"""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 的 rows/text（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"), # 表格数据不检 ("paragraph", "本機能は注文処理を行う。"), ) assert not find_language_violations(blocks, "ja") def _blocks_with_caption(*specs): """(type, text, caption) 构造内容块。""" out = [] for i, (t, text, caption) in enumerate(specs): out.append(ContentBlock(block_id=str(i), type=t, text=text, caption=caption)) return out def test_table_caption_checked_zh_expected(): # 表格 caption 是生成正文（非源数据）：zh 期望下含日文假名 → 违规 blocks = _blocks_with_caption( ("table", "", "TB001（訂単テーブル）与 TB002（即時行情テーブル）为既有表，本次变更涉及列定义调整。"), ) assert find_language_violations(blocks, "zh") def test_table_caption_checked_ja_expected(): # ja 期望下 caption 为纯中文（无假名 ≥12）→ 违规 blocks = _blocks_with_caption( ("table", "", "这是一段纯中文的表格说明内容，应当被判定为语言违规。"), ) assert find_language_violations(blocks, "ja") def test_table_caption_matching_language_not_flagged(): # 与期望语言一致的 caption 不违规 blocks = _blocks_with_caption( ("table", "", "表5-1 功能一览表（展示既有与新规功能清单）"), ) assert not find_language_violations(blocks, "zh") def test_table_rows_still_excluded_even_with_caption(): # 表格 rows 照抄源数据：即使含假名也不因 rows 判违规；仅 caption 参与检查 blocks = _blocks_with_caption( ("table", "", "表5-1 功能一览"), ) blocks[0].rows = [["機能ID", "機能名"], ["F001", "注文処理"]] assert not find_language_violations(blocks, "zh") 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 class JaRuleEngine(MixedLanguageEngine): """返回日文正文（含假名）。""" def test_generate_chapter_auto_with_ja_rules_but_chinese_source_data_enforces_ja(): """回归：真实试运行暴露——auto 模式 fallback 只用规则文档（日文）， 不得用 impact/data 源数据（含中文元素名）把期望误判为 zh。 构造：标题纯汉字「機能一覧」（无假名）+ 规则文档日文（含假名）+ 源数据中文， 期望应推导为 ja；日文正文应通过、中文正文应违规。 """ ja_rules_ctx = GenerationContext( chapter_id="function_list", title="2. 機能一覧", template_marker=ChapterSpec(chapter_id="function_list", title="2. 機能一覧"), structured_source="中文源数据：止损风控、下单流程", write_rules=["書込規則に従って記述する。"], # 日文含假名 design_rules=["設計方針は本書の通りである。"], # 日文含假名 template_styles=set(), output_language="auto", ) engine = MixedLanguageEngine(["本機能は注文処理を行う画面であり、詳細は以下の通り。"]) agent = WriterAgent(session_id="s", engine=engine, prompt_registry=FakePromptRegistry(), state=WriterState(["function_list"]), max_retries=1) content = agent.generate_chapter(ja_rules_ctx) assert content is not None and "本機能" in content.blocks[0].text