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>

1 files changed, 26 insertions, 0 deletions

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;
+  }
+'