hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-03-10 12:04:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added command line (default 0) min argument for minimum filtering, updated args.py to reflect this

Browse Source
This commit is contained in:
anqixxx
2025-05-29 09:25:08 -07:00
parent 8d0e767826
commit 40d5b78eb8
3 changed files with 11 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/nominatim_db/clicmd/args.py
View File

@@ -136,6 +136,7 @@ class NominatimArgs:
import_from_wiki: bool import_from_wiki: bool
import_from_csv: Optional[str] import_from_csv: Optional[str]
no_replace: bool no_replace: bool
min: int
# Arguments to all query functions # Arguments to all query functions
format: str format: str

6
src/nominatim_db/clicmd/special_phrases.py
View File

@@ -58,6 +58,8 @@ class ImportSpecialPhrases:
help='Import special phrases from a CSV file') help='Import special phrases from a CSV file')
group.add_argument('--no-replace', action='store_true', group.add_argument('--no-replace', action='store_true',
help='Keep the old phrases and only add the new ones') help='Keep the old phrases and only add the new ones')
group.add_argument('--min', type=int, default=0,
help='Restrict special phrases by minimum occurance')
def run(self, args: NominatimArgs) -> int: def run(self, args: NominatimArgs) -> int:
@@ -82,7 +84,9 @@ class ImportSpecialPhrases:
tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config) tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config)
should_replace = not args.no_replace should_replace = not args.no_replace
min = args.min
with connect(args.config.get_libpq_dsn()) as db_connection: with connect(args.config.get_libpq_dsn()) as db_connection:
SPImporter( SPImporter(
args.config, db_connection, loader args.config, db_connection, loader
).import_phrases(tokenizer, should_replace) ).import_phrases(tokenizer, should_replace, min)

9
src/nominatim_db/tools/special_phrases/sp_importer.py
View File

@@ -87,7 +87,7 @@ class SPImporter():
return db_combinations return db_combinations
def import_phrases(self, tokenizer: AbstractTokenizer, should_replace: bool) -> None: def import_phrases(self, tokenizer: AbstractTokenizer, should_replace: bool, min: int) -> None:
""" """
Iterate through all SpecialPhrases extracted from the Iterate through all SpecialPhrases extracted from the
loader and import them into the database. loader and import them into the database.
@@ -107,7 +107,7 @@ class SPImporter():
if result: if result:
class_type_pairs.add(result) class_type_pairs.add(result)
self._create_classtype_table_and_indexes(class_type_pairs) self._create_classtype_table_and_indexes(class_type_pairs, min)
if should_replace: if should_replace:
self._remove_non_existent_tables_from_db() self._remove_non_existent_tables_from_db()
@@ -186,7 +186,8 @@ class SPImporter():
return (phrase.p_class, phrase.p_type) return (phrase.p_class, phrase.p_type)
def _create_classtype_table_and_indexes(self, def _create_classtype_table_and_indexes(self,
class_type_pairs: Iterable[Tuple[str, str]]) -> None: class_type_pairs: Iterable[Tuple[str, str]],
min: int) -> None:
""" """
Create table place_classtype for each given pair. Create table place_classtype for each given pair.
Also create indexes on place_id and centroid. Also create indexes on place_id and centroid.
@@ -200,7 +201,7 @@ class SPImporter():
with self.db_connection.cursor() as db_cursor: with self.db_connection.cursor() as db_cursor:
db_cursor.execute("CREATE INDEX idx_placex_classtype ON placex (class, type)") db_cursor.execute("CREATE INDEX idx_placex_classtype ON placex (class, type)")
allowed_special_phrases = self.get_classtype_pairs() allowed_special_phrases = self.get_classtype_pairs(min)
for pair in class_type_pairs: for pair in class_type_pairs:
phrase_class = pair[0] phrase_class = pair[0]