def retrieveTermListMetadata(githubBaseUri):
# retrieve term list metadata from Github
dataUrl = githubBaseUri + 'term-lists/term-lists.csv'
table = http_library.retrieveData(dataUrl, 'csv', ',')
header = table[0]
# determine which columns contain the namespace info
for column in range(len(header)):
if header[column] == 'list':
listColumn = column
if header[column] == 'vann_preferredNamespacePrefix':
prefixColumn = column
if header[column] == 'vann_preferredNamespaceUri':
uriColumn = column
listFilename = {}
listNamespace = {}
listUri = {}
for row in range(1, len(table)): #skip the header row
for termList in termLists:
if termList == table[row][listColumn]:
listNamespace[termList] = table[row][
prefixColumn] # make a dictionary of namespaces
listUri[termList] = table[row][
uriColumn] # make a dictionary of URIs
if table[row][prefixColumn] == 'ac':
listFilename[termList] = 'audubon'
else:
listFilename[termList] = table[row][
prefixColumn] + '-for-ac' # make a dictionary of filenames
return [listFilename, listNamespace, listUri]
def createMasterMetadataTable(termLists, listMetadata):
fileNameDict = listMetadata[0]
namespaceDict = listMetadata[1]
uriDict = listMetadata[2]
masterTable = []
for termList in termLists:
# retrieve term metadata for a particular list from Github
dataUrl = githubBaseUri + fileNameDict[termList] + '/' + fileNameDict[
termList] + '.csv'
table = http_library.retrieveData(dataUrl, 'csv', ',')
header = table[0]
# determine which columns contain specified metadata fields
for column in range(len(header)):
if header[column] == 'term_localName':
localNameColumn = column
if header[column] == 'label':
labelColumn = column
if header[column] == 'tdwgutility_layer':
layerColumn = column
if header[column] == 'tdwgutility_required':
requiredColumn = column
if header[column] == 'tdwgutility_repeatable':
repeatableColumn = column
if header[column] == 'rdfs_comment':
definitionColumn = column
if header[column] == 'skos_scopeNote':
scopeNoteColumn = column
if header[column] == 'dcterms_description':
notesColumn = column
if header[column] == 'tdwgutility_organizedInClass':
organizedColumn = column
for row in range(1, len(table)): #skip the header row
masterTable.append([
namespaceDict[termList], uriDict[termList],
table[row][localNameColumn], table[row][labelColumn],
table[row][layerColumn], table[row][requiredColumn],
table[row][repeatableColumn], table[row][definitionColumn],
table[row][scopeNoteColumn], table[row][notesColumn],
table[row][organizedColumn]
])
return masterTable
def retrieveVocabularyInfo(githubBaseUri):
dataUrl = githubBaseUri + 'vocabularies/vocabularies-members.csv'
table = http_library.retrieveData(dataUrl, 'csv', ',')
header = table[0]
# determine which column contains the vocab and term list ids
for column in range(len(header)):
if header[column] == 'termList':
termListColumn = column
if header[column] == 'vocabulary':
vocabularyColumn = column
# store the identifiers of the term lists
termLists = []
for row in range(1, len(table)): #skip the header row
if table[row][vocabularyColumn] == 'http://rs.tdwg.org/ac/':
termLists.append(table[row][termListColumn])
return termLists