https://simplemaps.com/data/world-cities

world-cities-parser.php

<?php

// Function to extract city_ascii and country names
function extractLocationParts($filename) {
    // Initialize an empty array to hold the merged location strings
    $locations = [];

    // Open the CSV file
    if (($handle = fopen($filename, 'r')) !== false) {
        // Get the header line
        $header = fgetcsv($handle);

        // Find the indices for city_ascii and country
        $cityIndex = array_search('city_ascii', $header);
        $countryIndex = array_search('country', $header);

        // Read each row of the CSV file
        while (($row = fgetcsv($handle)) !== false) {
            // Get the city_ascii and country values
            $city = $row[$cityIndex] ?? '';
            $country = $row[$countryIndex] ?? '';

            // Merge city and country
            $mergedLocation = trim("$city $country");
            if (!empty($mergedLocation)) {
                $locations[] = $mergedLocation;
            }
        }

        // Close the file handle
        fclose($handle);
    } else {
        echo "Error opening the file.";
        return [];
    }

    // Initialize an empty array for the final flat array of parts
    $flatArray = [];

    // Explode each location string by spaces and merge into a flat array
    foreach ($locations as $location) {
        $parts = explode(' ', $location);
        $flatArray = array_merge($flatArray, $parts);
    }

    // Unique array
    $result = array_unique($flatArray);

    return $result;
}

// Usage example
$filename = __DIR__.'/worldcities.csv';
$locationParts = extractLocationParts($filename);

// Create a txt output file where we write 10 parts per line
$fp = fopen('output.txt', 'w');
$count = 0;
foreach ($locationParts as $key => $part) {
    $buffer = $part . ' | ';

    if ($count === 10) {
        fwrite($fp, $buffer . PHP_EOL);
        $count = 0;
    } else {
        fwrite($fp, $buffer);
        $count++;
    }
}

// Output the flat array of location parts
print_r($locationParts);