[thirdparty/git.git] / contrib / stats / git-common-hash

#!/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..$#count;
  }
'
Commit	Line	Data
750bd6ac NP	1	#!/bin/sh
	2
	3	# This script displays the distribution of longest common hash prefixes.
	4	# This can be used to determine the minimum prefix length to use
	5	# for object names to be unique.
	6
	7	git rev-list --objects --all \| sort \| perl -lne '
	8	substr($_, 40) = "";
	9	# uncomment next line for a distribution of bits instead of hex chars
	10	# $_ = unpack("B",pack("H",$_));
	11	if (defined $p) {
	12	($p ^ $_) =~ /^(\0*)/;
	13	$common = length $1;
	14	if (defined $pcommon) {
	15	$count[$pcommon > $common ? $pcommon : $common]++;
	16	} else {
	17	$count[$common]++; # first item
	18	}
	19	}
	20	$p = $_;
	21	$pcommon = $common;
	22	END {
	23	$count[$common]++; # last item
	24	print "$_: $count[$_]" for 0..$#count;
	25	}
	26	'