def train(self):
for category, file in self.to_train:
email = EmailObject(io.open(file, 'rb'))
self.categories.add(category)
for token in Tokenizer.unique_tokenizer(email.body()):
self.training[category][token] += 1
self.totals['_all'] += 1
self.totals[category] += 1
self.to_train = {}
class TestHTMLEmail(unittest.TestCase):
def setUp(self):
self.html_file = io.open('./tests/fixtures/html.eml', 'rb')
self.html = self.html_file.read()
self.html_file.seek(0)
self.html_email = EmailObject(self.html_file)
def test_parses_stores_inner_text_html(self):
body = "\n\n".join(self.html.split("\n\n")[1:])
expected = BeautifulSoup(body).text
self.assertEqual(self.html_email.body(), expected)
def test_stores_subject(self):
subject = re.search("Subject: (.*)", self.html).group(1)
self.assertEqual(self.html_email.subject(), subject)
class TestHTMLEmail(unittest.TestCase):
def setUp(self):
self.html_file = io.open("./tests/fixtures/html.eml", "rb")
self.html = self.html_file.read()
self.html_file.seek(0)
self.html_email = EmailObject(self.html_file)
def test_parses_stores_inner_text_html(self):
body = "\n\n".join(self.html.split("\n\n")[1:])
expected = BeautifulSoup(body).text
self.assertEqual(self.html_email.body(), expected)
def test_stores_subject(self):
subject = re.search("Subject: (.*)", self.html).group(1)
self.assertEqual(self.html_email.subject(), subject)
class TestHTMLEmail(unittest.TestCase):
def setUp(self):
self.html_file = io.open('./tests/fixtures/html.eml', 'rb')
self.html = self.html_file.read()
self.html_file.seek(0)
self.html_email = EmailObject(self.html_file)
self.maxDiff = None
def test_parses_stores_inner_text_html(self):
body = b'\n\n'.join(self.html.split(b'\n\n')[1:])
expected = BeautifulSoup(body, features = 'html.parser').text
self.assertEqual(self.html_email.body(), expected)
def test_stores_subject(self):
subject = re.search('Subject: (.*)', str(self.html)).group(1)
self.assertEqual(str(self.html_email.subject()), subject)
class TestPlaintextEmailObject(unittest.TestCase):
CLRF = "\n\n"
def setUp(self):
self.plain_file = './tests/fixtures/plain.eml'
self.plaintext = io.open(self.plain_file, 'r')
self.text = self.plaintext.read()
self.plaintext.seek(0)
self.plain_email = EmailObject(self.plaintext)
def test_parse_plain_body(self):
body = self.CLRF.join(self.text.split(self.CLRF)[1:])
self.assertEqual(self.plain_email.body(), body)
def test_parses_the_subject(self):
subject = re.search("Subject: (.*)", self.text).group(1)
self.assertEqual(self.plain_email.subject(), subject)
class TestPlaintextEmailObject(unittest.TestCase):
CLRF = "\n\n"
def setUp(self):
self.plain_file = './tests/fixtures/plain.eml'
self.plaintext = io.open(self.plain_file, 'r')
self.text = self.plaintext.read()
self.plaintext.seek(0)
self.plain_email = EmailObject(self.plaintext)
def test_parse_plain_body(self):
body = self.CLRF.join(self.text.split(self.CLRF)[1:])
self.assertEqual(self.plain_email.body(), body)
def test_parses_the_subject(self):
subject = re.search("Subject: (.*)", self.text).group(1)
self.assertEqual(self.plain_email.subject(), subject)
class TestPlaintextEmailObject(unittest.TestCase):
CLRF = b'\\ n'
def setUp(self):
self.plain_file = './tests/fixtures/plain.eml'
self.plaintext = io.open(self.plain_file, 'rb')
self.text = self.plaintext.read()
self.plaintext.seek(0)
self.plain_email = EmailObject(self.plaintext)
self.maxDiff = None
def test_parse_plain_body(self):
body = self.CLRF.join(self.text.split(self.CLRF)[:1])
self.assertEqual(self.plain_email.body(), body)
def test_parses_the_subject(self):
subject = re.search('Subject: (.*)', str(self.text)).group(1)
self.assertEqual(str(self.plain_email.subject()), subject)
class TestHTMLEmail(unittest.TestCase):
def setUp(self):
with io.open('./tests/fixtures/html.eml', 'rb') as html_file:
self.html = html_file.read().decode('utf-8')
html_file.seek(0)
self.html_email = EmailObject(html_file)
def test_parses_stores_inner_text_html(self):
body = "\n\n".join(self.html.split("\n\n")[1:])
expected = BeautifulSoup(body, 'html.parser').text
actual_body = self.html_email.body()
self.assertEqual(actual_body, expected)
def test_stores_subject(self):
expected_subject = re.search("Subject: (.*)", self.html).group(1)
actual_subject = self.html_email.subject()
self.assertEqual(actual_subject, expected_subject)
class TestMultipartEmailObject(unittest.TestCase):
def setUp(self):
self.multipart_file = './tests/fixtures/multipart.eml'
self.multipart = io.open(self.multipart_file, 'r')
self.text = self.multipart.read()
self.multipart.seek(0)
self.multipart_email = EmailObject(self.multipart)
def test_parse_concatenated_body_of_text(self):
internal_mail = self.multipart_email.mail
assert internal_mail.is_multipart()
body = ''
for part in internal_mail.walk():
if re.match("text/plain", part.get_content_type()):
body += part.get_payload(decode=True)
elif re.match("text/html", part.get_content_type()):
body += part.get_payload(decode=True)
self.assertEqual(self.multipart_email.body(), body)
def test_stores_subject(self):
subject = re.search("Subject: (.*)", self.text).group(1)
self.assertEqual(self.multipart_email.subject(), subject)
class TestMultipartEmailObject(unittest.TestCase):
def setUp(self):
self.multipart_file = './tests/fixtures/multipart.eml'
self.multipart = io.open(self.multipart_file, 'r')
self.text = self.multipart.read()
self.multipart.seek(0)
self.multipart_email = EmailObject(self.multipart)
def test_parse_concatenated_body_of_text(self):
internal_mail = self.multipart_email.mail
assert internal_mail.is_multipart()
body = ''
for part in internal_mail.walk():
if re.match("text/plain", part.get_content_type()):
body += part.get_payload(decode=True)
elif re.match("text/html", part.get_content_type()):
body += part.get_payload(decode=True)
self.assertEqual(self.multipart_email.body(), body)
def test_stores_subject(self):
subject = re.search("Subject: (.*)", self.text).group(1)
self.assertEqual(self.multipart_email.subject(), subject)
