diff --git a/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py b/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
index 425699d6a9b090120fac7e0bdcb79ffe39cecbd6..e8462a5d0c87efb745763dcc6e02736a992d2c7e 100644
--- a/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
+++ b/eu_basynthec/dist/etc/growth-profiles/data-set-handler.py
@@ -9,10 +9,19 @@ def retrieve_experiment(tr, exp_id):
exp = tr.getExperiment(exp_id)
return exp
+def extract_strains():
+ """Extract the strains from the data sheet"""
+ strains = []
+ lines = timeSeriesData.getRawDataLines()
+ for i in range(1, len(lines)):
+ line = lines[i]
+ strains.append(line[0])
+ return ",".join(strains)
+
def assign_properties(dataset, metadata):
"""Assign properties to the data set from information in the data."""
propertyNameMap = {
- "STRAIN":"STRAIN",
+ "STRAIN_NAMES": "STRAIN_NAMES",
"TIMEPOINT TYPE": "TIMEPOINT_TYPE",
"CELL LOCATION": "CELL_LOCATION",
"VALUE TYPE": "VALUE_TYPE",
@@ -53,6 +62,8 @@ timeSeriesData = TimeSeriesDataExcel.createTimeSeriesDataExcel(incoming.getAbsol
# create the data set and assign the metadata from the file
dataset = tr.createNewDataSet("OD600")
metadata = timeSeriesData.getMetadataMap()
+# Strains are not in the metadata, but in the data, so extract them
+metadata["STRAIN_NAMES"] = extract_strains()
assign_properties(dataset, metadata)
# Convert the data into a tsv file, and put that and the original data into the data set
diff --git a/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py b/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py
index c09a86937a65acebfb74653345354dad5a569e7c..c3c470a0a616bf5b86e76f5734e55ae9cb16e724 100644
--- a/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py
+++ b/eu_basynthec/dist/etc/growth-profiles/data-set-validator.py
@@ -1,120 +1,25 @@
-import os
-import re
-import sys
-import java.io.File
-from java.io import IOException
-from java.lang import IllegalArgumentException
-from ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation import ValidationError, ValidationScriptRunner
-from ch.systemsx.cisd.openbis.dss.generic.shared.utils import ExcelFileReader
-from ch.systemsx.cisd.common.logging import LogFactory, LogCategory
-
-operationLog = LogFactory.getLogger(LogCategory.OPERATION, ValidationScriptRunner)
-OPENBIS_METADATA_SHEET_NAME = "openbis-metadata"
-OPENBIS_DATA_SHEET_NAME = "openbis-data"
-
-class TimeSeriesDataExcel:
- """
- An abstraction for accessing time series data following the BaSynthec conventions
- from an Excel file. This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, file, fileReader):
- self.file = file
- self.fileReader = fileReader
-
- def getRawMetadataLines(self):
- """Get the raw lines of the metadata sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
- + OPENBIS_METADATA_SHEET_NAME + "]", ex)
- return []
-
- def getRawDataLines(self):
- """Get the raw lines of the data sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
- + OPENBIS_DATA_SHEET_NAME + "]", ex)
- return []
-
- def getMetadataMap(self):
- """
- Return the metadata has a hashmap, with all keys uppercased.
-
- Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
- that can be ignored], that is the property name is in column 1 and property value is in
- column 2, and everything else can be ignored.
- """
- metadataMap = {}
- metadataLines = self.getRawMetadataLines()
-
- # Skip the first line, this is just the header
- for i in range(1, metadataLines.size()):
- line = metadataLines.get(i)
- value = line[1];
- if "BLANK" == value:
- value = None
- metadataMap[line[0].upper()] = value
- return metadataMap
-
-def create_time_series_excel(fileName):
- """Factory method for the TimeSeriesData object. Returns None if it cannot be created"""
- file = java.io.File(fileName)
- try:
- workbook = ExcelFileReader.getExcelWorkbook(file)
- fileReader = ExcelFileReader(workbook, True)
- return TimeSeriesDataExcel(file, fileReader)
- except IllegalArgumentException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- except IOException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- return None
-
-
-
-class ValidationHelper:
- """
- Methods for simplifying validation in BaSynthec.
- This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, metadataMap, errors):
- self.metadataMap = metadataMap
- self.errors = errors
-
- def checkIsSpecified(self, property, displayName):
- if self.metadataMap.get(property) is None:
- self.errors.append(ValidationError.createFileValidationError("A " + displayName
- + " must be specified."))
- return False
- return True
-
def validate_data(timeSeriesData, errors):
dataLines = timeSeriesData.getRawDataLines()
lineCount = 0
for line in dataLines:
# The header needs to be Abs
if lineCount is 0:
- if line[0] != "Abs":
- errors.append(createFileValidationError("The first data column must be 'Abs'"))
+ if line[0] != "Strain":
+ errors.append(createFileValidationError("The first data column must be 'Strain'"))
break
lineCount = lineCount + 1
continue
# The compound id should be one of these forms
- od600 = line[0]
- if od600 != "OD600":
- errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be OD600 (instead of " + od600 + ")."))
+ strain = line[0]
+ if not isStrainIdValid(strain):
+ errors.append(createFileValidationError("Line " + str(lineCount + 1) + ", column 1 must be MGP[0-999] (instead of " + strain + ")."))
lineCount = lineCount + 1
def validate_metadata(time_series_data, errors):
metadata = time_series_data.getMetadataMap()
validationHelper = ValidationHelper(metadata, errors)
- # validate the strain
- validationHelper.checkIsSpecified("STRAIN", "strain")
-
# validate the timepoint type
if validationHelper.checkIsSpecified("TIMEPOINT TYPE", "time point type"):
if metadata.get("TIMEPOINT TYPE").upper() not in ['EX', 'IN', 'SI']:
diff --git a/eu_basynthec/dist/etc/metabolomics/data-set-validator.py b/eu_basynthec/dist/etc/metabolomics/data-set-validator.py
index e6e549068a48c1f997516173276b87809cdd84fc..d6ef4b4cb27397593927016ee35a575f189a445c 100644
--- a/eu_basynthec/dist/etc/metabolomics/data-set-validator.py
+++ b/eu_basynthec/dist/etc/metabolomics/data-set-validator.py
@@ -1,95 +1,3 @@
-import os
-import re
-import sys
-import java.io.File
-from java.io import IOException
-from java.lang import IllegalArgumentException
-from ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation import ValidationError, ValidationScriptRunner
-from ch.systemsx.cisd.openbis.dss.generic.shared.utils import ExcelFileReader
-from ch.systemsx.cisd.common.logging import LogFactory, LogCategory
-
-operationLog = LogFactory.getLogger(LogCategory.OPERATION, ValidationScriptRunner)
-OPENBIS_METADATA_SHEET_NAME = "openbis-metadata"
-OPENBIS_DATA_SHEET_NAME = "openbis-data"
-
-class TimeSeriesDataExcel:
- """
- An abstraction for accessing time series data following the BaSynthec conventions
- from an Excel file. This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, file, fileReader):
- self.file = file
- self.fileReader = fileReader
-
- def getRawMetadataLines(self):
- """Get the raw lines of the metadata sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
- + OPENBIS_METADATA_SHEET_NAME + "]", ex)
- return []
-
- def getRawDataLines(self):
- """Get the raw lines of the data sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
- + OPENBIS_DATA_SHEET_NAME + "]", ex)
- return []
-
- def getMetadataMap(self):
- """
- Return the metadata has a hashmap, with all keys uppercased.
-
- Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
- that can be ignored], that is the property name is in column 1 and property value is in
- column 2, and everything else can be ignored.
- """
- metadataMap = {}
- metadataLines = self.getRawMetadataLines()
-
- # Skip the first line, this is just the header
- for i in range(1, metadataLines.size()):
- line = metadataLines.get(i)
- value = line[1];
- if "BLANK" == value:
- value = None
- metadataMap[line[0].upper()] = value
- return metadataMap
-
-def create_time_series_excel(fileName):
- """Factory method for the TimeSeriesData object. Returns None if it cannot be created"""
- file = java.io.File(fileName)
- try:
- workbook = ExcelFileReader.getExcelWorkbook(file)
- fileReader = ExcelFileReader(workbook, True)
- return TimeSeriesDataExcel(file, fileReader)
- except IllegalArgumentException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- except IOException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- return None
-
-
-
-class ValidationHelper:
- """
- Methods for simplifying validation in BaSynthec.
- This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, metadataMap, errors):
- self.metadataMap = metadataMap
- self.errors = errors
-
- def checkIsSpecified(self, property, displayName):
- if self.metadataMap.get(property) is None:
- self.errors.append(ValidationError.createFileValidationError("A " + displayName
- + " must be specified."))
- return False
- return True
-
def validate_data(time_series_data, errors):
chebiRegex = re.compile("^CHEBI:[0-9]+")
diff --git a/eu_basynthec/dist/etc/proteomics/data-set-validator.py b/eu_basynthec/dist/etc/proteomics/data-set-validator.py
index c1150d736ebceb5234e38ff17f84daa1ba3a9d74..3b4b73e074b380653e688e811ad10db8e2dfdfa8 100644
--- a/eu_basynthec/dist/etc/proteomics/data-set-validator.py
+++ b/eu_basynthec/dist/etc/proteomics/data-set-validator.py
@@ -1,95 +1,3 @@
-import os
-import re
-import sys
-import java.io.File
-from java.io import IOException
-from java.lang import IllegalArgumentException
-from ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation import ValidationError, ValidationScriptRunner
-from ch.systemsx.cisd.openbis.dss.generic.shared.utils import ExcelFileReader
-from ch.systemsx.cisd.common.logging import LogFactory, LogCategory
-
-operationLog = LogFactory.getLogger(LogCategory.OPERATION, ValidationScriptRunner)
-OPENBIS_METADATA_SHEET_NAME = "openbis-metadata"
-OPENBIS_DATA_SHEET_NAME = "openbis-data"
-
-class TimeSeriesDataExcel:
- """
- An abstraction for accessing time series data following the BaSynthec conventions
- from an Excel file. This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, file, fileReader):
- self.file = file
- self.fileReader = fileReader
-
- def getRawMetadataLines(self):
- """Get the raw lines of the metadata sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
- + OPENBIS_METADATA_SHEET_NAME + "]", ex)
- return []
-
- def getRawDataLines(self):
- """Get the raw lines of the data sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
- + OPENBIS_DATA_SHEET_NAME + "]", ex)
- return []
-
- def getMetadataMap(self):
- """
- Return the metadata has a hashmap, with all keys uppercased.
-
- Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
- that can be ignored], that is the property name is in column 1 and property value is in
- column 2, and everything else can be ignored.
- """
- metadataMap = {}
- metadataLines = self.getRawMetadataLines()
-
- # Skip the first line, this is just the header
- for i in range(1, metadataLines.size()):
- line = metadataLines.get(i)
- value = line[1];
- if "BLANK" == value:
- value = None
- metadataMap[line[0].upper()] = value
- return metadataMap
-
-def create_time_series_excel(fileName):
- """Factory method for the TimeSeriesData object. Returns None if it cannot be created"""
- file = java.io.File(fileName)
- try:
- workbook = ExcelFileReader.getExcelWorkbook(file)
- fileReader = ExcelFileReader(workbook, True)
- return TimeSeriesDataExcel(file, fileReader)
- except IllegalArgumentException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- except IOException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- return None
-
-
-
-class ValidationHelper:
- """
- Methods for simplifying validation in BaSynthec.
- This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, metadataMap, errors):
- self.metadataMap = metadataMap
- self.errors = errors
-
- def checkIsSpecified(self, property, displayName):
- if self.metadataMap.get(property) is None:
- self.errors.append(ValidationError.createFileValidationError("A " + displayName
- + " must be specified."))
- return False
- return True
-
def validate_data(time_series_data, errors):
gene_locus_regex = re.compile("^BSU[0-9]+|^BSU_misc_RNA_[0-9]+|^VMG_[0-9]+_[0-9]+(_c)?")
column_header_regex = re.compile("(\+|-)?[0-9]+::(value|mean|median|std|var|error|iqr)")
diff --git a/eu_basynthec/dist/etc/shared/shared-classes.py b/eu_basynthec/dist/etc/shared/shared-classes.py
new file mode 100644
index 0000000000000000000000000000000000000000..07f7cecb4e3b60380657a2b35d7d4f84b25054d7
--- /dev/null
+++ b/eu_basynthec/dist/etc/shared/shared-classes.py
@@ -0,0 +1,101 @@
+import os
+import re
+import sys
+import java.io.File
+from java.io import IOException
+from java.lang import IllegalArgumentException
+from ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation import ValidationError, ValidationScriptRunner
+from ch.systemsx.cisd.openbis.dss.generic.shared.utils import ExcelFileReader
+from ch.systemsx.cisd.common.logging import LogFactory, LogCategory
+
+operationLog = LogFactory.getLogger(LogCategory.OPERATION, ValidationScriptRunner)
+OPENBIS_METADATA_SHEET_NAME = "openbis-metadata"
+OPENBIS_DATA_SHEET_NAME = "openbis-data"
+
+class TimeSeriesDataExcel:
+ """
+ An abstraction for accessing time series data following the BaSynthec conventions
+ from an Excel file. This class ported from Java, thus the camelCase naming.
+ """
+ def __init__(self, file, fileReader):
+ self.file = file
+ self.fileReader = fileReader
+
+ def getRawMetadataLines(self):
+ """Get the raw lines of the metadata sheet."""
+ try:
+ return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
+ except IOException, ex:
+ operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
+ + OPENBIS_METADATA_SHEET_NAME + "]", ex)
+ return []
+
+ def getRawDataLines(self):
+ """Get the raw lines of the data sheet."""
+ try:
+ return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
+ except IOException, ex:
+ operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
+ + OPENBIS_DATA_SHEET_NAME + "]", ex)
+ return []
+
+ def getMetadataMap(self):
+ """
+ Return the metadata has a hashmap, with all keys uppercased.
+
+ Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
+ that can be ignored], that is the property name is in column 1 and property value is in
+ column 2, and everything else can be ignored.
+ """
+ metadataMap = {}
+ metadataLines = self.getRawMetadataLines()
+
+ # Skip the first line, this is just the header
+ for i in range(1, metadataLines.size()):
+ line = metadataLines.get(i)
+ value = line[1];
+ if "BLANK" == value:
+ value = None
+ metadataMap[line[0].upper()] = value
+ return metadataMap
+
+def create_time_series_excel(fileName):
+ """Factory method for the TimeSeriesData object. Returns None if it cannot be created."""
+ file = java.io.File(fileName)
+ try:
+ workbook = ExcelFileReader.getExcelWorkbook(file)
+ fileReader = ExcelFileReader(workbook, True)
+ return TimeSeriesDataExcel(file, fileReader)
+ except IllegalArgumentException, ex:
+ operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
+ except IOException, ex:
+ operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
+ return None
+
+
+
+class ValidationHelper:
+ """
+ Methods for simplifying validation in BaSynthec.
+ This class is ported from Java, thus the camelCase naming.
+ """
+ def __init__(self, metadataMap, errors):
+ self.metadataMap = metadataMap
+ self.errors = errors
+
+ def checkIsSpecified(self, property, displayName):
+ """Verify that a property is specified; if not, add a validation error to the list."""
+ if self.metadataMap.get(property) is None:
+ self.errors.append(ValidationError.createFileValidationError("A " + displayName
+ + " must be specified."))
+ return False
+ return True
+
+
+strainIdRegex = re.compile("^MGP[0-9]{1,3}")
+def isStrainIdValid(strainId):
+ """Return true if the strain id passes validation (has the form MGP[:digit:]{1,3})"""
+ match = strainIdRegex.match(strainId)
+ if match is None:
+ return False
+ return match.end() == len(strainId)
diff --git a/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py b/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py
index 5cdf0840db0c90ff7924b16fc815d952788a3528..b42c2fdb592174caba11535c09fc11aef39273eb 100644
--- a/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py
+++ b/eu_basynthec/dist/etc/transcriptomics/data-set-validator.py
@@ -1,95 +1,3 @@
-import os
-import re
-import sys
-import java.io.File
-from java.io import IOException
-from java.lang import IllegalArgumentException
-from ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation import ValidationError, ValidationScriptRunner
-from ch.systemsx.cisd.openbis.dss.generic.shared.utils import ExcelFileReader
-from ch.systemsx.cisd.common.logging import LogFactory, LogCategory
-
-operationLog = LogFactory.getLogger(LogCategory.OPERATION, ValidationScriptRunner)
-OPENBIS_METADATA_SHEET_NAME = "openbis-metadata"
-OPENBIS_DATA_SHEET_NAME = "openbis-data"
-
-class TimeSeriesDataExcel:
- """
- An abstraction for accessing time series data following the BaSynthec conventions
- from an Excel file. This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, file, fileReader):
- self.file = file
- self.fileReader = fileReader
-
- def getRawMetadataLines(self):
- """Get the raw lines of the metadata sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_METADATA_SHEET_NAME);
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + self.file.getPath() + ", sheet: "
- + OPENBIS_METADATA_SHEET_NAME + "]", ex)
- return []
-
- def getRawDataLines(self):
- """Get the raw lines of the data sheet."""
- try:
- return self.fileReader.readLines(OPENBIS_DATA_SHEET_NAME)
- except IOException, ex:
- operationLog.error("Could not read data from [file: " + file.getPath() + ", sheet: "
- + OPENBIS_DATA_SHEET_NAME + "]", ex)
- return []
-
- def getMetadataMap(self):
- """
- Return the metadata has a hashmap, with all keys uppercased.
-
- Assumes the metadata sheet corresponds to the following format: [Property] [Value] [... stuff
- that can be ignored], that is the property name is in column 1 and property value is in
- column 2, and everything else can be ignored.
- """
- metadataMap = {}
- metadataLines = self.getRawMetadataLines()
-
- # Skip the first line, this is just the header
- for i in range(1, metadataLines.size()):
- line = metadataLines.get(i)
- value = line[1];
- if "BLANK" == value:
- value = None
- metadataMap[line[0].upper()] = value
- return metadataMap
-
-def create_time_series_excel(fileName):
- """Factory method for the TimeSeriesData object. Returns None if it cannot be created"""
- file = java.io.File(fileName)
- try:
- workbook = ExcelFileReader.getExcelWorkbook(file)
- fileReader = ExcelFileReader(workbook, True)
- return TimeSeriesDataExcel(file, fileReader)
- except IllegalArgumentException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- except IOException, ex:
- operationLog.error("Could not open file [" + fileName + "] as Excel data.", ex)
- return None
-
-
-
-class ValidationHelper:
- """
- Methods for simplifying validation in BaSynthec.
- This class ported from Java, thus the camelCase naming.
- """
- def __init__(self, metadataMap, errors):
- self.metadataMap = metadataMap
- self.errors = errors
-
- def checkIsSpecified(self, property, displayName):
- if self.metadataMap.get(property) is None:
- self.errors.append(ValidationError.createFileValidationError("A " + displayName
- + " must be specified."))
- return False
- return True
-
def validate_data(time_series_data, errors):
gene_locus_regex = re.compile("^BSU[0-9]+|^BSU_misc_RNA_[0-9]+|^VMG_[0-9]+_[0-9]+(_c)?")
dataLines = time_series_data.getRawDataLines()
diff --git a/eu_basynthec/sourceTest/examples/OD600-BadData.xlsx b/eu_basynthec/sourceTest/examples/OD600-BadData.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..77472c04d3163f7920b325721eaa0ad7c375796a
Binary files /dev/null and b/eu_basynthec/sourceTest/examples/OD600-BadData.xlsx differ
diff --git a/eu_basynthec/sourceTest/examples/OD600-Example.xlsx b/eu_basynthec/sourceTest/examples/OD600-Example.xlsx
index d6e35b4b893639449069f18023af3fb499c40204..4f83f9ce28149ce85353f1e0456bfaddba7aa093 100644
Binary files a/eu_basynthec/sourceTest/examples/OD600-Example.xlsx and b/eu_basynthec/sourceTest/examples/OD600-Example.xlsx differ
diff --git a/eu_basynthec/sourceTest/examples/OD600-Template.xlsx b/eu_basynthec/sourceTest/examples/OD600-Template.xlsx
index 08dbb1ba136006d62f943514eda36cfbc8d33a88..be43feb2f882179020b274e7f3ca47119135cad8 100644
Binary files a/eu_basynthec/sourceTest/examples/OD600-Template.xlsx and b/eu_basynthec/sourceTest/examples/OD600-Template.xlsx differ
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java
new file mode 100644
index 0000000000000000000000000000000000000000..eaa8a49f4226f153e3236ee4e1ef825b239f189d
--- /dev/null
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600DataSetRegistratorTest.java
@@ -0,0 +1,132 @@
+/*
+ * Copyright 2011 ETH Zuerich, CISD
+ *
+ * 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.
+ */
+
+package eu.basynthec.cisd.dss.growthprofiles;
+
+import static ch.systemsx.cisd.common.Constants.IS_FINISHED_PREFIX;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Properties;
+
+import org.apache.commons.io.FileUtils;
+import org.jmock.Expectations;
+import org.testng.annotations.Test;
+
+import ch.systemsx.cisd.common.filesystem.FileUtilities;
+import ch.systemsx.cisd.common.test.RecordingMatcher;
+import ch.systemsx.cisd.etlserver.registrator.AbstractJythonDataSetHandlerTest;
+import ch.systemsx.cisd.openbis.generic.shared.basic.dto.DataSetType;
+import ch.systemsx.cisd.openbis.generic.shared.basic.dto.Experiment;
+import ch.systemsx.cisd.openbis.generic.shared.basic.dto.builders.ExperimentBuilder;
+import ch.systemsx.cisd.openbis.generic.shared.dto.AtomicEntityOperationResult;
+import ch.systemsx.cisd.openbis.generic.shared.dto.NewExternalData;
+import ch.systemsx.cisd.openbis.generic.shared.dto.NewProperty;
+import ch.systemsx.cisd.openbis.generic.shared.dto.identifier.ExperimentIdentifierFactory;
+
+/**
+ * @author Chandrasekhar Ramakrishnan
+ */
+public class OD600DataSetRegistratorTest extends AbstractJythonDataSetHandlerTest
+{
+ private static final String STRAIN_NAMES_PROP = "STRAIN_NAMES";
+
+ private static final String DATA_SET_CODE = "data-set-code";
+
+ private static final DataSetType DATA_SET_TYPE = new DataSetType("OD600");
+
+ private static final String EXPERIMENT_IDENTIFIER = "/TEST/TEST/TEST";
+
+ @Test
+ public void testSimpleTransaction() throws IOException
+ {
+ setUpHomeDataBaseExpectations();
+ Properties properties =
+ createThreadPropertiesRelativeToScriptsFolder("data-set-handler.py",
+ "dist/etc/shared/shared-classes.py,dist/etc/growth-profiles/data-set-validator.py");
+ createHandler(properties, false, true);
+ createData();
+
+ ExperimentBuilder builder = new ExperimentBuilder().identifier(EXPERIMENT_IDENTIFIER);
+ final Experiment experiment = builder.getExperiment();
+ final RecordingMatcher<ch.systemsx.cisd.openbis.generic.shared.dto.AtomicEntityOperationDetails> atomicatOperationDetails =
+ new RecordingMatcher<ch.systemsx.cisd.openbis.generic.shared.dto.AtomicEntityOperationDetails>();
+ context.checking(new Expectations()
+ {
+ {
+ one(openBisService).createDataSetCode();
+ will(returnValue(DATA_SET_CODE));
+ atLeast(1).of(openBisService).tryToGetExperiment(
+ new ExperimentIdentifierFactory(experiment.getIdentifier())
+ .createIdentifier());
+ will(returnValue(experiment));
+
+ one(dataSetValidator).assertValidDataSet(DATA_SET_TYPE,
+ new File(new File(stagingDirectory, DATA_SET_CODE), "data"));
+ one(openBisService).performEntityOperations(with(atomicatOperationDetails));
+ will(returnValue(new AtomicEntityOperationResult()));
+ }
+ });
+
+ handler.handle(markerFile);
+
+ assertEquals(1, atomicatOperationDetails.recordedObject().getDataSetRegistrations().size());
+
+ NewExternalData dataSet =
+ atomicatOperationDetails.recordedObject().getDataSetRegistrations().get(0);
+
+ assertEquals(DATA_SET_CODE, dataSet.getCode());
+ assertEquals(DATA_SET_TYPE, dataSet.getDataSetType());
+
+ HashMap<String, NewProperty> propertyMap =
+ getDataSetPropertiesMap(dataSet.getDataSetProperties());
+ NewProperty strainProperty = propertyMap.get(STRAIN_NAMES_PROP);
+
+ assertNotNull(strainProperty);
+ assert null != strainProperty;
+ assertEquals("MGP1,MGP100,MGP20,MGP999", strainProperty.getValue());
+ context.assertIsSatisfied();
+ }
+
+ private void createData() throws IOException
+ {
+ File dataFile = new File("sourceTest/examples/OD600-Example.xlsx");
+ FileUtils.copyFileToDirectory(dataFile, workingDirectory);
+ incomingDataSetFile = new File(workingDirectory, dataFile.getName());
+
+ markerFile = new File(workingDirectory, IS_FINISHED_PREFIX + dataFile.getName());
+ FileUtilities.writeToFile(markerFile, "");
+ }
+
+ protected HashMap<String, NewProperty> getDataSetPropertiesMap(
+ List<NewProperty> dataSetProperties)
+ {
+ HashMap<String, NewProperty> propertyMap = new HashMap<String, NewProperty>();
+ for (NewProperty prop : dataSetProperties)
+ {
+ propertyMap.put(prop.getPropertyCode(), prop);
+ }
+ return propertyMap;
+ }
+
+ @Override
+ protected String getRegistrationScriptsFolderPath()
+ {
+ return "dist/etc/growth-profiles/";
+ }
+}
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600ValidatorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600ValidatorTest.java
index de98a23d1928e942f60f0c590258888a89c99185..3d4059fb0361ead8a98d8d60b0b82da41e2b7734 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600ValidatorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/growthprofiles/OD600ValidatorTest.java
@@ -31,7 +31,7 @@ import ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation.ValidationS
public class OD600ValidatorTest extends AssertJUnit
{
private static final String[] VALIDATION_SCRIPT_PATH = new String[]
- { "dist/etc/growth-profiles/data-set-validator.py" };
+ { "dist/etc/shared/shared-classes.py", "dist/etc/growth-profiles/data-set-validator.py" };
@Test
public void testGoodData()
@@ -43,6 +43,20 @@ public class OD600ValidatorTest extends AssertJUnit
assertTrue("The example should have no errors", errors.isEmpty());
}
+ @Test
+ public void testBadData()
+ {
+ ValidationScriptRunner scriptRunner =
+ ValidationScriptRunner.createValidatorFromScriptPaths(VALIDATION_SCRIPT_PATH);
+ List<ValidationError> errors =
+ scriptRunner.validate(new File("sourceTest/examples/OD600-BadData.xlsx"));
+ assertEquals("The bad data should have two errors", 2, errors.size());
+ assertEquals("Line 2, column 1 must be MGP[0-999] (instead of OD600).", errors.get(0)
+ .getErrorMessage());
+ assertEquals("Line 3, column 1 must be MGP[0-999] (instead of MGP1000).", errors.get(1)
+ .getErrorMessage());
+ }
+
@Test
public void testTemplate()
{
@@ -50,11 +64,7 @@ public class OD600ValidatorTest extends AssertJUnit
ValidationScriptRunner.createValidatorFromScriptPaths(VALIDATION_SCRIPT_PATH);
List<ValidationError> errors =
scriptRunner.validate(new File("sourceTest/examples/OD600-Template.xlsx"));
- if (errors.size() > 0)
- {
- System.out.println(errors);
- }
- assertEquals("The template should have five errors", 5, errors.size());
+ assertEquals("The template should have five errors", 4, errors.size());
}
}
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/metabolomics/MetabolomicsValidatorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/metabolomics/MetabolomicsValidatorTest.java
index 6d2fcf11532b3d7fef72af490035311ad4223f0d..8dc2ba733bd7ed9eb27c41b82ed5e74d371aa452 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/metabolomics/MetabolomicsValidatorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/metabolomics/MetabolomicsValidatorTest.java
@@ -31,7 +31,7 @@ import ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation.ValidationS
public class MetabolomicsValidatorTest extends AssertJUnit
{
private static final String[] VALIDATION_SCRIPT_PATH = new String[]
- { "dist/etc/metabolomics/data-set-validator.py" };
+ { "dist/etc/shared/shared-classes.py", "dist/etc/metabolomics/data-set-validator.py" };
@Test
public void testGoodData()
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/proteomics/ProteomicsValidatorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/proteomics/ProteomicsValidatorTest.java
index d75f588fc76cf87c67781bf237a98c32b1e6f40e..2a41d4361169c7fbad6ac98a6e082dc29c3ab685 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/proteomics/ProteomicsValidatorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/proteomics/ProteomicsValidatorTest.java
@@ -31,7 +31,7 @@ import ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation.ValidationS
public class ProteomicsValidatorTest extends AssertJUnit
{
private static final String[] VALIDATION_SCRIPT_PATH = new String[]
- { "dist/etc/proteomics/data-set-validator.py" };
+ { "dist/etc/shared/shared-classes.py", "dist/etc/proteomics/data-set-validator.py" };
@Test
public void testGoodData()
diff --git a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsValidatorTest.java b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsValidatorTest.java
index e6c76a7c28328c4b61e3c88839cc1913dd64e43d..1b009c1724585e0dced241ca08be1e4af6d6c3fa 100644
--- a/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsValidatorTest.java
+++ b/eu_basynthec/sourceTest/java/eu/basynthec/cisd/dss/transcriptomics/TranscriptomicsValidatorTest.java
@@ -31,7 +31,7 @@ import ch.systemsx.cisd.openbis.dss.generic.shared.api.v1.validation.ValidationS
public class TranscriptomicsValidatorTest extends AssertJUnit
{
private static final String[] VALIDATION_SCRIPT_PATH = new String[]
- { "dist/etc/transcriptomics/data-set-validator.py" };
+ { "dist/etc/shared/shared-classes.py", "dist/etc/transcriptomics/data-set-validator.py" };
@Test
public void testGoodData()