cpython/Tools/world/world

#! /usr/bin/env python

"""Print the long name of an Internet domain.

This script will take an Internet address and print out where in the
world that message originated from, based on the top-level domain code
found in the address.  Addresses can be in any of the following forms:

    xx                -- just the country code or top-level domain identifier
    host.domain.xx    -- any Internet host or network name
    somebody@where.xx -- an Internet email address

Country codes are maintained by the RIPE Network Coordination Centre,
in coordination with the ISO 3166 Maintenance Agency at DIN Berlin.

    <url:ftp://info.ripe.net/iso3166-countrycodes>

The latest known change to this information was:

    Thu Aug  7 17:59:51 MET DST 1997

This script also knows about non-geographic top-level domains.

Usage: %s [-d] [-p|-P file] [-h] addr [addr ...]

    --dump
    -d
        Print mapping of all top-level domains.

    --parse file
    --p file
    --P file
    --Parse file
        Parse an iso3166-countrycodes file (given as the argument).
        This first the two letter country code (it ignores the three
        letter code), followed by the country name.  With -P option,
        output is in the form of a Python dictionary, and country
        names are normalized w.r.t. capitalization.  This makes it
        appropriate for cutting and pasting back into this file.

    -h
    --help
        Print this message.

"""
__version__ = '2.0'
__author__ = 'Barry Warsaw <bwarsaw@python.org>'
__source__ = '<url:http://www.python.org/~bwarsaw/pyware/>'


import sys
import string
import getopt



def usage(status=0):
    print __doc__ % sys.argv[0]
    sys.exit(status)


def resolve(rawaddr):
    parts = string.splitfields(rawaddr, '.')
    if not len(parts):
	print 'No top-level domain in:', rawaddr
	return
    addr = parts[-1]
    if nameorg.has_key(addr):
	print rawaddr, 'is from a', nameorg[addr], 'organization'
    elif country.has_key(addr):
	print rawaddr, 'originated from', country[addr]
    else:
	print 'Where in the world is %s?' % rawaddr



def parse(file, normalize):
    try:
	import re
    except ImportError:
	print 'Parsing requires Python 1.5'
	sys.exit(1)

    try:
	fp = open(file)
    except IOError, (err, msg):
	print msg, ':', file

    cre = re.compile('(.*?)[ \t]+([A-Z]{2})[ \t]+[A-Z]{3}[ \t]+[0-9]{3}')
    scanning = 0

    if normalize:
	print 'country = {'

    while 1:
	line = fp.readline()
	if line == '':
	    break			# EOF
	if scanning:
	    mo = cre.match(line)
	    if not mo:
		line = string.strip(line)
		if not line:
		    continue
		elif line[0] == '-':
		    break
		else:
		    print 'Could not parse line:', line
		    continue
	    country, code = mo.group(1, 2)
	    if normalize:
		words = string.split(country)
		for i in range(len(words)):
		    w = words[i]
		    # XXX special cases
		    if w in ('AND', 'OF', 'OF)', 'name:', 'METROPOLITAN'):
			words[i] = string.lower(w)
		    elif w == 'THE' and i <> 1:
			words[i] = string.lower(w)
		    elif len(w) > 3 and w[1] == "'":
			words[i] = string.upper(w[0:3]) + \
				   string.lower(w[3:])
		    elif w == '(U.S.)':
			pass
		    elif w[0] == '(' and w <> '(local':
			words[i] = '(' + string.capitalize(w[1:])
		    elif string.find(w, '-'):
			words[i] = string.join(
			    map(string.capitalize, string.split(w, '-')),
			    '-')
		    else:
			words[i] = string.capitalize(w)
		code = string.lower(code)
		country = string.join(words)
		print '    "%s": "%s",' % (code, country)
	    else:
		print code, country
	    
	elif line[0] == '-':
	    scanning = 1

    if normalize:
	print '    }'


def main():
    help = 0
    status = 0
    dump = 0
    parsefile = None
    normalize = 0

    opts, args = getopt.getopt(sys.argv[1:],
			       'p:P:hd',
			       ['parse', 'Parse', 'PARSE', 'help', 'dump'])
    for arg, val in opts:
	if arg in ('-h', '--help'):
	    help = 1
	elif arg in ('-d', '--dump'):
	    dump = 1
	elif arg in ('-p', '--parse'):
	    parsefile = val
	elif arg in ('-P', '--Parse', '--PARSE'):
	    parsefile = val
	    normalize = 1

    if help:
	usage(status)

    if dump:
	print 'Non-geographic domains:'
	codes = nameorg.keys()
	codes.sort()
	for code in codes:
	    print '    %4s:' % code, nameorg[code]

	print '\nCountry coded domains:'
	codes = country.keys()
	codes.sort()
	for code in codes:
	    print '    %2s:' % code, country[code]
    elif parsefile:
	parse(parsefile, normalize)
    else:
	map(resolve, args)



# The mappings
nameorg = {
    "arpa": "Arpanet",
    "com": "commercial",
    "edu": "educational",
    "gov": "government",
    "mil": "military",
    "net": "networking",
    "org": "non-commercial",
    "int": "international",
    }



country = {
    "af": "Afghanistan",
    "al": "Albania",
    "dz": "Algeria",
    "as": "American Samoa",
    "ad": "Andorra",
    "ao": "Angola",
    "ai": "Anguilla",
    "aq": "Antarctica",
    "ag": "Antigua and Barbuda",
    "ar": "Argentina",
    "am": "Armenia",
    "aw": "Aruba",
    "au": "Australia",
    "at": "Austria",
    "az": "Azerbaijan",
    "bs": "Bahamas",
    "bh": "Bahrain",
    "bd": "Bangladesh",
    "bb": "Barbados",
    "by": "Belarus",
    "be": "Belgium",
    "bz": "Belize",
    "bj": "Benin",
    "bm": "Bermuda",
    "bt": "Bhutan",
    "bo": "Bolivia",
    "ba": "Bosnia and Herzegowina",
    "bw": "Botswana",
    "bv": "Bouvet Island",
    "br": "Brazil",
    "io": "British Indian Ocean Territory",
    "bn": "Brunei Darussalam",
    "bg": "Bulgaria",
    "bf": "Burkina Faso",
    "bi": "Burundi",
    "kh": "Cambodia",
    "cm": "Cameroon",
    "ca": "Canada",
    "cv": "Cape Verde",
    "ky": "Cayman Islands",
    "cf": "Central African Republic",
    "td": "Chad",
    "cl": "Chile",
    "cn": "China",
    "cx": "Christmas Island",
    "cc": "Cocos (Keeling) Islands",
    "co": "Colombia",
    "km": "Comoros",
    "cg": "Congo",
    "cd": "Congo, The Democratic Republic of the",
    "ck": "Cook Islands",
    "cr": "Costa Rica",
    "ci": "Cote D'Ivoire",
    "hr": "Croatia (local name: Hrvatska)",
    "cu": "Cuba",
    "cy": "Cyprus",
    "cz": "Czech Republic",
    "dk": "Denmark",
    "dj": "Djibouti",
    "dm": "Dominica",
    "do": "Dominican Republic",
    "tp": "East Timor",
    "ec": "Ecuador",
    "eg": "Egypt",
    "sv": "El Salvador",
    "gq": "Equatorial Guinea",
    "er": "Eritrea",
    "ee": "Estonia",
    "et": "Ethiopia",
    "fk": "Falkland Islands (Malvinas)",
    "fo": "Faroe Islands",
    "fj": "Fiji",
    "fi": "Finland",
    "fr": "France",
    "fx": "France, metropolitan",
    "gf": "French Guiana",
    "pf": "French Polynesia",
    "tf": "French Southern Territories",
    "ga": "Gabon",
    "gm": "Gambia",
    "ge": "Georgia",
    "de": "Germany",
    "gh": "Ghana",
    "gi": "Gibraltar",
    "gr": "Greece",
    "gl": "Greenland",
    "gd": "Grenada",
    "gp": "Guadeloupe",
    "gu": "Guam",
    "gt": "Guatemala",
    "gn": "Guinea",
    "gw": "Guinea-Bissau",
    "gy": "Guyana",
    "ht": "Haiti",
    "hm": "Heard and Mc Donald Islands",
    "va": "Holy See (Vatican City State)",
    "hn": "Honduras",
    "hk": "Hong Kong",
    "hu": "Hungary",
    "is": "Iceland",
    "in": "India",
    "id": "Indonesia",
    "ir": "Iran (Islamic Republic of)",
    "iq": "Iraq",
    "ie": "Ireland",
    "il": "Israel",
    "it": "Italy",
    "jm": "Jamaica",
    "jp": "Japan",
    "jo": "Jordan",
    "kz": "Kazakhstan",
    "ke": "Kenya",
    "ki": "Kiribati",
    "kp": "Korea, Democratic People's Republic of",
    "kr": "Korea, Republic of",
    "kw": "Kuwait",
    "kg": "Kyrgyzstan",
    "la": "Lao People's Democratic Republic",
    "lv": "Latvia",
    "lb": "Lebanon",
    "ls": "Lesotho",
    "lr": "Liberia",
    "ly": "Libyan Arab Jamahiriya",
    "li": "Liechtenstein",
    "lt": "Lithuania",
    "lu": "Luxembourg",
    "mo": "Macau",
    "mk": "Macedonia, The Former Yugoslav Republic of",
    "mg": "Madagascar",
    "mw": "Malawi",
    "my": "Malaysia",
    "mv": "Maldives",
    "ml": "Mali",
    "mt": "Malta",
    "mh": "Marshall Islands",
    "mq": "Martinique",
    "mr": "Mauritania",
    "mu": "Mauritius",
    "yt": "Mayotte",
    "mx": "Mexico",
    "fm": "Micronesia, Federated States of",
    "md": "Moldova, Republic of",
    "mc": "Monaco",
    "mn": "Mongolia",
    "ms": "Montserrat",
    "ma": "Morocco",
    "mz": "Mozambique",
    "mm": "Myanmar",
    "na": "Namibia",
    "nr": "Nauru",
    "np": "Nepal",
    "nl": "Netherlands",
    "an": "Netherlands Antilles",
    "nc": "New Caledonia",
    "nz": "New Zealand",
    "ni": "Nicaragua",
    "ne": "Niger",
    "ng": "Nigeria",
    "nu": "Niue",
    "nf": "Norfolk Island",
    "mp": "Northern Mariana Islands",
    "no": "Norway",
    "om": "Oman",
    "pk": "Pakistan",
    "pw": "Palau",
    "pa": "Panama",
    "pg": "Papua New Guinea",
    "py": "Paraguay",
    "pe": "Peru",
    "ph": "Philippines",
    "pn": "Pitcairn",
    "pl": "Poland",
    "pt": "Portugal",
    "pr": "Puerto Rico",
    "qa": "Qatar",
    "re": "Reunion",
    "ro": "Romania",
    "ru": "Russian Federation",
    "rw": "Rwanda",
    "kn": "Saint Kitts and Nevis",
    "lc": "Saint Lucia",
    "vc": "Saint Vincent and the Grenadines",
    "ws": "Samoa",
    "sm": "San Marino",
    "st": "Sao Tome and Principe",
    "sa": "Saudi Arabia",
    "sn": "Senegal",
    "sc": "Seychelles",
    "sl": "Sierra Leone",
    "sg": "Singapore",
    "sk": "Slovakia (Slovak Republic)",
    "si": "Slovenia",
    "sb": "Solomon Islands",
    "so": "Somalia",
    "za": "South Africa",
    "gs": "South Georgia and the South Sandwich Islands",
    "es": "Spain",
    "lk": "Sri Lanka",
    "sh": "St. Helena",
    "pm": "St. Pierre and Miquelon",
    "sd": "Sudan",
    "sr": "Suriname",
    "sj": "Svalbard and Jan Mayen Islands",
    "sz": "Swaziland",
    "se": "Sweden",
    "ch": "Switzerland",
    "sy": "Syrian Arab Republic",
    "tw": "Taiwan, Province of China",
    "tj": "Tajikistan",
    "tz": "Tanzania, United Republic of",
    "th": "Thailand",
    "tg": "Togo",
    "tk": "Tokelau",
    "to": "Tonga",
    "tt": "Trinidad and Tobago",
    "tn": "Tunisia",
    "tr": "Turkey",
    "tm": "Turkmenistan",
    "tc": "Turks and Caicos Islands",
    "tv": "Tuvalu",
    "ug": "Uganda",
    "ua": "Ukraine",
    "ae": "United Arab Emirates",
    "gb": "United Kingdom",
    "us": "United States",
    "um": "United States Minor Outlying Islands",
    "uy": "Uruguay",
    "uz": "Uzbekistan",
    "vu": "Vanuatu",
    "ve": "Venezuela",
    "vn": "Viet Nam",
    "vg": "Virgin Islands (British)",
    "vi": "Virgin Islands (U.S.)",
    "wf": "Wallis and Futuna Islands",
    "eh": "Western Sahara",
    "ye": "Yemen",
    "yu": "Yugoslavia",
    "zm": "Zambia",
    "zw": "Zimbabwe",
    }


if __name__ == '__main__':
    main()