def parse_ethnicity(wikicode: mwp.wikicode.Wikicode):
wikicode = parse_markup(wikicode)
wikicode_elements = wikicode.filter(forcetype=(Template, Wikilink))
if " and " in wikicode:
wikicode.replace(" and ", ", ")
if not wikicode_elements:
ethnicity = wikicode.strip_code().strip().title()
else:
for wc in wikicode_elements:
if isinstance(wc, Wikilink):
wikicode.replace(wc, wc.title.strip_code().strip())
elif isinstance(wc, Template):
params = tuple(
p
for p in (
p.name.strip_code()
if p.showkey is True
else p.value.strip_code()
for p in wc.params
)
if p != "cat"
)
if len(params) == 1:
wikicode.replace(wc, params[0])
elif "Noble" in params or "noble" in params:
wikicode.replace(wc, "Noble")
else:
wikicode.replace(wc, params)
ethnicity = wikicode.strip_code().strip().title()
if ethnicity == "Skaa, Noble":
ethnicity = "Half-Skaa"
return ethnicity
def parse_residence(wikicode: mwp.wikicode.Wikicode):
wikicode = parse_markup(wikicode)
wikicode_elements = wikicode.filter(forcetype=(Template, Wikilink))
if "<br>" in wikicode:
wikicode.replace("<br>", ", ")
if not wikicode_elements:
residence = wikicode.strip_code().strip()
else:
for wc in wikicode_elements:
if isinstance(wc, Wikilink):
wikicode.replace(wc, wc.title.strip_code().strip().title())
elif isinstance(wc, Template):
params = tuple(
p
for p in (
p.name.strip_code()
if p.showkey is True
else p.value.strip_code()
for p in wc.params
)
if p != "cat"
)
if len(params) == 1:
wikicode.replace(wc, params[0])
else:
wikicode.replace(wc, params)
residence = wikicode.strip_code().strip()
residence = re.sub(r"\s?\([\w\s]+\)", "", residence)
# special cases
if residence.startswith("15 Stranat Place"):
residence = "Elendel"
return residence
def naiveStrip(self, wikiCode:mwparserfromhell.wikicode.Wikicode):
"""removes the code delimiter, keeps the text. Accepts pages and sections in Wikicode format
Arguments:
wikiCode {mwparserfromhell.wikicode.Wikicode} -- wikicode for a page or a section.
"""
return wikiCode.strip_code()
def parse_names(wikicode: mwp.wikicode.Wikicode):
wikicode = parse_markup(wikicode)
for t in wikicode.filter(forcetype=Template):
if len(t.params) == 1:
wikicode.replace(t, t.params[0])
elif len(t.params) > 1:
if "highprince" in t.params[0].lower():
wikicode.replace(t, "{0} of {1}".format(*t.params))
elif "army" in t.params[0].lower():
wikicode.replace(t, "{1} {0}".format(*t.params))
return [
n for n in (n.strip() for n in wikicode.strip_code().split(",")) if n
]
def parse_family(wikicode: mwp.wikicode.Wikicode):
wikicode = parse_markup(wikicode)
links = [
link
for link in wikicode.filter_wikilinks()
if "category" not in link.lower()
]
if not links:
print("unable to find family", wikicode)
return None
elif len(links) == 1:
family = links[0].title.strip_code().strip()
else:
print("unexpected number of wikilinks", wikicode)
for wc in links:
wikicode.replace(wc, wc.title.strip_code().strip())
family = wikicode.strip_code().strip()
return family
def parse_species(wikicode: mwp.wikicode.Wikicode):
spec = species.get(wikicode.strip_code().lower().strip(), None)
if spec is not None and any(s in val.lower() for s in ("spren", "cryptic")):
char_info["subspecies"] = spec
spec = "Spren"
return spec
def parse_nation(wikicode: mwp.wikicode.Wikicode):
return demonyms.get(wikicode.strip_code().lower().strip(), None)
def parse_profession(wikicode: mwp.wikicode.Wikicode):
# todo: parse with simple NLP
return str(wikicode.strip_code().lower().strip())