lhl
d01e1b720f
- 步骤0: 新增中文镜像模板 scripts/make_zh_template.py 与 samples/概要设计书模板_中文.docx（7章锚点原样保留） - 步骤1: config.WriterConfig.output_language→Settings.writer；GenerationContext.output_language + to_vars.language_instruction（zh/ja/auto）；writer_agent【语言约束】改引变量；context_builder/orchestrator/run_trial 透传 --output-language - 步骤A: 新建 src/genesis/writer/language.py（detect_script/resolve_expected_language/find_language_violations）；WriterAgent.generate_chapter 按期望语言强制、违规重试、耗尽硬失败；max_retries 默认 1→2 - 步骤B: _format_impact 影响调查标签按 output_language 本地化（zh 新建/变更/删除/警告） - 步骤C: eval scorer 第 11 维度 language_consistency（不可验证=满分，不拉低总分）；ChapterArtifact.expected_language；QAValidator.validate_doc 透传；QALoop.run 透传 output_language - 测试: test_zh_template/test_language_plumbing/test_writer_language/test_scorer_language/test_language_coverage，并更新 test_phase5_e2e - 全量 pytest 424 passed / 99.15%（覆盖率门槛 99% 达标）
78 lines
2.6 KiB
Python
78 lines
2.6 KiB
Python
"""中文样本模板镜像测试（步骤 0）。
|
|
|
|
断言 zh 模板与 ja 模板章节结构一致：7 个 H1 章、锚点 id（section:xxx）逐一对应，
|
|
且锚点段落文本原样保留（映射/注入器零改动）。
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from docx import Document
|
|
|
|
from genesis.parsers.word_template_parser import WordTemplateParser
|
|
from genesis.writer.template_mapper import map_template
|
|
|
|
_SAMPLES = Path(r"D:\00_project\Genesis\samples")
|
|
_JA = _SAMPLES / "概要設計書テンプレート.docx"
|
|
_ZH = _SAMPLES / "概要设计书模板_中文.docx"
|
|
|
|
|
|
EXPECTED_ANCHORS = [
|
|
"introduction", "function_list", "screen_list", "report_list",
|
|
"db_design", "if_definition", "batch_list",
|
|
]
|
|
|
|
|
|
@pytest.fixture
|
|
def zh_template(tmp_path):
|
|
"""生成 zh 模板到临时目录并返回路径（不污染 samples/）。"""
|
|
from scripts.make_zh_template import build_zh_template
|
|
dst = tmp_path / "概要设计书模板_中文.docx"
|
|
build_zh_template(str(_JA), str(dst))
|
|
return dst
|
|
|
|
|
|
def _parse(path: Path):
|
|
return WordTemplateParser().parse(str(path))
|
|
|
|
|
|
def test_zh_template_has_same_seven_chapter_anchors(zh_template):
|
|
ja = _parse(_JA)
|
|
zh = _parse(zh_template)
|
|
|
|
ja_ids = [ph for ph in ja.placeholders if ph.startswith("section:")]
|
|
zh_ids = [ph for ph in zh.placeholders if ph.startswith("section:")]
|
|
|
|
assert sorted(zh_ids) == sorted(ja_ids)
|
|
assert zh_ids == [f"section:{a}" for a in EXPECTED_ANCHORS]
|
|
|
|
|
|
def test_zh_template_anchor_paragraphs_unchanged(zh_template):
|
|
"""锚点段落文本在 zh 模板中必须与 ja 完全一致（映射/注入器依赖它）。"""
|
|
ja_doc = Document(str(_JA))
|
|
zh_doc = Document(str(zh_template))
|
|
ja_anchors = [p.text for p in ja_doc.paragraphs if p.text.startswith("{{section:")]
|
|
zh_anchors = [p.text for p in zh_doc.paragraphs if p.text.startswith("{{section:")]
|
|
assert zh_anchors == ja_anchors
|
|
|
|
|
|
def test_zh_template_headings_translated(zh_template):
|
|
zh_doc = Document(str(zh_template))
|
|
texts = {p.text for p in zh_doc.paragraphs if p.style.name.startswith("Heading")}
|
|
assert "1. 前言" in texts
|
|
assert "2. 功能一览" in texts
|
|
assert "5. DB设计" in texts
|
|
assert "7. 批处理一览" in texts
|
|
|
|
|
|
def test_zh_template_maps_to_same_seven_chapters(zh_template):
|
|
"""template_mapper 对 zh 模板产出 7 个章节，锚点与 ja 对应。"""
|
|
pt = _parse(zh_template)
|
|
specs = map_template(pt)
|
|
assert len(specs) == 7
|
|
assert [s.section_placeholder for s in specs] == [
|
|
f"section:{a}" for a in EXPECTED_ANCHORS
|
|
]
|