def __call__(self, i_url):
for url, m in i_url:
if url.startswith('http') and regex.match(self.http_regex, url):
path = f"{config.hidden_folder}/pdfs/{urllib.parse.quote_plus(url)}.pdf"
path = path.replace("(", "")
path = path.replace(")", "")
if not os.path.exists(path):
os.system(f"chromium --headless \
--disable-gpu \
--disable-translate \
--disable-extensions \
--disable-background-networking \
--safebrowsing-disable-auto-update \
--disable-sync \
--metrics-recording-only \
--disable-default-apps \
--no-first-run \
--mute-audio \
--hide-scrollbars \
--disable-software-rasterizer "
f"--print-to-pdf={path} {url}")
yield path, m
elif os.path.exists(url) and regex.match(self.file_regex, url) is not None:
yield url, m
else:
logging.error(f"{url} is not a valid url/path")
def get_suffix_and_law_name(self, string: str):
"""
Returns: A tuple containing length of
1. the article between numbers and law name (eg. " der ")
2. length of name of law as in the given string
3. The type of the reference.
If not found lengths are 0.
"""
suffix_match = regex.match(r"^,?\s+?de[sr]\s+", string)
if suffix_match:
suffix_len = suffix_match.end()
law_test = string[suffix_len:suffix_len + 1000]
dict_suffix_len = self.get_dict_law_name_len(law_test)
if dict_suffix_len:
return suffix_len, dict_suffix_len, "dict"
sgb_suffix_len = self.get_sgb_law_name_len(law_test)
if sgb_suffix_len:
return suffix_len, sgb_suffix_len, "sgb"
eu_suffix_len = self.get_eu_law_name_len(law_test)
if eu_suffix_len:
return suffix_len, eu_suffix_len, "eu"
ignore_suffix_len = self.get_ignore_law_name_len(law_test)
if ignore_suffix_len:
return suffix_len, ignore_suffix_len, "ignore"
return suffix_len, 0, "unknown"
else: # no der/des suffix
suffix_match = regex.match(r"^[\s\n]+", string[:1000])
if suffix_match:
suffix_len = len(suffix_match[0])
law_test = string[suffix_len:1000]
dict_suffix_len = self.get_dict_law_name_len(law_test)
if dict_suffix_len:
return suffix_len, dict_suffix_len, "dict"
sgb_suffix_len = self.get_sgb_law_name_len(law_test)
if sgb_suffix_len:
return suffix_len, sgb_suffix_len, "sgb"
ignore_no_suffix_len = self.get_no_suffix_ignore_law_name_len(
law_test)
if ignore_no_suffix_len:
return suffix_len, ignore_no_suffix_len, "ignore"
return 0, 0, "internal"
def extract_abp(content):
"""Extracts blocked and unblocked domains from ABP style content."""
pattern_unsupported = re.compile(r"\S+(?>\/|\=)\S+", re.V1)
pattern_supported_block = re.compile(
r"^\|\|.+\^(?>$|.+(?:"
r"\bfirst-party\b|"
r"\b1p\b|"
r"\bthird-party\b|"
r"\b3p\b|"
r"\bdocument\b|"
r"\ball\b"
# r"\ball\b|"
# r"\bpopup\b"
r"))",
re.V1,
)
pattern_scrub_blocked_list = [
r"^\|\|",
r"\^($|.+(?>"
r"\bfirst-party\b|"
r"\b1p\b|"
r"\bthird-party\b|"
r"\b3p\b|\bdocument\b|"
r"\ball\b|"
r"\bpopup\b|"
r"\S+))",
]
pattern_scrub_blocked = re.compile(
"|".join(f"(?:{p})" for p in pattern_scrub_blocked_list), re.V1
)
block_rules = [
x
for x in content
if re.match(pattern_supported_block, x, concurrent=True)
and not re.match(pattern_unsupported, x, concurrent=True)
]
blocked_domains = [
re.sub(pattern_scrub_blocked, "", x, concurrent=True) for x in block_rules
]
blocked_domains = [x for x in blocked_domains if valid_domain(x)]
pattern_supported_unblock = re.compile(r"@@\|\|.+\^$")
unblock_rules = [
x
for x in content
if re.match(pattern_supported_unblock, x, concurrent=True)
and not re.match(pattern_unsupported, x, concurrent=True)
]
unblocked_domains = [
x.replace("@@||", "").replace("^", "").replace("$important", "")
for x in unblock_rules
]
regex_rules = []
return blocked_domains, unblocked_domains, unblock_rules, regex_rules
def find_references(soup, pattern, attrs):
"""
Finds the references in the soup and marks them a tag
"""
logs = [] # For debug
text_tags = list(soup.find_all("text"))
for text_tag in text_tags:
for text_tag_string in list(text_tag.contents):
if type(text_tag_string) is not bs4.element.NavigableString:
continue
tag_cursor = text_tag_string
last_match_end = 0
matches = pattern.finditer(text_tag_string)
for match in list(matches):
if regex.match(r"\s?,?of\b", text_tag_string[match.end():]):
continue
ref_tag = soup.new_tag("reference", **attrs)
pre_text, ref_tag, post_text = add_tag(text_tag_string,
match.start(),
match.end(), ref_tag)
pre_text = pre_text[last_match_end:]
last_match_end = match.end()
tag_cursor.replace_with(ref_tag)
ref_tag.insert_before(pre_text)
ref_tag.insert_after(post_text)
tag_cursor = post_text
logs.append(f"{post_text[:50]} --- {match[0]}") # For debug
return logs # For debug
def worker_unmatched_item(item, pattern):
"""Worker for remove_redundant via ThreadPoolExecutor
to get unmatched subdomains from subdomains.
"""
if not re.match(pattern, item, concurrent=True):
return item
return None
async def show(self, ctx, url):
result = regex.match(self.URL_REGEX, url)
if result:
url = result.group(0)
else:
raise commands.BadArgument("Invalid Instagram URL.")
await self.show_media(ctx, url)
def extract_rules(content):
pattern_supported_block = re.compile(r"^\|\|.+(\^|\^\$important)$")
block_rules = [
x for x in content
if re.match(pattern_supported_block, x, concurrent=True)
]
pattern_supported_unblock = re.compile(r"^@@.+(\^(\$important)?|\/)$")
unblock_rules = [
x for x in content
if re.match(pattern_supported_unblock, x, concurrent=True)
]
pattern_supported_regex = re.compile(r"^\/.*\/$")
regex_rules = [
x for x in content
if re.match(pattern_supported_regex, x, concurrent=True)
]
return block_rules, unblock_rules, regex_rules
def extract_regex(content):
"""
Extracts regex rules within two '/'.
"""
pattern_if_regexp = re.compile(r"^\/.*\/$", re.V1)
regex_rules = [
x for x in content if re.match(pattern_if_regexp, x, concurrent=True)
]
return regex_rules
def check_boxes(text_box: str, pattern: str):
"""
Used for Validation of REGEX Text.
:param text_box: Plain Text to validate.
:param pattern: Regex Pattern for validation.
:return: True if test_box is valid.
"""
return regex.match(pattern, text_box)
def is_valid(self) -> bool:
"""
:return Whether this variable has valid properties in order for it to work properly with the
Terraform API.
"""
key_pattern = r"^[a-zA-Z0-9_-]+$"
key_valid = regex.match(key_pattern, self.key) is not None
category_valid = self.category in ["terraform", "env"]
return key_valid and category_valid
def _extract_timestamps(video_id, content, word_to_extract):
logger.info(
f"Extract timestamps where the word {word_to_extract} is pronounced",
prefix=f"{video_id} >> ")
pattern = r"<(\d{2}:\d{2}:\d{2}.\d{3})>([^<]+)<(\d{2}:\d{2}:\d{2}.\d{3})>"
res = [(start, word.lower().strip(), end) for start, word, end in
regex.findall(pattern, content, overlapped=True)
if regex.match(word_to_extract,
word.lower().strip())]
logger.debug(f"Extracted {len(res)} words")
return res
def concat_category(out_file):
"""Concatenate category README.md files"""
files = glob(f"{DirPath.input}/*/*.md")
files = sorted(files, key=lambda x: x)
files = sorted(files, key=lambda x: x.__contains__("regional"))
files = sorted(files, key=lambda x: x.__contains__("main"), reverse=True)
for file in files:
with open(file, encoding="utf-8") as file_input:
with open(out_file, "a", encoding="utf-8") as file_output:
lines = (re.sub(r"^#", r"##", x)
if re.match(r"^#{0,6}+\s", x) else x
for x in file_input)
file_output.writelines(lines)
def bills():
data_dir = '../../lab1/data'
for directory in os.listdir(data_dir):
if directory.endswith('txt'):
# print("directory: " + directory)
bill = open(os.path.join(data_dir, directory), encoding='UTF-8').read()
text = regex.sub(r"[ \t\r\f\v ][ \t\r\f\v ]+", "", bill)
# print(text[:400])
r = regex.match(
r'\s*(Dz\.U\.\s*z\s*(?P<journal_year>\d+)\s*r\.\s*(N|n)r\s*(?P<journal_number>\d+),?\s*?poz.\s*(?P<position>\d+).?\s*)?([a-żA-Ż \d\.\(\)]*\s?){0,4}\s*(ustawa|USTAWA|U S T A W A|Ustawa|ustawA|USTAWa)[^\n]*\n[^\n]*\s*z\s*dnia\s*\d{1,2}\s*[a-żA-Ź]*\s*(?P<year>\d{4})\s*r\.\s*(?P<title>[\s\S]*?)\n\s*(Rozdział\s*(1|I)|Art.\s*(1|l)[^\d]|TYTUŁ\s*I|Dział\s*I|część\s*ogólna)',
text)
if r is None:
yield bill, "", "", "", "f"
else:
yield bill, r.group("title"), r.group("journal_year"), r.group("position"), directory.split('.')[0]
# print("directory: " + directory)
yield open(os.path.join(data_dir, directory), encoding='UTF-8').read()
if __name__ == '__main__':
b = {}
for year in range(1900, 2500):
b[str(year)] = {}
for bill in bills():
text = regex.sub(r"[ \t\r\f\v ][ \t\r\f\v ]+", "", bill)
# print(text[:400])
r = regex.match(r'\s*(Dz\.U\.\s*z\s*(?P<journal_year>\d+)\s*r\.\s*(N|n)r\s*(?P<journal_number>\d+),?\s*?poz.\s*(?P<position>\d+).?\s*)?([a-żA-Ż \d\.\(\)]*\s?){0,4}\s*(ustawa|USTAWA|U S T A W A|Ustawa|ustawA|USTAWa)[^\n]*\n[^\n]*\s*z\s*dnia\s*\d{1,2}\s*[a-żA-Ź]*\s*(?P<year>\d{4})\s*r\.\s*(?P<title>[\s\S]*?)\n\s*(Rozdział\s*(1|I)|Art.\s*(1|l)[^\d]|TYTUŁ\s*I|Dział\s*I|część\s*ogólna)', text)
# r = regex.match(r'\n*(Dz\.U\.z(?P<journal_year>\d+)r\.(N|n)r(?P<journal_number>\d+),?poz.(?P<position>\d+).?)?([a-żA-Ż\d\.\(\)]*\n?){0,4}\n*(ustawa|USTAWA|Ustawa|ustawA|USTAWa)[^\n]*\n[^\n]*\n*z\n?dnia\n?\d{1,2}\n?[a-żA-Ź]*\n?(?P<year>\d{4})\n?r\.\n*(?P<title>(.+\n)*?)\n*?(?P<title2>(.+\n)*?)\n*?(Rozdział(1|I)|Art.\n?(1|l)[^\d]|TYTUŁI|DziałI|częśćogólna)', text)
# print(title.group())
position = r.group("position")
year = r.group("journal_year") or r.group("year")
b[year][position] = {}
b[year][position]["counter"] = 0
b[year][position]["title"] = r.group("title")
b[year][position]["journal_number"] = r.group("journal_number")
b[year][position]["journal_year"] = r.group("journal_year")
b[year][position]["year"] = r.group("year")
b[year][position]["position"] = position
counter = 0
