@vannizhang/living-atlas-content-validator 1.5.13 → 1.5.14

package/dist/lib/recommendedText/matchLocationInfo.js

@@ -0,0 +1,744 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.matchLocationInfo = void 0;
+const helpers_1 = require("./helpers");
+const TitleSummaryMatchingPatterns_json_1 = __importDefault(require("../../data/TitleSummaryMatchingPatterns.json"));
+const WORLD_COUNTRIES = [
+    'Afghanistan',
+    'Albania',
+    'Algeria',
+    'American Samoa',
+    'Andorra',
+    'Angola',
+    'Anguilla',
+    'Antarctica',
+    'Antigua and Barbuda',
+    'Argentina',
+    'Armenia',
+    'Aruba',
+    'Australia',
+    'Austria',
+    'Azerbaijan',
+    'Azores',
+    'Bahamas',
+    'Bahrain',
+    'Bangladesh',
+    'Barbados',
+    'Belarus',
+    'Belgium',
+    'Belize',
+    'Benin',
+    'Bermuda',
+    'Bhutan',
+    'Bolivia',
+    'Bonaire',
+    'Bosnia and Herzegovina',
+    'Botswana',
+    'Bouvet Island',
+    'Brazil',
+    'British Indian Ocean Territory',
+    'British Virgin Islands',
+    'Brunei Darussalam',
+    'Bulgaria',
+    'Burkina Faso',
+    'Burundi',
+    'Cabo Verde',
+    'Cambodia',
+    'Cameroon',
+    'Canada',
+    'Canarias',
+    'Cayman Islands',
+    'Central African Republic',
+    'Chad',
+    'Chile',
+    'China',
+    'Christmas Island',
+    'Cocos Islands',
+    'Colombia',
+    'Comoros',
+    'Congo',
+    'Congo DRC',
+    'Cook Islands',
+    'Costa Rica',
+    "Côte d'Ivoire",
+    'Croatia',
+    'Cuba',
+    'Curacao',
+    'Cyprus',
+    'Czech Republic',
+    'Denmark',
+    'Djibouti',
+    'Dominica',
+    'Dominican Republic',
+    'Ecuador',
+    'Egypt',
+    'El Salvador',
+    'Equatorial Guinea',
+    'Eritrea',
+    'Estonia',
+    'Eswatini',
+    'Ethiopia',
+    'Falkland Islands',
+    'Faroe Islands',
+    'Fiji',
+    'Finland',
+    'France',
+    'French Guiana',
+    'French Polynesia',
+    'French Southern Territories',
+    'Gabon',
+    'Gambia',
+    'Georgia',
+    'Germany',
+    'Ghana',
+    'Gibraltar',
+    'Glorioso Islands',
+    'Greece',
+    'Greenland',
+    'Grenada',
+    'Guadeloupe',
+    'Guam',
+    'Guatemala',
+    'Guernsey',
+    'Guinea',
+    'Guinea-Bissau',
+    'Guyana',
+    'Haiti',
+    'Heard Island and McDonald Islands',
+    'Honduras',
+    'Hungary',
+    'Iceland',
+    'India',
+    'Indonesia',
+    'Iran',
+    'Iraq',
+    'Ireland',
+    'Isle of Man',
+    'Israel',
+    'Italy',
+    'Jamaica',
+    'Japan',
+    'Jersey',
+    'Jordan',
+    'Juan De Nova Island',
+    'Kazakhstan',
+    'Kenya',
+    'Kiribati',
+    'Kuwait',
+    'Kyrgyzstan',
+    'Laos',
+    'Latvia',
+    'Lebanon',
+    'Lesotho',
+    'Liberia',
+    'Libya',
+    'Liechtenstein',
+    'Lithuania',
+    'Luxembourg',
+    'Madagascar',
+    'Madeira',
+    'Malawi',
+    'Malaysia',
+    'Maldives',
+    'Mali',
+    'Malta',
+    'Marshall Islands',
+    'Martinique',
+    'Mauritania',
+    'Mauritius',
+    'Mayotte',
+    'Mexico',
+    'Micronesia',
+    'Moldova',
+    'Monaco',
+    'Mongolia',
+    'Montenegro',
+    'Montserrat',
+    'Morocco',
+    'Mozambique',
+    'Myanmar',
+    'Namibia',
+    'Nauru',
+    'Nepal',
+    'Netherlands',
+    'New Caledonia',
+    'New Zealand',
+    'Nicaragua',
+    'Niger',
+    'Nigeria',
+    'Niue',
+    'Norfolk Island',
+    'North Korea',
+    'North Macedonia',
+    'Northern Mariana Islands',
+    'Norway',
+    'Oman',
+    'Pakistan',
+    'Palau',
+    'Palestinian Territory',
+    'Panama',
+    'Papua New Guinea',
+    'Paraguay',
+    'Peru',
+    'Philippines',
+    'Pitcairn',
+    'Poland',
+    'Portugal',
+    'Puerto Rico',
+    'Qatar',
+    'Réunion',
+    'Romania',
+    'Russian Federation',
+    'Rwanda',
+    'Saba',
+    'Saint Barthelemy',
+    'Saint Eustatius',
+    'Saint Helena',
+    'Saint Kitts and Nevis',
+    'Saint Lucia',
+    'Saint Martin',
+    'Saint Pierre and Miquelon',
+    'Saint Vincent and the Grenadines',
+    'Samoa',
+    'San Marino',
+    'Sao Tome and Principe',
+    'Saudi Arabia',
+    'Senegal',
+    'Serbia',
+    'Seychelles',
+    'Sierra Leone',
+    'Singapore',
+    'Sint Maarten',
+    'Slovakia',
+    'Slovenia',
+    'Solomon Islands',
+    'Somalia',
+    'South Africa',
+    'South Georgia and South Sandwich Islands',
+    'South Korea',
+    'South Sudan',
+    'Spain',
+    'Sri Lanka',
+    'Sudan',
+    'Suriname',
+    'Svalbard',
+    'Sweden',
+    'Switzerland',
+    'Syria',
+    'Tajikistan',
+    'Tanzania',
+    'Thailand',
+    'Timor-Leste',
+    'Togo',
+    'Tokelau',
+    'Tonga',
+    'Trinidad and Tobago',
+    'Tunisia',
+    'Turkiye',
+    'Turkmenistan',
+    'Turks and Caicos Islands',
+    'Tuvalu',
+    'Uganda',
+    'Ukraine',
+    'United Arab Emirates',
+    'United Kingdom',
+    'United States',
+    'Uruguay',
+    'US Virgin Islands',
+    'Uzbekistan',
+    'Vanuatu',
+    'Vatican City',
+    'Venezuela',
+    'Vietnam',
+    'Wallis and Futuna',
+    'Yemen',
+    'Zambia',
+    'Zimbabwe',
+];
+const US_STATES = [
+    'Alabama',
+    'Alaska',
+    'Arizona',
+    'Arkansas',
+    'California',
+    'Colorado',
+    'Connecticut',
+    'Delaware',
+    'District of Columbia',
+    'Florida',
+    'Georgia',
+    'Hawaii',
+    'Idaho',
+    'Illinois',
+    'Indiana',
+    'Iowa',
+    'Kansas',
+    'Kentucky',
+    'Louisiana',
+    'Maine',
+    'Maryland',
+    'Massachusetts',
+    'Michigan',
+    'Minnesota',
+    'Mississippi',
+    'Missouri',
+    'Montana',
+    'Nebraska',
+    'Nevada',
+    'New Hampshire',
+    'New Jersey',
+    'New Mexico',
+    'New York',
+    'North Carolina',
+    'North Dakota',
+    'Ohio',
+    'Oklahoma',
+    'Oregon',
+    'Pennsylvania',
+    'Rhode Island',
+    'South Carolina',
+    'South Dakota',
+    'Tennessee',
+    'Texas',
+    'Utah',
+    'Vermont',
+    'Virginia',
+    'Washington',
+    'West Virginia',
+    'Wisconsin',
+    'Wyoming',
+    'Washington, D.C',
+];
+/**
+ * Major cities with population greater than 100K
+ * @see https://services.arcgis.com/P3ePLMYs2RVChkJx/ArcGIS/rest/services/USA_Major_Cities_/FeatureServer/0
+ */
+const US_MAJOR_CITIES = [
+    'Roanoke',
+    'Nampa',
+    'Edinburg',
+    'Federal Way',
+    'New Bedford',
+    "Lee's Summit",
+    'Lynn',
+    'Chico',
+    'Quincy',
+    'Davenport',
+    'Wichita Falls',
+    'Vacaville',
+    'Menifee',
+    'Norwalk',
+    'Spokane Valley',
+    'Highlands Ranch',
+    'South Bend',
+    'Rialto',
+    'Rio Rancho',
+    'Allen',
+    'Columbia',
+    'Daly City',
+    'Jurupa Valley',
+    'Concord',
+    'Brockton',
+    'San Mateo',
+    'Davie',
+    'Tyler',
+    'El Cajon',
+    'Hillsboro',
+    'Renton',
+    'Burbank',
+    'Green Bay',
+    'Riverview',
+    'South Fulton',
+    'Inglewood',
+    'Sandy Springs',
+    'Boulder',
+    'Centennial',
+    'Sparks',
+    'Greeley',
+    'El Monte',
+    'West Covina',
+    'Santa Maria',
+    'Dearborn',
+    'Temecula',
+    'Everett',
+    'San Buenaventura',
+    'Murrieta',
+    'Sugar Land',
+    'Las Cruces',
+    'Miami Gardens',
+    'Lewisville',
+    'Pueblo',
+    'Costa Mesa',
+    'Pompano Beach',
+    'Lakeland',
+    'Lansing',
+    'Peoria',
+    'Broken Arrow',
+    'Spring Hill',
+    'High Point',
+    'Gresham',
+    'Lehigh Acres',
+    'Downey',
+    'League City',
+    'Springfield',
+    'Waterbury',
+    'Odessa',
+    'The Woodlands',
+    'Brandon',
+    'Carlsbad',
+    'Elgin',
+    'North Charleston',
+    'Provo',
+    'Beaumont',
+    'Antioch',
+    'Wilmington',
+    'Lowell',
+    'Manchester',
+    'Westminster',
+    'Richmond',
+    'West Jordan',
+    'Billings',
+    'Clearwater',
+    'Evansville',
+    'West Palm Beach',
+    'Meridian',
+    'Cambridge',
+    'East Los Angeles',
+    'Round Rock',
+    'Richardson',
+    'Palm Bay',
+    'Fairfield',
+    'Clovis',
+    'College Station',
+    'Hartford',
+    'Lafayette',
+    'Rochester',
+    'Independence',
+    'Ann Arbor',
+    'Berkeley',
+    'Arvada',
+    'Abilene',
+    'Concord',
+    'Pearland',
+    'Allentown',
+    'Fargo',
+    'Vallejo',
+    'Columbia',
+    'Simi Valley',
+    'Topeka',
+    'Thousand Oaks',
+    'Athens',
+    'Santa Clara',
+    'Norman',
+    'Midland',
+    'Carrollton',
+    'New Haven',
+    'Sterling Heights',
+    'Coral Springs',
+    'Miramar',
+    'Victorville',
+    'Stamford',
+    'Kent',
+    'Columbia',
+    'Hampton',
+    'Elizabeth',
+    'Dayton',
+    'Cedar Rapids',
+    'Waco',
+    'Pasadena',
+    'Warren',
+    'Denton',
+    'Orange',
+    'West Valley City',
+    'Gainesville',
+    'Olathe',
+    'Visalia',
+    'Thornton',
+    'McAllen',
+    'Surprise',
+    'Metairie',
+    'Fullerton',
+    'Torrance',
+    'Roseville',
+    'Savannah',
+    'Syracuse',
+    'Bridgeport',
+    'Rockford',
+    'Naperville',
+    'Mesquite',
+    'Charleston',
+    'Joliet',
+    'Escondido',
+    'Pomona',
+    'Bellevue',
+    'Pasadena',
+    'Murfreesboro',
+    'Hollywood',
+    'Killeen',
+    'Jackson',
+    'Sunnyvale',
+    'Springfield',
+    'Lakewood',
+    'Kansas City',
+    'Corona',
+    'Macon-Bibb County',
+    'Alexandria',
+    'Paterson',
+    'Hayward',
+    'Salinas',
+    'Clarksville',
+    'Springfield',
+    'Palmdale',
+    'Fort Collins',
+    'Pembroke Pines',
+    'Garden Grove',
+    'Lancaster',
+    'Oceanside',
+    'Rancho Cucamonga',
+    'Cary',
+    'Ontario',
+    'Salem',
+    'Elk Grove',
+    'Eugene',
+    'Santa Rosa',
+    'Aurora',
+    'Tempe',
+    'Chattanooga',
+    'Fort Lauderdale',
+    'Newport News',
+    'Brownsville',
+    // 'Mobile',
+    'Shreveport',
+    'Akron',
+    'Knoxville',
+    'Vancouver',
+    'Providence',
+    'Peoria',
+    'Paradise',
+    'Sioux Falls',
+    'Cape Coral',
+    'McKinney',
+    'Grand Prairie',
+    'Tallahassee',
+    'Glendale',
+    'Overland Park',
+    'Huntington Beach',
+    'Grand Rapids',
+    'Salt Lake City',
+    'Amarillo',
+    'Frisco',
+    'Montgomery',
+    'Birmingham',
+    'Oxnard',
+    'Augusta',
+    'Little Rock',
+    'Port St. Lucie',
+    'Sunrise Manor',
+    'Worcester',
+    'Columbus',
+    'Fontana',
+    'Fayetteville',
+    'Moreno Valley',
+    'Rochester',
+    'Yonkers',
+    'Des Moines',
+    'Huntsville',
+    'Spring Valley',
+    'Modesto',
+    'Tacoma',
+    'Enterprise',
+    'San Bernardino',
+    'Hialeah',
+    'Richmond',
+    'Baton Rouge',
+    'Santa Clarita',
+    'Spokane',
+    'Fremont',
+    'Boise City',
+    'Norfolk',
+    'Arlington',
+    'Scottsdale',
+    'Garland',
+    'Louisville',
+    'Glendale',
+    'Chesapeake',
+    'Winston-Salem',
+    'Laredo',
+    'Irving',
+    'Lubbock',
+    'St. Petersburg',
+    'North Las Vegas',
+    'Fort Wayne',
+    'Reno',
+    'Gilbert',
+    'Madison',
+    'Toledo',
+    'Chula Vista',
+    'Chandler',
+    'Buffalo',
+    'Durham',
+    'Plano',
+    'Lincoln',
+    'Anchorage',
+    'Jersey City',
+    'Greensboro',
+    'St. Louis',
+    'Pittsburgh',
+    'Orlando',
+    'Irvine',
+    'Cincinnati',
+    'Santa Ana',
+    'St. Paul',
+    'Newark',
+    'Riverside',
+    'Henderson',
+    'Corpus Christi',
+    'Stockton',
+    'Lexington-Fayette',
+    'Anaheim',
+    'Urban Honolulu',
+    'Cleveland',
+    'New Orleans',
+    'Tampa',
+    'Aurora',
+    'Louisville',
+    'Arlington',
+    'Wichita',
+    'Bakersfield',
+    'Tulsa',
+    'Minneapolis',
+    'Oakland',
+    'Miami',
+    'Virginia Beach',
+    'Long Beach',
+    'Raleigh',
+    'Colorado Springs',
+    'Omaha',
+    'Atlanta',
+    'Mesa',
+    'Kansas City',
+    'Sacramento',
+    'Fresno',
+    'Tucson',
+    'Albuquerque',
+    'Milwaukee',
+    'Baltimore',
+    'Memphis',
+    'Detroit',
+    'Las Vegas',
+    'Portland',
+    'Boston',
+    'El Paso',
+    'Oklahoma City',
+    'Nashville',
+    'Washington',
+    'Denver',
+    'Seattle',
+    'San Francisco',
+    'Charlotte',
+    'Indianapolis',
+    'Columbus',
+    'Fort Worth',
+    'Jacksonville',
+    'Austin',
+    'San Jose',
+    'Dallas',
+    'San Diego',
+    'San Antonio',
+    'Philadelphia',
+    'Phoenix',
+    'Houston',
+    'Chicago',
+    'Los Angeles',
+    'New York',
+];
+const WORLD_REGIONS = [
+    'Antarctica',
+    'Caribbean',
+    'Central America',
+    'Central Asia',
+    'Eastern Africa',
+    'Eastern Asia',
+    'Eastern Europe',
+    'European Russia',
+    'Melanesia',
+    'Micronesia',
+    'Middle Africa',
+    'Northern Africa',
+    'Northern America',
+    'Northern Europe',
+    'Polynesia',
+    'South America',
+    'Southeastern Asia',
+    'Southern Africa',
+    'Southern Asia',
+    'Southern Europe',
+    'Western Africa',
+    'Western Asia',
+    'Western Europe',
+];
+const OTHER_LOCATIONS = [
+    'U.S',
+    'US',
+    'United States',
+    'USA',
+    'U.S. Virgin Islands',
+    'World',
+    'Global',
+    'North America',
+    'South America',
+    'Europe',
+    'Africa',
+    'Asia',
+    'Oceania',
+    'Antarctic',
+    'Arctic',
+    'Atlantic',
+    'Pacific',
+    'Lake Michigan',
+    'Lake Ontario',
+    'Lake Huron',
+    'Lake superior',
+    'Lake erie',
+    'Gulf of Mexico',
+    'New England',
+    'Hong Kong',
+    'Taiwan',
+    'Hudson Bay,',
+];
+const WorldCounrtiesPattern = WORLD_COUNTRIES.join('|');
+const USStatesPattern = US_STATES.join('|');
+const USCitiesPattern = US_MAJOR_CITIES.join('|');
+const WorldRegionsPattern = WORLD_REGIONS.join('|');
+const OthersPattern = OTHER_LOCATIONS.join('|');
+const PatternsFromTextLabelingTool = TitleSummaryMatchingPatterns_json_1.default.locations.join('|');
+// Combine patterns into one
+let matchingPatterns = `${WorldCounrtiesPattern}|${USStatesPattern}|${USCitiesPattern}|${WorldRegionsPattern}|${OthersPattern}|${PatternsFromTextLabelingTool}`;
+/**
+ * Matches location information from an item's title and snippet using predefined or custom matching patterns.
+ *
+ * @param {IItem} item - The item containing title and snippet to search for location information.
+ * @param {string[]} [customMatchingPattenrs] - Optional custom matching patterns to be included in the search.
+ * @returns {string[]} - An array of matched location strings after deduplication and removing overlaps.
+ */
+const matchLocationInfo = (item, customMatchingPattenrs) => {
+    if (customMatchingPattenrs) {
+        matchingPatterns = `${matchingPatterns}|${customMatchingPattenrs.join('|')}`;
+    }
+    const combinedRegex = new RegExp(`\\b(${matchingPatterns})\\b`, 'gi');
+    const title = item.title || '';
+    const snippet = item.snippet || '';
+    const matchedLocationsFromTitle = title.match(combinedRegex) || [];
+    const matchedLocationsFromSnippet = snippet.match(combinedRegex) || [];
+    const matchedLocations = [
+        ...matchedLocationsFromTitle,
+        ...matchedLocationsFromSnippet,
+    ];
+    const candidates = (0, helpers_1.deduplicate)(matchedLocations);
+    return (0, helpers_1.removeOverlapped)(candidates);
+};
+exports.matchLocationInfo = matchLocationInfo;
+//# sourceMappingURL=matchLocationInfo.js.map