1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
// Copyright 2018-2023 the Deno authors. All rights reserved. MIT license.
import { BytesList } from "../bytes/bytes_list.ts";import { createLPS } from "./_common.ts";
/** Disposition of the delimiter. */export type DelimiterDisposition =  /** Include delimiter in the found chunk. */  | "suffix"  /** Include delimiter in the subsequent chunk. */  | "prefix"  /** Discard the delimiter. */  | "discard" // delimiter discarded;
export interface DelimiterStreamOptions {  /** Disposition of the delimiter. */  disposition?: DelimiterDisposition;}
/** * Divide a stream into chunks delimited by a given byte sequence. * * @example * Divide a CSV stream by commas, discarding the commas: * ```ts * import { DelimiterStream } from "https://deno.land/std@$STD_VERSION/streams/delimiter_stream.ts"; * const res = await fetch("https://example.com/data.csv"); * const parts = res.body! *   .pipeThrough(new DelimiterStream(new TextEncoder().encode(","))) *   .pipeThrough(new TextDecoderStream()); * ``` * * @example * Divide a stream after semi-colons, keeping the semi-colons in the output: * ```ts * import { DelimiterStream } from "https://deno.land/std@$STD_VERSION/streams/delimiter_stream.ts"; * const res = await fetch("https://example.com/file.js"); * const parts = res.body! *   .pipeThrough( *     new DelimiterStream( *       new TextEncoder().encode(";"), *       { disposition: "suffix" }, *     ) *   ) *   .pipeThrough(new TextDecoderStream()); * ``` * * @param delimiter Delimiter byte sequence * @param options Options for the transform stream * @returns Transform stream */export class DelimiterStream extends TransformStream<Uint8Array, Uint8Array> {  #bufs = new BytesList();  #delimiter: Uint8Array;  #inspectIndex = 0;  #matchIndex = 0;  #delimLen: number;  #delimLPS: Uint8Array;  #disp?: DelimiterDisposition;
  constructor(    delimiter: Uint8Array,    options?: DelimiterStreamOptions,  ) {    super({      transform: (chunk, controller) => {        this.#handle(chunk, controller);      },      flush: (controller) => {        controller.enqueue(this.#bufs.concat());      },    });
    this.#delimiter = delimiter;    this.#delimLen = delimiter.length;    this.#delimLPS = createLPS(delimiter);    this.#disp = options?.disposition ?? "discard";  }
  #handle(    chunk: Uint8Array,    controller: TransformStreamDefaultController<Uint8Array>,  ) {    this.#bufs.add(chunk);    let localIndex = 0;    while (this.#inspectIndex < this.#bufs.size()) {      if (chunk[localIndex] === this.#delimiter[this.#matchIndex]) {        this.#inspectIndex++;        localIndex++;        this.#matchIndex++;        if (this.#matchIndex === this.#delimLen) {          // Full match          const start = this.#inspectIndex - this.#delimLen;          const end = this.#disp == "suffix" ? this.#inspectIndex : start;          const copy = this.#bufs.slice(0, end);          controller.enqueue(copy);          const shift = this.#disp == "prefix" ? start : this.#inspectIndex;          this.#bufs.shift(shift);          this.#inspectIndex = this.#disp == "prefix" ? this.#delimLen : 0;          this.#matchIndex = 0;        }      } else {        if (this.#matchIndex === 0) {          this.#inspectIndex++;          localIndex++;        } else {          this.#matchIndex = this.#delimLPS[this.#matchIndex - 1];        }      }    }  }}