def test(self):
DTEULAAPP.loadmodels()
resourcefolder = helpers.getresourcefolder()
outpath = os.path.join(resourcefolder, 'tempout.json')
DTEULAAPP.batch(resourcefolder, outpath)
self.assertEqual(
os.stat(outpath).st_size, 329185,
'The output file is 329185 bytes in size')
os.remove(outpath)
def test(self):
resourcefolder = helpers.getresourcefolder()
pdfPath = os.path.join(resourcefolder, 'sample_eula_1.pdf')
curdata = ''
with open(pdfPath, 'rb') as curfile:
curdata = base64.b64encode(curfile.read()).decode()
plaintext = DTEULAAPP.parsepdf(curdata)
clauses = DTEULAAPP.extractPDFClauses(plaintext)
self.assertEqual(len(clauses), 134,
'The sample PDF EULA should have 134 clauses')
def test(self):
resourcefolder = helpers.getresourcefolder()
wordPath = os.path.join(resourcefolder, 'sample_eula_1.docx')
curdata = ''
with open(wordPath, 'rb') as curfile:
curdata = base64.b64encode(curfile.read()).decode()
plaintext = DTEULAAPP.parseword(curdata)
self.assertEqual(
len(plaintext), 47608,
'The sample Word EULA should have 47608 characters of plain text')
def test(self):
resourcefolder = helpers.getresourcefolder()
pdfPath = os.path.join(resourcefolder, 'sample_eula_1.pdf')
curdata = ''
with open(pdfPath, 'rb') as curfile:
curdata = base64.b64encode(curfile.read()).decode()
plaintext = DTEULAAPP.parsepdf(curdata)
self.assertEqual(
len(plaintext), 45812,
'The sample PDF EULA should have 45812 characters of plain text')
def test(self):
DTEULAAPP.loadmodels()
resourcefolder = helpers.getresourcefolder()
wordPath = os.path.join(resourcefolder, 'sample_eula_1.docx')
curdata = ''
with open(wordPath, 'rb') as curfile:
curdata = base64.b64encode(curfile.read()).decode()
results = DTEULAAPP.processClauseText(curdata, 'word')
self.assertEqual(len(results), 140,
'There are 140 results of processing Word text')
accs = sum(1 for curresult in results
if curresult['classification'] == 'Acceptable')
self.assertEqual(accs, 139,
'There are 139 acceptable clauses in the Word text')