.README.md

> ./checkCountryName.sh China
People's Republic of China

checkCountryName.sh

#!/usr/bin/env sh
countryNameInput=$1
countryNameOutput=$(docker run \
    --interactive \
    --tty \
    --rm \
    --volume "$PWD":/source \
    php:cli-alpine php -r "require_once('/source/CountryApi.php'); echo CountryApi::_validateCountryName('$countryNameInput');");
echo $countryNameOutput
if [ "$2" = "--trump-mode" ] && [ "$countryNameOutput" = "People's Republic of China" ]
then
    echo "--  CHINA!  --  https://www.youtube.com/watch?v=RDrfE9I8_hs"
fi

CountryApi.php

<?php
// Copied from LF's SugarCRM system, but sans references to SugarAPI and ServiceBase
class CountryApi {

  /**
   * map of official country names to official 2-digit ISO
   * @see https://en.wikipedia.org/wiki/ISO_3166-1
   * @var array
   */
  private static $officialCountryNametoIsoList = array(
    'Afghanistan' => 'AF',
    'Åland Islands' => 'AX',
    'Albania' => 'AL',
    'Algeria' => 'DZ',
    'American Samoa' => 'AS',
    'Andorra' => 'AD',
    'Angola' => 'AO',
    'Anguilla' => 'AI',
    'Antarctica' => 'AQ',
    'Antigua and Barbuda' => 'AG',
    'Argentina' => 'AR',
    'Armenia' => 'AM',
    'Aruba' => 'AW',
    'Australia' => 'AU',
    'Austria' => 'AT',
    'Azerbaijan' => 'AZ',
    'Bahamas' => 'BS',
    'Bahrain' => 'BH',
    'Bangladesh' => 'BD',
    'Barbados' => 'BB',
    'Belarus' => 'BY',
    'Belgium' => 'BE',
    'Belize' => 'BZ',
    'Benin' => 'BJ',
    'Bermuda' => 'BM',
    'Bhutan' => 'BT',
    'Bolivia (Plurinational State of)' => 'BO',
    'Bonaire, Sint Eustatius and Saba' => 'BQ',
    'Bosnia and Herzegovina' => 'BA',
    'Botswana' => 'BW',
    'Bouvet Island' => 'BV',
    'Brazil' => 'BR',
    'British Indian Ocean Territory' => 'IO',
    'Brunei Darussalam' => 'BN',
    'Bulgaria' => 'BG',
    'Burkina Faso' => 'BF',
    'Burundi' => 'BI',
    'Cabo Verde' => 'CV',
    'Cambodia' => 'KH',
    'Cameroon' => 'CM',
    'Canada' => 'CA',
    'Cayman Islands' => 'KY',
    'Central African Republic' => 'CF',
    'Chad' => 'TD',
    'Chile' => 'CL',
    'People\'s Republic of China' => 'CN',
    'Christmas Island' => 'CX',
    'Cocos (Keeling) Islands' => 'CC',
    'Colombia' => 'CO',
    'Comoros' => 'KM',
    'Congo' => 'CG',
    'Congo (Democratic Republic of the)' => 'CD',
    'Cook Islands' => 'CK',
    'Costa Rica' => 'CR',
    'Côte d\'Ivoire' => 'CI',
    'Croatia' => 'HR',
    'Cuba' => 'CU',
    'Curaçao' => 'CW',
    'Cyprus' => 'CY',
    'Czech Republic' => 'CZ',
    'Denmark' => 'DK',
    'Djibouti' => 'DJ',
    'Dominica' => 'DM',
    'Dominican Republic' => 'DO',
    'Ecuador' => 'EC',
    'Egypt' => 'EG',
    'El Salvador' => 'SV',
    'Equatorial Guinea' => 'GQ',
    'Eritrea' => 'ER',
    'Estonia' => 'EE',
    'Ethiopia' => 'ET',
    'Falkland Islands (Malvinas)' => 'FK',
    'Faroe Islands' => 'FO',
    'Fiji' => 'FJ',
    'Finland' => 'FI',
    'France' => 'FR',
    'French Guiana' => 'GF',
    'French Polynesia' => 'PF',
    'French Southern Territories' => 'TF',
    'Gabon' => 'GA',
    'Gambia' => 'GM',
    'Georgia' => 'GE',
    'Germany' => 'DE',
    'Ghana' => 'GH',
    'Gibraltar' => 'GI',
    'Greece' => 'GR',
    'Greenland' => 'GL',
    'Grenada' => 'GD',
    'Guadeloupe' => 'GP',
    'Guam' => 'GU',
    'Guatemala' => 'GT',
    'Guernsey' => 'GG',
    'Guinea' => 'GN',
    'Guinea-Bissau' => 'GW',
    'Guyana' => 'GY',
    'Haiti' => 'HT',
    'Heard Island and McDonald Islands' => 'HM',
    'Holy See' => 'VA',
    'Honduras' => 'HN',
    'Hong Kong' => 'HK',
    'Hungary' => 'HU',
    'Iceland' => 'IS',
    'India' => 'IN',
    'Indonesia' => 'ID',
    'Iran (Islamic Republic of)' => 'IR',
    'Iraq' => 'IQ',
    'Ireland' => 'IE',
    'Isle of Man' => 'IM',
    'Israel' => 'IL',
    'Italy' => 'IT',
    'Jamaica' => 'JM',
    'Japan' => 'JP',
    'Jersey' => 'JE',
    'Jordan' => 'JO',
    'Kazakhstan' => 'KZ',
    'Kenya' => 'KE',
    'Kiribati' => 'KI',
    'Korea (Democratic People\'s Republic of)' => 'KP',
    'Korea (Republic of)' => 'KR',
    'Kuwait' => 'KW',
    'Kyrgyzstan' => 'KG',
    'Lao People\'s Democratic Republic' => 'LA',
    'Latvia' => 'LV',
    'Lebanon' => 'LB',
    'Lesotho' => 'LS',
    'Liberia' => 'LR',
    'Libya' => 'LY',
    'Liechtenstein' => 'LI',
    'Lithuania' => 'LT',
    'Luxembourg' => 'LU',
    'Macao' => 'MO',
    'Macedonia (the former Yugoslav Republic of)' => 'MK',
    'Madagascar' => 'MG',
    'Malawi' => 'MW',
    'Malaysia' => 'MY',
    'Maldives' => 'MV',
    'Mali' => 'ML',
    'Malta' => 'MT',
    'Marshall Islands' => 'MH',
    'Martinique' => 'MQ',
    'Mauritania' => 'MR',
    'Mauritius' => 'MU',
    'Mayotte' => 'YT',
    'Mexico' => 'MX',
    'Micronesia (Federated States of)' => 'FM',
    'Moldova (Republic of)' => 'MD',
    'Monaco' => 'MC',
    'Mongolia' => 'MN',
    'Montenegro' => 'ME',
    'Montserrat' => 'MS',
    'Morocco' => 'MA',
    'Mozambique' => 'MZ',
    'Myanmar' => 'MM',
    'Namibia' => 'NA',
    'Nauru' => 'NR',
    'Nepal' => 'NP',
    'Netherlands' => 'NL',
    'New Caledonia' => 'NC',
    'New Zealand' => 'NZ',
    'Nicaragua' => 'NI',
    'Niger' => 'NE',
    'Nigeria' => 'NG',
    'Niue' => 'NU',
    'Norfolk Island' => 'NF',
    'Northern Mariana Islands' => 'MP',
    'Norway' => 'NO',
    'Oman' => 'OM',
    'Pakistan' => 'PK',
    'Palau' => 'PW',
    'Palestine, State of' => 'PS',
    'Panama' => 'PA',
    'Papua New Guinea' => 'PG',
    'Paraguay' => 'PY',
    'Peru' => 'PE',
    'Philippines' => 'PH',
    'Pitcairn' => 'PN',
    'Poland' => 'PL',
    'Portugal' => 'PT',
    'Puerto Rico' => 'PR',
    'Qatar' => 'QA',
    'Réunion' => 'RE',
    'Romania' => 'RO',
    'Russian Federation' => 'RU',
    'Rwanda' => 'RW',
    'Saint Barthélemy' => 'BL',
    'Saint Helena, Ascension and Tristan da Cunha' => 'SH',
    'Saint Kitts and Nevis' => 'KN',
    'Saint Lucia' => 'LC',
    'Saint Martin (French part)' => 'MF',
    'Saint Pierre and Miquelon' => 'PM',
    'Saint Vincent and the Grenadines' => 'VC',
    'Samoa' => 'WS',
    'San Marino' => 'SM',
    'Sao Tome and Principe' => 'ST',
    'Saudi Arabia' => 'SA',
    'Senegal' => 'SN',
    'Serbia' => 'RS',
    'Seychelles' => 'SC',
    'Sierra Leone' => 'SL',
    'Singapore' => 'SG',
    'Sint Maarten (Dutch part)' => 'SX',
    'Slovakia' => 'SK',
    'Slovenia' => 'SI',
    'Solomon Islands' => 'SB',
    'Somalia' => 'SO',
    'South Africa' => 'ZA',
    'South Georgia and the South Sandwich Islands' => 'GS',
    'South Sudan' => 'SS',
    'Spain' => 'ES',
    'Sri Lanka' => 'LK',
    'Sudan' => 'SD',
    'Suriname' => 'SR',
    'Svalbard and Jan Mayen' => 'SJ',
    'Swaziland' => 'SZ',
    'Sweden' => 'SE',
    'Switzerland' => 'CH',
    'Syrian Arab Republic' => 'SY',
    'Taiwan, Province of China[a]' => 'TW',
    'Tajikistan' => 'TJ',
    'Tanzania, United Republic of' => 'TZ',
    'Thailand' => 'TH',
    'Timor-Leste' => 'TL',
    'Togo' => 'TG',
    'Tokelau' => 'TK',
    'Tonga' => 'TO',
    'Trinidad and Tobago' => 'TT',
    'Tunisia' => 'TN',
    'Turkey' => 'TR',
    'Turkmenistan' => 'TM',
    'Turks and Caicos Islands' => 'TC',
    'Tuvalu' => 'TV',
    'Uganda' => 'UG',
    'Ukraine' => 'UA',
    'United Arab Emirates' => 'AE',
    'United Kingdom of Great Britain and Northern Ireland' => 'GB',
    'United States of America' => 'US',
    'United States Minor Outlying Islands' => 'UM',
    'Uruguay' => 'UY',
    'Uzbekistan' => 'UZ',
    'Vanuatu' => 'VU',
    'Venezuela (Bolivarian Republic of)' => 'VE',
    'Viet Nam' => 'VN',
    'Virgin Islands (British)' => 'VG',
    'Virgin Islands (U.S.)' => 'VI',
    'Wallis and Futuna' => 'WF',
    'Western Sahara' => 'EH',
    'Yemen' => 'YE',
    'Zambia' => 'ZM',
    'Zimbabwe' => 'ZW',
  );

  /**
   * Map common conventions, legacy country names and frequently found typo's
   * to official country names. Keys are all lower case
   * @var array
   */
  private static $commonCountryNametoOfficialCountryNameList = array(
    'bolivia' => 'Bolivia (Plurinational State of)',
    'bosnia/herzegovina' => 'Bosnia and Herzegovina',
    'brasil' => 'Brazil',
    'china' => 'People\'s Republic of China',
    'china, peoples republic of' => 'People\'s Republic of China',
    'cote d&#039;ivoire' => 'Côte d\'Ivoire',
    'côte d’ivoire' => 'Côte d\'Ivoire',
    'hong kong s.a.r., china' => 'Hong Kong',
    'iran' => 'Iran (Islamic Republic of)',
    'iran, islamic republic of' => 'Iran (Islamic Republic of)',
    'kazakstan' => 'Kazakhstan',
    'korea' => 'Korea (Republic of)',
    'korea, republic of' => 'Korea (Republic of)',
    'korea, south' => 'Korea (Republic of)',
    'lao people&#039;s democratic republic' => 'Lao People\'s Democratic Republic',
    'laos' => 'Lao People\'s Democratic Republic',
    'libyan arab jamahiriya' => 'Libya',
    'macau' => 'Macao',
    'macedonia' => 'Macedonia (the former Yugoslav Republic of)',
    'moldova' => 'Moldova (Republic of)',
    'moldova, republic of' => 'Moldova (Republic of)',
    'netherlands antilles' => 'Netherlands',
    'p.r. china' => 'People\'s Republic of China',
    'p.r.china' => 'People\'s Republic of China',
    'palestinian territory' => 'Palestine, State of',
    'pr china' => 'People\'s Republic of China',
    'prc china' => 'People\'s Republic of China',
    'republic of korea' => 'Korea (Republic of)',
    'republic of south korea' => 'Korea (Republic of)',
    'roc' => 'Taiwan, Province of China[a]',
    'russia' => 'Russian Federation',
    'slovakia (slovak republic)' => 'Slovakia',
    'south korea' => 'Korea (Republic of)',
    'syria' => 'Syrian Arab Republic',
    'taiwan roc' => 'Taiwan, Province of China[a]',
    'taiwan' => 'Taiwan, Province of China[a]',
    'tanzania' => 'Tanzania, United Republic of',
    'the netherlands' => 'Netherlands',
    'u.s.' => 'United States of America',
    'u.s.a.' => 'United States of America',
    'uk' => 'United Kingdom of Great Britain and Northern Ireland',
    'united kingdom' => 'United Kingdom of Great Britain and Northern Ireland',
    'united states' => 'United States of America',
    'us' => 'United States of America',
    'usa' => 'United States of America',
    'venezuela' => 'Venezuela (Bolivarian Republic of)',
    'vietnam' => 'Viet Nam',
  );

  public function registerApiRest() {
    return array(
      'getCountriesList' => array(
        'reqType' => 'GET',
        'path' => array('getCountriesList'),
        'pathVars' => array(''),
        'method' => 'getCountriesList'
      ),
      'validateCountryName' => array(
        'reqType' => 'GET',
        'path' => array('validateCountryName', '?'),
        'pathVars' => array('', 'country'),
        'method' => 'validateCountryName'
      )
    );
  }

  /**
   * get list of proper country names and their ISO mappings
   * @return array
   */
  public static function getofficialCountryNametoIsoList() {
    return self::$officialCountryNametoIsoList;
  }

  /**
   * get list of common typo's mapped to official country names
   * @return array
   */
  public static function getcommonCountryNametoOfficialCountryNameList() {
    return self::$commonCountryNametoOfficialCountryNameList;
  }

  /**
   * Get the list of valid Country Names
   * @api
   * @param \ServiceBase $api
   * @param $args
   * @return array
   */
  public function getCountriesList($api, $args) {
    return array_keys($this->getofficialCountryNametoIsoList());
  }

  /**
   * Validate the passed-in name of a country, checking first for an official
   * country name and then for an unofficial one
   *
   * @param string $country
   * @return bool|string
   */
  public static function _validateCountryName($country) {
    if (empty($country)) {
      return FALSE;
    }

    /*
     * if the country name received is valid, return it as it came in
     */
    $country_to_iso = self::getofficialCountryNametoIsoList();
    if (isset($country_to_iso[$country])) {
      return $country;
    }

    /*
     * if the country name is valid but the casing is off, correct the casing
     */
    foreach ($country_to_iso as $country_name => $iso_code) {
      if (strtolower($country) == strtolower($country_name)) {
        return $country_name;
      }
      if (strtolower($country) == strtolower($iso_code)) {
        return $country_name;
      }
    }

    /*
     * if this is a valid ISO, return the associated country
     */
    if (in_array($country, $country_to_iso)) {
      $flipped = array_flip($country_to_iso);
      if (isset($flipped[$country])) {
        return $flipped[$country];
      }
    }

    /*
     * if the country name is a frequent convention or common typo, correct it
     * to the official country name. For easier comparison, just set to
     * lower-case
     */
    $typo_to_official = self::getcommonCountryNametoOfficialCountryNameList();
    foreach ($typo_to_official as $typo => $official) {
      if (trim(strtolower($country)) == $typo) {
        return $official;
      }
    }

    /*
     * check for metaphone for a sound-alike match, e.g. Chili => Chile
     */
    $metaphone = metaphone($country, 4);
    foreach ($country_to_iso as $country_name => $iso_code) {
      if (metaphone($country_name, 4) == $metaphone) {
        return $country_name;
      }
    }

    /*
     * try really hard ...
     */
    $clean_country = self::try_harder_clean($country);

    /*
     * try-harder match with official list
     */
    foreach ($country_to_iso as $country_name => $iso_code) {
      if ($clean_country == self::try_harder_clean($country_name)) {
        return $country_name;
      }
    }

    /*
     * try-hard match with a common typo
     */
    foreach ($typo_to_official as $typo => $official) {
      if ($clean_country == self::try_harder_clean($typo)) {
        return $official;
      }
    }


    return FALSE;

  }

  /**
   * Scrub a country name to try *really* hard for a direct comparison...
   * * trim
   * * drop case
   * * remove common words like "the" and "of"
   * * remove non-alphabetic characters
   *
   * @param string $value
   * @return string
   */
  private static function try_harder_clean($value) {
    $value = trim(strtolower($value));
    $value = str_replace(' of ', '', $value);
    $value = str_replace('the', '', $value);
    $value = str_replace('republic', '', $value);
    $value = str_replace('democratic', '', $value);
    $value = str_replace(' ', '', $value);
    $value = preg_replace("/[^A-Za-z]/", '', $value);
    return $value;
  }

  /**
   * @see CountryApi::_validateCountryName()
   * @api
   * @param \ServiceBase $api
   * @param $args
   * @return bool|string
   */
  public function validateCountryName($api, $args) {
    return !empty($args['country'])
      ? self::_validateCountryName($args['country'])
      : FALSE;
  }
}