def segment_string(text: str):
"""
Divides one larger word into segments
:param text:
:return:
"""
base = text.lstrip("-")
# Replace symbols with their unicode names
translated = re.sub(
"[^[:alpha:]\s\-_]", lambda match: human_readable_translate(match.group()), base
)
dash_tokens = re.split("[-_ ]", translated)
segment_tokens = itertools.chain.from_iterable(
[wordsegment.segment(w) for w in dash_tokens]
)
return [sanitize_token(tok) for tok in segment_tokens]
def text(self) -> typing.List[str]:
return list(
itertools.chain.from_iterable(
[wordsegment.segment(name) for name in self.choices]))
def text(self) -> typing.List[str]:
return list(wordsegment.segment(self.name))
def reserved(self) -> Set[Tuple[str, ...]]:
# Steal the keywords list from miniWDL
return {tuple(wordsegment.segment(key)) for key in keywords["1.0"]}