def test_016(self):
""" Document document setter - valid text file """
document = Document()
document.document = "test.txt"
self.assertEqual(document.name, "test")
self.assertEqual(len(document), 1)
self.assertEqual(document.text, ["foo"])
os.remove("test1.txt")
def test_023(self):
""" Document text setter """
document = Document("files/4page.pdf", "./")
document.text[0] = "goo"
# TODO
#self.assertEqual(document.text[0], "goo")
for i in range(1, 5):
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".json")
def test_064(self):
""" config stem is valid """
document = Document("files/4page.pdf", "./", config=['stem=gap'])
document = Document("files/4page.pdf", "./", config=['stem=porter'])
document = Document("files/4page.pdf", "./", config=['stem=snowball'])
document = Document("files/4page.pdf", "./", config=['stem=lancaster'])
document = Document("files/4page.pdf", "./", config=['stem=lemma'])
for i in range(1, 5):
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".json")
def test_018(self):
""" Document document setter - valid PDF file with page directory """
document = Document()
document.dir = "./"
document.document = "files/4page.pdf"
self.assertEqual(document.name, "4page")
self.assertEqual(len(document), 4)
for i in range(1, 5):
self.assertTrue(os.path.isfile("4page" + str(i) + ".pdf"))
self.assertTrue(os.path.isfile("4page" + str(i) + ".txt"))
self.assertTrue(os.path.isfile("4page" + str(i) + ".json"))
for i in range(1, 5):
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".json")
def test_074(self):
""" Document - lang type, page 1 """
document = Document("files/lang-en.txt", "./")
self.assertEquals(document.lang, 'en')
document = Document("files/lang-es.txt", "./")
self.assertEquals(document.lang, 'es')
document = Document("files/lang-fr.txt", "./")
self.assertEquals(document.lang, 'fr')
document = Document("files/lang-de.txt", "./")
self.assertEquals(document.lang, 'de')
document = Document("files/lang-it.txt", "./")
self.assertEquals(document.lang, 'it')
for lang in ['en', 'es', 'fr', 'de', 'it']:
os.remove("lang-" + lang + "1.txt")
os.remove("lang-" + lang + "1.json")
def test_008(self):
""" Document constructor - keyword argument: document """
document = Document(document="test.txt")
self.assertEqual(document.name, "test")
self.assertEqual(len(document), 1)
os.remove("test1.txt")
os.remove("test1.json")
def test_011(self):
""" Document constructor - store single page text file for raw text document """
document = Document("test.txt", "./")
self.assertEqual(document.name, "test")
self.assertTrue(os.path.isfile("test1.txt"))
os.remove("test1.txt")
os.remove("test1.json")
def test_026(self):
""" Document [] setter """
document = Document("test.txt")
page = Page(text='hello world')
document[0] = page
self.assertEqual(document[0].text, "hello world")
os.remove("test1.txt")
def test_067(self):
""" config segment image """
document = Document('files/text.png', './', config=['segment'])
self.assertEquals(len(document[0].words), 7)
os.remove('text1.png')
os.remove('text1.txt')
os.remove('text1.json')
def test_066(self):
""" config segment pdf """
document = Document('files/invoice.pdf', './', config=['segment'])
self.assertEquals(len(document[0].words), 15)
os.remove('invoice1.pdf')
os.remove('invoice1.txt')
os.remove('invoice1.json')
def test_028(self):
""" Document [] setter - not an int index """
document = Document("test.txt")
page = Page(text='hello world')
with pytest.raises(TypeError):
document['abc'] = page
os.remove("test1.txt")
def test_053(self):
# page.path for .txt file
document = Document("test.txt")
self.assertTrue(os.path.isfile("test1.json"))
self.assertEquals(document[0].path, "./test1.txt")
os.remove("test1.txt")
os.remove("test1.json")
def test_012(self):
""" Document constructor - non-ascii characters in document (UTF-8 encoding) """
document = Document("files/7page.pdf", "./")
self.assertEqual(document[0].text.strip()[0:7], "MEDICAL")
for i in range(1, 8):
os.remove("7page" + str(i) + ".pdf")
os.remove("7page" + str(i) + ".txt")
os.remove("7page" + str(i) + ".json")
def test_037(self):
""" Document type getter - PDF """
document = Document("files/4page.pdf", "./")
self.assertEqual(document.type, "pdf")
for i in range(1, 5):
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".json")
def test_035(self):
""" Document size getter - non-zero """
document = Document("files/4page.pdf", "./")
self.assertEqual(document.size, 32667)
for i in range(1, 5):
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".json")
def test_058(self):
""" config is empty """
document = Document("files/4page.pdf", "./", config=[])
self.assertTrue(document.bagOfWords != None)
for i in range(1, 5):
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".json")
def test_051(self):
""" async processing """
document = Document("files/invoice.pdf", "./", self.done)
time.sleep(6)
self.assertTrue(self.isdone)
os.remove("invoice1.pdf")
os.remove("invoice1.txt")
os.remove("invoice1.json")
def test_025(self):
""" Document [] getter - index out of range """
document = Document("files/4page.pdf", "./")
self.assertEqual(document[4], None)
for i in range(1, 5):
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".json")
def test_077(self):
""" Document - French Scanned PDF """
document = Document("files/french-scan.pdf", "./")
self.assertEquals(document.lang, 'fr')
self.assertEquals(document.scanned, (False, 0))
for i in range(1, 9):
os.remove("french-scan" + str(i) + ".pdf")
os.remove("french-scan" + str(i) + ".txt")
os.remove("french-scan" + str(i) + ".json")
def test_075(self):
""" Document - Spanish PDF """
document = Document("files/spanish.pdf", "./")
self.assertEquals(document.lang, 'es')
self.assertEquals(len(document), 2)
for i in range(1, 3):
os.remove("spanish" + str(i) + ".pdf")
os.remove("spanish" + str(i) + ".txt")
os.remove("spanish" + str(i) + ".json")
def test_076(self):
""" Document - French PDF """
document = Document("files/french.pdf", "./")
self.assertEquals(document.lang, 'fr')
self.assertEquals(len(document), 2)
for i in range(1, 3):
os.remove("french" + str(i) + ".pdf")
os.remove("french" + str(i) + ".txt")
os.remove("french" + str(i) + ".json")
def test_054(self):
""" bag of words / freqDist """
document = Document("files/4page.pdf", "./")
self.assertTrue(document.bagOfWords != None)
self.assertTrue(document.freqDist != None)
for i in range(1, 5):
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".json")
def test_013(self):
""" Document constructor - create page directory """
document = Document("files/4page.pdf", "tests2")
self.assertTrue(os.path.isdir("tests2"))
for i in range(1, 5):
os.remove("tests2/4page" + str(i) + ".pdf")
os.remove("tests2/4page" + str(i) + ".txt")
os.remove("tests2/4page" + str(i) + ".json")
os.removedirs("tests2")
def test_071(self):
""" config - spell checker - norvig """
with open("spell.txt", "w") as f:
f.write("mispell speling similiar")
Document.WORDDICT = 'norvig'
document = Document('spell.txt')
page = document[0]
os.remove('spell.txt')
os.remove('spell1.txt')
os.remove('spell1.json')
def test_041(self):
""" Document - invoice PDF """
document = Document("files/invoice.pdf", "./")
self.assertEqual(len(document), 1)
self.assertTrue(os.path.isfile("invoice1.txt"))
self.assertTrue(os.path.isfile("invoice1.pdf"))
self.assertTrue(os.path.isfile("invoice1.json"))
os.remove("invoice1.txt")
os.remove("invoice1.pdf")
os.remove("invoice1.json")
def test_059(self):
""" config has multiple entries """
document = Document("files/4page.pdf",
"./",
config=['bare', 'pos', 'roman'])
self.assertTrue(document.bagOfWords != None)
for i in range(1, 5):
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".json")
def test_040(self):
""" Document - color PDF with overlay """
document = Document("files/5page.pdf", "./")
self.assertEqual(len(document), 5)
for i in range(1, 6):
self.assertTrue(os.path.isfile("5page" + str(i) + ".txt"))
self.assertTrue(os.path.isfile("5page" + str(i) + ".json"))
for i in range(1, 6):
os.remove("5page" + str(i) + ".txt")
os.remove("5page" + str(i) + ".pdf")
os.remove("5page" + str(i) + ".json")
def test_065(self):
""" config segment txt """
document = Document('files/segment_para.txt', './', config=['segment'])
self.assertEquals(document[0].size, 91)
self.assertEquals(
document[0].text,
'This is a first paragraph\nand continues to next line.\n\nThen this is the second\nparagraph.'
)
self.assertEquals(len(document[0].words), 2)
os.remove('segment_para1.txt')
os.remove('segment_para1.json')
def test_022(self):
""" Document text getter - PDF file """
document = Document("files/4page.pdf", "./")
self.assertEqual(document.text[0].strip()[0:6], "TIER 1")
self.assertEqual(document.text[1].strip()[0:15], "COVERED MEDICAL")
self.assertEqual(document.text[2].strip()[0:14], "Emergency mean")
self.assertEqual(document.text[3].strip()[0:15], "Maximum Benefit")
for i in range(1, 5):
os.remove("4page" + str(i) + ".pdf")
os.remove("4page" + str(i) + ".txt")
os.remove("4page" + str(i) + ".json")
def test_005(self):
""" Document Constructor - document = valid text document """
document = Document("test.txt")
self.assertEqual(document.document, "test.txt")
self.assertEqual(document.name, "test")
self.assertEqual(len(document), 1)
self.assertEqual(document.text, ["foo"])
self.assertTrue(os.path.isfile("test1.txt"))
self.assertTrue(os.path.isfile("test1.json"))
os.remove("test1.txt")
os.remove("test1.json")
