text-to-map 1.0.0

package/dist/utils/helpers.js

@@ -0,0 +1,157 @@
+import { existsSync, mkdirSync } from "fs";
+import { tmpdir } from "os";
+import { join } from "path";
+import { MunicipalityType } from "../db/types";
+import { setDbConfig } from "../db/db";
+const appName = "text-to-map";
+export const getAppDataDirPath = () => join(process.env.APPDATA ||
+    (process.platform == "darwin"
+        ? process.env.HOME + "/Library/Preferences"
+        : process.env.HOME + "/.local/share"), appName);
+export const prepareOptions = (options) => {
+    var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k, _l, _m;
+    const dataDir = (_a = options.dataDir) !== null && _a !== void 0 ? _a : getAppDataDirPath();
+    if (!existsSync(dataDir)) {
+        mkdirSync(dataDir);
+    }
+    const tmpAppDir = join(tmpdir(), appName);
+    if (!existsSync(tmpAppDir)) {
+        mkdirSync(tmpAppDir);
+    }
+    return {
+        tmpDir: (_b = options.tmpDir) !== null && _b !== void 0 ? _b : tmpAppDir,
+        dataDir: dataDir,
+        dbFilePath: (_c = options.dbFilePath) !== null && _c !== void 0 ? _c : join(dataDir, "address_points.db"),
+        dbInitFilePath: (_d = options.dbInitFilePath) !== null && _d !== void 0 ? _d : join("src", "address_points_init.db"),
+        addressPointsAtomUrl: (_e = options.addressPointsAtomUrl) !== null && _e !== void 0 ? _e : "https://atom.cuzk.cz/RUIAN-CSV-ADR-ST/RUIAN-CSV-ADR-ST.xml",
+        addressPointsZipFileName: (_f = options.addressPointsZipFileName) !== null && _f !== void 0 ? _f : "ruian_csv.zip",
+        addressPointsCsvFolderName: (_g = options.addressPointsCsvFolderName) !== null && _g !== void 0 ? _g : "CSV",
+        streetsAtomUrl: (_h = options.streetsAtomUrl) !== null && _h !== void 0 ? _h : "https://atom.cuzk.cz/RUIAN-OBCE-SHP/RUIAN-OBCE-SHP.xml",
+        streetFolderName: (_j = options.streetZipFolderName) !== null && _j !== void 0 ? _j : "streets",
+        streetDbfFileName: (_k = options.streetDbfFileName) !== null && _k !== void 0 ? _k : "UL_L.dbf",
+        schoolsXmlUrl: (_l = options.schoolsXmlUrl) !== null && _l !== void 0 ? _l : "https://rejstriky.msmt.cz/opendata/vrejcelk.xml",
+        schoolsXmlFileName: (_m = options.schoolsXmlFileName) !== null && _m !== void 0 ? _m : "school-register.xml",
+    };
+};
+export const initDb = (options) => {
+    setDbConfig({
+        filePath: options.dbFilePath,
+        initFilePath: options.dbInitFilePath,
+    });
+};
+const cityPatterns = [
+    /^[sS]tatutární město +(.*)$/,
+    /^[oO]bec +(.*)$/,
+    /^[mM]ěsto +(.*)$/,
+    /^[mM]ěstys +(.*)$/,
+];
+const districtPatterns = [
+    /^[mM]ěstská část +(.*)$/,
+    /^[mM]ěstský obvod +(.*)$/,
+    /^[sS]tatutární město +.*, [mM]ěstská část +(.*)$/,
+    /^[sS]tatutární město +.*, [mM]ěstský obvod +(.*)$/,
+];
+export const extractMunicipalityName = (founder) => {
+    const patterns = founder.municipalityType === MunicipalityType.City
+        ? cityPatterns
+        : districtPatterns;
+    const correctPattern = patterns.filter((pattern) => pattern.test(founder.name));
+    if (correctPattern.length > 0) {
+        const result = correctPattern[0].exec(founder.name);
+        if (typeof result[1] !== "undefined") {
+            return result[1]
+                .replace(" - ", "-")
+                .replace(/\s{2,}/g, " ")
+                .trim();
+        }
+    }
+    return founder.name;
+};
+export const findClosestString = (str, arr) => {
+    let closestStr = "";
+    let closestDistance = Number.MAX_SAFE_INTEGER;
+    for (let i = 0; i < arr.length; i++) {
+        const currentStr = arr[i];
+        const distance = interpunctionDistance(str, currentStr);
+        if (distance < closestDistance) {
+            closestStr = currentStr;
+            closestDistance = distance;
+        }
+        // exact match found, exit loop
+        if (closestDistance === 0) {
+            break;
+        }
+    }
+    return closestStr;
+};
+const interpunctionDistance = (str1, str2) => {
+    let distance = levenshteinDistance(str1, str2);
+    const interpunctionMistakes = {
+        a: ["á"],
+        á: ["a"],
+        e: ["é", "ě"],
+        é: ["e", "ě"],
+        ě: ["e", "é"],
+        i: ["í"],
+        í: ["i"],
+        y: ["ý"],
+        ý: ["y"],
+        o: ["ó"],
+        ó: ["o"],
+        u: ["ú", "ů"],
+        ů: ["u", "ú"],
+        ú: ["u", "ů"],
+        c: ["č"],
+        č: ["c"],
+        d: ["ď"],
+        ď: ["d"],
+        n: ["ň"],
+        ň: ["n"],
+        r: ["ř"],
+        ř: ["r"],
+        s: ["š"],
+        š: ["s"],
+        t: ["ť"],
+        ť: ["t"],
+        z: ["ž"],
+        ž: ["z"],
+    };
+    const str1Chars = str1.split("");
+    const str2Chars = str2.split("");
+    for (let i = 0; i < str1Chars.length; i++) {
+        const char1 = str1Chars[i];
+        const char2 = str2Chars[i];
+        if (interpunctionMistakes[char1] &&
+            interpunctionMistakes[char1].includes(char2)) {
+            // Subtract a penalty from the distance for interpunction mistakes
+            distance -= 0.5;
+        }
+    }
+    return distance;
+};
+const levenshteinDistance = (str1, str2) => {
+    const matrix = Array(str2.length + 1)
+        .fill(null)
+        .map(() => Array(str1.length + 1).fill(null));
+    for (let i = 0; i <= str1.length; i++) {
+        matrix[0][i] = i;
+    }
+    for (let j = 0; j <= str2.length; j++) {
+        matrix[j][0] = j;
+    }
+    for (let j = 1; j <= str2.length; j++) {
+        for (let i = 1; i <= str1.length; i++) {
+            if (str1[i - 1] === str2[j - 1]) {
+                matrix[j][i] = matrix[j - 1][i - 1];
+            }
+            else {
+                matrix[j][i] =
+                    Math.min(matrix[j][i - 1], // deletion
+                    matrix[j - 1][i], // insertion
+                    matrix[j - 1][i - 1] // substitution
+                    ) + 1;
+            }
+        }
+    }
+    return matrix[str2.length][str1.length];
+};

package/package.json

@@ -0,0 +1,82 @@
+{
+  "type": "module",
+  "dependencies": {
+    "@arodax/jtsk2wgs84": "^1.0.2",
+    "@chevrotain/types": "^10.4.2",
+    "adm-zip": "^0.5.9",
+    "better-sqlite3": "^8.0.1",
+    "chevrotain": "^10.4.2",
+    "csv-parse": "^5.3.3",
+    "feedparser": "^2.2.10",
+    "iconv-lite": "^0.6.3",
+    "jtsk2wgs84": "^1.0.0",
+    "node-fetch": "^3.3.0",
+    "parsedbf": "^1.1.1",
+    "sax": "^1.2.4",
+    "superagent": "^8.0.6",
+    "typescript": "^4.9.4"
+  },
+  "devDependencies": {
+    "@jest/globals": "^29.3.1",
+    "@types/adm-zip": "^0.5.0",
+    "@types/better-sqlite3": "^7.6.3",
+    "@types/feedparser": "^2.2.5",
+    "@types/node": "^18.11.17",
+    "@types/superagent": "^4.1.16",
+    "jest": "^29.3.1",
+    "npm-run-all": "^4.1.5",
+    "rimraf": "^5.0.1",
+    "ts-jest": "^29.0.3",
+    "ts-node": "^10.9.1"
+  },
+  "scripts": {
+    "address-points": "ts-node --experimental-specifier-resolution=node --esm src/bin/address-points.ts",
+    "address-points-import-only": "ts-node --experimental-specifier-resolution=node --esm src/bin/address-points-import-only.ts",
+    "schools": "ts-node --experimental-specifier-resolution=node --esm src/bin/schools.ts",
+    "clear-all": "ts-node --experimental-specifier-resolution=node --esm src/bin/clear-all.ts",
+    "parse-ordinance": "ts-node --experimental-specifier-resolution=node --esm src/bin/parse-ordinance.ts",
+    "diagrams": "ts-node --experimental-specifier-resolution=node --esm src/bin/generate-syntax-diagrams.ts",
+    "streets": "ts-node --experimental-specifier-resolution=node --esm src/bin/streets.ts",
+    "dbf": "ts-node --experimental-specifier-resolution=node --esm src/bin/dbf.ts",
+    "test": "jest",
+    "ordinance-to-csv-rules": "node src/smd-to-csv/ordinance-to-csv-rules.js",
+    "clean": "rimraf dist",
+    "build": "npm-run-all clean -p build:*",
+    "build:types": "tsc --declaration --emitDeclarationOnly --outDir dist",
+    "build:js": "tsc --outDir dist",
+    "prepare": "npm run build"
+  },
+  "name": "text-to-map",
+  "description": "Text To Map usiluje o lepší, strojově zpracovatelné využití částí vyhlášek s výčtem ulic a dalších lokací. Jde o rozšiřitelnou sadu konceptů a nástrojů, které zajistí hladký převod výčtu ulic a jejich rozsahů v lidsky srozumitelném jazyce do strojově zpracovatelného, uchopitelného formátu.",
+  "version": "1.0.0",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "files": [
+    "dist/**/*",
+    "LICENSE",
+    "README.md"
+  ],
+  "directories": {
+    "example": "examples",
+    "test": "tests"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/maral/text-to-map.git"
+  },
+  "keywords": [
+    "streets",
+    "catchment areas",
+    "schools",
+    "map",
+    "geodata",
+    "address points",
+    "polygons"
+  ],
+  "author": "Marek Lisý",
+  "license": "MIT",
+  "bugs": {
+    "url": "https://github.com/maral/text-to-map/issues"
+  },
+  "homepage": "https://github.com/maral/text-to-map#readme"
+}