OLD | NEW |
(Empty) | |
| 1 // Copyright (C) 2011 Google Inc. |
| 2 // |
| 3 // Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 // you may not use this file except in compliance with the License. |
| 5 // You may obtain a copy of the License at |
| 6 // |
| 7 // http://www.apache.org/licenses/LICENSE-2.0 |
| 8 // |
| 9 // Unless required by applicable law or agreed to in writing, software |
| 10 // distributed under the License is distributed on an "AS IS" BASIS, |
| 11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 // See the License for the specific language governing permissions and |
| 13 // limitations under the License. |
| 14 |
| 15 // Author: George Yakovlev |
| 16 // Philippe Liard |
| 17 // |
| 18 // Regexp adapter to allow a pluggable regexp engine. It has been introduced |
| 19 // during the integration of the open-source version of this library into |
| 20 // Chromium to be able to use the ICU Regex engine instead of RE2, which is not |
| 21 // officially supported on Windows. |
| 22 // Since RE2 was initially used in this library, the interface of this adapter |
| 23 // is very close to the subset of the RE2 API used in phonenumberutil.cc. |
| 24 |
| 25 #ifndef I18N_PHONENUMBERS_REGEXP_ADAPTER_H_ |
| 26 #define I18N_PHONENUMBERS_REGEXP_ADAPTER_H_ |
| 27 |
| 28 #include <cstddef> |
| 29 #include <string> |
| 30 |
| 31 namespace i18n { |
| 32 namespace phonenumbers { |
| 33 |
| 34 using std::string; |
| 35 |
| 36 // RegExpInput is the interface that abstracts the input that feeds the |
| 37 // Consume() method of RegExp which may differ depending on its various |
| 38 // implementations (StringPiece for RE2, UnicodeString for ICU Regex). |
| 39 class RegExpInput { |
| 40 public: |
| 41 virtual ~RegExpInput() {} |
| 42 |
| 43 // Creates a new instance of the default RegExpInput implementation. The |
| 44 // deletion of the returned instance is under the responsibility of the |
| 45 // caller. |
| 46 static RegExpInput* Create(const string& utf8_input); |
| 47 |
| 48 // Converts to a C++ string. |
| 49 virtual string ToString() const = 0; |
| 50 }; |
| 51 |
| 52 // The regular expression abstract class. It supports only functions used in |
| 53 // phonenumberutil.cc. Consume(), Match() and Replace() methods must be |
| 54 // implemented. |
| 55 class RegExp { |
| 56 public: |
| 57 virtual ~RegExp() {} |
| 58 |
| 59 // Creates a new instance of the default RegExp implementation. The deletion |
| 60 // of the returned instance is under the responsibility of the caller. |
| 61 static RegExp* Create(const string& utf8_regexp); |
| 62 |
| 63 // Matches string to regular expression, returns true if expression was |
| 64 // matched, false otherwise, advances position in the match. |
| 65 // input_string - string to be searched. |
| 66 // anchor_at_start - if true, match would be successful only if it appears at |
| 67 // the beginning of the tested region of the string. |
| 68 // matched_string1 - the first string extracted from the match. Can be NULL. |
| 69 // matched_string2 - the second string extracted from the match. Can be NULL. |
| 70 // matched_string3 - the third string extracted from the match. Can be NULL. |
| 71 virtual bool Consume(RegExpInput* input_string, |
| 72 bool anchor_at_start, |
| 73 string* matched_string1, |
| 74 string* matched_string2, |
| 75 string* matched_string3) const = 0; |
| 76 |
| 77 // Helper methods calling the Consume method that assume the match must start |
| 78 // at the beginning. |
| 79 inline bool Consume(RegExpInput* input_string, |
| 80 string* matched_string1, |
| 81 string* matched_string2, |
| 82 string* matched_string3) const { |
| 83 return Consume(input_string, true, matched_string1, matched_string2, |
| 84 matched_string3); |
| 85 } |
| 86 |
| 87 inline bool Consume(RegExpInput* input_string, |
| 88 string* matched_string1, |
| 89 string* matched_string2) const { |
| 90 return Consume(input_string, true, matched_string1, matched_string2, NULL); |
| 91 } |
| 92 |
| 93 inline bool Consume(RegExpInput* input_string, string* matched_string) const { |
| 94 return Consume(input_string, true, matched_string, NULL, NULL); |
| 95 } |
| 96 |
| 97 inline bool Consume(RegExpInput* input_string) const { |
| 98 return Consume(input_string, true, NULL, NULL, NULL); |
| 99 } |
| 100 |
| 101 // Helper method calling the Consume method that assumes the match can start |
| 102 // at any place in the string. |
| 103 inline bool FindAndConsume(RegExpInput* input_string, |
| 104 string* matched_string) const { |
| 105 return Consume(input_string, false, matched_string, NULL, NULL); |
| 106 } |
| 107 |
| 108 // Matches string to regular expression, returns true if the expression was |
| 109 // matched, false otherwise. |
| 110 // input_string - string to be searched. |
| 111 // full_match - if true, match would be successful only if it matches the |
| 112 // complete string. |
| 113 // matched_string - the string extracted from the match. Can be NULL. |
| 114 virtual bool Match(const string& input_string, |
| 115 bool full_match, |
| 116 string* matched_string) const = 0; |
| 117 |
| 118 // Helper methods calling the Match method with the right arguments. |
| 119 inline bool PartialMatch(const string& input_string, |
| 120 string* matched_string) const { |
| 121 return Match(input_string, false, matched_string); |
| 122 } |
| 123 |
| 124 inline bool PartialMatch(const string& input_string) const { |
| 125 return Match(input_string, false, NULL); |
| 126 } |
| 127 |
| 128 inline bool FullMatch(const string& input_string, |
| 129 string* matched_string) const { |
| 130 return Match(input_string, true, matched_string); |
| 131 } |
| 132 |
| 133 inline bool FullMatch(const string& input_string) const { |
| 134 return Match(input_string, true, NULL); |
| 135 } |
| 136 |
| 137 // Replaces match(es) in 'string_to_process'. If 'global' is true, |
| 138 // replaces all the matches, otherwise only the first match. |
| 139 // replacement_string - text the matches are replaced with. The groups in the |
| 140 // replacement string are referenced with the $[0-9] notation. |
| 141 // Returns true if the pattern matches and a replacement occurs, false |
| 142 // otherwise. |
| 143 virtual bool Replace(string* string_to_process, |
| 144 bool global, |
| 145 const string& replacement_string) const = 0; |
| 146 |
| 147 // Helper methods calling the Replace method with the right arguments. |
| 148 inline bool Replace(string* string_to_process, |
| 149 const string& replacement_string) const { |
| 150 return Replace(string_to_process, false, replacement_string); |
| 151 } |
| 152 |
| 153 inline bool GlobalReplace(string* string_to_process, |
| 154 const string& replacement_string) const { |
| 155 return Replace(string_to_process, true, replacement_string); |
| 156 } |
| 157 }; |
| 158 |
| 159 } // namespace phonenumbers |
| 160 } // namespace i18n |
| 161 |
| 162 #endif // I18N_PHONENUMBERS_REGEXP_ADAPTER_H_ |
OLD | NEW |