1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
#!/usr/bin/env bash
#
# @license Apache-2.0
#
# Copyright (c) 2017 The Stdlib Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Extracts the first word from each commit message and ranks each word by frequency.
#
# <count> <word>
# * `git log --pretty=format:'%s'`
# - Show the commit message for each commit
# * `awk '{}'`
# - Extract first word.
# * `awk '{}'`
# - Remove commits which use sed syntax.
# * `tr '[:upper:]' '[:lower:]`
# - Convert each word to lowercase.
# * `sort`
# - Sort in lexicographic order.
# * `uniq -c`
# - Count repeated lines and then remove repeats.
# * `sort -nr`
# - Sort in reverse numeric order.
git log --pretty=format:'%s' | awk '
/^revert/ {
print $3
next
}
/^([A-Za-z0-9]+)(\([A-Za-z0-9]*\))?:/ {
print $2
next
}
{
print $1
}
' | awk '
! /^s\/.+\/.+\/$/ {
print $0
}
' | tr '[:upper:]' '[:lower:]' | sort | uniq -c | sort -nr
|
