chromium/third_party/liburlpattern/tokenize.cc

// Copyright 2020 The Chromium Authors
// Copyright 2014 Blake Embrey ([email protected])
// Use of this source code is governed by an MIT-style license that can be
// found in the LICENSE file or at https://opensource.org/licenses/MIT.

#include "third_party/liburlpattern/tokenize.h"

#include <string_view>

#include "third_party/abseil-cpp/absl/strings/str_format.h"
#include "third_party/icu/source/common/unicode/uchar.h"
#include "third_party/icu/source/common/unicode/utf8.h"
#include "third_party/liburlpattern/utils.h"

// The following code is a translation from the path-to-regexp typescript at:
//
//  https://github.com/pillarjs/path-to-regexp/blob/125c43e6481f68cc771a5af22b914acdb8c5ba1f/src/index.ts#L4-L124

namespace liburlpattern {

namespace {

bool IsASCII(UChar32 c) { … }

class Tokenizer { … };

}  // namespace

const char* TokenTypeToString(TokenType type) { … }

std::ostream& operator<<(std::ostream& o, Token token) { … }

// Split the input pattern into a list of tokens.
absl::StatusOr<std::vector<Token>> Tokenize(std::string_view pattern,
                                            TokenizePolicy policy) { … }

}  // namespace liburlpattern