Git pre-commit hook that blocks commits for files that contain swear words.

.pre-commit-config.yaml

## Example using https://pre-commit.com/
repos:
  - repo: local
    hooks:
    - id: dontship
      name: DONTSHIP check - Block words
      entry: '\bdie\b'
      language: pygrep  # https://pre-commit.com/#pygrep
      types: [php]

    - id: check-swear
      name: Check Swear Words
      entry: ./scripts/check_swear_words.sh
      language: script

check_swear_words.sh

#!/bin/bash

## This script should run under pre-commit control and return error in case of any bad word is present in the files staged

# If you want to commit something with swearing use FUCK_IT=1 git commit ...
if [ -n "$FUCK_IT" ]; then
  exit 0
fi

ROOT_DIR=$(git rev-parse --show-toplevel)
EXIT=0


# Definitely NSFW
WORD_FILE_URL_BASE="https://raw.githubusercontent.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words/master/"
WORD_FILE_PATH_BASE=~/.swearwords

TMPFILE=$(mktemp)

check_for_words(){
    LANG=$1 

    if [ ! -f "${WORD_FILE_PATH_BASE}-${LANG}" ]; then
        wget -q -O - "${WORD_FILE_URL_BASE}/${LANG}" | tr '\n' '|' | sed 's/\|$//g' > "${WORD_FILE_PATH_BASE}-${LANG}"
    fi

    PATTERN="$(cat ${WORD_FILE_PATH_BASE}-${LANG} )"
    if [[ -n "$PATTERN" ]]; then
        for file in $(git diff --cached --name-only --diff-filter=ACM); do
            if egrep -Hinw "$PATTERN" "$file" > $TMPFILE ; then
                echo "Swear word with language: ${LANG} found in file: $(cat $TMPFILE)"
                rm $TMPFILE
                return 1
            fi
        done
    fi
    return 0
}

for i in en fr pt ru it es; do
  check_for_words $i || exit 1
done

rm $TMPFILE

exit 0