~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Python academiaanthropicarxivbravedeep-researchencryptionhome-automationhomeserverlocallocal-deep-researchlocal-llmmistralollamaopenaipubmedresearchresearch-toolretrieval-augmented-generationsearxngself-hosted
"""
Full coverage tests for document_loaders/loader_registry.py.
Targets uncovered paths:
- get_loader_for_path: unsupported extension returns None
- Conditional registry entries (HAS_ODT_LOADER, etc.)
- get_supported_extensions returns correct list
"""
class TestGetLoaderForPathUnsupported:
"""Cover get_loader_for_path with unsupported extensions."""
def test_unsupported_extension_returns_none(self, tmp_path):
"""Returns None for file with unsupported extension."""
from local_deep_research.document_loaders.loader_registry import (
get_loader_for_path,
)
f = tmp_path / "data.xyz123"
f.write_text("content")
result = get_loader_for_path(f)
assert result is None
def test_no_extension_returns_none(self, tmp_path):
"""Returns None for file with no extension."""
from local_deep_research.document_loaders.loader_registry import (
get_loader_for_path,
)
f = tmp_path / "Makefile"
f.write_text("all: build")
result = get_loader_for_path(f)
assert result is None
def test_string_path_input(self, tmp_path):
"""Accepts string path input."""
from local_deep_research.document_loaders.loader_registry import (
get_loader_for_path,
)
f = tmp_path / "test.txt"
f.write_text("hello")
result = get_loader_for_path(str(f))
assert result is not None
class TestGetSupportedExtensions:
"""Cover get_supported_extensions."""
def test_returns_list_of_strings(self):
from local_deep_research.document_loaders.loader_registry import (
get_supported_extensions,
)
extensions = get_supported_extensions()
assert isinstance(extensions, list)
assert all(isinstance(e, str) for e in extensions)
assert all(e.startswith(".") for e in extensions)
def test_contains_required_extensions(self):
from local_deep_research.document_loaders.loader_registry import (
get_supported_extensions,
)
extensions = get_supported_extensions()
for required in [".pdf", ".txt", ".md", ".csv", ".json", ".yaml"]:
assert required in extensions
class TestConditionalLoaderRegistration:
"""Test conditional loader registration flags."""
def test_odt_loader_flag_is_bool(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_ODT_LOADER,
)
assert isinstance(HAS_ODT_LOADER, bool)
def test_epub_loader_flag_is_bool(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_EPUB_LOADER,
)
assert isinstance(HAS_EPUB_LOADER, bool)
def test_rtf_loader_flag_is_bool(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_RTF_LOADER,
)
assert isinstance(HAS_RTF_LOADER, bool)
def test_rst_loader_flag_is_bool(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_RST_LOADER,
)
assert isinstance(HAS_RST_LOADER, bool)
def test_org_loader_flag_is_bool(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_ORG_LOADER,
)
assert isinstance(HAS_ORG_LOADER, bool)
def test_image_loader_flag_is_bool(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_IMAGE_LOADER,
)
assert isinstance(HAS_IMAGE_LOADER, bool)
def test_odt_in_registry_iff_flag_and_dep(self):
# ODT uploads convert through the bounded pandoc wrapper, so ODT
# is gated on the pandoc bridge like EPUB/RTF/RST/Org.
from local_deep_research.document_loaders.loader_registry import (
HAS_ODT_LOADER,
HAS_PANDOC_DEP,
LOADER_REGISTRY,
)
assert (".odt" in LOADER_REGISTRY) == (
HAS_ODT_LOADER and HAS_PANDOC_DEP
)
def test_epub_in_registry_iff_flag_and_dep(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_EPUB_LOADER,
HAS_PANDOC_DEP,
LOADER_REGISTRY,
)
assert (".epub" in LOADER_REGISTRY) == (
HAS_EPUB_LOADER and HAS_PANDOC_DEP
)
def test_rtf_in_registry_iff_flag_and_dep(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_PANDOC_DEP,
HAS_RTF_LOADER,
LOADER_REGISTRY,
)
assert (".rtf" in LOADER_REGISTRY) == (
HAS_RTF_LOADER and HAS_PANDOC_DEP
)
def test_rst_in_registry_iff_flag_and_dep(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_PANDOC_DEP,
HAS_RST_LOADER,
LOADER_REGISTRY,
)
assert (".rst" in LOADER_REGISTRY) == (
HAS_RST_LOADER and HAS_PANDOC_DEP
)
def test_org_in_registry_iff_flag_and_dep(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_ORG_LOADER,
HAS_PANDOC_DEP,
LOADER_REGISTRY,
)
assert (".org" in LOADER_REGISTRY) == (
HAS_ORG_LOADER and HAS_PANDOC_DEP
)
def test_image_extensions_in_registry_iff_flag_and_dep(self):
from local_deep_research.document_loaders.loader_registry import (
HAS_IMAGE_LOADER,
HAS_OCR_DEP,
LOADER_REGISTRY,
)
image_exts = [".png", ".jpg", ".jpeg", ".tiff", ".tif", ".bmp", ".heic"]
for ext in image_exts:
assert (ext in LOADER_REGISTRY) == (
HAS_IMAGE_LOADER and HAS_OCR_DEP
)
class TestIsExtensionSupportedCaseInsensitive:
"""Cover case-insensitive extension checking."""
def test_uppercase_with_dot(self):
from local_deep_research.document_loaders.loader_registry import (
is_extension_supported,
)
assert is_extension_supported(".PDF") is True
def test_mixed_case_without_dot(self):
from local_deep_research.document_loaders.loader_registry import (
is_extension_supported,
)
assert is_extension_supported("Html") is True
def test_uppercase_json(self):
from local_deep_research.document_loaders.loader_registry import (
is_extension_supported,
)
assert is_extension_supported(".JSON") is True