[rac] Parse postal code formats and required fields in libaddressinput.

third_party/libaddressinput/chromium/cpp/src/rule.cc

 // Copyright (C) 2013 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.
 
 #include "rule.h"
 
 #include <libaddressinput/address_field.h>
 #include <libaddressinput/util/scoped_ptr.h>
 
+#include <cassert>
+#include <cstddef>
 #include <map>
 #include <string>
 #include <utility>
+#include <vector>
 
-#include "address_field_util.h"
 #include "grit.h"
 #include "messages.h"
 #include "util/json.h"
 #include "util/string_split.h"
 
 namespace i18n {
 namespace addressinput {
 
 namespace {
 
 typedef std::map<std::string, int> NameMessageIdMap;
 
 const char kAdminAreaNameTypeKey[] = "state_name_type";
 const char kFormatKey[] = "fmt";
 const char kLanguageKey[] = "lang";
 const char kLanguagesKey[] = "languages";
+const char kPostalCodeFormatKey[] = "zip";
 const char kPostalCodeNameTypeKey[] = "zip_name_type";
+const char kRequiredKey[] = "require";
 const char kSubKeysKey[] = "sub_keys";
 
 // Used as a separator in a list of items. For example, the list of supported
 // languages can be "de~fr~it".
 const char kSeparator = '~';
 
 NameMessageIdMap InitAdminAreaMessageIds() {
   NameMessageIdMap message_ids;
   message_ids.insert(std::make_pair(
       "area", IDS_LIBADDRESSINPUT_I18N_AREA));
@@ skipping 39 matching lines @@
       InitPostalCodeMessageIds());
   return kPostalCodeMessageIds;
 }
 
 int GetMessageIdFromName(const std::string& name,
                          const NameMessageIdMap& message_ids) {
   NameMessageIdMap::const_iterator it = message_ids.find(name);
   return it != message_ids.end() ? it->second : INVALID_MESSAGE_ID;
 }
 
+std::map<char, AddressField> InitFields() {
+  std::map<char, AddressField> fields;
+  fields.insert(std::make_pair('R', COUNTRY));
+  fields.insert(std::make_pair('S', ADMIN_AREA));
+  fields.insert(std::make_pair('C', LOCALITY));
+  fields.insert(std::make_pair('D', DEPENDENT_LOCALITY));
+  fields.insert(std::make_pair('x', SORTING_CODE));
+  fields.insert(std::make_pair('Z', POSTAL_CODE));
+  fields.insert(std::make_pair('A', STREET_ADDRESS));
+  fields.insert(std::make_pair('O', ORGANIZATION));
+  fields.insert(std::make_pair('N', RECIPIENT));
+  return fields;
+}
+
+const std::map<char, AddressField>& GetFields() {
+  static const std::map<char, AddressField> kFields(InitFields());

[Evan Stade, 2013/12/19 23:00:04]

no static non-PODs allowed

use switch/case for this.

[please use gerrit instead, 2013/12/20 00:37:43]

Switch/case does not work for strings. Changed to if-else.

+  return kFields;
+}
+
+bool IsTokenPrefix(char c) {
+  return c == '%';
+}
+
+bool IsNewlineToken(char c) {
+  return c == 'n';
+}
+
+bool IsToken(char c) {
+  return GetFields().find(c) != GetFields().end();
+}
+
+AddressField ParseToken(char c) {
+  std::map<char, AddressField>::const_iterator it = GetFields().find(c);
+  assert(it != GetFields().end());
+  return it->second;
+}
+
+// Clears |fields|, parses |format|, and adds the format address fields to
+// |fields|. For example, parses "%S%C%n%D%X" into {{ADMIN_AREA, LOCALITY},
+// {DEPENDENT_LOCALITY, SORTING_CODE}}.
+void ParseAddressFieldsFormat(const std::string& format,
+                              std::vector<std::vector<AddressField> >* fields) {
+  assert(fields != NULL);
+  fields->clear();
+  bool begin_newline = true;
+  for (std::string::const_iterator current = format.begin(),
+                                   next = format.begin() + 1;

[Evan Stade, 2013/12/19 23:00:04]

splitstring on % makes this shorter I think?

[please use gerrit instead, 2013/12/20 00:37:43]

Good guess! I tried your suggestion, but the result was -8 lines removed and +8
lines added. No net gain. Therefore, I've decided to keep the algorithm as-is.

+       current != format.end() && next != format.end();
+       ++current, ++next) {
+    if (!IsTokenPrefix(*current)) {
+      continue;
+    }
+    if (IsToken(*next)) {
+      if (begin_newline) {
+        fields->push_back(std::vector<AddressField>());
+        begin_newline = false;
+      }
+      fields->back().push_back(ParseToken(*next));
+    } else if (IsNewlineToken(*next)) {
+      begin_newline = true;
+    }
+  }
+}
+
+// Clears |fields|, parses |required|, and adds the required fields to |fields|.
+// For example, parses "SCDX" into {ADMIN_AREA, LOCALITY, DEPENDENT_LOCALITY,
+// SORTING_CODE}.
+void ParseAddressFieldsRequired(const std::string& required,
+                                std::vector<AddressField>* fields) {
+  assert(fields != NULL);
+  fields->clear();
+  for (std::string::const_iterator token = required.begin();
+       token != required.end(); ++token) {
+    if (IsToken(*token)) {
+      fields->push_back(ParseToken(*token));
+    }
+  }
+}
+
 }  // namespace
 
 Rule::Rule()
     : format_(),
+      required_(),
       sub_keys_(),
       languages_(),
       language_(),
+      postal_code_format_(),
       admin_area_name_message_id_(INVALID_MESSAGE_ID),
       postal_code_name_message_id_(INVALID_MESSAGE_ID) {}
 
 Rule::~Rule() {}
 
 void Rule::CopyFrom(const Rule& rule) {
   format_ = rule.format_;
+  required_ = rule.required_;
   sub_keys_ = rule.sub_keys_;
   languages_ = rule.languages_;
   language_ = rule.language_;
+  postal_code_format_ = rule.postal_code_format_;
   admin_area_name_message_id_ = rule.admin_area_name_message_id_;
   postal_code_name_message_id_ = rule.postal_code_name_message_id_;
 }
 
 bool Rule::ParseSerializedRule(const std::string& serialized_rule) {
   scoped_ptr<Json> json(Json::Build());
   if (!json->ParseObject(serialized_rule)) {
     return false;
   }
 
   if (json->HasStringValueForKey(kFormatKey)) {
     ParseAddressFieldsFormat(json->GetStringValueForKey(kFormatKey), &format_);
   }
 
+  if (json->HasStringValueForKey(kRequiredKey)) {
+    ParseAddressFieldsRequired(
+        json->GetStringValueForKey(kRequiredKey), &required_);
+  }
+
   if (json->HasStringValueForKey(kSubKeysKey)) {
     SplitString(
         json->GetStringValueForKey(kSubKeysKey), kSeparator, &sub_keys_);
   }
 
   if (json->HasStringValueForKey(kLanguagesKey)) {
     SplitString(
         json->GetStringValueForKey(kLanguagesKey), kSeparator, &languages_);
   }
 
   if (json->HasStringValueForKey(kLanguageKey)) {
     language_ = json->GetStringValueForKey(kLanguageKey);
   }
 
+  if (json->HasStringValueForKey(kPostalCodeFormatKey)) {
+    postal_code_format_ = json->GetStringValueForKey(kPostalCodeFormatKey);
+  }
+
   if (json->HasStringValueForKey(kAdminAreaNameTypeKey)) {
     admin_area_name_message_id_ =
         GetMessageIdFromName(json->GetStringValueForKey(kAdminAreaNameTypeKey),
                              GetAdminAreaMessageIds());
   }
 
   if (json->HasStringValueForKey(kPostalCodeNameTypeKey)) {
     postal_code_name_message_id_ =
         GetMessageIdFromName(json->GetStringValueForKey(kPostalCodeNameTypeKey),
                              GetPostalCodeMessageIds());
   }
 
   return true;
 }
 
 }  // namespace addressinput
 }  // namespace i18n