summaryrefslogtreecommitdiff
path: root/README
diff options
context:
space:
mode:
Diffstat (limited to 'README')
-rw-r--r--README8
1 files changed, 4 insertions, 4 deletions
diff --git a/README b/README
index bc1b715..55a8eb6 100644
--- a/README
+++ b/README
@@ -30,17 +30,17 @@ SQL database by hand. Here are some example queries.
Finding the 100 largest files shared with multiple packages.
- SELECT a.package, a.filename, b.package, b.filename, a.size FROM content AS a JOIN content AS b ON a.hash = b.hash WHERE (a.package != b.package OR a.filename != b.filename) ORDER BY a.size DESC LIMIT 100;
+ SELECT a.package, a.filename, b.package, b.filename, a.size FROM content AS a JOIN hash AS ha ON a.id = ha.cid JOIN hash AS hb ON ha.hash = hb.hash JOIN content AS b ON b.id = hb.cid WHERE (a.package != b.package OR a.filename != b.filename) ORDER BY a.size DESC LIMIT 100;
Finding those top 100 files that save most space when being reduced to only
one copy in the archive.
- SELECT hash, sum(size)-min(size), count(*), count(distinct package) FROM content GROUP BY hash ORDER BY sum(size)-min(size) DESC LIMIT 100;
+ SELECT hash, sum(size)-min(size), count(*), count(distinct package) FROM content JOIN hash ON content.id = hash.cid WHERE hash.function = "sha512" GROUP BY hash ORDER BY sum(size)-min(size) DESC LIMIT 100;
Finding PNG images that do not carry a .png file extension.
- SELECT package, filename, size FROM content WHERE function = "image_sha512" AND filename NOT LIKE "%.png";
+ SELECT package, filename, size FROM content JOIN hash ON content.id = hash.cid WHERE function = "image_sha512" AND filename NOT LIKE "%.png";
Finding .gz files which either are not gziped or contain errors.
- SELECT package, filename FROM content AS a WHERE function = "sha512" AND filename LIKE "%.gz" AND (SELECT count(*) FROM content AS b WHERE b.package = a.package AND b.filename = a.filename AND b.function = "gzip_sha512") = 0;
+ SELECT a.package, a.filename FROM content AS a JOIN hash AS ha ON a.id = ha.cid WHERE ha.function = "sha512" AND a.filename LIKE "%.gz" AND (SELECT count(*) FROM content AS b JOIN hash AS hb ON b.id = hb.cid WHERE b.package = a.package AND b.filename = a.filename AND hb.function = "gzip_sha512") = 0;