charset.h

网络爬虫程序

/***************************************************************************/
/*    This code is part of WWW grabber called pavuk                        */
/*    Copyright (c) 1997 - 2001 Stefan Ondrejicka                          */
/*    Distributed under GPL 2 or later                                     */
/***************************************************************************/

#ifndef _charset_h_
#define _charset_h_

/***********
this list of character sets was grabed from
ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets
it includes any of names and aliases registered by IANA
************/
static const char *char_sets[] = {
  "ascii",
  "Big5",
  "euc-jp",
  "euc-kr",
  "ucs-2",
  "ucs-4",
  "ucs-basic",
  "utf-1",
  "iso-10646",
  "iso-2022-cn",
  "iso-2022-jp",
  "iso-2022-kr",
  "iso-8859-1",
  "iso-8859-2",
  "iso-8859-3",
  "iso-8859-4",
  "iso-8859-5",
  "iso-8859-6",
  "iso-8859-7",
  "iso-8859-8",
  "iso-8859-9",
  "iso646-ca",
  "iso646-ca2",
  "iso646-cn",
  "iso646-cu",
  "iso646-de",
  "iso646-dk",
  "iso646-es",
  "iso646-es2",
  "iso646-fi",
  "iso646-fr",
  "iso646-fr1",
  "iso646-gb",
  "iso646-hu",
  "iso646-it",
  "iso646-jp",
  "iso646-kr",
  "iso646-no",
  "iso646-no2",
  "iso646-pt",
  "iso646-pt2",
  "iso646-se",
  "iso646-se2",
  "iso646-us",
  "iso646-yu",
  "jis_x0201",
  "jis_x0208-1983",
  "jis_x0212-1990",
  "koi8-r",
  "koi8-u",
  "us-ascii",
  "utf-7",
  "utf-8",
  "cp037",
  "cp038",
  "cp275",
  "cp281",
  "cp290",
  "cp297",
  "cp367",
  "cp420",
  "cp423",
  "cp424",
  "cp437",
  "cp775",
  "cp850",
  "cp851",
  "cp852",
  "cp855",
  "cp857",
  "cp860",
  "cp861",
  "cp862",
  "cp863",
  "cp864",
  "cp865",
  "cp866",
  "cp869",
  "cp880",
  "cp891",
  "cp903",
  "cp904",
  "iso-ir-10",
  "iso-ir-100",
  "iso-ir-101",
  "iso-ir-102",
  "iso-ir-103",
  "iso-ir-109",
  "iso-ir-11",
  "iso-ir-110",
  "iso-ir-111",
  "iso-ir-121",
  "iso-ir-122",
  "iso-ir-123",
  "iso-ir-126",
  "iso-ir-127",
  "iso-ir-128",
  "iso-ir-13",
  "iso-ir-138",
  "iso-ir-139",
  "iso-ir-14",
  "iso-ir-141",
  "iso-ir-142",
  "iso-ir-143",
  "iso-ir-144",
  "iso-ir-146",
  "iso-ir-147",
  "iso-ir-148",
  "iso-ir-149",
  "iso-ir-15",
  "iso-ir-150",
  "iso-ir-151",
  "iso-ir-152",
  "iso-ir-153",
  "iso-ir-154",
  "iso-ir-155",
  "iso-ir-157",
  "iso-ir-158",
  "iso-ir-159",
  "iso-ir-16",
  "iso-ir-17",
  "iso-ir-18",
  "iso-ir-19",
  "iso-ir-2",
  "iso-ir-21",
  "iso-ir-25",
  "iso-ir-27",
  "iso-ir-37",
  "iso-ir-4",
  "iso-ir-42",
  "iso-ir-47",
  "iso-ir-49",
  "iso-ir-50",
  "iso-ir-51",
  "iso-ir-54",
  "iso-ir-55",
  "iso-ir-57",
  "iso-ir-58",
  "iso-ir-6",
  "iso-ir-60",
  "iso-ir-61",
  "iso-ir-69",
  "iso-ir-70",
  "iso-ir-8-1",
  "iso-ir-8-2",
  "iso-ir-84",
  "iso-ir-85",
  "iso-ir-86",
  "iso-ir-87",
  "iso-ir-88",
  "iso-ir-89",
  "iso-ir-9-1",
  "iso-ir-9-2",
  "iso-ir-90",
  "iso-ir-91",
  "iso-ir-92",
  "iso-ir-93",
  "iso-ir-94",
  "iso-ir-95",
  "iso-ir-96",
  "iso-ir-98",
  "iso-ir-99",
  "windows-1250",
  "windows-1251",
  "windows-1253",
  "windows-1254",
  "windows-1255",
  "windows-1256",
  "windows-1257",
  "windows-1258",
  NULL,
};

#endif