Inspect static PDF and OOXML content with bounded local coverage

apps/inspector/engine.py

@@ -200,51 +200,12 @@ def extract(data, kind):
         text,complete=ocr_image(data)
         return text,complete,[("image",data)]
     if kind=="pdf":
-        from pypdf import PdfReader
-        reader=PdfReader(io.BytesIO(data),strict=True)
-        if reader.is_encrypted: raise ValueError("Encrypted PDF cannot be inspected")
-        if len(reader.pages)>100: raise ValueError("PDF page budget exceeded")
-        text=[];complete=True;media=[]
-        for page in reader.pages:
-            value=page.extract_text() or ""
-            text.append(value)
-            images=list(page.images)
-            if not value.strip() and not images: complete=False
-            for image in images:
-                if len(image.data)>MAX_BYTES: raise ValueError("PDF image budget exceeded")
-                scanned,ok=ocr_image(image.data);text.append(scanned);complete=complete and ok
-                media.append(("image",image.data))
-                if len(media)>100: raise ValueError("PDF media budget exceeded")
-            # Attachments, JavaScript, forms, actions and vector drawings need deeper inspection.
-            if page.get("/Annots"): complete=False
-        root=reader.trailer["/Root"]
-        if root.get("/AcroForm") or root.get("/OpenAction") or root.get("/Names"): complete=False
-        # Text extraction is useful, but does not prove all visible/vector PDF content was covered.
-        return "\n".join(text),False,media
+        from pdf_documents import extract_pdf
+        return extract_pdf(data, ocr_image)
     if kind=="office":
-        from defusedxml.ElementTree import fromstring
-        text=[];media=[];complete=True
-        with zipfile.ZipFile(io.BytesIO(data)) as archive:
-            members=archive.infolist()
-            if len(members)>2000 or sum(x.file_size for x in members)>MAX_BYTES:
-                raise ValueError("Archive expansion budget exceeded")
-            if not any(x.filename in ["word/document.xml","ppt/presentation.xml","xl/workbook.xml"] for x in members):
-                raise ValueError("Only OOXML document archives are supported")
-            for entry in members:
-                if entry.flag_bits&1 or entry.file_size>MAX_BYTES or entry.file_size>max(entry.compress_size,1)*200:
-                    raise ValueError("Unsafe document archive")
-                name=entry.filename
-                if any(s in name.lower() for s in ["vbaproject","embeddings/","activex/","customxml/"]): complete=False
-                if name.endswith(".xml"):
-                    root=fromstring(archive.read(entry))
-                    text.extend(element.text for element in root.iter() if element.tag.rsplit("}",1)[-1] in ["t","v"] and element.text)
-                elif "/media/" in name:
-                    payload=archive.read(entry)
-                    if content_kind(payload)!="image": complete=False; continue
-                    scanned,ok=ocr_image(payload);text.append(scanned);complete=complete and ok;media.append(("image",payload))
-                    if len(media)>100: raise ValueError("Office media budget exceeded")
-        # Charts, relationships, equations and rendered layout are not yet fully inspected.
-        return "\n".join(text),False,media
+        from office_content import extract_office
+        result=extract_office(data,ocr_image,max_bytes=MAX_BYTES)
+        return result["text"],result["complete"],result["media"]
     if kind in ["audio","video"]: return "",False,[(kind,data)]
     raise ValueError("Unsupported content type")