Python pre-commit hook

pre-commit.py

#!/usr/bin/env python

# Inspired by: https://gist.github.com/thraxil/3123935
# Differs from above link by using the results of `git show` 
# instead of using `git stash`, which prevents unintended
# side-effects

import os
import re
import subprocess
import sys
import atexit
import traceback

gitcmd = 'git'
tmpfile = 'check.tmp'

CHECKS = [
    {
        'output': 'Checking for pdbs...',
        'command': 'grep -n "import pdb" %s',
        'match_files': ['.*\.py$'],
        'ignore_files': ['.*scripts/.*'],
    },
    {
        'output': 'Checking for print statements...',
        'command': "grep -n '\sprint(' %s",
        'match_files': ['.*\.py$'],
        'ignore_files': ['.*scripts/.*'],
    },
    {
        'output': 'Checking for tabs...',
        'command': 'grep -n -P "\t" %s',
        'match_files': ['.*\.py$'],
    },
    {
        'output': 'Running pyflakes...',
        'command': "pyflakes %s",
        'match_files': ['.*\.py$'],
        'ignore_files': ['.*scripts/.*'],
    },
    {
        'output': 'Running pep8...',
        # ignore line too long, whitespace before :, etc.
        'command': "pep8 --ignore=E501,E203 %s",
        'match_files': ['.*\.py$'],
        'ignore_files': ['.*scripts/.*'],
    }
]

CMDS = [
    {
        'output'  : 'Running git whitespace check...',
        'command' : 'git diff --cached --check'
    }
]


def matches_file(file_name, match_files):
    return any(re.compile(match_file).match(file_name) for match_file in match_files)


@atexit.register
def exit():
    try:
        os.remove(tmpfile)
    except:
        pass

def check_files(files, check):
    result = 0
    print(check['output'])

    def strip_prefix(s,p):
        return s[len(p):] if s.startswith(p) else s

    for file_name in files:
        if not 'match_files' in check or matches_file(file_name, check['match_files']):
            if not 'ignore_files' in check or not matches_file(file_name, check['ignore_files']):
                process = subprocess.Popen(gitcmd
                                           + ' show :'
                                           + file_name
                                           + '> '
                                           + tmpfile
                                           +' && '
                                           + check['command'] % 'check.tmp',
                                           stdout=subprocess.PIPE,
                                           stderr=subprocess.PIPE,
                                           shell=True)
                out, err = process.communicate()
                if out or err:
                    prefix = '\t%s:' % file_name
                    output_lines = ['%s%s' % (prefix, strip_prefix(line,tmpfile+':'))
                                    for line
                                    in out.splitlines()]
                    print('\n'.join(output_lines))
                    if err:
                        print(err)
                    result = 1
    return result


def main(all_files):

    files = []

    if all_files:
        for root, dirs, file_names in os.walk('.'):
            for file_name in file_names:
                files.append(os.path.join(root, file_name))
    else:
        p = subprocess.Popen([
                gitcmd,
                'diff-index',
                '-z',
                '--cached',
                'HEAD',
                '--name-only',
                '--diff-filter=AM'], stdout=subprocess.PIPE)
        f,err = p.communicate()
        files = filter(bool,f.split('\0'))

    result = 0

    # for one-off commands
    for cmd in CMDS:
        print(cmd['output'])
        result = (subprocess.call(cmd['command'], shell=True)
                  or result)

    # for command that must be run on multiple files
    for check in CHECKS:
        result = check_files(files, check) or result

    if not result:
        print('No errors found!')
    else:
        print('Errors found!')
    sys.exit(result)


if __name__ == '__main__':
    all_files = False
    if len(sys.argv) > 1 and (sys.argv[1] == '--all-files' or sys.argv[1] == '-a'):
        all_files = True
    try:
        main(all_files)
    except KeyboardInterrupt:
        print("Early termination requested...")
        # always fail out when exiting early
        sys.exit(1)
    except Exception:
        traceback.print_exc(file=sys.stdout)
        sys.exit(1)