Skip to content

fix(core): preserve OCR continuity for blank pages #135

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

Merged
jb-thery merged 1 commit into from
Jul 18, 2026
Merged

fix(core): preserve OCR continuity for blank pages #135

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
25 changes: 23 additions & 2 deletions packages/ragmir-core/src/ocr.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,22 @@ describe("PDF OCR onboarding", () => {
).resolves.toBe("Synthetic OCR text from Tesseract\n")
})

it("should keep an empty OCR payload when the requested page has no text", async () => {
const root = await createTempRoot("ragmir-ocr-tesseract-empty-")
const binDir = await createFakeTools(root, {
tesseract: true,
pdftoppm: true,
emptyTesseractOutput: true,
})
process.env.PATH = binDir
const input = path.join(root, "scan.pdf")
await writeFile(input, "synthetic PDF fixture")

await expect(
extractPdfPage({ engine: "tesseract", input, page: 2, language: "eng" }),
).resolves.toBe("")
})

it("should extract multiple PDF pages through one bounded Tesseract batch", async () => {
const root = await createTempRoot("ragmir-ocr-tesseract-batch-")
const binDir = await createFakeTools(root, { tesseract: true, pdftoppm: true })
Expand Down Expand Up @@ -186,7 +202,12 @@ async function createTempRoot(prefix: string): Promise<string> {

async function createFakeTools(
root: string,
tools: { ocrmypdf?: boolean; tesseract?: boolean; pdftoppm?: boolean },
tools: {
ocrmypdf?: boolean
tesseract?: boolean
pdftoppm?: boolean
emptyTesseractOutput?: boolean
},
): Promise<string> {
const binDir = path.join(root, "bin")
await mkdir(binDir, { recursive: true })
Expand All @@ -200,7 +221,7 @@ if (args.includes("--list-langs")) {
process.stdout.write("List of available languages (2):\\neng\\nfra\\n")
} else if (args.includes("stdout")) {
const pages = readFileSync(args[0], "utf8").trim().split("\\n").filter(Boolean)
process.stdout.write(pages.map(() => "Synthetic OCR text from Tesseract\\n").join("\\f") + "\\f")
process.stdout.write(${tools.emptyTesseractOutput ? '""' : 'pages.map(() => "Synthetic OCR text from Tesseract\\n").join("\\f") + "\\f"'})
} else {
process.stdout.write("tesseract 5.5.0\\n")
}`,
Expand Down
2 changes: 1 addition & 1 deletion packages/ragmir-core/src/ocr.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -375,7 +375,7 @@ async function extractWithTesseract(options: {

function pairOcrPageText(pages: number[], output: string): Array<{ page: number; text: string }> {
const pageTexts = output.replace(/\r\n?/gu, "\n").split("\f")
if (pageTexts.at(-1) === "") {
if (pageTexts.length === pages.length + 1 && pageTexts.at(-1) === "") {
pageTexts.pop()
}
if (pageTexts.length !== pages.length) {
Expand Down