var tokenize = function(src, filename) {
  var len = length(src)

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

  // 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"
  }

  var escape_map = {
    n: "\n", t: "\t", r: "\r", "\\": "\\",
    "'": "'", "\"": "\"", "`": "`",
    "0": character(0)
  }

  var pk = function() {
    if (pos >= len) return null
    return src[pos]
  }

  var pk_at = function(n) {
    var idx = pos + n
    if (idx >= len) return null
    return src[idx]
  }

  var adv = function() {
    var c = src[pos]
    pos = pos + 1
    if (c == "\n") {
      row = row + 1
      col = 0
    } else {
      col = col + 1
    }
    return c
  }

  var is_digit = function(c) {
    return c >= "0" && c <= "9"
  }

  var is_hex = function(c) {
    return (c >= "0" && c <= "9") || (c >= "a" && c <= "f") || (c >= "A" && c <= "F")
  }

  var hex_val = function(c) {
    if (c >= "0" && c <= "9") return codepoint(c) - codepoint("0")
    if (c >= "a" && c <= "f") return codepoint(c) - codepoint("a") + 10
    if (c >= "A" && c <= "F") return codepoint(c) - codepoint("A") + 10
    return 0
  }

  var read_unicode_escape = function() {
    var cp_val = 0
    var hi = 0
    while (hi < 4 && pos < len && is_hex(pk())) {
      cp_val = cp_val * 16 + hex_val(adv())
      hi = hi + 1
    }
    return character(cp_val)
  }

  var is_alpha = function(c) {
    return (c >= "a" && c <= "z") || (c >= "A" && c <= "Z")
  }

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

  var is_ident_start = function(c) {
    return is_alpha(c) || c == "_" || c == "$"
  }

  var is_ident_char = function(c) {
    return is_alnum(c) || c == "_" || c == "$" || c == "?" || c == "!"
  }

  var substr = function(start, end) {
    return text(src, start, end)
  }

  var read_string = function(quote) {
    var start = pos
    var start_row = row
    var start_col = col
    var parts = []
    var run_start = 0
    var esc = null
    var esc_val = null
    adv() // skip opening quote
    run_start = pos
    while (pos < len && pk() != quote) {
      if (pk() == "\\") {
        if (pos > run_start) parts[] = text(src, run_start, pos)
        adv()
        esc = adv()
        esc_val = escape_map[esc]
        if (esc_val != null) { parts[] = esc_val }
        else if (esc == "u") { parts[] = read_unicode_escape() }
        else { parts[] = esc }
        run_start = pos
      } else {
        adv()
      }
    }
    if (pos > run_start) parts[] = text(src, run_start, pos)
    if (pos < len) adv() // skip closing quote
    tokens[] = {
      kind: "text", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: text(parts)
    }
  }

  var read_template = function() {
    var start = pos
    var start_row = row
    var start_col = col
    var parts = []
    var run_start = 0
    var depth = 0
    var tc = null
    var q = null
    var interp_start = 0
    adv() // skip opening backtick
    run_start = pos
    while (pos < len && pk() != "`") {
      if (pk() == "\\" && pos + 1 < len) {
        if (pos > run_start) parts[] = text(src, run_start, pos)
        parts[] = text(src, pos, pos + 2)
        adv(); adv()
        run_start = pos
      } else if (pk() == "$" && pos + 1 < len && pk_at(1) == "{") {
        if (pos > run_start) parts[] = text(src, run_start, pos)
        interp_start = pos
        adv(); adv() // $ {
        depth = 1
        while (pos < len && depth > 0) {
          tc = pk()
          if (tc == "{") { depth = depth + 1; adv() }
          else if (tc == "}") {
            depth = depth - 1
            adv()
          }
          else if (tc == "'" || tc == "\"" || tc == "`") {
            q = adv()
            while (pos < len && pk() != q) {
              if (pk() == "\\" && pos + 1 < len) adv()
              adv()
            }
            if (pos < len) adv()
          } else { adv() }
        }
        parts[] = text(src, interp_start, pos)
        run_start = pos
      } else {
        adv()
      }
    }
    if (pos > run_start) parts[] = text(src, run_start, pos)
    if (pos < len) adv() // skip closing backtick
    tokens[] = {
      kind: "text", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: text(parts)
    }
  }

  var read_number = function() {
    var start = pos
    var start_row = row
    var start_col = col
    var raw = ""
    if (pk() == "0" && (pk_at(1) == "x" || pk_at(1) == "X")) {
      adv(); adv()
      while (pos < len && (is_hex(pk()) || pk() == "_")) adv()
    } else if (pk() == "0" && (pk_at(1) == "b" || pk_at(1) == "B")) {
      adv(); adv()
      while (pos < len && (pk() == "0" || pk() == "1" || pk() == "_")) adv()
    } else if (pk() == "0" && (pk_at(1) == "o" || pk_at(1) == "O")) {
      adv(); adv()
      while (pos < len && pk() >= "0" && pk() <= "7") adv()
    } else {
      while (pos < len && (is_digit(pk()) || pk() == "_")) adv()
      if (pos < len && pk() == ".") {
        adv()
        while (pos < len && (is_digit(pk()) || pk() == "_")) adv()
      }
      if (pos < len && (pk() == "e" || pk() == "E")) {
        adv()
        if (pos < len && (pk() == "+" || pk() == "-")) adv()
        while (pos < len && is_digit(pk())) adv()
      }
    }
    raw = substr(start, pos)
    tokens[] = {
      kind: "number", at: start,
      from_row: start_row, from_column: start_col,
      to_row: row, to_column: col,
      value: raw, number: number(raw)
    }
  }

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

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

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

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

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

    if (c == "\n") {
      start = pos; start_row = row; start_col = col
      adv()
      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 == "\r") {
      start = pos; start_row = row; start_col = col
      adv()
      if (pos < len && pk() == "\n") adv()
      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 == " " || c == "\t") {
      start = pos; start_row = row; start_col = col
      while (pos < len && (pk() == " " || pk() == "\t")) adv()
      raw = substr(start, pos)
      tokens[] = { kind: "space", at: start, from_row: start_row, from_column: start_col, to_row: row, to_column: col, value: raw }
      return true
    }
    if (c == "'" || c == "\"") { read_string(c); return true }
    if (c == "`") { read_template(); return true }
    if (is_digit(c)) { read_number(); return true }
    if (c == "." && is_digit(pk_at(1))) { read_number(); return true }
    if (is_ident_start(c)) { read_name(); return true }
    if (c == "/") {
      if (pk_at(1) == "/" || pk_at(1) == "*") { read_comment(); return true }
      if (pk_at(1) == "=") { emit_op("/=", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("/", 1); return true
    }
    if (c == "*") {
      if (pk_at(1) == "*") {
        if (pk_at(2) == "!") { emit_ident(3); return true }
        if (pk_at(2) == "=") { emit_op("**=", 3); return true }
        emit_op("**", 2); return true
      }
      if (pk_at(1) == "=") { emit_op("*=", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("*", 1); return true
    }
    if (c == "%") {
      if (pk_at(1) == "=") { emit_op("%=", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("%", 1); return true
    }
    if (c == "+") {
      if (pk_at(1) == "=") { emit_op("+=", 2); return true }
      if (pk_at(1) == "+") { emit_op("++", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("+", 1); return true
    }
    if (c == "-") {
      if (pk_at(1) == "=") { emit_op("-=", 2); return true }
      if (pk_at(1) == "-") { emit_op("--", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("-", 1); return true
    }
    if (c == "<") {
      if (pk_at(1) == "=" && pk_at(2) == "!") { emit_ident(3); return true }
      if (pk_at(1) == "=") { emit_op("<=", 2); return true }
      if (pk_at(1) == "<") {
        if (pk_at(2) == "!") { emit_ident(3); return true }
        if (pk_at(2) == "=") { emit_op("<<=", 3); return true }
        emit_op("<<", 2); return true
      }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("<", 1); return true
    }
    if (c == ">") {
      if (pk_at(1) == "=" && pk_at(2) == "!") { emit_ident(3); return true }
      if (pk_at(1) == "=") { emit_op(">=", 2); return true }
      if (pk_at(1) == ">") {
        if (pk_at(2) == ">") {
          if (pk_at(3) == "!") { emit_ident(4); return true }
          if (pk_at(3) == "=") { emit_op(">>>=", 4); return true }
          emit_op(">>>", 3); return true
        }
        if (pk_at(2) == "!") { emit_ident(3); return true }
        if (pk_at(2) == "=") { emit_op(">>=", 3); return true }
        emit_op(">>", 2); return true
      }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op(">", 1); return true
    }
    if (c == "=") {
      if (pk_at(1) == "=") {
        if (pk_at(2) == "=") { emit_op("===", 3); return true }
        emit_op("==", 2); return true
      }
      if (pk_at(1) == ">") { emit_op("=>", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("=", 1); return true
    }
    if (c == "!") {
      if (pk_at(1) == "=") {
        if (pk_at(2) == "!") { emit_ident(3); return true }
        if (pk_at(2) == "=") { emit_op("!==", 3); return true }
        emit_op("!=", 2); return true
      }
      emit_op("!", 1); return true
    }
    if (c == "&") {
      if (pk_at(1) == "&") {
        if (pk_at(2) == "!") { emit_ident(3); return true }
        if (pk_at(2) == "=") { emit_op("&&=", 3); return true }
        emit_op("&&", 2); return true
      }
      if (pk_at(1) == "=") { emit_op("&=", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("&", 1); return true
    }
    if (c == "|") {
      if (pk_at(1) == "|") {
        if (pk_at(2) == "!") { emit_ident(3); return true }
        if (pk_at(2) == "=") { emit_op("||=", 3); return true }
        emit_op("||", 2); return true
      }
      if (pk_at(1) == "=") { emit_op("|=", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("|", 1); return true
    }
    if (c == "^") {
      if (pk_at(1) == "=") { emit_op("^=", 2); return true }
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("^", 1); return true
    }
    if (c == "[") {
      if (pk_at(1) == "]" && pk_at(2) == "!") { emit_ident(3); return true }
      emit_op("[", 1); return true
    }
    if (c == "~") {
      if (pk_at(1) == "!") { emit_ident(2); return true }
      emit_op("~", 1); return true
    }
    emit_op(c, 1)
    return true
  }

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

  // EOF token
  tokens[] = { kind: "eof", at: pos, from_row: row, from_column: col, to_row: row, to_column: col }

  return {filename: filename, tokens: tokens}
}

return tokenize