From 750bd6ac350079cf1f76c24acb7686ad89a95102 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nico@cam.org>
Date: Thu, 12 Jul 2007 03:40:18 -0400
Subject: script to display a distribution of longest common hash prefixes
This script was originally posted on the git mailing list by
Randal L. Schwartz <merlyn@stonehenge.com>.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
contrib/stats/git-common-hash | 26 ++++++++++++++++++++++++++
1 file changed, 26 insertions(+)
create mode 100755 contrib/stats/git-common-hash
(limited to 'contrib/stats')
diff --git a/contrib/stats/git-common-hash b/contrib/stats/git-common-hash
new file mode 100755
index 000000000..e27fd088b
--- /dev/null
+++ b/contrib/stats/git-common-hash
@@ -0,0 +1,26 @@
+#!/bin/sh
+
+# This script displays the distribution of longest common hash prefixes.
+# This can be used to determine the minimum prefix length to use
+# for object names to be unique.
+
+git rev-list --objects --all | sort | perl -lne '
+ substr($_, 40) = "";
+ # uncomment next line for a distribution of bits instead of hex chars
+ # $_ = unpack("B*",pack("H*",$_));
+ if (defined $p) {
+ ($p ^ $_) =~ /^(\0*)/;
+ $common = length $1;
+ if (defined $pcommon) {
+ $count[$pcommon > $common ? $pcommon : $common]++;
+ } else {
+ $count[$common]++; # first item
+ }
+ }
+ $p = $_;
+ $pcommon = $common;
+ END {
+ $count[$common]++; # last item
+ print "$_: $count[$_]" for 0..$#count;
+ }
+'
--
cgit v1.2.1