LineSegmenter.mjs (11486B)
1 // generated by diplomat-tool 2 import { DataError } from "./DataError.mjs" 3 import { DataProvider } from "./DataProvider.mjs" 4 import { LineBreakIteratorUtf16 } from "./LineBreakIteratorUtf16.mjs" 5 import { LineBreakOptions } from "./LineBreakOptions.mjs" 6 import { Locale } from "./Locale.mjs" 7 import wasm from "./diplomat-wasm.mjs"; 8 import * as diplomatRuntime from "./diplomat-runtime.mjs"; 9 10 11 /** 12 * An ICU4X line-break segmenter, capable of finding breakpoints in strings. 13 * 14 * See the [Rust documentation for `LineSegmenter`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html) for more information. 15 */ 16 const LineSegmenter_box_destroy_registry = new FinalizationRegistry((ptr) => { 17 wasm.icu4x_LineSegmenter_destroy_mv1(ptr); 18 }); 19 20 export class LineSegmenter { 21 // Internal ptr reference: 22 #ptr = null; 23 24 // Lifetimes are only to keep dependencies alive. 25 // Since JS won't garbage collect until there are no incoming edges. 26 #selfEdge = []; 27 28 #internalConstructor(symbol, ptr, selfEdge) { 29 if (symbol !== diplomatRuntime.internalConstructor) { 30 console.error("LineSegmenter is an Opaque type. You cannot call its constructor."); 31 return; 32 } 33 this.#ptr = ptr; 34 this.#selfEdge = selfEdge; 35 36 // Are we being borrowed? If not, we can register. 37 if (this.#selfEdge.length === 0) { 38 LineSegmenter_box_destroy_registry.register(this, this.#ptr); 39 } 40 41 return this; 42 } 43 get ffiValue() { 44 return this.#ptr; 45 } 46 47 48 /** 49 * Construct a [`LineSegmenter`] with default options (no locale-based tailoring) using compiled data. It automatically loads the best 50 * available payload data for Burmese, Khmer, Lao, and Thai. 51 * 52 * See the [Rust documentation for `new_auto`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_auto) for more information. 53 */ 54 static createAuto() { 55 56 const result = wasm.icu4x_LineSegmenter_create_auto_mv1(); 57 58 try { 59 return new LineSegmenter(diplomatRuntime.internalConstructor, result, []); 60 } 61 62 finally { 63 } 64 } 65 66 /** 67 * Construct a [`LineSegmenter`] with default options (no locale-based tailoring) and LSTM payload data for 68 * Burmese, Khmer, Lao, and Thai, using compiled data. 69 * 70 * See the [Rust documentation for `new_lstm`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_lstm) for more information. 71 */ 72 static createLstm() { 73 74 const result = wasm.icu4x_LineSegmenter_create_lstm_mv1(); 75 76 try { 77 return new LineSegmenter(diplomatRuntime.internalConstructor, result, []); 78 } 79 80 finally { 81 } 82 } 83 84 /** 85 * Construct a [`LineSegmenter`] with default options (no locale-based tailoring) and dictionary payload data for 86 * Burmese, Khmer, Lao, and Thai, using compiled data 87 * 88 * See the [Rust documentation for `new_dictionary`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_dictionary) for more information. 89 */ 90 static createDictionary() { 91 92 const result = wasm.icu4x_LineSegmenter_create_dictionary_mv1(); 93 94 try { 95 return new LineSegmenter(diplomatRuntime.internalConstructor, result, []); 96 } 97 98 finally { 99 } 100 } 101 102 /** 103 * Construct a [`LineSegmenter`] with custom options using compiled data. It automatically loads the best 104 * available payload data for Burmese, Khmer, Lao, and Thai. 105 * 106 * See the [Rust documentation for `new_auto`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_auto) for more information. 107 */ 108 static autoWithOptions(contentLocale, options) { 109 let functionCleanupArena = new diplomatRuntime.CleanupArena(); 110 111 112 const result = wasm.icu4x_LineSegmenter_create_auto_with_options_v2_mv1(contentLocale.ffiValue ?? 0, ...LineBreakOptions._fromSuppliedValue(diplomatRuntime.internalConstructor, options)._intoFFI(functionCleanupArena, {})); 113 114 try { 115 return new LineSegmenter(diplomatRuntime.internalConstructor, result, []); 116 } 117 118 finally { 119 functionCleanupArena.free(); 120 121 } 122 } 123 124 /** 125 * Construct a [`LineSegmenter`] with custom options. It automatically loads the best 126 * available payload data for Burmese, Khmer, Lao, and Thai, using a particular data source. 127 * 128 * See the [Rust documentation for `new_auto`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_auto) for more information. 129 */ 130 static autoWithOptionsAndProvider(provider, contentLocale, options) { 131 let functionCleanupArena = new diplomatRuntime.CleanupArena(); 132 133 const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true); 134 135 136 const result = wasm.icu4x_LineSegmenter_create_auto_with_options_v2_and_provider_mv1(diplomatReceive.buffer, provider.ffiValue, contentLocale.ffiValue ?? 0, ...LineBreakOptions._fromSuppliedValue(diplomatRuntime.internalConstructor, options)._intoFFI(functionCleanupArena, {})); 137 138 try { 139 if (!diplomatReceive.resultFlag) { 140 const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer)); 141 throw new globalThis.Error('DataError: ' + cause.value, { cause }); 142 } 143 return new LineSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []); 144 } 145 146 finally { 147 functionCleanupArena.free(); 148 149 diplomatReceive.free(); 150 } 151 } 152 153 /** 154 * Construct a [`LineSegmenter`] with custom options and LSTM payload data for 155 * Burmese, Khmer, Lao, and Thai, using compiled data. 156 * 157 * See the [Rust documentation for `new_lstm`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_lstm) for more information. 158 */ 159 static lstmWithOptions(contentLocale, options) { 160 let functionCleanupArena = new diplomatRuntime.CleanupArena(); 161 162 163 const result = wasm.icu4x_LineSegmenter_create_lstm_with_options_v2_mv1(contentLocale.ffiValue ?? 0, ...LineBreakOptions._fromSuppliedValue(diplomatRuntime.internalConstructor, options)._intoFFI(functionCleanupArena, {})); 164 165 try { 166 return new LineSegmenter(diplomatRuntime.internalConstructor, result, []); 167 } 168 169 finally { 170 functionCleanupArena.free(); 171 172 } 173 } 174 175 /** 176 * Construct a [`LineSegmenter`] with custom options and LSTM payload data for 177 * Burmese, Khmer, Lao, and Thai, using a particular data source. 178 * 179 * See the [Rust documentation for `new_lstm`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_lstm) for more information. 180 */ 181 static lstmWithOptionsAndProvider(provider, contentLocale, options) { 182 let functionCleanupArena = new diplomatRuntime.CleanupArena(); 183 184 const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true); 185 186 187 const result = wasm.icu4x_LineSegmenter_create_lstm_with_options_v2_and_provider_mv1(diplomatReceive.buffer, provider.ffiValue, contentLocale.ffiValue ?? 0, ...LineBreakOptions._fromSuppliedValue(diplomatRuntime.internalConstructor, options)._intoFFI(functionCleanupArena, {})); 188 189 try { 190 if (!diplomatReceive.resultFlag) { 191 const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer)); 192 throw new globalThis.Error('DataError: ' + cause.value, { cause }); 193 } 194 return new LineSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []); 195 } 196 197 finally { 198 functionCleanupArena.free(); 199 200 diplomatReceive.free(); 201 } 202 } 203 204 /** 205 * Construct a [`LineSegmenter`] with custom options and dictionary payload data for 206 * Burmese, Khmer, Lao, and Thai, using compiled data. 207 * 208 * See the [Rust documentation for `new_dictionary`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_dictionary) for more information. 209 */ 210 static dictionaryWithOptions(contentLocale, options) { 211 let functionCleanupArena = new diplomatRuntime.CleanupArena(); 212 213 214 const result = wasm.icu4x_LineSegmenter_create_dictionary_with_options_v2_mv1(contentLocale.ffiValue ?? 0, ...LineBreakOptions._fromSuppliedValue(diplomatRuntime.internalConstructor, options)._intoFFI(functionCleanupArena, {})); 215 216 try { 217 return new LineSegmenter(diplomatRuntime.internalConstructor, result, []); 218 } 219 220 finally { 221 functionCleanupArena.free(); 222 223 } 224 } 225 226 /** 227 * Construct a [`LineSegmenter`] with custom options and dictionary payload data for 228 * Burmese, Khmer, Lao, and Thai, using a particular data source. 229 * 230 * See the [Rust documentation for `new_dictionary`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenter.html#method.new_dictionary) for more information. 231 */ 232 static dictionaryWithOptionsAndProvider(provider, contentLocale, options) { 233 let functionCleanupArena = new diplomatRuntime.CleanupArena(); 234 235 const diplomatReceive = new diplomatRuntime.DiplomatReceiveBuf(wasm, 5, 4, true); 236 237 238 const result = wasm.icu4x_LineSegmenter_create_dictionary_with_options_v2_and_provider_mv1(diplomatReceive.buffer, provider.ffiValue, contentLocale.ffiValue ?? 0, ...LineBreakOptions._fromSuppliedValue(diplomatRuntime.internalConstructor, options)._intoFFI(functionCleanupArena, {})); 239 240 try { 241 if (!diplomatReceive.resultFlag) { 242 const cause = new DataError(diplomatRuntime.internalConstructor, diplomatRuntime.enumDiscriminant(wasm, diplomatReceive.buffer)); 243 throw new globalThis.Error('DataError: ' + cause.value, { cause }); 244 } 245 return new LineSegmenter(diplomatRuntime.internalConstructor, diplomatRuntime.ptrRead(wasm, diplomatReceive.buffer), []); 246 } 247 248 finally { 249 functionCleanupArena.free(); 250 251 diplomatReceive.free(); 252 } 253 } 254 255 /** 256 * Segments a string. 257 * 258 * Ill-formed input is treated as if errors had been replaced with REPLACEMENT CHARACTERs according 259 * to the WHATWG Encoding Standard. 260 * 261 * See the [Rust documentation for `segment_utf16`](https://docs.rs/icu/latest/icu/segmenter/struct.LineSegmenterBorrowed.html#method.segment_utf16) for more information. 262 */ 263 segment(input) { 264 let functionGarbageCollectorGrip = new diplomatRuntime.GarbageCollectorGrip(); 265 const inputSlice = diplomatRuntime.DiplomatBuf.str16(wasm, input); 266 // This lifetime edge depends on lifetimes 'a 267 let aEdges = [this, inputSlice]; 268 269 270 const result = wasm.icu4x_LineSegmenter_segment_utf16_mv1(this.ffiValue, ...inputSlice.splat()); 271 272 try { 273 return new LineBreakIteratorUtf16(diplomatRuntime.internalConstructor, result, [], aEdges); 274 } 275 276 finally { 277 functionGarbageCollectorGrip.releaseToGarbageCollector(); 278 279 } 280 } 281 282 constructor(symbol, ptr, selfEdge) { 283 return this.#internalConstructor(...arguments) 284 } 285 }