diff --git a/CHANGELOG.md b/CHANGELOG.md
index 03db407..41e56d1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,7 @@ Follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) · versioned wi
## [Unreleased]
### Added
+- **Magazine import from PNG/JPEG page images.** Choose or drop several scans or phone photos; they are checked by content (not by name), ordered by filename with natural numbering, turned into one scan-style PDF (page size from the image's own resolution, EXIF rotation applied, 72 dpi treated as unknown) and ingested like any scanned issue. Limits: 300 images, 25 MB and 60 megapixels each; a bad image rejects the whole upload and leaves nothing behind; an existing source is never replaced. Verified on real pages: OCR through the image path scored like the original PDF (F1 0.85 / 0.78).
- `architecture/ocr-porting-prompt-general.md`: the OCR porting brief rewritten for general documents (letters, papers, forms, invoices). Adds privacy, pre-processing of skewed/photographed scans, document-type handling, field-level accuracy and handwriting, and tags every claim as measured on magazines, a general principle, or untested for these document types.
---
diff --git a/Manual.md b/Manual.md
index bc7b3fe..b23d4ea 100644
--- a/Manual.md
+++ b/Manual.md
@@ -77,7 +77,7 @@ turned into a podcast discussion between two or three voices you pick.
### Prerequisites
-- The magazine as a PDF (native text or scanned — both work).
+- The magazine as a PDF (native text or scanned — both work), **or** its pages as PNG/JPEG images (scans or phone photos): choose or drop several at once and they become one magazine, pages in filename order (`page2` before `page10`). Up to 300 images of at most 25 MB each; a photo's EXIF rotation is applied. Images carry no text, so every page is read with OCR. Do not mix a PDF with images.
- At least one voice in the library for narration.
- For podcast mode: an LLM configured in Settings (`llm_url`, `llm_model`), and
two or three voices chosen as hosts.
diff --git a/TODO.md b/TODO.md
index 49d5ee8..22f550f 100644
--- a/TODO.md
+++ b/TODO.md
@@ -656,7 +656,7 @@ casting. The original PDF remains the visual source of truth while approved arti
### P0 — Magazine foundation
- [x] Add a Magazine project type beside Books and Theater Plays.
-- [~] Add PDF/JPG/PNG import with page previews and safe local storage. *(PDF + page renders done; JPG/PNG not done)*
+- [x] Add PDF/JPG/PNG import with page previews and safe local storage. *(2026-09-29: JPG/PNG page images become one scan-style PDF, see architecture/magazine-ingestion.md)*
- [x] Add OCR-engine selection from Engines > OCR & Document Parsing, with page-image input and structured output.
- [x] Detect contents/index pages and propose article titles, authors, and page ranges.
- [x] Build a review screen where users approve or correct article boundaries before TTS.
diff --git a/architecture/magazine-ingestion.md b/architecture/magazine-ingestion.md
index 93fa82f..9bbee00 100644
--- a/architecture/magazine-ingestion.md
+++ b/architecture/magazine-ingestion.md
@@ -448,6 +448,17 @@ Verified end-to-end against a synthetic 8-page issue (contents page, two-column
feature with a byline and a page-8 jump, full-page advert, second feature,
reviews) and against an image-only rendering of the same file to exercise OCR.
+## Import from page images
+
+`POST /api/magazine/{id}/source-images` (multipart `files`, in the order sent) builds `source.pdf` with
+`images_to_pdf`, so nothing downstream changes: the PDF has no text layer and every page takes the OCR path.
+Content is sniffed from the header (PNG/JPEG), never from the name or declared type; limits are 300 files, 25 MB and
+60 megapixels per image (checked before decoding); EXIF orientation is applied (an unrotated JPEG is embedded
+byte-for-byte, not re-encoded). Page size comes from the image's dpi; 72 and anything below 100 is the placeholder most
+tools write, so it is treated as unknown (150 assumed) rather than producing a 33-inch page. The PDF is written through a
+temporary file, one bad image rejects the whole upload, and a magazine that already has a source returns 409 so pages that
+were reviewed can never be replaced. The browser orders files by name with numeric collation.
+
## Vision OCR escalation
Engines → OCR & Document Parsing lists layout-aware parsers (KDL Frontier Parser
diff --git a/core/magazine.py b/core/magazine.py
index bb954d5..8cc22f1 100644
--- a/core/magazine.py
+++ b/core/magazine.py
@@ -2367,6 +2367,81 @@ def ocr_page(png_path: Path, lang: str = "deu+eng",
return out
+# ── Image import ─────────────────────────────────────────────────────────────
+
+IMAGE_IMPORT_MAX_FILES = 300
+IMAGE_IMPORT_MAX_BYTES = 25 * 1024 * 1024 # per image
+IMAGE_IMPORT_MAX_PIXELS = 60_000_000 # refuses decompression bombs before decoding
+_ASSUMED_SCAN_DPI = 150 # when an image carries no (or an absurd) resolution
+
+
+class ImageImportError(ValueError):
+ """An uploaded page image was rejected; the message is safe to show the user."""
+
+
+def _sniff_image(data: bytes) -> str | None:
+ """'png' or 'jpeg' judged by the file's own header, never by its name or declared type."""
+ if data[:8] == b"\x89PNG\r\n\x1a\n":
+ return "png"
+ if data[:3] == b"\xff\xd8\xff":
+ return "jpeg"
+ return None
+
+
+def images_to_pdf(images: Sequence[tuple[str, bytes]], dest: Path) -> int:
+ """Combine page images (PNG/JPEG, in the given order) into one PDF at `dest`; returns the page count.
+
+ Each image becomes one page sized from its own resolution (so the app's fixed-dpi render of the
+ page comes out at the scan's real proportions), with EXIF rotation applied. The result has no text
+ layer, so ingestion OCRs every page exactly as for a scanned PDF. Nothing is written on failure.
+ """
+ if not images:
+ raise ImageImportError("Choose at least one image")
+ if len(images) > IMAGE_IMPORT_MAX_FILES:
+ raise ImageImportError(f"At most {IMAGE_IMPORT_MAX_FILES} images per magazine")
+ import io
+ import pymupdf
+ from PIL import Image, ImageOps
+
+ doc = pymupdf.open()
+ try:
+ for name, data in images:
+ label = Path(name or "image").name[:80]
+ if len(data) > IMAGE_IMPORT_MAX_BYTES:
+ raise ImageImportError(f"{label} is larger than {IMAGE_IMPORT_MAX_BYTES // (1024 * 1024)} MB")
+ kind = _sniff_image(data)
+ if kind is None:
+ raise ImageImportError(f"{label} is not a PNG or JPEG image")
+ try:
+ with Image.open(io.BytesIO(data)) as im:
+ width, height = im.size
+ if width * height > IMAGE_IMPORT_MAX_PIXELS:
+ raise ImageImportError(f"{label} has too many pixels")
+ dpi = im.info.get("dpi", (0, 0))[0] or 0
+ if im.getexif().get(0x0112, 1) not in (0, 1): # EXIF says the pixels are rotated/flipped
+ upright = ImageOps.exif_transpose(im)
+ buf = io.BytesIO()
+ upright.convert("RGB" if kind == "jpeg" else upright.mode).save(
+ buf, format="JPEG" if kind == "jpeg" else "PNG", **({"quality": 95} if kind == "jpeg" else {}))
+ data = buf.getvalue()
+ width, height = upright.size
+ except ImageImportError:
+ raise
+ except Exception as e: # truncated / corrupt file
+ raise ImageImportError(f"{label} could not be read as an image") from e
+ # 72 (and anything below 100) is the placeholder most tools write, not a real scan resolution.
+ dpi = float(dpi) if 100 <= float(dpi or 0) <= 1200 else _ASSUMED_SCAN_DPI
+ w_pt, h_pt = width * 72.0 / dpi, height * 72.0 / dpi
+ page = doc.new_page(width=w_pt, height=h_pt)
+ page.insert_image(pymupdf.Rect(0, 0, w_pt, h_pt), stream=data)
+ tmp = dest.with_suffix(".part")
+ doc.save(str(tmp))
+ tmp.replace(dest)
+ return len(images)
+ finally:
+ doc.close()
+
+
_VISION_QUALITY_THRESHOLD = 0.5 # below this, existing native/OCR text is escalated
diff --git a/routes/magazine.py b/routes/magazine.py
index a12d1d4..3225501 100644
--- a/routes/magazine.py
+++ b/routes/magazine.py
@@ -31,7 +31,7 @@ import zipfile
from pathlib import Path
from typing import Any
-from fastapi import APIRouter, HTTPException, Request
+from fastapi import APIRouter, File, HTTPException, Request, UploadFile
from fastapi.responses import FileResponse, Response
from core import magazine as mag
@@ -121,6 +121,29 @@ async def magazine_create(request: Request):
return {"id": doc_id}
+@router.post("/api/magazine/{doc_id}/source-images")
+async def magazine_source_images(doc_id: str, files: list[UploadFile] = File(...)):
+ """Build the magazine's source.pdf from uploaded page images (PNG/JPEG, in the order sent).
+
+ Ingestion then treats it as any scanned PDF. Refused when a source already exists, so an upload can
+ never silently replace pages that were already reviewed.
+ """
+ d, _ = _require_magazine(doc_id)
+ if (d / "source.pdf").exists():
+ raise HTTPException(409, "This magazine already has a source file")
+ if len(files) > mag.IMAGE_IMPORT_MAX_FILES:
+ raise HTTPException(400, f"At most {mag.IMAGE_IMPORT_MAX_FILES} images per magazine")
+ images: list[tuple[str, bytes]] = []
+ for f in files:
+ data = await f.read(mag.IMAGE_IMPORT_MAX_BYTES + 1)
+ images.append((f.filename or "image", data))
+ try:
+ pages = await asyncio.to_thread(mag.images_to_pdf, images, d / "source.pdf")
+ except mag.ImageImportError as e:
+ raise HTTPException(400, str(e))
+ return {"ok": True, "pages": pages}
+
+
@router.patch("/api/magazine/{doc_id}")
async def magazine_update_meta(doc_id: str, request: Request):
"""Edit title/issue/publisher after creation -- there was previously no
diff --git a/static/js/magazine.js b/static/js/magazine.js
index a3800d0..c6d7b6d 100644
--- a/static/js/magazine.js
+++ b/static/js/magazine.js
@@ -230,7 +230,7 @@ async function magDelete(docId) {
}
// ── Add-magazine dropzone (mirrors reader.js's setupReaderDropzone) ─────────
-const MAG_DROPZONE_DEFAULT_NOTE = 'Scanned issues work too — pages without selectable text are read with OCR.';
+const MAG_DROPZONE_DEFAULT_NOTE = 'Scanned issues and phone photos work too — pages without selectable text are read with OCR. Several images are read in filename order.';
function magFormatFilenameAsTitle(filename) {
if (!filename) return '';
@@ -241,6 +241,25 @@ function magFormatFilenameAsTitle(filename) {
.trim();
}
+// What was chosen or dropped: exactly one PDF, or several page images (PNG/JPEG) read in filename order.
+// Returns { kind, files, label: {name, size} } or { error }. The server re-checks content by its bytes.
+function magClassifyFiles(list) {
+ const files = Array.from(list || []).filter(Boolean);
+ if (!files.length) return { error: 'Choose or drop a PDF or page images first' };
+ const isPdf = (f) => f.type === 'application/pdf' || /\.pdf$/i.test(f.name);
+ const isImg = (f) => /^image\/(png|jpeg)$/.test(f.type) || /\.(png|jpe?g)$/i.test(f.name);
+ if (files.every(isPdf)) {
+ if (files.length > 1) return { error: 'Choose one PDF, or several page images — not several PDFs' };
+ return { kind: 'pdf', files, label: files[0] };
+ }
+ if (files.every(isImg)) {
+ files.sort((a, b) => a.name.localeCompare(b.name, undefined, { numeric: true, sensitivity: 'base' }));
+ const size = files.reduce((n, f) => n + f.size, 0);
+ return { kind: 'images', files, label: { name: files.length === 1 ? files[0].name : files.length + ' page images', size } };
+ }
+ return { error: 'Only a PDF, or PNG/JPEG page images, can be imported' };
+}
+
function magShowDroppedFile(file) {
const noteEl = $('mag-dropzone-note');
const titleEl = $('mag-dropzone-title');
@@ -252,7 +271,7 @@ function magShowDroppedFile(file) {
const sizeMb = (file.size / (1024 * 1024)).toFixed(1);
if (dropzone) dropzone.classList.add('is-selected');
if (noteEl) noteEl.textContent = `Selected: ${file.name} (${sizeMb} MB)`;
- if (titleEl) titleEl.textContent = 'PDF file selected — uploading...';
+ if (titleEl) titleEl.textContent = 'File selected — uploading...';
if (iconEl) iconEl.className = 'mdi mdi-file-check-outline reader-dropzone-icon';
// Auto-fill title from filename if title input is empty
@@ -262,7 +281,7 @@ function magShowDroppedFile(file) {
} else {
if (dropzone) dropzone.classList.remove('is-selected', 'is-uploading');
if (noteEl) noteEl.textContent = MAG_DROPZONE_DEFAULT_NOTE;
- if (titleEl) titleEl.textContent = 'Drop a PDF document';
+ if (titleEl) titleEl.textContent = 'Drop a PDF or page images';
if (iconEl) iconEl.className = 'mdi mdi-cloud-upload-outline reader-dropzone-icon';
}
}
@@ -330,30 +349,29 @@ function setupMagDropzone() {
dragCounter = 0;
zone.classList.remove('dragover');
- let file = e.dataTransfer?.files?.[0];
- if (!file && e.dataTransfer?.items?.[0]) {
- file = e.dataTransfer.items[0].getAsFile();
+ let dropped = Array.from(e.dataTransfer?.files || []);
+ if (!dropped.length && e.dataTransfer?.items?.length) {
+ dropped = Array.from(e.dataTransfer.items).map((i) => i.getAsFile()).filter(Boolean);
}
- if (!file) return;
- if (file.type !== 'application/pdf' && !/\.pdf$/i.test(file.name)) {
- return say('Only PDF files are supported', 'err');
- }
- magShowDroppedFile(file);
- magCreate(file);
+ const picked = magClassifyFiles(dropped);
+ if (picked.error) return say(picked.error, 'err');
+ magShowDroppedFile(picked.label);
+ magCreate(picked.files);
});
input.addEventListener('change', () => {
- const file = input.files?.[0];
- if (file) {
- magShowDroppedFile(file);
- magCreate(file);
- }
+ if (!input.files?.length) return;
+ const picked = magClassifyFiles(input.files);
+ if (picked.error) return say(picked.error, 'err');
+ magShowDroppedFile(picked.label);
+ magCreate(picked.files);
});
}
-async function magCreate(droppedFile = null) {
- const file = droppedFile || $('mag-new-file')?.files?.[0];
- if (!file) return say('Choose or drop a PDF file first', 'err');
+async function magCreate(dropped = null) {
+ const picked = magClassifyFiles(dropped ? (Array.isArray(dropped) ? dropped : [dropped]) : $('mag-new-file')?.files);
+ if (picked.error) return say(picked.error, 'err');
+ const file = picked.label;
let title = ($('mag-new-title')?.value || '').trim();
if (!title) {
@@ -418,7 +436,13 @@ async function magCreate(droppedFile = null) {
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ title, issue }),
});
- await api('/api/reader/docs/' + id + '/source?ext=pdf', { method: 'PUT', body: file });
+ if (picked.kind === 'pdf') {
+ await api('/api/reader/docs/' + id + '/source?ext=pdf', { method: 'PUT', body: picked.files[0] });
+ } else {
+ const form = new FormData();
+ picked.files.forEach((f) => form.append('files', f, f.name));
+ await api('/api/magazine/' + id + '/source-images', { method: 'POST', body: form });
+ }
say('Magazine uploaded — starting ingestion', 'ok');
if ($('mag-new-title')) $('mag-new-title').value = '';
diff --git a/static/sections/s-magazine.html b/static/sections/s-magazine.html
index 9b9dd14..007750e 100644
--- a/static/sections/s-magazine.html
+++ b/static/sections/s-magazine.html
@@ -25,22 +25,22 @@
-
- Drop a PDF document
+ Drop a PDF or page imagesScanned issues work too — pages without selectable text are read with OCR.