{
  "status": "shipping",
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-17",
  "slug": "parquet",
  "term": "Apache Parquet",
  "aliases": [],
  "definition": "Apache Parquet is a column-oriented file format that organizes data into row groups, column chunks and encoded pages.",
  "note": "Structure: file metadata describes row groups and column chunks; page headers describe individual pages. A reader can select a subset without decoding all data in the file. [parquet-metadata] [arrow-read]\n\nIntegrity: optional page checksums and their verification are separate from schema readability or correct row counts. A successful projected read is not evidence about the unselected payload. [parquet-crc] [arrow-read]",
  "related": [
    "parquet-page-checksum",
    "checksum",
    "file-storage",
    "zone-map",
    "parquet-row-group",
    "parquet-column-chunk"
  ],
  "advantages": [],
  "limitations": [],
  "citations": [
    {
      "id": "parquet-crc",
      "title": "Apache Parquet: page checksumming",
      "url": "https://parquet.apache.org/docs/file-format/data-pages/checksumming/",
      "accessed": "2026-10-17"
    },
    {
      "id": "arrow-read",
      "title": "Apache Arrow 21.0: read_table checksum verification and column selection",
      "url": "https://arrow.apache.org/docs/21.0/python/generated/pyarrow.parquet.read_table.html",
      "accessed": "2026-10-17"
    },
    {
      "id": "arrow-write",
      "title": "Apache Arrow 21.0: write_table page checksum option",
      "url": "https://arrow.apache.org/docs/21.0/python/generated/pyarrow.parquet.write_table.html",
      "accessed": "2026-10-17"
    },
    {
      "id": "arrow-code",
      "title": "Apache Arrow 21.0.0: SerializedPageReader checksum presence guard",
      "url": "https://github.com/apache/arrow/blob/apache-arrow-21.0.0/cpp/src/parquet/column_reader.cc#L433-L443",
      "accessed": "2026-10-17"
    },
    {
      "id": "parquet-encoding",
      "title": "Apache Parquet: PLAIN INT64 encoding",
      "url": "https://parquet.apache.org/docs/file-format/data-pages/encodings/",
      "accessed": "2026-10-17"
    },
    {
      "id": "parquet-metadata",
      "title": "Apache Parquet: file, column and page metadata",
      "url": "https://parquet.apache.org/docs/file-format/metadata/",
      "accessed": "2026-10-17"
    }
  ]
}