about summary refs log tree commit diff
path: root/contrib/stats/git-common-hash
diff options
context:
space:
mode:
authorVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
committerVincent Ambo <Vincent Ambo>2020-01-11T23·36+0000
commit1b593e1ea4d2af0f6444d9a7788d5d99abd6fde5 (patch)
treee3accb9beed5c4c1b5a05c99db71ab2841f0ed04 /contrib/stats/git-common-hash
Squashed 'third_party/git/' content from commit cb71568594
git-subtree-dir: third_party/git
git-subtree-split: cb715685942260375e1eb8153b0768a376e4ece7
Diffstat (limited to 'contrib/stats/git-common-hash')
-rwxr-xr-xcontrib/stats/git-common-hash26
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 000000000000..e27fd088be1b
--- /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;
+  }
+'