From 40d5b78eb80c1e7479a51d62969a35e8c31ca98a Mon Sep 17 00:00:00 2001
From: anqixxx <anqix2002@gmail.com>
Date: Thu, 29 May 2025 09:25:08 -0700
Subject: [PATCH] Added command line (default 0) min argument for minimum
 filtering, updated args.py to reflect this

---
 src/nominatim_db/clicmd/args.py                       | 1 +
 src/nominatim_db/clicmd/special_phrases.py            | 6 +++++-
 src/nominatim_db/tools/special_phrases/sp_importer.py | 9 +++++----
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/src/nominatim_db/clicmd/args.py b/src/nominatim_db/clicmd/args.py
index 45df9b7c..5c6a806a 100644
--- a/src/nominatim_db/clicmd/args.py
+++ b/src/nominatim_db/clicmd/args.py
@@ -136,6 +136,7 @@ class NominatimArgs:
     import_from_wiki: bool
     import_from_csv: Optional[str]
     no_replace: bool
+    min: int
 
     # Arguments to all query functions
     format: str
diff --git a/src/nominatim_db/clicmd/special_phrases.py b/src/nominatim_db/clicmd/special_phrases.py
index 9ba751a0..90560fb7 100644
--- a/src/nominatim_db/clicmd/special_phrases.py
+++ b/src/nominatim_db/clicmd/special_phrases.py
@@ -58,6 +58,8 @@ class ImportSpecialPhrases:
                            help='Import special phrases from a CSV file')
         group.add_argument('--no-replace', action='store_true',
                            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:
 
@@ -82,7 +84,9 @@ class ImportSpecialPhrases:
 
         tokenizer = tokenizer_factory.get_tokenizer_for_db(args.config)
         should_replace = not args.no_replace
+        min = args.min
+
         with connect(args.config.get_libpq_dsn()) as db_connection:
             SPImporter(
                 args.config, db_connection, loader
-            ).import_phrases(tokenizer, should_replace)
+            ).import_phrases(tokenizer, should_replace, min)
diff --git a/src/nominatim_db/tools/special_phrases/sp_importer.py b/src/nominatim_db/tools/special_phrases/sp_importer.py
index ac50377f..6bd3c287 100644
--- a/src/nominatim_db/tools/special_phrases/sp_importer.py
+++ b/src/nominatim_db/tools/special_phrases/sp_importer.py
@@ -87,7 +87,7 @@ class SPImporter():
 
         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
             loader and import them into the database.
@@ -107,7 +107,7 @@ class SPImporter():
             if 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:
             self._remove_non_existent_tables_from_db()
 
@@ -186,7 +186,8 @@ class SPImporter():
         return (phrase.p_class, phrase.p_type)
 
     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.
             Also create indexes on place_id and centroid.
@@ -200,7 +201,7 @@ class SPImporter():
         with self.db_connection.cursor() as db_cursor:
             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:
             phrase_class = pair[0]
-- 
2.39.5