1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
|
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
#include <arrow/api.h>
#include <arrow/io/api.h>
#include <parquet/arrow/reader.h>
#include <parquet/arrow/writer.h>
#include <parquet/exception.h>
#include <iostream>
// #0 Build dummy data to pass around
// To have some input data, we first create an Arrow Table that holds
// some data.
std::shared_ptr<arrow::Table> generate_table() {
arrow::Int64Builder i64builder;
PARQUET_THROW_NOT_OK(i64builder.AppendValues({1, 2, 3, 4, 5}));
std::shared_ptr<arrow::Array> i64array;
PARQUET_THROW_NOT_OK(i64builder.Finish(&i64array));
arrow::StringBuilder strbuilder;
PARQUET_THROW_NOT_OK(strbuilder.Append("some"));
PARQUET_THROW_NOT_OK(strbuilder.Append("string"));
PARQUET_THROW_NOT_OK(strbuilder.Append("content"));
PARQUET_THROW_NOT_OK(strbuilder.Append("in"));
PARQUET_THROW_NOT_OK(strbuilder.Append("rows"));
std::shared_ptr<arrow::Array> strarray;
PARQUET_THROW_NOT_OK(strbuilder.Finish(&strarray));
std::shared_ptr<arrow::Schema> schema = arrow::schema(
{arrow::field("int", arrow::int64()), arrow::field("str", arrow::utf8())});
return arrow::Table::Make(schema, {i64array, strarray});
}
// #1 Write out the data as a Parquet file
void write_parquet_file(const arrow::Table& table) {
std::shared_ptr<arrow::io::FileOutputStream> outfile;
PARQUET_ASSIGN_OR_THROW(
outfile, arrow::io::FileOutputStream::Open("parquet-arrow-example.parquet"));
// The last argument to the function call is the size of the RowGroup in
// the parquet file. Normally you would choose this to be rather large but
// for the example, we use a small value to have multiple RowGroups.
PARQUET_THROW_NOT_OK(
parquet::arrow::WriteTable(table, arrow::default_memory_pool(), outfile, 3));
}
// #2: Fully read in the file
void read_whole_file() {
std::cout << "Reading parquet-arrow-example.parquet at once" << std::endl;
std::shared_ptr<arrow::io::ReadableFile> infile;
PARQUET_ASSIGN_OR_THROW(infile,
arrow::io::ReadableFile::Open("parquet-arrow-example.parquet",
arrow::default_memory_pool()));
std::unique_ptr<parquet::arrow::FileReader> reader;
PARQUET_THROW_NOT_OK(
parquet::arrow::OpenFile(infile, arrow::default_memory_pool(), &reader));
std::shared_ptr<arrow::Table> table;
PARQUET_THROW_NOT_OK(reader->ReadTable(&table));
std::cout << "Loaded " << table->num_rows() << " rows in " << table->num_columns()
<< " columns." << std::endl;
}
// #3: Read only a single RowGroup of the parquet file
void read_single_rowgroup() {
std::cout << "Reading first RowGroup of parquet-arrow-example.parquet" << std::endl;
std::shared_ptr<arrow::io::ReadableFile> infile;
PARQUET_ASSIGN_OR_THROW(infile,
arrow::io::ReadableFile::Open("parquet-arrow-example.parquet",
arrow::default_memory_pool()));
std::unique_ptr<parquet::arrow::FileReader> reader;
PARQUET_THROW_NOT_OK(
parquet::arrow::OpenFile(infile, arrow::default_memory_pool(), &reader));
std::shared_ptr<arrow::Table> table;
PARQUET_THROW_NOT_OK(reader->RowGroup(0)->ReadTable(&table));
std::cout << "Loaded " << table->num_rows() << " rows in " << table->num_columns()
<< " columns." << std::endl;
}
// #4: Read only a single column of the whole parquet file
void read_single_column() {
std::cout << "Reading first column of parquet-arrow-example.parquet" << std::endl;
std::shared_ptr<arrow::io::ReadableFile> infile;
PARQUET_ASSIGN_OR_THROW(infile,
arrow::io::ReadableFile::Open("parquet-arrow-example.parquet",
arrow::default_memory_pool()));
std::unique_ptr<parquet::arrow::FileReader> reader;
PARQUET_THROW_NOT_OK(
parquet::arrow::OpenFile(infile, arrow::default_memory_pool(), &reader));
std::shared_ptr<arrow::ChunkedArray> array;
PARQUET_THROW_NOT_OK(reader->ReadColumn(0, &array));
PARQUET_THROW_NOT_OK(arrow::PrettyPrint(*array, 4, &std::cout));
std::cout << std::endl;
}
// #5: Read only a single column of a RowGroup (this is known as ColumnChunk)
// from the Parquet file.
void read_single_column_chunk() {
std::cout << "Reading first ColumnChunk of the first RowGroup of "
"parquet-arrow-example.parquet"
<< std::endl;
std::shared_ptr<arrow::io::ReadableFile> infile;
PARQUET_ASSIGN_OR_THROW(infile,
arrow::io::ReadableFile::Open("parquet-arrow-example.parquet",
arrow::default_memory_pool()));
std::unique_ptr<parquet::arrow::FileReader> reader;
PARQUET_THROW_NOT_OK(
parquet::arrow::OpenFile(infile, arrow::default_memory_pool(), &reader));
std::shared_ptr<arrow::ChunkedArray> array;
PARQUET_THROW_NOT_OK(reader->RowGroup(0)->Column(0)->Read(&array));
PARQUET_THROW_NOT_OK(arrow::PrettyPrint(*array, 4, &std::cout));
std::cout << std::endl;
}
int main(int argc, char** argv) {
std::shared_ptr<arrow::Table> table = generate_table();
write_parquet_file(*table);
read_whole_file();
read_single_rowgroup();
read_single_column();
read_single_column_chunk();
}
|
