def text(self):
"""
Extract the raw plain text.
Returns:
str: The text content.
"""
ft = self.libmagic_file_type
# Empty:
if ft == 'inode/x-empty':
return None
# Plaintext:
elif ft == 'text/plain':
with open(self.path, 'r') as fh:
return fh.read()
# HTML/XML:
elif ft == 'text/html':
return utils.html_text(self.path)
# PDF:
elif ft == 'application/pdf':
return utils.pdf_text(self.path)
# Everything else:
else:
return utils.docx_text(self.path)
def text(self):
"""
Extract the raw plain text.
Returns:
str: The text content.
"""
ft = self.libmagic_file_type
# Empty:
if ft == 'inode/x-empty':
return None
# Plaintext:
elif ft == 'text/plain':
with open(self.path, 'r') as fh:
return fh.read()
# HTML/XML:
elif ft == 'text/html':
return utils.html_text(self.path)
# PDF:
elif ft == 'application/pdf':
return utils.pdf_text(self.path)
# Everything else:
else:
return utils.docx_text(self.path)
def test_extract_text(mock_osp):
"""
Text should be extracted via Tika.
"""
# Create a .docx.
path = mock_osp.add_file(content='text', ftype='docx')
# Should extract the text.
text = docx_text(path).strip()
assert text == 'text'
