feat(data_process): 显式关闭 docling OCR 并拒绝无文本层 PDF
- docling 转换器通过 PdfPipelineOptions 显式设置 do_ocr=False, 混合 PDF 的图片页不再产出 OCR 文字;不提供重新开启 OCR 的参数。 - 无文本层 PDF 的错误文案改为"扫描版或图片型 PDF 不支持", 上传阶段整批拒绝,保留混合 PDF 的可处理判定。 - 新增 test_layout_converter_disables_ocr 守护开关状态, 同步设计文档与 disable-ocr 实施计划/设计说明。
This commit is contained in:
@@ -104,7 +104,9 @@ def extract_pdf_page_texts(raw: bytes) -> tuple[PdfPageText, ...]:
|
|||||||
)
|
)
|
||||||
has_text = True
|
has_text = True
|
||||||
if not has_text:
|
if not has_text:
|
||||||
raise ValueError("PDF contains no extractable text; scanned PDF requires OCR")
|
raise ValueError(
|
||||||
|
"PDF contains no extractable text; scanned or image-only PDF files are not supported"
|
||||||
|
)
|
||||||
return tuple(pages)
|
return tuple(pages)
|
||||||
|
|
||||||
def _pdf_page_lines(page: PdfPageText) -> tuple[_PdfLine, ...]:
|
def _pdf_page_lines(page: PdfPageText) -> tuple[_PdfLine, ...]:
|
||||||
|
|||||||
@@ -262,9 +262,17 @@ def _make_text_chunk(source: str, start: int, end: int) -> DocumentChunk:
|
|||||||
|
|
||||||
@lru_cache(maxsize=1)
|
@lru_cache(maxsize=1)
|
||||||
def _document_converter():
|
def _document_converter():
|
||||||
from docling.document_converter import DocumentConverter
|
from docling.datamodel.base_models import InputFormat
|
||||||
|
from docling.datamodel.pipeline_options import PdfPipelineOptions
|
||||||
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
||||||
|
|
||||||
return DocumentConverter()
|
pipeline_options = PdfPipelineOptions()
|
||||||
|
pipeline_options.do_ocr = False
|
||||||
|
return DocumentConverter(
|
||||||
|
format_options={
|
||||||
|
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class _MarkdownSerializerProvider(ChunkingSerializerProvider):
|
class _MarkdownSerializerProvider(ChunkingSerializerProvider):
|
||||||
|
|||||||
@@ -654,7 +654,10 @@ def test_office_zip_bomb_and_invalid_pdf_are_rejected_before_parsing() -> None:
|
|||||||
blank_writer = PdfWriter()
|
blank_writer = PdfWriter()
|
||||||
blank_writer.add_blank_page(width=612, height=792)
|
blank_writer.add_blank_page(width=612, height=792)
|
||||||
blank_writer.write(blank_pdf)
|
blank_writer.write(blank_pdf)
|
||||||
with pytest.raises(ValueError, match="scanned PDF requires OCR"):
|
with pytest.raises(
|
||||||
|
ValueError,
|
||||||
|
match="scanned or image-only PDF files are not supported",
|
||||||
|
):
|
||||||
parse_text_content(blank_pdf.getvalue(), filename="scanned.pdf")
|
parse_text_content(blank_pdf.getvalue(), filename="scanned.pdf")
|
||||||
|
|
||||||
aes_pdf_without_open_password = parse_text_content(
|
aes_pdf_without_open_password = parse_text_content(
|
||||||
|
|||||||
@@ -1,10 +1,14 @@
|
|||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import sys
|
||||||
|
from types import ModuleType, SimpleNamespace
|
||||||
|
|
||||||
from llama_index.core.embeddings import MockEmbedding
|
from llama_index.core.embeddings import MockEmbedding
|
||||||
|
|
||||||
from app.modules.data_process.document_chunking import (
|
from app.modules.data_process.document_chunking import (
|
||||||
DocumentChunk,
|
DocumentChunk,
|
||||||
_compact_with_offsets,
|
_compact_with_offsets,
|
||||||
|
_document_converter,
|
||||||
_project_layout_span,
|
_project_layout_span,
|
||||||
chunk_fixed_text,
|
chunk_fixed_text,
|
||||||
chunk_semantic_text,
|
chunk_semantic_text,
|
||||||
@@ -42,6 +46,48 @@ def test_semantic_splitter_uses_llamaindex_and_reapplies_maximum_size() -> None:
|
|||||||
assert "".join(chunk.original_content for chunk in chunks) == text
|
assert "".join(chunk.original_content for chunk in chunks) == text
|
||||||
|
|
||||||
|
|
||||||
|
def test_layout_converter_disables_ocr(monkeypatch) -> None:
|
||||||
|
class FakePipelineOptions:
|
||||||
|
def __init__(self) -> None:
|
||||||
|
self.do_ocr = True
|
||||||
|
|
||||||
|
class FakePdfFormatOption:
|
||||||
|
def __init__(self, *, pipeline_options) -> None:
|
||||||
|
self.pipeline_options = pipeline_options
|
||||||
|
|
||||||
|
class FakeDocumentConverter:
|
||||||
|
def __init__(self, *, format_options) -> None:
|
||||||
|
self.format_options = format_options
|
||||||
|
|
||||||
|
docling_module = ModuleType("docling")
|
||||||
|
docling_module.__path__ = []
|
||||||
|
document_converter_module = ModuleType("docling.document_converter")
|
||||||
|
document_converter_module.DocumentConverter = FakeDocumentConverter
|
||||||
|
document_converter_module.PdfFormatOption = FakePdfFormatOption
|
||||||
|
datamodel_module = ModuleType("docling.datamodel")
|
||||||
|
datamodel_module.__path__ = []
|
||||||
|
base_models_module = ModuleType("docling.datamodel.base_models")
|
||||||
|
base_models_module.InputFormat = SimpleNamespace(PDF="pdf")
|
||||||
|
pipeline_options_module = ModuleType("docling.datamodel.pipeline_options")
|
||||||
|
pipeline_options_module.PdfPipelineOptions = FakePipelineOptions
|
||||||
|
for name, module in {
|
||||||
|
"docling": docling_module,
|
||||||
|
"docling.document_converter": document_converter_module,
|
||||||
|
"docling.datamodel": datamodel_module,
|
||||||
|
"docling.datamodel.base_models": base_models_module,
|
||||||
|
"docling.datamodel.pipeline_options": pipeline_options_module,
|
||||||
|
}.items():
|
||||||
|
monkeypatch.setitem(sys.modules, name, module)
|
||||||
|
|
||||||
|
_document_converter.cache_clear()
|
||||||
|
try:
|
||||||
|
converter = _document_converter()
|
||||||
|
options = converter.format_options["pdf"].pipeline_options
|
||||||
|
assert options.do_ocr is False
|
||||||
|
finally:
|
||||||
|
_document_converter.cache_clear()
|
||||||
|
|
||||||
|
|
||||||
def test_layout_projection_ignores_layout_whitespace_but_keeps_source_lines() -> None:
|
def test_layout_projection_ignores_layout_whitespace_but_keeps_source_lines() -> None:
|
||||||
source = "标题\n第一条 这是正文。\n第二条 后续正文。"
|
source = "标题\n第一条 这是正文。\n第二条 后续正文。"
|
||||||
compact_source, offsets = _compact_with_offsets(source)
|
compact_source, offsets = _compact_with_offsets(source)
|
||||||
|
|||||||
@@ -118,7 +118,7 @@ pending ──start/generate──> running ──success──> completed
|
|||||||
抽取幻灯片文本与表格,随后统一进入切片算法。
|
抽取幻灯片文本与表格,随后统一进入切片算法。
|
||||||
- 旧版二进制 DOC、XLS、PPT 不直接解析,返回 415 并提示分别转换为
|
- 旧版二进制 DOC、XLS、PPT 不直接解析,返回 415 并提示分别转换为
|
||||||
DOCX、XLSX、PPTX。
|
DOCX、XLSX、PPTX。
|
||||||
- 扫描 PDF 没有文本层时明确提示需要 OCR;当前流程不执行 OCR。加密、损坏或
|
- 扫描 PDF 没有文本层时明确提示扫描版或图片型 PDF 不支持。加密、损坏或
|
||||||
超出页数/工作表/行列/解压规模限制的文件整批拒绝。
|
超出页数/工作表/行列/解压规模限制的文件整批拒绝。
|
||||||
|
|
||||||
现代 Office 文件在交给解析库前检查 ZIP 成员路径、重复成员、加密标记、活动
|
现代 Office 文件在交给解析库前检查 ZIP 成员路径、重复成员、加密标记、活动
|
||||||
|
|||||||
204
docs/superpowers/plans/2026-08-18-disable-ocr.md
Normal file
204
docs/superpowers/plans/2026-08-18-disable-ocr.md
Normal file
@@ -0,0 +1,204 @@
|
|||||||
|
# 屏蔽数据处理 OCR 能力实施计划
|
||||||
|
|
||||||
|
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||||
|
|
||||||
|
**Goal:** 在保留 Docling 版面分析和 `layout_hybrid` 的前提下,显式关闭 PDF pipeline 的 OCR,并拒绝无文本层 PDF。
|
||||||
|
|
||||||
|
**Architecture:** 只修改 `document_chunking.py` 中的 Docling converter 构造,使 PDF 使用 `PdfPipelineOptions(do_ocr=False)`;不修改切分方式、依赖、前端配置或版面 chunker。pypdf 继续负责上传阶段文本提取和扫描 PDF 边界判断。
|
||||||
|
|
||||||
|
**Tech Stack:** Python 3.12、FastAPI、pypdf、Docling 2.115.0、LlamaIndex、pytest、Ruff、Vue 3、Node 回归脚本。
|
||||||
|
|
||||||
|
## Global Constraints
|
||||||
|
|
||||||
|
- 必须保留 `layout_hybrid`、Docling 版面分析和现有前端切分选项。
|
||||||
|
- 只能关闭 OCR,不删除 Docling、版面/表格分析、PDF 页码映射或普通切分。
|
||||||
|
- 纯扫描/图片型 PDF 明确拒绝;混合 PDF 保留,图片页不产生文字。
|
||||||
|
- 不新增 OCR 开关,不提供重新开启 OCR 的参数或环境变量。
|
||||||
|
- 不修改 `.codex-tmp/` 和 `outputs/` 等既有未跟踪用户文件。
|
||||||
|
- 不执行 `git commit`;提交前必须取得用户明确确认。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Task 1: 显式关闭 Docling PDF OCR
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Modify: `backend/app/modules/data_process/document_chunking.py:261-265`
|
||||||
|
- Test: `backend/tests/test_document_chunking.py`
|
||||||
|
|
||||||
|
**Interfaces:**
|
||||||
|
- `_document_converter()` 保持无参数、缓存和返回 `DocumentConverter` 的现有接口。
|
||||||
|
- PDF 的 `PdfFormatOption` 必须收到 `pipeline_options.do_ocr is False`。
|
||||||
|
|
||||||
|
- [ ] **Step 1: Add a failing configuration test**
|
||||||
|
|
||||||
|
在 `backend/tests/test_document_chunking.py` 导入 `_document_converter`、`sys`、`ModuleType` 和 `SimpleNamespace`,添加使用假的 Docling 模块的测试:
|
||||||
|
|
||||||
|
```python
|
||||||
|
def test_layout_converter_disables_ocr(monkeypatch) -> None:
|
||||||
|
class FakePipelineOptions:
|
||||||
|
def __init__(self) -> None:
|
||||||
|
self.do_ocr = True
|
||||||
|
|
||||||
|
class FakePdfFormatOption:
|
||||||
|
def __init__(self, *, pipeline_options) -> None:
|
||||||
|
self.pipeline_options = pipeline_options
|
||||||
|
|
||||||
|
class FakeDocumentConverter:
|
||||||
|
def __init__(self, *, format_options) -> None:
|
||||||
|
self.format_options = format_options
|
||||||
|
|
||||||
|
# 将这些 fake 类注册到 docling.document_converter、
|
||||||
|
# docling.datamodel.base_models 和 docling.datamodel.pipeline_options。
|
||||||
|
# 调用 _document_converter 后断言:
|
||||||
|
_document_converter.cache_clear()
|
||||||
|
converter = _document_converter()
|
||||||
|
assert converter.format_options["pdf"].pipeline_options.do_ocr is False
|
||||||
|
_document_converter.cache_clear()
|
||||||
|
```
|
||||||
|
|
||||||
|
测试保留现有版面投影和 provenance 测试,证明本任务不是删除版面分析。
|
||||||
|
|
||||||
|
- [ ] **Step 2: Run the new test before implementation**
|
||||||
|
|
||||||
|
Run:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd backend && PYTHONPATH=. .venv/bin/pytest tests/test_document_chunking.py::test_layout_converter_disables_ocr -q
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: FAIL,因为当前 `_document_converter()` 没有 PDF pipeline options,fake converter 不会收到 `format_options`。
|
||||||
|
|
||||||
|
- [ ] **Step 3: Implement the explicit PDF options**
|
||||||
|
|
||||||
|
将 `_document_converter()` 改为:
|
||||||
|
|
||||||
|
```python
|
||||||
|
@lru_cache(maxsize=1)
|
||||||
|
def _document_converter():
|
||||||
|
from docling.datamodel.base_models import InputFormat
|
||||||
|
from docling.datamodel.pipeline_options import PdfPipelineOptions
|
||||||
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
||||||
|
|
||||||
|
pipeline_options = PdfPipelineOptions()
|
||||||
|
pipeline_options.do_ocr = False
|
||||||
|
return DocumentConverter(
|
||||||
|
format_options={
|
||||||
|
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
不要删除 `_MarkdownSerializerProvider`、`chunk_layout_document`、`HybridChunker`、来源页码或 bbox 代码。
|
||||||
|
|
||||||
|
- [ ] **Step 4: Run OCR and layout regression tests**
|
||||||
|
|
||||||
|
Run:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd backend && PYTHONPATH=. .venv/bin/pytest tests/test_document_chunking.py::test_layout_converter_disables_ocr tests/test_document_chunking.py::test_layout_projection_ignores_layout_whitespace_but_keeps_source_lines -q
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: PASS;OCR 配置关闭,版面文本投影仍通过。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Task 2: 更新无文本 PDF 的错误和文档
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Modify: `backend/app/modules/data_process/algorithms/parsers/pdf.py:106-108`
|
||||||
|
- Modify: `backend/tests/test_data_process_algorithms.py:650-658`
|
||||||
|
- Modify: `docs/data-process-design.md:121-122`
|
||||||
|
|
||||||
|
**Interfaces:**
|
||||||
|
- `extract_pdf_page_texts()` 的判定逻辑不变,只更新无文本 PDF 的错误文案。
|
||||||
|
- 混合 PDF 仍由 `has_text` 判定为可处理。
|
||||||
|
|
||||||
|
- [ ] **Step 1: Update the expected error**
|
||||||
|
|
||||||
|
将测试断言改为:
|
||||||
|
|
||||||
|
```python
|
||||||
|
with pytest.raises(
|
||||||
|
ValueError,
|
||||||
|
match="scanned or image-only PDF files are not supported",
|
||||||
|
):
|
||||||
|
parse_text_content(blank_pdf.getvalue(), filename="scanned.pdf")
|
||||||
|
```
|
||||||
|
|
||||||
|
- [ ] **Step 2: Change only the error message**
|
||||||
|
|
||||||
|
将解析器分支改为:
|
||||||
|
|
||||||
|
```python
|
||||||
|
if not has_text:
|
||||||
|
raise ValueError(
|
||||||
|
"PDF contains no extractable text; scanned or image-only PDF files are not supported"
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
不要修改 `has_text` 逻辑,以保留混合 PDF。
|
||||||
|
|
||||||
|
- [ ] **Step 3: Update the design documentation**
|
||||||
|
|
||||||
|
将 `docs/data-process-design.md` 中“扫描 PDF 没有文本层时明确提示需要 OCR;当前流程不执行 OCR”改为“扫描版或图片型 PDF 不支持”,保留其余格式限制说明。
|
||||||
|
|
||||||
|
- [ ] **Step 4: Run PDF boundary tests**
|
||||||
|
|
||||||
|
Run:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd backend && PYTHONPATH=. .venv/bin/pytest tests/test_data_process_algorithms.py::test_office_zip_bomb_and_invalid_pdf_are_rejected_before_parsing -q
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: PASS;纯扫描 PDF 明确拒绝。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Task 3: 运行受影响验证并检查范围
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Test: `backend/tests/test_document_chunking.py`
|
||||||
|
- Test: `backend/tests/test_data_process_algorithms.py`
|
||||||
|
- Test: `frontend/scripts/regression-data-process-wizard.mjs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Run targeted backend tests and Ruff**
|
||||||
|
|
||||||
|
Run:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd backend && PYTHONPATH=. .venv/bin/pytest tests/test_document_chunking.py::test_layout_converter_disables_ocr tests/test_document_chunking.py::test_layout_projection_ignores_layout_whitespace_but_keeps_source_lines tests/test_data_process_algorithms.py::test_office_zip_bomb_and_invalid_pdf_are_rejected_before_parsing -q
|
||||||
|
.venv/bin/ruff check app/modules/data_process/document_chunking.py tests/test_document_chunking.py app/modules/data_process/algorithms/parsers/pdf.py
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: targeted tests pass. Any pre-existing Ruff findings outside the changed OCR configuration must be reported separately, not fixed as unrelated refactoring.
|
||||||
|
|
||||||
|
- [ ] **Step 2: Run the frontend regression and type check**
|
||||||
|
|
||||||
|
Run:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd frontend && node scripts/regression-data-process-wizard.mjs
|
||||||
|
npm run type-check
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: existing `layout_hybrid`/semantic/fixed assertions remain unchanged; any unrelated pre-existing regression failure is reported separately.
|
||||||
|
|
||||||
|
- [ ] **Step 3: Check OCR references and final diff**
|
||||||
|
|
||||||
|
Run from the repository root:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
rg -n -i --hidden \
|
||||||
|
--glob '!.git/**' \
|
||||||
|
--glob '!node_modules/**' \
|
||||||
|
--glob '!dist/**' \
|
||||||
|
--glob '!outputs/**' \
|
||||||
|
--glob '!.codex-tmp/**' \
|
||||||
|
'(tesseract|paddleocr|easyocr|ocrmypdf|pytesseract)' \
|
||||||
|
backend frontend docs/data-process-design.md
|
||||||
|
|
||||||
|
git diff --check
|
||||||
|
git status --short
|
||||||
|
```
|
||||||
|
|
||||||
|
Expected: no OCR engine dependency or executable OCR integration; the only intended OCR-related runtime setting is `do_ocr = False`, and the diff does not touch layout options, frontend method choices, Docling dependencies, `.codex-tmp/` or `outputs/`.
|
||||||
69
docs/superpowers/specs/2026-08-18-disable-ocr-design.md
Normal file
69
docs/superpowers/specs/2026-08-18-disable-ocr-design.md
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
# 屏蔽数据处理中的 OCR 能力设计
|
||||||
|
|
||||||
|
日期:2026-08-18
|
||||||
|
|
||||||
|
## 1. 目标
|
||||||
|
|
||||||
|
屏蔽数据处理运行时的 OCR 能力,同时保留 Docling、`layout_hybrid` 版面分析、文本型 PDF 解析和现有前端切分选项。版面分析继续使用 Docling 的结构识别模型,但 PDF pipeline 必须显式设置 `do_ocr=False`,不再从图片或扫描页面识别文字。
|
||||||
|
|
||||||
|
## 2. 行为边界
|
||||||
|
|
||||||
|
- `layout_hybrid`、`semantic`、`fixed` 三种切分方式保持不变。
|
||||||
|
- `layout_hybrid` 继续通过 Docling 识别文本层 PDF 的版面、阅读顺序、表格和列表结构。
|
||||||
|
- OCR 是独立阶段,只在 Docling PDF pipeline 中关闭;不删除 Docling 版面/表格分析模型。
|
||||||
|
- 整份 PDF 没有可提取文本时继续拒绝,并提示扫描版或图片型 PDF 不支持。
|
||||||
|
- 混合 PDF 继续接收;有文本页正常处理,无文本图片页不产生文字,也不触发 OCR。
|
||||||
|
- TXT、Markdown、结构化文件、DOCX、XLSX、PPTX 和文本型 PDF 的其他流程不变。
|
||||||
|
- 不新增 OCR 配置项,不提供任何重新开启 OCR 的请求参数或环境开关。
|
||||||
|
|
||||||
|
## 3. 数据流
|
||||||
|
|
||||||
|
上传阶段仍由 `pypdf` 提取 PDF 文本。整份 PDF 没有文本层时在上传阶段失败;混合 PDF 保留空文本页。
|
||||||
|
|
||||||
|
预览阶段的 `layout_hybrid` 仍读取原始文件并调用 `DocumentConverter`,但转换器使用 PDF 专用配置:
|
||||||
|
|
||||||
|
```python
|
||||||
|
pipeline_options = PdfPipelineOptions()
|
||||||
|
pipeline_options.do_ocr = False
|
||||||
|
DocumentConverter(
|
||||||
|
format_options={
|
||||||
|
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
这样 Docling 仍可对已有文本层执行版面分析,图片内容不会被 OCR 成文字。`semantic` 继续使用 LlamaIndex/HuggingFace embedding 模型;该模型与 OCR 无关。
|
||||||
|
|
||||||
|
## 4. 代码改动
|
||||||
|
|
||||||
|
### 4.1 PDF 版面转换
|
||||||
|
|
||||||
|
修改 `backend/app/modules/data_process/document_chunking.py` 的 `_document_converter()`:
|
||||||
|
|
||||||
|
- 导入 `InputFormat`、`PdfPipelineOptions` 和 `PdfFormatOption`;
|
||||||
|
- 创建 `PdfPipelineOptions` 后将 `do_ocr` 固定为 `False`;
|
||||||
|
- 只为 `InputFormat.PDF` 注册该配置;
|
||||||
|
- 保留现有 `HybridChunker`、版面序列化、来源页码和 bbox 映射。
|
||||||
|
|
||||||
|
### 4.2 扫描 PDF 错误与文档
|
||||||
|
|
||||||
|
将无文本 PDF 的错误从“需要 OCR”改为“扫描版或图片型 PDF 不支持”,避免向用户暗示系统可以提供 OCR。同步更新数据处理设计文档;不删除测试中与 DPO 字段验证无关的历史文本样例。
|
||||||
|
|
||||||
|
### 4.3 依赖与界面
|
||||||
|
|
||||||
|
不删除 `docling`、`docling_core`、`layout_hybrid`、前端版面切分选项或相关配置。仅增加 OCR 关闭回归测试,不修改切分类型、默认值和前端交互。
|
||||||
|
|
||||||
|
## 5. 测试设计
|
||||||
|
|
||||||
|
- 使用假的 Docling 模块测试 `_document_converter()` 传入的 PDF pipeline options 最终为 `do_ocr=False`,不要求测试环境安装 Docling 才能验证配置。
|
||||||
|
- 保留并运行版面投影、来源页码、短块合并和已有文本 PDF 测试,确认版面分析代码未被删除。
|
||||||
|
- 更新纯扫描 PDF 错误断言。
|
||||||
|
- 运行受影响的后端 pytest、Ruff 和前端数据处理回归;前端切分方式回归应继续要求 `layout_hybrid`、`semantic`、`fixed` 三种配置。
|
||||||
|
- 静态检查确认没有新增 OCR 开关、OCR 调用或 OCR 引擎依赖;`do_ocr=False` 是唯一运行时设置。
|
||||||
|
|
||||||
|
## 6. 非目标
|
||||||
|
|
||||||
|
- 不移除版面结构混合切分。
|
||||||
|
- 不移除 Docling 或其版面/表格分析模型。
|
||||||
|
- 不把 `layout_hybrid` 改为语义或固定切分。
|
||||||
|
- 不删除 PDF 支持,不改变混合 PDF 的接收策略。
|
||||||
Reference in New Issue
Block a user