Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: ZModel generator support JSON Type #1965

Merged
merged 3 commits into from
Jan 17, 2025
Merged

fix: ZModel generator support JSON Type #1965

merged 3 commits into from
Jan 17, 2025

Conversation

jiashengguo
Copy link
Member

No description provided.

Copy link
Contributor

coderabbitai bot commented Jan 16, 2025

📝 Walkthrough

Walkthrough

The pull request introduces modifications to the schema and code generation functionalities. In the schema file, a new Image model and a Metadata type are added, while existing models are reformatted for improved readability. Concurrently, the zmodel-code-generator.ts file is updated with new methods for generating type definitions and handling type fields, enhancing its capabilities for source code generation from the abstract syntax tree (AST).

Changes

File Change Summary
packages/schema/tests/schema/all-features.zmodel - Added new Image model with id and metadata fields
- Introduced Metadata type with width, height, and format fields
- Reformatted property alignments for existing models (Space, SpaceUser, User, List, Todo)
packages/sdk/src/zmodel-code-generator.ts - Added _generateTypeDef() method for type definition generation
- Added _generateTypeDefField() method for type field generation
- Updated fieldType() method signature to support multiple type inputs
- Introduced TypeDef and TypeDefField types
packages/ide/jetbrains/build.gradle.kts - Updated version from 2.11.3 to 2.11.4

Sequence Diagram

sequenceDiagram
    participant CodeGenerator
    participant AST
    participant TypeDef
    participant TypeDefField

    CodeGenerator->>AST: Parse type definition
    AST->>TypeDef: Extract type information
    TypeDef->>TypeDefField: Process individual fields
    CodeGenerator->>TypeDef: Generate type definition string
    CodeGenerator->>TypeDefField: Generate field representation
Loading

The sequence diagram illustrates the new type definition generation process, showing how the code generator interacts with the abstract syntax tree (AST) to create type definitions and their corresponding fields.


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 197e42e and 129ea27.

⛔ Files ignored due to path filters (12)
  • package.json is excluded by !**/*.json
  • packages/ide/jetbrains/package.json is excluded by !**/*.json
  • packages/language/package.json is excluded by !**/*.json
  • packages/misc/redwood/package.json is excluded by !**/*.json
  • packages/plugins/openapi/package.json is excluded by !**/*.json
  • packages/plugins/swr/package.json is excluded by !**/*.json
  • packages/plugins/tanstack-query/package.json is excluded by !**/*.json
  • packages/plugins/trpc/package.json is excluded by !**/*.json
  • packages/runtime/package.json is excluded by !**/*.json
  • packages/schema/package.json is excluded by !**/*.json
  • packages/server/package.json is excluded by !**/*.json
  • packages/testtools/package.json is excluded by !**/*.json
📒 Files selected for processing (1)
  • packages/ide/jetbrains/build.gradle.kts (1 hunks)
✅ Files skipped from review due to trivial changes (1)
  • packages/ide/jetbrains/build.gradle.kts
⏰ Context from checks skipped due to timeout of 90000ms (3)
  • GitHub Check: build-test (20.x)
  • GitHub Check: build-test (20.x)
  • GitHub Check: build-test (20.x)

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

‼️ IMPORTANT
Auto-reply has been disabled for this repository in the CodeRabbit settings. The CodeRabbit bot will not respond to your replies unless it is explicitly tagged.

  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🧹 Nitpick comments (2)
packages/schema/tests/schema/all-features.zmodel (1)

181-190: Consider using Metadata type for better type safety.

The metadata field in the Image model is currently using Json type, while there's a well-defined Metadata type available. Consider using the Metadata type directly for better type safety and schema validation at runtime.

model Image {
    id       Int      @id @default(autoincrement())
-    metadata Json
+    metadata Metadata
}
packages/sdk/src/zmodel-code-generator.ts (1)

Line range hint 183-190: Consider using type predicate for better type narrowing.

The type check could be improved using a type predicate function for clearer type discrimination.

+private isDataModelFieldType(type: DataModelFieldType | TypeDefFieldType): type is DataModelFieldType {
+    return type.$type === 'DataModelFieldType';
+}

 private fieldType(type: DataModelFieldType | TypeDefFieldType) {
     const baseType = type.type
         ? type.type
-        : type.$type == 'DataModelFieldType' && type.unsupported
+        : this.isDataModelFieldType(type) && type.unsupported
         ? 'Unsupported(' + this.generate(type.unsupported.value) + ')'
         : type.reference?.$refText;
     return `${baseType}${type.array ? '[]' : ''}${type.optional ? '?' : ''}`;
 }
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 506cf99 and 20252f2.

⛔ Files ignored due to path filters (1)
  • packages/sdk/package.json is excluded by !**/*.json
📒 Files selected for processing (2)
  • packages/schema/tests/schema/all-features.zmodel (6 hunks)
  • packages/sdk/src/zmodel-code-generator.ts (3 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (1)
  • GitHub Check: build-test (20.x)
🔇 Additional comments (8)
packages/schema/tests/schema/all-features.zmodel (6)

39-47: LGTM! Clean formatting of Space model properties.

The properties are well-aligned and maintain consistent spacing.


69-76: LGTM! Clean formatting of SpaceUser model properties.

The properties maintain consistent alignment and spacing.


95-106: LGTM! Clean formatting of User model properties.

The properties are well-organized with consistent spacing.


122-131: LGTM! Clean formatting of List model properties.

The properties maintain consistent alignment and spacing.


154-161: LGTM! Clean formatting of Todo model properties.

The properties are well-aligned with consistent spacing.


176-179: LGTM! Well-structured view definition.

The view captures essential space fields with appropriate constraints.

packages/sdk/src/zmodel-code-generator.ts (2)

42-44: LGTM! Necessary imports for type definition support.

The imports maintain consistent style with other AST types.


339-344: LGTM! Well-implemented type definition field generation.

The implementation follows the established patterns and maintains consistency with other field generators.

packages/sdk/src/zmodel-code-generator.ts Outdated Show resolved Hide resolved
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (1)
packages/sdk/src/zmodel-code-generator.ts (1)

183-189: Consider using type guards for better type safety and readability.

The current implementation works but could be more maintainable with explicit type guards.

Consider this refactor:

-    private fieldType(type: DataModelFieldType | TypeDefFieldType) {
+    private fieldType(type: DataModelFieldType | TypeDefFieldType) {
+        function isDataModelFieldType(t: DataModelFieldType | TypeDefFieldType): t is DataModelFieldType {
+            return t.$type === 'DataModelFieldType';
+        }
+
         const baseType = type.type
             ? type.type
-            : type.$type == 'DataModelFieldType' && type.unsupported
+            : isDataModelFieldType(type) && type.unsupported
             ? 'Unsupported(' + this.generate(type.unsupported.value) + ')'
             : type.reference?.$refText;
         return `${baseType}${type.array ? '[]' : ''}${type.optional ? '?' : ''}`;
     }
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 20252f2 and 197e42e.

📒 Files selected for processing (1)
  • packages/sdk/src/zmodel-code-generator.ts (3 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (1)
  • GitHub Check: build-test (20.x)
🔇 Additional comments (2)
packages/sdk/src/zmodel-code-generator.ts (2)

42-44: LGTM! Import statements are well-organized.

The new type imports are correctly placed and necessary for implementing the type definition functionality.


328-344: LGTM! Type definition generation methods are well-implemented.

The new methods follow consistent patterns with existing code:

  • Proper decoration with @gen
  • Consistent handling of attributes
  • Correct indentation and formatting

Note: There was a past review comment about a typo in the method name _genearteTypeDef, but I can see that it has been fixed to _generateTypeDef in this version.

@ymc9 ymc9 merged commit da50917 into dev Jan 17, 2025
9 checks passed
@ymc9 ymc9 deleted the jiasheng-dev branch January 17, 2025 01:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants