anthropics/claude-code-action
1
0
Fork 0
mirror of https://github.com/anthropics/claude-code-action.git synced 2026-01-23 06:54:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor tests to remove redundancy and improve structure

Browse Source 
- Remove redundant 'mixed input patterns' test from sanitizer.test.ts
- Consolidate integration tests into 2 focused real-world scenarios
- Add HTML comment stripping to sanitizeContent function
- Update test expectations to match sanitization behavior
- Maintain full coverage with fewer, more focused tests
This commit is contained in:
Lina Tawfik
2025-05-28 18:12:07 -07:00
parent 046ef964a9
commit cf04e19dbc
3 changed files with 91 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/github/utils/sanitizer.ts
View File

@@ -52,6 +52,7 @@ export function normalizeHtmlEntities(content: string): string {
} }
export function sanitizeContent(content: string): string { export function sanitizeContent(content: string): string {
content = stripHtmlComments(content);
content = stripInvisibleCharacters(content); content = stripInvisibleCharacters(content);
content = stripMarkdownImageAltText(content); content = stripMarkdownImageAltText(content);
content = stripMarkdownLinkTitles(content); content = stripMarkdownLinkTitles(content);

202
test/integration-sanitization.test.ts
View File

@@ -2,50 +2,47 @@ import { describe, expect, it } from "bun:test";
import { formatBody, formatComments } from "../src/github/data/formatter"; import { formatBody, formatComments } from "../src/github/data/formatter";
import type { GitHubComment } from "../src/github/types"; import type { GitHubComment } from "../src/github/types";
describe("Integration: Text Sanitization", () => { describe("Sanitization Integration", () => {
it("should sanitize text in issue body", () => { it("should sanitize complete issue/PR body with various hidden content patterns", () => {
const body = ` const issueBody = `
# Title text # Feature Request: Add user dashboard
Some content here. ## Description
We need a new dashboard for users to track their activity.
Here's an image: <img alt="some alt text" src="image.jpg"> <!-- HTML comment that should be removed -->
And a markdown image: ![image text](screenshot.png) ## Technical Details
The dashboard should display:
- User statistics ![dashboard mockup with hidden​‌‍text](dashboard.png)
- Activity graphs <img alt="example graph description" src="graph.jpg">
- Recent actions
Check this link: [Click here](https://example.com "link title") ## Implementation Notes
See [documentation](https://docs.example.com "internal docs title") for API details.
Text with hidden​‌‍characters <div data-instruction="example instruction" aria-label="dashboard label" title="hover text">
The implementation should follow our standard patterns.
<div data-prompt="test data" aria-label="label text" title="title text">
Content with attributes
</div> </div>
Entity-encoded: &#72;&#69;&#76;&#76;&#79; Additional notes: Text­with­soft­hyphens and &#72;&#105;&#100;&#100;&#101;&#110; encoded content.
Direction: ‮reversed‬ text <input placeholder="search placeholder" type="text" />
<input placeholder="placeholder text" type="text"> Direction override test: ‮reversed‬ text should be normalized.`;
Text­with­soft­hyphens
More text: with‌zero‍width​characters`;
const imageUrlMap = new Map<string, string>(); const imageUrlMap = new Map<string, string>();
const result = formatBody(body, imageUrlMap); const result = formatBody(issueBody, imageUrlMap);
expect(result).not.toContain("some alt text"); // Verify hidden content is removed
expect(result).not.toContain("image text"); expect(result).not.toContain("<!-- HTML comment");
expect(result).not.toContain("link title"); expect(result).not.toContain("hidden​‌‍text");
expect(result).not.toContain("test data"); expect(result).not.toContain("example graph description");
expect(result).not.toContain("label text"); expect(result).not.toContain("internal docs title");
expect(result).not.toContain("title text"); expect(result).not.toContain("example instruction");
expect(result).not.toContain("placeholder text"); expect(result).not.toContain("dashboard label");
expect(result).not.toContain('alt="'); expect(result).not.toContain("hover text");
expect(result).not.toContain('title="'); expect(result).not.toContain("search placeholder");
expect(result).not.toContain('aria-label="');
expect(result).not.toContain('data-prompt="');
expect(result).not.toContain('placeholder="');
expect(result).not.toContain("\u200B"); expect(result).not.toContain("\u200B");
expect(result).not.toContain("\u200C"); expect(result).not.toContain("\u200C");
expect(result).not.toContain("\u200D"); expect(result).not.toContain("\u200D");
@@ -53,104 +50,79 @@ More text: with‌zero‍width​characters`;
expect(result).not.toContain("\u202E"); expect(result).not.toContain("\u202E");
expect(result).not.toContain("&#72;"); expect(result).not.toContain("&#72;");
expect(result).toContain("# Title text"); // Verify legitimate content is preserved
expect(result).toContain("Some content here."); expect(result).toContain("# Feature Request: Add user dashboard");
expect(result).toContain("Here's an image:"); expect(result).toContain("## Description");
expect(result).toContain('<img src="image.jpg">'); expect(result).toContain("We need a new dashboard");
expect(result).toContain("![](screenshot.png)"); expect(result).toContain("User statistics");
expect(result).toContain("[Click here](https://example.com)"); expect(result).toContain("![](dashboard.png)");
expect(result).toContain("Content with attributes"); expect(result).toContain('<img src="graph.jpg">');
expect(result).toContain("HELLO"); expect(result).toContain("[documentation](https://docs.example.com)");
expect(result).toContain('<input type="text">'); expect(result).toContain("The implementation should follow our standard patterns");
expect(result).toContain("Hidden encoded content");
expect(result).toContain('<input type="text" />');
}); });
it("should sanitize text in comments", () => { it("should sanitize GitHub comments preserving discussion flow", () => {
const comments: GitHubComment[] = [ const comments: GitHubComment[] = [
{ {
id: "1", id: "1",
databaseId: "100001", databaseId: "100001",
body: `Comment text body: `Great idea! Here are my thoughts:
Check this: ![description text](image.png) 1. We should consider the performance impact
[Documentation](https://docs.com "doc title") 2. The UI mockup looks good: ![ui design](mockup.png)
3. Check the [API docs](https://api.example.com "api reference") for rate limits
Text​‌‍with characters <div aria-label="comment metadata" data-comment-type="review">
This change would affect multiple systems.
</div>
<span aria-label="span label" data-cmd="data value">Visible text</span>`, Note: Implementation​should​follow​best​practices.`,
author: { login: "user1" }, author: { login: "reviewer1" },
createdAt: "2023-01-01T00:00:00Z", createdAt: "2023-01-01T10:00:00Z",
},
{
id: "2",
databaseId: "100002",
body: `Thanks for the feedback!
<!-- Internal note: discussed with team -->
I've updated the proposal based on your suggestions.
&#84;&#101;&#115;&#116; &#110;&#111;&#116;&#101;: All systems checked.
<span title="status update" data-status="approved">Ready for implementation</span>`,
author: { login: "author1" },
createdAt: "2023-01-01T12:00:00Z",
}, },
]; ];
const result = formatComments(comments); const result = formatComments(comments);
expect(result).not.toContain("description text"); // Verify hidden content is removed
expect(result).not.toContain("doc title"); expect(result).not.toContain("<!-- Internal note");
expect(result).not.toContain("span label"); expect(result).not.toContain("api reference");
expect(result).not.toContain("data value"); expect(result).not.toContain("comment metadata");
expect(result).not.toContain('aria-label="'); expect(result).not.toContain("data-comment-type=\"review\"");
expect(result).not.toContain('data-cmd="'); expect(result).not.toContain("status update");
expect(result).not.toContain("data-status=\"approved\"");
expect(result).not.toContain("\u200B"); expect(result).not.toContain("\u200B");
expect(result).not.toContain("\u200C"); expect(result).not.toContain("&#84;");
expect(result).not.toContain("\u200D");
expect(result).toContain("Comment text"); // Verify discussion flow is preserved
expect(result).toContain("![](image.png)"); expect(result).toContain("Great idea! Here are my thoughts:");
expect(result).toContain("[Documentation](https://docs.com)"); expect(result).toContain("1. We should consider the performance impact");
expect(result).toContain("Visible text"); expect(result).toContain("2. The UI mockup looks good: ![](mockup.png)");
expect(result).toContain("Textwith characters"); expect(result).toContain("3. Check the [API docs](https://api.example.com)");
}); expect(result).toContain("This change would affect multiple systems.");
expect(result).toContain("Implementationshouldfollowbestpractices");
it("should handle complex mixed patterns", () => { expect(result).toContain("Thanks for the feedback!");
const content = ` expect(result).toContain("I've updated the proposal based on your suggestions.");
Text content here. expect(result).toContain("Test note: All systems checked.");
expect(result).toContain("Ready for implementation");
<div title="div​title​text" data-instruction="data&#32;text"> expect(result).toContain("[reviewer1 at");
<img src="image.jpg" alt="img­alt­text"> expect(result).toContain("[author1 at");
Text with ‮reversed‬ content
</div>
![alt text\u200Bwith\u200Ccharacters](image.png)
[link](url.com "title\u00ADtext")
Mix: &#72;idden <span aria-label="&#77;ore">text</span>`;
const imageUrlMap = new Map<string, string>();
const result = formatBody(content, imageUrlMap);
expect(result).not.toContain('title="');
expect(result).not.toContain('data-instruction="');
expect(result).not.toContain('alt="');
expect(result).not.toContain('aria-label="');
expect(result).not.toContain("\u200B");
expect(result).not.toContain("\u200C");
expect(result).not.toContain("\u00AD");
expect(result).not.toContain("\u202E");
expect(result).toContain("Text content here.");
expect(result).toContain("<div>");
expect(result).toContain('<img src="image.jpg">');
expect(result).toContain("![](image.png)");
expect(result).toContain("[link](url.com)");
expect(result).toContain("Hidden <span>text</span>");
});
it("should handle edge cases with empty attributes", () => {
const edgeCases = `
<img alt="" src="test.jpg">
<div title="" data-x="">Content</div>
![](already-empty.png)
[link](url.com)
Normal text`;
const imageUrlMap = new Map<string, string>();
const result = formatBody(edgeCases, imageUrlMap);
expect(result).toContain('<img src="test.jpg">');
expect(result).toContain("<div>Content</div>");
expect(result).toContain("![](already-empty.png)");
expect(result).toContain("[link](url.com)");
expect(result).toContain("Normal text");
}); });
}); });

18
test/sanitizer.test.ts
View File

@@ -172,6 +172,7 @@ describe("sanitizeContent", () => {
const sanitized = sanitizeContent(testContent); const sanitized = sanitizeContent(testContent);
expect(sanitized).not.toContain("<!-- This is a comment -->");
expect(sanitized).not.toContain("example alt text"); expect(sanitized).not.toContain("example alt text");
expect(sanitized).not.toContain("example image description"); expect(sanitized).not.toContain("example image description");
expect(sanitized).not.toContain("example title"); expect(sanitized).not.toContain("example title");
@@ -240,23 +241,6 @@ describe("sanitizeContent", () => {
expect(sanitized).toContain("<div>Test</div>"); expect(sanitized).toContain("<div>Test</div>");
}); });
it("should handle mixed input patterns", () => {
const mixedInput = `
![example\u200Btext\u00ADwith\u00ADcharacters](image.png)
<img alt="&#101;&#120;&#97;&#109;&#112;&#108;&#101;" src="pic.jpg">
[link](url.com "title\u202Ewith\u202Ccharacters")
<span data-cmd="data value" aria-label="label text">visible text</span>
`;
const sanitized = sanitizeContent(mixedInput);
expect(sanitized).not.toContain("example");
expect(sanitized).not.toContain("characters");
expect(sanitized).not.toContain("title");
expect(sanitized).not.toContain("data value");
expect(sanitized).not.toContain("label text");
expect(sanitized).toContain("visible text");
});
}); });
describe("stripHtmlComments (legacy)", () => { describe("stripHtmlComments (legacy)", () => {