Skip to content

Preserve DOCX manual line breaks #186

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.

Sign up for GitHub

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

Open
dipeshbabu wants to merge 2 commits into
base: main
Choose a base branch
from
+17 −4
Open

Preserve DOCX manual line breaks #186

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
51f5909
Preserve DOCX manual line breaks
dipeshbabu Jul 31, 2026
3fe6cf9
Handle paired DOCX break elements
dipeshbabu Aug 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions sdk/typescript/src/knowledge-base.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,6 +193,7 @@ function extractDocx(path: string, bytes: Uint8Array): string {
return decodeXml(
xml
.replace(/<\/(?:\w+:)?p\s*>/gu, "\n")
.replace(/<(?:\w+:)?br\b[^>]*>/gu, "\n")
.replace(/<(?:\w+:)?tab\b[^>]*\/>/gu, "\t")
.replace(/<[^>]+>/gu, ""),
);
Expand Down
20 changes: 16 additions & 4 deletions sdk/typescript/tests-ts/knowledge-base.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,10 +41,14 @@ async function extractedDocuments(path: string): Promise<string[]> {
);
}

function docx(text: string): Uint8Array {
function docx(
text: string,
secondLine?: string,
breakElement = "<w:br/>",
): Uint8Array {
return zipSync({
"word/document.xml": strToU8(
`<?xml version="1.0"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body><w:p><w:r><w:t>${text}</w:t></w:r></w:p></w:body></w:document>`,
`<?xml version="1.0"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body><w:p><w:r><w:t>${text}</w:t></w:r>${secondLine === undefined ? "" : `${breakElement}<w:r><w:t>${secondLine}</w:t></w:r>`}</w:p></w:body></w:document>`,
),
});
}
Expand Down Expand Up @@ -111,14 +115,22 @@ describe("scan knowledge bases", () => {
join(root, "architecture.pdf"),
pdf("Payment service boundary"),
);
await writeFile(join(root, "threat-model.docx"), docx("SSRF &amp; IDOR"));
await writeFile(
join(root, "threat-model.docx"),
docx("SSRF &amp; IDOR", "Review authentication"),
);
await writeFile(
join(root, "paired-break.docx"),
docx("Authorization", "Review permissions", "<w:br></w:br>"),
);

const knowledgeBase = await prepareKnowledgeBase([root]);
temporaryDirectories.push(knowledgeBase.path);
const documents = await extractedDocuments(knowledgeBase.path);

expect(documents).toContain("Payment service boundary");
expect(documents).toContain("SSRF & IDOR\n");
expect(documents).toContain("SSRF & IDOR\nReview authentication\n");
expect(documents).toContain("Authorization\nReview permissions\n");
});

test("cleans up documents and rediscovers directory contents on later runs", async () => {
Expand Down