Extract a value from a JSON object or array in awk

json.awk

#
# Extract a JSON value in an object or array:
#
# name = decode_json_string(get_json_value(json, "author.name"))
# date = decode_json_string(get_json_value(json, "events.0.date"))
#
# Or an entire object:
#
# get_json_value(json, "dependencies", deps)
#
# for (name in deps)
# 	version = decode_json_string(deps[name])
#
# Or array:
#
# get_json_value(json, "payload.tree.items", items)
#
# for (i = 0; items[i]; i++) {
# 	get_json_value(items[i], null, item)
# 	type = decode_json_string(item["type"])
# 	name = decode_json_string(item["name"])
# }
#
function get_json_value( \
	s, key, a,
	skip, type, all, rest, isval, i, c, k, null \
) {
	if (match(s, /^[[:space:]]+/)) s = substr(s, RLENGTH+1)
	type = substr(s, 1, 1)
	all = key == "" && key == 0
	if (type != "{" && type != "[") {
		if (!all) error("invalid json array/object " s)
		if (!match(s, /^(null|true|false|"(\\.|[^\\"])*"|[.0-9Ee+-]+)/))
			error("invalid json value " s)
		return substr(s, 1, RLENGTH)
	}
	if (!all && (i = index(key, "."))) {
		rest = substr(key, i+1)
		key = substr(key, 1, i-1)
	}
	if ((isval = type == "[")) k = 0
	for (i = 2; i <= length(s); i += length(c)) {
		if (match(substr(s, i), /^[[:space:]]+/)) {
			c = substr(s, i, RLENGTH)
			continue
		}
		c = substr(s, i, 1)
		if (c == "}" || c == "]") break
		else if (c == ",") { if ((isval = type == "[")) ++k }
		else if (c == ":") isval = 1
		else {
			if (!all && k == key && isval)
				return get_json_value(substr(s, i), rest, a)
			c = get_json_value(substr(s, i), null, null, 1)
			if (all && !skip && isval) a[k] = c
			if (c ~ /^"/ && !isval) k = substr(c, 2, length(c)-2)
		}
	}
	if ((type == "{" && c != "}") || (type == "[" && c != "]"))
		error("unterminated json array/object " s)
	if (all) return substr(s, 1, i)
}

function decode_json_string(s, out, esc) {
	if (s !~ /^"./ || substr(s, length(s), 1) != "\"")
		error("invalid json string " s)
	s = substr(s, 2, length(s)-2)
	esc["b"] = "\b"; esc["f"] = "\f"; esc["n"] = "\n"; esc["\""] = "\""
	esc["r"] = "\r"; esc["t"] = "\t"; esc["/"] = "/" ; esc["\\"] = "\\"
	while (match(s, /\\/)) {
		if (!(substr(s, RSTART+1, 1) in esc))
			error("unknown json escape " substr(s, RSTART, 2))
		out = out substr(s, 1, RSTART-1) esc[substr(s, RSTART+1, 1)]
		s = substr(s, RSTART+2)
	}
	return out s
}

function error(msg) {
	printf "%s: %s\n", ARGV[0], msg > "/dev/stderr"
	exit 1
}

#
# Example usage
#
# $ curl https://httpbin.org/json | awk -f json.awk slideshow.title
# "Sample Slide Show"
#
BEGIN {
	while (ret = getline l < "/dev/stdin") {
		if (ret == -1) error("getline error")
		s = s l "\n"
	}
	print get_json_value(s, ARGV[1])
}