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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
|
// 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.
#pragma once
#include <cstdint>
#include <memory>
#include <string>
#include <vector>
#include "arrow/chunked_array.h" // IWYU pragma: keep
#include "arrow/record_batch.h"
#include "arrow/status.h"
#include "arrow/type.h"
#include "arrow/type_fwd.h"
#include "arrow/util/macros.h"
#include "arrow/util/visibility.h"
namespace arrow {
class Array;
class ChunkedArray;
class KeyValueMetadata;
class MemoryPool;
/// \class Table
/// \brief Logical table as sequence of chunked arrays
class ARROW_EXPORT Table {
public:
virtual ~Table() = default;
/// \brief Construct a Table from schema and columns
///
/// If columns is zero-length, the table's number of rows is zero
///
/// \param[in] schema The table schema (column types)
/// \param[in] columns The table's columns as chunked arrays
/// \param[in] num_rows number of rows in table, -1 (default) to infer from columns
static std::shared_ptr<Table> Make(std::shared_ptr<Schema> schema,
std::vector<std::shared_ptr<ChunkedArray>> columns,
int64_t num_rows = -1);
/// \brief Construct a Table from schema and arrays
///
/// \param[in] schema The table schema (column types)
/// \param[in] arrays The table's columns as arrays
/// \param[in] num_rows number of rows in table, -1 (default) to infer from columns
static std::shared_ptr<Table> Make(std::shared_ptr<Schema> schema,
const std::vector<std::shared_ptr<Array>>& arrays,
int64_t num_rows = -1);
/// \brief Construct a Table from a RecordBatchReader.
///
/// \param[in] reader the arrow::Schema for each batch
static Result<std::shared_ptr<Table>> FromRecordBatchReader(RecordBatchReader* reader);
/// \brief Construct a Table from RecordBatches, using schema supplied by the first
/// RecordBatch.
///
/// \param[in] batches a std::vector of record batches
static Result<std::shared_ptr<Table>> FromRecordBatches(
const std::vector<std::shared_ptr<RecordBatch>>& batches);
/// \brief Construct a Table from RecordBatches, using supplied schema. There may be
/// zero record batches
///
/// \param[in] schema the arrow::Schema for each batch
/// \param[in] batches a std::vector of record batches
static Result<std::shared_ptr<Table>> FromRecordBatches(
std::shared_ptr<Schema> schema,
const std::vector<std::shared_ptr<RecordBatch>>& batches);
/// \brief Construct a Table from a chunked StructArray. One column will be produced
/// for each field of the StructArray.
///
/// \param[in] array a chunked StructArray
static Result<std::shared_ptr<Table>> FromChunkedStructArray(
const std::shared_ptr<ChunkedArray>& array);
/// \brief Return the table schema
std::shared_ptr<Schema> schema() const { return schema_; }
/// \brief Return a column by index
virtual std::shared_ptr<ChunkedArray> column(int i) const = 0;
/// \brief Return vector of all columns for table
virtual const std::vector<std::shared_ptr<ChunkedArray>>& columns() const = 0;
/// Return a column's field by index
std::shared_ptr<Field> field(int i) const { return schema_->field(i); }
/// \brief Return vector of all fields for table
std::vector<std::shared_ptr<Field>> fields() const;
/// \brief Construct a zero-copy slice of the table with the
/// indicated offset and length
///
/// \param[in] offset the index of the first row in the constructed
/// slice
/// \param[in] length the number of rows of the slice. If there are not enough
/// rows in the table, the length will be adjusted accordingly
///
/// \return a new object wrapped in std::shared_ptr<Table>
virtual std::shared_ptr<Table> Slice(int64_t offset, int64_t length) const = 0;
/// \brief Slice from first row at offset until end of the table
std::shared_ptr<Table> Slice(int64_t offset) const { return Slice(offset, num_rows_); }
/// \brief Return a column by name
/// \param[in] name field name
/// \return an Array or null if no field was found
std::shared_ptr<ChunkedArray> GetColumnByName(const std::string& name) const {
auto i = schema_->GetFieldIndex(name);
return i == -1 ? NULLPTR : column(i);
}
/// \brief Remove column from the table, producing a new Table
virtual Result<std::shared_ptr<Table>> RemoveColumn(int i) const = 0;
/// \brief Add column to the table, producing a new Table
virtual Result<std::shared_ptr<Table>> AddColumn(
int i, std::shared_ptr<Field> field_arg,
std::shared_ptr<ChunkedArray> column) const = 0;
/// \brief Replace a column in the table, producing a new Table
virtual Result<std::shared_ptr<Table>> SetColumn(
int i, std::shared_ptr<Field> field_arg,
std::shared_ptr<ChunkedArray> column) const = 0;
/// \brief Return names of all columns
std::vector<std::string> ColumnNames() const;
/// \brief Rename columns with provided names
Result<std::shared_ptr<Table>> RenameColumns(
const std::vector<std::string>& names) const;
/// \brief Return new table with specified columns
Result<std::shared_ptr<Table>> SelectColumns(const std::vector<int>& indices) const;
/// \brief Replace schema key-value metadata with new metadata
/// \since 0.5.0
///
/// \param[in] metadata new KeyValueMetadata
/// \return new Table
virtual std::shared_ptr<Table> ReplaceSchemaMetadata(
const std::shared_ptr<const KeyValueMetadata>& metadata) const = 0;
/// \brief Flatten the table, producing a new Table. Any column with a
/// struct type will be flattened into multiple columns
///
/// \param[in] pool The pool for buffer allocations, if any
virtual Result<std::shared_ptr<Table>> Flatten(
MemoryPool* pool = default_memory_pool()) const = 0;
/// \return PrettyPrint representation suitable for debugging
std::string ToString() const;
/// \brief Perform cheap validation checks to determine obvious inconsistencies
/// within the table's schema and internal data.
///
/// This is O(k*m) where k is the total number of field descendents,
/// and m is the number of chunks.
///
/// \return Status
virtual Status Validate() const = 0;
/// \brief Perform extensive validation checks to determine inconsistencies
/// within the table's schema and internal data.
///
/// This is O(k*n) where k is the total number of field descendents,
/// and n is the number of rows.
///
/// \return Status
virtual Status ValidateFull() const = 0;
/// \brief Return the number of columns in the table
int num_columns() const { return schema_->num_fields(); }
/// \brief Return the number of rows (equal to each column's logical length)
int64_t num_rows() const { return num_rows_; }
/// \brief Determine if tables are equal
///
/// Two tables can be equal only if they have equal schemas.
/// However, they may be equal even if they have different chunkings.
bool Equals(const Table& other, bool check_metadata = false) const;
/// \brief Make a new table by combining the chunks this table has.
///
/// All the underlying chunks in the ChunkedArray of each column are
/// concatenated into zero or one chunk.
///
/// \param[in] pool The pool for buffer allocations
Result<std::shared_ptr<Table>> CombineChunks(
MemoryPool* pool = default_memory_pool()) const;
protected:
Table();
std::shared_ptr<Schema> schema_;
int64_t num_rows_;
private:
ARROW_DISALLOW_COPY_AND_ASSIGN(Table);
};
/// \brief Compute a stream of record batches from a (possibly chunked) Table
///
/// The conversion is zero-copy: each record batch is a view over a slice
/// of the table's columns.
class ARROW_EXPORT TableBatchReader : public RecordBatchReader {
public:
/// \brief Construct a TableBatchReader for the given table
explicit TableBatchReader(const Table& table);
std::shared_ptr<Schema> schema() const override;
Status ReadNext(std::shared_ptr<RecordBatch>* out) override;
/// \brief Set the desired maximum chunk size of record batches
///
/// The actual chunk size of each record batch may be smaller, depending
/// on actual chunking characteristics of each table column.
void set_chunksize(int64_t chunksize);
private:
const Table& table_;
std::vector<ChunkedArray*> column_data_;
std::vector<int> chunk_numbers_;
std::vector<int64_t> chunk_offsets_;
int64_t absolute_row_position_;
int64_t max_chunksize_;
};
/// \defgroup concat-tables ConcatenateTables function.
///
/// ConcatenateTables function.
/// @{
/// \brief Controls the behavior of ConcatenateTables().
struct ARROW_EXPORT ConcatenateTablesOptions {
/// If true, the schemas of the tables will be first unified with fields of
/// the same name being merged, according to `field_merge_options`, then each
/// table will be promoted to the unified schema before being concatenated.
/// Otherwise, all tables should have the same schema. Each column in the output table
/// is the result of concatenating the corresponding columns in all input tables.
bool unify_schemas = false;
Field::MergeOptions field_merge_options = Field::MergeOptions::Defaults();
static ConcatenateTablesOptions Defaults() { return {}; }
};
/// \brief Construct table from multiple input tables.
ARROW_EXPORT
Result<std::shared_ptr<Table>> ConcatenateTables(
const std::vector<std::shared_ptr<Table>>& tables,
ConcatenateTablesOptions options = ConcatenateTablesOptions::Defaults(),
MemoryPool* memory_pool = default_memory_pool());
/// \brief Promotes a table to conform to the given schema.
///
/// If a field in the schema does not have a corresponding column in the
/// table, a column of nulls will be added to the resulting table.
/// If the corresponding column is of type Null, it will be promoted to
/// the type specified by schema, with null values filled.
/// Returns an error:
/// - if the corresponding column's type is not compatible with the
/// schema.
/// - if there is a column in the table that does not exist in the schema.
///
/// \param[in] table the input Table
/// \param[in] schema the target schema to promote to
/// \param[in] pool The memory pool to be used if null-filled arrays need to
/// be created.
ARROW_EXPORT
Result<std::shared_ptr<Table>> PromoteTableToSchema(
const std::shared_ptr<Table>& table, const std::shared_ptr<Schema>& schema,
MemoryPool* pool = default_memory_pool());
} // namespace arrow
|