bash function for git log as JSON

git-log-json.sh

# attempting to be the most robust solution for outputting git log as JSON,
# using only bash shell syntax, `git`, `sed` and `tr`.

# - uses traditional JSON camelCase
# - includes every major field that git log can output, including the body
# - proper sections for author, committer, and signature
# - multiple date formats (one for reading, ISO for parsing)
# - properly handle body values, even those that contain quotation marks and
#   escaped characters
# - outputs as minimized JSON, can be piped to `jq` for pretty printing
# - can run against the current directory as `git-log-json` or against a file
#   or folder with `git-log-json foo`
# - easily piped into `jq`, e.g. this will get all the commit subjects:
#   $ git-log-json foo | jq -r '.[] | .subject'
# - accept any option git log accepts, --pretty etc does not make sense but accepted
# - requires support for en_US.UTF-8 locale, needed to support \0 as delim

# credit to @nsisodiya, @varemenos, @overengineer, and others for the
# original working code:
# https://gist.github.com/varemenos/e95c2e098e657c7688fd

git-log-json() {
  local a
  for a in "$@"; do
    case "${a}" in
      --) break ;;
      --format=*|--pretty|--pretty=*|--oneline|-p|-u|--patch)
        >&2 echo "ERROR: git-log-json does not accept ${a} as option"
        return 1
        ;;
    esac
  done
  local LANG=en_US.UTF-8
  # Force UTF-8 to handle \0 as native
  git log --pretty=format:"$(
    {
      # Normalize, handle delims between keys and values and entries
      tr -d '\r\n ' | sed -E 's/"([^"]*)"/%x00\1%x00/g;s/$/,%x00/'
    } << 'EOF'
{
  "author":
  {
    "name": "%aN",
    "email": "%aE",
    "date": "%aD",
    "dateISO8601": "%aI"
  },
  "body": "%b",
  "commitHash": "%H",
  "commitHashAbbreviated": "%h",
  "committer":
  {
    "name": "%cN",
    "email": "%cE",
    "date": "%cD",
    "dateISO8601": "%cI"
  },
  "encoding": "%e",
  "notes": "%N",
  "parent": "%P",
  "parentAbbreviated": "%p",
  "refs": "%D",
  "signature":
  {
    "key": "%GK",
    "signer": "%GS",
    "verificationFlag": "%G?"
  },
  "subject": "%s",
  "subjectSanitized": "%f",
  "tree": "%T",
  "treeAbbreviated": "%t"
}
EOF
  )" "$@" | \
  # Force UTF-8 to handle \0 as native
  sed -E '
# Slurp all into memory
:a
N
$!ba
# Handle quotations
s/\\/\\\\/g
s/"/\\"/g
# Join entries, drop \n so it does not mess later
s/(\x00[}],)\x00\n([{]\x00)/\1\2/g
# Handle \n\r\t
s/\r//g
s/\n/\\n/g
s/\t/\\t/g
# Wrap with [ ], drops last entry delim
s/^(.*),\x00$/[\1]/
# Handle key/value delims
s/\x00/"/g;
'
}