iceberg-cpp
Loading...
Searching...
No Matches
content_file_util.h
Go to the documentation of this file.
1/*
2 * Licensed to the Apache Software Foundation (ASF) under one
3 * or more contributor license agreements. See the NOTICE file
4 * distributed with this work for additional information
5 * regarding copyright ownership. The ASF licenses this file
6 * to you under the Apache License, Version 2.0 (the
7 * "License"); you may not use this file except in compliance
8 * with the License. You may obtain a copy of the License at
9 *
10 * http://www.apache.org/licenses/LICENSE-2.0
11 *
12 * Unless required by applicable law or agreed to in writing,
13 * software distributed under the License is distributed on an
14 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
15 * KIND, either express or implied. See the License for the
16 * specific language governing permissions and limitations
17 * under the License.
18 */
19
20#pragma once
21
24
25#include <optional>
26#include <span>
27#include <string>
28#include <unordered_set>
29
32#include "iceberg/result.h"
33#include "iceberg/type_fwd.h"
34
35namespace iceberg {
36
38struct ICEBERG_EXPORT ContentFileUtil {
40 static bool IsDV(const DataFile& file);
41
44
46 static Result<bool> IsFileScoped(const DataFile& file);
47
49 static bool ContainsSingleDV(std::span<const std::shared_ptr<DataFile>> files);
50
52 static std::string DVDesc(const DataFile& file);
53
56 static int64_t ContentSizeInBytes(const DataFile& file);
57
59 static void DropAllStats(DataFile& data_file);
60
62 static void DropUnselectedStats(DataFile& data_file,
63 const std::unordered_set<int32_t>& selected_columns);
64};
65
66} // namespace iceberg
Define symbol visibility macros for core Iceberg APIs.
Core Apache Iceberg C++ APIs.
Definition arrow_io_util.h:33
std::expected< T, E > Result
Result alias.
Definition result.h:88
Define Result, Status, and error helpers.
Utility functions for content files.
Definition content_file_util.h:38
static void DropUnselectedStats(DataFile &data_file, const std::unordered_set< int32_t > &selected_columns)
Preserve stats based on selected columns.
static bool ContainsSingleDV(std::span< const std::shared_ptr< DataFile > > files)
Check if a collection of delete files contains exactly one DV.
static void DropAllStats(DataFile &data_file)
In-place drop stats.
static std::string DVDesc(const DataFile &file)
Generate a description string for a deletion vector.
static Result< bool > IsFileScoped(const DataFile &file)
Check if a delete file is file-scoped.
static bool IsDV(const DataFile &file)
Check if a delete file is a deletion vector (DV).
static int64_t ContentSizeInBytes(const DataFile &file)
Size in bytes of the portion of file relevant to a scan task — the DV's own content size when set,...
static Result< std::optional< std::string > > ReferencedDataFile(const DataFile &file)
Get the referenced data file path from a position delete file.
DataFile carries data file path, partition tuple, metrics, ...
Definition manifest_entry.h:62