#autoload

## usage: _regex_arguments funcname regex

## configuration key used:

# regex_arguments_path
#  The path to a directory for caching. (default: ~/.zsh/regex_arguments)

##

# _regex_arguments compiles `regex' and emit the result of the state
# machine into the function `funcname'. `funcname' parses a command line
# according to `regex' and evaluate appropriate actions in `regex'. Before
# parsing the command line string is genereted by concatinating `words'
# (before `PREFIX') and `PREFIX' with a separator NUL ($'\0').

# The `regex' is defined as follows.

## regex word definition:

# pattern = "/" ( glob | "[]" ) "/" [ "+" | "-" ]
# lookahead = "%" glob "%"
# guard = "-" zsh-code-to-eval
# caction = ":" zsh-code-to-eval
# action = "{" zsh-code-to-eval "}"

## regex word sequence definition:

# element = pattern [ lookahead ] [ guard ] [ caction ]
# 
# regex = element 
#	| "(" regex ")"
#	| regex "#"
#	| ( regex | action ) #
#	| regex "|" regex

# example:

# compdef _tst tst

# _regex_arguments _tst /$'[^\0]#\0'/ /$'[^\0]#\0'/ :'compadd aaa'
#  _tst complete `aaa' for first argument.
#  First $'[^\0]#\0' is required to match with command name.

# _regex_arguments _tst /$'[^\0]#\0'/ \( /$'[^\0]#\0'/ :'compadd aaa' /$'[^\0]#\0'/ :'compadd bbb' \) \#
#  _tst complete `aaa' for (2i+1)th argument and `bbb' for (2i)th argument.

# _regex_arguments _tst /$'[^\0]#\0'/ \( /$'[^\0]#\0'/ :'compadd aaa' \| /$'[^\0]#\0'/ :'compadd bbb' \) \#
#  _tst complete `aaa' or `bbb'.

## Recursive decent regex parser

# return status of parser functions:

# 0 : success
# 1 : parse error
# 2 : fatal parse error

_ra_comp () {
  _ra_actions=("$_ra_actions[@]" "$1")
}

_regex_arguments () {
  local regex funcname="$1"
  shift
  regex=(${@:/(#b):(*)/":_ra_comp ${(qqqq)match[1]}"})

  eval \
  "$funcname"' () {
    local _ra_p1 _ra_p2 _ra_left _ra_right _ra_com
    local _ra_actions _ra_line="${(pj:\0:)${(@)words[1,CURRENT - 1]:Q}}"$'\''\0'\''"$PREFIX"
    zregexparse -c _ra_p1 _ra_p2 "$_ra_line" '"${(j: :)${(qqqq)regex[@]}}"'
    case "$?" in
    0|2) _message "no more arguments";;
    1) 
      if [[ "$_ra_line[_ra_p1 + 1, -1]" = *$'\''\0'\''* ]]; then
	_message "parse failed before current word"
      else
	_ra_left="$_ra_line[_ra_p1 + 1, _ra_p2]"
	_ra_right="$_ra_line[_ra_p2 + 1, -1]"
	compset -p $(( $#PREFIX - $#_ra_line + $_ra_p1 ))
	for _ra_com in "$_ra_actions[@]"; do
	  eval "$_ra_com"
	done
      fi
      ;;
    3) _message "invalid regex";;
    esac
  }'
}

_regex_arguments "$@"