def infer_from_etyma(sense, subjectFilter=False):
etymon, target_instance = (None, None)
if len(sense.etyma) == 1 and sense.etyma[0][0] == sense.lemma:
etymon = sense.etyma[0]
elif (len(sense.etyma) == 2 and
re.search(r'^[a-zA-Z]+$', sense.etyma[0][0]) and
re.search(r'^-[a-z]+$', sense.etyma[1][0])):
suffix = sense.etyma[1][0]
if (deriv_tester.is_neutral_suffix(suffix) or
(suffix in ('-ist', '-ian', '-ful') and sense.wordclass == 'JJ')):
etymon = sense.etyma[0]
if etymon is not None:
# First try to find the exact sense, in case the etymon points to a
# specific sense - see e.g. lam n./3
target_instance = tdb.highest_ranked(lemma=etymon[0],
refentry=etymon[1],
refid=etymon[2],
exact_sense=True)
# ...but if the etymon just points to an entry in general, find that
# entry's main sense
if target_instance is None and not subjectFilter:
target_instance = main_sense_finder.main_sense(lemma=etymon[0],
refentry=etymon[1])
elif target_instance is None and subjectFilter:
main_sense = tdb.highest_ranked(lemma=etymon[0],
refentry=etymon[1],
subjects=sense.subjects)
if main_sense is not None and main_sense.entry_size < 100:
target_instance = main_sense
if target_instance is not None:
# Check if the target is also referenced in the sense's
# cross-references (in case a particular sense is pointed to,
# as in 'nocturning').
for xr in sense.cross_references:
if (xr.lemma == target_instance.lemma and
xr.refentry == target_instance.refentry):
specific_target = tdb.highest_ranked(lemma=xr.lemma,
refentry=xr.refentry,
refid=xr.refid,
exact_sense=True)
if specific_target is not None:
target_instance = specific_target
break
if target_instance is not None and target_instance.thesclass is not None:
if target_instance.wordclass == sense.wordclass:
match = target_instance.thesclass.wordclass_parent()
else:
match = tdb.equivalent_class(target_instance.thesclass, sense.wordclass)
if match is not None:
match.reason_code = 'etym'
match.reason_text = 'Analogy with "%s" in etymology' % etymon[0]
return match
else:
return None
def main_sense(self, **kwargs):
lemma = kwargs.get('lemma')
wordclass = kwargs.get('wordclass', None)
entry_id = kwargs.get('refentry', None)
listed_only = kwargs.get('listed_only', False)
# Work out what the wordclass should be, if it's not been passed
# explicitly
naive_main_sense = None
if wordclass is None:
naive_main_sense = tdb.highest_ranked(lemma=lemma,
refentry=entry_id)
if naive_main_sense is not None:
wordclass = naive_main_sense.wordclass
else:
wordclass = 'NN'
# Find the main sense from the look-up tables
instance = None
try:
instance = MainSense.cache[wordclass][lemma]
except KeyError:
try:
refentry, refid = MainSense.data[wordclass][lemma]
except KeyError:
pass
else:
instance = tdb.highest_ranked(lemma=lemma,
wordclass=wordclass,
refentry=refentry,
refid=refid)
# Store this instance in the cache
MainSense.cache[wordclass][lemma] = instance
# Nix the instance if it's got the wrong refentry value
if (instance is not None and
entry_id is not None and
instance.refentry != entry_id):
instance = None
# Fall back to ThesaurusDB's main_sense algorithm,
# unless the listed_only argument has been passed
if not listed_only:
if instance is None and naive_main_sense is not None:
# Don't bother recalculating if already calculated above
instance = naive_main_sense
elif instance is None:
instance = tdb.highest_ranked(lemma=lemma,
wordclass=wordclass,
refentry=entry_id)
return instance
def attributive_of_noun(sense, main_sense_of_entry):
"""
An attrib. sense of a noun is treated as the adj. equivalent
of the main sense of the entry (or of a particular sense, if referenced)
"""
# Use a particular sense if it's cross-referenced
# Check that it's an internal cross-reference to a main sense
# (hence no lemma)
xrefs = [xr for xr in sense.cross_references if
xr.refentry == sense.entry_id and xr.lemma is None]
if xrefs:
target_sense = tdb.highest_ranked(lemma=sense.lemma,
wordclass='NN',
refentry=xrefs[0].refentry,
refid=xrefs[0].refid)
if target_sense is not None and target_sense.thesclass is not None:
equiv = tdb.equivalent_class(target_sense.thesclass, 'JJ')
equiv.reason_text = 'Adjective equivalent of cross-referenced noun sense'
equiv.reason_code = 'attb'
return equiv
elif target_sense is not None:
return None
# ... otherwise, default to the main sense of the entry
if (main_sense_of_entry is not None and
main_sense_of_entry.thesclass is not None):
equiv = tdb.equivalent_class(main_sense_of_entry.thesclass, 'JJ')
equiv.reason_text = 'Adjective equivalent of main noun sense'
equiv.reason_code = 'attb'
return equiv
else:
return None
def infer_from_neighbouring_wordclass(sense):
match = None
if sense.wordclass in ('JJ', 'VB'):
opposite_class = 'NN'
elif sense.wordclass in ('NN', 'RB'):
opposite_class = 'JJ'
else:
opposite_class = None
if opposite_class is not None:
opposite = tdb.highest_ranked(lemma=sense.lemma,
refentry=sense.entry_id,
wordclass=opposite_class)
if opposite is not None and opposite.thesclass is not None:
match = tdb.equivalent_class(opposite.thesclass, sense.wordclass)
if match is not None:
match.reason_code = 'nbor'
match.reason_text = 'Inferred from neighbouring %s branch' % opposite_class
return match
def affix_subentry(sense):
stem = sense.entry_lemma.strip('-')
if sense.lemma.startswith(stem) and re.search(r'^[a-zA-Z]+$', stem):
ending = re.sub(r'^' + stem, '', sense.lemma)
ending = ending.strip(' -')
if len(ending) < 4:
target_sense = None
elif sense.subjects:
target_sense = tdb.highest_ranked(lemma=ending,
wordclass=sense.wordclass,
subjects=sense.subjects)
else:
target_sense = main_sense_finder.main_sense(lemma=ending,
wordclass=sense.wordclass)
if target_sense is not None and target_sense.thesclass is not None:
match = target_sense.thesclass
match.reason_text = 'Inferred from last element ("%s")' % ending
match.reason_code = 'driv'
return match
return None
def find_branch_from_superordinate(self, sense):
"""Classify by finding the main or only sense of the superordinate
"""
if (sense.wordclass not in ('NN', 'JJ') or
not sense.superordinate or
len(sense.superordinate) < 3 or
sense.superordinate in GENERICS):
return None
target_sense = None
# If the superordinate is (more or less) single-sense, we assume that
# sense to be the correct one
candidates = tdb.ranked_search(
lemma=sense.superordinate,
wordclass='NN',
current_only=True)
if candidates and tdb.distinct_senses(candidates) <= 2:
target_sense = candidates[0]
# Otherwise, narrow by Bayes classification
if target_sense is None and sense.bayes.confidence() >= 8:
target_sense = tdb.highest_ranked(
lemma=sense.superordinate,
wordclass='NN',
branches=sense.bayes_based_classifications,
current_only=True)
# Otherwise, narrow by branches based on subject labels
if target_sense is None and sense.label_based_classifications:
target_sense = tdb.highest_ranked(
lemma=sense.superordinate,
wordclass='NN',
branches=sense.label_based_classifications,
current_only=True)
# Otherwise, narrow by branches based on cross-references
if target_sense is None and sense.xref_branches:
target_sense = tdb.highest_ranked(
lemma=sense.superordinate,
wordclass='NN',
branches=sense.xref_branches,
current_only=True)
# Last gasp: If the gloss consists more or less *only* of the
# superordinate (e.g. 'an abbey'), then it should be adequate to
# just use the main sense of the superordinate, even if it's
# multi-sense.
# But don't risk this is there are cross-references or subject
# labels which might suggest a more specific use
if (target_sense is None and not sense.subjects and
not sense.xref_branches and sense.gloss is not None):
g = re.sub(r'^(a|an|the) ', '', sense.gloss.lower())
if g == sense.superordinate:
target_sense = MAIN_SENSE_FINDER.main_sense(
lemma=sense.superordinate, wordclass='NN')
# Otherwise, narrow by Bayes classification
if target_sense is None and sense.bayes.is_usable():
target_sense = tdb.highest_ranked(
lemma=sense.superordinate,
wordclass='NN',
branches=sense.bayes_based_classifications,
current_only=True)
if target_sense is not None and target_sense.thesclass is not None:
match = target_sense.thesclass
if sense.wordclass == 'JJ':
match = tdb.equivalent_class(match, 'JJ')
return match
else:
return None
def superordinate_lookup(self, sense, panic=False):
"""
Classify by looking up how other senses with the same superordinate
have been classified.
"""
# Get all the branches relevant for this sense's long and/or short
# superordinate.
branches = []
superordinates = [sense.superordinate_full,]
if sense.superordinate != sense.superordinate_full:
superordinates.append(sense.superordinate)
seen = set()
for superordinate in [s for s in superordinates if s is not None]:
superordinate = superordinate.replace('-', '').replace(' ', '')
record = tdb.get_superordinate_record(superordinate)
if record is not None:
for b in record.branches:
if b.thesclass.id not in seen:
branches.append(b)
seen.add(b.thesclass.id)
if branches:
branches_filtered = []
if panic:
branches_filtered = [b for b in branches if b.probability > 0.4]
else:
xref_nodes = set(sense.xref_branches)
branches_filtered = [b for b in branches if
set.intersection(b.thesclass.ancestor_ids(), xref_nodes)]
if not branches_filtered and sense.bayes.confidence() >= 4:
bayes_ids = set(sense.bayes.ids())
branches_filtered = [b for b in branches if
set.intersection(b.thesclass.ancestor_ids(), bayes_ids)]
if not branches_filtered and sense.bayes.confidence() >= 4:
# Try again with the Bayes classifications, but this
# time just use their level-3 parents
bayes_ids = set([b.ancestor(level=3).id for b in
sense.bayes.branches()
if b.ancestor(level=3) is not None])
branches_filtered = [b for b in branches if
set.intersection(
b.thesclass.ancestor_ids(), bayes_ids)]
if branches_filtered:
# Find the best branch below wordclass level, or failing that,
# above wordclass level
wc_branches = [b for b in branches_filtered if
b.thesclass.wordclass is not None] or branches_filtered
wc_branches.sort(key=lambda b: b.probability, reverse=True)
winning_branch = wc_branches[0].thesclass
# If this is a compound, see if we can get more specific
# by finding an instance of the second element within the
# winning branch.
# (Fairly unlikely, since most of these should already
# have been picked off by the compound classifiers.)
if sense.last_element() is not None:
subclass = tdb.highest_ranked(lemma=sense.last_element(),
wordclass=sense.wordclass,
branches=[winning_branch.id,])
if (subclass is not None and
subclass.thesclass is not None):
winning_branch = subclass.thesclass
return winning_branch
return None