def testRead(self):
occurrence = CSVReader("data/occurrence.txt",
delimiter="\t",
quoteChar="\"",
indexFields=["id", "eventID"])
indexes = occurrence.indexes()
self.assertTrue("id" in indexes)
self.assertTrue("eventID" in indexes)
self.assertTrue(
"Cruise68:Station593:EventSorbeSledge9887:Subsample16687" in
indexes["eventID"])
self.assertTrue(
len(indexes["eventID"]
["Cruise68:Station593:EventSorbeSledge9887:Subsample16687"]) ==
39)
records = occurrence.getLines(
"id", "Cruise68:Station565:EventSorbeSledge9781:Subsample17409")
self.assertTrue(len(records) > 0)
self.assertTrue(
records[0]["eventID"] ==
"Cruise68:Station565:EventSorbeSledge9781:Subsample17409")
self.assertTrue(records[0]["scientificNameID"] ==
"urn:lsid:marinespecies.org:taxname:131495")
records = occurrence.getLines(
"eventID",
"Cruise68:Station622:EventSorbeSledge10018:Subsample15224")
self.assertTrue(
records[21]["eventID"] ==
"Cruise68:Station622:EventSorbeSledge10018:Subsample15224")
self.assertTrue(records[21]["scientificNameID"] ==
"urn:lsid:marinespecies.org:taxname:120144")
def testNotIndexed(self):
occurrence = CSVReader("data/occurrence.txt",
delimiter="\t",
quoteChar="\"")
with self.assertRaises(RuntimeError):
records = list(
occurrence.getLines(
"eventID",
"Cruise68:Station593:EventSorbeSledge9887:Subsample16687"))
def testDev(self):
occurrence = CSVReader("data/occurrence.txt",
delimiter="\t",
quoteChar="\"",
indexFields=["scientificName"])
print occurrence.indexes()
records = occurrence.getLines("scientificName", "Neomysis integer")
print records
def testFieldNamesDict(self):
names = {"scientificName": 7}
occurrence = CSVReader("data/occurrence.txt",
delimiter="\t",
quoteChar="\"",
indexFields=["scientificName"],
fieldNames=names)
records = list(
occurrence.getLines("scientificName", "Neomysis integer"))
self.assertTrue(records[0]["scientificName"] == "Neomysis integer")
self.assertTrue(
records[0]["col_6"] == "urn:lsid:marinespecies.org:taxname:120136")
def testFieldNamesList(self):
names = [
"id", "basisOfRecord", "occurrenceID", "sex", "lifeStage",
"eventID"
]
occurrence = CSVReader("data/occurrence.txt",
delimiter="\t",
quoteChar="\"",
indexFields=["eventID"],
fieldNames=names)
records = list(
occurrence.getLines(
"eventID",
"Cruise68:Station593:EventSorbeSledge9887:Subsample16687"))
self.assertTrue(
records[0]["eventID"] ==
"Cruise68:Station593:EventSorbeSledge9887:Subsample16687")
self.assertTrue(records[0]["occurrenceID"] == "Ugenthyperbenthos51168")
self.assertTrue(records[0]["col_6"] == "Sagitta elegans")
from csvreader import CSVReader
#names = {"scientificName": 7}
#occurrence = CSVReader("data/occurrence.txt", delimiter="\t", quoteChar="\"", indexFields=["scientificName"], fieldNames=names)
#print occurrence.indexes()
#records = occurrence.getLines("scientificName", "Neomysis integer")
#print records
#names = ["id", "basisOfRecord", "occurrenceID", "sex", "lifeStage", "eventID", "scientificNameID", "scientificName"]
#occurrence = CSVReader("data/occurrence.txt", delimiter="\t", quoteChar="\"", indexFields=["scientificName"], fieldNames=names)
#print occurrence.indexes()
#records = occurrence.getLines("scientificName", "Neomysis integer")
#print records
names = ["id", "basisOfRecord", "occurrenceID", "sex", "lifeStage", "eventID"]
occurrence = CSVReader("data/occurrence.txt",
delimiter="\t",
quoteChar="\"",
indexFields=["eventID"],
fieldNames=names)
print occurrence.indexes()
records = occurrence.getLines(
"eventID", "Cruise68:Station593:EventSorbeSledge9887:Subsample16687")
for r in records:
print r
#print len(occurrence)
#for line in occurrence:
# print line
# break