chromium/third_party/sentencepiece/src/src/normalizer.h

// Copyright 2016 Google Inc.
//
// Licensed 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.!

#ifndef NORMALIZER_NORMALIZER_H_
#define NORMALIZER_NORMALIZER_H_

#include <memory>
#include <set>
#include <string>
#include <utility>
#include <vector>

#include "absl/strings/string_view.h"
#include "common.h"
#include "sentencepiece_model.pb.h"
#include "sentencepiece_processor.h"
#include "third_party/darts_clone/darts.h"

namespace sentencepiece {
namespace normalizer {

// Given a list of strings, finds the longest string which is a
// prefix of a query.
class PrefixMatcher { … };

// Normalizer implements a simple text normalizer with
// user-defined string-to-string rules and leftmost longest
// matching. The rules of Normalizer are built with
// Builder::CompileCharsMap() method. Pre-compiled rules are
// also available via Builder::GetPrecompiledCharsMap(<name>) method.
//
// The motivation of Normalizer is to make flexible, user-customizable
// and self-contained normalizer.  All the logic of normalization is
// encoded in the model proto which allows us to define language/task
// dependent normalization rules without breaking the default rule.
class Normalizer { … };
}  // namespace normalizer
}  // namespace sentencepiece
#endif  // NORMALIZER_NORMALIZER_H_