feat(writer): 输出语言一致性保障 + 用户可选输出语言
- 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）
This commit is contained in:
@@ -0,0 +1,102 @@
|
||||
"""步骤 A/C 边界覆盖测试（恢复覆盖率至 ≥99%）。"""
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
|
||||
from genesis.writer.language import find_language_violations
|
||||
from genesis.writer.models import ChapterContent, ContentBlock, GenerationContext, ChapterSpec
|
||||
from genesis.writer.writer_agent import WriterAgent
|
||||
from genesis.writer.writer_state import WriterState
|
||||
from genesis.writer.exceptions import WriterGenerationError
|
||||
from genesis.qa.qa_loop import QALoop
|
||||
from genesis.data_models import StructuredSource
|
||||
from genesis.parsers.word_template_parser import WordTemplateParser
|
||||
|
||||
|
||||
class _Reg:
|
||||
@staticmethod
|
||||
def get_or_create(name, template):
|
||||
return SimpleNamespace(name=name, version="1", template=template)
|
||||
|
||||
|
||||
def test_find_violations_unexpected_language_code_returns_empty():
|
||||
blocks = [ContentBlock(block_id="0", type="paragraph", text="中文正文内容充分长度足够")]
|
||||
# 非 zh/ja 的期望语言 → 不强制，返回空
|
||||
assert find_language_violations(blocks, "xx") == []
|
||||
|
||||
|
||||
def test_writer_agent_zh_expected_rejects_japanese():
|
||||
class JpEngine:
|
||||
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
||||
return SimpleNamespace(
|
||||
data={"title": variables["title"],
|
||||
"blocks": [{"type": "paragraph",
|
||||
"text": "本機能は注文処理を行う画面であり、詳細は以下の通り。"}]},
|
||||
status="ok",
|
||||
)
|
||||
agent = WriterAgent(session_id="s", engine=JpEngine(), prompt_registry=_Reg(),
|
||||
state=WriterState(["db_design"]), max_retries=1)
|
||||
ctx = GenerationContext(chapter_id="db_design", title="DB 設計",
|
||||
template_marker=ChapterSpec(chapter_id="db_design", title="DB 設計"),
|
||||
structured_source=None, write_rules=[], design_rules=[],
|
||||
template_styles=set(), output_language="zh")
|
||||
try:
|
||||
agent.generate_chapter(ctx)
|
||||
assert False, "应抛 WriterGenerationError"
|
||||
except WriterGenerationError:
|
||||
pass
|
||||
|
||||
|
||||
def test_qa_loop_passes_with_explicit_zh_on_chinese_fake(tmp_path):
|
||||
"""显式 zh + 中文 Fake → 语言维度通过（验证透传链路）。"""
|
||||
template = Path("samples/phase5-slice/template.docx")
|
||||
if not template.exists():
|
||||
import pytest
|
||||
pytest.skip("样本模板缺失")
|
||||
parsed = WordTemplateParser().parse(str(template))
|
||||
ss = StructuredSource(template=parsed, tables=[], rule_docs=[], image_analyses=[],
|
||||
existing_system=None, comments=[])
|
||||
out = tmp_path / "o.docx"
|
||||
|
||||
class ZhEngine:
|
||||
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
||||
return SimpleNamespace(
|
||||
data={"title": variables["title"],
|
||||
"blocks": [{"type": "paragraph",
|
||||
"text": "由 FakeLLM 生成的充分说明内容，满足写入规则要求。"}]},
|
||||
status="ok",
|
||||
)
|
||||
loop = QALoop(max_rounds=1)
|
||||
report = loop.run(ss, str(out), samples_dir="nonexistent_dir_xyz",
|
||||
engine=ZhEngine(), template_path=str(template), output_language="zh")
|
||||
assert report.passed is True
|
||||
|
||||
|
||||
def test_qa_loop_fails_with_explicit_ja_on_chinese_fake(tmp_path):
|
||||
"""显式 ja + 中文 Fake → 语言维度判失败。"""
|
||||
template = Path("samples/phase5-slice/template.docx")
|
||||
if not template.exists():
|
||||
import pytest
|
||||
pytest.skip("样本模板缺失")
|
||||
parsed = WordTemplateParser().parse(str(template))
|
||||
ss = StructuredSource(template=parsed, tables=[], rule_docs=[], image_analyses=[],
|
||||
existing_system=None, comments=[])
|
||||
out = tmp_path / "o.docx"
|
||||
|
||||
class ZhEngine:
|
||||
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
||||
return SimpleNamespace(
|
||||
data={"title": variables["title"],
|
||||
"blocks": [{"type": "paragraph",
|
||||
"text": "由 FakeLLM 生成的充分说明内容，满足写入规则要求。"}]},
|
||||
status="ok",
|
||||
)
|
||||
loop = QALoop(max_rounds=1)
|
||||
# 显式 ja + 中文 Fake：writer 生成阶段即因语言不一致硬失败（设计语义）
|
||||
try:
|
||||
loop.run(ss, str(out), samples_dir="nonexistent_dir_xyz",
|
||||
engine=ZhEngine(), template_path=str(template), output_language="ja")
|
||||
assert False, "应抛出 WriterGenerationError"
|
||||
except WriterGenerationError:
|
||||
pass
|
||||
@@ -0,0 +1,93 @@
|
||||
"""步骤 1：语言参数贯通测试（config → GenerationContext → to_vars → context_builder → run_trial）。"""
|
||||
from __future__ import annotations
|
||||
|
||||
from genesis.data_models import (
|
||||
CellValue, ExcelTable, ParsedTemplate, Provenance, SheetType, StructuredSource,
|
||||
)
|
||||
from genesis.writer.context_builder import build_contexts
|
||||
from genesis.writer.models import ChapterSpec, GenerationContext
|
||||
|
||||
|
||||
def _src() -> StructuredSource:
|
||||
return StructuredSource(
|
||||
tables=[],
|
||||
template=ParsedTemplate("t.docx", [__import__("genesis.data_models", fromlist=["ChapterMarker"]).ChapterMarker("heading", "1. はじめに", 1)], {}, {"used": []}),
|
||||
rule_docs=[], image_analyses=[], existing_system=None, comments=[],
|
||||
)
|
||||
|
||||
|
||||
def test_generation_context_default_output_language_is_auto():
|
||||
ctx = GenerationContext(
|
||||
chapter_id="db_design", title="DB 設計",
|
||||
template_marker=ChapterSpec(chapter_id="db_design", title="DB 設計"),
|
||||
structured_source=None, write_rules=[], design_rules=[], template_styles=set(),
|
||||
)
|
||||
assert ctx.output_language == "auto"
|
||||
|
||||
|
||||
def test_to_vars_language_instruction_explicit_zh():
|
||||
ctx = GenerationContext(
|
||||
chapter_id="db_design", title="DB 设計",
|
||||
template_marker=ChapterSpec(chapter_id="db_design", title="DB 设計"),
|
||||
structured_source=None, write_rules=[], design_rules=[], template_styles=set(),
|
||||
output_language="zh",
|
||||
)
|
||||
v = ctx.to_vars()
|
||||
assert "language_instruction" in v
|
||||
assert "简体中文" in v["language_instruction"]
|
||||
|
||||
|
||||
def test_to_vars_language_instruction_explicit_ja():
|
||||
ctx = GenerationContext(
|
||||
chapter_id="db_design", title="DB 設計",
|
||||
template_marker=ChapterSpec(chapter_id="db_design", title="DB 設計"),
|
||||
structured_source=None, write_rules=[], design_rules=[], template_styles=set(),
|
||||
output_language="ja",
|
||||
)
|
||||
v = ctx.to_vars()
|
||||
assert "日本語" in v["language_instruction"]
|
||||
|
||||
|
||||
def test_to_vars_language_instruction_auto_follows_title():
|
||||
ctx = GenerationContext(
|
||||
chapter_id="db_design", title="DB 設計",
|
||||
template_marker=ChapterSpec(chapter_id="db_design", title="DB 設計"),
|
||||
structured_source=None, write_rules=[], design_rules=[], template_styles=set(),
|
||||
output_language="auto",
|
||||
)
|
||||
v = ctx.to_vars()
|
||||
assert "标题" in v["language_instruction"] and "一致" in v["language_instruction"]
|
||||
|
||||
|
||||
def test_context_builder_passes_output_language():
|
||||
src = _src()
|
||||
ctxs = build_contexts(src, output_language="zh")
|
||||
assert all(c.output_language == "zh" for c in ctxs)
|
||||
# 回归：默认仍为 auto
|
||||
ctxs2 = build_contexts(src)
|
||||
assert all(c.output_language == "auto" for c in ctxs2)
|
||||
|
||||
|
||||
def test_format_impact_zh_labels_localized():
|
||||
"""步骤 B：output_language=zh 时影响调查标签本地化为中文，且不影响 ja 默认。"""
|
||||
from genesis.data_models import (
|
||||
ChangeAnalysis, ChangeElement, ChangeType, ImpactReport, ImpactWarning,
|
||||
)
|
||||
from genesis.writer.models import _format_impact
|
||||
|
||||
ca = ChangeAnalysis(
|
||||
project_type="enhancement",
|
||||
new_elements=[ChangeElement("F001", "機能", "止损风控", ChangeType.NEW)],
|
||||
modified_elements=[ChangeElement("F002", "機能", "下单流程", ChangeType.MODIFIED)],
|
||||
deleted_elements=[ChangeElement("F030", "機能", "旧功能", ChangeType.DELETED)],
|
||||
unchanged_elements=[],
|
||||
warnings=[ImpactWarning("F030", "缺少既存対応")],
|
||||
)
|
||||
report = ImpactReport(metadata={}, change_analysis=ca, summary={})
|
||||
|
||||
zh = _format_impact(report, None, "zh")
|
||||
assert "[新建]" in zh and "[变更]" in zh and "[删除]" in zh and "[警告]" in zh
|
||||
assert "受影响" in zh
|
||||
# ja / auto 回落仍用日文标签
|
||||
ja = _format_impact(report, None, "ja")
|
||||
assert "[新規]" in ja and "[削除]" in ja
|
||||
@@ -12,13 +12,14 @@ from genesis.qa.qa_loop import QALoop
|
||||
class FakeEngine:
|
||||
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
||||
cid = variables.get("title", "x")
|
||||
# 日文模板章节（标题含假名）→ 返回日文正文，满足语言一致性强制
|
||||
return SimpleNamespace(
|
||||
data={
|
||||
"title": cid,
|
||||
"blocks": [
|
||||
{"type": "heading", "level": 2, "text": f"{cid} 小节"},
|
||||
{"type": "paragraph", "text": "由 FakeLLM 生成的充分说明内容，满足写入规则要求。"},
|
||||
{"type": "table", "caption": "示例表", "rows": [["列1", "列2"], ["值1", "值2"]]},
|
||||
{"type": "heading", "level": 2, "text": f"{cid} 小節"},
|
||||
{"type": "paragraph", "text": "本機能はFakeLLMにより生成された十分な説明内容であり、書込規則を満たす。"},
|
||||
{"type": "table", "caption": "示例表", "rows": [["列1", "列2"], ["値1", "値2"]]},
|
||||
],
|
||||
},
|
||||
status="ok",
|
||||
@@ -50,5 +51,5 @@ def test_phase5_e2e_fake_llm(tmp_path):
|
||||
assert report.passed is True
|
||||
loaded = Document(str(out))
|
||||
text = _all_text(loaded)
|
||||
assert "由 FakeLLM 生成的充分说明内容" in text
|
||||
assert "本機能はFakeLLMにより生成された十分な説明内容" in text
|
||||
assert "示例表" in text
|
||||
|
||||
@@ -0,0 +1,92 @@
|
||||
"""步骤 C：QA 第 11 维度 language_consistency 测试。
|
||||
|
||||
评审 R1：不可验证（expected_language 为空/auto）→ 维度满分 1.0 通过，不拉低总分，
|
||||
使既有 test_eval_scorer / test_phase5_scorer 的 total_score==1.0 断言继续成立。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from genesis.data_models import (
|
||||
CellValue, ExcelTable, ParsedTemplate, Provenance, SheetType, StructuredSource,
|
||||
)
|
||||
from genesis.eval.scorer import ChapterArtifact, ChapterScorer, EvalReport
|
||||
|
||||
|
||||
def _dim(report: EvalReport, name: str):
|
||||
for d in report.dimensions:
|
||||
if d.name == name:
|
||||
return d
|
||||
raise AssertionError(f"维度未找到: {name}")
|
||||
|
||||
|
||||
def _source() -> StructuredSource:
|
||||
cell = CellValue(
|
||||
value="登録",
|
||||
provenance=Provenance(file_name="f.xlsx", sheet_name="機能一覧", row=3, column="C", column_header="x"),
|
||||
)
|
||||
table = ExcelTable(
|
||||
name="機能一覧", detected_type=SheetType.FUNCTION,
|
||||
extraction_method="structured", headers=["v"], rows=[{"v": cell}],
|
||||
)
|
||||
return StructuredSource(
|
||||
tables=[table],
|
||||
template=ParsedTemplate(file_name="t.docx", sections=[], placeholders={}, styles={}),
|
||||
rule_docs=[], image_analyses=[], existing_system=None, comments=[],
|
||||
)
|
||||
|
||||
|
||||
def test_language_dim_unverifiable_is_full_score():
|
||||
"""expected_language 为空（auto/不可验证）→ 维度满分通过，不拉低总分。"""
|
||||
src = _source()
|
||||
artifact = ChapterArtifact(
|
||||
chapter_id="ch3", text="本機能は注文処理を行う画面である。",
|
||||
source_uris=[], template_sections_expected=["ch3"],
|
||||
expected_language="",
|
||||
)
|
||||
report = ChapterScorer().score([artifact], src)
|
||||
dim = _dim(report, "language_consistency")
|
||||
assert dim.score == 1.0
|
||||
assert dim.passed is True
|
||||
# 既有总分断言仍成立（全部确定性维度满分）
|
||||
assert report.total_score == 1.0
|
||||
|
||||
|
||||
def test_language_dim_ja_expected_but_chinese_fails():
|
||||
src = _source()
|
||||
artifact = ChapterArtifact(
|
||||
chapter_id="ch3", text="这是一段纯中文的章节正文内容，应当判定为语言违规。",
|
||||
source_uris=[], template_sections_expected=["ch3"],
|
||||
expected_language="ja",
|
||||
)
|
||||
report = ChapterScorer().score([artifact], src)
|
||||
dim = _dim(report, "language_consistency")
|
||||
assert dim.score == 0.0
|
||||
assert dim.passed is False
|
||||
assert report.total_score < 1.0
|
||||
|
||||
|
||||
def test_language_dim_zh_expected_japanese_fails():
|
||||
src = _source()
|
||||
artifact = ChapterArtifact(
|
||||
chapter_id="ch3", text="本機能は注文処理を行う画面であり、詳細は以下の通り。",
|
||||
source_uris=[], template_sections_expected=["ch3"],
|
||||
expected_language="zh",
|
||||
)
|
||||
report = ChapterScorer().score([artifact], src)
|
||||
dim = _dim(report, "language_consistency")
|
||||
assert dim.score == 0.0
|
||||
|
||||
|
||||
def test_language_dim_threshold_in_defaults():
|
||||
assert ChapterScorer().thresholds["language_consistency"] == 1.0
|
||||
|
||||
|
||||
def test_dimension_count_increases_by_one():
|
||||
src = _source()
|
||||
artifact = ChapterArtifact(
|
||||
chapter_id="ch3", text="正常内容", source_uris=[], template_sections_expected=["ch3"],
|
||||
)
|
||||
before = len(ChapterScorer(thresholds={}, llm_evaluators={}).score([artifact], src).dimensions)
|
||||
# 默认 scorer 含 language_consistency；对比一个不含该维度的基线不可行，
|
||||
# 此处仅断言维度中包含 language_consistency 名称
|
||||
report = ChapterScorer().score([artifact], src)
|
||||
assert any(d.name == "language_consistency" for d in report.dimensions)
|
||||
@@ -0,0 +1,172 @@
|
||||
"""步骤 A：确定性语言检测 + 输出语言强制测试。
|
||||
|
||||
- detect_script：含假名→ja，CJK 零假名→zh，否则 None
|
||||
- resolve_expected_language：显式 > 标题假名 > 规则文档主导脚本 > ""（不可验证）
|
||||
- find_language_violations：仅检正文块（heading/table 不检），长度≥12 防误杀
|
||||
- WriterAgent.generate_chapter：期望语言非空时违规即重试，耗尽→硬失败
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from genesis.writer.language import (
|
||||
detect_script,
|
||||
find_language_violations,
|
||||
resolve_expected_language,
|
||||
)
|
||||
from genesis.writer.models import ChapterContent, ContentBlock, GenerationContext, ChapterSpec
|
||||
from genesis.writer.writer_agent import WriterAgent
|
||||
from genesis.writer.writer_state import WriterState
|
||||
from genesis.writer.exceptions import WriterGenerationError
|
||||
|
||||
|
||||
# ---------- detect_script ----------
|
||||
|
||||
def test_detect_script_kana_is_ja():
|
||||
assert detect_script("機能一覧の説明を記述します。") == "ja"
|
||||
|
||||
|
||||
def test_detect_script_cjk_no_kana_is_zh():
|
||||
assert detect_script("功能一览的说明内容。") == "zh"
|
||||
|
||||
|
||||
def test_detect_script_ascii_is_none():
|
||||
assert detect_script("Hello world 123") is None
|
||||
|
||||
|
||||
def test_detect_script_mixed_cjk_kana_is_ja():
|
||||
# 含假名即判 ja，即使混有汉字（中文不可能含日文假名）
|
||||
assert detect_script("DB設計の概要を説明する。") == "ja"
|
||||
|
||||
|
||||
# ---------- resolve_expected_language ----------
|
||||
|
||||
def test_resolve_explicit_overrides():
|
||||
assert resolve_expected_language("zh", "DB 設計", ["日本語の影響"]) == "zh"
|
||||
assert resolve_expected_language("ja", "DB 设計", ["中文影响"]) == "ja"
|
||||
|
||||
|
||||
def test_resolve_falls_back_to_title_kana():
|
||||
# 标题含假名→ja（注意：纯汉字日文标题如「DB設計」无假名，会落入 fallback）
|
||||
assert resolve_expected_language("auto", "機能一覧の説明", []) == "ja"
|
||||
|
||||
|
||||
def test_resolve_falls_back_to_fallback_text():
|
||||
# 标题纯汉字无假名（中文式）→ 看 fallback（日文影响书）→ ja
|
||||
assert resolve_expected_language("auto", "DB 設計", ["影響調査の結果（日本語）"]) == "ja"
|
||||
|
||||
|
||||
def test_resolve_unverifiable_when_no_hint():
|
||||
assert resolve_expected_language("auto", "DB 設計", ["123 abc"]) == ""
|
||||
|
||||
|
||||
# ---------- find_language_violations ----------
|
||||
|
||||
def _blocks(*specs):
|
||||
out = []
|
||||
for i, (t, text) in enumerate(specs):
|
||||
out.append(ContentBlock(block_id=str(i), type=t, text=text))
|
||||
return out
|
||||
|
||||
|
||||
def test_violation_ja_expected_but_pure_chinese_paragraph():
|
||||
blocks = _blocks(("paragraph", "这是一段纯中文的章节正文内容。"))
|
||||
viol = find_language_violations(blocks, "ja")
|
||||
assert viol # 期望日文却为中文 → 违规
|
||||
|
||||
|
||||
def test_no_violation_ja_expected_japanese_paragraph():
|
||||
blocks = _blocks(("paragraph", "本機能は注文処理を行う画面であり、詳細は以下の通り。"))
|
||||
assert not find_language_violations(blocks, "ja")
|
||||
|
||||
|
||||
def test_heading_and_table_blocks_excluded():
|
||||
# heading 与 table（照抄原文）即使含中文也不算违规
|
||||
blocks = _blocks(
|
||||
("heading", "機能一覧表"),
|
||||
("table", "機能ID 機能名"), # 表格不检
|
||||
("paragraph", "本機能は注文処理を行う。"),
|
||||
)
|
||||
assert not find_language_violations(blocks, "ja")
|
||||
|
||||
|
||||
def test_short_chinese_not_flagged_under_threshold():
|
||||
# 长度<12 的短术语不误杀
|
||||
blocks = _blocks(("paragraph", "中文术语"))
|
||||
assert not find_language_violations(blocks, "ja")
|
||||
|
||||
|
||||
def test_violation_zh_expected_but_kana_present():
|
||||
blocks = _blocks(("paragraph", "本機能は注文処理を行う画面である。"))
|
||||
assert find_language_violations(blocks, "zh")
|
||||
|
||||
|
||||
# ---------- WriterAgent 强制 ----------
|
||||
|
||||
class MixedLanguageEngine:
|
||||
"""返回中英混杂（期望日文时违规）的章节内容。"""
|
||||
def __init__(self, texts):
|
||||
self._texts = list(texts)
|
||||
self._i = 0
|
||||
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
||||
from types import SimpleNamespace
|
||||
text = self._texts[min(self._i, len(self._texts) - 1)]
|
||||
self._i += 1
|
||||
return SimpleNamespace(
|
||||
data={"title": variables["title"], "blocks": [{"type": "paragraph", "text": text}]},
|
||||
status="ok",
|
||||
)
|
||||
|
||||
|
||||
class FakePromptRegistry:
|
||||
@staticmethod
|
||||
def get_or_create(name, template):
|
||||
from types import SimpleNamespace
|
||||
return SimpleNamespace(name=name, version="1", template=template)
|
||||
|
||||
|
||||
def _ctx_with_lang(cid, title, lang):
|
||||
return GenerationContext(
|
||||
chapter_id=cid, title=title,
|
||||
template_marker=ChapterSpec(chapter_id=cid, title=title),
|
||||
structured_source=None, write_rules=[], design_rules=[],
|
||||
template_styles=set(), output_language=lang,
|
||||
)
|
||||
|
||||
|
||||
def test_generate_chapter_retries_on_language_violation_then_passes():
|
||||
# 第一次返回中文（ja 期望→违规），第二次返回日文（通过）
|
||||
engine = MixedLanguageEngine([
|
||||
"这是一段纯中文的章节正文内容，应当被判定为语言违规。",
|
||||
"本機能は注文処理を行う画面であり、詳細は以下の通り記述する。",
|
||||
])
|
||||
agent = WriterAgent(session_id="s", engine=engine,
|
||||
prompt_registry=FakePromptRegistry(),
|
||||
state=WriterState(["db_design"]), max_retries=3)
|
||||
content = agent.generate_chapter(_ctx_with_lang("db_design", "DB 設計", "ja"))
|
||||
assert content is not None
|
||||
assert "本機能" in content.blocks[0].text
|
||||
|
||||
|
||||
def test_generate_chapter_hard_fails_when_violation_persists():
|
||||
# 始终返回中文（ja 期望），重试耗尽→硬失败
|
||||
engine = MixedLanguageEngine([
|
||||
"这是一段纯中文的章节正文内容，应当被判定为语言违规。",
|
||||
"还是一段纯中文的章节正文内容，依旧违规。",
|
||||
])
|
||||
agent = WriterAgent(session_id="s", engine=engine,
|
||||
prompt_registry=FakePromptRegistry(),
|
||||
state=WriterState(["db_design"]), max_retries=2)
|
||||
try:
|
||||
agent.generate_chapter(_ctx_with_lang("db_design", "DB 設計", "ja"))
|
||||
assert False, "应抛出 WriterGenerationError"
|
||||
except WriterGenerationError as e:
|
||||
assert "语言" in str(e) or "language" in str(e).lower()
|
||||
|
||||
|
||||
def test_generate_chapter_auto_unverifiable_not_enforced():
|
||||
# auto 且无法推导期望语言（标题纯汉字无假名、无日文 fallback）→ 不强制，直接通过
|
||||
engine = MixedLanguageEngine(["这是中文正文但 auto 不可验证所以放行。"])
|
||||
agent = WriterAgent(session_id="s", engine=engine,
|
||||
prompt_registry=FakePromptRegistry(),
|
||||
state=WriterState(["db_design"]), max_retries=1)
|
||||
content = agent.generate_chapter(_ctx_with_lang("db_design", "DB 設計", "auto"))
|
||||
assert content is not None
|
||||
@@ -0,0 +1,77 @@
|
||||
"""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
|
||||
]
|
||||
Reference in New Issue
Block a user