mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
ae65e281f3
to reflect the new license. We understand that people may be surprised that we're moving the header entirely to discuss the new license. We checked this carefully with the Foundation's lawyer and we believe this is the correct approach. Essentially, all code in the project is now made available by the LLVM project under our new license, so you will see that the license headers include that license only. Some of our contributors have contributed code under our old license, and accordingly, we have retained a copy of our old license notice in the top-level files in each project and repository. llvm-svn: 351636
70 lines
2.9 KiB
C++
70 lines
2.9 KiB
C++
//===-- TrigramIndex.h - a heuristic for SpecialCaseList --------*- 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
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// TrigramIndex implements a heuristic for SpecialCaseList that allows to
|
|
// filter out ~99% incoming queries when all regular expressions in the
|
|
// SpecialCaseList are simple wildcards with '*' and '.'. If rules are more
|
|
// complicated, the check is defeated and it will always pass the queries to a
|
|
// full regex.
|
|
//
|
|
// The basic idea is that in order for a wildcard to match a query, the query
|
|
// needs to have all trigrams which occur in the wildcard. We create a trigram
|
|
// index (trigram -> list of rules with it) and then count trigrams in the query
|
|
// for each rule. If the count for one of the rules reaches the expected value,
|
|
// the check passes the query to a regex. If none of the rules got enough
|
|
// trigrams, the check tells that the query is definitely not matched by any
|
|
// of the rules, and no regex matching is needed.
|
|
// A similar idea was used in Google Code Search as described in the blog post:
|
|
// https://swtch.com/~rsc/regexp/regexp4.html
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_SUPPORT_TRIGRAMINDEX_H
|
|
#define LLVM_SUPPORT_TRIGRAMINDEX_H
|
|
|
|
#include "llvm/ADT/SmallVector.h"
|
|
#include "llvm/ADT/StringMap.h"
|
|
|
|
#include <string>
|
|
#include <unordered_map>
|
|
#include <vector>
|
|
|
|
namespace llvm {
|
|
class StringRef;
|
|
|
|
class TrigramIndex {
|
|
public:
|
|
/// Inserts a new Regex into the index.
|
|
void insert(std::string Regex);
|
|
|
|
/// Returns true, if special case list definitely does not have a line
|
|
/// that matches the query. Returns false, if it's not sure.
|
|
bool isDefinitelyOut(StringRef Query) const;
|
|
|
|
/// Returned true, iff the heuristic is defeated and not useful.
|
|
/// In this case isDefinitelyOut always returns false.
|
|
bool isDefeated() { return Defeated; }
|
|
private:
|
|
// If true, the rules are too complicated for the check to work, and full
|
|
// regex matching is needed for every rule.
|
|
bool Defeated = false;
|
|
// The minimum number of trigrams which should match for a rule to have a
|
|
// chance to match the query. The number of elements equals the number of
|
|
// regex rules in the SpecialCaseList.
|
|
std::vector<unsigned> Counts;
|
|
// Index holds a list of rules indices for each trigram. The same indices
|
|
// are used in Counts to store per-rule limits.
|
|
// If a trigram is too common (>4 rules with it), we stop tracking it,
|
|
// which increases the probability for a need to match using regex, but
|
|
// decreases the costs in the regular case.
|
|
std::unordered_map<unsigned, SmallVector<size_t, 4>> Index{256};
|
|
};
|
|
|
|
} // namespace llvm
|
|
|
|
#endif // LLVM_SUPPORT_TRIGRAMINDEX_H
|