def test_multi(self):
text = "aio blah blah $$%^q 32 5432 3096 6798 2217 1740 \n"
text += "CCNO: 4109 4533 4898 8521\n"
text += "MY PAN%5162702975322904\n"
self.assertEqual(panscan(text), [(29, "3096 6798 2217 1740"),
(56, "4109 4533 4898 8521"),
(83, "5162702975322904")])
def plugin(fname, data=None):
try:
if data != None:
flo = StringIO.StringIO(data)
wb = load_workbook(flo)
else:
wb = load_workbook(filename=fname, use_iterators=True)
except InvalidFileException:
logger.Logger().log_ignore(fname, "Invalid Excel file")
return
sheetNames = wb.get_sheet_names()
for name in sheetNames:
sheet = wb.get_sheet_by_name(name)
for cell in sheet.get_cell_collection():
if cell.value != None:
# scan text for pans and return as a list
value = str(cell.value)
pans = panscan.panscan(" " + value + " ")
# log each pan found - bit of a hack to see if the pans list is empty
for p in pans:
logger.Logger().log_pan(fname, p[1], name + " Cell " + cell.column + ":" + str(cell.row))
def plugin(fname, data = None):
try:
if (data != None):
flo = StringIO.StringIO(data)
wb = load_workbook(flo)
else:
wb = load_workbook(filename = fname, use_iterators = True)
except InvalidFileException:
logger.Logger().log_ignore(fname, "Invalid Excel file")
return
sheetNames = wb.get_sheet_names()
for name in sheetNames:
sheet = wb.get_sheet_by_name(name)
for cell in sheet.get_cell_collection():
if (cell.value !=None):
# scan text for pans and return as a list
value = str(cell.value)
pans = panscan.panscan(" " + value + " ")
# log each pan found - bit of a hack to see if the pans list is empty
for p in pans:
logger.Logger().log_pan(fname, p[1], name +" Cell " + cell.column +":"+ str(cell.row))
def plugin(file, data=None):
if data is not None:
try:
filelikeObj = StringIO.StringIO(data)
except Exception as e:
Logger().log_error(e)
return
try:
mydoc = zipfile.ZipFile(filelikeObj)
except zipfile.BadZipfile as e:
Logger().log_error(e)
return
else:
try:
mydoc = zipfile.ZipFile(file)
except (zipfile.BadZipfile, zipfile.LargeZipFile) as e:
Logger().log_error(e)
return
try:
xmlcontent = mydoc.read('word/document.xml')
except IOError as e:
Logger().log_error(e)
return
try:
document = etree.fromstring(xmlcontent)
except Exception as e:
Logger().log_error(e)
return
# Create a list of paragraphs
paratextlist = []
paralist = []
for element in document.iter():
if element.tag == '{' + nsprefixes['w'] + '}p':
paralist.append(element)
for para in paralist:
paratext = u''
for element in para.iter():
if element.tag == '{' + nsprefixes['w'] + '}t':
if element.text:
paratext = paratext + element.text
if not len(paratext) == 0:
paratextlist.append(paratext)
# Scan and log
paraNum = 1
for i in paratextlist:
pans = panscan.panscan(i)
for p in pans:
logger.Logger().log_pan(file, p, "Paragraph number " + i + ".")
paraNum += 1
def plugin(file, data=None):
if data is not None:
try:
filelikeObj = StringIO.StringIO(data)
except Exception as e:
Logger().log_error(e)
return
try:
mydoc = zipfile.ZipFile(filelikeObj)
except zipfile.BadZipfile as e:
Logger().log_error(e)
return
else:
try:
mydoc = zipfile.ZipFile(file)
except (zipfile.BadZipfile, zipfile.LargeZipFile) as e:
Logger().log_error(e)
return
try:
xmlcontent = mydoc.read('word/document.xml')
except IOError as e:
Logger().log_error(e)
return
try:
document = etree.fromstring(xmlcontent)
except Exception as e:
Logger().log_error(e)
return
# Create a list of paragraphs
paratextlist=[]
paralist = []
for element in document.iter():
if element.tag == '{'+nsprefixes['w']+'}p':
paralist.append(element)
for para in paralist:
paratext=u''
for element in para.iter():
if element.tag == '{'+nsprefixes['w']+'}t':
if element.text:
paratext = paratext+element.text
if not len(paratext) == 0:
paratextlist.append(paratext)
# Scan and log
paraNum = 1
for i in paratextlist:
pans = panscan.panscan(i)
for p in pans:
logger.Logger().log_pan(file, p, "Paragraph number " + i +".")
paraNum += 1
def plugin(fileName, data = None):
if data == None:
try:
fd = file(fileName, "rb")
pdf = PdfFileReader(fd)
except Exception as e:
Logger().log_error(e)
return
else:
# handle data as a block
# TODO test this actually works
try:
flo = StringIO.StringIO(data)
pdf = PdfFileReader(flo)
except Exception as e:
Logger().log_error(e)
return
# create and zero contents string
contents = ""
# find how many pages input1 has:
try:
numPages = pdf.getNumPages()
except Exception as e:
Logger().log_error(e)
return
# iterate over all pages and extract text
for i in range(numPages):
# get next page from pdf and extract text as a single string
try:
s = pdf.getPage(i).extractText() + "\n"
s.encode("ascii", "ignore")
except Exception as e:
Logger().log_error(e)
return
# scan text for pans and return as a list
pans = panscan(s)
# log each pan found
for p in pans:
Logger().log_pan(fileName, p[1], "on page %s" % (i + 1))
if data == None:
fd.close()
def plugin(fileName, data=None):
if data == None:
try:
fd = file(fileName, "rb")
pdf = PdfFileReader(fd)
except Exception as e:
Logger().log_error(e)
return
else:
# handle data as a block
# TODO test this actually works
try:
flo = StringIO.StringIO(data)
pdf = PdfFileReader(flo)
except Exception as e:
Logger().log_error(e)
return
# create and zero contents string
contents = ""
# find how many pages input1 has:
try:
numPages = pdf.getNumPages()
except Exception as e:
Logger().log_error(e)
return
# iterate over all pages and extract text
for i in range(numPages):
# get next page from pdf and extract text as a single string
try:
s = pdf.getPage(i).extractText() + "\n"
s.encode("ascii", "ignore")
except Exception as e:
Logger().log_error(e)
return
# scan text for pans and return as a list
pans = panscan(s)
# log each pan found
for p in pans:
Logger().log_pan(fileName, p[1], "on page %s" % (i + 1))
if data == None:
fd.close()
def plugin(filename, data):
if not data:
try:
f = open(filename)
except IOError as e:
Logger().log_error(e)
return
try:
data = f.read()
except IOError as e:
Logger().log_error(e)
finally:
f.close()
results = panscan(data)
for r in results:
Logger().log_pan(filename, r[1], "at offset %d" % (r[0]))
def plugin(filename, data):
if not data:
try:
f = open(filename)
except IOError as e:
Logger().log_error(e)
return
try:
data = f.read()
except IOError as e:
Logger().log_error(e)
finally:
f.close()
results = panscan(data)
for r in results:
Logger().log_pan(filename, r[1], "at offset %d" % (r[0]))
def parse(filename, fileType, data=None):
"""
This will open the file, and then will proceed to parse myFile: String
containing the path of the file to parse fileType: just the extension of
the file. I would parse it myself, but the caller will already know this"""
try:
if data:
filelikeObj = StringIO.StringIO(data)
myfile = zipfile.ZipFile(filelikeObj, "r", zipfile.ZIP_DEFLATED)
else:
myfile = zipfile.ZipFile(filename, 'r', zipfile.ZIP_DEFLATED)
except zipfile.BadZipfile:
logger.Logger().log_ignore(filename, "Bad zip file")
return
xmldata = myfile.read("content.xml")
myfile.close()
pans = panscan.panscan(xmldata)
for p in pans:
logger.Logger().log_pan(filename, p[1], "at offset %d" % p[0])
def parse(filename, fileType, data = None):
"""
This will open the file, and then will proceed to parse myFile: String
containing the path of the file to parse fileType: just the extension of
the file. I would parse it myself, but the caller will already know this"""
try:
if data:
filelikeObj = StringIO.StringIO(data)
myfile = zipfile.ZipFile(filelikeObj, "r", zipfile.ZIP_DEFLATED)
else:
myfile = zipfile.ZipFile(filename,'r', zipfile.ZIP_DEFLATED)
except zipfile.BadZipfile:
logger.Logger().log_ignore(filename, "Bad zip file")
return
xmldata = myfile.read("content.xml")
myfile.close()
pans = panscan.panscan(xmldata)
for p in pans:
logger.Logger().log_pan(filename, p[1], "at offset %d" % p[0])
def plugin(filename, data=None):
if data is not None:
book = xlrd.open_workbook(filename, file_contents=data)
else:
book = xlrd.open_workbook(filename) # Open an .xls file
# iterate over sheets
for i in range(len(book.sheet_names())):
sheet = book.sheet_by_index(i)
for rownum in range(sheet.nrows):
for column in range(len(sheet.row_values(rownum))):
# scan text for pans and return as a list
pans = panscan.panscan(" " + unicode(sheet.row_values(rownum)[column]) + " ")
# log each pan found
for p in pans:
logger.Logger().log_pan(
filename,
p[1],
"in sheet %s, in cell %s:%d" % (book.sheet_names()[i], intToChar(column), rownum),
)
def plugin(filename, data=None):
try:
if data is not None:
book = xlrd.open_workbook(filename, file_contents=data)
else:
book = xlrd.open_workbook(filename) # Open an .xls file
except xlrd.biffh.XLRDError as e:
Logger().log_error(e)
return
# iterate over sheets
for i in range(len(book.sheet_names())):
sheet = book.sheet_by_index(i)
for rownum in range(sheet.nrows):
for column in range(len(sheet.row_values(rownum))):
# scan text for pans and return as a list
pans = panscan.panscan(
" " + unicode(sheet.row_values(rownum)[column]) + " ")
# log each pan found
for p in pans:
Logger().log_pan(
filename, p[1], "in sheet %s, in cell %s:%d" %
(book.sheet_names()[i], inttochar(column), rownum))
def test_all_numbers(self):
text = "11238947524713897214 128951673475 435413 483576107"
self.assertEqual(panscan(text), [])
def test_no_numbers(self):
text = "wiubfoiranvquwrhruehig uhegw\nweowiuhwfe weoif$%&wgoirgh\n"
self.assertEqual(panscan(text), [])
def test_invalid_jcb2(self):
text = "213118001438560 "
self.assertEqual(panscan(text), [])
def test_valid_jcb2(self):
text = "2 1 3 1 1 8 0 0 0 4 0 8 5 6 0 "
self.assertEqual(panscan(text), [(0, "2 1 3 1 1 8 0 0 0 4 0 8 5 6 0")])
def test_valid_jcb(self):
text = "3096 6798 2217 1740 "
self.assertEqual(panscan(text), [(0, "3096 6798 2217 1740")])
def test_invalid_short_visa(self):
text = "4410 5535 6357 6 "
self.assertEqual(panscan(text), [])
def test_invalid_visa(self):
text = "4109 4533 4898 8520\n"
self.assertEqual(panscan(text), [])
def test_valid_short_visa(self):
text = "4410 5535 6357 5 "
self.assertEqual(panscan(text), [(0, "4410 5535 6357 5")])
def test_invalid_visa(self):
text = "4109 4533 4898 8520\n"
self.assertEqual(panscan(text), [])
def test_valid_visa(self):
text = "4109 4533 4898 8521\n"
self.assertEqual(panscan(text), [(0, "4109 4533 4898 8521")])
def test_invalid_amex34(self):
text = "3401 1825 3784 805 "
self.assertEqual(panscan(text), [])
def test_valid_amex34(self):
text = "3401 1825 3784 804 "
self.assertEqual(panscan(text), [(0, "3401 1825 3784 804")])
def test_invalid_mastercard(self):
text = "8293396262570410"
self.assertEqual(panscan(text), [])
def test_valid_mastercard(self):
text = "5162702975322904\n"
self.assertEqual(panscan(text), [(0, "5162702975322904")])
def test_invalid_jcb(self):
text = "3096 6798 2217 1741 "
self.assertEqual(panscan(text), [])
def test_valid_amex37(self):
text = "3730 4625 0745 132 "
self.assertEqual(panscan(text), [(0, "3730 4625 0745 132")])
def test_valid_short_visa(self):
text = "4410 5535 6357 5 "
self.assertEqual(panscan(text), [(0, "4410 5535 6357 5")])
def test_valid_mastercard(self):
text = "5162702975322904\n"
self.assertEqual(panscan(text), [(0, "5162702975322904")])
def test_invalid_amex37(self):
text = "3730 4625 0745 133 "
self.assertEqual(panscan(text), [])
def test_valid_visa(self):
text = "4109 4533 4898 8521\n"
self.assertEqual(panscan(text), [(0, "4109 4533 4898 8521")])
def test_valid_diners(self):
text = "3001 7970 1170 97 "
self.assertEqual(panscan(text), [(0, "3001 7970 1170 97")])
def test_invalid_short_visa(self):
text = "4410 5535 6357 6 "
self.assertEqual(panscan(text), [])
def test_invalid_diners(self):
text = "3001 7970 1170 99 "
self.assertEqual(panscan(text), [])