def convert_to_num(token):
if multiplier is not None:
token = TOK.Number(token.txt, multiplier,
all_cases(token),
all_genders(token))
return token
def parse_phrases_1(token_stream):
""" Parse numbers and amounts """
with BIN_Db.get_db() as db:
token = None
try:
# Maintain a one-token lookahead
token = next(token_stream)
while True:
next_token = next(token_stream)
# Logic for numbers that are partially or entirely
# written out in words
def number(tok):
""" If the token denotes a number, return that number - or None """
if tok.txt.lower() == "áttu":
# Do not accept 'áttu' (stem='átta', no kvk) as a number
return None
return match_stem_list(
tok,
MULTIPLIERS,
filter_func=lambda m: m.ordfl in NUMBER_CATEGORIES)
# Check whether we have an initial number word
multiplier = number(token) if token.kind == TOK.WORD else None
# Check for [number] 'hundred|thousand|million|billion'
while (token.kind == TOK.NUMBER or multiplier is not None) \
and next_token.kind == TOK.WORD:
multiplier_next = number(next_token)
def convert_to_num(token):
if multiplier is not None:
token = TOK.Number(token.txt, multiplier,
all_cases(token),
all_genders(token))
return token
if multiplier_next is not None:
# Retain the case of the last multiplier, except
# if it is possessive (eignarfall) and the previous
# token had a case ('hundruðum milljarða' is dative,
# not possessive)
next_case = all_cases(next_token)
next_gender = all_genders(next_token)
if "ef" in next_case:
# We may have something like 'hundruðum milljarða':
# use the case and gender of 'hundruðum', not 'milljarða'
next_case = all_cases(token) or next_case
next_gender = all_genders(token) or next_gender
token = convert_to_num(token)
token = TOK.Number(token.txt + " " + next_token.txt,
token.val[0] * multiplier_next,
next_case, next_gender)
# Eat the multiplier token
next_token = next(token_stream)
elif next_token.txt in AMOUNT_ABBREV:
# Abbreviations for ISK amounts
# For abbreviations, we do not know the case,
# but we try to retain the previous case information if any
token = convert_to_num(token)
token = TOK.Amount(
token.txt + " " + next_token.txt,
"ISK",
token.val[0] *
AMOUNT_ABBREV[next_token.txt], # Number
token.val[1],
token.val[2]) # Cases and gender
next_token = next(token_stream)
else:
# Check for [number] 'percent'
percentage = match_stem_list(next_token, PERCENTAGES)
if percentage is not None:
token = convert_to_num(token)
token = TOK.Percent(
token.txt + " " + next_token.txt, token.val[0],
all_cases(next_token), all_genders(next_token))
# Eat the percentage token
next_token = next(token_stream)
else:
break
multiplier = None
# Check for currency name doublets, for example
# 'danish krona' or 'british pound'
if token.kind == TOK.WORD and next_token.kind == TOK.WORD:
nat = match_stem_list(token, NATIONALITIES)
if nat is not None:
cur = match_stem_list(next_token, CURRENCIES)
if cur is not None:
if (nat, cur) in ISO_CURRENCIES:
# Match: accumulate the possible cases
iso_code = ISO_CURRENCIES[(nat, cur)]
# Filter the possible cases by considering adjectives
# having a strong declination (indefinite form) only
token = TOK.Currency(
token.txt + " " + next_token.txt, iso_code,
all_common_cases(
token, next_token, lambda m:
(m.ordfl == "lo" and "SB" in m.beyging
)), [CURRENCY_GENDERS[cur]])
next_token = next(token_stream)
# Check for composites:
# 'stjórnskipunar- og eftirlitsnefnd'
# 'viðskipta- og iðnaðarráðherra'
# 'marg-ítrekaðri'
if token.kind == TOK.WORD and \
next_token.kind == TOK.PUNCTUATION and next_token.txt == COMPOSITE_HYPHEN:
og_token = next(token_stream)
if og_token.kind != TOK.WORD or (og_token.txt != "og" and
og_token.txt != "eða"):
# Incorrect prediction: make amends and continue
handled = False
if og_token.kind == TOK.WORD:
composite = token.txt + "-" + og_token.txt
if token.txt.lower() in ADJECTIVE_PREFIXES:
# hálf-opinberri, marg-ítrekaðri
token = TOK.Word(composite, [
m for m in og_token.val
if m.ordfl == "lo" or m.ordfl == "ao"
])
next_token = next(token_stream)
handled = True
else:
# Check for Vestur-Þýskaland, Suður-Múlasýsla (which are in BÍN in their entirety)
m = db.meanings(composite)
if m:
# Found composite in BÍN: return it as a single token
token = TOK.Word(composite, m)
next_token = next(token_stream)
handled = True
if not handled:
yield token
# Put a normal hyphen instead of the composite one
token = TOK.Punctuation(HYPHEN)
next_token = og_token
else:
# We have 'viðskipta- og'
final_token = next(token_stream)
if final_token.kind != TOK.WORD:
# Incorrect: unwind
yield token
yield TOK.Punctuation(HYPHEN) # Normal hyphen
token = og_token
next_token = final_token
else:
# We have 'viðskipta- og iðnaðarráðherra'
# Return a single token with the meanings of
# the last word, but an amalgamated token text.
# Note: there is no meaning check for the first
# part of the composition, so it can be an unknown word.
txt = token.txt + "- " + og_token.txt + \
" " + final_token.txt
token = TOK.Word(txt, final_token.val)
next_token = next(token_stream)
# Yield the current token and advance to the lookahead
yield token
token = next_token
except StopIteration:
pass
# Final token (previous lookahead)
if token:
yield token