ocr update

tests/parser/file/test_bulk.py

@@ -628,3 +628,115 @@ class TestParserEngineSwitch:
         assert ".xhtml" in extractor
         for suffix in (".pdf", ".docx", ".csv", ".xlsx", ".html", ".xhtml", ".pptx"):
             extractor[suffix].init_parser()
+
+
+# =====================================================================
+# Gained formats (anydoc-only: legacy/macro Office, OpenDocument, RTF)
+# =====================================================================
+
+
+@pytest.mark.unit
+class TestGainedFormats:
+    def test_every_supported_extension_has_a_parser_under_both_engines(self):
+        """The invariant that keeps constants.py and the parser maps in lockstep.
+
+        Without it, an extension accepted at upload but missing from the map
+        falls to SimpleDirectoryReader's plain-text read — for a binary
+        format that means mojibake silently ingested and embedded.
+        (`.txt` is the one deliberate plain-text read.)
+        """
+        pytest.importorskip("anydoc")
+        from application.parser.file.bulk import get_default_file_extractor
+        from application.parser.file.constants import (
+            SUPPORTED_SOURCE_DOCUMENT_EXTENSIONS,
+        )
+
+        for engine in ("anydoc", "docling"):
+            extractor = get_default_file_extractor(engine=engine)
+            missing = [
+                suffix
+                for suffix in SUPPORTED_SOURCE_DOCUMENT_EXTENSIONS
+                if suffix != ".txt" and suffix not in extractor
+            ]
+            assert missing == [], (engine, missing)
+
+    def test_gained_formats_map_to_anydoc_under_both_engines(self):
+        pytest.importorskip("anydoc")
+        from application.parser.file.anydoc_parser import (
+            ANYDOC_GAINED_SUFFIXES,
+            AnydocParser,
+        )
+        from application.parser.file.bulk import get_default_file_extractor
+
+        for engine in ("anydoc", "docling"):
+            extractor = get_default_file_extractor(engine=engine)
+            for suffix in ANYDOC_GAINED_SUFFIXES:
+                assert isinstance(extractor[suffix], AnydocParser), (engine, suffix)
+
+    def test_gained_formats_never_fall_back_to_anydoc_itself(self):
+        pytest.importorskip("anydoc")
+        from application.parser.file.anydoc_parser import AnydocParser
+        from application.parser.file.bulk import get_default_file_extractor
+
+        extractor = get_default_file_extractor(engine="anydoc")
+        assert extractor[".doc"].fallback_parser is None
+        assert extractor[".rtf"].fallback_parser is None
+        # ...while the core five keep their real fallback.
+        assert extractor[".pdf"].fallback_parser is not None
+        assert not isinstance(extractor[".pdf"].fallback_parser, AnydocParser)
+
+    def test_gained_entries_absent_without_anydoc(self, monkeypatch):
+        import sys
+
+        from application.parser.file.bulk import get_default_file_extractor
+
+        monkeypatch.setitem(sys.modules, "anydoc", None)
+        extractor = get_default_file_extractor(engine="docling")
+        assert ".doc" not in extractor  # degrades to the pre-anydoc map
+
+    def test_rtf_converts_end_to_end(self, tmp_path):
+        pytest.importorskip("anydoc")
+        from application.parser.file.bulk import get_default_file_extractor
+
+        path = tmp_path / "note.rtf"
+        path.write_text(r"{\rtf1\ansi Hello {\b bold} world.\par Second paragraph.}")
+        parser = get_default_file_extractor()[".rtf"]
+        parser.init_parser()
+
+        out = parser.parse_file(path)
+
+        assert "Hello **bold** world." in out
+        assert "Second paragraph." in out
+
+    def test_odt_converts_end_to_end(self, tmp_path):
+        pytest.importorskip("anydoc")
+        import zipfile
+
+        from application.parser.file.bulk import get_default_file_extractor
+
+        path = tmp_path / "doc.odt"
+        with zipfile.ZipFile(path, "w") as z:
+            z.writestr(
+                "mimetype",
+                "application/vnd.oasis.opendocument.text",
+                compress_type=zipfile.ZIP_STORED,
+            )
+            z.writestr(
+                "META-INF/manifest.xml",
+                '<?xml version="1.0"?><manifest:manifest xmlns:manifest="urn:oasis:names:tc:opendocument:xmlns:manifest:1.0">'
+                '<manifest:file-entry manifest:full-path="/" manifest:media-type="application/vnd.oasis.opendocument.text"/>'
+                '<manifest:file-entry manifest:full-path="content.xml" manifest:media-type="text/xml"/></manifest:manifest>',
+            )
+            z.writestr(
+                "content.xml",
+                '<?xml version="1.0"?><office:document-content xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" '
+                'xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0"><office:body><office:text>'
+                '<text:h text:outline-level="1">Title</text:h><text:p>Body text here.</text:p>'
+                "</office:text></office:body></office:document-content>",
+            )
+        parser = get_default_file_extractor()[".odt"]
+
+        out = parser.parse_file(path)
+
+        assert "# Title" in out
+        assert "Body text here." in out