Tools/world/world

   1 #! /usr/bin/env python
   2
   3 """world -- Print mappings between country names and DNS country codes.
   4
   5 Contact: Barry Warsaw
   6 Email:   barry@python.org
   7 Version: %(__version__)s
   8
   9 This script will take a list of Internet addresses and print out where in the
  10 world those addresses originate from, based on the top-level domain country
  11 code found in the address.  Addresses can be in any of the following forms:
  12
  13     xx                -- just the country code or top-level domain identifier
  14     host.domain.xx    -- any Internet host or network name
  15     somebody@where.xx -- an Internet email address
  16
  17 If no match is found, the address is interpreted as a regular expression and a
  18 reverse lookup is attempted.  This script will search the country names and
  19 print a list of matching entries.  You can force reverse mappings with the
  20 `-r' flag (see below).
  21
  22 For example:
  23
  24     %% world tz us
  25     tz originated from Tanzania, United Republic of
  26     us originated from United States
  27
  28     %% world united
  29     united matches 6 countries:
  30         ae: United Arab Emirates
  31         uk: United Kingdom (common practice)
  32         um: United States Minor Outlying Islands
  33         us: United States
  34         tz: Tanzania, United Republic of
  35         gb: United Kingdom
  36
  37 Country codes are maintained by the RIPE Network Coordination Centre,
  38 in coordination with the ISO 3166 Maintenance Agency at DIN Berlin.  The
  39 authoritative source of country code mappings is:
  40
  41     <url:ftp://ftp.ripe.net/iso3166-countrycodes.txt>
  42
  43 The latest known change to this information was:
  44
  45     Friday, 5 April 2002, 12.00 CET 2002
  46
  47 This script also knows about non-geographic top-level domains, and the
  48 additional ccTLDs reserved by IANA.
  49
  50 Usage: %(PROGRAM)s [-d] [-p file] [-o] [-h] addr [addr ...]
  51
  52     --dump
  53     -d
  54         Print mapping of all top-level domains.
  55
  56     --parse file
  57     -p file
  58         Parse an iso3166-countrycodes file extracting the two letter country
  59         code followed by the country name.  Note that the three letter country
  60         codes and numbers, which are also provided in the standard format
  61         file, are ignored.
  62
  63     --outputdict
  64     -o
  65         When used in conjunction with the `-p' option, output is in the form
  66         of a Python dictionary, and country names are normalized
  67         w.r.t. capitalization.  This makes it appropriate for cutting and
  68         pasting back into this file.  Output is always to standard out.
  69
  70     --reverse
  71     -r
  72         Force reverse lookup.  In this mode the address can be any Python
  73         regular expression; this is matched against all country names and a
  74         list of matching mappings is printed.  In normal mode (e.g. without
  75         this flag), reverse lookup is performed on addresses if no matching
  76         country code is found.
  77
  78     -h
  79     --help
  80         Print this message.
  81 """
  82 __version__ = '$Revision$'
  83
  84
  85 import sys
  86 import getopt
  87 import re
  88
  89 PROGRAM = sys.argv[0]
  90
  91
  92 \f
  93 def usage(code, msg=''):
  94     print __doc__ % globals()
  95     if msg:
  96         print msg
  97     sys.exit(code)
  98
  99
 100 \f
 101 def resolve(rawaddr):
 102     parts = rawaddr.split('.')
 103     if not len(parts):
 104         # no top level domain found, bounce it to the next step
 105         return rawaddr
 106     addr = parts[-1]
 107     if nameorgs.has_key(addr):
 108         print rawaddr, 'is in the', nameorgs[addr], 'top level domain'
 109         return None
 110     elif countries.has_key(addr):
 111         print rawaddr, 'originated from', countries[addr]
 112         return None
 113     else:
 114         # Not resolved, bounce it to the next step
 115         return rawaddr
 116
 117
 118 \f
 119 def reverse(regexp):
 120     matches = []
 121     cre = re.compile(regexp, re.IGNORECASE)
 122     for code, country in all.items():
 123         mo = cre.search(country)
 124         if mo:
 125             matches.append(code)
 126     # print results
 127     if not matches:
 128         # not resolved, bounce it to the next step
 129         return regexp
 130     if len(matches) == 1:
 131         code = matches[0]
 132         print regexp, "matches code `%s', %s" % (code, all[code])
 133     else:
 134         print regexp, 'matches %d countries:' % len(matches)
 135         for code in matches:
 136             print "    %s: %s" % (code, all[code])
 137     return None
 138
 139
 140 \f
 141 def parse(file, normalize):
 142     try:
 143         fp = open(file)
 144     except IOError, (err, msg):
 145         print msg, ':', file
 146
 147     cre = re.compile('(.*?)[ \t]+([A-Z]{2})[ \t]+[A-Z]{3}[ \t]+[0-9]{3}')
 148     scanning = 0
 149
 150     if normalize:
 151         print 'countries = {'
 152
 153     while 1:
 154         line = fp.readline()
 155         if line == '':
 156             break                       # EOF
 157         if scanning:
 158             mo = cre.match(line)
 159             if not mo:
 160                 line = line.strip()
 161                 if not line:
 162                     continue
 163                 elif line[0] == '-':
 164                     break
 165                 else:
 166                     print 'Could not parse line:', line
 167                     continue
 168             country, code = mo.group(1, 2)
 169             if normalize:
 170                 words = country.split()
 171                 for i in range(len(words)):
 172                     w = words[i]
 173                     # XXX special cases
 174                     if w in ('AND', 'OF', 'OF)', 'name:', 'METROPOLITAN'):
 175                         words[i] = w.lower()
 176                     elif w == 'THE' and i <> 1:
 177                         words[i] = w.lower()
 178                     elif len(w) > 3 and w[1] == "'":
 179                         words[i] = w[0:3].upper() + w[3:].lower()
 180                     elif w in ('(U.S.)', 'U.S.'):
 181                         pass
 182                     elif w[0] == '(' and w <> '(local':
 183                         words[i] = '(' + w[1:].capitalize()
 184                     elif w.find('-') <> -1:
 185                         words[i] = '-'.join(
 186                             [s.capitalize() for s in w.split('-')])
 187                     else:
 188                         words[i] = w.capitalize()
 189                 code = code.lower()
 190                 country = ' '.join(words)
 191                 print '    "%s": "%s",' % (code, country)
 192             else:
 193                 print code, country
 194
 195         elif line[0] == '-':
 196             scanning = 1
 197
 198     if normalize:
 199         print '    }'
 200
 201 \f
 202 def main():
 203     help = 0
 204     status = 0
 205     dump = 0
 206     parsefile = None
 207     normalize = 0
 208     forcerev = 0
 209
 210     try:
 211         opts, args = getopt.getopt(
 212             sys.argv[1:],
 213             'p:rohd',
 214             ['parse=', 'reverse', 'outputdict', 'help', 'dump'])
 215     except getopt.error, msg:
 216         usage(1, msg)
 217
 218     for opt, arg in opts:
 219         if opt in ('-h', '--help'):
 220             help = 1
 221         elif opt in ('-d', '--dump'):
 222             dump = 1
 223         elif opt in ('-p', '--parse'):
 224             parsefile = arg
 225         elif opt in ('-o', '--outputdict'):
 226             normalize = 1
 227         elif opt in ('-r', '--reverse'):
 228             forcerev = 1
 229
 230     if help:
 231         usage(status)
 232
 233     if dump:
 234         print 'Non-geographic domains:'
 235         codes = nameorgs.keys()
 236         codes.sort()
 237         for code in codes:
 238             print '    %4s:' % code, nameorgs[code]
 239
 240         print '\nCountry coded domains:'
 241         codes = countries.keys()
 242         codes.sort()
 243         for code in codes:
 244             print '    %2s:' % code, countries[code]
 245     elif parsefile:
 246         parse(parsefile, normalize)
 247     else:
 248         if not forcerev:
 249             args = filter(None, map(resolve, args))
 250         args = filter(None, map(reverse, args))
 251         for arg in args:
 252             print 'Where in the world is %s?' % arg
 253
 254
 255 \f
 256 # The mappings
 257 nameorgs = {
 258     # New top level domains as described by ICANN
 259     # http://www.icann.org/tlds/
 260     "aero": "air-transport industry",
 261     "arpa": "Arpanet",
 262     "biz": "business",
 263     "com": "commercial",
 264     "coop": "cooperatives",
 265     "edu": "educational",
 266     "gov": "government",
 267     "info": "unrestricted `info'",
 268     "int": "international",
 269     "mil": "military",
 270     "museum": "museums",
 271     "name": "`name' (for registration by individuals)",
 272     "net": "networking",
 273     "org": "non-commercial",
 274     "pro": "professionals",
 275     # These additional ccTLDs are included here even though they are not part
 276     # of ISO 3166.  IANA has 5 reserved ccTLDs as described here:
 277     #
 278     # http://www.iso.org/iso/en/prods-services/iso3166ma/04background-on-iso-3166/iso3166-1-and-ccTLDs.html
 279     #
 280     # but I can't find an official list anywhere.
 281     #
 282     # Note that `uk' is the common practice country code for the United
 283     # Kingdom.  AFAICT, the official `gb' code is routinely ignored!
 284     #
 285     # <D.M.Pick@qmw.ac.uk> tells me that `uk' was long in use before ISO3166
 286     # was adopted for top-level DNS zone names (although in the reverse order
 287     # like uk.ac.qmw) and was carried forward (with the reversal) to avoid a
 288     # large-scale renaming process as the UK switched from their old `Coloured
 289     # Book' protocols over X.25 to Internet protocols over IP.
 290     #
 291     # See <url:ftp://ftp.ripe.net/ripe/docs/ripe-159.txt>
 292     #
 293     # Also, `su', while obsolete is still in limited use.
 294     "ac": "Ascension Island",
 295     "gg": "Guernsey",
 296     "im": "Isle of Man",
 297     "je": "Jersey",
 298     "uk": "United Kingdom (common practice)",
 299     "su": "Soviet Union (still in limited use)",
 300     }
 301
 302
 303 \f
 304 countries = {
 305     "af": "Afghanistan",
 306     "al": "Albania",
 307     "dz": "Algeria",
 308     "as": "American Samoa",
 309     "ad": "Andorra",
 310     "ao": "Angola",
 311     "ai": "Anguilla",
 312     "aq": "Antarctica",
 313     "ag": "Antigua and Barbuda",
 314     "ar": "Argentina",
 315     "am": "Armenia",
 316     "aw": "Aruba",
 317     "au": "Australia",
 318     "at": "Austria",
 319     "az": "Azerbaijan",
 320     "bs": "Bahamas",
 321     "bh": "Bahrain",
 322     "bd": "Bangladesh",
 323     "bb": "Barbados",
 324     "by": "Belarus",
 325     "be": "Belgium",
 326     "bz": "Belize",
 327     "bj": "Benin",
 328     "bm": "Bermuda",
 329     "bt": "Bhutan",
 330     "bo": "Bolivia",
 331     "ba": "Bosnia and Herzegowina",
 332     "bw": "Botswana",
 333     "bv": "Bouvet Island",
 334     "br": "Brazil",
 335     "io": "British Indian Ocean Territory",
 336     "bn": "Brunei Darussalam",
 337     "bg": "Bulgaria",
 338     "bf": "Burkina Faso",
 339     "bi": "Burundi",
 340     "kh": "Cambodia",
 341     "cm": "Cameroon",
 342     "ca": "Canada",
 343     "cv": "Cape Verde",
 344     "ky": "Cayman Islands",
 345     "cf": "Central African Republic",
 346     "td": "Chad",
 347     "cl": "Chile",
 348     "cn": "China",
 349     "cx": "Christmas Island",
 350     "cc": "Cocos (Keeling) Islands",
 351     "co": "Colombia",
 352     "km": "Comoros",
 353     "cg": "Congo",
 354     "cd": "Congo, The Democratic Republic of the",
 355     "ck": "Cook Islands",
 356     "cr": "Costa Rica",
 357     "ci": "Cote D'Ivoire",
 358     "hr": "Croatia",
 359     "cu": "Cuba",
 360     "cy": "Cyprus",
 361     "cz": "Czech Republic",
 362     "dk": "Denmark",
 363     "dj": "Djibouti",
 364     "dm": "Dominica",
 365     "do": "Dominican Republic",
 366     "tp": "East Timor",
 367     "ec": "Ecuador",
 368     "eg": "Egypt",
 369     "sv": "El Salvador",
 370     "gq": "Equatorial Guinea",
 371     "er": "Eritrea",
 372     "ee": "Estonia",
 373     "et": "Ethiopia",
 374     "fk": "Falkland Islands (Malvinas)",
 375     "fo": "Faroe Islands",
 376     "fj": "Fiji",
 377     "fi": "Finland",
 378     "fr": "France",
 379     "gf": "French Guiana",
 380     "pf": "French Polynesia",
 381     "tf": "French Southern Territories",
 382     "ga": "Gabon",
 383     "gm": "Gambia",
 384     "ge": "Georgia",
 385     "de": "Germany",
 386     "gh": "Ghana",
 387     "gi": "Gibraltar",
 388     "gr": "Greece",
 389     "gl": "Greenland",
 390     "gd": "Grenada",
 391     "gp": "Guadeloupe",
 392     "gu": "Guam",
 393     "gt": "Guatemala",
 394     "gn": "Guinea",
 395     "gw": "Guinea-Bissau",
 396     "gy": "Guyana",
 397     "ht": "Haiti",
 398     "hm": "Heard Island and Mcdonald Islands",
 399     "va": "Holy See (Vatican City State)",
 400     "hn": "Honduras",
 401     "hk": "Hong Kong",
 402     "hu": "Hungary",
 403     "is": "Iceland",
 404     "in": "India",
 405     "id": "Indonesia",
 406     "ir": "Iran, Islamic Republic of",
 407     "iq": "Iraq",
 408     "ie": "Ireland",
 409     "il": "Israel",
 410     "it": "Italy",
 411     "jm": "Jamaica",
 412     "jp": "Japan",
 413     "jo": "Jordan",
 414     "kz": "Kazakstan",
 415     "ke": "Kenya",
 416     "ki": "Kiribati",
 417     "kp": "Korea, Democratic People's Republic of",
 418     "kr": "Korea, Republic of",
 419     "kw": "Kuwait",
 420     "kg": "Kyrgyzstan",
 421     "la": "Lao People's Democratic Republic",
 422     "lv": "Latvia",
 423     "lb": "Lebanon",
 424     "ls": "Lesotho",
 425     "lr": "Liberia",
 426     "ly": "Libyan Arab Jamahiriya",
 427     "li": "Liechtenstein",
 428     "lt": "Lithuania",
 429     "lu": "Luxembourg",
 430     "mo": "Macau",
 431     "mk": "Macedonia, The Former Yugoslav Republic of",
 432     "mg": "Madagascar",
 433     "mw": "Malawi",
 434     "my": "Malaysia",
 435     "mv": "Maldives",
 436     "ml": "Mali",
 437     "mt": "Malta",
 438     "mh": "Marshall Islands",
 439     "mq": "Martinique",
 440     "mr": "Mauritania",
 441     "mu": "Mauritius",
 442     "yt": "Mayotte",
 443     "mx": "Mexico",
 444     "fm": "Micronesia, Federated States of",
 445     "md": "Moldova, Republic of",
 446     "mc": "Monaco",
 447     "mn": "Mongolia",
 448     "ms": "Montserrat",
 449     "ma": "Morocco",
 450     "mz": "Mozambique",
 451     "mm": "Myanmar",
 452     "na": "Namibia",
 453     "nr": "Nauru",
 454     "np": "Nepal",
 455     "nl": "Netherlands",
 456     "an": "Netherlands Antilles",
 457     "nc": "New Caledonia",
 458     "nz": "New Zealand",
 459     "ni": "Nicaragua",
 460     "ne": "Niger",
 461     "ng": "Nigeria",
 462     "nu": "Niue",
 463     "nf": "Norfolk Island",
 464     "mp": "Northern Mariana Islands",
 465     "no": "Norway",
 466     "om": "Oman",
 467     "pk": "Pakistan",
 468     "pw": "Palau",
 469     "ps": "Palestinian Territory, Occupied",
 470     "pa": "Panama",
 471     "pg": "Papua New Guinea",
 472     "py": "Paraguay",
 473     "pe": "Peru",
 474     "ph": "Philippines",
 475     "pn": "Pitcairn",
 476     "pl": "Poland",
 477     "pt": "Portugal",
 478     "pr": "Puerto Rico",
 479     "qa": "Qatar",
 480     "re": "Reunion",
 481     "ro": "Romania",
 482     "ru": "Russian Federation",
 483     "rw": "Rwanda",
 484     "sh": "Saint Helena",
 485     "kn": "Saint Kitts and Nevis",
 486     "lc": "Saint Lucia",
 487     "pm": "Saint Pierre and Miquelon",
 488     "vc": "Saint Vincent and the Grenadines",
 489     "ws": "Samoa",
 490     "sm": "San Marino",
 491     "st": "Sao Tome and Principe",
 492     "sa": "Saudi Arabia",
 493     "sn": "Senegal",
 494     "sc": "Seychelles",
 495     "sl": "Sierra Leone",
 496     "sg": "Singapore",
 497     "sk": "Slovakia",
 498     "si": "Slovenia",
 499     "sb": "Solomon Islands",
 500     "so": "Somalia",
 501     "za": "South Africa",
 502     "gs": "South Georgia and the South Sandwich Islands",
 503     "es": "Spain",
 504     "lk": "Sri Lanka",
 505     "sd": "Sudan",
 506     "sr": "Suriname",
 507     "sj": "Svalbard and Jan Mayen",
 508     "sz": "Swaziland",
 509     "se": "Sweden",
 510     "ch": "Switzerland",
 511     "sy": "Syrian Arab Republic",
 512     "tw": "Taiwan, Province of China",
 513     "tj": "Tajikistan",
 514     "tz": "Tanzania, United Republic of",
 515     "th": "Thailand",
 516     "tg": "Togo",
 517     "tk": "Tokelau",
 518     "to": "Tonga",
 519     "tt": "Trinidad and Tobago",
 520     "tn": "Tunisia",
 521     "tr": "Turkey",
 522     "tm": "Turkmenistan",
 523     "tc": "Turks and Caicos Islands",
 524     "tv": "Tuvalu",
 525     "ug": "Uganda",
 526     "ua": "Ukraine",
 527     "ae": "United Arab Emirates",
 528     "gb": "United Kingdom",
 529     "us": "United States",
 530     "um": "United States Minor Outlying Islands",
 531     "uy": "Uruguay",
 532     "uz": "Uzbekistan",
 533     "vu": "Vanuatu",
 534     "ve": "Venezuela",
 535     "vn": "Viet Nam",
 536     "vg": "Virgin Islands, British",
 537     "vi": "Virgin Islands, U.S.",
 538     "wf": "Wallis and Futuna",
 539     "eh": "Western Sahara",
 540     "ye": "Yemen",
 541     "yu": "Yugoslavia",
 542     "zm": "Zambia",
 543     "zw": "Zimbabwe",
 544     }
 545
 546 all = nameorgs.copy()
 547 all.update(countries)
 548
 549 \f
 550 if __name__ == '__main__':
 551     main()