Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
fix(ci): align MHTML API and suffix checks
myhloli70725915a534
diff --git a/mineru/backend/analysis/mhtml.py b/mineru/backend/analysis/mhtml.pyindex b073293e..9ef036b4 100644--- a/mineru/backend/analysis/mhtml.py+++ b/mineru/backend/analysis/mhtml.py@@ -1,3 +1,4 @@+# Copyright (c) Opendatalab. All rights reserved."""MHTML 文档的 DocVortex 原生分析适配。"""from __future__ import annotationsdiff --git a/tests/unittest/test_docvortex_import_boundary.py b/tests/unittest/test_docvortex_import_boundary.pyindex 81b52eb4..36ed67fb 100644--- a/tests/unittest/test_docvortex_import_boundary.py+++ b/tests/unittest/test_docvortex_import_boundary.py@@ -6,8 +6,13 @@ import astfrom pathlib import Pathimport pytest+from docvortex.document.mhtml import __all__ as MHTML_EXPORTSfrom docvortex.public_api import PUBLIC_API+# DocVortex 0.4.24 已通过模块 __all__ 导出归档接口,公开清单将在后续版本同步。+_DECLARED_API = dict(PUBLIC_API)+_DECLARED_API.setdefault("docvortex.document.mhtml", tuple(MHTML_EXPORTS))+def _dotted_name(node: ast.AST) -> str:"""读取静态属性链,函数调用和下标表达式不冒充模块路径。"""@@ -28,7 +33,7 @@ def _check_source(source: str, *, model_layer: bool = False) -> list[str]:def check_module(module: str, line: int) -> None:"""按公开清单和宿主层级校验模块依赖。"""- if module not in PUBLIC_API:+ if module not in _DECLARED_API:errors.append(f"{line}: undeclared module {module}")if model_layer and module not in model_modules:errors.append(f"{line}: model layer cannot import {module}")@@ -38,10 +43,10 @@ def _check_source(source: str, *, model_layer: bool = False) -> list[str]:module = node.module or ""check_module(module, node.lineno)for alias in node.names:- if alias.name not in PUBLIC_API.get(module, ()):+ if alias.name not in _DECLARED_API.get(module, ()):errors.append(f"{node.lineno}: undeclared symbol {module}.{alias.name}")target = f"{module}.{alias.name}"- if target in PUBLIC_API:+ if target in _DECLARED_API:aliases[alias.asname or alias.name] = targetelif isinstance(node, ast.Import):for alias in node.names:@@ -62,10 +67,10 @@ def _check_source(source: str, *, model_layer: bool = False) -> list[str]:if root not in aliases:continuequalified = f"{aliases[root]}.{suffix}"- if qualified in PUBLIC_API:+ if qualified in _DECLARED_API:continuemodule, _, symbol = qualified.rpartition(".")- if module in PUBLIC_API and symbol not in PUBLIC_API[module]:+ if module in _DECLARED_API and symbol not in _DECLARED_API[module]:errors.append(f"{node.lineno}: undeclared member {qualified}")return errors@@ -92,6 +97,7 @@ def test_mineru_uses_declared_docvortex_api() -> None:"from docvortex.document import page_range as ranges\nranges.unknown()","import docvortex\ndocvortex.foundation._geometry.normalize_to_int_bbox([])","import importlib\nimportlib.import_module('docvortex.foundation._geometry')",+ "from docvortex.document.mhtml import unknown",],)def test_guard_rejects_unpublished_imports(source: str) -> None:diff --git a/tests/unittest/test_pdf_analyze_visual_blocks.py b/tests/unittest/test_pdf_analyze_visual_blocks.pyindex e555e6c7..5517746e 100644--- a/tests/unittest/test_pdf_analyze_visual_blocks.py+++ b/tests/unittest/test_pdf_analyze_visual_blocks.py@@ -1097,6 +1097,7 @@ def test_doc_analyze_effort_annotation_exposes_only_supported_values() -> None:"tsv","epub","html",+ "mhtml","ofd","odt","ods",