any-file to PDF (Phase 1): converters/ dispatcher, images/text/md/csv/json/xml/svg/pdf-passthrough, 112 tests green

converters/image_converter.py

@@ -0,0 +1,53 @@
+"""Raster images (.png/.jpg/.jpeg/.webp/.tiff/.bmp) -> PDF, one page per image.
+
+Rendered directly by Pillow (img.save(format='PDF')) — no WeasyPrint in
+this path, so image fidelity is exactly what the encoder produces.
+Transparency (RGBA/P) is flattened to RGB over white. Images wider or
+taller than MAX_DIM are downscaled proportionally to keep the PDF sane
+for e.g. 12 MP camera photos.
+
+An unopenable/corrupt file is a job error: "Invalid image: ..." (the
+contract asserts 'image' in error.lower()).
+"""
+from __future__ import annotations
+
+import io
+from pathlib import Path
+
+from PIL import Image
+
+from . import common
+
+MAX_DIM = 2000
+
+
+def convert(path: Path, job_id: str, progress_cb=None, output_dir=None,
+            source_name=None) -> str:
+    """Render a raster image to a one-page PDF."""
+    try:
+        img = Image.open(path)
+        img.load()  # force full decode: a truncated file fails here, not later
+    except Exception as exc:  # noqa: BLE001 - PIL raises many types
+        raise ValueError(f"Invalid image: {path.name} could not be opened ({exc})") from exc
+
+    if img.mode in ("RGBA", "P"):
+        bg = Image.new("RGB", img.size, (255, 255, 255))
+        if img.mode == "P":
+            img = img.convert("RGBA")
+        bg.paste(img, mask=img.getchannel("A"))
+        img = bg
+    elif img.mode != "RGB":
+        img = img.convert("RGB")
+
+    w, h = img.size
+    scale = min(1.0, MAX_DIM / max(w, h))
+    if scale < 1.0:
+        img = img.resize((max(1, int(w * scale)), max(1, int(h * scale))), Image.LANCZOS)
+
+    common.report(progress_cb, 30.0, f"Rendering {path.name} (1/1)")
+    buf = io.BytesIO()
+    img.save(buf, format="PDF")
+    out_dir = common.default_output_dir(output_dir)
+    filename = common.derive_export_name(source_name or path.name, out_dir)
+    return common.finalize_pdf(buf.getvalue(), out_dir, filename, job_id,
+                               progress_cb=progress_cb)