mirror of
https://github.com/hanzoai/jube-fork.git
synced 2026-10-30 18:33:33 +00:00
* Added `Cache` flag to `EntityAnalysisRequestXPath`, updating POCOs, DTOs, and synchronisation mappings. Included migrations and updated pages and JS for new fields. * Updated the Completions Endpoint to only return values if Cache is enabled in the EntityAnalysisModelRequestXPath for EntityAnalysisModelAbstractionRule configuration. * Updated the parser to ignore fields if the parse processing type is Abstraction Rule, so to ensure that an Abstraction Rule does not compile anywhere, in the controller or syncronisation, if it trys to use a key that exists but is marked as Cache. * Created migrations for the cache flag and added indexes to cache key columns. * Implemented a new serialisation pattern for message pack payloads to reduce byte storage of names, replacing them with a `CacheIndexId` serialised as a single byte. * Implemented indexing logic for `CacheIndexId`, which increments within a transaction per `EntityAnalysisModel`. Created `CacheIndexId` values for legacy data. * Created migrations for legacy Redis cache payload data to adopt the new `CacheIndexId` format. Added a unique composite index to enforce sequencing and eliminate conflict risks. * Implemented a new LRU cache warming strategy that populates the LRU cache based on journal usage. During warming, cache entries are populated in order of most recently used journals, exiting when byte limits are reached. This replaces a full cursor scan of payload data, reducing container startup time and mitigating Redis herd-stampede risks. Each journal recall writes to a sorted set (`LruJournals`) that maintains an ordered activity list for cache population. On payload entry removal, the corresponding journal is checked and the `LruJournal` key is removed if no further data exists. Added a `SortedSetLruJournalRemove` enum for task tracking. Implemented an `IsFull` method on the local LRU cache to exit warming once full. * Updated TTL Counters to process `double` values instead of `int` to support summing of integer and float payload types, making Volume and Velocity rules available to TTL Counters and long-term state. Updated POCOs, DTOs, and synchronisation mappings, applied logic in invocation processes, and included migrations. Updated pages and JS for new fields. * Updated TTL Counters to specify date resolution for TTL Counter entries, reducing memory footprint by allowing aggregation at broader date roundings (e.g. for long-term state, a daily entry expiry is sufficient). Updated VB.NET code wrappers for the new generic. * Updated TTL Counters to support an `EnableSum` flag, which uses a `TtlCounterDataValue` field to specify the value to sum. Implemented a dropdown in the page and JS that returns only integer and float data types for selection. * Updated the efficient no-boxing dictionary to instantiate on the basis of generic type, enabling use with both `int` (message pack) and `string` (core processing and legacy payload migrations). This touched a large number of files and is the primary reason for the size of this commit. Updated the dictionary to support addition of internal values via the interface for serialisation and mapping. Updated JSON serialisers to support the generic. * Implemented invocation mapping logic for insert and recall between the indexed Redis payload and the string-keyed payload required for processing. * Bumped the message pack envelope version flag to version 2 to reflect the new payload formats (noting that all data has been migrated and version 1 no longer exists in Redis). * Updated documentation to cover `LruJournals` in the Redis section, the `Cache` field on the `EntityAnalysisModelsRequestXPath` page, and the `ResolutionInterval` and `TtlCounterDataValue` fields on the `EntityAnalysisTtlCounters` page.
326 lines
15 KiB
C#
326 lines
15 KiB
C#
/* Copyright (C) 2022-present Jube Holdings Limited.
|
|
*
|
|
* This file is part of Jube™ software.
|
|
*
|
|
* Jube™ is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License
|
|
* as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
|
|
* Jube™ is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty
|
|
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.
|
|
|
|
* You should have received a copy of the GNU Affero General Public License along with Jube™. If not,
|
|
* see <https://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
namespace Jube.Engine.EntityAnalysisModelInvoke.Extraction
|
|
{
|
|
using System;
|
|
using System.Collections.Generic;
|
|
using System.Diagnostics;
|
|
using System.IO;
|
|
using System.Text;
|
|
using Context;
|
|
using Data.Poco;
|
|
using Dictionary;
|
|
using DynamicEnvironment;
|
|
using EntityAnalysisModelManager.EntityAnalysisModel.Models.Models;
|
|
using Extensions.YourNamespace.Extensions;
|
|
using Helpers;
|
|
using log4net;
|
|
using Models.Payload.EntityAnalysisModelInstanceEntryPayload;
|
|
using Newtonsoft.Json.Linq;
|
|
using EntityAnalysisModel=EntityAnalysisModelManager.EntityAnalysisModel.EntityAnalysisModel;
|
|
|
|
public class EntityAnalysisModelJsonExtractor(
|
|
EntityAnalysisModel entityAnalysisModel,
|
|
Dictionary<int, EntityAnalysisModel> availableModels,
|
|
DynamicEnvironment environment,
|
|
ILog log)
|
|
{
|
|
public Context CreateContext(
|
|
MemoryStream inputStream)
|
|
{
|
|
var stopwatch = new Stopwatch();
|
|
stopwatch.Start();
|
|
|
|
var entityAnalysisModelInstanceEntryPayload = EntityAnalysisModelInstanceEntryPayloadHelpers.Create(entityAnalysisModel);
|
|
entityAnalysisModelInstanceEntryPayload.Payload = new DictionaryNoBoxing<string>(entityAnalysisModel.References.PayloadInitialSize);
|
|
var reportDatabaseValues = new List<ArchiveKey>();
|
|
|
|
var json = ParseJson(inputStream, entityAnalysisModel, entityAnalysisModelInstanceEntryPayload);
|
|
|
|
var (entryId, referenceDate) = ExtractEntryAndReferenceDate(json, entityAnalysisModel, entityAnalysisModelInstanceEntryPayload.Payload);
|
|
|
|
entityAnalysisModelInstanceEntryPayload.EntityInstanceEntryId = entryId;
|
|
entityAnalysisModelInstanceEntryPayload.ReferenceDate = referenceDate;
|
|
|
|
ProcessRequestXPaths(json, entityAnalysisModel, entityAnalysisModelInstanceEntryPayload, entityAnalysisModelInstanceEntryPayload.Payload, reportDatabaseValues, false, log);
|
|
|
|
return new Context
|
|
{
|
|
StartBytesUsed = GC.GetAllocatedBytesForCurrentThread(),
|
|
EntityAnalysisModel = entityAnalysisModel,
|
|
AvailableEntityAnalysisModels = availableModels,
|
|
EntityAnalysisModelInstanceEntryPayload = entityAnalysisModelInstanceEntryPayload,
|
|
Stopwatch = stopwatch,
|
|
Log = log,
|
|
Random = new Random(Environment.TickCount ^ Guid.NewGuid().GetHashCode()),
|
|
Environment = environment,
|
|
Async = false
|
|
};
|
|
}
|
|
|
|
private JObject ParseJson(MemoryStream inputStream, EntityAnalysisModel model,
|
|
EntityAnalysisModelInstanceEntryPayload payload)
|
|
{
|
|
if (inputStream.Length == 0)
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {payload.EntityAnalysisModelInstanceEntryGuid} model id is {model.Instance.Id} has zero content length.");
|
|
return null;
|
|
}
|
|
|
|
var json = JObject.Parse(Encoding.UTF8.GetString(inputStream.ToArray()));
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {payload.EntityAnalysisModelInstanceEntryGuid} model id is {model.Instance.Id} JSON parsed successfully.");
|
|
return json;
|
|
}
|
|
|
|
private (string entryId, DateTime referenceDate) ExtractEntryAndReferenceDate(
|
|
JObject json,
|
|
EntityAnalysisModel model,
|
|
DictionaryNoBoxing<string> payload)
|
|
{
|
|
var modelEntryValue = "";
|
|
var referenceDateValue = DateTime.Now;
|
|
JToken jToken;
|
|
|
|
try
|
|
{
|
|
jToken = json?.SelectToken(model.References.EntryXPath);
|
|
if (jToken != null)
|
|
{
|
|
modelEntryValue = jToken.ToString();
|
|
}
|
|
|
|
log.Info($"Json to Context Extractor: Entity {model.Instance.Id}: extracted entry via {model.References.EntryXPath} value {modelEntryValue}");
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
log.Error($"Json to Context Extractor: Could not extract entry path {model.References.EntryXPath}: {ex.Message}");
|
|
}
|
|
|
|
try
|
|
{
|
|
switch (model.References.ReferenceDatePayloadLocationTypeId)
|
|
{
|
|
case 3:
|
|
referenceDateValue = DateTime.Now;
|
|
break;
|
|
|
|
default:
|
|
jToken = json?.SelectToken(model.References.ReferenceDateXpath);
|
|
if (jToken is { Type: JTokenType.Date })
|
|
{
|
|
referenceDateValue = Convert.ToDateTime(jToken);
|
|
}
|
|
else if (jToken != null && !DateTime.TryParse(jToken.ToString(), out referenceDateValue))
|
|
{
|
|
referenceDateValue = DateTime.Now;
|
|
}
|
|
break;
|
|
}
|
|
|
|
log.Info($"Json to Context Extractor: Entity {model.Instance.Id}: extracted reference date {referenceDateValue}");
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
log.Error($"Json to Context Extractor: Could not extract reference date: {ex.Message}");
|
|
}
|
|
|
|
payload.TryAdd(model.References.ReferenceDateName, referenceDateValue);
|
|
payload.TryAdd(model.References.EntryName, modelEntryValue);
|
|
|
|
return (modelEntryValue, referenceDateValue);
|
|
}
|
|
|
|
private static void ProcessRequestXPaths(
|
|
JObject json,
|
|
EntityAnalysisModel entityAnalysisModel,
|
|
EntityAnalysisModelInstanceEntryPayload entityInstanceEntryPayloadStore,
|
|
DictionaryNoBoxing<string> payload,
|
|
List<ArchiveKey> reportDatabaseValues,
|
|
bool isReprocess,
|
|
ILog log)
|
|
{
|
|
if (entityAnalysisModel.Collections?.EntityAnalysisModelRequestXPaths == null)
|
|
{
|
|
return;
|
|
}
|
|
|
|
if (log.IsInfoEnabled)
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {entityInstanceEntryPayloadStore.EntityAnalysisModelInstanceEntryGuid} model id {entityAnalysisModel.Instance.Id} beginning request XPath extraction.");
|
|
}
|
|
|
|
foreach (var xPath in entityAnalysisModel.Collections.EntityAnalysisModelRequestXPaths)
|
|
{
|
|
try
|
|
{
|
|
if (payload.ContainsKey(xPath.Name))
|
|
{
|
|
if (log.IsInfoEnabled)
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {entityInstanceEntryPayloadStore.EntityAnalysisModelInstanceEntryGuid} duplicate key {xPath.Name} detected, skipping extraction.");
|
|
}
|
|
continue;
|
|
}
|
|
|
|
if (log.IsInfoEnabled)
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {entityInstanceEntryPayloadStore.EntityAnalysisModelInstanceEntryGuid} evaluating {xPath.Name} with path {xPath.XPath}.");
|
|
}
|
|
|
|
string value;
|
|
var defaultFallback = false;
|
|
|
|
try
|
|
{
|
|
value = json.SelectToken(xPath.XPath)?.ToString();
|
|
if (value == null)
|
|
{
|
|
value = xPath.DefaultValue;
|
|
defaultFallback = true;
|
|
}
|
|
}
|
|
catch (Exception ex) when (ex is not OperationCanceledException)
|
|
{
|
|
value = xPath.DefaultValue;
|
|
defaultFallback = true;
|
|
|
|
if (log.IsInfoEnabled)
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {entityInstanceEntryPayloadStore.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} failed: {ex.Message}. Using default {xPath.DefaultValue}.");
|
|
}
|
|
}
|
|
|
|
if (value == null)
|
|
{
|
|
continue;
|
|
}
|
|
|
|
ProcessTypedInsertion(entityInstanceEntryPayloadStore,
|
|
xPath,
|
|
value,
|
|
defaultFallback,
|
|
payload,
|
|
reportDatabaseValues,
|
|
isReprocess,
|
|
log);
|
|
}
|
|
catch (Exception ex) when (ex is not OperationCanceledException)
|
|
{
|
|
log.Error($"Json to Context Extractor: GUID payload {entityInstanceEntryPayloadStore.EntityAnalysisModelInstanceEntryGuid} unhandled error processing {xPath.Name}: {ex}");
|
|
}
|
|
}
|
|
}
|
|
|
|
private static void ProcessTypedInsertion(EntityAnalysisModelInstanceEntryPayload entityAnalysisModelInstanceEntryPayload,
|
|
EntityAnalysisModelRequestXPath xPath,
|
|
string value,
|
|
bool defaultFallback,
|
|
DictionaryNoBoxing<string> payload,
|
|
List<ArchiveKey> reportDatabaseValues,
|
|
bool isReprocess,
|
|
ILog log)
|
|
{
|
|
try
|
|
{
|
|
switch (xPath.DataTypeId)
|
|
{
|
|
case 1:
|
|
payload.TryAdd(xPath.Name, value);
|
|
reportDatabaseValues.AddArchiveKey(xPath, entityAnalysisModelInstanceEntryPayload, value, isReprocess: isReprocess);
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as string {(defaultFallback ? "is default" : String.Empty)}.");
|
|
|
|
break;
|
|
case 2:
|
|
if (Int32.TryParse(value, out var intVal))
|
|
{
|
|
payload.TryAdd(xPath.Name, intVal);
|
|
reportDatabaseValues.AddArchiveKey(xPath, entityAnalysisModelInstanceEntryPayload, valueInt: Int32.Parse(value), isReprocess: isReprocess);
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as integer {(defaultFallback ? "is default" : String.Empty)}.");
|
|
}
|
|
else
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as null integer {(defaultFallback ? "is default" : String.Empty)}.");
|
|
}
|
|
|
|
break;
|
|
case 4:
|
|
DateTime dateValue;
|
|
if (defaultFallback && Int32.TryParse(xPath.DefaultValue, out var daysBack))
|
|
{
|
|
dateValue = DateTime.Now.AddDays(-daysBack);
|
|
}
|
|
else if (!DateTime.TryParse(value, out dateValue))
|
|
{
|
|
dateValue = DateTime.Now;
|
|
}
|
|
|
|
payload.TryAdd(xPath.Name, dateValue);
|
|
reportDatabaseValues.AddArchiveKey(xPath, entityAnalysisModelInstanceEntryPayload, valueDate: dateValue, isReprocess: isReprocess);
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as datetime {(defaultFallback ? "is default" : String.Empty)}.");
|
|
|
|
break;
|
|
case 5:
|
|
var boolVal = value.Equals("true", StringComparison.OrdinalIgnoreCase) || value == "1";
|
|
payload.TryAdd(xPath.Name, boolVal);
|
|
reportDatabaseValues.AddArchiveKey(xPath, entityAnalysisModelInstanceEntryPayload, valueBool: boolVal, isReprocess: isReprocess);
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as boolean {(defaultFallback ? "is default" : String.Empty)}.");
|
|
|
|
break;
|
|
case 6:
|
|
case 7:
|
|
case 3:
|
|
if (Double.TryParse(value, out var dblVal))
|
|
{
|
|
payload.TryAdd(xPath.Name, dblVal);
|
|
reportDatabaseValues.AddArchiveKey(xPath, entityAnalysisModelInstanceEntryPayload, valueFloat: Double.Parse(value), isReprocess: isReprocess);
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as double {(defaultFallback ? "is default" : String.Empty)}.");
|
|
}
|
|
else
|
|
{
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as null double {(defaultFallback ? "is default" : String.Empty)}.");
|
|
}
|
|
break;
|
|
|
|
default:
|
|
payload.TryAdd(xPath.Name, value);
|
|
reportDatabaseValues.AddArchiveKey(xPath, entityAnalysisModelInstanceEntryPayload, value, isReprocess: isReprocess);
|
|
|
|
log.Info($"Json to Context Extractor: GUID payload {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} XPath {xPath.XPath} value {value} as string {(defaultFallback ? "is default" : String.Empty)}.");
|
|
|
|
break;
|
|
}
|
|
|
|
if (log.IsInfoEnabled)
|
|
{
|
|
log.Info($"Json to Context Extractor: {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} processed field {xPath.Name} of type {xPath.DataTypeId} with value {value}");
|
|
}
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
if (log.IsInfoEnabled)
|
|
{
|
|
log.Info($"Json to Context Extractor: {entityAnalysisModelInstanceEntryPayload.EntityAnalysisModelInstanceEntryGuid} error parsing {xPath.Name}: {ex.Message}. Defaulting to string insert.");
|
|
}
|
|
payload.TryAdd(xPath.Name, value);
|
|
}
|
|
}
|
|
}
|
|
}
|