distinct on bigmerge and version bump

bigmerge was leaving duplicated alleles
ACEnglish · Feb 13, 2025 · 3728a16 · 3728a16
1 parent d74c695
commit 3728a16
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/setup.py b/setup.py
@@ -8,7 +8,7 @@ def read(rel_path):
     with codecs.open(os.path.join(here, rel_path), 'r') as fp:
         return fp.read()
 
-VERSION = "0.2.0"
+VERSION = "0.3.0"
 
 setup(
     name="tdb",

diff --git a/tdb/__main__.py b/tdb/__main__.py
@@ -25,7 +25,7 @@
 
 cmd_str = ", ".join(list(CMDS.keys()))
 USAGE = f"""
-tdb v0.2.0 - Tandem repeat database tools
+tdb v0.3.0 - Tandem repeat database tools
 
 Commands: {cmd_str}"""
 

diff --git a/tdb/bigmerge.py b/tdb/bigmerge.py
@@ -335,7 +335,7 @@ def consolidate_allele(con, db_paths, output_dir, compress=False, threads=1):
     alocus = os.path.join(output_dir, "allele.pq")
     query = f"""
     COPY (
-        SELECT *
+        SELECT DISTINCT *
         FROM read_parquet('{base["allele"]}')
         UNION ALL
         SELECT *