def generate_shex_from_csv(filepath, delim=",", skip_header=False):
"""
This method can be used to generate ShEx from application profile CSV file. However, the input file must contain one or more lines. Each line contains '|' separated values. If filepath is a string, filename should be set to false.
Parameters
----------
filepath : str
This parameter can contain either a file path of a CSV file or shexstatements in CSV format.
delim : str
a delimiter. Allowed values include ',', '|' and ';'
skip_header : bool
if the first line is a header, set this value to True. By default, the value is False.
Returns
-------
shex
shape expression
"""
shexstatement = ""
try:
data = ""
with open(filepath, 'r') as csvfile:
csvreader = csv.reader(csvfile, delimiter=delim)
rowno = 0
shapename = ""
typelines = set()
for row in csvreader:
rowno = rowno + 1
if skip_header and rowno == 1:
continue
line = ""
# Ignore lines with incorrect number of values
if (len(row) != 8):
continue
if row[0]:
shapename = "@" + row[0]
if row[6] and row[1]:
typelines.add("@" + row[6] + "type" + "|rdf:type|" +
row[6] + "\n")
line = shapename + "|" + \
row[1]+"|" + "@" + row[6]+"type"
else:
line = shapename + "|" + row[1] + "|" + row[5]
mand = row[3].lower() == "yes"
repeat = row[4].lower() == "yes"
if mand and repeat:
line = line + "|+"
elif mand and not repeat:
line = line + "|1"
elif not mand and repeat:
line = line + "|*"
elif not mand and not repeat:
line = line + "|0,1"
if row[7]:
line = line + "|#" + row[7]
data = data + line + "\n"
if typelines:
data = data + "".join(typelines) + "\n"
shexstatement = CSV.generate_shex_from_data_string(data)
except Exception as e:
print("Unable to parse. Error: " + str(e))
return shexstatement
def generate_shex_from_spreadsheet(filepath,
skip_header=False,
stream=None):
"""
This method can be used to generate ShEx from data string. However, the input data string must contain one or more lines. Each line contains '|' separated values. If filepath is a string, filename should be set to false.
Parameters
----------
filepath : str
This parameter contains path of a Spreadsheet file
skip_header : bool
if the first line is a header, set this value to True. By default, the value is False.
Returns
-------
shex
shape expression
"""
shexstatement = ""
try:
pattern = '^\s*$'
data = ""
filename, file_extension = splitext(filepath)
if (file_extension in {".xlsx", ".xlsm", ".xltx", ".xltm"}):
wb = None
if stream is not None:
with open("tmp" + filepath, "wb") as sf:
sf.write(stream)
sf.close()
filepath = "tmp" + filepath
wb = load_workbook(filepath)
for ws in wb.worksheets:
for i in range(1, ws.max_row + 1):
line = list()
for j in range(1, ws.max_column + 1):
cell = ws.cell(row=i, column=j).value
if cell is not None:
line.append(cell)
line = "|".join(line)
data = data + line + "\n"
if stream is not None:
remove(filepath)
elif (file_extension in {".xls"}):
wb = None
if stream is not None:
#wb = open_workbook(file_contents=stream, encoding_override="cp1252")
wb = open_workbook(file_contents=stream)
else:
wb = open_workbook(filepath)
for sheet in wb.sheets():
for i in range(0, wb.sheets()[0].nrows):
line = list()
for j in range(0, wb.sheets()[0].ncols):
cell = sheet.cell(i, j).value
if len(str(cell)) > 0:
line.append(cell)
data = data + "|".join(line) + "\n"
elif (file_extension in {".ods"}):
wb = None
if stream is not None:
with open("tmp" + filepath, "wb") as sf:
sf.write(stream)
sf.close()
filepath = "tmp" + filepath
wb = load(filepath)
wb = wb.spreadsheet
rows = wb.getElementsByType(TableRow)
for row in rows:
cells = row.getElementsByType(TableCell)
line = list()
for cell in cells:
if len(str(cell)) > 0:
line.append(str(cell))
data = data + "|".join(line) + "\n"
if stream is not None:
remove(filepath)
shexstatement = CSV.generate_shex_from_data_string(data)
except Exception as e:
print("Unable to read file. Error: " + str(e))
return shexstatement
