Apache ORC Files API

openapi: 3.0.3
info:
  title: Apache ORC Tools Conversion Files API
  description: Apache ORC is a self-describing, type-aware columnar file format for Hadoop workloads. This API represents the ORC tools REST service for reading, writing, and analyzing ORC files with support for predicate pushdown, compression, and schema evolution.
  version: 2.0.0
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
  contact:
    url: https://orc.apache.org/
servers:
- url: https://{host}/orc
  description: Apache ORC REST service
  variables:
    host:
      default: localhost:8080
tags:
- name: Files
paths:
  /files:
    get:
      operationId: listFiles
      summary: Apache ORC List ORC Files
      description: List ORC files available in the configured directory.
      tags:
      - Files
      responses:
        '200':
          description: List of ORC files
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/FileList'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /files/{filePath}/schema:
    get:
      operationId: getFileSchema
      summary: Apache ORC Get File Schema
      description: Get the schema of an ORC file including column names, types, and statistics.
      tags:
      - Files
      parameters:
      - name: filePath
        in: path
        required: true
        schema:
          type: string
        description: Path to the ORC file
        example: data/sales.orc
      responses:
        '200':
          description: ORC file schema
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OrcSchema'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /files/{filePath}/metadata:
    get:
      operationId: getFileMetadata
      summary: Apache ORC Get File Metadata
      description: Get metadata about an ORC file including stripes, row count, and compression info.
      tags:
      - Files
      parameters:
      - name: filePath
        in: path
        required: true
        schema:
          type: string
        description: Path to the ORC file
      responses:
        '200':
          description: ORC file metadata
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/FileMetadata'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /files/{filePath}/statistics:
    get:
      operationId: getColumnStatistics
      summary: Apache ORC Get Column Statistics
      description: Get per-column statistics from an ORC file including min, max, sum, and null counts.
      tags:
      - Files
      parameters:
      - name: filePath
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Column statistics
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ColumnStatisticsResponse'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    OrcSchema:
      type: object
      properties:
        typeName:
          type: string
          description: Top-level type name
          example: struct
        columns:
          type: array
          items:
            $ref: '#/components/schemas/ColumnType'
    ColumnStatistics:
      type: object
      properties:
        columnIndex:
          type: integer
          example: 0
        columnName:
          type: string
          example: customer_id
        valueCount:
          type: integer
          example: 999500
        nullCount:
          type: integer
          example: 500
        hasMinimum:
          type: boolean
          example: true
        minimum:
          type: string
          example: '1'
        maximum:
          type: string
          example: '999999'
    ColumnType:
      type: object
      properties:
        name:
          type: string
          description: Column name
          example: customer_id
        type:
          type: string
          description: ORC type
          example: int
          enum:
          - boolean
          - tinyint
          - smallint
          - int
          - bigint
          - float
          - double
          - string
          - binary
          - timestamp
          - date
          - decimal
          - varchar
          - char
          - list
          - map
          - struct
          - union
        nullable:
          type: boolean
          example: true
        children:
          type: array
          items:
            $ref: '#/components/schemas/ColumnType'
    FileMetadata:
      type: object
      properties:
        filePath:
          type: string
          example: data/sales.orc
        fileVersion:
          type: string
          example: '0.12'
        writerVersion:
          type: string
          example: ORC_135
        compression:
          type: string
          example: ZLIB
          enum:
          - NONE
          - ZLIB
          - SNAPPY
          - LZO
          - LZ4
          - ZSTD
        compressionBlockSize:
          type: integer
          example: 262144
        rowCount:
          type: integer
          example: 1000000
        rawDataSize:
          type: integer
          example: 104857600
        numberOfStripes:
          type: integer
          example: 10
        stripes:
          type: array
          items:
            $ref: '#/components/schemas/StripeInfo'
    FileInfo:
      type: object
      properties:
        path:
          type: string
          example: data/sales.orc
        size:
          type: integer
          description: File size in bytes
          example: 10485760
        rowCount:
          type: integer
          example: 1000000
        stripes:
          type: integer
          example: 10
    StripeInfo:
      type: object
      properties:
        stripeIndex:
          type: integer
          example: 0
        offset:
          type: integer
          example: 3
        length:
          type: integer
          example: 1048576
        rowCount:
          type: integer
          example: 100000
    FileList:
      type: object
      properties:
        files:
          type: array
          items:
            $ref: '#/components/schemas/FileInfo'
    ColumnStatisticsResponse:
      type: object
      properties:
        filePath:
          type: string
          example: data/sales.orc
        statistics:
          type: array
          items:
            $ref: '#/components/schemas/ColumnStatistics'
x-generated-from: documentation