You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
102 lines
3.6 KiB
102 lines
3.6 KiB
2 years ago
|
import { EndOfStreamError } from 'peek-readable';
|
||
|
|
import { Buffer } from 'node:buffer';
|
||
|
|
/**
|
||
|
|
* Core tokenizer
|
||
|
|
*/
|
||
|
|
export class AbstractTokenizer {
|
||
|
|
constructor(fileInfo) {
|
||
|
|
/**
|
||
|
|
* Tokenizer-stream position
|
||
|
|
*/
|
||
|
|
this.position = 0;
|
||
|
|
this.numBuffer = new Uint8Array(8);
|
||
|
|
this.fileInfo = fileInfo ? fileInfo : {};
|
||
|
|
}
|
||
|
|
/**
|
||
|
|
* Read a token from the tokenizer-stream
|
||
|
|
* @param token - The token to read
|
||
|
|
* @param position - If provided, the desired position in the tokenizer-stream
|
||
|
|
* @returns Promise with token data
|
||
|
|
*/
|
||
|
|
async readToken(token, position = this.position) {
|
||
|
|
const uint8Array = Buffer.alloc(token.len);
|
||
|
|
const len = await this.readBuffer(uint8Array, { position });
|
||
|
|
if (len < token.len)
|
||
|
|
throw new EndOfStreamError();
|
||
|
|
return token.get(uint8Array, 0);
|
||
|
|
}
|
||
|
|
/**
|
||
|
|
* Peek a token from the tokenizer-stream.
|
||
|
|
* @param token - Token to peek from the tokenizer-stream.
|
||
|
|
* @param position - Offset where to begin reading within the file. If position is null, data will be read from the current file position.
|
||
|
|
* @returns Promise with token data
|
||
|
|
*/
|
||
|
|
async peekToken(token, position = this.position) {
|
||
|
|
const uint8Array = Buffer.alloc(token.len);
|
||
|
|
const len = await this.peekBuffer(uint8Array, { position });
|
||
|
|
if (len < token.len)
|
||
|
|
throw new EndOfStreamError();
|
||
|
|
return token.get(uint8Array, 0);
|
||
|
|
}
|
||
|
|
/**
|
||
|
|
* Read a numeric token from the stream
|
||
|
|
* @param token - Numeric token
|
||
|
|
* @returns Promise with number
|
||
|
|
*/
|
||
|
|
async readNumber(token) {
|
||
|
|
const len = await this.readBuffer(this.numBuffer, { length: token.len });
|
||
|
|
if (len < token.len)
|
||
|
|
throw new EndOfStreamError();
|
||
|
|
return token.get(this.numBuffer, 0);
|
||
|
|
}
|
||
|
|
/**
|
||
|
|
* Read a numeric token from the stream
|
||
|
|
* @param token - Numeric token
|
||
|
|
* @returns Promise with number
|
||
|
|
*/
|
||
|
|
async peekNumber(token) {
|
||
|
|
const len = await this.peekBuffer(this.numBuffer, { length: token.len });
|
||
|
|
if (len < token.len)
|
||
|
|
throw new EndOfStreamError();
|
||
|
|
return token.get(this.numBuffer, 0);
|
||
|
|
}
|
||
|
|
/**
|
||
|
|
* Ignore number of bytes, advances the pointer in under tokenizer-stream.
|
||
|
|
* @param length - Number of bytes to ignore
|
||
|
|
* @return resolves the number of bytes ignored, equals length if this available, otherwise the number of bytes available
|
||
|
|
*/
|
||
|
|
async ignore(length) {
|
||
|
|
if (this.fileInfo.size !== undefined) {
|
||
|
|
const bytesLeft = this.fileInfo.size - this.position;
|
||
|
|
if (length > bytesLeft) {
|
||
|
|
this.position += bytesLeft;
|
||
|
|
return bytesLeft;
|
||
|
|
}
|
||
|
|
}
|
||
|
|
this.position += length;
|
||
|
|
return length;
|
||
|
|
}
|
||
|
|
async close() {
|
||
|
|
// empty
|
||
|
|
}
|
||
|
|
normalizeOptions(uint8Array, options) {
|
||
|
|
if (options && options.position !== undefined && options.position < this.position) {
|
||
|
|
throw new Error('`options.position` must be equal or greater than `tokenizer.position`');
|
||
|
|
}
|
||
|
|
if (options) {
|
||
|
|
return {
|
||
|
|
mayBeLess: options.mayBeLess === true,
|
||
|
|
offset: options.offset ? options.offset : 0,
|
||
|
|
length: options.length ? options.length : (uint8Array.length - (options.offset ? options.offset : 0)),
|
||
|
|
position: options.position ? options.position : this.position
|
||
|
|
};
|
||
|
|
}
|
||
|
|
return {
|
||
|
|
mayBeLess: false,
|
||
|
|
offset: 0,
|
||
|
|
length: uint8Array.length,
|
||
|
|
position: this.position
|
||
|
|
};
|
||
|
|
}
|
||
|
|
}
|