_ID)
+ project.setDescription("A demo project")
+ expID = FLOWCELL_PROJECT_ID + '/' + datetime.now().strftime("%Y.%m")
+ exp = transaction.getExperiment(expID)
+ if exp == None:
+ exp = transaction.createNewExperiment(expID, EXPERIMENT_TYPE_CODE)
+ newFlowCell = transaction.createNewSample('/' + FLOWCELL_SPACE + '/' + name, "ILLUMINA_FLOW_CELL")
+ newFlowCell.setExperiment(exp)
+
+ if IS_HISEQ_RUN:
+ run = runInfo.getAllchildren('Run')[0].attrib
+ if (run['Id'] != name):
+ raise NameError('Flowcell names do not match between directory name '+ name +
+ ' and ' + RUNINFO + 'property file: ' + run['Id'])
+
+ # The HiSeq is providing more infos, which we will parse here:
+ runParameters = parseXmlFile(incomingPath + '/' + RUNPARAMETERS)
+
+ newFlowCell.setPropertyValue("ILLUMINA_PIPELINE_VERSION", runParameters.getXmlElement(RUNPARAMETERS_XML['RTAVERSION']))
+ newFlowCell.setPropertyValue("FLOWCELLTYPE", runParameters.getXmlElement(RUNPARAMETERS_XML['FLOWCELL']))
+ newFlowCell.setPropertyValue("CONTROL_LANE", runParameters.getXmlElement(RUNPARAMETERS_XML['CONTROLLANE']))
+ newFlowCell.setPropertyValue("SBS_KIT", runParameters.getXmlElement(RUNPARAMETERS_XML['SBS']))
+
+ read1 = runParameters.getAllchildren('Read1')
+ newFlowCell.setPropertyValue("CYCLES_REQUESTED_BY_CUSTOMER", read1[0].text)
+
+ read2 = runParameters.getAllchildren('Read2')
+ if (str(read2[0].text) == '0'):
+ newFlowCell.setPropertyValue("END_TYPE", "SINGLE_READ")
+ else:
+ newFlowCell.setPropertyValue("END_TYPE", "PAIRED_END")
+ newFlowCell.setPropertyValue("PAIRED_END_KIT", runParameters.getXmlElement(RUNPARAMETERS_XML['PE']))
+
+ indexRead1 = runParameters.getAllchildren('IndexRead1')
+ newFlowCell.setPropertyValue("INDEXREAD", indexRead1[0].text)
+
+ indexRead2 = runParameters.getAllchildren('IndexRead2')
+ newFlowCell.setPropertyValue("INDEXREAD2", indexRead2[0].text)
-[registerFlowLane(lane) for lane in range(1,int(maxLanes)+1)]
+ def setFcProperty(searchId, dict):
+ children = runInfo.getAllchildren(searchId)
+ for element in (dict):
+ if (element <> '') and (dict[element] <> ''):
+ newFlowCell.setPropertyValue(element, children[0].attrib[dict[element]])
+
+ setFcProperty('FlowcellLayout', RUNINFO_XML)
+
+ sequencer = runInfo.getAllchildren('Instrument')
+ newFlowCell.setPropertyValue("SEQUENCER", INSTRUMENT[sequencer[0].text])
+
+ newFlowCell.setPropertyValue("FLOW_CELL_SEQUENCED_ON", create_openbis_timestamp())
+ if IS_HISEQ_RUN:
+ maxLanes = runInfo.getAllchildren('FlowcellLayout')[0].attrib[RUNINFO_XML['LANECOUNT']]
+ else:
+ maxLanes = len(runInfo.getAllchildren('Tiles')[0])
+
+ [registerFlowLane(transaction, lane, name, newFlowCell) for lane in range(1,int(maxLanes)+1)]
-shutil.rmtree(incomingPath)
+ shutil.rmtree(incomingPath)
diff --git a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/plugin.properties b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/plugin.properties
index e4d25523f27..9480a66c84c 100644
--- a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/plugin.properties
+++ b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/create-flowcell-dropbox/plugin.properties
@@ -7,6 +7,6 @@
# Path to the directory which contains incoming directories for drop boxes.
incoming-dir = ${incoming-root-dir}/incoming-create-flowcell
incoming-data-completeness-condition = auto-detection
-top-level-data-set-handler = ch.systemsx.cisd.etlserver.registrator.JythonTopLevelDataSetHandler
+top-level-data-set-handler = ch.systemsx.cisd.etlserver.registrator.api.v2.JythonTopLevelDataSetHandlerV2
script-path = create-flowcell-dropbox.py
-storage-processor = ch.systemsx.cisd.etlserver.DefaultStorageProcessor
\ No newline at end of file
+storage-processor = ch.systemsx.cisd.etlserver.DefaultStorageProcessor
diff --git a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/plugin.properties b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/plugin.properties
index 7534e445085..9c4e3bbc2c1 100644
--- a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/plugin.properties
+++ b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/plugin.properties
@@ -6,6 +6,6 @@
# Path to the directory which contains incoming directories for drop boxes.
incoming-dir = ${incoming-root-dir}/incoming-register-flowcell
incoming-data-completeness-condition = auto-detection
-top-level-data-set-handler = ch.systemsx.cisd.etlserver.registrator.JythonTopLevelDataSetHandler
+top-level-data-set-handler = ch.systemsx.cisd.etlserver.registrator.api.v2.JythonTopLevelDataSetHandlerV2
script-path = register-flowcell-dropbox.py
-storage-processor = ch.systemsx.cisd.etlserver.DefaultStorageProcessor
\ No newline at end of file
+storage-processor = ch.systemsx.cisd.etlserver.DefaultStorageProcessor
diff --git a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/register-flowcell-dropbox.py b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/register-flowcell-dropbox.py
index e19f4394b94..48c1f20c76e 100644
--- a/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/register-flowcell-dropbox.py
+++ b/deep_sequencing_unit/source/core-plugins/illumina-ngs/1/dss/drop-boxes/register-flowcell-dropbox/register-flowcell-dropbox.py
@@ -1,9 +1,31 @@
'''
-expected incoming Name for HiSeq2000 runs: 110715_SN792_0054_BC035RACXX
+@copyright:
+2012 ETH Zuerich, CISD
+
+@license:
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+@description:
+Registers an incoming directory as a data set in openBIS. The name of the directory is used to
+search for the matching sample.
+
+@note:
+print statements go to: <openBIS_HOME>/datastore_server/log/startup_log.txt
+expected incoming Name for HiSeq runs: 110715_SN792_0054_BC035RACXX
expected incoming Name for GAII runs: 110812_6353WAAXX
-Note:
-print statements go to: ~openbis/sprint/datastore_server/log/startup_log.txt
+@author:
+Manuel Kohler
'''
from ch.systemsx.cisd.openbis.generic.shared.api.v1.dto import SearchCriteria
@@ -13,34 +35,32 @@ IS_HISEQ_RUN = False
DATASET_TYPE_HISEQ = "ILLUMINA_HISEQ_OUTPUT"
DATASET_TYPE_GA = "ILLUMINA_GA_OUTPUT"
-# Create a "transaction" -- a way of grouping operations together so they all
-# happen or none of them do.
-transaction = service.transaction()
+def process(transaction):
-incomingPath = incoming.getAbsolutePath()
+ incomingPath = transaction.getIncoming().getAbsolutePath()
-# Get the incoming name
-name = incoming.getName()
+ # Get the incoming name
+ name = transaction.getIncoming().getName()
-split = name.split("_")
-if (len(split) == 4):
- dataSet = transaction.createNewDataSet(DATASET_TYPE_HISEQ)
- IS_HISEQ_RUN = True
-if (len(split) == 2):
- dataSet = transaction.createNewDataSet(DATASET_TYPE_GA)
+ split = name.split("_")
+ if (len(split) == 4):
+ dataSet = transaction.createNewDataSet(DATASET_TYPE_HISEQ)
+ IS_HISEQ_RUN = True
+ if (len(split) == 2):
+ dataSet = transaction.createNewDataSet(DATASET_TYPE_GA)
-# Create a data set and set type
-dataSet.setMeasuredData(False)
+ # Create a data set and set type
+ dataSet.setMeasuredData(False)
-# Get the search service
-search_service = transaction.getSearchService()
+ # Get the search service
+ search_service = transaction.getSearchService()
-# Search for the sample
-sc = SearchCriteria()
-sc.addMatchClause(SearchCriteria.MatchClause.createAttributeMatch(SearchCriteria.MatchClauseAttribute.CODE, name));
-foundSamples = search_service.searchForSamples(sc)
-
-if foundSamples.size() > 0:
- # Add the incoming file into the data set
- transaction.moveFile(incomingPath, dataSet)
- dataSet.setSample(foundSamples[0])
+ # Search for the sample
+ sc = SearchCriteria()
+ sc.addMatchClause(SearchCriteria.MatchClause.createAttributeMatch(SearchCriteria.MatchClauseAttribute.CODE, name));
+ foundSamples = search_service.searchForSamples(sc)
+
+ if foundSamples.size() > 0:
+ # Add the incoming file into the data set
+ transaction.moveFile(incomingPath, dataSet)
+ dataSet.setSample(foundSamples[0])
--
GitLab