Teamup/client/src/lib/diff.ts

export interface DiffSegment {
  kind: 'same' | 'removed' | 'added'
  text: string
}

const MAX_TOKENS = 1500

/**
 * Word-level diff (LCS) between two texts — used by the review inbox to show what the reviewer
 * changed vs the agent's proposal. Inputs are capped so the O(n·m) table stays cheap.
 */
export function diffWords(before: string, after: string): DiffSegment[] {
  const a = tokenize(before).slice(0, MAX_TOKENS)
  const b = tokenize(after).slice(0, MAX_TOKENS)

  // LCS length table.
  const dp: number[][] = Array.from({ length: a.length + 1 }, () => new Array<number>(b.length + 1).fill(0))
  for (let i = a.length - 1; i >= 0; i--) {
    for (let j = b.length - 1; j >= 0; j--) {
      dp[i][j] = a[i] === b[j] ? dp[i + 1][j + 1] + 1 : Math.max(dp[i + 1][j], dp[i][j + 1])
    }
  }

  // Walk the table, merging consecutive segments of the same kind.
  const segments: DiffSegment[] = []
  const push = (kind: DiffSegment['kind'], text: string) => {
    const last = segments[segments.length - 1]
    if (last && last.kind === kind) {
      last.text += text
    } else {
      segments.push({ kind, text })
    }
  }

  let i = 0
  let j = 0
  while (i < a.length && j < b.length) {
    if (a[i] === b[j]) {
      push('same', a[i])
      i++
      j++
    } else if (dp[i + 1][j] >= dp[i][j + 1]) {
      push('removed', a[i])
      i++
    } else {
      push('added', b[j])
      j++
    }
  }
  while (i < a.length) push('removed', a[i++])
  while (j < b.length) push('added', b[j++])

  return segments
}

/** Splits text into words + whitespace separators (kept, so the diff re-renders faithfully). */
function tokenize(text: string): string[] {
  return text.split(/(\s+)/).filter((t) => t.length > 0)
}