def generate_table(self, document, meta, sheet, row_set):
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
tabular = self.create_tabular(sheet, row_set.name)
columns = [tabular.add_column(h) for h in headers]
if not len(columns):
return
def generate_rows():
for i, row in enumerate(row_set):
record = {}
try:
for cell, column in zip(row, columns):
record[column.name] = string_value(cell.value)
if len(record):
for column in columns:
record[column.name] = record.get(column.name, None)
yield record
except Exception as exception:
log.warning("Could not decode row %s in %s: %s",
i, meta, exception)
document.insert_records(sheet, generate_rows())
return tabular
def get_schema(self, filename):
"""
Guess schema using messytables
"""
table_set = self.read_file(filename)
# Have I been able to read the filename
if table_set is None:
return []
# Get the first table as rowset
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
# Get a sample as well..
sample = next(row_set.sample)
clean = lambda v: str(v) if not isinstance(v, str) else v
schema = []
for i, h in enumerate(headers):
schema.append([h,
str(types[i]),
clean(sample[i].value)])
return schema
def get_column_types(data: io.BytesIO) \
-> Tuple[List[str], List[types.CellType]]:
"""derive the column types
Using messytables' CSV API, attempt to derive the column types based on a
best-guess of a sample of the rows.
This is still a WIP due to the parlous state of the DV360/CM CSV data formats
in general
Arguments:
data (io.BytesIO): sample of the CSV file
Returns:
(List[str], List[str]): tuple of list of header names and list of
column types
"""
table_set = messytables.CSVTableSet(data)
row_set = table_set.tables[0]
offset, csv_headers = messytables.headers_guess(row_set.sample)
row_set.register_processor(messytables.headers_processor(csv_headers))
row_set.register_processor(messytables.offset_processor(offset + 1))
csv_types = messytables.type_guess(row_set.sample, strict=True)
return (csv_headers, csv_types)
def main(basic_config_file, batch_config_file):
with open(basic_config_file, "r") as f:
base_settings = yaml.load(f)
if batch_config_file:
# RUN MANY
# parse csv into a list of settings-dicts
import messytables
with open(batch_config_file, "rb") as f:
row_set = messytables.CSVRowSet("", f)
offset, headers = messytables.headers_guess(row_set.sample)
row_set.register_processor(messytables.headers_processor(headers))
row_set.register_processor(messytables.offset_processor(offset +
1))
types = messytables.type_guess(row_set.sample, strict=True)
row_set.register_processor(messytables.types_processor(types))
settings_list = row_set.dicts()
name = batch_config_file.replace(".csv", "")
run_many(settings_list, name, base_settings=base_settings)
else:
# RUN ONE
# parse yaml into a settings-dict
settings_file = os.path.join(base_settings["out_dir"], "settings.yml")
with open(settings_file, "w") as f:
yaml.dump(base_settings, f)
training_log, exit_status = run_one(**base_settings)
training_log_file = os.path.join(base_settings["out_dir"],
"training_log.csv")
training_log.to_csv(training_log_file)
stats = compute_final_stats(training_log)
stats["exit_status"] = exit_status
training_stats_file = os.path.join(base_settings["out_dir"],
"training_stats.yml")
with open(training_stats_file, "w") as f:
yaml.dump(stats, f)
def get_schema(self, filename):
"""
Guess schema using messytables
"""
table_set = self.read_file(filename)
# Have I been able to read the filename
if table_set is None:
return []
# Get the first table as rowset
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
# Get a sample as well..
sample = next(row_set.sample)
clean = lambda v: str(v) if not isinstance(v, str) else v
schema = []
for i, h in enumerate(headers):
schema.append([h, str(types[i]), clean(sample[i].value)])
return schema
def generate_table(self, meta, sheet, row_set):
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
schema = TabularSchema({
'sheet_name': row_set.name,
'content_hash': meta.content_hash,
'sheet': sheet
})
columns = [schema.add_column(h) for h in headers]
log.info("Creating internal table: %s columns, table: %r", len(columns),
schema.table_name)
tabular = Tabular(schema)
tabular.drop()
tabular.create()
def generate_rows():
for i, row in enumerate(row_set):
record = {}
for cell, column in zip(row, columns):
record[column.name] = string_value(cell.value)
if len(record):
for column in columns:
record[column.name] = record.get(column.name, None)
yield record
log.info("Loaded %s rows.", i)
tabular.load_iter(generate_rows())
return schema
def convert(self):
table_set = CSVTableSet.from_fileobj(self.stream)
row_set = table_set.tables.pop()
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', str(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, str(dup_columns[field])])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id']
for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
data_row = {}
result = []
for row in row_set:
for index, cell in enumerate(row):
data_row[cell.column] = cell.value
result.append(data_row)
return fields, result
def get_column_types(data: io.BytesIO) -> Tuple[List[str], List[str]]:
"""derive the column types
Using messytables' CSV API, attempt to derive the column types based on a best-guess
of a sample of the rows.
This is still a WIP due to the parlous state of the DV360/CM CSV data formats in
general
Arguments:
data {io.BytesIO} -- sample of the CSV file
Returns:
(List[str], List[str]) -- tuple of list of header names and list of column types
"""
table_set = CSVTableSet(data)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
logging.info(headers)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
logging.info(types)
return (headers, types)
def convert(self):
table_set = CSVTableSet.from_fileobj(self.stream)
row_set = table_set.tables.pop()
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', str(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, str(dup_columns[field])])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id'] for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
data_row = {}
result = []
for row in row_set:
for index, cell in enumerate(row):
data_row[cell.column] = cell.value
result.append(data_row)
return fields, result
def main(argv=None):
args = parse_args(argv)
if args.file is None:
# slurp the whole input since there seems to be a bug in messytables
# which should be able to handle streams but doesn't
args.file = cStringIO.StringIO(sys.stdin.read())
relation_key = args_to_relation_key(args)
table_set = any_tableset(args.file)
if len(table_set.tables) != 1:
raise ValueError("Can only handle files with a single table, not %s" % len(table_set.tables))
row_set = table_set.tables[0]
# guess header names and the offset of the header:
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(strip_processor())
row_set.register_processor(headers_processor(headers))
# Temporarily, mark the offset of the header
row_set.register_processor(offset_processor(offset + 1))
# guess types and register them
types = type_guess(replace_empty_string(row_set.sample), strict=True, types=[StringType, DecimalType, IntegerType])
row_set.register_processor(types_processor(types))
# Messytables seems to not handle the case where there are no headers.
# Work around this as follows:
# 1) offset must be 0
# 2) if the types of the data match the headers, assume there are
# actually no headers
if offset == 0:
try:
[t.cast(v) for (t, v) in zip(types, headers)]
except:
pass
else:
# We don't need the headers_processor or the offset_processor
row_set._processors = []
row_set.register_processor(strip_processor())
row_set.register_processor(types_processor(types))
headers = None
# Construct the Myria schema
schema = messy_to_schema(types, headers)
logging.info("Myria schema: {}".format(json.dumps(schema)))
# Prepare data for writing to Myria
data, kwargs = write_data(row_set, schema)
if not args.dry:
# Connect to Myria and send the data
connection = myria.MyriaConnection(hostname=args.hostname, port=args.port, ssl=args.ssl)
ret = connection.upload_file(relation_key, schema, data, args.overwrite, **kwargs)
sys.stdout.write(pretty_json(ret))
else:
sys.stdout.write(data)
def test_guess_headers(self):
fh = horror_fobj("weird_head_padding.csv")
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
data = list(row_set)
assert "Frauenheilkunde" in data[9][0].value, data[9][0].value
fh = horror_fobj("weird_head_padding.csv")
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
row_set.register_processor(headers_processor(["foo", "bar"]))
data = list(row_set)
assert "foo" in data[12][0].column, data[12][0]
assert "Chirurgie" in data[12][0].value, data[12][0].value
def test_guess_headers(self):
fh = horror_fobj('weird_head_padding.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
data = list(row_set)
assert 'Frauenheilkunde' in data[9][0].value, data[9][0].value
fh = horror_fobj('weird_head_padding.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
row_set.register_processor(headers_processor(['foo', 'bar']))
data = list(row_set)
assert 'foo' in data[12][0].column, data[12][0]
assert 'Chirurgie' in data[12][0].value, data[12][0].value
def lines(self):
fh = urlopen(self.source.url)
row_set = CSVRowSet('data', fh, window=3)
headers = list(row_set.sample)[0]
headers = [c.value for c in headers]
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(1))
for row in row_set:
yield dict([(c.column, c.value) for c in row])
def parse(stream, excel_type='xls', sheet=1, guess_types=True, **kwargs):
'''Parse Excel (xls or xlsx) to structured objects.
:param excel_type: xls | xlsx
:param sheet: index of sheet in spreadsheet to convert (starting from index = 1)
'''
sheet_number = int(sheet) - 1
xlsclass = XLSTableSet
if excel_type == 'xlsx':
xlsclass = XLSXTableSet
table_set = xlsclass.from_fileobj(stream)
try:
row_set = table_set.tables[sheet_number]
except IndexError:
raise Exception('This file does not have sheet number %d' %
(sheet_number + 1))
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
if guess_types:
guess_types = [
StringType, IntegerType, FloatType, DecimalType, DateUtilType
]
row_types = type_guess(row_set.sample, guess_types)
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', str(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, str(dup_columns[field])])
if guess_types:
if isinstance(row_types[index], DateUtilType):
field_dict['type'] = 'DateTime'
else:
field_dict['type'] = str(row_types[index])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id'] for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
def row_iterator():
for row in row_set:
data_row = {}
for index, cell in enumerate(row):
data_row[cell.column] = cell.value
yield data_row
return row_iterator(), {'fields': fields}
def parse(stream, excel_type='xls', sheet=1, guess_types=True, **kwargs):
'''Parse Excel (xls or xlsx) to structured objects.
:param excel_type: xls | xlsx
:param sheet: index of sheet in spreadsheet to convert (starting from index = 1)
'''
sheet_number = int(sheet) - 1
xlsclass = XLSTableSet
if excel_type == 'xlsx':
xlsclass = XLSXTableSet
table_set = xlsclass.from_fileobj(stream)
try:
row_set = table_set.tables[sheet_number]
except IndexError:
raise Exception('This file does not have sheet number %d' %
(sheet_number + 1))
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
if guess_types:
guess_types = [StringType, IntegerType, FloatType, DecimalType,
DateUtilType]
row_types = type_guess(row_set.sample, guess_types)
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', str(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, str(dup_columns[field])])
if guess_types:
if isinstance(row_types[index], DateUtilType):
field_dict['type'] = 'DateTime'
else:
field_dict['type'] = str(row_types[index])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id'] for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
def row_iterator():
for row in row_set:
data_row = {}
for index, cell in enumerate(row):
data_row[cell.column] = cell.value
yield data_row
return row_iterator(), {'fields': fields}
def test_read_encoded_characters_csv(self):
fh = horror_fobj('characters.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
data = list(row_set)
assert_equal(382, len(data))
assert_equal(data[0][2].value, u'雲嘉南濱海國家風景區管理處')
assert_equal(data[-1][2].value, u'沈光文紀念廳')
def test_read_encoded_characters_csv(self):
fh = horror_fobj('characters.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
data = list(row_set)
assert_equal(382, len(data))
assert_equal(data[0][2].value, u'雲嘉南濱海國家風景區管理處')
assert_equal(data[-1][2].value, u'沈光文紀念廳')
def connect(self,
host=None,
port=None,
database=None,
username=None,
password=None,
file=None):
# TODO: mysql, pymssql, csv, sqlite3, pymongo, cx_Oracle
self.database = database
conn_string = ''
if self.engine == 'psycopg2':
if database:
conn_string += "dbname='%s' " % database
if username:
conn_string += "user='******' " % username
if host:
conn_string += "host='%s' " % host
if port:
conn_string += "port='%s' " % port
if password:
conn_string += "password='******' " % password
self.conn = psycopg2.connect(conn_string)
elif self.engine == 'pymssql':
self.conn = pymssql.connect(host,
username,
password,
database,
port=port,
as_dict=True,
charset='LATIN1')
elif self.engine == 'csv':
# https://messytables.readthedocs.io/en/latest/
fh = StringIO.StringIO(self.data)
#dialect = csv.Sniffer().sniff(f.read(1024))
#f.seek(0)
#self.conn = csv.DictReader(f, dialect=dialect)
#fh = open('messy.csv', 'rb')
# Load a file object:
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
self.conn = row_set
return self.conn
def proc(f, database_name, table_name):
table_set = messytables.any_tableset(f)
row_set = table_set.tables[0]
# guess header names and the offset of the header:
offset, headers = messytables.headers_guess(row_set.sample)
row_set.register_processor(messytables.headers_processor(headers))
row_set.register_processor(messytables.offset_processor(offset + 1))
types = messytables.type_guess(row_set.sample, types=[
messytables.types.StringType,
messytables.types.DateType,
], strict=True)
hive_data_file = tempfile.NamedTemporaryFile(mode='w')
fields_ddl = ','.join([
' {0} {1}\n'.format(
canonicalize_column_name(colName),
hive_column_type(colType)
)
for colName, colType in zip(headers, types)
])
hive_sql = '''
DROP TABLE IF EXISTS {0};
CREATE TABLE {0} (
{1}
)
STORED AS TEXTFILE
TBLPROPERTIES ("comment"="add_messytable on {3}");
LOAD DATA LOCAL INPATH '{2}' OVERWRITE INTO TABLE {0};
'''.format(table_name, fields_ddl, hive_data_file.name,
datetime.datetime.now().isoformat())
hive_cmd_file = tempfile.NamedTemporaryFile(mode='w')
print(hive_sql, file=hive_cmd_file)
hive_cmd_file.flush()
row_set.register_processor(messytables.types_processor(types))
for row in row_set:
print('\001'.join(map(str, [ c.value for c in row])),
file=hive_data_file)
hive_data_file.flush()
subprocess.call([
'hive',
'--database', database_name,
'-f', hive_cmd_file.name,
])
def validate_file(file_tmp, file_name, tmp_filepath):
log.info("upload: checking file * %s * ", file_name)
MAX_HEADER_LENGTH = 64
# not allowed characters ( - ' " ’ ‘) regex
inappropriate_chars = re.compile(r"[\-|\'|\"|\u2018|\u2019]");
datastore_ext = config.get('ckan.mimetype_guess', "csv xls xlsx tsv")
tmp_file_name, tmp_file_ext = os.path.splitext(file_name)
#check if datastore file (csv xls xlsx tsv)
if tmp_file_ext[1:].lower() in datastore_ext:
table_set = any_tableset(file_tmp)
#check if only one data sheet in the file
if len(table_set.tables)>1:
rollback_tmp(file_tmp, tmp_filepath)
log.error("upload: the file * %s * was not uploaded - There is more then one data sheet in the file", file_name)
raise logic.ValidationError(
{'upload': ['There is more then one data sheet in the file']}
)
else:
row_set = table_set.tables[0]
# guess header names and the offset of the header:
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
for header in headers:
# too long header
if len(header) > MAX_HEADER_LENGTH:
rollback_tmp(file_tmp, tmp_filepath)
log.error("upload: the file * %s * was not uploaded - too long header - * %s *",
file_name, header)
raise logic.ValidationError(
{'upload': ['too long header (64 max)']}
)
# not allowed characters in header ( - ' " ’ ‘)
if inappropriate_chars.search(header):
rollback_tmp(file_tmp, tmp_filepath)
log.error("upload: the file * %s * was not uploaded - there are inappropriate characters in headers * %s *",
file_name, header)
raise logic.ValidationError(
{'upload': ['there are inappropriate characters in headers (apostrophe/apostrophes/dash)']}
)
# Check for duplicate fields
unique_fields = set(headers)
if not len(unique_fields) == len(headers):
rollback_tmp(file_tmp, tmp_filepath)
log.error("upload: the file * %s * was not uploaded - Duplicate column names are not supported", file_name)
raise logic.ValidationError({'upload': ['Duplicate column names are not supported']})
log.info("passed validation succesfully - the file * %s * was uploaded to CKAN (filestore)", file_name)
else:
pass
def test_read_head_padding_csv(self):
fh = horror_fobj("weird_head_padding.csv")
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
assert 11 == len(headers), headers
assert_equal(u"1985", headers[1].strip())
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
data = list(row_set.sample)
for row in row_set:
assert_equal(11, len(row))
value = data[1][0].value.strip()
assert value == u"Gefäßchirurgie", value
def csvParse(csv_file_path):
fh = open(csv_file_path, 'rb')
# Load a file object:
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
# guess header names and the offset of the header:
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
# add one to begin with content, not the header:
row_set.register_processor(offset_processor(offset + 1))
# guess column types:
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
return row_set, headers, offset, types
def test_read_head_padding_csv(self):
fh = horror_fobj('weird_head_padding.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
assert 11 == len(headers), headers
assert_equal('1985', headers[1].strip())
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
data = list(row_set.sample)
for row in row_set:
assert_equal(11, len(row))
value = data[1][0].value.strip()
assert value == u'Gefäßchirurgie', value
def get_diff(self, filename1, filename2):
# print("get_diff", filename1, filename2)
ext = filename1.split(".")[-1].lower()
if ext not in ['csv', 'tsv', 'xls']:
return None
csvs = {}
for f in [filename1, filename2]:
# print("Loading file", f)
table_set = self.read_file(f)
if table_set is None:
raise Exception("Invalid table set")
row_set = table_set.tables[0]
#print("Guessing headers")
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset+1))
# Output of rowset is a structure
csvs[f] = [headers]
for row in row_set:
csvs[f].append([r.value for r in row])
#print(csvs[f][:3])
# Loaded csv1 and csv2
table1 = daff.PythonTableView(csvs[filename1])
table2 = daff.PythonTableView(csvs[filename2])
alignment = daff.Coopy.compareTables(table1,table2).align()
# print("Achieved alignment")
data_diff = []
table_diff = daff.PythonTableView(data_diff)
flags = daff.CompareFlags()
highlighter = daff.TableDiff(alignment,flags)
highlighter.hilite(table_diff)
# Parse the differences
#print("Parsing diff")
diff = self.parse_diff(table_diff)
# print("Computed diff", diff)
return diff
def get_diff(self, filename1, filename2):
#print("get_diff", filename1, filename2)
ext = filename1.split(".")[-1].lower()
if ext not in ['csv', 'tsv', 'xls']:
return None
csvs = {}
for f in [filename1, filename2]:
# print("Loading file", f)
table_set = self.read_file(f)
if table_set is None:
raise Exception("Invalid table set")
row_set = table_set.tables[0]
#print("Guessing headers")
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
# Output of rowset is a structure
csvs[f] = [headers]
for row in row_set:
csvs[f].append([r.value for r in row])
#print(csvs[f][:3])
# Loaded csv1 and csv2
table1 = daff.PythonTableView(csvs[filename1])
table2 = daff.PythonTableView(csvs[filename2])
alignment = daff.Coopy.compareTables(table1, table2).align()
# print("Achieved alignment")
data_diff = []
table_diff = daff.PythonTableView(data_diff)
flags = daff.CompareFlags()
highlighter = daff.TableDiff(alignment, flags)
highlighter.hilite(table_diff)
# Parse the differences
#print("Parsing diff")
diff = self.parse_diff(table_diff)
#print("Computed diff", diff)
return diff
def load_data(config):
if not 'url' in config:
yield {config.get('field'): config.get('value')}
return
fh = urlopen(config.get('url'))
table_set = CSVTableSet.from_fileobj(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
for row in row_set:
row = [(c.column, c.value) for c in row]
yield dict(row)
fh.close()
def csvimport_table(name):
from messytables import CSVTableSet, type_guess
from messytables import types_processor, headers_guess
from messytables import headers_processor, offset_processor
from spendb.etl.extract import parse_table
row_set = CSVTableSet(data_fixture(name)).tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
rows = []
for num_rows, (fields, row, samples) in enumerate(parse_table(row_set)):
rows.append(row)
return fields, rows
def csvimport_table(name):
from messytables import CSVTableSet, type_guess
from messytables import types_processor, headers_guess
from messytables import headers_processor, offset_processor
from spendb.etl.extract import parse_table
row_set = CSVTableSet(data_fixture(name)).tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
rows = []
for num_rows, (fields, row, samples) in enumerate(parse_table(row_set)):
rows.append(row)
return fields, rows
def parse_data(input):
fh = open(input, 'rb')
try:
table_set = messytables.any_tableset(fh)
except messytables.ReadError as e:
print(e)
get_row_set = lambda table_set: table_set.tables.pop()
row_set = get_row_set(table_set)
offset, headers = messytables.headers_guess(row_set.sample)
# Some headers might have been converted from strings to floats and such.
headers = [str(header) for header in headers]
row_set.register_processor(messytables.headers_processor(headers))
row_set.register_processor(messytables.offset_processor(offset + 1))
types = messytables.type_guess(row_set.sample, types=TYPES, strict=True)
row_set.register_processor(messytables.types_processor(types))
headers = [header.strip() for header in headers if header.strip()]
headers_set = set(headers)
def row_iterator():
for row in row_set:
data_row = {}
for index, cell in enumerate(row):
column_name = cell.column.strip()
if column_name not in headers_set:
continue
data_row[column_name] = cell.value
yield data_row
result = row_iterator()
headers_dicts = [
dict(id=field[0], type=TYPE_MAPPING[str(field[1])])
for field in zip(headers, types)
]
print('Determined headers and types: {headers}'.format(
headers=headers_dicts))
return headers_dicts, result
def parse_table(source):
# This is a work-around because messytables hangs on boto file
# handles, so we're doing it via plain old HTTP.
# We're also passing in an extended window size to give more
# reliable type detection.
# Because Python's CSV dialect sniffer isn't the best, this also
# constrains the field quoting character to a double quote.
table_set = mt.any_tableset(source.fh(),
extension=source.meta.get('extension'),
mimetype=source.meta.get('mime_type'),
quotechar='"',
window=20000)
tables = list(table_set.tables)
if not len(tables):
log.error("No tables were found in the source file.")
return
row_set = tables[0]
headers = [c.value for c in next(row_set.sample)]
row_set.register_processor(mt.headers_processor(headers))
row_set.register_processor(mt.offset_processor(1))
types = mt.type_guess(row_set.sample, strict=True)
row_set.register_processor(mt.types_processor(types, strict=True))
fields, i = {}, 0
row_iter = iter(row_set)
while True:
i += 1
try:
row = row_iter.next()
if not len(fields):
fields = generate_field_spec(row)
data = convert_row(row, fields, i)
check_empty = set(data.values())
if None in check_empty and len(check_empty) == 1:
continue
yield None, fields, data
except StopIteration:
return
except Exception, e:
# log.exception(e)
yield e, fields, None
def load_data(config):
if not 'url' in config:
yield {
config.get('field'): config.get('value')
}
return
fh = urlopen(config.get('url'))
table_set = CSVTableSet.from_fileobj(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
for row in row_set:
row = [(c.column, c.value) for c in row]
yield dict(row)
fh.close()
def parse_table(source):
# This is a work-around because messytables hangs on boto file
# handles, so we're doing it via plain old HTTP.
# We're also passing in an extended window size to give more
# reliable type detection.
# Because Python's CSV dialect sniffer isn't the best, this also
# constrains the field quoting character to a double quote.
table_set = mt.any_tableset(source.fh(),
extension=source.meta.get('extension'),
mimetype=source.meta.get('mime_type'),
quotechar='"', window=20000)
tables = list(table_set.tables)
if not len(tables):
log.error("No tables were found in the source file.")
return
row_set = tables[0]
headers = [c.value for c in next(row_set.sample)]
row_set.register_processor(mt.headers_processor(headers))
row_set.register_processor(mt.offset_processor(1))
types = mt.type_guess(row_set.sample, strict=True)
row_set.register_processor(mt.types_processor(types, strict=True))
fields, i = {}, 0
row_iter = iter(row_set)
while True:
i += 1
try:
row = row_iter.next()
if not len(fields):
fields = generate_field_spec(row)
data = convert_row(row, fields, i)
check_empty = set(data.values())
if None in check_empty and len(check_empty) == 1:
continue
yield None, fields, data
except StopIteration:
return
except Exception, e:
# log.exception(e)
yield e, fields, None
def _get_table_columns(self, csv_file_path: str) -> zip:
"""
Read the csv file and tries to guess the the type of each column using messytables library.
The type can be 'Integer', 'Decimal', 'String' or 'Bool'
:param csv_file_path: path to the csv file with content in it
:return: a Zip object where each tuple has two elements: the first is the column name and the second is the type
"""
with gzip.open(csv_file_path, 'rb') as f:
table_set = CSVTableSet(f)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = list(map(jts.celltype_as_string, type_guess(row_set.sample, strict=True)))
return zip(headers, types)
def resource_row_set(package, resource):
""" Generate an iterator over all the rows in this resource's
source data. """
# This is a work-around because messytables hangs on boto file
# handles, so we're doing it via plain old HTTP.
table_set = any_tableset(resource.fh(),
extension=resource.meta.get('extension'),
mimetype=resource.meta.get('mime_type'))
tables = list(table_set.tables)
if not len(tables):
log.error("No tables were found in the source file.")
return
row_set = tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
return row_set
def convert(self):
xlsclass = XLSTableSet
if 'xlsx' == self.excel_type:
xlsclass = XLSXTableSet
table_set = xlsclass.from_fileobj(self.stream)
try:
row_set = table_set.tables[self.sheet_number]
except IndexError:
raise Exception('This file does not have worksheet number %d' %
(self.sheet_number + 1))
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', str(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, str(dup_columns[field])])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id']
for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
info = {}
result = []
for row in row_set:
for index, cell in enumerate(row):
if isinstance(cell.value, datetime):
info[cell.column] = cell.value.isoformat()
else:
info[cell.column] = cell.value
result.append(info)
return fields, result
def _guess_csv_datatype(fh):
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
logger.info("(offset, headers) = ({}, {})".format(offset, headers))
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
counter = 0
for row in row_set:
logger.info(row)
counter += 1
if counter >= 32:
break
d = {h: t for h, t in zip(headers, types)}
logger.info(d)
return d
def generate_table(self, document, sheet, row_set):
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
tabular = self.create_tabular(sheet, row_set.name)
columns = [tabular.add_column(h) for h in headers]
if not len(columns):
return
def generate_rows():
for row in row_set:
record = {}
for cell, column in zip(row, columns):
record[column.name] = string_value(cell.value)
if len(record):
for column in columns:
record[column.name] = record.get(column.name, None)
yield record
document.insert_records(sheet, generate_rows())
return tabular
def generate_schema(samples: List[Dict], table_spec: Dict) -> Dict:
"""
Guess columns types from the given samples and build json schema
:param samples: List of dictionaries containing samples data from csv file(s)
:param table_spec: table/stream specs given in the tap definition
:return: dictionary where the keys are the headers and values are the guessed types - compatible with json schema
"""
schema = {}
table_set = CSVTableSet(_csv2bytesio(samples))
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
for header, header_type in zip(headers, types):
date_overrides = set(table_spec.get('date_overrides', []))
if header in date_overrides:
schema[header] = {'type': ['null', 'string'], 'format': 'date-time'}
else:
if isinstance(header_type, IntegerType):
schema[header] = {
'type': ['null', 'integer']
}
elif isinstance(header_type, DecimalType):
schema[header] = {
'type': ['null', 'number']
}
else:
schema[header] = {
'type': ['null', 'string']
}
return schema
def lines(self):
fh = urlopen(self.source.url)
row_set = CSVRowSet('data', fh, window=3)
headers = list(row_set.sample)[0]
headers = [c.value for c in headers]
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(1))
for row in row_set:
row_dict = dict([(c.column, c.value) for c in row])
# Rename id to row_id
row_dict['row_id'] = row_dict.pop('id')
# Set time as empty string to use the default value
row_dict['time'] = ''
# Transform COFOG field into six fields with code and label as
# the same value
cofog = row_dict.pop('cofog', None)
if cofog:
row_dict['cofog1code'] = self.cofog_code(cofog, level=1)
row_dict['cofog1label'] = self.cofog_code(cofog, level=1)
row_dict['cofog2code'] = self.cofog_code(cofog, level=2)
row_dict['cofog2label'] = self.cofog_code(cofog, level=2)
row_dict['cofog3code'] = self.cofog_code(cofog, level=3)
row_dict['cofog3label'] = self.cofog_code(cofog, level=3)
# Transform gfsm expense field into three fields
gfsmexpense = row_dict.pop('gfsmexpense', None)
if gfsmexpense:
row_dict['gfsmexpense1'] = self.gfsm_code(gfsmexpense, level=1)
row_dict['gfsmexpense2'] = self.gfsm_code(gfsmexpense, level=2)
row_dict['gfsmexpense3'] = self.gfsm_code(gfsmexpense, level=3)
# Transform gfsm revenue field into three fields
gfsmrevenue = row_dict.pop('gfsmrevenue', None)
if gfsmrevenue:
row_dict['gfsmrevenue1'] = self.gfsm_code(gfsmrevenue, level=1)
row_dict['gfsmrevenue2'] = self.gfsm_code(gfsmrevenue, level=2)
row_dict['gfsmrevenue3'] = self.gfsm_code(gfsmrevenue, level=3)
yield row_dict
def lines(self):
fh = urlopen(self.source.url)
row_set = CSVRowSet('data', fh, window=3)
headers = list(row_set.sample)[0]
headers = [c.value for c in headers]
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(1))
for row in row_set:
row_dict = dict([(c.column, c.value) for c in row])
# Rename id to row_id
row_dict['row_id'] = row_dict.pop('id')
# Set time as empty string to use the default value
row_dict['time'] = ''
# Transform COFOG field into six fields with code and label as
# the same value
cofog = row_dict.pop('cofog', None)
if cofog:
row_dict['cofog1code'] = self.cofog_code(cofog, level=1)
row_dict['cofog1label'] = self.cofog_code(cofog, level=1)
row_dict['cofog2code'] = self.cofog_code(cofog, level=2)
row_dict['cofog2label'] = self.cofog_code(cofog, level=2)
row_dict['cofog3code'] = self.cofog_code(cofog, level=3)
row_dict['cofog3label'] = self.cofog_code(cofog, level=3)
# Transform gfsm expense field into three fields
gfsmexpense = row_dict.pop('gfsmexpense', None)
if gfsmexpense:
row_dict['gfsmexpense1'] = self.gfsm_code(gfsmexpense, level=1)
row_dict['gfsmexpense2'] = self.gfsm_code(gfsmexpense, level=2)
row_dict['gfsmexpense3'] = self.gfsm_code(gfsmexpense, level=3)
# Transform gfsm revenue field into three fields
gfsmrevenue = row_dict.pop('gfsmrevenue', None)
if gfsmrevenue:
row_dict['gfsmrevenue1'] = self.gfsm_code(gfsmrevenue, level=1)
row_dict['gfsmrevenue2'] = self.gfsm_code(gfsmrevenue, level=2)
row_dict['gfsmrevenue3'] = self.gfsm_code(gfsmrevenue, level=3)
yield row_dict
def convert(self):
xlsclass = XLSTableSet
if 'xlsx' == self.excel_type:
xlsclass = XLSXTableSet
table_set = xlsclass.from_fileobj(self.stream)
try:
row_set = table_set.tables[self.sheet_number]
except IndexError:
raise Exception('This file does not have worksheet number %d' % (self.sheet_number + 1))
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', str(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, str(dup_columns[field])])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id'] for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
info = {}
result = []
for row in row_set:
for index, cell in enumerate(row):
if isinstance(cell.value, datetime):
info[cell.column] = cell.value.isoformat()
else:
info[cell.column] = cell.value
result.append(info)
return fields, result
def _get_table_columns(self, csv_file_path: str) -> zip:
"""
Read the csv file and tries to guess the the type of each column using messytables library.
The type can be 'Integer', 'Decimal', 'String' or 'Bool'
:param csv_file_path: path to the csv file with content in it
:return: a Zip object where each tuple has two elements: the first is the column name and the second is the type
"""
with gzip.open(csv_file_path, 'rb') as csvfile:
table_set = CSVTableSet(csvfile, window=1)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = [
'integer' if header == S3Helper.SDC_SOURCE_LINENO_COLUMN else 'string'
for header in headers
]
return zip(headers, types)
def headersDataTypes(CSV):
'''Get column headers and data types using messytables'''
table = open(path[0]+CSV, 'rb')
# Creates a set of tables as file object, although it'll just be one
tableset = messytables.CSVTableSet(table)
rowset = tableset.tables[0] # get first and only table as iterator
# guesses header names and offset of header, returns headers as list
offset, headers = messytables.headers_guess(rowset.sample)
print "Here is the offset", str(offset), "\nHere are the headers:\n"\
, str(headers) # test
# establish headers in table
rowset.register_processor(messytables.headers_processor(headers))
# begin iterator at content, rather than header
rowset.register_processor(messytables.offset_processor(offset + 1))
# guess column types, return as list
types = messytables.type_guess(rowset.sample, strict=True)
print "Here are the data types", str(types)
dtypedict = {} # empty dictionary to append columns and datatype needed
# for pandas csv to dataframe conversion
colcount = 0 # location to append datatypes to match columns in dict
for column in types:
dtypedict[headers[colcount]]=column
colcount+=1
return headers, dtypedict
def parse_table(row_set, save_func):
num_rows = 0
fields = {}
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample, strict=True)
row_set.register_processor(types_processor(types))
for i, row in enumerate(row_set):
if not len(fields):
fields = generate_field_spec(row)
data = {}
for cell, field in zip(row, fields):
value = cell.value
if isinstance(value, datetime):
value = value.date()
if isinstance(value, Decimal):
# Baby jesus forgive me.
value = float(value)
if isinstance(value, basestring) and not len(value.strip()):
value = None
data[field['name']] = value
random_sample(value, field, i)
check_empty = set(data.values())
if None in check_empty and len(check_empty) == 1:
continue
save_func(data)
num_rows = i
fields = {f.get('name'): f for f in fields}
return num_rows, fields
def determine_messytables_types(file_handle, types=messytables.types.TYPES):
"""
:param file_handle: file handle opened in binary mode
:return: (headers, types, row_set)
"""
# Load a file object:
table_set = messytables.CSVTableSet(file_handle)
# If you aren't sure what kind of file it is
# table_set = messytables.any_tableset(file_handle)
# A table set is a collection of tables:
row_set = table_set.tables[0]
# A row set is an iterator over the table, but it can only
# be run once. To peek, a sample is provided:
print(next(row_set.sample))
# guess header names and the offset of the header:
offset, headers = messytables.headers_guess(row_set.sample)
row_set.register_processor(messytables.headers_processor(headers))
# add one to begin with content, not the header:
row_set.register_processor(messytables.offset_processor(offset + 1))
# guess column types:
types = messytables.type_guess(row_set.sample, types, strict=True)
# and tell the row set to apply these types to
# each row when traversing the iterator:
row_set.register_processor(messytables.types_processor(types))
# now run some operation on the data:
return headers, types, row_set
raise util.JobError(e)
row_set = table_set.tables.pop()
offset, headers = messytables.headers_guess(row_set.sample)
existing = datastore_resource_exists(resource_id, api_key, ckan_url)
existing_info = None
if existing:
existing_info = dict((f['id'], f['info'])
for f in existing.get('fields', [])
if 'info' in f)
# Some headers might have been converted from strings to floats and such.
headers = [unicode(header) for header in headers]
row_set.register_processor(messytables.headers_processor(headers))
row_set.register_processor(messytables.offset_processor(offset + 1))
types = messytables.type_guess(row_set.sample, types=TYPES, strict=True)
# override with types user requested
if existing_info:
types = [{
'text': messytables.StringType(),
'numeric': messytables.DecimalType(),
'timestamp': messytables.DateUtilType(),
}.get(existing_info.get(h, {}).get('type_override'), t)
for t, h in zip(types, headers)]
row_set.register_processor(messytables.types_processor(types))
headers = [header.strip() for header in headers if header.strip()]
def parse(stream, guess_types=True, **kwargs):
'''Parse CSV file and return row iterator plus metadata (fields etc).
Additional CSV arguments as per
http://docs.python.org/2/library/csv.html#csv-fmt-params
:param delimiter:
:param quotechar:
:param window: the size of the sample used for analysis
There is also support for:
:param encoding: file encoding (will be guess with chardet if not provided)
You can process csv as well as tsv files using this function. For tsv just
pass::
delimiter='\t'
'''
metadata = dict(**kwargs)
delimiter = metadata.get('delimiter', None)
quotechar = metadata.get('quotechar', None)
window = metadata.get('window', None)
encoding = metadata.get('encoding', None)
table_set = CSVTableSet.from_fileobj(stream, delimiter=delimiter,
quotechar=quotechar, encoding=encoding, window=window)
row_set = table_set.tables.pop()
offset, headers = headers_guess(row_set.sample)
fields = []
dup_columns = {}
noname_count = 1
if guess_types:
guessable_types = [StringType, IntegerType, FloatType, DecimalType,
DateUtilType]
row_types = type_guess(row_set.sample, guessable_types)
for index, field in enumerate(headers):
field_dict = {}
if "" == field:
field = '_'.join(['column', unicode(noname_count)])
headers[index] = field
noname_count += 1
if headers.count(field) == 1:
field_dict['id'] = field
else:
dup_columns[field] = dup_columns.get(field, 0) + 1
field_dict['id'] = u'_'.join([field, unicode(dup_columns[field])])
if guess_types:
if isinstance(row_types[index], DateUtilType):
field_dict['type'] = 'DateTime'
else:
field_dict['type'] = str(row_types[index])
fields.append(field_dict)
row_set.register_processor(headers_processor([x['id'] for x in fields]))
row_set.register_processor(offset_processor(offset + 1))
if guess_types:
row_set.register_processor(types_processor(row_types))
def row_iterator():
for row in row_set:
data_row = {}
for index, cell in enumerate(row):
data_row[cell.column] = cell.value
yield data_row
return row_iterator(), {'fields': fields}
# Uses Messytables example (https://messytables.readthedocs.io/en/latest/#example)
# To extract from a CSV flatfile the required BIGQUERY JSON metadata
# For importing a table in BIGQUERY
# Example: python csv_to_json_import_bq.py the_csv_file.csv
from messytables import CSVTableSet, type_guess, \
types_processor, headers_guess, headers_processor, \
offset_processor, any_tableset
import sys
fh = open(sys.argv[1], 'rb')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset+1))
types = type_guess(row_set.sample, strict=True)
for i in range(len(headers)):
output = "[\n"
if ("DATE" in str(types[i]).upper()):
types[i] = "TIMESTAMP"
elif ("DECIMAL" in str(types[i]).upper()):
types[i] = "FLOAT"
output = "{\"name\":\"" + str(headers[i]).lower() + "\", \"type\":\"" + str(types[i]).upper() + "\"}"
if i == (len(headers)-1):
output += "\n]"
else:
output += ","
print output
def ku_openlearning(self, filename, source_id):
CATEGORY_MAPPING = {
'Assessment of learning': 2298, #Assessment,
'Finance': 2235,
'Public Service': 'Criminal Justice',
'Health Science': 'Health Sciences',
'Management': 2248,
'Online Instruction': 'Hybrid and Online Course Development',
'Early Childhood': ['Career Counseling and Services', 'Childhood and Adolescence'],
'Law, Legal': 'Law',
'Psychology': 'Psychology',
'Customer Service': 2246,
'Communications': 'Communications',
'Professionalism': 'Personal Development'
}
source = Source.objects.get(pk=source_id)
fh = open(filename, 'rb')
table_set = XLSTableSet(fh)
row_set = table_set.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
for row in row_set:
url = row[0].value
title = row[1].value
description = row[2].value
# language = row[4].value
# material_type = row[5].value
license = row[6].value
categories = row[7].value
keywords = row[8].value
# audience = row[9].value
course, is_created = Course.objects.get_or_create(
linkurl = url,
provider = source.provider,
source = source,
defaults = {
'title': title,
'description': description,
'tags': keywords,
'language': 'English',
'license': license,
'content_medium': 'text',
'creative_commons': 'Yes',
'creative_commons_commercial': 'No',
'creative_commons_derivatives': 'No'
}
)
merlot_cat = CATEGORY_MAPPING[categories]
if type(merlot_cat) != list:
merlot_cat = [merlot_cat,]
for item in merlot_cat:
try:
m = MerlotCategory.objects.get(merlot_id=item)
course.merlot_categories.add(m)
except ValueError:
m = MerlotCategory.objects.get(name=item)
course.merlot_categories.add(m)
def push_to_datastore(task_id, input, dry_run=False):
'''Download and parse a resource push its data into CKAN's DataStore.
An asynchronous job that gets a resource from CKAN, downloads the
resource's data file and, if the data file has changed since last time,
parses the data and posts it into CKAN's DataStore.
:param dry_run: Fetch and parse the data file but don't actually post the
data to the DataStore, instead return the data headers and rows that
would have been posted.
:type dry_run: boolean
'''
handler = util.StoringHandler(task_id, input)
logger = logging.getLogger(task_id)
logger.addHandler(handler)
logger.setLevel(logging.DEBUG)
validate_input(input)
data = input['metadata']
ckan_url = data['ckan_url']
resource_id = data['resource_id']
api_key = input.get('api_key')
try:
resource = get_resource(resource_id, ckan_url, api_key)
except util.JobError as e:
# try again in 5 seconds just incase CKAN is slow at adding resource
time.sleep(5)
resource = get_resource(resource_id, ckan_url, api_key)
# check if the resource url_type is a datastore
if resource.get('url_type') == 'datastore':
logger.info('Dump files are managed with the Datastore API')
return
# check scheme
url = resource.get('url')
scheme = urlsplit(url).scheme
if scheme not in ('http', 'https', 'ftp'):
raise util.JobError(
'Only http, https, and ftp resources may be fetched.'
)
# fetch the resource data
logger.info('Fetching from: {0}'.format(url))
headers = {}
if resource.get('url_type') == 'upload':
# If this is an uploaded file to CKAN, authenticate the request,
# otherwise we won't get file from private resources
headers['Authorization'] = api_key
try:
response = requests.get(
url,
headers=headers,
timeout=DOWNLOAD_TIMEOUT,
verify=SSL_VERIFY,
stream=True, # just gets the headers for now
)
response.raise_for_status()
cl = response.headers.get('content-length')
try:
if cl and int(cl) > MAX_CONTENT_LENGTH:
raise util.JobError(
'Resource too large to download: {cl} > max ({max_cl}).'
.format(cl=cl, max_cl=MAX_CONTENT_LENGTH))
except ValueError:
pass
tmp = tempfile.TemporaryFile()
length = 0
m = hashlib.md5()
for chunk in response.iter_content(CHUNK_SIZE):
length += len(chunk)
if length > MAX_CONTENT_LENGTH:
raise util.JobError(
'Resource too large to process: {cl} > max ({max_cl}).'
.format(cl=length, max_cl=MAX_CONTENT_LENGTH))
tmp.write(chunk)
m.update(chunk)
ct = response.headers.get('content-type', '').split(';', 1)[0]
except requests.HTTPError as e:
raise HTTPError(
"DataPusher received a bad HTTP response when trying to download "
"the data file", status_code=e.response.status_code,
request_url=url, response=e.response.content)
except requests.RequestException as e:
raise HTTPError(
message=str(e), status_code=None,
request_url=url, response=None)
file_hash = m.hexdigest()
tmp.seek(0)
if (resource.get('hash') == file_hash
and not data.get('ignore_hash')):
logger.info("The file hash hasn't changed: {hash}.".format(
hash=file_hash))
return
resource['hash'] = file_hash
try:
table_set = messytables.any_tableset(tmp, mimetype=ct, extension=ct)
except messytables.ReadError as e:
# try again with format
tmp.seek(0)
try:
format = resource.get('format')
table_set = messytables.any_tableset(tmp, mimetype=format, extension=format)
except:
raise util.JobError(e)
get_row_set = web.app.config.get('GET_ROW_SET',
lambda table_set: table_set.tables.pop())
row_set = get_row_set(table_set)
offset, headers = messytables.headers_guess(row_set.sample)
existing = datastore_resource_exists(resource_id, api_key, ckan_url)
existing_info = None
if existing:
existing_info = dict((f['id'], f['info'])
for f in existing.get('fields', []) if 'info' in f)
# Some headers might have been converted from strings to floats and such.
headers = [str(header) for header in headers]
row_set.register_processor(messytables.headers_processor(headers))
row_set.register_processor(messytables.offset_processor(offset + 1))
types = messytables.type_guess(row_set.sample, types=TYPES, strict=True)
# override with types user requested
if existing_info:
types = [{
'text': messytables.StringType(),
'numeric': messytables.DecimalType(),
'timestamp': messytables.DateUtilType(),
}.get(existing_info.get(h, {}).get('type_override'), t)
for t, h in zip(types, headers)]
row_set.register_processor(messytables.types_processor(types))
headers = [header.strip() for header in headers if header.strip()]
headers_set = set(headers)
def row_iterator():
for row in row_set:
data_row = {}
for index, cell in enumerate(row):
column_name = cell.column.strip()
if column_name not in headers_set:
continue
if isinstance(cell.value, str):
try:
data_row[column_name] = cell.value.encode('latin-1').decode('utf-8')
except (UnicodeDecodeError, UnicodeEncodeError):
data_row[column_name] = cell.value
else:
data_row[column_name] = cell.value
yield data_row
result = row_iterator()
'''
Delete existing datstore resource before proceeding. Otherwise
'datastore_create' will append to the existing datastore. And if
the fields have significantly changed, it may also fail.
'''
if existing:
logger.info('Deleting "{res_id}" from datastore.'.format(
res_id=resource_id))
delete_datastore_resource(resource_id, api_key, ckan_url)
headers_dicts = [dict(id=field[0], type=TYPE_MAPPING[str(field[1])])
for field in zip(headers, types)]
# Maintain data dictionaries from matching column names
if existing_info:
for h in headers_dicts:
if h['id'] in existing_info:
h['info'] = existing_info[h['id']]
# create columns with types user requested
type_override = existing_info[h['id']].get('type_override')
if type_override in list(_TYPE_MAPPING.values()):
h['type'] = type_override
logger.info('Determined headers and types: {headers}'.format(
headers=headers_dicts))
if dry_run:
return headers_dicts, result
count = 0
for i, chunk in enumerate(chunky(result, 250)):
records, is_it_the_last_chunk = chunk
count += len(records)
logger.info('Saving chunk {number} {is_last}'.format(
number=i, is_last='(last)' if is_it_the_last_chunk else ''))
send_resource_to_datastore(resource, headers_dicts, records,
is_it_the_last_chunk, api_key, ckan_url)
logger.info('Successfully pushed {n} entries to "{res_id}".'.format(
n=count, res_id=resource_id))
if data.get('set_url_type', False):
update_resource(resource, api_key, ckan_url)
def push_to_datastore(self, context, resource):
try:
result = download(
context,
resource,
self.max_content_length,
DATA_FORMATS
)
except Exception as e:
logger.exception(e)
return
content_type = result['headers'].get('content-type', '')\
.split(';', 1)[0] # remove parameters
f = open(result['saved_file'], 'rb')
table_sets = AnyTableSet.from_fileobj(
f,
mimetype=content_type,
extension=resource['format'].lower()
)
##only first sheet in xls for time being
row_set = table_sets.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
row_set.register_processor(datetime_procesor())
logger.info('Header offset: {0}.'.format(offset))
guessed_types = type_guess(
row_set.sample,
[
messytables.types.StringType,
messytables.types.IntegerType,
messytables.types.FloatType,
messytables.types.DecimalType,
messytables.types.DateUtilType
],
strict=True
)
logger.info('Guessed types: {0}'.format(guessed_types))
row_set.register_processor(types_processor(guessed_types, strict=True))
row_set.register_processor(stringify_processor())
guessed_type_names = [TYPE_MAPPING[type(gt)] for gt in
guessed_types]
def send_request(data):
data_dict = {
'resource_id': resource['id'],
'fields': [dict(id=name, type=typename) for name, typename
in zip(headers, guessed_type_names)],
'records': data
}
response = logic.get_action('datastore_create')(
context,
data_dict
)
return response
# Delete any existing data before proceeding. Otherwise
# 'datastore_create' will append to the existing datastore. And if the
# fields have significantly changed, it may also fail.
logger.info('Deleting existing datastore (it may not exist): '
'{0}.'.format(resource['id']))
try:
logic.get_action('datastore_delete')(
context,
{'resource_id': resource['id']}
)
except Exception as e:
logger.exception(e)
logger.info('Creating: {0}.'.format(resource['id']))
# generates chunks of data that can be loaded into ckan
# n is the maximum size of a chunk
def chunky(iterable, n):
it = iter(iterable)
while True:
chunk = list(
itertools.imap(
dict, itertools.islice(it, n)))
if not chunk:
return
yield chunk
count = 0
for data in chunky(row_set.dicts(), 100):
count += len(data)
send_request(data)
logger.info("There should be {n} entries in {res_id}.".format(
n=count,
res_id=resource['id']
))
resource.update({
'webstore_url': 'active',
'webstore_last_updated': datetime.datetime.now().isoformat()
})
logic.get_action('resource_update')(context, resource)
def push_to_datastore(self, context, resource):
# Get the resource's content hash, which is used to check whether the
# resource file has changed since last time.
hash_dict = resource.get('hash')
if hash_dict:
original_content_hash = json.loads(hash_dict)['content']
check_hash = not self.options.force
else:
# This resource has no hash yet, it must be a new resource.
original_content_hash = ''
check_hash = False
try:
result = fetch_resource.download(context,
resource,
self.max_content_length,
DATA_FORMATS,
check_modified=check_hash)
except fetch_resource.ResourceNotModified as e:
logger.info(
u'Skipping unmodified resource: {0}'.format(resource['url'])
)
return {'success': True,
'resource': resource['id'],
'error': None}
except Exception as e:
logger.exception(e)
return {'success': False,
'resource': resource['id'],
'error': 'Could not download resource'}
if check_hash and (result['hash'] == original_content_hash):
logger.info(
u'Skipping unmodified resource: {0}'.format(resource['url'])
)
os.remove(result['saved_file'])
return {'success': True,
'resource': resource['id'],
'error': None}
content_type = result['headers'].get('content-type', '')\
.split(';', 1)[0] # remove parameters
f = open(result['saved_file'], 'rb')
try:
table_sets = any_tableset(
f,
mimetype=content_type,
extension=resource['format'].lower()
)
# only first sheet in xls for time being
row_set = table_sets.tables[0]
offset, headers = headers_guess(row_set.sample)
except Exception as e:
logger.exception(e)
os.remove(result['saved_file'])
return {'success': False,
'resource': resource['id'],
'error': 'Error parsing the resource'}
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
row_set.register_processor(datetime_procesor())
logger.info('Header offset: {0}.'.format(offset))
guessed_types = type_guess(
row_set.sample,
[
messytables.types.StringType,
messytables.types.IntegerType,
messytables.types.FloatType,
messytables.types.DecimalType,
messytables.types.DateUtilType
],
strict=True
)
logger.info('Guessed types: {0}'.format(guessed_types))
row_set.register_processor(types_processor(guessed_types, strict=True))
row_set.register_processor(stringify_processor())
guessed_type_names = [TYPE_MAPPING[type(gt)] for gt in
guessed_types]
def send_request(data):
data_dict = {
'resource_id': resource['id'],
'fields': [dict(id=name, type=typename) for name, typename
in zip(headers, guessed_type_names)],
'records': data,
'force': True,
}
response = toolkit.get_action('datastore_create')(
context,
data_dict
)
return response
# Delete any existing data before proceeding. Otherwise
# 'datastore_create' will append to the existing datastore. And if the
# fields have significantly changed, it may also fail.
logger.info('Trying to delete existing datastore for resource {0} '
'(may not exist).'.format(resource['id']))
try:
toolkit.get_action('datastore_delete')(
context,
{'resource_id': resource['id'], 'force': True}
)
except toolkit.ObjectNotFound:
logger.info('Datastore not found for resource {0}.'.format(
resource['id']))
except Exception as e:
logger.exception(e)
logger.info('Creating: {0}.'.format(resource['id']))
# generates chunks of data that can be loaded into ckan
# n is the maximum size of a chunk
def chunky(iterable, n):
it = iter(iterable)
while True:
chunk = list(
itertools.imap(
dict, itertools.islice(it, n)))
if not chunk:
return
yield chunk
count = 0
try:
for data in chunky(row_set.dicts(), 100):
count += len(data)
send_request(data)
except Exception as e:
logger.exception(e)
os.remove(result['saved_file'])
return {'success': False,
'resource': resource['id'],
'error': 'Error pushing data to datastore'}
logger.info("There should be {n} entries in {res_id}.".format(
n=count,
res_id=resource['id']
))
resource.update({
'webstore_url': 'active',
'webstore_last_updated': datetime.now().isoformat()
})
toolkit.get_action('resource_update')(context, resource)
os.remove(result['saved_file'])
return {'success': True,
'resource': resource['id'],
'error': None}
def detect_headers(row_set):
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
return headers
def _datastorer_upload(context, resource, logger):
result = download(context, resource, data_formats=DATA_FORMATS)
logger.info('Downloaded resource %r' %(resource))
content_type = result['headers'].get('content-type', '')\
.split(';', 1)[0] # remove parameters
extension = resource['format'].lower()
fp = open(result['saved_file'], 'rb')
if zipfile.is_zipfile(result['saved_file']):
fp, zf = open_zipped_tableset(fp, extension=extension)
logger.info('Opened entry %s from ZIP archive %s', zf, result['saved_file'])
else:
logger.info('Opened file %s' %(result['saved_file']))
table_sets = any_tableset(fp, extension=extension)
if 'sample_size' in context:
table_sets.window = max(1000, int(context['sample_size']))
logger.info('Using a sample window of %d', table_sets.window)
##only first sheet in xls for time being
row_set = table_sets.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
row_set.register_processor(datetime_procesor())
logger.info('Header offset: {0}.'.format(offset))
guessed_types = type_guess(
row_set.sample,
[
messytables.types.StringType,
messytables.types.IntegerType,
messytables.types.FloatType,
messytables.types.DecimalType,
messytables.types.DateUtilType
],
strict=True
)
logger.info('Guessed types: {0}'.format(guessed_types))
row_set.register_processor(types_processor(guessed_types, strict=True))
row_set.register_processor(stringify_processor())
ckan_url = context['site_url'].rstrip('/')
datastore_create_request_url = '%s/api/action/datastore_create' % (ckan_url)
guessed_type_names = [TYPE_MAPPING[type(gt)] for gt in guessed_types]
def send_request(data):
request = {'resource_id': resource['id'],
'fields': [dict(id=name, type=typename) for name, typename in zip(headers, guessed_type_names)],
'force': True,
'records': data}
response = requests.post(datastore_create_request_url,
data=json.dumps(request),
headers={'Content-Type': 'application/json',
'Authorization': context['apikey']},
)
check_response_and_retry(response, datastore_create_request_url, logger)
# Delete any existing data before proceeding. Otherwise 'datastore_create' will
# append to the existing datastore. And if the fields have significantly changed,
# it may also fail.
try:
logger.info('Deleting existing datastore (it may not exist): {0}.'.format(resource['id']))
response = requests.post('%s/api/action/datastore_delete' % (ckan_url),
data=json.dumps({'resource_id': resource['id'], 'force': True}),
headers={'Content-Type': 'application/json',
'Authorization': context['apikey']}
)
if not response.status_code or response.status_code not in (200, 404):
# skips 200 (OK) or 404 (datastore does not exist, no need to delete it)
logger.error('Deleting existing datastore failed: {0}'.format(get_response_error(response)))
raise DatastorerException("Deleting existing datastore failed.")
except requests.exceptions.RequestException as e:
logger.error('Deleting existing datastore failed: {0}'.format(str(e)))
raise DatastorerException("Deleting existing datastore failed.")
logger.info('Creating: {0}.'.format(resource['id']))
# generates chunks of data that can be loaded into ckan
# n is the maximum size of a chunk
def chunky(iterable, n):
it = iter(iterable)
while True:
chunk = list(
itertools.imap(
dict, itertools.islice(it, n)))
if not chunk:
return
yield chunk
count = 0
for data in chunky(row_set.dicts(), 100):
count += len(data)
send_request(data)
logger.info("There should be {n} entries in {res_id}.".format(n=count, res_id=resource['id']))
ckan_request_url = ckan_url + '/api/action/resource_update'
resource.update({
'webstore_url': 'active',
'webstore_last_updated': datetime.datetime.now().isoformat()
})
response = requests.post(
ckan_request_url,
data=json.dumps(resource),
headers={'Content-Type': 'application/json',
'Authorization': context['apikey']})
if response.status_code not in (201, 200):
raise DatastorerException('Ckan bad response code (%s). Response was %s' %
(response.status_code, response.content))
resource['hash'] = file_hash
try:
table_set = messytables.any_tableset(f, mimetype=ct, extension=ct)
except messytables.ReadError as e:
## try again with format
f.seek(0)
try:
format = resource.get('format')
table_set = messytables.any_tableset(f, mimetype=format, extension=format)
except:
raise util.JobError(e)
row_set = table_set.tables.pop()
offset, headers = messytables.headers_guess(row_set.sample)
row_set.register_processor(messytables.headers_processor(headers))
row_set.register_processor(messytables.offset_processor(offset + 1))
types = messytables.type_guess(row_set.sample, types=TYPES, strict=True)
row_set.register_processor(messytables.types_processor(types))
headers = [header.strip() for header in headers if header.strip()]
headers_set = set(headers)
def row_iterator():
for row in row_set:
data_row = {}
for index, cell in enumerate(row):
column_name = cell.column.strip()
if column_name not in headers_set:
continue
data_row[column_name] = cell.value
def _datastorer_upload(context, resource):
excel_types = ['xls', 'application/ms-excel', 'application/xls', 'application/vnd.ms-excel']
result = download(context, resource, data_formats=DATA_FORMATS)
content_type = result['headers'].get('content-type', '')
f = open(result['saved_file'], 'rb')
if content_type in excel_types or resource['format'] in excel_types:
table_sets = XLSTableSet.from_fileobj(f)
else:
table_sets = CSVTableSet.from_fileobj(f)
##only first sheet in xls for time being
row_set = table_sets.tables[0]
offset, headers = headers_guess(row_set.sample)
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
row_set.register_processor(datetime_procesor())
types = guess_types(list(row_set.dicts(sample=True)))
row_set.register_processor(offset_processor(offset + 1))
row_set.register_processor(types_processor(types))
ckan_url = context['site_url'].rstrip('/')
webstore_request_url = '%s/api/data/%s/' % (ckan_url,
resource['id']
)
def send_request(data):
return requests.post(webstore_request_url + '_bulk',
data = "%s%s" % ("\n".join(data), "\n"),
headers = {'Content-Type': 'application/json',
'Authorization': context['apikey']},
)
data = []
for count,dict_ in enumerate(row_set.dicts()):
data.append(json.dumps({"index": {"_id": count+1}}))
data.append(json.dumps(dict_))
if (count % 100) == 0:
response = send_request(data)
check_response_and_retry(response, webstore_request_url+'_mapping')
data[:] = []
if data:
respose = send_request(data)
check_response_and_retry(response, webstore_request_url+'_mapping')
ckan_request_url = ckan_url + '/api/action/resource_update'
ckan_resource_data = {
'id': resource["id"],
'webstore_url': webstore_request_url,
'webstore_last_updated': datetime.datetime.now().isoformat()
}
response = requests.post(
ckan_request_url,
data=json.dumps(ckan_resource_data),
headers = {'Content-Type': 'application/json',
'Authorization': context['apikey']},
)
if response.status_code not in (201, 200):
raise WebstorerError('Ckan bad response code (%s). Response was %s'%
(response.status_code, response.content)
)