var src = args[0]
var filename = length(args) > 1 ? args[1] : "<stdin>"

// Convert to codepoint array - integers are GC-safe immediate values
var len = length(src)
var cp = []
var _i = 0
while (_i < len) {
  push(cp, codepoint(src[_i]))
  _i = _i + 1
}

var pos = 0
var row = 0
var col = 0
var tokens = []

// Codepoint constants
def CP_LF = 10
def CP_CR = 13
def CP_TAB = 9
def CP_SPACE = 32
def CP_BANG = 33
def CP_DQUOTE = 34
def CP_HASH = 35
def CP_DOLLAR = 36
def CP_PERCENT = 37
def CP_AMP = 38
def CP_SQUOTE = 39
def CP_LPAREN = 40
def CP_RPAREN = 41
def CP_STAR = 42
def CP_PLUS = 43
def CP_COMMA = 44
def CP_MINUS = 45
def CP_DOT = 46
def CP_SLASH = 47
def CP_0 = 48
def CP_1 = 49
def CP_7 = 55
def CP_9 = 57
def CP_COLON = 58
def CP_SEMI = 59
def CP_LT = 60
def CP_EQ = 61
def CP_GT = 62
def CP_QMARK = 63
def CP_AT = 64
def CP_A = 65
def CP_B = 66
def CP_E = 69
def CP_F = 70
def CP_O = 79
def CP_X = 88
def CP_Z = 90
def CP_LBRACKET = 91
def CP_BSLASH = 92
def CP_RBRACKET = 93
def CP_CARET = 94
def CP_UNDERSCORE = 95
def CP_BACKTICK = 96
def CP_a = 97
def CP_b = 98
def CP_e = 101
def CP_f = 102
def CP_n = 110
def CP_o = 111
def CP_r = 114
def CP_t = 116
def CP_x = 120
def CP_z = 122
def CP_LBRACE = 123
def CP_PIPE = 124
def CP_RBRACE = 125
def CP_TILDE = 126

// Keywords lookup
var keywords = {
  if: "if", in: "in", do: "do", go: "go",
  var: "var", def: "def", for: "for",
  else: "else", this: "this", null: "null", true: "true",
  false: "false", while: "while", break: "break",
  return: "return", delete: "delete",
  disrupt: "disrupt", function: "function", continue: "continue",
  disruption: "disruption"
}

function pk() {
  if (pos >= len) return -1
  return cp[pos]
}

function pk_at(n) {
  var idx = pos + n
  if (idx >= len) return -1
  return cp[idx]
}

function adv() {
  var c = cp[pos]
  pos = pos + 1
  if (c == CP_LF) {
    row = row + 1
    col = 0
  } else {
    col = col + 1
  }
  return c
}

function is_digit(c) {
  return c >= CP_0 && c <= CP_9
}

function is_hex(c) {
  return (c >= CP_0 && c <= CP_9) || (c >= CP_a && c <= CP_f) || (c >= CP_A && c <= CP_F)
}

function is_alpha(c) {
  return (c >= CP_a && c <= CP_z) || (c >= CP_A && c <= CP_Z)
}

function is_alnum(c) {
  return is_alpha(c) || is_digit(c)
}

function is_ident_start(c) {
  return is_alpha(c) || c == CP_UNDERSCORE || c == CP_DOLLAR
}

function is_ident_char(c) {
  return is_alnum(c) || c == CP_UNDERSCORE || c == CP_DOLLAR || c == CP_QMARK || c == CP_BANG
}

function substr(start, end) {
  var s = ""
  var i = start
  while (i < end) {
    s = s + character(cp[i])
    i = i + 1
  }
  return s
}

function read_string(quote_cp) {
  var start = pos
  var start_row = row
  var start_col = col
  var value = ""
  var esc = 0
  adv() // skip opening quote
  while (pos < len && pk() != quote_cp) {
    if (pk() == CP_BSLASH) {
      adv()
      esc = adv()
      if (esc == CP_n) { value = value + "\n" }
      else if (esc == CP_t) { value = value + "\t" }
      else if (esc == CP_r) { value = value + "\r" }
      else if (esc == CP_BSLASH) { value = value + "\\" }
      else if (esc == CP_SQUOTE) { value = value + "'" }
      else if (esc == CP_DQUOTE) { value = value + "\"" }
      else if (esc == CP_0) { value = value + character(0) }
      else if (esc == CP_BACKTICK) { value = value + "`" }
      else { value = value + character(esc) }
    } else {
      value = value + character(adv())
    }
  }
  if (pos < len) adv() // skip closing quote
  push(tokens, {
    kind: "text", at: start,
    from_row: start_row, from_column: start_col,
    to_row: row, to_column: col,
    value: value
  })
}

function read_template() {
  var start = pos
  var start_row = row
  var start_col = col
  var value = ""
  var esc = 0
  var depth = 0
  var tc = 0
  var q = 0
  adv() // skip opening backtick
  while (pos < len && pk() != CP_BACKTICK) {
    if (pk() == CP_BSLASH && pos + 1 < len) {
      adv()
      esc = adv()
      if (esc == CP_n) { value = value + "\n" }
      else if (esc == CP_t) { value = value + "\t" }
      else if (esc == CP_r) { value = value + "\r" }
      else if (esc == CP_BSLASH) { value = value + "\\" }
      else if (esc == CP_BACKTICK) { value = value + "`" }
      else if (esc == CP_DOLLAR) { value = value + "$" }
      else if (esc == CP_0) { value = value + character(0) }
      else { value = value + character(esc) }
    } else if (pk() == CP_DOLLAR && pos + 1 < len && pk_at(1) == CP_LBRACE) {
      adv() // $
      adv() // {
      depth = 1
      while (pos < len && depth > 0) {
        tc = pk()
        if (tc == CP_LBRACE) { depth = depth + 1; adv() }
        else if (tc == CP_RBRACE) { depth = depth - 1; adv() }
        else if (tc == CP_SQUOTE || tc == CP_DQUOTE || tc == CP_BACKTICK) {
          q = adv()
          while (pos < len && pk() != q) {
            if (pk() == CP_BSLASH && pos + 1 < len) adv()
            adv()
          }
          if (pos < len) adv()
        } else { adv() }
      }
    } else {
      value = value + character(adv())
    }
  }
  if (pos < len) adv() // skip closing backtick
  push(tokens, {
    kind: "text", at: start,
    from_row: start_row, from_column: start_col,
    to_row: row, to_column: col,
    value: value
  })
}

function read_number() {
  var start = pos
  var start_row = row
  var start_col = col
  if (pk() == CP_0 && (pk_at(1) == CP_x || pk_at(1) == CP_X)) {
    adv(); adv()
    while (pos < len && (is_hex(pk()) || pk() == CP_UNDERSCORE)) adv()
  } else if (pk() == CP_0 && (pk_at(1) == CP_b || pk_at(1) == CP_B)) {
    adv(); adv()
    while (pos < len && (pk() == CP_0 || pk() == CP_1 || pk() == CP_UNDERSCORE)) adv()
  } else if (pk() == CP_0 && (pk_at(1) == CP_o || pk_at(1) == CP_O)) {
    adv(); adv()
    while (pos < len && pk() >= CP_0 && pk() <= CP_7) adv()
  } else {
    while (pos < len && (is_digit(pk()) || pk() == CP_UNDERSCORE)) adv()
    if (pos < len && pk() == CP_DOT) {
      adv()
      while (pos < len && (is_digit(pk()) || pk() == CP_UNDERSCORE)) adv()
    }
    if (pos < len && (pk() == CP_e || pk() == CP_E)) {
      adv()
      if (pos < len && (pk() == CP_PLUS || pk() == CP_MINUS)) adv()
      while (pos < len && is_digit(pk())) adv()
    }
  }
  var raw = substr(start, pos)
  push(tokens, {
    kind: "number", at: start,
    from_row: start_row, from_column: start_col,
    to_row: row, to_column: col,
    value: raw, number: number(raw)
  })
}

function read_name() {
  var start = pos
  var start_row = row
  var start_col = col
  while (pos < len && is_ident_char(pk())) adv()
  var name = substr(start, pos)
  var kw = keywords[name]
  if (kw != null) {
    push(tokens, {
      kind: kw, at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col
    })
  } else {
    push(tokens, {
      kind: "name", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: name
    })
  }
}

function read_comment() {
  var start = pos
  var start_row = row
  var start_col = col
  if (pk_at(1) == CP_SLASH) {
    while (pos < len && pk() != CP_LF && pk() != CP_CR) adv()
  } else {
    adv(); adv() // skip /*
    while (pos < len) {
      if (pk() == CP_STAR && pk_at(1) == CP_SLASH) {
        adv(); adv()
        break
      }
      adv()
    }
  }
  var raw = substr(start, pos)
  push(tokens, {
    kind: "comment", at: start,
    from_row: start_row, from_column: start_col,
    to_row: row, to_column: col,
    value: raw
  })
}

function emit_op(kind, count) {
  var start = pos
  var start_row = row
  var start_col = col
  var i = 0
  while (i < count) { adv(); i = i + 1 }
  push(tokens, {
    kind: kind, at: start,
    from_row: start_row, from_column: start_col,
    to_row: row, to_column: col
  })
}

function emit_ident(count) {
  var start = pos
  var start_row = row
  var start_col = col
  var val = ""
  var i = 0
  while (i < count) { val = val + character(adv()); i = i + 1 }
  push(tokens, {
    kind: "name", at: start,
    from_row: start_row, from_column: start_col,
    to_row: row, to_column: col,
    value: val
  })
}

function tokenize_one() {
  var c = pk()
  var start = 0
  var start_row = 0
  var start_col = 0
  var raw = ""
  if (c == -1) return false

  // Newline
  if (c == CP_LF) {
    start = pos
    start_row = row
    start_col = col
    adv()
    push(tokens, {
      kind: "newline", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: "\n"
    })
    return true
  }

  if (c == CP_CR) {
    start = pos
    start_row = row
    start_col = col
    adv()
    if (pos < len && pk() == CP_LF) adv()
    push(tokens, {
      kind: "newline", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: "\n"
    })
    return true
  }

  // Whitespace
  if (c == CP_SPACE || c == CP_TAB) {
    start = pos
    start_row = row
    start_col = col
    while (pos < len && (pk() == CP_SPACE || pk() == CP_TAB)) adv()
    raw = substr(start, pos)
    push(tokens, {
      kind: "space", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: raw
    })
    return true
  }

  // Strings
  if (c == CP_SQUOTE || c == CP_DQUOTE) {
    read_string(c)
    return true
  }

  // Template
  if (c == CP_BACKTICK) {
    read_template()
    return true
  }

  // Numbers
  if (is_digit(c)) {
    read_number()
    return true
  }
  if (c == CP_DOT && is_digit(pk_at(1))) {
    read_number()
    return true
  }

  // Identifiers and keywords
  if (is_ident_start(c)) {
    read_name()
    return true
  }

  // Comments and /
  if (c == CP_SLASH) {
    if (pk_at(1) == CP_SLASH || pk_at(1) == CP_STAR) {
      read_comment()
      return true
    }
    if (pk_at(1) == CP_EQ) { emit_op("/=", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("/", 1)
    return true
  }

  // Operators
  if (c == CP_STAR) {
    if (pk_at(1) == CP_STAR) {
      if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
      if (pk_at(2) == CP_EQ) { emit_op("**=", 3); return true }
      emit_op("**", 2); return true
    }
    if (pk_at(1) == CP_EQ) { emit_op("*=", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("*", 1); return true
  }

  if (c == CP_PERCENT) {
    if (pk_at(1) == CP_EQ) { emit_op("%=", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("%", 1); return true
  }

  if (c == CP_PLUS) {
    if (pk_at(1) == CP_EQ) { emit_op("+=", 2); return true }
    if (pk_at(1) == CP_PLUS) { emit_op("++", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("+", 1); return true
  }

  if (c == CP_MINUS) {
    if (pk_at(1) == CP_EQ) { emit_op("-=", 2); return true }
    if (pk_at(1) == CP_MINUS) { emit_op("--", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("-", 1); return true
  }

  if (c == CP_LT) {
    if (pk_at(1) == CP_EQ && pk_at(2) == CP_BANG) { emit_ident(3); return true }
    if (pk_at(1) == CP_EQ) { emit_op("<=", 2); return true }
    if (pk_at(1) == CP_LT) {
      if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
      if (pk_at(2) == CP_EQ) { emit_op("<<=", 3); return true }
      emit_op("<<", 2); return true
    }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("<", 1); return true
  }

  if (c == CP_GT) {
    if (pk_at(1) == CP_EQ && pk_at(2) == CP_BANG) { emit_ident(3); return true }
    if (pk_at(1) == CP_EQ) { emit_op(">=", 2); return true }
    if (pk_at(1) == CP_GT) {
      if (pk_at(2) == CP_GT) {
        if (pk_at(3) == CP_BANG) { emit_ident(4); return true }
        if (pk_at(3) == CP_EQ) { emit_op(">>>=", 4); return true }
        emit_op(">>>", 3); return true
      }
      if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
      if (pk_at(2) == CP_EQ) { emit_op(">>=", 3); return true }
      emit_op(">>", 2); return true
    }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op(">", 1); return true
  }

  if (c == CP_EQ) {
    if (pk_at(1) == CP_EQ) {
      if (pk_at(2) == CP_EQ) { emit_op("===", 3); return true }
      emit_op("==", 2); return true
    }
    if (pk_at(1) == CP_GT) { emit_op("=>", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("=", 1); return true
  }

  if (c == CP_BANG) {
    if (pk_at(1) == CP_EQ) {
      if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
      if (pk_at(2) == CP_EQ) { emit_op("!==", 3); return true }
      emit_op("!=", 2); return true
    }
    emit_op("!", 1); return true
  }

  if (c == CP_AMP) {
    if (pk_at(1) == CP_AMP) {
      if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
      if (pk_at(2) == CP_EQ) { emit_op("&&=", 3); return true }
      emit_op("&&", 2); return true
    }
    if (pk_at(1) == CP_EQ) { emit_op("&=", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("&", 1); return true
  }

  if (c == CP_PIPE) {
    if (pk_at(1) == CP_PIPE) {
      if (pk_at(2) == CP_BANG) { emit_ident(3); return true }
      if (pk_at(2) == CP_EQ) { emit_op("||=", 3); return true }
      emit_op("||", 2); return true
    }
    if (pk_at(1) == CP_EQ) { emit_op("|=", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("|", 1); return true
  }

  if (c == CP_CARET) {
    if (pk_at(1) == CP_EQ) { emit_op("^=", 2); return true }
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("^", 1); return true
  }

  if (c == CP_LBRACKET) {
    if (pk_at(1) == CP_RBRACKET && pk_at(2) == CP_BANG) { emit_ident(3); return true }
    emit_op("[", 1); return true
  }

  if (c == CP_TILDE) {
    if (pk_at(1) == CP_BANG) { emit_ident(2); return true }
    emit_op("~", 1); return true
  }

  // Single character tokens
  emit_op(character(c), 1)
  return true
}

// Main loop
while (pos < len) {
  tokenize_one()
}

// EOF token
push(tokens, {
  kind: "eof", at: pos,
  from_row: row, from_column: col,
  to_row: row, to_column: col
})

print(json.encode({filename: filename, tokens: tokens}))