summaryrefslogtreecommitdiff
path: root/packages/cli/src/ui/utils/textUtils.ts
blob: f700604779a9838a42d2eeecc3ad656eebe0d47c (plain)
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
/**
 * @license
 * Copyright 2025 Google LLC
 * SPDX-License-Identifier: Apache-2.0
 */

/**
 * Calculates the maximum width of a multi-line ASCII art string.
 * @param asciiArt The ASCII art string.
 * @returns The length of the longest line in the ASCII art.
 */
export const getAsciiArtWidth = (asciiArt: string): number => {
  if (!asciiArt) {
    return 0;
  }
  const lines = asciiArt.split('\n');
  return Math.max(...lines.map((line) => line.length));
};

/**
 * Checks if a Buffer is likely binary by testing for the presence of a NULL byte.
 * The presence of a NULL byte is a strong indicator that the data is not plain text.
 * @param data The Buffer to check.
 * @param sampleSize The number of bytes from the start of the buffer to test.
 * @returns True if a NULL byte is found, false otherwise.
 */
export function isBinary(
  data: Buffer | null | undefined,
  sampleSize = 512,
): boolean {
  if (!data) {
    return false;
  }

  const sample = data.length > sampleSize ? data.subarray(0, sampleSize) : data;

  for (let i = 0; i < sample.length; i++) {
    // The presence of a NULL byte (0x00) is one of the most reliable
    // indicators of a binary file. Text files should not contain them.
    if (sample[i] === 0) {
      return true;
    }
  }

  // If no NULL bytes were found in the sample, we assume it's text.
  return false;
}

/*
 * -------------------------------------------------------------------------
 *  Unicode‑aware helpers (work at the code‑point level rather than UTF‑16
 *  code units so that surrogate‑pair emoji count as one "column".)
 * ---------------------------------------------------------------------- */

export function toCodePoints(str: string): string[] {
  // [...str] or Array.from both iterate by UTF‑32 code point, handling
  // surrogate pairs correctly.
  return Array.from(str);
}

export function cpLen(str: string): number {
  return toCodePoints(str).length;
}

export function cpSlice(str: string, start: number, end?: number): string {
  // Slice by code‑point indices and re‑join.
  const arr = toCodePoints(str).slice(start, end);
  return arr.join('');
}