我得到了一个应用程序，其中输入已从 50K 条位置记录扩展到 110 万条位置记录。这导致了严重的问题，因为整个文件以前被反序列化为单个对象。对于具有 110 万条记录的生产类文件，对象的大小为 ~1GB。由于大型对象 GC 问题，我希望将反序列化对象保持在 85K 标记以下。
我正在尝试一次解析出单个位置对象并对其进行反序列化，以便我可以控制对象的数量反序列化并反过来控制对象的大小。我正在使用 Json.Net 库来执行此操作。
下面是我作为流接收到应用程序中的 JSON 文件的示例。
{
"Locations": [{
"LocationId": "",
"ParentLocationId": "",
"DisplayFlag": "Y",
"DisplayOptions": "",
"DisplayName": "",
"Address": "",
"SecondaryAddress": "",
"City": "",
"State": "",
"PostalCode": "",
"Country": "",
"Latitude": 40.59485,
"Longitude": -73.96174,
"LatLonQuality": 99,
"BusinessLogoUrl": "",
"BusinessUrl": "",
"DisplayText": "",
"PhoneNumber": "",
"VenueGroup": 7,
"VenueType": 0,
"SubVenue": 0,
"IndoorFlag": "",
"OperatorDefined": "",
"AccessPoints": [{
"AccessPointId": "",
"MACAddress": "",
"DisplayFlag": "",
"DisplayOptions": "",
"Latitude": 40.59485,
"Longitude": -73.96174,
"Status": "Up",
"OperatorDefined": "",
"RoamingGroups": [{
"GroupName": ""
},
{
"GroupName": ""
}],
"Radios": [{
"RadioId": "",
"RadioFrequency": "",
"RadioProtocols": [{
"Protocol": ""
}],
"WifiConnections": [{
"BSSID": "",
"ServiceSets": [{
"SSID": "",
"SSID_Broadcasted": ""
}]
}]
}]
}]
},
{
"LocationId": "",
"ParentLocationId": "",
"DisplayFlag": "Y",
"DisplayOptions": "",
"DisplayName": "",
"Address": "",
"SecondaryAddress": "",
"City": "",
"State": "",
"PostalCode": "",
"Country": "",
"Latitude": 40.59485,
"Longitude": -73.96174,
"LatLonQuality": 99,
"BusinessLogoUrl": "",
"BusinessUrl": "",
"DisplayText": "",
"PhoneNumber": "",
"VenueGroup": 7,
"VenueType": 0,
"SubVenue": 0,
"IndoorFlag": "",
"OperatorDefined": "",
"AccessPoints": [{
"AccessPointId": "",
"MACAddress": "",
"DisplayFlag": "",
"DisplayOptions": "",
"Latitude": 40.59485,
"Longitude": -73.96174,
"Status": "Up",
"OperatorDefined": "",
"RoamingGroups": [{
"GroupName": ""
},
{
"GroupName": ""
}],
"Radios": [{
"RadioId": "",
"RadioFrequency": "",
"RadioProtocols": [{
"Protocol": ""
}],
"WifiConnections": [{
"BSSID": "",
"ServiceSets": [{
"SSID": "",
"SSID_Broadcasted": ""
}]
}]
}]
}]
}]
}
我需要能够拉出单个位置对象，以便我查看以下内容
{
"LocationId": "",
"ParentLocationId": "",
"DisplayFlag": "Y",
"DisplayOptions": "",
"DisplayName": "",
"Address": "",
"SecondaryAddress": "",
"City": "",
"State": "",
"PostalCode": "",
"Country": "",
"Latitude": 40.59485,
"Longitude": -73.96174,
"LatLonQuality": 99,
"BusinessLogoUrl": "",
"BusinessUrl": "",
"DisplayText": "",
"PhoneNumber": "",
"VenueGroup": 7,
"VenueType": 0,
"SubVenue": 0,
"IndoorFlag": "",
"OperatorDefined": "",
"AccessPoints": [{
"AccessPointId": "",
"MACAddress": "",
"DisplayFlag": "",
"DisplayOptions": "",
"Latitude": 40.59485,
"Longitude": -73.96174,
"Status": "Up",
"OperatorDefined": "",
"RoamingGroups": [{
"GroupName": ""
},
{
"GroupName": ""
}],
"Radios": [{
"RadioId": "",
"RadioFrequency": "",
"RadioProtocols": [{
"Protocol": ""
}],
"WifiConnections": [{
"BSSID": "",
"ServiceSets": [{
"SSID": "",
"SSID_Broadcasted": ""
}]
}]
}]
}]
}
我正在尝试使用 Json.NET JsonTextReader 来完成此操作，但是我无法让读取器在其缓冲区中包含整个位置，因为流中记录的大小最初读取器将下降到"RadioProtocols"，这是在对象的中间，当流到达对象的末尾时， 读取器已丢弃对象的开头。
我用来尝试使此功能工作的代码是
var ser = new JsonSerializer();
using (var reader = new JsonTextReader(new StreamReader(stream)))
{
reader.SupportMultipleContent = true;
while (reader.Read())
{
if (reader.TokenType == JsonToken.StartObject && reader.Depth == 2)
{
do
{
reader.Read();
} while (reader.TokenType != JsonToken.EndObject && reader.Depth == 2);
var singleLocation = ser.Deserialize<Locations>(reader);
}
}
}
任何关于这方面的信息或替代方法将不胜感激。作为旁注，我们的客户发送信息的方式目前无法改变。
当读取器位于要反序列化的对象的开头（在本例中是 Locations 数组中的一个条目）时，您只需调用 ser.Deserialize<T>(reader) 它就会起作用，在该级别前进到对象的末尾，而不是更进一步。 因此，以下内容应遍历文件中的Location对象，并分别加载每个对象：
public static IEnumerable<T> DeserializeNestedItems<T>(TextReader textReader)
{
var ser = new JsonSerializer();
using (var reader = new JsonTextReader(textReader))
{
reader.SupportMultipleContent = true;
while (reader.Read())
{
if (reader.TokenType == JsonToken.StartObject && reader.Depth == 2)
{
var item = ser.Deserialize<T>(reader);
yield return item;
}
}
}
}
以及使用测试字符串的使用示例：
Debug.Assert(DeserializeNestedItems<Location>(new StringReader(json)).Count() == 2); // No assert.
var list = DeserializeNestedItems<Location>(new StringReader(json)).SelectMany(l => l.AccessPoints).Select(a => new { a.Latitude, a.Longitude }).ToList();
Debug.WriteLine(JsonConvert.SerializeObject(list, Formatting.Indented));
哪些输出：
[ { "Latitude": 40.59485, "Longitude": -73.96174 }, { "Latitude": 40.59485, "Longitude": -73.96174 } ]
注意 - Location类来自将 JSON 发布到 http://json2csharp.com/。
感谢您的所有帮助，我已经设法让它做我想做的事情，即反序列化单个位置对象。
如果将项转换为 JObject，它将读取完整对象并对其进行反序列化，可以循环以获取解决方案。
这是确定
的代码while (reader.Read())
{
if (reader.TokenType == JsonToken.StartObject && reader.Depth == 2)
{
location = JObject.Load(reader).ToObject<Location>();
var lv = new LocationValidator(location, FootprintInfo.OperatorId, FootprintInfo.RoamingGroups, true);
var vr = lv.IsValid();
if (vr.Successful)
{
yield return location;
}
else
{
errors.Add(new Error(elNumber, location.LocationId, vr.Error.Field, vr.Error.Detail));
if (errors.Count >= maxErrors)
{
yield break;
}
}
++elNumber;
}
}