lao-grammar-checker/dist/laoWordSplitter2.d.ts

A utility to check grammar and split Lao language sentences into individual words

/**
 * Splits Lao text into individual words.
 * A class for splitting Lao text into individual words.
 * This class handles various Lao language specific rules for word segmentation,
 * including consonant clusters, leading vowels, and special character sequences.
 */
export interface LaoWordInfo {
    word: string;
    startIndex: number;
    endIndex: number;
}
export declare class LaoWordSplitter {
    private readonly LAO_CONSONANTS;
    private readonly LEADING_VOWELS;
    private readonly MIDDLE_CHARS;
    private readonly DIGRAPH_FOLLOWERS;
    private readonly MAI_YAMOK;
    /**
     * Checks if a character is part of Lao script
     *
     * Examples:
     * isLaoCharacter('ກ') => true
     * isLaoCharacter('a') => false
     * isLaoCharacter('1') => false
     */
    private isLaoCharacter;
    /**
     * Helper function to add a word to the result array and start a new word
     * Also tracks the position of words in the original text
     *
     * Examples:
     * addWordToResult('ປະ', words, 2, 0, 'ເ') =>
     *   returns { word: 'ເ', startIndex: 2 } and
     *   words = [{ word: 'ປະ', startIndex: 0, endIndex: 1 }]
     *
     * addWordToResult('ລາວ', words, 8, 5, 'ເ') =>
     *   returns { word: 'ເ', startIndex: 8 } and
     *   words = [..., { word: 'ລາວ', startIndex: 5, endIndex: 7 }]
     */
    private addWordToResult;
    /**
     * Helper function to handle consonant + 'ວ' sequences
     * Also tracks the position of words in the original text
     *
     * Examples:
     * "ຈົນກວ່າຈະ" when encountering '່' after 'ກວ':
     * handleConsonantVSequence('ຈົນກວ', '່', words, 5, 0) =>
     *   returns { word: 'ກວ່', startIndex: 3 } and
     *   words = [{ word: 'ຈົນ', startIndex: 0, endIndex: 2 }]
     *
     * "ຄວາມຮັກ" when encountering 'າ' after 'ຄວ':
     * handleConsonantVSequence('ຄວ', 'າ', words, 2, 0) =>
     *   returns { word: 'ຄວາ', startIndex: 0 } and words = []
     *
     * "ຂວາງາມ" when encountering 'າ' after 'ຂວ':
     * handleConsonantVSequence('ຂວ', 'າ', words, 2, 0) =>
     *   returns { word: 'ຂວາ', startIndex: 0 } and words = []
     */
    private handleConsonantVSequence;
    /**
     * Helper function to handle consonant + 'ຣ' sequences
     * Also tracks the position of words in the original text
     *
     * Examples:
     * "ທຣັມ" when encountering 'ັ' after 'ຣ':
     * handleConsonantRSequence('ທຣ', 'ັ', words, 2, 0) =>
     *   returns { word: 'ທຣັ', startIndex: 0 } and words = []
     *
     * "ປຣິນເຕີ" when encountering 'ິ' after 'ຣ':
     * handleConsonantRSequence('ປຣ', 'ິ', words, 2, 0) =>
     *   returns { word: 'ປຣິ', startIndex: 0 } and words = []
     *
     * "ກຣາມ" when encountering 'າ' after 'ຣ':
     * handleConsonantRSequence('ກຣ', 'າ', words, 2, 0) =>
     *   returns { word: 'ກຣາ', startIndex: 0 } and words = []
     */
    private handleConsonantRSequence;
    /**
     * Helper function to handle digraphs with 'ຫ'
     * Also tracks the position of words in the original text
     *
     * Examples:
     * "ຫວານຫລາຍ" when encountering 'າ' after 'ຫວ':
     * handleDigraphSequence('ຫວ', 'າ', words, 2, 0) =>
     *   returns { word: 'ຫວາ', startIndex: 0 } and words = []
     *
     * "ຫລັງຈາກ" when encountering 'ັ' after 'ຫລ':
     * handleDigraphSequence('ຫລ', 'ັ', words, 2, 0) =>
     *   returns { word: 'ຫລັ', startIndex: 0 } and words = []
     */
    private handleDigraphSequence;
    /**
     * Helper function to handle regular middle character processing
     * Also tracks the position of words in the original text
     *
     * Examples:
     * "ເທດລາວ" when encountering 'າ' after 'ລ':
     * handleRegularMiddleChar('ເທດລ', 'າ', words, 5, 0) =>
     *   returns { word: 'ລາ', startIndex: 4 } and
     *   words = [{ word: 'ເທດ', startIndex: 0, endIndex: 3 }]
     *
     * "ພາສາ" when encountering 'າ' after 'ສ':
     * handleRegularMiddleChar('ພາສ', 'າ', words, 3, 0) =>
     *   returns { word: 'ສາ', startIndex: 2 } and
     *   words = [{ word: 'ພາ', startIndex: 0, endIndex: 1 }]
     */
    private handleRegularMiddleChar;
    /**
     * Helper function to handle 'ວ' or 'ອ' between consonants
     * Also tracks the position of words in the original text
     *
     * Examples:
     * "ສຶ່ງສວຍງາມ" when encountering "ວ" after "ສ" and followed by "ຍ":
     * handleVaOrOSequence('ສຶ່ງສ', 'ວ', words, 5, 0) =>
     *   returns { word: 'ສວ', startIndex: 4 } and
     *   words = [{ word: 'ສຶ່ງ', startIndex: 0, endIndex: 3 }]
     *
     * "ຂອງກິນ" when encountering "ອ" after "ຂ" and followed by "ງ":
     * handleVaOrOSequence('ຂ', 'ອ', words, 1, 0) =>
     *   returns { word: 'ຂອ', startIndex: 0 } and words = []
     */
    private handleVaOrOSequence;
    /**
     * Remove Zero Width Spaces
     *
     * Examples:
     * removeZeroWidthSpaces("ສະ​ບາຍ​ດີ") => "ສະບາຍດີ"
     */
    private removeZeroWidthSpaces;
    /**
     * Splits a Lao language sentence into individual words based on syllable structure rules.
     * Also provides the start and end indices of each word in the original text.
     *
     * @param sentence The Lao sentence to be segmented.
     * @returns An array of segmented words with their indices.
     *
     * Examples:
     * splitLao("ປະເທດລາວ") => [
     *   { word: "ປະ", startIndex: 0, endIndex: 1 },
     *   { word: "ເທດ", startIndex: 2, endIndex: 4 },
     *   { word: "ລາວ", startIndex: 5, endIndex: 7 }
     * ]
     *
     * splitLao("ຈົນກວ່າຈະ") => [
     *   { word: "ຈົນ", startIndex: 0, endIndex: 2 },
     *   { word: "ກວ່າ", startIndex: 3, endIndex: 6 },
     *   { word: "ຈະ", startIndex: 7, endIndex: 8 }
     * ]
     *
     * splitLao("ຫວຽດນາມ") => [
     *   { word: "ຫວຽດ", startIndex: 0, endIndex: 3 },
     *   { word: "ນາມ", startIndex: 4, endIndex: 6 }
     * ]
     *
     * splitLao("ພາສາລາວ 101") => [
     *   { word: "ພາ", startIndex: 0, endIndex: 1 },
     *   { word: "ສາ", startIndex: 2, endIndex: 3 },
     *   { word: "ລາວ", startIndex: 4, endIndex: 6 },
     *   { word: "101", startIndex: 8, endIndex: 10 }
     * ]
     */
    split(sentence: string): LaoWordInfo[];
}