def check(self, ctext: T) -> Optional[str]:
logging.debug("Trying PyWhat checker")
returned_regexes = self.id.identify(ctext, api=True)
if len(returned_regexes["Regexes"]) > 0:
matched_regex = returned_regexes["Regexes"][0]["Regex Pattern"]
ret = f'The plaintext is a [yellow]{matched_regex["Name"]}[/yellow]'
human = f'\nI think the plaintext is a [yellow]{matched_regex["Name"]}[/yellow]'
if "Description" in matched_regex and matched_regex["Description"]:
s = matched_regex['Description']
# lowercases first letter so it doesn't look weird
s = f", which is {s[0].lower() + s[1:]}\n"
ret += s
human += s
# if URL is attached, include that too.
if "URL" in matched_regex:
link = matched_regex['URL'] + ctext.replace(' ', '')
ret += f"\nClick here to view in browser [#CAE4F1][link={link}]{link}[/link][/#CAE4F1]\n"
# If greppable mode is on, don't print this
if self.config.verbosity > 0:
# Print with full stop
console.print(human)
return ret
return None
def decode(self, ctext: T) -> Optional[U]:
try:
ctext = re.sub(r"[^\S \n]", " ", ctext, flags=re.UNICODE)
ctext = ctext.replace("\n", " ")
existing_split = self.try_split(ctext.split(" "))
if existing_split is not None:
return existing_split
# Now we try our own grouping
# Remove final bit of whitespace
ctext = ctext.replace(" ", "")
# Split into bytes, and test
return self.try_split([ctext[i : i + 8] for i in range(0, len(ctext), 8)])
# Catch bad octal chars
except ValueError:
return None
def decode(self, ctext: T) -> Optional[U]:
"""
Takes a string written in the 'Standard Galactic Alphabet'
(aka Minecraft Enchanting Table Symbols) and translates it to ASCII text.
"""
logger.trace("Attempting Standard Galactic Alphabet Decoder")
# To avoid complications, only move forward with the decoding if we can
# reasonably assume that the input string is written in the galactic alphabet
galactic_matches = 0
for symbol in self.GALACTIC_DICT.keys():
# These symbols are assumed to be frequent enough in regular
# text to be skipped when counting the matches. All others are counted.
if symbol in ctext and symbol not in ["!", "|"]:
galactic_matches += 1
else:
continue
if galactic_matches == 0:
logger.trace(
"No matching galactic alphabet letters found. Skipping galactic decoder..."
)
return None
logger.trace(f"{galactic_matches} galactic alphabet letters found. ")
result = ""
ctext = (ctext.replace("||",
"|").replace("/", "").replace("¡", "").replace(
" ̣ ", "").replace(" ̇", " x"))
logger.trace(f"Modified string is {ctext}")
# Take out the problematic characters consisting of multiple symbols
for letter in ctext:
if letter in self.GALACTIC_DICT.keys():
# Match every letter of the input to its galactic counterpoint
result += self.GALACTIC_DICT[letter]
else:
# If the current character is not in the defined alphabet,
# just accept it as-is (useful for numbers, punctuation,...)
result += letter
result = result.replace("x ", "x")
# Remove the trailing space (appearing as a leading space)
# from the x that results from the diacritic replacement
logger.trace(f"Decoded string is {result}")
return result
def decode(self, ctext: T) -> Optional[U]:
for src, dst in self.translate.items():
ctext = ctext.replace(src, dst)
return ctext