Function collectBlobSizes

src/codeScan/git/diffProcessor.ts:189–242

(
  repoPath: string,
  files: FileRecord[],
)

}

async function collectBlobSizes(
  repoPath: string,
  files: FileRecord[],
): Promise<Map<string, number>> {
  const shas = new Set<string>();

  for (const file of files) {
    if (file.skipReason) {
      continue; // Skip files already marked for skipping
    }

    if (file.shaA) {
      shas.add(file.shaA);
    }
    if (file.shaB) {
      shas.add(file.shaB);
    }
  }

  if (shas.size === 0) {
    return new Map();
  }

  // Use git cat-file --batch-check
  const shaList = Array.from(shas).join('\n');
  const result = await execa(
    'git',
    ['cat-file', '--batch-check=%(objectname) %(objecttype) %(objectsize)'],
    {
      cwd: repoPath,
      input: shaList,
    },
  );

  const sizeMap = new Map<string, number>();

  for (const line of result.stdout.split('\n')) {
    if (!line.trim()) {
      continue;
    }

    const parts = line.split(/\s+/);
    if (parts.length < 3) {
      continue;
    }

    const sha = parts[0];
    const size = Number.parseInt(parts[2], 10);

    sizeMap.set(sha, size);
  }

  return sizeMap;
}

function attachBlobSizesAndFilter(files: FileRecord[], sizeMap: Map<string, number>): FileRecord[] {
  return files.map((file) => {