From 61ac47c7afddcca7cf146e97378e0c0ae655d5e5 Mon Sep 17 00:00:00 2001 From: lhl Date: Sun, 23 Aug 2026 18:49:34 +0800 Subject: [PATCH] =?UTF-8?q?refactor(impact):=20CodeParser=20=E5=A4=9A?= =?UTF-8?q?=E8=AF=AD=E8=A8=80=E5=B0=B1=E7=BB=AA=E2=80=94=E2=80=94=E8=AF=AD?= =?UTF-8?q?=E8=A8=80=E9=80=82=E9=85=8D=E5=99=A8=E6=B3=A8=E5=86=8C=E8=A1=A8?= =?UTF-8?q?=EF=BC=88=E4=BB=85=20Java=EF=BC=8C=E8=A1=8C=E4=B8=BA=E4=B8=8D?= =?UTF-8?q?=E5=8F=98=EF=BC=89?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - BaseLanguageParser 抽象基类 + JavaLanguageParser（迁移全部 Java 正则，输出逐字节一致） - LANGUAGE_PARSERS 注册表 + register_language_parser 扩展点（新增语言=加适配器类并注册，下游零改动） - CodeParser 分发器：parse(root, language=None) 自动按扩展名探测 / 显式语言覆盖 / 多语言合并（language 逗号连接）/ 无源码或语言不支持抛 CodeParseError - source_aggregator 新增 existing_system_language 透传；config.py 探测扩展名补 .py/.ts/.go/.cs - 删除自动探测下不可达死分支；全量 362 passed / 99.28%（基线 351/99.27%） - 门禁复跑 PASS：summary 与 MVP 基线一致（16/5/8/3/50/0），概要设计书 13 章 --- _AI_USAGE_LOG.md | 1 + src/genesis/config.py | 3 +- src/genesis/impact/code_parser.py | 265 +++++++++++++++-------- src/genesis/parsers/source_aggregator.py | 5 +- tests/test_code_parser.py | 115 +++++++++- tests/test_source_aggregator.py | 28 +++ 6 files changed, 324 insertions(+), 93 deletions(-) diff --git a/_AI_USAGE_LOG.md b/_AI_USAGE_LOG.md index d76eac4..35c28b5 100644 --- a/_AI_USAGE_LOG.md +++ b/_AI_USAGE_LOG.md @@ -112,3 +112,4 @@ | 2026-08-23 | Agent 实现 | 7 章模板只注入 2/3/5 章缺陷修复（用户圈定两项）：①正则宽容化——word_template_parser.PLACEHOLDER_RE 键名大小写不敏感+支持全角冒号（解析归一为小写 section:id）；template_mapper._SECTION_RE 与 docx_injector._SECTION_RE 加 IGNORECASE/全角冒号容忍；②防静默丢章——orchestrator 新增 _warn_unanchored(ctxs)，对无 {{section:id}} 锚点章打 WARNING 列章名，generate 与 qa_loop._build 调用；TDD RED（6 failed）→ GREEN（子集 25 passed）→ 全量 304 passed / 99.19% 覆盖，fail_under=99 达标；端到端冒烟 PASS（{{Section:1}}/{{section：2}} 注入 + 无锚点章告警） | src/genesis/parsers/word_template_parser.py; src/genesis/writer/template_mapper.py; src/genesis/writer/docx_injector.py; src/genesis/writer/orchestrator.py; src/genesis/qa/qa_loop.py; tests/test_word_template_parser.py; tests/test_phase5_template_mapper.py; tests/test_docx_injector.py; tests/test_phase5_writer_orchestrator.py; _AI_USAGE_LOG.md | deepseek-v4-flash || 2026-08-23 | 需求理解 | 用户指出写概要设计书需「要件定義 + 既有系统（设计/代码）做影响调查 → 确定修改范围」；确认场景=追加改修、输入=Java 项目源码；选定既有系统样本 sunOnly/stock-trade-system（股票量化交易系统，无 LICENSE，仅作测试输入保留来源标注，引入 samples/existing-system/，13 模块 278 Java 文件）；确认领域不一致 → 新造股票交易域追加改修样本 | docs/superpowers/specs/2026-08-23-impact-mvp.md; samples/existing-system/README.md | deepseek-v4-flash | | 2026-08-23 | 架构设计 | Impact Agent MVP 设计（brainstorming 逐问确认）：门控=用户是否提供 existing_system 路径（流水线级，非章节级）；范围确认=与用户确认调查范围（模块/深度）；消费模型=影响调查结果是生成概要设计书的主上下文（整本基于影响结果生成，无专用影响章/无 {{section:impact}} 锚点门控）；MVP=变更点定位（确定性规则，无 LLM）；spec 落盘 docs/superpowers/specs/2026-08-23-impact-mvp.md | docs/superpowers/specs/2026-08-23-impact-mvp.md | deepseek-v4-flash | | 2026-08-23 | Agent 实现 | Impact Agent MVP 实现（TDD RED→GREEN→全量 351 passed / 99.27%）：data_models 新增 ChangeType/ChangeElement/ImpactWarning/ChangeAnalysis/ImpactReport + StructuredSource.impact_report；新增 src/genesis/impact/（code_parser.py Java 解析 @RestController/@Service/@Entity/@TableName、existing_system_explorer.py 组装、impact_agent.py 变更点定位+impact_report_to_dict 序列化）；source_aggregator 解除 existing_system=None 硬编码（新增 existing_system_path 门控）；writer 集成——GenerationContext.impact_report + to_vars()[impact]、WRITER_PROMPT_TEMPLATE 加「影响调查上下文」、context_builder 透传、WriteOrchestrator.generate 门控自动跑 ImpactAgent + 回填 + 默认 meta（doc_title/version/created_at）；新造样本 要件定義_追加改修_股票.xlsx（对齐 sunOnly 真实类名）；门禁（fake 模式）PASS：影响调查 total=16 new=5 modified=8 deleted=3 unchanged=50 warnings=0，概要设计书 13 章产出，影响调查书 JSON 可下载 | src/genesis/data_models.py; src/genesis/impact/code_parser.py; src/genesis/impact/existing_system_explorer.py; src/genesis/impact/impact_agent.py; src/genesis/parsers/source_aggregator.py; src/genesis/writer/models.py; src/genesis/writer/writer_agent.py; src/genesis/writer/context_builder.py; src/genesis/writer/orchestrator.py; tests/test_data_models.py; tests/test_code_parser.py; tests/test_existing_system_explorer.py; tests/test_impact_agent.py; tests/test_source_aggregator.py; tests/test_phase5_models.py; tests/test_phase5_writer_agent.py; tests/test_phase5_context_builder.py; tests/test_phase5_writer_orchestrator.py; samples/要件定義_追加改修_股票.xlsx; samples/existing-system/; docs/superpowers/specs/2026-08-23-impact-mvp.md; _AI_USAGE_LOG.md | deepseek-v4-flash | +| 2026-08-23 | Agent 实现 | CodeParser 多语言就绪预备性重构（行为不变）：code_parser.py 重构为语言适配器注册表——BaseLanguageParser 抽象基类（extensions/source_files/parse_file 契约）+ JavaLanguageParser（迁移全部 Java 正则，输出与重构前逐字节一致：20Ctrl/25Svc/22Ent/113EP/13模块/219类/278imports）+ LANGUAGE_PARSERS 注册表 + register_language_parser 扩展点 + CodeParser 分发器（parse(root, language=None) 自动按扩展名探测/显式语言覆盖/多语言合并 language 逗号连接/无源码与不支持语言抛 CodeParseError）；source_aggregator 新增 existing_system_language 透传参数；config.py allowed_extensions 补 .py/.ts/.go/.cs；删除自动探测下不可达 continue 死分支；TDD RED（ImportError）→ GREEN（test_code_parser 17 passed + test_source_aggregator 19 passed）→ 全量 362 passed / 99.28%（基线 351/99.27%，+11 新测试）；门禁（fake 模式）复跑 PASS：summary 与 MVP 基线一致（total=16 new=5 modified=8 deleted=3 unchanged=50 warnings=0），概要设计书 13 章；未实现任何新语言（仅 Java，后续加语言=新增适配器类+register_language_parser，下游零改动） | src/genesis/impact/code_parser.py; src/genesis/parsers/source_aggregator.py; src/genesis/config.py; tests/test_code_parser.py; tests/test_source_aggregator.py; _AI_USAGE_LOG.md | deepseek-v4-flash | diff --git a/src/genesis/config.py b/src/genesis/config.py index 1401ffb..7e11b8d 100644 --- a/src/genesis/config.py +++ b/src/genesis/config.py @@ -17,7 +17,8 @@ ENV_PREFIX = "GENESIS_" class ServerConfig(BaseModel): max_upload_mb: int = 100 allowed_extensions: list[str] = Field( - default_factory=lambda: [".xlsx", ".xls", ".docx", ".pptx", ".java", ".xml", ".yml"] + default_factory=lambda: [".xlsx", ".xls", ".docx", ".pptx", ".java", ".xml", ".yml", + ".py", ".ts", ".go", ".cs"] ) diff --git a/src/genesis/impact/code_parser.py b/src/genesis/impact/code_parser.py index 8efbfdd..1d3a419 100644 --- a/src/genesis/impact/code_parser.py +++ b/src/genesis/impact/code_parser.py @@ -1,7 +1,11 @@ -"""CodeParser：Java 项目源码解析 → CodeStructure（Impact Agent MVP）。 +"""CodeParser：多语言源码解析 → CodeStructure（Impact Agent）。 -识别 @RestController/@Controller、@Service、@Entity/@Table 及方法级路由映射， -输出供 ExistingSystemExplorer 组装 ExistingSystemInfo 的结构化清单。 +通过语言适配器注册表（LANGUAGE_PARSERS）分发：每种开发语言一个适配器 +（BaseLanguageParser 子类），定义文件扩展名、类名识别、角色（控制器/服务/实体） +与端点提取。当前内置 Java 适配器（Spring Boot / JPA / MyBatis-Plus）。 + +新增语言 = 实现一个适配器类并调用 register_language_parser 注册， +下游（ExistingSystemExplorer / ImpactAgent / Writer）零改动。 """ from __future__ import annotations @@ -18,27 +22,7 @@ from genesis.data_models import ( class CodeParseError(Exception): - """既有系统解析失败（路径无效或非 Java 源码项目）。""" - - -_JAVA_EXT = ".java" - -_CLASS_RE = re.compile( - r"(?:public\s+|abstract\s+|final\s+)?(?:class|interface|enum|record)\s+(\w+)" -) -_TABLE_RE = re.compile(r"@(?:Table|TableName)\s*\(\s*(?:name\s*=\s*)?[\"']([^\"']+)[\"']") -_CLASS_MAPPING_RE = re.compile(r"@RequestMapping\s*\(\s*[\"']([^\"']+)[\"']") -_METHOD_MAPPING_RE = re.compile( - r"@(Get|Post|Put|Delete|Patch|Request)Mapping\s*(?:\(\s*[\"']([^\"']*)[\"'])?" -) -_METHOD_DECL_RE = re.compile( - r"(?:public|private|protected|)\s+(?:static\s+|final\s+|synchronized\s+)*" - r"[\w<>\[\],.?]+\s+(\w+)\s*\(" -) -_FIELD_DECL_RE = re.compile( - r"(?:private|public|protected)\s+[\w<>\[\],]+\s+(\w+)\s*;" -) -_IMPORT_RE = re.compile(r"^import\s+([\w.]+);", re.MULTILINE) + """既有系统解析失败（路径无效或无可识别源码）。""" def _relative(path: Path, root: Path) -> str: @@ -49,81 +33,100 @@ def _read(path: Path) -> str: return path.read_text(encoding="utf-8", errors="ignore") -class CodeParser: - """解析 Java 项目目录，输出 CodeStructure（控制器/服务/实体/端点/模块）。""" +class BaseLanguageParser: + """语言适配器基类：定义扩展名与单文件解析契约。 - def parse(self, root_path: str | Path) -> CodeStructure: - root = Path(root_path) - if not root.is_dir(): - raise CodeParseError(f"既有系统路径无效或不存在: {root_path}") + 子类需设置 language / extensions，并实现 parse_file： + 返回 dict（keys: imports / classes / controllers / services / entities / endpoints）。 + """ - java_files = sorted(p for p in root.rglob(f"*{_JAVA_EXT}") if p.is_file()) - if not java_files: - raise CodeParseError(f"未找到 Java 源码: {root_path}") + language: str = "" + extensions: tuple[str, ...] = () - controllers: list[ControllerInfo] = [] - services: list[ServiceInfo] = [] - entities: list[EntityInfo] = [] - endpoints: list[EndpointInfo] = [] - classes: list[dict] = [] - raw_imports: list[dict] = [] + def source_files(self, root: Path) -> list[Path]: + """返回本语言适配器覆盖的源文件（排序 + 去重，保证确定性）。""" + files: list[Path] = [] + for ext in self.extensions: + files.extend(p for p in root.rglob(f"*{ext}") if p.is_file()) + return sorted(set(files)) - for path in java_files: - text = _read(path) - rel = _relative(path, root) - class_name = self._class_name(text) + def parse_file(self, text: str, rel: str) -> dict: + """解析单个源文件，返回该文件对 CodeStructure 各分层的贡献。""" + raise NotImplementedError - imports = _IMPORT_RE.findall(text) - raw_imports.append({"path": rel, "imports": imports}) - if not class_name: - # package-info.java 等无类声明文件：仅登记 imports，不参与要素提取 - continue +class JavaLanguageParser(BaseLanguageParser): + """Java（Spring Boot / JPA / MyBatis-Plus）适配器。""" - is_controller = "@RestController" in text or "@Controller" in text - is_service = "@Service" in text - # 既有系统实体可能用 JPA @Entity 或 MyBatis-Plus @TableName 标注 - is_entity = "@Entity" in text or "@TableName" in text + language = "java" + extensions = (".java",) - if is_controller: - controllers.append(self._parse_controller(text, rel, class_name, endpoints)) - elif is_service: - services.append(self._parse_service(text, rel, class_name)) - elif is_entity: - entities.append(self._parse_entity(text, rel, class_name)) + _CLASS_RE = re.compile( + r"(?:public\s+|abstract\s+|final\s+)?(?:class|interface|enum|record)\s+(\w+)" + ) + _TABLE_RE = re.compile(r"@(?:Table|TableName)\s*\(\s*(?:name\s*=\s*)?[\"']([^\"']+)[\"']") + _CLASS_MAPPING_RE = re.compile(r"@RequestMapping\s*\(\s*[\"']([^\"']+)[\"']") + _METHOD_MAPPING_RE = re.compile( + r"@(Get|Post|Put|Delete|Patch|Request)Mapping\s*(?:\(\s*[\"']([^\"']*)[\"'])?" + ) + _METHOD_DECL_RE = re.compile( + r"(?:public|private|protected|)\s+(?:static\s+|final\s+|synchronized\s+)*" + r"[\w<>\[\],.?]+\s+(\w+)\s*\(" + ) + _FIELD_DECL_RE = re.compile( + r"(?:private|public|protected)\s+[\w<>\[\],]+\s+(\w+)\s*;" + ) + _IMPORT_RE = re.compile(r"^import\s+([\w.]+);", re.MULTILINE) - classes.append({"class_name": class_name, "path": rel}) + def parse_file(self, text: str, rel: str) -> dict: + class_name = self._class_name(text) + imports = self._IMPORT_RE.findall(text) + out: dict = { + "imports": imports, + "classes": [], + "controllers": [], + "services": [], + "entities": [], + "endpoints": [], + } + if not class_name: + # package-info.java 等无类声明文件：仅登记 imports，不参与要素提取 + return out - modules = self._modules(root, java_files) + out["classes"].append({"class_name": class_name, "path": rel}) - return CodeStructure( - root_path=str(root), - language="java", - modules=modules, - classes=classes, - controllers=controllers, - services=services, - entities=entities, - endpoints=endpoints, - raw_imports=raw_imports, - ) + is_controller = "@RestController" in text or "@Controller" in text + is_service = "@Service" in text + # 既有系统实体可能用 JPA @Entity 或 MyBatis-Plus @TableName 标注 + is_entity = "@Entity" in text or "@TableName" in text + + if is_controller: + ctrl, endpoints = self._parse_controller(text, rel, class_name) + out["controllers"].append(ctrl) + out["endpoints"] = endpoints + elif is_service: + out["services"].append(self._parse_service(text, rel, class_name)) + elif is_entity: + out["entities"].append(self._parse_entity(text, rel, class_name)) + return out @staticmethod def _class_name(text: str) -> str | None: - m = _CLASS_RE.search(text) + m = JavaLanguageParser._CLASS_RE.search(text) return m.group(1) if m else None @staticmethod def _parse_controller( - text: str, rel: str, class_name: str, endpoints: list[EndpointInfo] - ) -> ControllerInfo: + text: str, rel: str, class_name: str + ) -> tuple[ControllerInfo, list[EndpointInfo]]: base_path = "" - m = _CLASS_MAPPING_RE.search(text) + m = JavaLanguageParser._CLASS_MAPPING_RE.search(text) if m: base_path = m.group(1) ctrl_endpoints: list[str] = [] - for m in _METHOD_MAPPING_RE.finditer(text): + endpoints: list[EndpointInfo] = [] + for m in JavaLanguageParser._METHOD_MAPPING_RE.finditer(text): verb, sub = m.group(1).upper(), m.group(2) or "" if verb == "REQUEST": verb = "ANY" @@ -139,18 +142,21 @@ class CodeParser: ) ) - return ControllerInfo( - name=class_name, - class_name=class_name, - path=rel, - base_path=base_path, - endpoints=ctrl_endpoints, - source_uri=rel, + return ( + ControllerInfo( + name=class_name, + class_name=class_name, + path=rel, + base_path=base_path, + endpoints=ctrl_endpoints, + source_uri=rel, + ), + endpoints, ) @staticmethod def _parse_service(text: str, rel: str, class_name: str) -> ServiceInfo: - methods = list(dict.fromkeys(_METHOD_DECL_RE.findall(text))) + methods = list(dict.fromkeys(JavaLanguageParser._METHOD_DECL_RE.findall(text))) return ServiceInfo( name=class_name, class_name=class_name, @@ -162,10 +168,10 @@ class CodeParser: @staticmethod def _parse_entity(text: str, rel: str, class_name: str) -> EntityInfo: table_name = None - m = _TABLE_RE.search(text) + m = JavaLanguageParser._TABLE_RE.search(text) if m: table_name = m.group(1) - fields = list(dict.fromkeys(_FIELD_DECL_RE.findall(text))) + fields = list(dict.fromkeys(JavaLanguageParser._FIELD_DECL_RE.findall(text))) return EntityInfo( name=class_name, class_name=class_name, @@ -175,12 +181,93 @@ class CodeParser: source_uri=rel, ) + +# ---------- 语言适配器注册表 ---------- + +LANGUAGE_PARSERS: dict[str, type[BaseLanguageParser]] = {} + + +def register_language_parser(name: str, parser_cls: type[BaseLanguageParser]) -> None: + """注册语言适配器（未来扩展点：新增语言只需实现并注册，下游零改动）。""" + LANGUAGE_PARSERS[name] = parser_cls + + +register_language_parser(JavaLanguageParser.language, JavaLanguageParser) + + +class CodeParser: + """按语言分发解析既有系统目录，输出 CodeStructure。""" + + def parse(self, root_path: str | Path, language: str | None = None) -> CodeStructure: + root = Path(root_path) + if not root.is_dir(): + raise CodeParseError(f"既有系统路径无效或不存在: {root_path}") + + if language is not None: + cls = LANGUAGE_PARSERS.get(language) + if cls is None: + raise CodeParseError( + f"不支持的源码语言: {language}（支持: {', '.join(sorted(LANGUAGE_PARSERS))}）" + ) + parser_cls = [cls] + else: + # 自动探测：仅保留在根目录下确有源文件的语言 + present = [ + name for name in sorted(LANGUAGE_PARSERS) + if LANGUAGE_PARSERS[name]().source_files(root) + ] + if not present: + raise CodeParseError( + f"未找到可识别的源码（支持: {', '.join(sorted(LANGUAGE_PARSERS))}）: {root_path}" + ) + parser_cls = [LANGUAGE_PARSERS[name] for name in present] + + controllers: list[ControllerInfo] = [] + services: list[ServiceInfo] = [] + entities: list[EntityInfo] = [] + endpoints: list[EndpointInfo] = [] + classes: list[dict] = [] + raw_imports: list[dict] = [] + all_files: list[Path] = [] + + for cls in parser_cls: + parser = cls() + files = parser.source_files(root) + if not files: + # 自动探测的 present 过滤已保证有文件；此处仅显式 language 时可达 + raise CodeParseError(f"未找到 {parser.language} 源码: {root_path}") + all_files.extend(files) + for path in files: + text = _read(path) + rel = _relative(path, root) + out = parser.parse_file(text, rel) + raw_imports.append({"path": rel, "imports": out["imports"]}) + controllers.extend(out["controllers"]) + services.extend(out["services"]) + entities.extend(out["entities"]) + endpoints.extend(out["endpoints"]) + classes.extend(out["classes"]) + + modules = self._modules(root, all_files) + langs = [cls.language for cls in parser_cls] + return CodeStructure( + root_path=str(root), + language=",".join(langs) if len(langs) > 1 else langs[0], + modules=modules, + classes=classes, + controllers=controllers, + services=services, + entities=entities, + endpoints=endpoints, + raw_imports=raw_imports, + ) + @staticmethod - def _modules(root: Path, java_files: list[Path]) -> list[str]: - """顶层目录中凡包含 Java 源码者视为一个模块（按名排序，保证确定性）。""" + def _modules(root: Path, files: list[Path]) -> list[str]: + """顶层目录中凡包含源码者视为一个模块（按名排序，保证确定性）。""" mods = { p.relative_to(root).parts[0] - for p in java_files + for p in files if len(p.relative_to(root).parts) > 1 } return sorted(mods) diff --git a/src/genesis/parsers/source_aggregator.py b/src/genesis/parsers/source_aggregator.py index 7f8bdaa..4792745 100644 --- a/src/genesis/parsers/source_aggregator.py +++ b/src/genesis/parsers/source_aggregator.py @@ -45,11 +45,14 @@ class SourceParser: write_instruction_paths: list[str | Path] | None = None, rule_paths: list[str | Path] | None = None, existing_system_path: str | Path | None = None, + existing_system_language: str | None = None, ) -> StructuredSource: """扩展名校验先于存在性校验（不存在的文件若扩展名未知将抛出 ValueError 而非 FileNotFoundError）。 existing_system_path：既有系统源码目录（追加/改修场景）。提供时解析为 ExistingSystemInfo（门控通过 → 进入影响调查）；未提供/解析失败 → 保持 None。 + existing_system_language：既有系统源码开发语言（如 "java"）。默认 None 表示 + 由 CodeParser 按扩展名自动探测；显式指定时按该语言解析（多语言支持扩展点）。 """ requirement_paths = requirement_paths or [] @@ -77,7 +80,7 @@ class SourceParser: existing_system = None if existing_system_path is not None: - code = CodeParser().parse(existing_system_path) + code = CodeParser().parse(existing_system_path, language=existing_system_language) existing_system = ExistingSystemExplorer().explore(code) return StructuredSource( diff --git a/tests/test_code_parser.py b/tests/test_code_parser.py index ef94caa..96883bd 100644 --- a/tests/test_code_parser.py +++ b/tests/test_code_parser.py @@ -1,9 +1,17 @@ -"""CodeParser 测试（Impact Agent MVP）：Java 项目解析 → CodeStructure。""" +"""CodeParser 测试（Impact Agent MVP）：多语言适配器注册表 + Java 项目解析。""" from pathlib import Path import pytest -from genesis.impact.code_parser import CodeParseError, CodeParser +from genesis.data_models import ControllerInfo, EndpointInfo +from genesis.impact.code_parser import ( + LANGUAGE_PARSERS, + BaseLanguageParser, + CodeParseError, + CodeParser, + JavaLanguageParser, + register_language_parser, +) FIXTURE_JAVA = { "trade-order/src/main/java/com/trade/order/controller/OrderController.java": ( @@ -124,3 +132,106 @@ def test_parse_real_sample_has_entities_and_endpoints(): assert result.entities, "既有系统样本应至少有一个实体类" assert result.endpoints, "既有系统样本应至少有一个端点" assert result.services, "既有系统样本应至少有一个 @Service 类" + + +# ---------- 多语言适配器注册表（预备性重构） ---------- + +class _FakeParser(BaseLanguageParser): + """测试用假语言适配器：验证注册表/分发/多语言合并。""" + + language = "fake" + extensions = (".fx",) + + def parse_file(self, text: str, rel: str) -> dict: + return { + "imports": ["fake.import"], + "classes": [{"class_name": "FakeThing", "path": rel}], + "controllers": [ + ControllerInfo( + name="FakeThing", class_name="FakeThing", path=rel, + base_path="/fake", endpoints=["/fake"], source_uri=rel, + ) + ], + "services": [], + "entities": [], + "endpoints": [ + EndpointInfo( + method="GET", path="/fake", controller="FakeThing", + description="", source_uri=rel, + ) + ], + } + + +def test_language_registry_contains_java(): + assert "java" in LANGUAGE_PARSERS + assert issubclass(LANGUAGE_PARSERS["java"], BaseLanguageParser) + + +def test_java_parser_adapter_metadata(): + jp = JavaLanguageParser() + assert jp.language == "java" + assert ".java" in jp.extensions + + +def test_base_parser_parse_file_contract(): + with pytest.raises(NotImplementedError): + BaseLanguageParser().parse_file("text", "rel") + + +def test_parse_explicit_language(tmp_path): + root = _make_project(tmp_path, FIXTURE_JAVA) + result = CodeParser().parse(root, language="java") + assert {c.class_name for c in result.controllers} == {"OrderController"} + assert result.language == "java" + + +def test_parse_unsupported_language_raises(tmp_path): + root = _make_project(tmp_path, FIXTURE_JAVA) + with pytest.raises(CodeParseError): + CodeParser().parse(root, language="kotlin") + + +def test_parse_explicit_language_no_files_raises(tmp_path): + (tmp_path / "readme.txt").write_text("hello", encoding="utf-8") + with pytest.raises(CodeParseError): + CodeParser().parse(tmp_path, language="java") + + +def test_java_parse_file_interface(tmp_path): + jp = JavaLanguageParser() + text = FIXTURE_JAVA["trade-order/src/main/java/com/trade/order/controller/OrderController.java"] + out = jp.parse_file(text, "OrderController.java") + assert len(out["controllers"]) == 1 + assert out["controllers"][0].class_name == "OrderController" + assert {"/api/order/{id}", "/api/order/create"} <= {e.path for e in out["endpoints"]} + assert out["classes"] == [{"class_name": "OrderController", "path": "OrderController.java"}] + + +def test_register_and_dispatch_new_language(tmp_path): + register_language_parser("fake", _FakeParser) + try: + root = _make_project(tmp_path, { + "app/main.fx": "FAKE", + "trade-order/src/main/java/com/trade/order/controller/OrderController.java": ( + FIXTURE_JAVA["trade-order/src/main/java/com/trade/order/controller/OrderController.java"] + ), + }) + result = CodeParser().parse(root) + names = {c.class_name for c in result.controllers} + assert names == {"OrderController", "FakeThing"} + assert result.language == "fake,java" # 多语言按名排序逗号连接 + assert any(e.path == "/fake" for e in result.endpoints) + finally: + LANGUAGE_PARSERS.pop("fake", None) + + +def test_register_language_explicit_only(tmp_path): + register_language_parser("fake", _FakeParser) + try: + root = _make_project(tmp_path, {"a/main.fx": "FAKE"}) + result = CodeParser().parse(root, language="fake") + assert result.language == "fake" + assert [c.class_name for c in result.controllers] == ["FakeThing"] + finally: + LANGUAGE_PARSERS.pop("fake", None) diff --git a/tests/test_source_aggregator.py b/tests/test_source_aggregator.py index f116682..4702dfe 100644 --- a/tests/test_source_aggregator.py +++ b/tests/test_source_aggregator.py @@ -199,3 +199,31 @@ def test_parse_existing_system_path_without_java_raises(tmp_path): empty.mkdir() with pytest.raises(CodeParseError): SourceParser().parse(requirement_paths=[xlsx], existing_system_path=empty) + + +# ---------- 多语言预备重构：existing_system_language 透传 ---------- + +def test_parse_existing_system_language_explicit(tmp_path): + xlsx = _xlsx(tmp_path) + existing = _java_project(tmp_path) + + result = SourceParser().parse( + requirement_paths=[xlsx], + existing_system_path=existing, + existing_system_language="java", + ) + + assert result.existing_system is not None + assert {c.class_name for c in result.existing_system.controller_layer} == {"OrderController"} + + +def test_parse_existing_system_language_unsupported_raises(tmp_path): + xlsx = _xlsx(tmp_path) + existing = _java_project(tmp_path) + + with pytest.raises(CodeParseError): + SourceParser().parse( + requirement_paths=[xlsx], + existing_system_path=existing, + existing_system_language="kotlin", + )