#!/bin/bash
# embeds source text in the compiler, so the editor can show a built-in's definition and `include std;` needs
# no file. a text becomes a function that returns it in pieces of at most 3000 bytes (the bootstrap
# compiler's token buffer is 4 KB), one byte string per piece:
#   bstr NAME_part(int i) { if (i == 0) return b"..."; if (i == 1) return b"..."; ... return 0; }
#
#   src/tools/embed.sh all            embeds src/lib modules in the compiler
#   src/tools/embed.sh all --check    exits 1 when an embedded module is out of date
#   src/tools/embed.sh lsp OUT        writes OUT: rt_part, compiler_part and server_part, for the language server's image
set -e
case "${1:-}" in
    --help|-h) printf '%s\n' 'usage: src/tools/embed.sh std|icon|all [--check]' '       src/tools/embed.sh lsp OUT' 'embeds library sources in the compiler, or writes the lsp source providers to OUT.' 'options:' '  --check     report stale embedded library sources without changing files' '  --help, -h  show this help and exit'; exit 0 ;;
    -*) echo "embed: unknown option $1; use --help for usage" >&2; exit 2 ;;
esac
cd "$(dirname "$0")/../.."
export LC_ALL=C
# parts NAME FILE: the NAME_part function for FILE
parts() {
	echo "bstr $1_part(int i) {"
	awk -v LIMIT=3000 '
	function flush() { if (cnt > 0) { printf("\tif (i == %d) return b\"%s\";\n", n, buf); n++; buf = ""; cnt = 0 } }
	{
		line = $0; sub(/\r$/, "", line); line = line "\n"
		len = length(line)
		for (j = 1; j <= len; j++) {
			if (cnt >= LIMIT) flush()
			c = substr(line, j, 1)
			if (c == "\\") e = "\\\\"; else if (c == "\"") e = "\\\""; else if (c == "\t") e = "\\t"; else if (c == "\n") e = "\\n"; else e = c
			buf = buf e; cnt++
		}
	}
	END { flush() }' "$2"
	echo "	return 0;"
	echo "}"
}
embed() {
	name=$1; file=$2; check=$3; C=src/compiler/compiler.zc; T=$(mktemp -d)
	BEGIN_MARK="// ---- embedded $name library (generated by src/tools/embed.sh from $file; do not edit) ----"
	END_MARK="// ---- end embedded $name library ----"
	if grep -qF "$BEGIN_MARK" "$C"; then
		awk -v b="$BEGIN_MARK" '$0 == b { exit } { print }' "$C" > "$T/head"
		awk -v e="$END_MARK" 'found { print } $0 == e { found = 1; next }' "$C" > "$T/tail"
	else
		cp "$C" "$T/head"
		: > "$T/tail"
	fi
	{
		cat "$T/head"
		echo "$BEGIN_MARK"
		parts "$name" "$file"
		echo "$END_MARK"
		cat "$T/tail"
	} > "$T/new"
	if [ "$check" = "--check" ]; then
		cmp -s "$T/new" "$C" && result=0 || result=1
		rm -rf "$T"
		return "$result"
	fi
	cp "$T/new" "$C"
	rm -rf "$T"
}
case "$1" in
std)
	embed std src/lib/std.zc "$2"
	;;
icon)
	embed icon src/lib/icon.zc "$2"
	;;
all)
	if [ "$2" = "--check" ]; then
		embed std src/lib/std.zc --check && embed icon src/lib/icon.zc --check
	else
		embed std src/lib/std.zc
		embed icon src/lib/icon.zc
	fi
	;;
lsp)
	[ -n "$2" ] || { echo "usage: src/tools/embed.sh lsp OUT" >&2; exit 2; }
	{
		echo "// the sources of this image, embedded (generated by src/tools/embed.sh; do not edit)"
		parts rt src/runtime/rt.zc
		parts compiler src/compiler/compiler.zc
		parts server src/lsp/server.zc
		parts core src/core/core.zc
	} > "$2"
	;;
*)
		echo "usage: src/tools/embed.sh all [--check] | std | icon | lsp OUT" >&2; exit 2;;
esac