1// Licensed to the Apache Software Foundation (ASF) under one
2// or more contributor license agreements. See the NOTICE file
3// distributed with this work for additional information
4// regarding copyright ownership. The ASF licenses this file
5// to you under the Apache License, Version 2.0 (the
6// "License"); you may not use this file except in compliance
7// with the License. You may obtain a copy of the License at
8//
9// http://www.apache.org/licenses/LICENSE-2.0
10//
11// Unless required by applicable law or agreed to in writing,
12// software distributed under the License is distributed on an
13// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14// KIND, either express or implied. See the License for the
15// specific language governing permissions and limitations
16// under the License.
17
18#include <iostream>
19#include <list>
20#include <memory>
21
22#include "parquet/api/reader.h"
23
24int main(int argc, char** argv) {
25 if (argc > 5 || argc < 2) {
26 std::cerr << "Usage: parquet-reader [--only-metadata] [--no-memory-map] [--json] "
27 << "[--dump] [--print-key-value-metadata] [--columns=...] <file>"
28 << std::endl;
29 return -1;
30 }
31
32 std::string filename;
33 bool print_values = true;
34 bool print_key_value_metadata = false;
35 bool memory_map = true;
36 bool format_json = false;
37 bool format_dump = false;
38
39 // Read command-line options
40 const std::string COLUMNS_PREFIX = "--columns=";
41 std::list<int> columns;
42
43 char *param, *value;
44 for (int i = 1; i < argc; i++) {
45 if ((param = std::strstr(argv[i], "--only-metadata"))) {
46 print_values = false;
47 } else if ((param = std::strstr(argv[i], "--print-key-value-metadata"))) {
48 print_key_value_metadata = true;
49 } else if ((param = std::strstr(argv[i], "--no-memory-map"))) {
50 memory_map = false;
51 } else if ((param = std::strstr(argv[i], "--json"))) {
52 format_json = true;
53 } else if ((param = std::strstr(argv[i], "--dump"))) {
54 format_dump = true;
55 } else if ((param = std::strstr(argv[i], COLUMNS_PREFIX.c_str()))) {
56 value = std::strtok(param + COLUMNS_PREFIX.length(), ",");
57 while (value) {
58 columns.push_back(std::atoi(value));
59 value = std::strtok(nullptr, ",");
60 }
61 } else {
62 filename = argv[i];
63 }
64 }
65
66 try {
67 std::unique_ptr<parquet::ParquetFileReader> reader =
68 parquet::ParquetFileReader::OpenFile(filename, memory_map);
69 parquet::ParquetFilePrinter printer(reader.get());
70 if (format_json) {
71 printer.JSONPrint(std::cout, columns, filename.c_str());
72 } else {
73 printer.DebugPrint(std::cout, columns, print_values,
74 format_dump, print_key_value_metadata, filename.c_str());
75 }
76 } catch (const std::exception& e) {
77 std::cerr << "Parquet error: " << e.what() << std::endl;
78 return -1;
79 }
80
81 return 0;
82}
83