1#!/usr/bin/env python3 2 3## 4# Licensed to the Apache Software Foundation (ASF) under one 5# or more contributor license agreements. See the NOTICE file 6# distributed with this work for additional information 7# regarding copyright ownership. The ASF licenses this file 8# to you under the Apache License, Version 2.0 (the 9# "License"); you may not use this file except in compliance 10# with the License. You may obtain a copy of the License at 11# 12# https://www.apache.org/licenses/LICENSE-2.0 13# 14# Unless required by applicable law or agreed to in writing, software 15# distributed under the License is distributed on an "AS IS" BASIS, 16# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 17# 18# See the License for the specific language governing permissions and 19# limitations under the License. 20 21import argparse 22import base64 23import io 24import json 25import os 26from pathlib import Path 27from typing import IO, TextIO 28 29import avro.codecs 30import avro.datafile 31import avro.io 32import avro.schema 33 34NULL_CODEC = avro.datafile.NULL_CODEC 35CODECS_TO_VALIDATE = avro.codecs.KNOWN_CODECS.keys() 36 37DATUM = { 38 "intField": 12, 39 "longField": 15234324, 40 "stringField": "hey", 41 "boolField": True, 42 "floatField": 1234.0, 43 "doubleField": -1234.0, 44 "bytesField": b"12312adf", 45 "nullField": None, 46 "arrayField": [5.0, 0.0, 12.0], 47 "mapField": {"a": {"label": "a"}, "bee": {"label": "cee"}}, 48 "unionField": 12.0, 49 "enumField": "C", 50 "fixedField": b"1019181716151413", 51 "recordField": {"label": "blah", "children": [{"label": "inner", "children": []}]}, 52} 53 54 55def gen_data(codec: str, datum_writer: avro.io.DatumWriter, interop_schema: avro.schema.Schema) -> bytes: 56 with io.BytesIO() as file_, avro.datafile.DataFileWriter(file_, datum_writer, interop_schema, codec=codec) as dfw: 57 dfw.append(DATUM) 58 dfw.flush() 59 return file_.getvalue() 60 61 62def generate(schema_file: TextIO, output_path: IO) -> None: 63 interop_schema = avro.schema.parse(schema_file.read()) 64 datum_writer = avro.io.DatumWriter() 65 output = ((codec, gen_data(codec, datum_writer, interop_schema)) for codec in CODECS_TO_VALIDATE) 66 if output_path.isatty(): 67 json.dump({codec: base64.b64encode(data).decode() for codec, data in output}, output_path) 68 return 69 for codec, data in output: 70 if codec == NULL_CODEC: 71 output_path.write(data) 72 continue 73 base, ext = os.path.splitext(output_path.name) 74 Path(f"{base}_{codec}{ext}").write_bytes(data) 75 76 77def _parse_args() -> argparse.Namespace: 78 """Parse the command-line arguments""" 79 parser = argparse.ArgumentParser() 80 parser.add_argument("schema_path", type=argparse.FileType("r")) 81 parser.add_argument( 82 "output_path", 83 type=argparse.FileType("wb"), 84 help=( 85 "Write the different codec variants to these files. " 86 "Will append codec extensions to multiple files. " 87 "If '-', will output base64 encoded binary" 88 ), 89 ) 90 return parser.parse_args() 91 92 93def main() -> int: 94 args = _parse_args() 95 generate(args.schema_path, args.output_path) 96 return 0 97 98 99if __name__ == "__main__": 100 raise SystemExit(main()) 101