Initial commit

readme.txt

@@ -0,0 +1,141 @@
+
+Readme for GeoNames Gazetteer extract files
+
+============================================================================================================
+
+This work is licensed under a Creative Commons Attribution 4.0 License,
+see https://creativecommons.org/licenses/by/4.0/
+The Data is provided "as is" without warranty or any representation of accuracy, timeliness or completeness.
+
+The data format is tab-delimited text in utf8 encoding.
+
+
+Files :
+-------
+XX.zip                   : features for country with iso code XX, see 'geoname' table for columns. 'no-country' for features not belonging to a country.
+allCountries.zip         : all countries combined in one file, see 'geoname' table for columns
+cities500.zip            : all cities with a population > 500 or seats of adm div down to PPLA4 (ca 185.000), see 'geoname' table for columns
+cities1000.zip           : all cities with a population > 1000 or seats of adm div down to PPLA3 (ca 130.000), see 'geoname' table for columns
+cities5000.zip           : all cities with a population > 5000 or PPLA (ca 50.000), see 'geoname' table for columns
+cities15000.zip          : all cities with a population > 15000 or capitals (ca 25.000), see 'geoname' table for columns
+alternateNamesV2.zip     : alternate names with language codes and geonameId, file with iso language codes, with new columns from and to
+alternateNames.zip       : obsolete use V2, this file does not have the new columns to and from and will be removed in the future
+admin1CodesASCII.txt     : names in English for admin divisions. Columns: code, name, name ascii, geonameid
+admin2Codes.txt          : names for administrative subdivision 'admin2 code' (UTF8), Format : concatenated codes <tab>name <tab> asciiname <tab> geonameId
+iso-languagecodes.txt    : iso 639 language codes, as used for alternate names in file alternateNames.zip
+featureCodes.txt         : name and description for feature classes and feature codes 
+timeZones.txt            : countryCode, timezoneId, gmt offset on 1st of January, dst offset to gmt on 1st of July (of the current year), rawOffset without DST
+countryInfo.txt          : country information : iso codes, fips codes, languages, capital ,...
+                           see the geonames webservices for additional country information,
+                                bounding box                         : http://api.geonames.org/countryInfo?
+                                country names in different languages : http:/api.geonames.org/countryInfoCSV?lang=it
+modifications-<date>.txt : all records modified on the previous day, the date is in yyyy-MM-dd format. You can use this file to daily synchronize your own geonames database.
+deletes-<date>.txt       : all records deleted on the previous day, format : geonameId <tab> name <tab> comment.
+
+alternateNamesModifications-<date>.txt : all alternate names modified on the previous day,
+alternateNamesDeletes-<date>.txt       : all alternate names deleted on the previous day, format : alternateNameId <tab> geonameId <tab> name <tab> comment.
+userTags.zip		: user tags , format : geonameId <tab> tag.
+hierarchy.zip		: parentId, childId, type. The type 'ADM' stands for the admin hierarchy modeled by the admin1-4 codes. The other entries are entered with the user interface. The relation toponym-adm hierarchy is not included in the file, it can instead be built from the admincodes of the toponym.
+adminCode5.zip		: the new adm5 column is not yet exported in the other files (in order to not break import scripts). Instead it is availabe as separate file.
+			  columns: geonameId,adm5code
+
+The main 'geoname' table has the following fields :
+---------------------------------------------------
+geonameid         : integer id of record in geonames database
+name              : name of geographical point (utf8) varchar(200)
+asciiname         : name of geographical point in plain ascii characters, varchar(200)
+alternatenames    : alternatenames, comma separated, ascii names automatically transliterated, convenience attribute from alternatename table, varchar(10000)
+latitude          : latitude in decimal degrees (wgs84)
+longitude         : longitude in decimal degrees (wgs84)
+feature class     : see http://www.geonames.org/export/codes.html, char(1)
+feature code      : see http://www.geonames.org/export/codes.html, varchar(10)
+country code      : ISO-3166 2-letter country code, 2 characters
+cc2               : alternate country codes, comma separated, ISO-3166 2-letter country code, 200 characters
+admin1 code       : fipscode (subject to change to iso code), see exceptions below, see file admin1Codes.txt for display names of this code; varchar(20)
+admin2 code       : code for the second administrative division, a county in the US, see file admin2Codes.txt; varchar(80) 
+admin3 code       : code for third level administrative division, varchar(20)
+admin4 code       : code for fourth level administrative division, varchar(20)
+population        : bigint (8 byte int) 
+elevation         : in meters, integer
+dem               : digital elevation model, srtm3 or gtopo30, average elevation of 3''x3'' (ca 90mx90m) or 30''x30'' (ca 900mx900m) area in meters, integer. srtm processed by cgiar/ciat.
+timezone          : the iana timezone id (see file timeZone.txt) varchar(40)
+modification date : date of last modification in yyyy-MM-dd format
+
+
+AdminCodes:
+Most adm1 are FIPS codes. ISO codes are used for US, CH, BE and ME. UK and Greece are using an additional level between country and fips code. The code '00' stands for general features where no specific adm1 code is defined.
+The corresponding admin feature is found with the same countrycode and adminX codes and the respective feature code ADMx.
+
+
+
+The table 'alternate names' :
+-----------------------------
+alternateNameId   : the id of this alternate name, int
+geonameid         : geonameId referring to id in table 'geoname', int
+isolanguage       : iso 639 language code 2- or 3-characters; 4-characters 'post' for postal codes and 'iata','icao' and faac for airport codes, fr_1793 for French Revolution names,  abbr for abbreviation, link to a website (mostly to wikipedia), wkdt for the wikidataid, varchar(7)
+alternate name    : alternate name or name variant, varchar(400)
+isPreferredName   : '1', if this alternate name is an official/preferred name
+isShortName       : '1', if this is a short name like 'California' for 'State of California'
+isColloquial      : '1', if this alternate name is a colloquial or slang term. Example: 'Big Apple' for 'New York'.
+isHistoric        : '1', if this alternate name is historic and was used in the past. Example 'Bombay' for 'Mumbai'.
+from		  : from period when the name was used
+to		  : to period when the name was used
+
+Remark : the field 'alternatenames' in the table 'geoname' is a short version of the 'alternatenames' table without links and postal codes but with ascii transliterations. You probably don't need both. 
+If you don't need to know the language of a name variant, the field 'alternatenames' will be sufficient. If you need to know the language
+of a name variant, then you will need to load the table 'alternatenames' and you can drop the column in the geoname table.
+
+
+
+
+Boundaries:
+Simplified country boundaries are available in two slightly different formats:
+shapes_simplified_low:
+geonameId: 	The geonameId of the feature
+geoJson:	The boundary in geoJson format
+
+shapes_simplified_low.json:
+similar to the abovementioned file, but fully in geojson format. The geonameId is a feature property in the geojson string.
+
+
+Statistics on the number of features per country and the feature class and code distributions : http://www.geonames.org/statistics/ 
+
+
+Continent codes :
+AF : Africa			geonameId=6255146
+AS : Asia			geonameId=6255147
+EU : Europe			geonameId=6255148
+NA : North America		geonameId=6255149
+OC : Oceania			geonameId=6255151
+SA : South America		geonameId=6255150
+AN : Antarctica			geonameId=6255152
+
+
+feature classes:
+A: country, state, region,...
+H: stream, lake, ...
+L: parks,area, ...
+P: city, village,...
+R: road, railroad 
+S: spot, building, farm
+T: mountain,hill,rock,... 
+U: undersea
+V: forest,heath,...
+
+
+If you find errors or miss important places, please do use the wiki-style edit interface on our website 
+https://www.geonames.org to correct inaccuracies and to add new records. 
+Thanks in the name of the geonames community for your valuable contribution.
+
+Data Sources:
+https://www.geonames.org/data-sources.html
+
+
+More Information is also available in the geonames faq :
+
+https://forum.geonames.org/gforum/forums/show/6.page
+
+The forum : https://forum.geonames.org
+
+or the google group : https://groups.google.com/group/geonames
+

requirements.txt

@@ -0,0 +1,5 @@
+googletrans==3.1.0a0
+transliterate==1.10.2
+Flask==2.2.2
+pandas~=1.3.4
+pytz~=2021.3

script.py

@@ -0,0 +1,178 @@
+import pandas as pd
+from googletrans import Translator
+from difflib import SequenceMatcher
+from transliterate import translit
+from datetime import datetime
+from pytz import timezone
+from flask import Flask, request, jsonify
+
+
+class GeoName:
+
+    def __init__(self):
+        """ Чтение данных из файла.
+        Фильтрация населенных пунктов из всех данных.
+        Заполнение NaN значений пустой строкой.
+        """
+        headers = [
+            'geonameid',
+            'name',
+            'asciiname',
+            'alternatenames',
+            'latitude',
+            'longitude',
+            'feature class',
+            'feature code',
+            'country code',
+            'cc2',
+            'admin1',
+            'admin2',
+            'admin3',
+            'admin4',
+            'population',
+            'elevation',
+            'dem',
+            'timezone',
+            'date'
+        ]
+        data = pd.read_csv("RU.txt", sep="\t", names=headers, low_memory=False)
+        self.data_frame = data[data['feature class'] == 'P'].reset_index(drop=True)
+        self.data_frame = self.data_frame.fillna('')
+
+    def get_by_id(self, name_id: int):
+        """ Получение информации о населенном пункте по geonameid. """
+        return self.data_frame[self.data_frame['geonameid'] == name_id]
+
+    def get_page(self, page_num: int, display_num: int):
+        """ Получение страницы с информацией о городах.
+        :param page_num: номер страницы.
+        :param display_num: количество городов на странице.
+        :return: Возвращает нужную страницу с заданным количеством городов.
+        """
+        start_index = (page_num - 1) * display_num
+        end_index = start_index + display_num
+        num_row = self.data_frame.shape[0]
+        num_pages = (num_row + display_num - 1) // display_num
+        if (start_index >= 0) and (start_index < num_row) and (page_num < num_pages):
+            return self.data_frame[start_index:end_index]
+        else:
+            return pd.DataFrame()
+
+    def search_in_string(self, city_name):
+        """ Поиск названия в строке.
+        :param city_name: Название города.
+        :return: Возвращает список городов, которые имеют схожие альтернативные названия.
+        """
+        return self.data_frame[pd.Series(
+            max([True if elm.lower() == city_name.lower() else False for elm in row]) for row in
+            self.data_frame['alternatenames'].str.split(','))]
+
+    def find_city(self, city_name):
+        """ Поиск городов с заданным названием.
+        :param city_name: Название города
+        :return: Список городов, отсортированных в порядке убывания по населению
+        """
+        found_cities = pd.concat([self.data_frame[self.data_frame['name'].str.fullmatch(city_name, case=False)],
+                                  self.search_in_string(city_name)]).drop_duplicates()
+        return found_cities.sort_values('population', ascending=False).reset_index(drop=True)
+
+    def translate_name(self, name):
+        """ Перевод с русского на английский.
+        :param name: Название города на русском.
+        :return: Название на английском.
+
+        Сравниваем два перевод и транслит названия.
+        Если они схожи, то выбираем перевод, иначе транслит.
+        Например проблемы перевода названий Zyabrikovo и Ladnoye
+        """
+        translator = Translator()
+        name_1 = translator.translate(name).text.title()
+        name_2 = translit(name, reversed=True)
+        if SequenceMatcher(None, name_1, name_2).ratio() >= 0.8:
+            return name_1
+        else:
+            return name_2
+
+    def find_matches(self, part_name):
+        """ Поиск похожих названий.
+        :param part_name: Название или часть названия города.
+        :return: Список городов, имеющих похожее название.
+        """
+        found_cities = pd.concat([self.data_frame[self.data_frame['name'].str.find(part_name) != -1], self.data_frame[
+            self.data_frame['alternatenames'].str.find(part_name) != -1]]).drop_duplicates()
+        return found_cities.sort_values('population', ascending=False).reset_index(drop=True)
+
+
+app = Flask(__name__)
+app.config['JSON_SORT_KEYS'] = False
+app.config['JSON_AS_ASCII'] = False
+geo_date = GeoName()
+
+
+@app.route('/get_info/<int:name_id>', methods=['GET'])
+def get_info(name_id):
+    """ Получение информации о населенном пункте по geonameid. """
+    city_info = geo_date.get_by_id(name_id)
+    if city_info.empty:
+        return "No matches found", 400
+    return jsonify(city_info.to_dict(orient="records"))
+
+
+@app.route('/get_page', methods=['GET'])
+def get_page():
+    """ Получение страницы с информацией о городах.
+    :param page_num: номер страницы.
+    :param display_num: количество городов на странице.
+    :return: Возвращает нужную страницу с заданным количеством городов.
+    """
+    page_num = request.args.get('page', type=int)
+    display_num = request.args.get('num', type=int)
+    page = geo_date.get_page(page_num, display_num)
+    if page.empty:
+        return "Invalid page", 400
+    return jsonify(page.to_dict(orient="records"))
+
+
+@app.route('/get_compare', methods=['GET'])
+def get_compare():
+    """ Сравнение двух городов.
+    :param first_city: Название первого города.
+    :param second_city: Название второго города.
+    :return: Возвращает информацию о городах, какой из них расположен севернее,
+     одинаковые ли временные зоны и на сколько часов отличаются.
+    """
+    first_city = request.args.get('first')
+    second_city = request.args.get('second')
+    if (first_city is None or first_city == "") or (second_city is None or second_city == ""):
+        return "Empty request", 400
+    first_city = geo_date.find_city(geo_date.translate_name(first_city))
+    second_city = geo_date.find_city(geo_date.translate_name(second_city))
+    if first_city.empty or second_city.empty:
+        return "No matches found", 400
+    first_city = first_city.loc[first_city.index[0]]
+    second_city = second_city.loc[second_city.index[0]]
+    northeren = first_city['name'] if (first_city['latitude'] > second_city['latitude']) else second_city['name']
+    timezone_equal = first_city['timezone'] == second_city['timezone']
+    time_difference = abs(datetime.now(timezone(first_city['timezone'])).time().hour - datetime.now(
+        timezone(second_city['timezone'])).time().hour)
+    return jsonify(first_city.to_dict(), second_city.to_dict(), northeren, timezone_equal, time_difference)
+
+
+@app.route('/get_matches', methods=['GET'])
+def get_matches():
+    """ Поиск похожих названий.
+    :param name: Название или часть названия города.
+    :return: Список городов, имеющих похожее название.
+    """
+    city_name = request.args.get('name')
+    if city_name is None or city_name == "":
+        return "Empty request", 400
+    name_list = geo_date.find_matches(city_name)['name'].to_list()
+    if not name_list:
+        return "No matches found", 204
+    return jsonify(name_list)  # .to_json(orient='records')
+
+
+# driver function
+if __name__ == '__main__':
+    app.run(host='127.0.0.1', port=8000, debug=True)