author Hiroyuki Ikezoe <>
Thu, 09 Aug 2018 14:27:55 +0900
changeset 430753 5bbec1fa2d0781b95234b619dc2aedbb6686035f
parent 429731 20668aaf20ebbef0dad5b18b0db001bee589da3e
child 477015 25ff3ab8a3415c7ff43b1a05df58b11541561c0e
permissions -rw-r--r--
Bug 1469054 - Adapt implementations for adb.start() and adb.stop() and relevant stuff. r=jdescottes MozReview-Commit-ID: LF23OQtXxkj

# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at

import codecs
import encodings.idna
import imp
import os
import re
import sys
from make_dafsa import words_to_cxx

Processes a file containing effective TLD data.  See the following URL for a
description of effective TLDs and of the file format that this script
processes (although for the latter you're better off just reading this file's
short source code).

def getEffectiveTLDs(path):
  file =, "r", "UTF-8")
  entries = []
  domains = set()
  for line in file:
    # line always contains a line terminator unless the file is empty
    if len(line) == 0:
      raise StopIteration
    line = line.rstrip()
    # comment, empty, or superfluous line for explicitness purposes
    if line.startswith("//") or "." not in line:
    line = re.split(r"[ \t\n]", line, 1)[0]
    entry = EffectiveTLDEntry(line)
    domain = entry.domain()
    assert domain not in domains, \
           "repeating domain %s makes no sense" % domain
    yield entry

def _normalizeHostname(domain):
  Normalizes the given domain, component by component.  ASCII components are
  lowercased, while non-ASCII components are processed using the ToASCII
  def convertLabel(label):
    if _isASCII(label):
      return label.lower()
    return encodings.idna.ToASCII(label)
  return ".".join(map(convertLabel, domain.split(".")))

def _isASCII(s):
  "True if s consists entirely of ASCII characters, false otherwise."
  for c in s:
    if ord(c) > 127:
      return False
  return True

class EffectiveTLDEntry:
  Stores an entry in an effective-TLD name file.

  _exception = False
  _wild = False

  def __init__(self, line):
    Creates a TLD entry from a line of data, which must have been stripped of
    the line ending.
    if line.startswith("!"):
      self._exception = True
      domain = line[1:]
    elif line.startswith("*."):
      self._wild = True
      domain = line[2:]
      domain = line
    self._domain = _normalizeHostname(domain)

  def domain(self):
    "The domain this represents."
    return self._domain

  def exception(self):
    "True if this entry's domain denotes does not denote an effective TLD."
    return self._exception

  def wild(self):
    "True if this entry represents a class of effective TLDs."
    return self._wild


def main(output, effective_tld_filename):
  effective_tld_filename is the effective TLD file to parse.
  A C++ array of a binary representation of a DAFSA representing the
  eTLD file is then printed to output.

  def typeEnum(etld):
    Maps the flags to the DAFSA's enum types.
    if etld.exception():
      return 1
    elif etld.wild():
      return 2
      return 0

  def dafsa_words():
    make_dafsa expects lines of the form "<domain_name><enum_value>"
    for etld in getEffectiveTLDs(effective_tld_filename):
      yield "%s%d" % (etld.domain(), typeEnum(etld))


if __name__ == '__main__':
    main(sys.stdout, sys.argv[1])