vectorscan/src/nfa/limex_compile.h
Justin Viiret 7b54856642 Rose: allow block-mode merge of small prefixes
Previously, we disallowed the merging of all Rose prefixes in block mode
where the literal sets are not identical.

This change allows merging if the prefix graphs to be merged are very
small, as a small performance improvement for cases with lots of tiny
prefixes.

This check is deliberately conservative: graphs must have some common
vertices, and the result of the merge must not give up any
accelerability.
2016-03-01 11:34:26 +11:00

99 lines
3.9 KiB
C++

/*
* Copyright (c) 2015-2016, Intel Corporation
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Intel Corporation nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
/** \file
* \brief Main NFA build code.
*/
#ifndef LIMEX_COMPILE_H
#define LIMEX_COMPILE_H
#include <map>
#include <memory>
#include <vector>
#include "ue2common.h"
#include "nfagraph/ng_holder.h"
#include "nfagraph/ng_squash.h" // for NFAStateSet
#include "util/alloc.h"
#include "util/ue2_containers.h"
struct NFA;
namespace ue2 {
struct BoundedRepeatData;
struct CompileContext;
/** \brief Construct a LimEx NFA from an NGHolder.
*
* \param g Input NFA graph. Must have state IDs assigned.
* \param repeats Bounded repeat information, if any.
* \param reportSquashMap Single-match mode squash map.
* \param squashMap More general squash map.
* \param tops Tops and their start vertices,
* \param zombies The set of zombifying states.
* \param do_accel Calculate acceleration schemes.
* \param stateCompression Allow (and calculate masks for) state compression.
* \param hint If not INVALID_NFA, this allows a particular LimEx NFA model
to be requested.
* \param cc Compile context.
* \return a built NFA, or nullptr if no NFA could be constructed for this
* graph.
*/
aligned_unique_ptr<NFA> generate(NGHolder &g,
const ue2::unordered_map<NFAVertex, u32> &states,
const std::vector<BoundedRepeatData> &repeats,
const std::map<NFAVertex, NFAStateSet> &reportSquashMap,
const std::map<NFAVertex, NFAStateSet> &squashMap,
const std::map<u32, NFAVertex> &tops,
const std::set<NFAVertex> &zombies,
bool do_accel,
bool stateCompression,
u32 hint,
const CompileContext &cc);
/**
* \brief For a given graph, count the number of accelerable states it has.
*
* Note that this number may be greater than the number that are actually
* implementable.
*/
u32 countAccelStates(NGHolder &h,
const ue2::unordered_map<NFAVertex, u32> &states,
const std::vector<BoundedRepeatData> &repeats,
const std::map<NFAVertex, NFAStateSet> &reportSquashMap,
const std::map<NFAVertex, NFAStateSet> &squashMap,
const std::map<u32, NFAVertex> &tops,
const std::set<NFAVertex> &zombies,
const CompileContext &cc);
} // namespace ue2
#endif