def refine_index():
"""
Refine the data build by index_raw_forms(), in particular removing minor
homographs (both lemma-level homographs and wordform-level homographs).
Also swaps in standard lemma forms, main-sense definitions, and
thesaurus links.
"""
# Determine which alien variants are okay to keep (because they don't
# shadow main forms). - Alien types are wordforms which begin with
# a different letter from their parent lemma, and so wouldn't be
# correctly filtered by the main letter-by-letter filtering process.
stdout.write("Filtering alien types...\n")
allowed_alien_types = _filter_alien_types()
stdout.write("...done\n")
# Initialize the resources that will be used for look-ups
vitalstats = VitalStatisticsCache()
main_sense_checker = MainSensesCache(with_definitions=True)
for letter in string.ascii_lowercase:
stdout.write("Refining index for %s...\n" % letter)
blocks = []
for block in _raw_pickle_iterator(letter):
blocks.append(block)
# Remove duplicate types, so that only the version
# in the block with the highest frequency is retained.
# Cluster together typeunits with the same wordform + wordclass
standardmap = defaultdict(lambda: defaultdict(list))
for i, block in enumerate(blocks):
for typeunit in block.standard_types:
standardmap[typeunit.wordform][typeunit.wordclassflat].append((i, typeunit))
# Go through each wordclass-cluster for each wordform, and pick
# the highest-frequency instance in each case
for wordform, wordclasses in standardmap.items():
winners = []
for candidates in wordclasses.values():
# Sort by frequency (highest first)
candidates.sort(key=lambda c: c[1].f2000, reverse=True)
# Remove the first candidate (the highest-frequency one);
# this is the one we'll keep.
winners.append(candidates.pop(0))
# Delete all the rest
for index, typeunit in candidates:
blocks[index].standard_types.discard(typeunit)
# We should now be left with the highest-scoring wordclasses
# for the current wordform (e.g. the highest-frequency
# homograph for spell_VB and the highest-frequency
# homograph for one spell_NN). We now need to decide which
# of these to keep and which to discard
discards = _discardable_homographs(winners)
for index, typeunit in discards:
blocks[index].standard_types.discard(typeunit)
# Remove variant types which either duplicate each other
# or that shadow a standard type. (Standard types are always
# given precedence.)
varmap = defaultdict(list)
for i, block in enumerate(blocks):
for typeunit in block.variant_types:
varmap[typeunit.wordform].append((i, typeunit, block.f2000))
for wordform, candidates in varmap.items():
if wordform not in standardmap:
# Sort by the frequency of the parent lemma
candidates.sort(key=lambda c: c[2], reverse=True)
# Remove the first candidate (the highest-frequency
# one); this is the one we'll keep.
candidates.pop(0)
# Delete all the rest
for index, typeunit, _ in candidates:
blocks[index].variant_types.discard(typeunit)
# Remove any alien types that are not allowed (because they
# shadow other standard types or variants).
for block in blocks:
to_be_deleted = set()
for typeunit in block.alien_types:
if typeunit.wordform not in allowed_alien_types:
to_be_deleted.add(typeunit)
for typeunit in to_be_deleted:
block.alien_types.discard(typeunit)
# Remove any blocks whose standard_types and
# variant_types sets have now been completely emptied
# For the remainder, turn standard_forms and variant_forms
# from sets into lists
blocks = [_listify_forms(b) for b in blocks if b.standard_types or b.variant_types]
blocks_filtered = []
for block in blocks:
language = vitalstats.find(block.refentry, field="indirect_language")
if not language and block.start and block.start < 1200:
language = "West Germanic"
block = _replace_language(block, language)
# Acquire main-sense data for this block (which will be
# used to swap in a new definition and a thesaurus link)
if block.type == "entry":
ms_block_data = main_sense_checker.find_block_data(block.refentry, block.refid)
if ms_block_data and ms_block_data.senses:
main_sense_data = ms_block_data.senses[0]
main_sense_confidence = ms_block_data.confidence()
else:
main_sense_data = None
main_sense_confidence = None
else:
main_sense_data = None
main_sense_confidence = None
# Swap in thesaurus-class link
block = _replace_htclass(block, main_sense_data, main_sense_confidence)
if block.type == "entry":
# Make sure we use the OED headword, not the headword
# that's been used in GEL (which could be the version
# of the headword found in ODE or NOAD).
headword = vitalstats.find(block.refentry, field="headword")
if headword and headword != block.lemma:
block = _replace_lemma(block, headword)
# Make sure we use the best main-sense definition
if main_sense_data and main_sense_data.definition:
block = _replace_definition(block, main_sense_data.definition)
blocks_filtered.append(block)
out_file = os.path.join(FORM_INDEX_DIR, "refined", letter + ".json")
with open(out_file, "w") as filehandle:
for block in blocks_filtered:
filehandle.write(json.dumps(block) + "\n")
def refine_index(self):
allowed_alien_types = _filter_alien_types()
vitalstats = VitalStatisticsCache()
main_sense_checker = MainSensesCache(with_definitions=True)
for letter in string.ascii_lowercase:
print('Refining index for %s...' % letter)
blocks = []
for block in raw_pickle_iterator(letter):
blocks.append(block)
# Remove duplicate types, so that only the version
# in the block with the highest frequency is retained.
standardmap = defaultdict(list)
for i, block in enumerate(blocks):
for wordform in block.standard_types:
standardmap[wordform].append((i, block.frequency))
for wordform, candidates in standardmap.items():
if len(candidates) > 1:
# Sort by frequency
candidates.sort(key=lambda c: c[1], reverse=True)
# Remove the first candidate (the highest-frequency
# one); this is the one we'll keep.
candidates.pop(0)
# Delete all the rest
for index in [c[0] for c in candidates]:
blocks[index].standard_types.discard(wordform)
# Remove variant types which either duplicate each other
# or that shadow a standard type (standard types are always
# given precedence).
varmap = defaultdict(list)
for i, block in enumerate(blocks):
for wordform in block.variant_types:
varmap[wordform].append((i, block.frequency))
for wordform, candidates in varmap.items():
if wordform not in standardmap:
# Sort by frequency
candidates.sort(key=lambda c: c[1], reverse=True)
# Remove the first candidate (the highest-frequency
# one); this is the one we'll keep.
candidates.pop(0)
# Delete all the rest
for index in [c[0] for c in candidates]:
blocks[index].variant_types.discard(wordform)
# Remove any alien types that are not allowed (because they
# shadow other standard types or variants).
for block in blocks:
to_be_deleted = set()
for wordform in block.alien_types:
if wordform not in allowed_alien_types:
to_be_deleted.add(wordform)
for wordform in to_be_deleted:
block.alien_types.discard(wordform)
# Remove any blocks whose standard_types and
# variant_types sets have now been completely emptied
# For the remainder, turn standard_forms and variant_forms
# from sets into lists
blocks = [_listify_forms(b) for b in blocks if b.standard_types
or b.variant_types]
blocks_filtered = []
for block in blocks:
language = vitalstats.find(block.refentry,
field='indirect_language')
if not language and block.start and block.start < 1200:
language = 'West Germanic'
block = _replace_language(block, language)
if block.type == 'entry':
# Make sure we use the OED headword, not the headword
# that's been used in GEL (which could be the version
# of the headword found in ODE or NOAD).
headword = vitalstats.find(block.refentry,
field='headword')
if headword and headword != block.lemma:
block = _replace_lemma(block, headword)
# Make sure we use the correct main-sense definition
main_sense = main_sense_checker.find_main_sense_data(
block.refentry,
block.refid)
if main_sense and main_sense.definition:
block = _replace_definition(block, main_sense.definition)
blocks_filtered.append(block)
out_file = os.path.join(FORM_INDEX_DIR, 'refined', letter + '.json')
with open(out_file, 'w') as filehandle:
for block in blocks_filtered:
filehandle.write(json.dumps(block) + '\n')
