Query to show files that have duplicate hashes.

2014-03-20 22:28:15 -07:00 · 2014-03-20 22:28:15 -07:00 · 0701a210db
commit 0701a210db
parent 1b8afaa73f
1 changed files with 17 additions and 0 deletions
--- a/pq/dup.sql
+++ b/pq/dup.sql
@ -0,0 +1,17 @@
+SELECT
+    count(f.path) AS Cnt,
+    f.hash AS Hash,
+    array_agg(distinct i.path) Paths
+FROM
+    files AS f
+INNER JOIN
+    files i
+ON
+    i.hash = f.hash
+GROUP BY
+    f.hash
+HAVING
+    count(f.path)>1
+ORDER BY
+    Cnt DESC
+;