llvm/clang-tools-extra/clangd/index/dex/PostingList.h

//===--- PostingList.h - Symbol identifiers storage interface  --*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This defines posting list interface: a storage for identifiers of symbols
/// which can be characterized by a specific feature (such as fuzzy-find
/// trigram, scope, type or any other Search Token). Posting lists can be
/// traversed in order using an iterator and are values for inverted index,
/// which maps search tokens to corresponding posting lists.
///
/// In order to decrease size of Index in-memory representation, Variable Byte
/// Encoding (VByte) is used for PostingLists compression. An overview of VByte
/// algorithm can be found in "Introduction to Information Retrieval" book:
/// https://nlp.stanford.edu/IR-book/html/htmledition/variable-byte-codes-1.html
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANGD_INDEX_DEX_POSTINGLIST_H
#define LLVM_CLANG_TOOLS_EXTRA_CLANGD_INDEX_DEX_POSTINGLIST_H

#include "Iterator.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallVector.h"
#include <cstdint>
#include <vector>

namespace clang {
namespace clangd {
namespace dex {
class Token;

/// NOTE: This is an implementation detail.
///
/// Chunk is a fixed-width piece of PostingList which contains the first DocID
/// in uncompressed format (Head) and delta-encoded Payload. It can be
/// decompressed upon request.
struct Chunk { … };
static_assert …;

/// PostingList is the storage of DocIDs which can be inserted to the Query
/// Tree as a leaf by constructing Iterator over the PostingList object. DocIDs
/// are stored in underlying chunks. Compression saves memory at a small cost
/// in access time, which is still fast enough in practice.
class PostingList { … };

} // namespace dex
} // namespace clangd
} // namespace clang

#endif // LLVM_CLANG_TOOLS_EXTRA_CLANGD_INDEX_DEX_POSTINGLIST_H