def download(self, engine=None, debug=False):
Script.download(self, engine, debug)
reload(sys)
if hasattr(sys, 'setdefaultencoding'):
sys.setdefaultencoding("utf-8")
self.engine.download_file(self.urls["GWDD"], "GlobalWoodDensityDatabase.xls")
filename = os.path.basename("GlobalWoodDensityDatabase.xls")
book = xlrd.open_workbook(self.engine.format_filename(filename))
sh = book.sheet_by_index(1)
rows = sh.nrows
# Creating data files
file_path = self.engine.format_filename("gwdd_data.csv")
gwdd_data = open_fw(file_path)
csv_writer = open_csvw(gwdd_data)
csv_writer.writerow(["Number", "Family", "Binomial", "Wood_Density", "Region", "Reference_Number"])
for index in range(1, rows):
row = sh.row(index)
# get each row and format the sell value.
row_as_list = [to_str(column_value.value) for column_value in row]
csv_writer.writerow(row_as_list)
gwdd_data.close()
table = Table("data", delimiter=",")
table.columns = [("Number", ("pk-int",)),
("Family", ("char",)),
("Binomial", ("char",)),
("Wood_Density", ("double",)),
("Region", ("char",)),
("Reference_Number", ("int",))]
table.pk = 'Number'
table.contains_pk = True
self.engine.table = table
self.engine.create_table()
self.engine.insert_data_from_file(engine.format_filename(file_path))
# Creating reference tale file
file_path = self.engine.format_filename("gwdd_ref.csv")
ref_file = open_fw(file_path)
csv_writerd = open_csvw(ref_file)
csv_writerd.writerow(["Reference_Number", "Reference"])
sh = book.sheet_by_index(2)
rows = sh.nrows
for index in range(1, rows):
row = sh.row(index)
# get each row and format the sell value.
row_as_list = [to_str(column_value.value, object_encoding=sys.stdout) for column_value in row]
csv_writerd.writerow(row_as_list)
ref_file.close()
table = Table("reference", delimiter=",")
table.columns = [("Reference_Number", ("pk-int",)), ("Reference", ("char",))]
table.pk = 'Reference_Number'
table.contains_pk = True
self.engine.table = table
self.engine.create_table()
self.engine.insert_data_from_file(engine.format_filename(file_path))
return self.engine
def download(self, engine=None, debug=False):
Script.download(self, engine, debug)
reload(sys)
if hasattr(sys, 'setdefaultencoding'):
sys.setdefaultencoding("utf-8")
self.engine.download_file(self.urls["GWDD"],
"GlobalWoodDensityDatabase.xls")
filename = os.path.basename("GlobalWoodDensityDatabase.xls")
book = xlrd.open_workbook(self.engine.format_filename(filename))
sh = book.sheet_by_index(1)
rows = sh.nrows
# Creating data files
file_path = self.engine.format_filename("gwdd_data.csv")
gwdd_data = open_fw(file_path)
csv_writer = open_csvw(gwdd_data)
csv_writer.writerow([
"Number", "Family", "Binomial", "Wood_Density", "Region",
"Reference_Number"
])
for index in range(1, rows):
row = sh.row(index)
# get each row and format the sell value.
row_as_list = [to_str(column_value.value) for column_value in row]
csv_writer.writerow(row_as_list)
gwdd_data.close()
table = Table("data", delimiter=",")
table.columns = [("Number", ("pk-int", )), ("Family", ("char", )),
("Binomial", ("char", )),
("Wood_Density", ("double", )),
("Region", ("char", )),
("Reference_Number", ("int", ))]
table.pk = 'Number'
table.contains_pk = True
self.engine.table = table
self.engine.create_table()
self.engine.insert_data_from_file(engine.format_filename(file_path))
# Creating reference tale file
file_path = self.engine.format_filename("gwdd_ref.csv")
ref_file = open_fw(file_path)
csv_writerd = open_csvw(ref_file)
csv_writerd.writerow(["Reference_Number", "Reference"])
sh = book.sheet_by_index(2)
rows = sh.nrows
for index in range(1, rows):
row = sh.row(index)
# get each row and format the sell value.
row_as_list = [
to_str(column_value.value, object_encoding=sys.stdout)
for column_value in row
]
csv_writerd.writerow(row_as_list)
ref_file.close()
table = Table("reference", delimiter=",")
table.columns = [("Reference_Number", ("pk-int", )),
("Reference", ("char", ))]
table.pk = 'Reference_Number'
table.contains_pk = True
self.engine.table = table
self.engine.create_table()
self.engine.insert_data_from_file(engine.format_filename(file_path))
return self.engine
def download(self, engine=None, debug=False):
Script.download(self, engine, debug)
engine = self.engine
engine.download_files_from_archive(self.urls["capture"], archive_type="zip")
# Convert xlsx to csv.
xlsx_file = self.engine.format_filename("DSD_FI_CAPTURE.xlsx")
file_path = self.engine.format_filename("DSD_CAPTURE.csv")
book = xlrd.open_workbook(xlsx_file)
sh = book.sheet_by_index(0)
rows = sh.nrows
# Creating data files
new_data = open_fw(file_path)
csv_writer = open_csvw(new_data)
csv_writer.writerow(["Order", "Concept_id",
"Role_Type", "Codelist_id",
"Codelist_Code_id", "Description"])
for index in range(2, rows):
row = sh.row(index)
# Get each row and format the sell value.
# Data starts at index 2
row_as_list = [to_str(column_value.value) for column_value in row]
csv_writer.writerow(row_as_list)
new_data.close()
file_names = [
('CL_FI_UNIT.csv', 'unit_data'),
('CL_FI_WATERAREA_GROUPS.csv', 'waterarea_groups'),
('DSD_CAPTURE.csv', 'dsd_capture_data'),
('CL_FI_SPECIES_GROUPS.csv', 'species_group')
]
for (filename, tablename) in file_names:
data_path = self.engine.format_filename(filename)
table = Table(tablename, delimiter=',', cleanup=self.cleanup_func_table)
self.engine.auto_create_table(table, filename=filename)
self.engine.insert_data_from_file(data_path)
# File CL_FI_COUNTRY_GROUPS.csv has multi encoding
file_names_encoded = [
('CL_FI_COUNTRY_GROUPS.csv', 'country_groups'),
]
for (filename, tablename) in file_names_encoded:
data_path = self.engine.format_filename(filename)
table = Table(tablename, delimiter=',', cleanup=self.cleanup_func_table)
table.columns = [('UN_Code', ('int', )),
('Identifier', ('int', )),
('ISO2_Code', ('char', '5')),
('ISO3_Code', ('char', '5')),
('Name_En', ('char', '50')),
('Name_Fr', ('char', '50')),
('Name_Es', ('char', '50')),
('Name_Ar', ('char', '120')),
('Name_Cn', ('char', '90')),
('Name_Ru', ('char', '150')),
('Official_Name_En', ('char', '70')),
('Official_Name_Fr', ('char', '70')),
('Official_Name_Es', ('char', '70')),
('Official_Name_Ar', ('char', '1100')),
('Official_Name_Cn', ('char', '70')),
('Official_Name_Ru', ('char', '130')),
('Continent_Group', ('char', '15')),
('EcoClass_Group', ('char', '50')),
('GeoRegion_Group', ('char', '30'))]
self.engine.auto_create_table(table, filename=filename)
self.engine.insert_data_from_file(data_path)
# TS_FI_CAPTURE is
file_names_encoded = [
('TS_FI_CAPTURE.csv', 'ts_capture_data',)
]
for (filename, tablename) in file_names_encoded:
data_path = self.engine.format_filename(filename)
table = Table(tablename, delimiter=',', cleanup=self.cleanup_func_table)
table.columns = [('COUNTRY', ('int', )),
('FISHING_AREA', ('int', )),
('SPECIES', ('char', '10')),
('YEAR', ('int', )),
('UNIT', ('char', '5')),
('QUANTITY', ('double', )),
('SYMBOL', ('char', '4'))]
self.engine.auto_create_table(table, filename=filename)
self.engine.insert_data_from_file(data_path)