| OLD | NEW |
| (Empty) |
| 1 // Copyright (C) 2014 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 #include <libaddressinput/address_formatter.h> | |
| 16 | |
| 17 #include <libaddressinput/address_data.h> | |
| 18 #include <libaddressinput/address_field.h> | |
| 19 | |
| 20 #include <algorithm> | |
| 21 #include <cassert> | |
| 22 #include <cstddef> | |
| 23 #include <functional> | |
| 24 #include <string> | |
| 25 #include <vector> | |
| 26 | |
| 27 #include "language.h" | |
| 28 #include "region_data_constants.h" | |
| 29 #include "rule.h" | |
| 30 #include "util/cctype_tolower_equal.h" | |
| 31 | |
| 32 namespace i18n { | |
| 33 namespace addressinput { | |
| 34 | |
| 35 namespace { | |
| 36 | |
| 37 const char kCommaSeparator[] = ", "; | |
| 38 const char kSpaceSeparator[] = " "; | |
| 39 const char kArabicCommaSeparator[] = "\xD8\x8C" " "; /* "، " */ | |
| 40 | |
| 41 const char* kLanguagesThatUseSpace[] = { | |
| 42 "th", | |
| 43 "ko" | |
| 44 }; | |
| 45 | |
| 46 const char* kLanguagesThatHaveNoSeparator[] = { | |
| 47 "ja", | |
| 48 "zh" // All Chinese variants. | |
| 49 }; | |
| 50 | |
| 51 // This data is based on CLDR, for languages that are in official use in some | |
| 52 // country, where Arabic is the most likely script tag. | |
| 53 // TODO: Consider supporting variants such as tr-Arab by detecting the script | |
| 54 // code. | |
| 55 const char* kLanguagesThatUseAnArabicComma[] = { | |
| 56 "ar", | |
| 57 "az", | |
| 58 "fa", | |
| 59 "kk", | |
| 60 "ku", | |
| 61 "ky", | |
| 62 "ps", | |
| 63 "tg", | |
| 64 "tk", | |
| 65 "ur", | |
| 66 "uz" | |
| 67 }; | |
| 68 | |
| 69 std::string GetLineSeparatorForLanguage(const std::string& language_tag) { | |
| 70 Language address_language(language_tag); | |
| 71 | |
| 72 // First deal with explicit script tags. | |
| 73 if (address_language.has_latin_script) { | |
| 74 return kCommaSeparator; | |
| 75 } | |
| 76 | |
| 77 // Now guess something appropriate based on the base language. | |
| 78 const std::string& base_language = address_language.base; | |
| 79 if (std::find_if(kLanguagesThatUseSpace, | |
| 80 kLanguagesThatUseSpace + arraysize(kLanguagesThatUseSpace), | |
| 81 std::bind2nd(EqualToTolowerString(), base_language)) != | |
| 82 kLanguagesThatUseSpace + arraysize(kLanguagesThatUseSpace)) { | |
| 83 return kSpaceSeparator; | |
| 84 } else if (std::find_if( | |
| 85 kLanguagesThatHaveNoSeparator, | |
| 86 kLanguagesThatHaveNoSeparator + | |
| 87 arraysize(kLanguagesThatHaveNoSeparator), | |
| 88 std::bind2nd(EqualToTolowerString(), base_language)) != | |
| 89 kLanguagesThatHaveNoSeparator + | |
| 90 arraysize(kLanguagesThatHaveNoSeparator)) { | |
| 91 return ""; | |
| 92 } else if (std::find_if( | |
| 93 kLanguagesThatUseAnArabicComma, | |
| 94 kLanguagesThatUseAnArabicComma + | |
| 95 arraysize(kLanguagesThatUseAnArabicComma), | |
| 96 std::bind2nd(EqualToTolowerString(), base_language)) != | |
| 97 kLanguagesThatUseAnArabicComma + | |
| 98 arraysize(kLanguagesThatUseAnArabicComma)) { | |
| 99 return kArabicCommaSeparator; | |
| 100 } | |
| 101 // Either the language is a latin-script language, or no language was | |
| 102 // specified. In the latter case we still return ", " as the most common | |
| 103 // separator in use. In countries that don't use this, e.g. Thailand, | |
| 104 // addresses are often written in latin script where this would still be | |
| 105 // appropriate, so this is a reasonable default in the absence of information. | |
| 106 return kCommaSeparator; | |
| 107 } | |
| 108 | |
| 109 void CombineLinesForLanguage( | |
| 110 const std::vector<std::string>& lines, const std::string& language_tag, | |
| 111 std::string *line) { | |
| 112 if (lines.size() > 0) { | |
| 113 line->assign(lines[0]); | |
| 114 } | |
| 115 std::string separator = GetLineSeparatorForLanguage(language_tag); | |
| 116 for (std::vector<std::string>::const_iterator it = lines.begin() + 1; | |
| 117 it < lines.end(); ++it) { | |
| 118 line->append(separator); | |
| 119 line->append(*it); | |
| 120 } | |
| 121 } | |
| 122 | |
| 123 } // namespace | |
| 124 | |
| 125 void GetFormattedNationalAddress( | |
| 126 const AddressData& address_data, std::vector<std::string>* lines) { | |
| 127 assert(lines != NULL); | |
| 128 lines->clear(); | |
| 129 | |
| 130 Rule rule; | |
| 131 rule.CopyFrom(Rule::GetDefault()); | |
| 132 // TODO: Eventually, we should get the best rule for this country and | |
| 133 // language, rather than just for the country. | |
| 134 rule.ParseSerializedRule(RegionDataConstants::GetRegionData( | |
| 135 address_data.region_code)); | |
| 136 | |
| 137 Language language(address_data.language_code); | |
| 138 | |
| 139 // If latinized rules are available and the |language_code| of this address is | |
| 140 // explicitly tagged as being Latin, then use the latinized formatting rules. | |
| 141 const std::vector<std::vector<FormatElement> >& format = | |
| 142 language.has_latin_script && !rule.GetLatinFormat().empty() | |
| 143 ? rule.GetLatinFormat() : rule.GetFormat(); | |
| 144 | |
| 145 lines->push_back(std::string()); | |
| 146 for (size_t i = 0; i < format.size(); ++i) { | |
| 147 if (!lines->back().empty()) { | |
| 148 lines->push_back(std::string()); | |
| 149 } | |
| 150 for (size_t j = 0; j < format[i].size(); ++j) { | |
| 151 const FormatElement& element = format[i][j]; | |
| 152 if (element.IsField()) { | |
| 153 if (element.field == STREET_ADDRESS) { | |
| 154 // The field "street address" represents the street address lines of | |
| 155 // an address, so there can be multiple values. | |
| 156 if (lines->back().empty()) { | |
| 157 lines->pop_back(); | |
| 158 } | |
| 159 lines->insert(lines->end(), | |
| 160 address_data.address_line.begin(), | |
| 161 address_data.address_line.end()); | |
| 162 } else { | |
| 163 lines->back().append(address_data.GetFieldValue(element.field)); | |
| 164 } | |
| 165 } else { | |
| 166 lines->back().append(element.literal); | |
| 167 } | |
| 168 } | |
| 169 } | |
| 170 | |
| 171 if (lines->back().empty()) { | |
| 172 lines->pop_back(); | |
| 173 } | |
| 174 } | |
| 175 | |
| 176 void GetFormattedNationalAddressLine( | |
| 177 const AddressData& address_data, std::string* line) { | |
| 178 std::vector<std::string> address_lines; | |
| 179 GetFormattedNationalAddress(address_data, &address_lines); | |
| 180 CombineLinesForLanguage(address_lines, address_data.language_code, line); | |
| 181 } | |
| 182 | |
| 183 void GetStreetAddressLinesAsSingleLine( | |
| 184 const AddressData& address_data, std::string* line) { | |
| 185 CombineLinesForLanguage( | |
| 186 address_data.address_line, address_data.language_code, line); | |
| 187 } | |
| 188 | |
| 189 } // namespace addressinput | |
| 190 } // namespace i18n | |
| OLD | NEW |