feat(cv-import): add source-grounded review and explicit corrections

tools/summarizer/parser_child.py

@@ -242,6 +242,10 @@ def _validate_import_docx(data: bytes) -> None:
                         if node.tag.rsplit("}", 1)[-1] in {"altChunk", "OLEObject", "object"}:
                             raise ParserError("external_content")
                         if node.attrib.get("TargetMode", "").lower() == "external":
+                            # Hyperlinks are inert source data; converters cannot follow them in the sandbox.
+                            from urllib.parse import urlsplit
+                            if node.attrib.get("Type", "").endswith("/hyperlink") and urlsplit(node.attrib.get("Target", "")).scheme.lower() in {"http", "https", "mailto"}:
+                                continue
                             raise ParserError("external_content")
                         target = node.attrib.get("Target", "")
                         if ":" in target or "\\" in target or target.startswith("/"):
@@ -265,7 +269,7 @@ def _validate_import_pdf(data: bytes) -> int:
         count = len(reader.pages)
         if count > MAX_PDF_PAGES:
             raise ParserError("pdf_page_limit")
-        forbidden = {"/OpenAction", "/AA", "/JS", "/JavaScript", "/Launch", "/GoToR", "/URI", "/SubmitForm", "/ImportData", "/EmbeddedFiles", "/Filespec", "/RichMedia", "/XFA"}
+        forbidden = {"/OpenAction", "/AA", "/JS", "/JavaScript", "/Launch", "/GoToR", "/SubmitForm", "/ImportData", "/EmbeddedFiles", "/Filespec", "/RichMedia", "/XFA"}
         pending = [(reader.trailer, 0)]
         seen: set[int] = set()
         while pending:
@@ -278,6 +282,9 @@ def _validate_import_pdf(data: bytes) -> int:
             if depth > 40 or len(seen) > 10_000:
                 raise ParserError("pdf_object_limit")
             if isinstance(value, DictionaryObject):
+                from urllib.parse import urlsplit
+                if "/URI" in value and urlsplit(str(value["/URI"])).scheme.lower() not in {"http", "https", "mailto"}:
+                    raise ParserError("external_content")
                 if forbidden.intersection(value) or str(value.get("/S", "")) in forbidden or str(value.get("/Type", "")) in forbidden:
                     raise ParserError("external_content")
                 pending.extend((item, depth + 1) for item in value.values())