dorfteich/packages/shared/src/text-diff.ts

/**
 * A minimal word-level text diff for the version-history view (issue #42,
 * ADR 0013 documents that a diff on the derived Markdown is sufficient — no
 * structural diff UI in v1). Kept dependency-free and in `packages/shared` so
 * the web app renders it and it can be unit-tested in isolation.
 */

export type DiffSegmentType = 'equal' | 'added' | 'removed';

export interface DiffSegment {
  type: DiffSegmentType;
  value: string;
}

/** Split into alternating word and whitespace tokens so the text round-trips. */
function tokenize(text: string): string[] {
  return text.match(/\s+|\S+/g) ?? [];
}

function pushSegment(segments: DiffSegment[], type: DiffSegmentType, value: string): void {
  const last = segments[segments.length - 1];
  if (last && last.type === type) {
    last.value += value;
  } else {
    segments.push({ type, value });
  }
}

/**
 * Diff `before` (an older version) against `after` (the current text),
 * returning ordered segments. `removed` marks text only in `before`, `added`
 * marks text only in `after`, `equal` is shared — consecutive tokens of the
 * same kind are merged so the UI renders whole runs.
 *
 * Uses a standard longest-common-subsequence DP over tokens; page Markdown is
 * small enough that the O(n·m) table is not a concern.
 */
export function diffMarkdown(before: string, after: string): DiffSegment[] {
  const a = tokenize(before);
  const b = tokenize(after);
  const n = a.length;
  const m = b.length;

  // lcs[i][j] = length of the LCS of a[i..] and b[j..].
  const lcs: number[][] = Array.from({ length: n + 1 }, () => new Array<number>(m + 1).fill(0));
  for (let i = n - 1; i >= 0; i -= 1) {
    for (let j = m - 1; j >= 0; j -= 1) {
      lcs[i]![j] =
        a[i] === b[j] ? lcs[i + 1]![j + 1]! + 1 : Math.max(lcs[i + 1]![j]!, lcs[i]![j + 1]!);
    }
  }

  const segments: DiffSegment[] = [];
  let i = 0;
  let j = 0;
  while (i < n && j < m) {
    if (a[i] === b[j]) {
      pushSegment(segments, 'equal', a[i]!);
      i += 1;
      j += 1;
    } else if (lcs[i + 1]![j]! >= lcs[i]![j + 1]!) {
      pushSegment(segments, 'removed', a[i]!);
      i += 1;
    } else {
      pushSegment(segments, 'added', b[j]!);
      j += 1;
    }
  }
  while (i < n) {
    pushSegment(segments, 'removed', a[i]!);
    i += 1;
  }
  while (j < m) {
    pushSegment(segments, 'added', b[j]!);
    j += 1;
  }
  return segments;
}