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 test_skip_blank(self): occurrence = CSVReader("data/occurrence_blanklines.txt", delimiter="\t", quote_char="\"", index_fields=["institutionCode"], skip_blank=False) self.assertTrue("" in occurrence.indexes()["institutionCode"]) occurrence = CSVReader("data/occurrence_blanklines.txt", delimiter="\t", quote_char="\"", index_fields=["institutionCode"], skip_blank=True) self.assertFalse("" in occurrence.indexes()["institutionCode"])
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")
#occurrence = CSVReader("data/occurrence.txt", delimiter="\t", quote_char="\"", index_fields=["scientificName"], field_names=names) #print(occurrence.indexes()) #records = occurrence.get_lines("scientificName", "Neomysis integer") #print(records) names = { 'eventID': 2, 'decimalLatitude': 10, 'minimumDepthInMeters': 8, 'habitat': 5, 'locality': 7, 'parentEventID': 3, 'modified': 1, 'footprintWKT': 13, 'decimalLongitude': 11, 'maximumDepthInMeters': 9, 'locationID': 6, 'id': 0, 'coordinateUncertaintyInMeters': 12, 'eventDate': 4 } event = CSVReader("data/event2.txt", delimiter="\t", quote_char=None, index_fields=["eventID", "parentEventID", "id"], field_names=names) print(json.dumps(event.indexes(), indent=4)) #event = CSVReader("data/occurrence_blanklines.txt", delimiter="\t", quote_char=None, index_fields=["institutionCode"], skip_blank=True) #print(json.dumps(event.indexes(), indent=4))
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