def setUpClass(cls):
cls.text_out = TextOutput(Document(cls.mandarin_pdf))
cls.all_text = []
# see FIXME
for i in range(19):
with open(file_in_test_dir('mandarin_txts', '{0}.txt'.format(i)),
'r',
encoding='utf-8') as f:
cls.all_text.append(f.read())
def test_rawimageoutput(self):
for pdf in self.pdfs:
for mode in self.img_modes:
imgout = RawImageOutput(Document(pdf),
mode,
resolution=74,
scale_before_rotation=True)
for img in page_iterator(imgout, scale_pixel_box=(50, 50)):
pass
def test_extracted_image_properties(self):
for t in self.tests:
iout = PDFImageOutput(Document(t["pdf"]))
with open(t["prop_file"]) as f:
img_props = self.fix_props(json.load(f))
assert type(img_props) == list
i = 0
for imgs in page_iterator(iout):
for img in imgs:
self.assertPropertyDict(img, img_props[i])
i += 1
def test_document_page_iter(self):
doc = Document(self.dmca_pdf)
with self.assertRaises(KeyError):
doc['abc']
with self.assertRaises(IndexError):
doc[-19]
with self.assertRaises(IndexError):
doc[18]
with self.assertRaises(TypeError):
doc[list()]
self.assertEqual([], doc[18:])
def test_document_text_raw(self):
doc = Document(self.mandarin_pdf)
with open(file_in_test_dir('mandarin_first.txt'),
'r',
encoding='utf-8') as fp:
self.assertEqual(doc.text(end=0), fp.read())
def test_document_page_by_label(self):
doc = Document(self.mandarin_pdf)
for i in range(len(doc)):
self.assertEqual(doc[i].index, doc[str(i + 1)].index)
def test_load_pdf_without_xref(self):
doc = Document(self.simple_file)
self.assertEqual(1, len(doc))
def test_load_from_path(self):
doc = Document(self.dmca_pdf)
self.dmca_prop['filename'] = self.dmca_pdf
self._test_doc_properties(doc)
def test_load_from_file_like(self):
with open(self.dmca_pdf, 'rb') as fp:
doc = Document(fp)
self.dmca_prop['filename'] = ''
self._test_doc_properties(doc)
def test_document_page_by_label(self):
doc = Document(self.mandarin_pdf)
with self.subTest("Test get page by labels"):
for i in range(len(doc)):
self.assertEqual(doc[i].index, doc[str(i + 1)].index)
def setUp(self):
super(PageTestCase, self).setUp()
self.doc = Document(self.mandarin_pdf)
def setUp(self):
super(PageTestCase, self).setUp()
Config.text_encoding = 'utf-8'
Config.text_eol = 'unix'
self.doc = Document(self.mandarin_pdf)
def test_load_from_Path_object(self):
doc = Document(Path(self.dmca_pdf))
self.dmca_prop["filename"] = self.dmca_pdf
self._test_doc_properties(doc)
def test_load_from_file_like(self):
with open(self.dmca_pdf, "rb") as fp:
doc = Document(fp)
self.dmca_prop["filename"] = ""
self._test_doc_properties(doc)
def test_document_text_raw(self):
doc = Document(self.mandarin_pdf)
with open(file_in_test_dir("mandarin_first.txt"), "r", encoding="utf-8") as fp:
self.assertEqual(doc.text(end=0), fp.read())