def test_illegal_urls(self):
self.assertRaises(TypeError, helper.is_empty_string, None)
self.assertRaises(TypeError, helper.is_empty_string, {})
self.assertRaises(TypeError, helper.is_empty_string, 42)
self.assertRaises(TypeError, helper.is_empty_string, [])
self.assertFalse(helper.is_url(""), "Empty string")
self.assertFalse(helper.is_url("42"), "Unrecognized URL")
self.assertFalse(helper.is_url("www.example.com"), "Missing protocol")
def test_illegal_urls(self):
self.assertRaises(TypeError, helper.is_empty_string, None)
self.assertRaises(TypeError, helper.is_empty_string, {})
self.assertRaises(TypeError, helper.is_empty_string, 42)
self.assertRaises(TypeError, helper.is_empty_string, [])
self.assertFalse(helper.is_url(""), "Empty string")
self.assertFalse(helper.is_url("42"), "Unrecognized URL")
self.assertFalse(helper.is_url("www.example.com"), "Missing protocol")
def _by_pdfplumber(stream: Union[str, object]) -> Union[None, object]:
'''
take url, local path, or BtyeIO objectas input
return a pdfplumber object
'''
if isinstance(stream, str) and is_url(stream):
with _byte_obj_from_url(stream) as byte_obj:
yield pdfplumber.open(byte_obj)
else:
yield pdfplumber.open(stream)
def byte_obj_from_url(url: str) -> object:
'''
get byteIO object from url
'''
from io import BytesIO
import requests
if not is_url(url):
return None
response = requests.get(url)
response.raise_for_status()
return BytesIO(response.content)
def _byte_obj_from_url(url: str) -> object:
'''
get byteIO object from url
'''
if is_url(url) is None:
raise ValueError('Invalid url.')
with requests.get(url) as response:
response.raise_for_status()
byte_obj = BytesIO(response.content)
yield byte_obj
byte_obj.close()
def by_pypdf(stream: Union[str, object]) -> Union[None, object]:
'''
take url, local path, or BtyeIO objectas input
return a pypdf2 object
'''
import PyPDF2, os
if isinstance(stream, str):
if is_url(stream):
stream = byte_obj_from_url(stream)
elif os.path.isfile(stream):
# with as f:
stream = open(stream, 'rb')
return PyPDF2.PdfFileReader(stream, strict=False)
def by_pdfplumber(stream: Union[str, object]) -> Union[None, object]:
'''
take url, local path, or BtyeIO objectas input
return a pdfplumber object
'''
import pdfplumber
import os
if isinstance(stream, str):
if is_url(stream):
stream = byte_obj_from_url(stream)
elif os.path.isfile(stream):
return pdfplumber.open(stream)
else:
logging.critical(f'Invaild url or local path.')
return pdfplumber.open(stream)
def _by_pypdf(stream: Union[str, object]) -> Union[None, object]:
'''
take url, local path, or BtyeIO objectas input
return a pypdf2 object
'''
if isinstance(stream, str):
if is_url(stream):
with byte_obj_from_url(stream) as byte_obj:
yield PyPDF2.PdfFileReader(byte_obj, strict=False)
# byte_obj.close()
elif os.path.isfile(stream):
with open(stream, 'rb') as file_obj:
yield PyPDF2.PdfFileReader(file_obj, strict=False)
# file_obj.close()
else:
yield PyPDF2.PdfFileReader(stream, strict=False)
def is_project_repository(url):
"""Validates the specified project repository URL.
Args:
url (string): A URL to validate.
Returns:
<bool, str|None>: A pair containing the value True if the specified URL
is valid, False otherwise; and an error message in case the URL is invalid.
"""
try:
ERROR_MESSAGE = "A repository configuration must be a valid URL and include the URL protocol."
return (True, None) if is_url(url) else (False, ERROR_MESSAGE)
except TypeError:
# The is_empty_string function will raise a TypeError if the url argument is not a string.
# If the argument is not a string, it stands to reason that it's not a valid URL.
return (False, "The 'url' argument must be a string.")
def is_project_repository(url):
"""Validates the specified project repository URL.
Args:
url (string): A URL to validate.
Returns:
<bool, str|None>: A pair containing the value True if the specified URL
is valid, False otherwise; and an error message in case the URL is invalid.
"""
try:
ERROR_MESSAGE = "A repository configuration must be a valid URL and include the URL protocol."
return (True, None) if is_url(url) else (False, ERROR_MESSAGE)
except TypeError:
# The is_empty_string function will raise a TypeError if the url argument is not a string.
# If the argument is not a string, it stands to reason that it's not a valid URL.
return (False, "The 'url' argument must be a string.")
def __init__(self,
stream,
company=None,
stock_num=None,
release_date=None,
report_title=None):
logging.warning(f'Initialising {type(self).__name__}("{stream}")')
self.url = stream if is_url(stream) else stream
self.pdf_obj = byte_obj_from_url(self.url) or stream
self.toc = self._toc()
self.auditor = self.valid_auditor() or self.raw_auditor()
self.report_title = report_title
self.company = company
self.stock_num = int(stock_num)
self.audit_fee = self._audit_fee()
self.release_date = str_to_date(release_date,
str_time_pattern='%d/%m/%Y %H:%M',
format_pattern='%d %b %Y')
def set_buttons(self, enable=True):
if enable:
self.cancel_btn.Enable()
self.browse_btn.Enable()
self.filename_text.Enable()
else:
self.cancel_btn.Disable()
self.browse_btn.Disable()
self.filename_text.Disable()
if enable and self.ok:
self.ok_btn.Enable()
else:
self.ok_btn.Disable()
if enable and helper.is_url(self.url_text.GetValue().strip()):
self.retrieve_btn.Enable()
else:
self.retrieve_btn.Disable()
def test_valid_urls(self):
self.assertTrue(helper.is_url("http://www.example.com"), "Simple URL")
self.assertTrue(
helper.is_url(
"https://github.com/geotagx/geotagx-tool-sanitizer.git"),
"Github repository URL")
def test_valid_urls(self):
self.assertTrue(helper.is_url("http://www.example.com"), "Simple URL")
self.assertTrue(helper.is_url("https://github.com/geotagx/geotagx-tool-sanitizer.git"), "Github repository URL")
def on_url_change(self, event):
self.ok = False
if helper.is_url(self.url_text.GetValue().strip()):
self.retrieve_btn.Enable()
else:
self.retrieve_btn.Disable()