[NAE-2261] SEARCH Node - fetch cases from mongo#385
[NAE-2261] SEARCH Node - fetch cases from mongo#385Kovy95 wants to merge 7 commits intorelease/7.0.0-rev10from
Conversation
- add AuthPrincipalDto to object library - remove immediate data from elasticCase and add NodeInfo - rework of elastic Datafields to remove dependency to TextField
- remove code from 2251 - when the search node fetches cases from mongo, its not nessessery anymore to store translations of value into elastic
WalkthroughMap/value translation handling changed: map field entry values now use Collection of translations instead of I18nString; several field classes switch inheritance from TextField to DataField; ElasticCase lost Changes
Sequence Diagram(s)mermaid Estimated code review effort🎯 3 (Moderate) | ⏱️ ~30 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
coderabbitai
bot
added
improvement
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/StringCollectionField.java (1)
10-17: Consider using private access modifier forcollectionValuefield.The field
collectionValueon line 12 is declared aspublic, which breaks encapsulation. Since the class uses Lombok@Data, getters and setters are already generated. Consider making itprivatefor consistency with typical Java bean conventions.Also note: the constructor stores
valuesboth in the parent class viasuper(values)(which setsfulltextValue) and incollectionValue. If this dual storage is intentional for different Elasticsearch query patterns (similar to thecaseValue/fulltextValuepattern in CaseField), this is fine. Otherwise, consider whether both are necessary.- public String[] collectionValue; + private String[] collectionValue;
♻️ Duplicate comments (1)
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java (1)
136-136: Same null handling concern applies here.Similar to the multichoice map field transformation, if
selectedKeyis not present in theoptionsmap, the result will be an entry with an empty collection of translations.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: ASSERTIVE
Plan: Pro
📒 Files selected for processing (8)
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java(2 hunks)nae-object-library/src/main/java/com/netgrif/application/engine/objects/auth/dto/AuthPrincipalDto.java(1 hunks)nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java(1 hunks)nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java(1 hunks)nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.java(1 hunks)nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/NodeInfo.java(1 hunks)nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/StringCollectionField.java(1 hunks)nae-spring-core-adapter/src/main/java/com/netgrif/application/engine/adapter/spring/elastic/domain/MapField.java(1 hunks)
🧰 Additional context used
🧠 Learnings (6)
📓 Common learnings
Learnt from: renczesstefan
Repo: netgrif/application-engine PR: 339
File: application-engine/src/test/groovy/com/netgrif/application/engine/filters/FilterImportExportTest.groovy:341-341
Timestamp: 2025-08-19T20:07:15.621Z
Learning: In the Elasticsearch migration, the stringId property was removed from ElasticCase and ElasticTask, with the id property now containing the MongoDB case/task object ID directly. This consolidation eliminates redundancy and simplifies the data model.
📚 Learning: 2025-08-19T20:07:15.621Z
Learnt from: renczesstefan
Repo: netgrif/application-engine PR: 339
File: application-engine/src/test/groovy/com/netgrif/application/engine/filters/FilterImportExportTest.groovy:341-341
Timestamp: 2025-08-19T20:07:15.621Z
Learning: In the Elasticsearch migration, the stringId property was removed from ElasticCase and ElasticTask, with the id property now containing the MongoDB case/task object ID directly. This consolidation eliminates redundancy and simplifies the data model.
Applied to files:
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java
📚 Learning: 2025-08-19T20:13:40.087Z
Learnt from: renczesstefan
Repo: netgrif/application-engine PR: 339
File: nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/CaseField.java:16-16
Timestamp: 2025-08-19T20:13:40.087Z
Learning: In CaseField.java, fulltextValue is mapped as a keyword field type in Elasticsearch (for exact matches, filtering, aggregations), while the separate caseValue field serves different Elasticsearch query requirements, allowing the system to support multiple query patterns on the same data through different field mappings.
Applied to files:
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/StringCollectionField.javanae-spring-core-adapter/src/main/java/com/netgrif/application/engine/adapter/spring/elastic/domain/MapField.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java
📚 Learning: 2025-08-19T20:07:43.748Z
Learnt from: renczesstefan
Repo: netgrif/application-engine PR: 339
File: nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/CaseField.java:16-16
Timestamp: 2025-08-19T20:07:43.748Z
Learning: In CaseField.java, the separate caseValue field (List<String>) is intentionally maintained alongside fulltextValue for specific Elasticsearch query requirements, rather than being derived on-the-fly from fulltextValue.
Applied to files:
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/StringCollectionField.javanae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java
📚 Learning: 2025-06-23T13:30:13.096Z
Learnt from: renczesstefan
Repo: netgrif/application-engine PR: 318
File: nae-object-library/src/main/java/com/netgrif/application/engine/objects/workflow/domain/menu/MenuItemConstants.java:60-62
Timestamp: 2025-06-23T13:30:13.096Z
Learning: In MenuItemConstants enum in nae-object-library/src/main/java/com/netgrif/application/engine/objects/workflow/domain/menu/MenuItemConstants.java, the field `attributeId` will be renamed to `value` to make it more generic and appropriate for both dataset attribute identifiers and technical constants like PATH_SEPARATOR.
Applied to files:
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java
📚 Learning: 2025-12-02T14:35:05.305Z
Learnt from: renczesstefan
Repo: netgrif/application-engine PR: 373
File: nae-spring-core-adapter/src/main/java/com/netgrif/application/engine/adapter/spring/actions/ActionApi.java:98-98
Timestamp: 2025-12-02T14:35:05.305Z
Learning: In ActionApi, the deleteCase method intentionally does not include an AuthPrincipalDto parameter because it does not require author information, unlike createCase which needs the author via authPrincipalDto.
Applied to files:
nae-object-library/src/main/java/com/netgrif/application/engine/objects/auth/dto/AuthPrincipalDto.java
🧬 Code graph analysis (2)
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java (1)
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nStringUtils.java (1)
I18nStringUtils(8-18)
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/NodeInfo.java (1)
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java (1)
Data(18-126)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: task-list-completed
- GitHub Check: task-list-completed
- GitHub Check: Build
🔇 Additional comments (10)
nae-object-library/src/main/java/com/netgrif/application/engine/objects/auth/dto/AuthPrincipalDto.java (1)
11-24: LGTM!The DTO structure is well-designed. Excluding
sessionIdfromtoStringandequals/hashCodeis a good practice—it prevents accidental logging of sensitive session data and ensures object equality is based on identity attributes rather than transient session state.nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java (2)
14-24: LGTM on the DataField migration.The inheritance change to
DataFieldand constructor update align with the broader refactoring in this PR.
26-32: Verify single-value behavior is intentional.The
getValue()method only usesfulltextValue[0]when constructing theI18nString. IffulltextValuecan contain multiple elements (sincevaluesis aSetpassed to the constructor), confirm this single-value extraction is the intended behavior.nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java (3)
82-107: LGTM on constructor logic.The constructor properly initializes all case-related fields from the source
Caseobject, with appropriate null-safety checks for tasks and proper use of defensive copies for collections.
109-125: LGTM on update method.The update method correctly synchronizes relevant mutable fields while incrementing the version counter.
80-81: Remove the unusednodeInfofield or integrate it properly.The
nodeInfofield is declared at line 80 but is not initialized in the constructor, not updated in theupdate()method, and is never accessed anywhere in the codebase. Either remove this unused field or integrate it fully by initializing it during construction and updating it in theupdate()method.Likely an incorrect or invalid review comment.
nae-spring-core-adapter/src/main/java/com/netgrif/application/engine/adapter/spring/elastic/domain/MapField.java (1)
14-31: LGTM!The constructor signatures correctly align with the base class refactoring from I18nString to Collection. The Elasticsearch field annotations are properly applied: Text type for full-text search and Keyword type for exact matching and aggregations.
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.java (3)
12-12: Architectural change aligns with PR objectives.The change from extending
TextFieldtoDataFieldremoves the dependency on TextField as stated in the PR objectives. This is part of the broader refactoring to decouple Elasticsearch datafields from TextField.
16-29: Constructor implementation is correct.The refactored constructors properly handle the transition from I18nString to Collection:
- Single-entry constructor delegates to the list constructor
- List constructor correctly extracts keys into
keyValuearray and flattens all translation collections intofulltextValue
31-38: getValue() method provides convenient API.The new
getValue()method returns:
- A single key as String for enumeration fields
- A LinkedHashSet of keys for multichoice fields
- null for empty/null keyValue
The LinkedHashSet preserves insertion order while ensuring uniqueness, which is appropriate for multichoice selections.
| List<Map.Entry<String, Collection<String>>> values = new ArrayList<>(); | ||
| for (String key : (Set<String>) mapValues) { | ||
| I18nString selectedValue = options.get(key); | ||
| values.add(new AbstractMap.SimpleEntry<>(key, selectedValue != null ? selectedValue : new I18nString(""))); | ||
| values.add(new AbstractMap.SimpleEntry<>(key, I18nStringUtils.collectTranslations(options.get(key)))); | ||
| } |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, let's look at the file and the complete method context
cat -n application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java | sed -n '80,110p'Repository: netgrif/application-engine
Length of output: 2089
🏁 Script executed:
# Search for I18nStringUtils.collectTranslations implementation
find . -type f -name "*.java" | xargs grep -l "I18nStringUtils" | head -5Repository: netgrif/application-engine
Length of output: 292
🏁 Script executed:
# Look for the I18nStringUtils class definition
fd -type f -name "I18nStringUtils.java"Repository: netgrif/application-engine
Length of output: 240
🏁 Script executed:
# Read the I18nStringUtils file to see the collectTranslations implementation
cat -n nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nStringUtils.javaRepository: netgrif/application-engine
Length of output: 786
🏁 Script executed:
# Search for getFieldOptions implementation
rg -nA10 "getFieldOptions" application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.javaRepository: netgrif/application-engine
Length of output: 1830
🏁 Script executed:
# Search for tests related to transformMultichoiceMapField
fd -type f -name "*.java" | xargs grep -l "transformMultichoiceMapField\|ElasticCaseMappingService" | grep -i testRepository: netgrif/application-engine
Length of output: 240
🏁 Script executed:
# Search for tests of ElasticCaseMappingService
find . -type f -name "*.java" -path "*/test/*" | xargs grep -l "ElasticCaseMappingService" 2>/dev/null | head -3Repository: netgrif/application-engine
Length of output: 52
🏁 Script executed:
# Search for any validation or warnings about missing keys
rg -n "mapValues|options\.get" application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java -B2 -A2Repository: netgrif/application-engine
Length of output: 1025
🏁 Script executed:
# Check if there's any logging or warning in the surrounding code
rg -n "logger|log\.|warn|error" application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java | head -20Repository: netgrif/application-engine
Length of output: 1771
🏁 Script executed:
# Check the git history of this specific method to understand its evolution
git log --oneline -n 20 -- application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.javaRepository: netgrif/application-engine
Length of output: 150
Inconsistent error handling: missing options keys are silently converted to empty translations.
The code at line 98 does not validate that all keys from mapValues exist in the options map. While I18nStringUtils.collectTranslations(null) handles null gracefully by returning an empty list, this pattern is inconsistent with the error handling established elsewhere in this class. Other methods (e.g., lines 163, 180, 194) log errors when encountering data inconsistencies. Consider either adding validation to ensure all keys are present in the options map, or logging a warning when options.get(key) returns null to make data issues visible during debugging.
🤖 Prompt for AI Agents
In
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java
around lines 96-99, the code blindly calls options.get(key) and passes the
result to I18nStringUtils.collectTranslations, silently producing empty
translations for missing keys; change this to first check
options.containsKey(key) and if the key is missing log a warning (including the
missing key and identifying context such as the parent map or document id), then
either continue with an explicit empty translation list or handle it
consistently with the class’s error strategy (throw or collect an error),
ensuring missing keys are visible in logs rather than silently ignored.
| import lombok.Data; | ||
| import lombok.EqualsAndHashCode; | ||
| import lombok.NonNull; | ||
| import lombok.ToString; |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Remove unused import.
lombok.NonNull is imported but not used in this class.
import lombok.Data;
import lombok.EqualsAndHashCode;
-import lombok.NonNull;
import lombok.ToString;📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| import lombok.Data; | |
| import lombok.EqualsAndHashCode; | |
| import lombok.NonNull; | |
| import lombok.ToString; | |
| import lombok.Data; | |
| import lombok.EqualsAndHashCode; | |
| import lombok.ToString; |
🤖 Prompt for AI Agents
In
nae-object-library/src/main/java/com/netgrif/application/engine/objects/auth/dto/AuthPrincipalDto.java
around lines 3 to 6, the import lombok.NonNull is unused; remove that import
line and keep only the required lombok imports (Data, EqualsAndHashCode,
ToString) so there are no unused imports.
...ct-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/NodeInfo.java
Show resolved
Hide resolved
machacjozef
changed the base branch from
release/7.0.0-rev9
to
release/7.0.0-rev10
...ct-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/NodeInfo.java
Show resolved
Hide resolved
# Conflicts: # nae-object-library/src/main/java/com/netgrif/application/engine/objects/auth/dto/AuthPrincipalDto.java # nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java # nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.java # nae-spring-core-adapter/src/main/java/com/netgrif/application/engine/adapter/spring/elastic/domain/MapField.java
- add NoArgsConstructor
There was a problem hiding this comment.
Actionable comments posted: 3
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java (1)
113-135: 🧹 Nitpick | 🔵 TrivialConsider consistency: other fields handle null explicitly, but
nodeInfois completely absent.All other fields in
update()explicitly handle null cases (e.g.,taskIds = useCase.getTaskIds() == null ? new HashSet<>() : ...). ThenodeInfofield is not addressed at all.If the intent is for
nodeInfoto remain unchanged during updates, consider adding a brief comment to clarify this design decision for future maintainers:// nodeInfo intentionally not updated - represents the originating search node
🤖 Fix all issues with AI agents
In
`@nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java`:
- Around line 82-83: The nodeInfo field in class ElasticCase is declared but
never initialized or copied; update the constructor (the ElasticCase(...)
initializer that sets other fields like id, title, etc.) to initialize
this.nodeInfo from the source ElasticCase (e.g., this.nodeInfo =
source.getNodeInfo() or new NodeInfo(source.getNodeInfo()) if a defensive copy
is needed) and also modify the update(...) method to set/replace nodeInfo the
same way when copying fields from another ElasticCase (ensure you use the same
copying semantics used for other complex fields in this class to maintain
immutability/defensive copying).
In
`@nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java`:
- Around line 35-38: I18nField's getValue() currently returns only
fulltextValue[0], but the constructor accepts Set<String> inputs and populates
fulltextValue and keyValue as parallel arrays, causing a cardinality mismatch;
either enforce single-value semantics in the constructor (in I18nField's
constructor validate that fulltextValue/keyValue sets contain exactly one
element and throw an IllegalArgumentException if not) or change getValue() to
return a multi-value representation (e.g., return a collection or map of
keys->values, or a list of I18nString instances) so that each index in
fulltextValue/keyValue is preserved; update usages of getValue() accordingly to
handle the chosen representation and keep translations consistent.
In
`@nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.java`:
- Around line 21-27: In the MapField constructor the call
values.addAll(valuePairs.get(i).getValue()) can NPE if an entry's value is null;
update the constructor (MapField(List<Map.Entry<String, Collection<String>>>
valuePairs)) to null-safe aggregate by retrieving the entry value into a local
variable, defaulting to Collections.emptyList() (or new ArrayList<>()) when
null, then addAll that safe collection to values while still populating
keyValue[i]; ensure keyValue and values sizing logic remains unchanged.
| private NodeInfo nodeInfo; | ||
|
|
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Find where nodeInfo is set/used
echo "=== Searching for nodeInfo usage patterns ==="
rg -n 'nodeInfo' --type=java -C2Repository: netgrif/application-engine
Length of output: 760
🏁 Script executed:
#!/bin/bash
# Find where NodeInfo is instantiated
echo "=== Searching for NodeInfo instantiation ==="
rg -n 'new NodeInfo\(' --type=java -C3Repository: netgrif/application-engine
Length of output: 114
🏁 Script executed:
#!/bin/bash
# Search for setNodeInfo method calls
echo "=== Searching for setNodeInfo calls ==="
rg -n 'setNodeInfo' --type=java -C2Repository: netgrif/application-engine
Length of output: 109
🏁 Script executed:
#!/bin/bash
# Find NodeInfo class definition
echo "=== Searching for NodeInfo class definition ==="
rg -n 'class NodeInfo|interface NodeInfo' --type=java -C3Repository: netgrif/application-engine
Length of output: 1019
🏁 Script executed:
#!/bin/bash
# Check ElasticCase for getter/setter methods related to nodeInfo
echo "=== Searching for nodeInfo getter/setter in ElasticCase ==="
rg -n 'getNodeInfo|setNodeInfo|nodeInfo' nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java -C1Repository: netgrif/application-engine
Length of output: 171
🏁 Script executed:
#!/bin/bash
# Search for any assignment to nodeInfo field
echo "=== Searching for nodeInfo field assignments ==="
rg -n 'this\.nodeInfo\s*=' --type=java -C2Repository: netgrif/application-engine
Length of output: 118
🏁 Script executed:
#!/bin/bash
# Look at the complete ElasticCase file around the nodeInfo field and constructor
echo "=== ElasticCase constructor and nodeInfo field context ==="
cat -n nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java | sed -n '78,140p'Repository: netgrif/application-engine
Length of output: 4641
Initialize nodeInfo in the constructor and update it in the update() method.
The nodeInfo field is declared (line 82) but never initialized in the constructor (lines 84-111) or updated in the update() method (lines 113-135). Unlike all other fields in this class which are explicitly initialized and copied, nodeInfo will remain null. Either this field should be initialized from the source ElasticCase like other fields, or justify why it requires different handling.
🤖 Prompt for AI Agents
In
`@nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/ElasticCase.java`
around lines 82 - 83, The nodeInfo field in class ElasticCase is declared but
never initialized or copied; update the constructor (the ElasticCase(...)
initializer that sets other fields like id, title, etc.) to initialize
this.nodeInfo from the source ElasticCase (e.g., this.nodeInfo =
source.getNodeInfo() or new NodeInfo(source.getNodeInfo()) if a defensive copy
is needed) and also modify the update(...) method to set/replace nodeInfo the
same way when copying fields from another ElasticCase (ensure you use the same
copying semantics used for other complex fields in this class to maintain
immutability/defensive copying).
There was a problem hiding this comment.
Seems like the humans are having a chat. I'll hop back into my burrow for now. If you need me again, just tag @coderabbitai in a new comment, and I'll come hopping out!
| public Object getValue() { | ||
| if (textValue != null && textValue.length > 0) { | ||
| return new I18nString(textValue[0], translations); | ||
| if (fulltextValue != null && fulltextValue.length > 0) { | ||
| return new I18nString(fulltextValue[0], translations); | ||
| } |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, let's read the I18nField.java file to see its full structure
find . -type f -name "I18nField.java" | head -5Repository: netgrif/application-engine
Length of output: 402
🏁 Script executed:
# Search for fulltextValue usage across the codebase to understand the pattern
rg -n "fulltextValue" --type java | head -30Repository: netgrif/application-engine
Length of output: 2581
🏁 Script executed:
# Let's specifically look at CaseField.java since the learning mentions it has a related pattern
find . -type f -name "CaseField.java" | head -3Repository: netgrif/application-engine
Length of output: 402
🏁 Script executed:
# Read the I18nField.java file in elastic domain
cat -n ./nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.javaRepository: netgrif/application-engine
Length of output: 1606
🏁 Script executed:
# Read the CaseField.java file to understand the separate field pattern
cat -n ./nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/CaseField.javaRepository: netgrif/application-engine
Length of output: 1133
🏁 Script executed:
# Check how I18nField is populated/instantiated
rg -n "new I18nField|I18nField(" -A 5 --type java | head -50Repository: netgrif/application-engine
Length of output: 168
🏁 Script executed:
# Fix regex syntax to search for I18nField instantiation
rg "I18nField\(" -A 3 --type java | head -50Repository: netgrif/application-engine
Length of output: 6140
🏁 Script executed:
# Find concrete implementations/subclasses of I18nField
rg "extends I18nField|class.*I18nField" --type javaRepository: netgrif/application-engine
Length of output: 783
🏁 Script executed:
# Search for tests related to I18nField
find . -type f -name "*I18nField*Test*.java" -o -name "*Test*I18nField*.java"Repository: netgrif/application-engine
Length of output: 52
🏁 Script executed:
# Check DataField to see how it handles single vs multi-value
cat -n ./nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/DataField.javaRepository: netgrif/application-engine
Length of output: 1267
🏁 Script executed:
# Check if I18nField has abstract methods that might clarify intent
cat -n ./nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.javaRepository: netgrif/application-engine
Length of output: 1606
🏁 Script executed:
# Search for concrete implementations of the elastic I18nField
rg "class.*extends.*I18nField" -A 3 --type java | grep -A 3 "elastic"Repository: netgrif/application-engine
Length of output: 685
🏁 Script executed:
# Check how I18nField is actually used in the codebase (elastic domain variant)
rg "I18nField\(.*Set" --type java -A 2 | head -20Repository: netgrif/application-engine
Length of output: 1058
🏁 Script executed:
# Look for actual tests of the elastic domain module
find ./nae-object-library -type f -name "*Test*.java" | xargs grep -l "I18nField" 2>/dev/null | head -5Repository: netgrif/application-engine
Length of output: 52
Address cardinality mismatch between constructor design and getValue() implementation.
The constructor accepts Set<String> keys and values (supporting multiple entries) and stores them in parallel arrays, but getValue() returns only fulltextValue[0]. This creates a design inconsistency: either enforce single-value semantics in the constructor or return all values. The parallel keyValue array suggests each index should correspond to a value, making the silent truncation of additional entries problematic. Consider enforcing single-value semantics explicitly (fail fast) or returning a multi-value representation like CaseField does with its separate caseValue field.
🤖 Prompt for AI Agents
In
`@nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/I18nField.java`
around lines 35 - 38, I18nField's getValue() currently returns only
fulltextValue[0], but the constructor accepts Set<String> inputs and populates
fulltextValue and keyValue as parallel arrays, causing a cardinality mismatch;
either enforce single-value semantics in the constructor (in I18nField's
constructor validate that fulltextValue/keyValue sets contain exactly one
element and throw an IllegalArgumentException if not) or change getValue() to
return a multi-value representation (e.g., return a collection or map of
keys->values, or a list of I18nString instances) so that each index in
fulltextValue/keyValue is preserved; update usages of getValue() accordingly to
handle the chosen representation and keep translations consistent.
| public MapField(List<Map.Entry<String, Collection<String>>> valuePairs) { | ||
| super(new String[0]); | ||
| this.keyValue = new String[valueTranslationPairs.size()]; | ||
| this.keyValue = new String[valuePairs.size()]; | ||
| List<String> values = new ArrayList<>(); | ||
| this.keyValueTranslations = new HashMap<>(); | ||
| for (int i = 0; i < valueTranslationPairs.size(); i++) { | ||
| this.keyValue[i] = valueTranslationPairs.get(i).getKey(); | ||
| values.addAll(I18nStringUtils.collectTranslations(valueTranslationPairs.get(i).getValue())); | ||
| this.keyValueTranslations.put(valueTranslationPairs.get(i).getKey(), valueTranslationPairs.get(i).getValue()); | ||
| for (int i = 0; i < valuePairs.size(); i++) { | ||
| keyValue[i] = valuePairs.get(i).getKey(); | ||
| values.addAll(valuePairs.get(i).getValue()); |
There was a problem hiding this comment.
Null-safe aggregation of entry values to prevent NPEs.
values.addAll(valuePairs.get(i).getValue()) will throw if any entry carries a null collection. Consider guarding or defaulting to an empty collection to keep indexing resilient.
🔧 Proposed fix
for (int i = 0; i < valuePairs.size(); i++) {
keyValue[i] = valuePairs.get(i).getKey();
- values.addAll(valuePairs.get(i).getValue());
+ Collection<String> entryValues = valuePairs.get(i).getValue();
+ if (entryValues != null) {
+ values.addAll(entryValues);
+ }
}🤖 Prompt for AI Agents
In
`@nae-object-library/src/main/java/com/netgrif/application/engine/objects/elastic/domain/MapField.java`
around lines 21 - 27, In the MapField constructor the call
values.addAll(valuePairs.get(i).getValue()) can NPE if an entry's value is null;
update the constructor (MapField(List<Map.Entry<String, Collection<String>>>
valuePairs)) to null-safe aggregate by retrieving the entry value into a local
variable, defaulting to Collections.emptyList() (or new ArrayList<>()) when
null, then addAll that safe collection to values while still populating
keyValue[i]; ensure keyValue and values sizing logic remains unchanged.
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
application-engine/src/main/java/com/netgrif/application/engine/elastic/service/ElasticCaseMappingService.java (1)
136-141:⚠️ Potential issue | 🟡 MinorSame silent null handling pattern as
transformMultichoiceMapField.If
selectedKeydoes not exist in theoptionsmap,options.get(selectedKey)returnsnullandcollectTranslationswill return an empty list without any indication of data inconsistency. This contrasts withtransformEnumerationField(line 198) which logs an error when encountering unexpected data.Consider adding validation or logging consistent with the class's error handling strategy:
🛡️ Suggested validation
protected Optional<DataField> transformEnumerationMapField (com.netgrif.application.engine.objects.workflow.domain.DataField enumMap, EnumerationMapField netField) { Map<String, I18nString> options = this.getFieldOptions(enumMap, netField); String selectedKey = (String) enumMap.getValue(); + if (!options.containsKey(selectedKey)) { + log.warn("EnumerationMapField selected key '{}' not found in options map", selectedKey); + } return Optional.of(new com.netgrif.application.engine.adapter.spring.elastic.domain.MapField(new AbstractMap.SimpleEntry<>(selectedKey, I18nStringUtils.collectTranslations(options.get(selectedKey))))); }
| private NodeInfo nodeInfo; | ||
|
|
2 participants
Description
Implements NAE-2261
Dependencies
none
Third party dependencies
Blocking Pull requests
Depends on #(373) and merging rev8 into rev9
How Has Been This Tested?
manually
Test Configuration
Checklist:
Summary by CodeRabbit
New Features
Bug Fixes
Refactor