#!/usr/bin/env bash

#

# Tabulates commit sizes based on their classification.

#

# References:

#

# * Arafat, Oliver, and Dirk Riehle. 2009. "The Commit Size Distribution of Open Source Software." In *Proceedings of the 42nd Hawaii International Conference on System Sciences*. IEEE Computer Society.

# * Hattori, Lile P., and Michele Lanza. 2008. "On the nature of commits." In *ASE Workshops 2008. 23rd IEEE/ACM International Conference on Automated Software Engineering - Workshops, 2008.* IEEE. doi:[10.1109/ASEW.2008.4686322](http://dx.doi.org/10.1109/ASEW.2008.4686322).

# Determine root directory:

root="$(git rev-parse --show-toplevel)"

# Define the path to a utility to compute commit sizes:

commit_sizes="${root}/tools/git/scripts/commit_sizes"

# * `commit_sizes`

# - Get commit sizes.

# * `awk '{}'`

# - Classify sizes.

# * `sort -n`

# - Sort in numeric order.

"${commit_sizes}" | awk '

$1 < 5 {

table["tiny"] += 1

next

}

$1 < 20 {

table["small"] += 1

next

}

$1 < 200 {

table["medium"] += 1

next

}

$1 < 10000 {

table["large"] += 1

next

}

# Everything else...

{

table["huge"] += 1

}

END {

for (row in table) {

print row OFS table[row]

}

}

' | sort -k2nr