From 94eb867119af05639691ec7990dcf2d6a956dd86 Mon Sep 17 00:00:00 2001 From: Helmut Grohne Date: Wed, 24 Apr 2013 20:56:46 +0200 Subject: implement the /compare/pkg1/pkg2 page differently The original version had two major drawbacks: 1) The SQL query used would cause a btree sort, so the time waiting for the first output was rather long. 2) For packages with many equal files, the output would grow with O(n^2). Thanks to the suggestions by Christine Grohne and Klaus Aehlig. The approach now groups files in package1 by their main hash value (sha512). It also does some work SQL was designed to solve manually now. To speed up page generation a new caching table was added identifying which files have corresponding shared files. --- schema.sql | 1 + 1 file changed, 1 insertion(+) (limited to 'schema.sql') diff --git a/schema.sql b/schema.sql index a67c807..e942c7b 100644 --- a/schema.sql +++ b/schema.sql @@ -9,3 +9,4 @@ CREATE INDEX hash_hash_index ON hash (hash); CREATE TABLE sharing (package1 TEXT, package2 TEXT, func1 TEXT, func2 TEXT, files INTEGER, size INTEGER, FOREIGN KEY (package1) REFERENCES package(package) ON DELETE CASCADE, FOREIGN KEY (package2) REFERENCES package(package) ON DELETE CASCADE); CREATE INDEX sharing_insert_index ON sharing (package1, package2, func1, func2); CREATE INDEX sharing_package_index ON sharing (package1); +CREATE TABLE duplicate (cid INTEGER PRIMARY KEY, FOREIGN KEY (cid) REFERENCES content(id) ON DELETE CASCADE); -- cgit v1.2.3