Function parseGitNumstat

source code/utils/gitDiff.ts:150–191

(stdout: string)

 * Only stores first MAX_FILES entries in perFileStats.
 */
export function parseGitNumstat(stdout: string): NumstatResult {
  const lines = stdout.trim().split('\n').filter(Boolean)
  let added = 0
  let removed = 0
  let validFileCount = 0
  const perFileStats = new Map<string, PerFileStats>()

  for (const line of lines) {
    const parts = line.split('\t')
    // Valid numstat lines have exactly 3 tab-separated parts: added, removed, filename
    if (parts.length < 3) continue

    validFileCount++
    const addStr = parts[0]
    const remStr = parts[1]
    const filePath = parts.slice(2).join('\t') // filename may contain tabs
    const isBinary = addStr === '-' || remStr === '-'
    const fileAdded = isBinary ? 0 : parseInt(addStr ?? '0', 10) || 0
    const fileRemoved = isBinary ? 0 : parseInt(remStr ?? '0', 10) || 0

    added += fileAdded
    removed += fileRemoved

    // Only store first MAX_FILES entries
    if (perFileStats.size < MAX_FILES) {
      perFileStats.set(filePath, {
        added: fileAdded,
        removed: fileRemoved,
        isBinary,
      })
    }
  }

  return {
    stats: {
      filesCount: validFileCount,
      linesAdded: added,
      linesRemoved: removed,
    },
    perFileStats,
  }
}

/**
 * Parse unified diff output into per-file hunks.