@igk19/rus-text-gen/dist/cjs/index.d.ts

Generator of coherent and random texts in Russian language from real texts containing (as of now) about 30000 words.

interface ILine {
    wordIndices: number[];
    isCapitalized: Set<number>;
    symbolAfter: Map<number, string>;
}
interface IParseOutput {
    lines: ILine[];
    words: string[];
}
/**
 * A generates random or coherent Russian text from an existing text file.
 * The text file contains corrected excerpts from various philosophers of
 * the end of 19th/beginning of 20th century.
 */
declare class TextGenerator {
    /**
     * All unique words of the text sorted
     * in alphabetical order.
     */
    private readonly words;
    /**
     * Each line of the text
     */
    private readonly lines;
    constructor(input: IParseOutput);
    /**
     * Parses the default text file `./texts/text1.txt` and returns an
     * instance of `TextGenerator` with the parsed data.
     *
     * @returns A promise that resolves when the file has been parsed.
     *
     * @private
     */
    static build(): Promise<TextGenerator>;
    /**
     * Parses a text file.
     *
     * @param path The path to the text file to parse.
     * @returns A promise that resolves when the file has been parsed.
     *
     * This function reads the file line by line, splits each line into words,
     * and adds the words to a set to get all unique words.
     * Besides, it creates an array of line objects, where each object has
     * three properties: `wordIndices`, `isCapitalized` and `symbolAfter`.
     * `wordIndices` is an array of indices of words in the `this.words` array.
     * `isCapitalized` is a set of indices of words in the `this.words` array
     * that are capitalized.
     * `symbolAfter` is a map of indices of words in the `this.words` array
     * to the symbol right after the word.
     *
     * The returned data structure optimizes generation of the text.
     */
    private static parseFile;
    /**
     * Create random text.
     * @param textLength Text length measured in words.
     * @param isSentences Create random-length sentences (by capitalizing first sentence words and adding punctuation symbols).
     * @param isParagraphs Create random-length paragraphs (by adding new line symbols).
     *
     * @public
     */
    createRandomText(textLength?: number, isSentences?: boolean, isParagraphs?: boolean): string;
    /**
     * Generate coherent text of given length.
     * @param length - length of the output text
     * @returns a string of coherent text
     * Note: maximum length is 30000 words
     *
     * @public
     */
    createText(length?: number): string;
    /**
     * Creates a string of random text of given length, consisting of sentences.
     *
     * @param textLength - length of the output text
     * @param isParagraphs - whether to split sentences into paragraphs (by adding "\n" symbols)
     * @returns a string of random text formed into a semblance of sentences.
     *
     * @private
     */
    private createRandomSentences;
    /**
     * Generates an array of paragraph split points. A split point is a point in
     * an array of sentences where a paragraph break is inserted.
     * The split points are chosen randomly to simulate the distribution of
     * paragraph breaks in a natural text.
     * The number of split points is limited by the number of sentences, and the
     * distance between split points is limited to 6.
     * The distance between split points is chosen randomly from the range [2, 6].
     * @param numberOfSentences The number of sentences in the text.
     * @returns An array of paragraph split points.
     *
     * @static @private
     */
    private static calculateParagraphSplitPoints;
    /**
     * Joins elements of a string array into a single string with spaces between them.
     * Appends a space after each element unless it ends with a newline character.
     *
     * @param acc - The accumulator string that collects the joined elements.
     * @param s - The current string element to be added to the accumulator.
     * @returns The updated accumulator string with the current element appended.
     *
     * @static @private
     */
    private static joinTextOutputArray;
    /**
     * Performs a binary search on a sorted array of Cyrillic strings to find the target string.
     *
     * @param arr - A sorted array of strings to search within.
     * @param target - The target string to search for in the array.
     * @returns The index of the target string if found, otherwise -1.
     *
     * Note: Uses `localeCompare()` for comparison to handle Cyrillic characters correctly.
     */
    private static binarySearchCyrillic;
    /**
     * Check if the given word is written in cyrillic alphabet.
     * @param {string} word - The word to check.
     * @returns {boolean} true if the word is cyrillic, false otherwise.
     *
     * @static @private
     */
    private static isCyrillicWord;
    /**
     * Returns the given string with the first letter capitalized.
     * @param {string} text - The string to capitalize.
     * @returns {string} The capitalized string.
     *
     * @static @private
     */
    private static capitalize;
    /**
     * Check if the given text is capitalized.
     * @param {string} text - The string to check.
     * @returns {boolean} true if the string is capitalized, false otherwise.
     *
     * @static @private
     */
    private static isCapitalized;
    /**
     * Generates a random number in the range [from, to).
     * @param to Upper limit of the range.
     * @param from Lower limit of the range. Defaults to 0.
     * @returns A random number in the range [from, to).
     *
     * @private
     */
    private static randomNumberGen;
    /**
     * Returns the given string with the last punctuation symbol removed and
     * the symbol itself as the second element of the returned array.
     * If the string does not end with a punctuation symbol,
     * the second element of the returned array is `null`.
     * @param {string} text - The string to strip of punctuation.
     * @returns {Array.<string, string | null>} An array containing the string
     * without the last punctuation symbol and the symbol itself.
     * @static @private
     */
    private static stripPunctuation;
    /**
     * Removes all punctuation symbols from the start and end of the given text.
     * @param {string} text - The text to trim.
     * @returns {string} The trimmed string.
     *
     * @static @private
     */
    private static trimAllSymbols;
}
export default TextGenerator;