mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
Addresses items 9-13 and a/b/c/f from the max-effort review of PR #272. - pdf.py: image colorspace check was `pix.n > 4`, which treats CMYK-without- alpha (n==4, same as RGBA) as not needing RGB conversion; pix.save() as .png then raises "unsupported colorspace", silently dropped by the surrounding except. Fixed to `pix.n - pix.alpha >= 4` (correctly converts CMYK, leaves RGBA untouched). - pipeline.py: detect_strategy([]) (an empty/whitespace-only source file) returned "content_based", routing into the PDF-oriented TOC-detection pipeline -- wasting a real LLM call before raising IndexingError. Empty node lists now route to level_based, whose build_tree_from_levels([]) returns an empty structure instantly with zero LLM calls. - page_index.py (shim): pageindex/__init__.py binds the canonical `page_index` function as the package attribute, but this file is ALSO a real submodule of the same name -- importing it anywhere (import machinery, unconditional) overwrites that attribute with the module object, breaking `from pageindex import page_index; page_index(x)` for the rest of the process. Made the shim module itself callable (delegates to the real function via a ModuleType subclass), so whichever object ends up in that slot is callable regardless of import order. - storage/sqlite.py: create_collection let a raw sqlite3.IntegrityError escape on a duplicate name (new CollectionAlreadyExistsError); the collections table's CHECK constraint only validated the name's first character (GLOB '*' is a wildcard, not a regex quantifier over the preceding class) -- fixed to validate the whole string, and SQLiteStorage now also validates in Python (it's a public StorageEngine usable directly, bypassing LocalBackend's own check). - tests/test_review_fixes_2.py: two tests used a ContentNode with no `level` set, so build_index took the content_based path and made real (retried, slow, and -- with a valid key -- billable) LLM calls instead of testing the text-stripping logic they claimed to. Mocked out _content_based_pipeline. - retrieve.py: _parse_pages/_get_pdf_page_content were independent copies of the canonical parse_pages/get_pdf_page_content that had already drifted (missing the p>=1 filter and 1000-page DoS cap) -- delegate to canonical now, so the legacy pageindex.get_page_content path can't silently regress again. - parser/markdown.py: a leading UTF-8 BOM broke first-header detection (not whitespace, .strip() doesn't remove it) -- decode utf-8-sig. Only backtick fences were recognized as code blocks, so a '#'-prefixed line inside a ~~~-fenced block (valid CommonMark) was misparsed as a heading -- recognize both fence styles. - run_pageindex.py: --if-thinning wasn't migrated to the bare-flag + legacy-yes/no convention the other four --if-add-* flags got; bare usage raised an argparse error and it never went through the shared coercion. - types.py: DocumentDetail's `structure` field was inside the class's total=False body, so TypedDict rules made it optional even though every backend always populates it. Split into a required base class. Adds regression tests for all of the above. Full suite: 244 passed, 2 skipped (one pre-existing, unrelated flaky cloud-streaming test). Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
147 lines
6 KiB
Python
147 lines
6 KiB
Python
"""The top-level pageindex.page_index / .page_index_md / .utils modules are
|
|
now deprecation shims over the canonical pageindex.index.* modules. These
|
|
tests pin the compatibility contract."""
|
|
import asyncio
|
|
import importlib
|
|
import subprocess
|
|
import sys
|
|
import warnings
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
_REPO_ROOT = Path(__file__).resolve().parent.parent
|
|
|
|
|
|
def test_plain_import_pageindex_does_not_warn():
|
|
# `import pageindex` must not route through the deprecation shims.
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("error", PendingDeprecationWarning)
|
|
importlib.import_module("pageindex")
|
|
|
|
|
|
@pytest.mark.parametrize("mod", [
|
|
"pageindex.utils",
|
|
"pageindex.page_index",
|
|
"pageindex.page_index_md",
|
|
])
|
|
def test_legacy_submodule_import_warns(mod):
|
|
with warnings.catch_warnings(record=True) as caught:
|
|
warnings.simplefilter("always")
|
|
importlib.reload(importlib.import_module(mod))
|
|
assert any(issubclass(w.category, PendingDeprecationWarning) for w in caught)
|
|
|
|
|
|
def test_legacy_symbols_resolve_through_shims():
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("ignore")
|
|
from pageindex.utils import ( # noqa: F401
|
|
get_page_tokens, ConfigLoader, convert_page_to_int,
|
|
get_leaf_nodes, remove_fields,
|
|
)
|
|
from pageindex.page_index import page_index, page_index_main # noqa: F401
|
|
from pageindex.page_index_md import md_to_tree # noqa: F401
|
|
|
|
|
|
def test_canonical_and_shim_share_one_implementation():
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("ignore")
|
|
import pageindex.utils as shim
|
|
import pageindex.index.utils as canonical
|
|
# Same function object -> a single source of truth (no divergence possible).
|
|
assert shim.get_leaf_nodes is canonical.get_leaf_nodes
|
|
assert shim.get_page_tokens is canonical.get_page_tokens
|
|
|
|
|
|
def test_get_leaf_nodes_has_331_fix():
|
|
"""Canonical get_leaf_nodes must use .get('nodes'); clean_node deletes the
|
|
key on leaf nodes so [...]['nodes'] would KeyError (issue #330)."""
|
|
from pageindex.index.utils import get_leaf_nodes
|
|
# A leaf node with the 'nodes' key deleted (as clean_node leaves it).
|
|
leaves = get_leaf_nodes({"title": "Leaf", "start_index": 1, "end_index": 2})
|
|
assert leaves == [{"title": "Leaf", "start_index": 1, "end_index": 2}]
|
|
|
|
|
|
def test_configloader_no_longer_needs_config_yaml():
|
|
"""config.yaml was removed; ConfigLoader must build defaults from IndexConfig."""
|
|
from pageindex.index.utils import ConfigLoader
|
|
cfg = ConfigLoader().load({"model": "gpt-5.4"})
|
|
assert cfg.model == "gpt-5.4"
|
|
assert cfg.if_add_node_summary is True # IndexConfig default
|
|
with pytest.raises(ValueError, match="Unknown config keys"):
|
|
ConfigLoader().load({"nope": 1})
|
|
|
|
|
|
def test_configloader_coerces_legacy_yes_no_strings():
|
|
"""A legacy caller passing 'no' must get a real False, not a truthy
|
|
string — page_index_main's `if opt.if_add_node_summary:` checks (bare
|
|
truthy, not `== 'yes'`) would otherwise silently invert caller intent and
|
|
fire unwanted billed LLM calls."""
|
|
from pageindex.index.utils import ConfigLoader
|
|
cfg = ConfigLoader().load({"if_add_node_summary": "no", "if_add_doc_description": "no"})
|
|
assert cfg.if_add_node_summary is False
|
|
assert cfg.if_add_doc_description is False
|
|
assert bool(cfg.if_add_node_summary) is False
|
|
|
|
cfg2 = ConfigLoader().load({"if_add_node_id": "yes"})
|
|
assert cfg2.if_add_node_id is True
|
|
|
|
|
|
def test_md_to_tree_shim_is_the_canonical_function():
|
|
"""The shim no longer wraps md_to_tree with its own coercion — the
|
|
canonical implementation coerces internally, so the shim is a pure
|
|
re-export (single source of truth, can't diverge from the canonical
|
|
behavior)."""
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("ignore")
|
|
import pageindex.page_index_md as shim
|
|
import pageindex.index.page_index_md as canonical
|
|
assert shim.md_to_tree is canonical.md_to_tree
|
|
|
|
|
|
def test_md_to_tree_coerces_legacy_yes_no_strings(tmp_path):
|
|
"""A bare 'no' must not read as truthy True — exercised end-to-end (no
|
|
LLM calls needed with summary/description disabled)."""
|
|
from pageindex.index.page_index_md import md_to_tree
|
|
|
|
md_path = tmp_path / "doc.md"
|
|
md_path.write_text("# Title\nbody\n\n## Sub\nmore body\n")
|
|
|
|
result = asyncio.run(md_to_tree(
|
|
md_path=str(md_path),
|
|
if_add_node_summary="no",
|
|
if_add_node_id="yes",
|
|
if_add_doc_description="no",
|
|
))
|
|
assert "doc_description" not in result
|
|
|
|
def _has_summary(nodes):
|
|
return any("summary" in n or (n.get("nodes") and _has_summary(n["nodes"]))
|
|
for n in nodes)
|
|
|
|
assert not _has_summary(result["structure"])
|
|
assert all("node_id" in n for n in result["structure"])
|
|
|
|
|
|
def test_page_index_stays_callable_after_the_submodule_is_imported():
|
|
"""pageindex/__init__.py binds the FUNCTION `page_index` as the package
|
|
attribute, but pageindex/page_index.py is ALSO a real submodule of the
|
|
same name — importing that submodule anywhere clobbers the package
|
|
attribute with the module object (Python's import machinery does this
|
|
unconditionally). Must run in a fresh subprocess: the effect depends on
|
|
import order, so it can't be reliably observed against an
|
|
already-imported pageindex in this test process."""
|
|
script = (
|
|
"import warnings; warnings.simplefilter('ignore')\n"
|
|
"import pageindex.page_index\n" # the clobbering import
|
|
"from pageindex import page_index\n"
|
|
"assert callable(page_index), f'page_index is not callable: {type(page_index)}'\n"
|
|
"from pageindex.page_index import page_index_main\n" # old multi-symbol import still works
|
|
"assert callable(page_index_main)\n"
|
|
"print('OK')\n"
|
|
)
|
|
result = subprocess.run(
|
|
[sys.executable, "-c", script], capture_output=True, text=True, cwd=str(_REPO_ROOT),
|
|
)
|
|
assert result.returncode == 0, result.stderr
|
|
assert "OK" in result.stdout
|