cpython/Tools/world/world

#! /usr/bin/env python

"""world -- Print mappings between country names and DNS country codes.

Contact: Barry Warsaw
Email:   barry@python.org
Version: %(__version__)s

This script will take a list of Internet addresses and print out where in the
world those addresses originate from, based on the top-level domain country
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

If no match is found, the address is interpreted as a regular expression and a
reverse lookup is attempted.  This script will search the country names and
print a list of matching entries.  You can force reverse mappings with the
`-r' flag (see below).

For example:

    %% world tz us
    tz originated from Tanzania, United Republic of
    us originated from United States

    %% world united
    united matches 6 countries:
        ae: United Arab Emirates
        uk: United Kingdom (common practice)
        um: United States Minor Outlying Islands
        us: United States
        tz: Tanzania, United Republic of
        gb: United Kingdom

Country codes are maintained by the RIPE Network Coordination Centre,
in coordination with the ISO 3166 Maintenance Agency at DIN Berlin.  The
authoritative source of country code mappings is:

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

The latest known change to this information was:

    Friday, 5 April 2002, 12.00 CET 2002

This script also knows about non-geographic top-level domains, and the
additional ccTLDs reserved by IANA.

Usage: %(PROGRAM)s [-d] [-p file] [-o] [-h] addr [addr ...]

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

    --parse file
    -p file
        Parse an iso3166-countrycodes file extracting the two letter country
        code followed by the country name.  Note that the three letter country
        codes and numbers, which are also provided in the standard format
        file, are ignored.

    --outputdict
    -o
        When used in conjunction with the `-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.  Output is always to standard out.

    --reverse
    -r
        Force reverse lookup.  In this mode the address can be any Python
        regular expression; this is matched against all country names and a
        list of matching mappings is printed.  In normal mode (e.g. without
        this flag), reverse lookup is performed on addresses if no matching
        country code is found.

    -h
    --help
        Print this message.
"""
__version__ = '$Revision$'


import sys
import getopt
import re

PROGRAM = sys.argv[0]



def usage(code, msg=''):
    print __doc__ % globals()
    if msg:
        print msg
    sys.exit(code)



def resolve(rawaddr):
    parts = rawaddr.split('.')
    if not len(parts):
        # no top level domain found, bounce it to the next step
        return rawaddr
    addr = parts[-1]
    if nameorgs.has_key(addr):
        print rawaddr, 'is in the', nameorgs[addr], 'top level domain'
        return None
    elif countries.has_key(addr):
        print rawaddr, 'originated from', countries[addr]
        return None
    else:
        # Not resolved, bounce it to the next step
        return rawaddr



def reverse(regexp):
    matches = []
    cre = re.compile(regexp, re.IGNORECASE)
    for code, country in all.items():
        mo = cre.search(country)
        if mo:
            matches.append(code)
    # print results
    if not matches:
        # not resolved, bounce it to the next step
        return regexp
    if len(matches) == 1:
        code = matches[0]
        print regexp, "matches code `%s', %s" % (code, all[code])
    else:
        print regexp, 'matches %d countries:' % len(matches)
        for code in matches:
            print "    %s: %s" % (code, all[code])
    return None



def parse(file, normalize):
    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 'countries = {'

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

    try:
        opts, args = getopt.getopt(
            sys.argv[1:],
            'p:rohd',
            ['parse=', 'reverse', 'outputdict', 'help', 'dump'])
    except getopt.error, msg:
        usage(1, msg)

    for opt, arg in opts:
        if opt in ('-h', '--help'):
            help = 1
        elif opt in ('-d', '--dump'):
            dump = 1
        elif opt in ('-p', '--parse'):
            parsefile = arg
        elif opt in ('-o', '--outputdict'):
            normalize = 1
        elif opt in ('-r', '--reverse'):
            forcerev = 1

    if help:
        usage(status)

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

        print '\nCountry coded domains:'
        codes = countries.keys()
        codes.sort()
        for code in codes:
            print '    %2s:' % code, countries[code]
    elif parsefile:
        parse(parsefile, normalize)
    else:
        if not forcerev:
            args = filter(None, map(resolve, args))
        args = filter(None, map(reverse, args))
        for arg in args:
            print 'Where in the world is %s?' % arg



# The mappings
nameorgs = {
    # New top level domains as described by ICANN
    # http://www.icann.org/tlds/
    "aero": "air-transport industry",
    "arpa": "Arpanet",
    "biz": "business",
    "com": "commercial",
    "coop": "cooperatives",
    "edu": "educational",
    "gov": "government",
    "info": "unrestricted `info'",
    "int": "international",
    "mil": "military",
    "museum": "museums",
    "name": "`name' (for registration by individuals)",
    "net": "networking",
    "org": "non-commercial",
    "pro": "professionals",
    # These additional ccTLDs are included here even though they are not part
    # of ISO 3166.  IANA has 5 reserved ccTLDs as described here:
    #
    # http://www.iso.org/iso/en/prods-services/iso3166ma/04background-on-iso-3166/iso3166-1-and-ccTLDs.html
    #
    # but I can't find an official list anywhere.
    #
    # Note that `uk' is the common practice country code for the United
    # Kingdom.  AFAICT, the official `gb' code is routinely ignored!
    #
    # <D.M.Pick@qmw.ac.uk> tells me that `uk' was long in use before ISO3166
    # was adopted for top-level DNS zone names (although in the reverse order
    # like uk.ac.qmw) and was carried forward (with the reversal) to avoid a
    # large-scale renaming process as the UK switched from their old `Coloured
    # Book' protocols over X.25 to Internet protocols over IP.
    #
    # See <url:ftp://ftp.ripe.net/ripe/docs/ripe-159.txt>
    #
    # Also, `su', while obsolete is still in limited use.
    "ac": "Ascension Island",
    "gg": "Guernsey",
    "im": "Isle of Man",
    "je": "Jersey",
    "uk": "United Kingdom (common practice)",
    "su": "Soviet Union (still in limited use)",
    }



countries = {
    "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",
    "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",
    "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 Island and Mcdonald 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": "Kazakstan",
    "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",
    "ps": "Palestinian Territory, Occupied",
    "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",
    "sh": "Saint Helena",
    "kn": "Saint Kitts and Nevis",
    "lc": "Saint Lucia",
    "pm": "Saint Pierre and Miquelon",
    "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",
    "si": "Slovenia",
    "sb": "Solomon Islands",
    "so": "Somalia",
    "za": "South Africa",
    "gs": "South Georgia and the South Sandwich Islands",
    "es": "Spain",
    "lk": "Sri Lanka",
    "sd": "Sudan",
    "sr": "Suriname",
    "sj": "Svalbard and Jan Mayen",
    "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",
    "eh": "Western Sahara",
    "ye": "Yemen",
    "yu": "Yugoslavia",
    "zm": "Zambia",
    "zw": "Zimbabwe",
    }

all = nameorgs.copy()
all.update(countries)


if __name__ == '__main__':
    main()