tor-browser

WordSegmenter.mjs (12535B)

---

// generated by diplomat-tool
import { DataError } from "./DataError.mjs"
import { DataProvider } from "./DataProvider.mjs"
import { Locale } from "./Locale.mjs"
import { WordBreakIteratorUtf16 } from "./WordBreakIteratorUtf16.mjs"
import wasm from "./diplomat-wasm.mjs";
import * as diplomatRuntime from "./diplomat-runtime.mjs";


/**
* An ICU4X word-break segmenter, capable of finding word breakpoints in strings.
*
* See the [Rust documentation for `WordSegmenter`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html) for more information.
*/
const WordSegmenter_box_destroy_registry = new FinalizationRegistry((ptr) => {
   wasm.icu4x_WordSegmenter_destroy_mv1(ptr);
});

export class WordSegmenter {
   // Internal ptr reference:
   #ptr = null;

   // Lifetimes are only to keep dependencies alive.
   // Since JS won't garbage collect until there are no incoming edges.
   #selfEdge = [];

   #internalConstructor(symbol, ptr, selfEdge) {
       if (symbol !== diplomatRuntime.internalConstructor) {
           console.error("WordSegmenter is an Opaque type. You cannot call its constructor.");
           return;
       }
       this.#ptr = ptr;
       this.#selfEdge = selfEdge;

       // Are we being borrowed? If not, we can register.
       if (this.#selfEdge.length === 0) {
           WordSegmenter_box_destroy_registry.register(this, this.#ptr);
       }

       return this;
   }
   get ffiValue() {
       return this.#ptr;
   }


   /**
    * Construct an [`WordSegmenter`] with automatically selecting the best available LSTM
    * or dictionary payload data, using compiled data. This does not assume any content locale.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `new_auto`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.new_auto) for more information.
    */
   static createAuto() {

       const result = wasm.icu4x_WordSegmenter_create_auto_mv1();

       try {
           return new WordSegmenter(diplomatRuntime.internalConstructor, result, []);
       }

       finally {
       }
   }

   /**
    * Construct an [`WordSegmenter`] with automatically selecting the best available LSTM
    * or dictionary payload data, using compiled data.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `try_new_auto`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.try_new_auto) for more information.
    */
   static createAutoWithContentLocale(locale) {
       const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true);


       const result = wasm.icu4x_WordSegmenter_create_auto_with_content_locale_mv1(diplomatReceive.buffer, locale.ffiValue);

       try {
           if (!diplomatReceive.resultFlag) {
               const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer));
               throw new globalThis.Error('DataError: ' + cause.value, { cause });
           }
           return new WordSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []);
       }

       finally {
           diplomatReceive.free();
       }
   }

   /**
    * Construct an [`WordSegmenter`] with automatically selecting the best available LSTM
    * or dictionary payload data, using a particular data source.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `try_new_auto`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.try_new_auto) for more information.
    */
   static createAutoWithContentLocaleAndProvider(provider, locale) {
       const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true);


       const result = wasm.icu4x_WordSegmenter_create_auto_with_content_locale_and_provider_mv1(diplomatReceive.buffer, provider.ffiValue, locale.ffiValue);

       try {
           if (!diplomatReceive.resultFlag) {
               const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer));
               throw new globalThis.Error('DataError: ' + cause.value, { cause });
           }
           return new WordSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []);
       }

       finally {
           diplomatReceive.free();
       }
   }

   /**
    * Construct an [`WordSegmenter`] with LSTM payload data for Burmese, Khmer, Lao, and
    * Thai, using compiled data.  This does not assume any content locale.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `new_lstm`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.new_lstm) for more information.
    */
   static createLstm() {

       const result = wasm.icu4x_WordSegmenter_create_lstm_mv1();

       try {
           return new WordSegmenter(diplomatRuntime.internalConstructor, result, []);
       }

       finally {
       }
   }

   /**
    * Construct an [`WordSegmenter`] with LSTM payload data for Burmese, Khmer, Lao, and
    * Thai, using compiled data.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `try_new_lstm`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.try_new_lstm) for more information.
    */
   static createLstmWithContentLocale(locale) {
       const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true);


       const result = wasm.icu4x_WordSegmenter_create_lstm_with_content_locale_mv1(diplomatReceive.buffer, locale.ffiValue);

       try {
           if (!diplomatReceive.resultFlag) {
               const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer));
               throw new globalThis.Error('DataError: ' + cause.value, { cause });
           }
           return new WordSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []);
       }

       finally {
           diplomatReceive.free();
       }
   }

   /**
    * Construct an [`WordSegmenter`] with LSTM payload data for Burmese, Khmer, Lao, and
    * Thai, using a particular data source.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `try_new_lstm`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.try_new_lstm) for more information.
    */
   static createLstmWithContentLocaleAndProvider(provider, locale) {
       const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true);


       const result = wasm.icu4x_WordSegmenter_create_lstm_with_content_locale_and_provider_mv1(diplomatReceive.buffer, provider.ffiValue, locale.ffiValue);

       try {
           if (!diplomatReceive.resultFlag) {
               const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer));
               throw new globalThis.Error('DataError: ' + cause.value, { cause });
           }
           return new WordSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []);
       }

       finally {
           diplomatReceive.free();
       }
   }

   /**
    * Construct an [`WordSegmenter`] with with dictionary payload data for Chinese, Japanese,
    * Burmese, Khmer, Lao, and Thai, using compiled data.  This does not assume any content locale.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and dictionary for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `new_dictionary`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.new_dictionary) for more information.
    */
   static createDictionary() {

       const result = wasm.icu4x_WordSegmenter_create_dictionary_mv1();

       try {
           return new WordSegmenter(diplomatRuntime.internalConstructor, result, []);
       }

       finally {
       }
   }

   /**
    * Construct an [`WordSegmenter`] with dictionary payload data for Chinese, Japanese,
    * Burmese, Khmer, Lao, and Thai, using compiled data.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and dictionary for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `try_new_dictionary`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.try_new_dictionary) for more information.
    */
   static createDictionaryWithContentLocale(locale) {
       const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true);


       const result = wasm.icu4x_WordSegmenter_create_dictionary_with_content_locale_mv1(diplomatReceive.buffer, locale.ffiValue);

       try {
           if (!diplomatReceive.resultFlag) {
               const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer));
               throw new globalThis.Error('DataError: ' + cause.value, { cause });
           }
           return new WordSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []);
       }

       finally {
           diplomatReceive.free();
       }
   }

   /**
    * Construct an [`WordSegmenter`] with dictionary payload data for Chinese, Japanese,
    * Burmese, Khmer, Lao, and Thai, using a particular data source.
    *
    * Note: currently, it uses dictionary for Chinese and Japanese, and dictionary for Burmese,
    * Khmer, Lao, and Thai.
    *
    * See the [Rust documentation for `try_new_dictionary`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenter.html#method.try_new_dictionary) for more information.
    */
   static createDictionaryWithContentLocaleAndProvider(provider, locale) {
       const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true);


       const result = wasm.icu4x_WordSegmenter_create_dictionary_with_content_locale_and_provider_mv1(diplomatReceive.buffer, provider.ffiValue, locale.ffiValue);

       try {
           if (!diplomatReceive.resultFlag) {
               const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer));
               throw new globalThis.Error('DataError: ' + cause.value, { cause });
           }
           return new WordSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []);
       }

       finally {
           diplomatReceive.free();
       }
   }

   /**
    * Segments a string.
    *
    * Ill-formed input is treated as if errors had been replaced with REPLACEMENT CHARACTERs according
    * to the WHATWG Encoding Standard.
    *
    * See the [Rust documentation for `segment_utf16`](https://docs.rs/icu/latest/icu/segmenter/struct.WordSegmenterBorrowed.html#method.segment_utf16) for more information.
    */
   segment(input) {
       let functionGarbageCollectorGrip = new diplomatRuntime.GarbageCollectorGrip();
       const inputSlice = diplomatRuntime.DiplomatBuf.str16(wasm, input);
       // This lifetime edge depends on lifetimes 'a
       let aEdges = [this, inputSlice];


       const result = wasm.icu4x_WordSegmenter_segment_utf16_mv1(this.ffiValue, ...inputSlice.splat());

       try {
           return new WordBreakIteratorUtf16(diplomatRuntime.internalConstructor, result, [], aEdges);
       }

       finally {
           functionGarbageCollectorGrip.releaseToGarbageCollector();

       }
   }

   constructor(symbol, ptr, selfEdge) {
       return this.#internalConstructor(...arguments)
   }
}