Print lemma numbers

src/proficiency/database.py

@@ -1,3 +1,4 @@
+import logging
 import sqlite3
 from pathlib import Path
 
@@ -53,11 +54,14 @@ def init_db(
     return conn
 
 
-def create_indexes_then_close(conn: sqlite3.Connection) -> None:
+def create_indexes_then_close(conn: sqlite3.Connection, lemma_lang: str) -> None:
     create_indexes_sql = """
     CREATE INDEX idx_lemmas ON lemmas (lemma);
     CREATE INDEX idx_senses ON senses (lemma_id, pos);
     """
     conn.executescript(create_indexes_sql)
+    if lemma_lang != "":
+        for (lemma_num,) in conn.execute("SELECT count(*) FROM lemmas"):
+            logging.info(f"{lemma_lang}: {lemma_num}")
     conn.commit()
     conn.close()

src/proficiency/extract_dbnary.py

@@ -265,7 +265,7 @@ def create_lemmas_db_from_dbnary(
     if has_morphology and lemma_lang == gloss_lang:
         insert_forms(store, conn, lemma_lang, lemma_ids)
     insert_senses(store, conn, lemma_lang, gloss_lang, lemma_ids)
-    create_indexes_then_close(conn)
+    create_indexes_then_close(conn, lemma_lang)
     return [db_path]
 
 

src/proficiency/extract_kaikki.py

@@ -180,9 +180,9 @@ def create_lemmas_db_from_kaikki(lemma_lang: str, gloss_lang: str) -> list[Path]
                     ]
                     insert_senses(zh_cn_conn, zh_cn_senses, lemma_id, pos, difficulty)
 
-    create_indexes_then_close(conn)
+    create_indexes_then_close(conn, lemma_lang)
     if gloss_lang == "zh":
-        create_indexes_then_close(zh_cn_conn)
+        create_indexes_then_close(zh_cn_conn, "")
     kaikki_json_path.unlink()
     return [db_path, zh_cn_db_path] if gloss_lang == "zh" else [db_path]
 

src/proficiency/extract_kindle_lemmas.py

@@ -87,7 +87,7 @@ def create_kindle_lemmas_db(db_path: Path) -> None:
             en_data = (sense_id, enabled, pos_type, difficulty)
             insert_en_data(conn, lemma, en_data, lemminflect_pos, lemma_ids)
 
-    create_indexes_then_close(conn)
+    create_indexes_then_close(conn, "")
 
 
 def insert_lemma(