tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[phrases] additions to venue names dictionaries and a more restrictive version of street types dictionaries

Browse Source
This commit is contained in:
Al
2016-11-19 02:58:27 -05:00
parent 71be0fdfbc
commit 5140db536a
1 changed files with 21 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
scripts/geodata/address_expansions/gazetteers.py
View File

@@ -139,7 +139,7 @@ class DictionaryPhraseFilter(PhraseFilter):
for d in data: for d in data:
lang, dictionary, is_canonical, canonical = d.split(six.b('|')) lang, dictionary, is_canonical, canonical = d.split(six.b('|'))
if (bool(int(is_canonical)) or not canonical_only) and (languages is None or lang in languages): if (bool(int(is_canonical)) or not canonical_only) and (languages is None or lang in languages or lang == 'all'):
phrase = phrase if phrase is not None else six.u(' ').join([t_i for t_i, c_i in t]) phrase = phrase if phrase is not None else six.u(' ').join([t_i for t_i, c_i in t])
yield phrase yield phrase
@@ -155,17 +155,20 @@ class DictionaryPhraseFilter(PhraseFilter):
return set(self.gen_phrases(s, canonical_only=canonical_only, languages=languages)) return set(self.gen_phrases(s, canonical_only=canonical_only, languages=languages))
STREET_TYPES_DICTIONARIES = ('street_types', STREET_TYPES_ONLY_DICTIONARIES = ('street_types',
'directionals', 'concatenated_suffixes_separable',
'concatenated_suffixes_separable', 'concatenated_suffixes_inseparable',
'concatenated_suffixes_inseparable', 'concatenated_prefixes_separable',
'concatenated_prefixes_separable', )
'organizations',
'people', STREET_TYPES_DICTIONARIES = STREET_TYPES_ONLY_DICTIONARIES + ('directionals',
'personal_suffixes', 'organizations',
'personal_titles', 'people',
'qualifiers', 'personal_suffixes',
'stopwords',) 'personal_titles',
'qualifiers',
'stopwords',
)
GIVEN_NAME_DICTIONARY = 'given_names' GIVEN_NAME_DICTIONARY = 'given_names'
SURNAME_DICTIONARY = 'surnames' SURNAME_DICTIONARY = 'surnames'
@@ -215,12 +218,17 @@ UNIT_ABBREVIATION_DICTIONARIES = ('level_types_basement',
VENUE_NAME_DICTIONARIES = ('academic_degrees', VENUE_NAME_DICTIONARIES = ('academic_degrees',
'building_types', 'building_types',
'chains',
'company_types', 'company_types',
'directionals',
'given_names',
'organizations', 'organizations',
'people', 'people',
'personal_suffixes', 'personal_suffixes',
'personal_titles', 'personal_titles',
'place_names', 'place_names',
'stopwords',
'surnames',
) )
ALL_ABBREVIATION_DICTIONARIES = STREET_TYPES_DICTIONARIES + \ ALL_ABBREVIATION_DICTIONARIES = STREET_TYPES_DICTIONARIES + \
@@ -239,6 +247,7 @@ def create_gazetteer(*dictionaries):
street_types_gazetteer = create_gazetteer(*STREET_TYPES_DICTIONARIES) street_types_gazetteer = create_gazetteer(*STREET_TYPES_DICTIONARIES)
street_types_only_gazetteer = create_gazetteer(*STREET_TYPES_ONLY_DICTIONARIES)
qualifiers_gazetteer = create_gazetteer(QUALIFIERS_DICTIONARY) qualifiers_gazetteer = create_gazetteer(QUALIFIERS_DICTIONARY)
names_gazetteer = create_gazetteer(*NAME_DICTIONARIES) names_gazetteer = create_gazetteer(*NAME_DICTIONARIES)
chains_gazetteer = create_gazetteer(CHAIN_DICTIONARY) chains_gazetteer = create_gazetteer(CHAIN_DICTIONARY)