def get_tika_content(d, a):
"""Call TIKA api for rmeta content.
Calls the rmeta api from TIKA which extracts file metadata
and content.
Input:
d: Mayan document API output
a: Mayan authorization
Output:
c: Dictionary of document metadata and content
"""
down_url = d['latest_version']['download_url']
pages = get_resp(d['latest_version']['pages_url'], a)['results']
try:
page_no = get_page_num(pages[0])
except:
page_no = 0
f = get_resp(down_url, a, True)
try:
c = remove_key_periods(unpack.from_buffer(f))
c['page_no'] = page_no
c['uuid'] = d['uuid']
c['checksum'] = d['latest_version']['checksum']
c['success'] = 1
except:
c = dict()
c['page_no'] = 0
c['uuid'] = d['uuid']
c['checksum'] = d['latest_version']['checksum']
c['success'] = 0
return (c, f)
def test_unpack_pdf_from_buffer(self):
pfile = os.path.join(os.path.dirname(__file__), 'files', 'rwservlet.pdf')
with open(pfile, 'rb') as fp:
buffer = fp.read()
unpacked = unpack.from_buffer(buffer)
self.assertIn("On the $5 menu, the consumer advisory is missing for eggs",unpacked['content'])
self.assertTrue(unpacked['metadata'])
self.assertFalse(unpacked['attachments'])
def get_tika_content_stream(f):
"""Call TIKA api for rmeta content.
Calls the rmeta api from TIKA which extracts file metadata
and content.
Input:
f: file stream
Output:
c: Dictionary of document metadata and content
"""
try:
c = remove_key_periods(unpack.from_buffer(f))
c['success'] = 1
except:
c = dict()
c['success'] = 0
return c
def test_ascii_frombuffer(self):
parsed = unpack.from_buffer(self.text_ascii)
self.assertEqual(parsed["content"].strip(), self.text_ascii)
def test_utf8_frombuffer(self):
parsed = unpack.from_buffer(self.text_utf8.encode('utf8'))
self.assertEqual(parsed["content"].strip(), self.text_utf8)