From be9bbcb8848271cba0c5b87be6e59625da4a4c66 Mon Sep 17 00:00:00 2001 From: shenjack <3695888@qq.com> Date: Fri, 15 Dec 2023 09:03:08 +0800 Subject: [PATCH] =?UTF-8?q?=E8=A7=A3=E6=9E=90=E4=B8=AD?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- scripts/parse-label.py | 105 ++++++++++++++++++++++++++--------------- tags/readme.md | 4 ++ 2 files changed, 72 insertions(+), 37 deletions(-) diff --git a/scripts/parse-label.py b/scripts/parse-label.py index f456a8c..b51cdcb 100644 --- a/scripts/parse-label.py +++ b/scripts/parse-label.py @@ -1,5 +1,5 @@ from pathlib import Path -from typing import Union +from typing import Union, Callable from pprint import pprint import mistune @@ -10,55 +10,78 @@ from lib_not_dr import loggers from lib_not_dr.types.options import Options -ast_markdown = mistune.create_markdown(renderer='ast') +ast_markdown = mistune.create_markdown(renderer="ast") ast_type = list[dict[str, Union[str, dict]]] +def get_all_iter( + ast: ast_type, type: str, func: Callable[[ast_type], bool] = None +) -> tuple[int, dict]: + for i, node in enumerate(ast): + if node["type"] == type: + if func is not None: + if not func(node): + continue + yield i, node + return -1, {} + + +def get_text(ast: ast_type) -> str: + """ + 返回第一个找到的字符串 + """ + ast = ast[0] + if ast['type'] == 'text': + return ast['raw'] + elif ast['type'] in ('link', 'block_text'): + return get_text(ast['children']) + + class TagParser(Options): module_root: Path tags: dict[str, list[str]] = {} + tag_map: dict[str, list[str]] = {} logger: loggers.logger.Logger = None # noqa - + def load_module(self, **kwargs): - for readme in self.module_root.rglob('readme.md'): + for readme in self.module_root.rglob("readme.md"): self.logger.debug(readme.absolute(), tag="load file") self.get_module_data(readme) - + tag_toml = dumps(self.tags) tag_path = self.module_root / ".." / "build" / "tags.toml" tag_path.parent.mkdir(parents=True, exist_ok=True) tag_path.touch(exist_ok=True) - with open(tag_path, 'w', encoding='utf-8') as file: + with open(tag_path, "w", encoding="utf-8") as file: file.write(tag_toml) - - + def get_module_data(self, module_path: Path): - with open(module_path, 'r', encoding='utf-8') as f: + with open(module_path, "r", encoding="utf-8") as f: file = f.read() ast = ast_markdown(file) if len(ast) == 0: return - if ast[0] != {'type': 'thematic_break'}: + if ast[0] != {"type": "thematic_break"}: # 排除开头不是注释块的 return - + self.logger.info(f"开始解析 {ast[1]}") config_code = ast[1].get("raw", "") config_dict = loads(config_code) self.logger.trace(config_dict) - - if not (tag_list := config_dict.get('tags')): + + if not (tag_list := config_dict.get("tags")): self.logger.warn("未找到 tags", tag=str(module_path)) return - + for tag in tag_list: if tag not in self.tags: self.tags[tag] = [module_path.__str__()] else: self.tags[tag].append(module_path.__str__()) - + def init(self, **kwargs) -> bool: self.logger = loggers.get_logger() self.logger.global_level = 0 @@ -71,42 +94,50 @@ class TagParser(Options): self.logger.error("未找到 tags/readme.md") return False - with open(tag_list_path, 'r', encoding='utf-8') as f: + with open(tag_list_path, "r", encoding="utf-8") as f: file = f.read() tag_ast: ast_type = ast_markdown(file) start_tag = -1 - for i, node in enumerate(tag_ast): - if node['type'] != 'heading': - continue - if node['attrs']['level'] != 2: - continue - # 说明是二级标题 - start_tag = i - break + # 找到二级标题 + start_tag = get_all_iter( + tag_ast, "heading", lambda node: node["attrs"]["level"] == 2 + ) + start_tag, node = next(start_tag) if start_tag == -1: self.logger.error("未找到二级标题") return False # 获取 tag - tag_ast: ast_type = tag_ast[start_tag + 1:] - - start_tag = -1 - for i, node in enumerate(tag_ast): - if node['type'] != 'list': - continue - start_tag = i - break + tag_ast: ast_type = tag_ast[start_tag + 1 :] + start_tag = get_all_iter(tag_ast, "list") + start_tag, node = next(start_tag) if start_tag == -1: self.logger.error("未找到 tag 列表") return False - tag_ast: ast_type = [item['children'] for item in tag_ast[start_tag]['children'] if item.get('type') == 'list_item'] + tag_ast: ast_type = [ + item["children"] + for item in tag_ast[start_tag]["children"] + if item.get("type") == "list_item" + ] # 顺手过滤一下 - pprint(tag_ast) - self.logger.info(tag_ast) + # pprint(tag_ast) + # self.logger.info(tag_ast) + for tag in tag_ast: + # self.logger.debug([(item['type'], item['children']) for item in tag]) + this_tag = get_text(tag) + if len(tag) == 1: + # 只有一个 tag, 无别名 + self.tag_map[this_tag] = [this_tag] + self.logger.info(f'添加 tag {this_tag}') + # len > 1 + elif len(tag) >= 1: + # 寻找 "别名" + self.logger.debug(tag) + pprint(tag) # 获取 tag 列表 -if __name__ == '__main__': - parser = TagParser(module_root = Path("modules")) +if __name__ == "__main__": + parser = TagParser(module_root=Path("modules")) parser.load_module() parser.logger.info(parser.tags) diff --git a/tags/readme.md b/tags/readme.md index 95b48cb..40d3a20 100644 --- a/tags/readme.md +++ b/tags/readme.md @@ -29,3 +29,7 @@ - [静音](./tags/silent.md) : 不会发出响声的模块。 - [单片](./tags/single_chip.md) : 1高或1宽的模块。 - [传统红石](./tags/traditional_redstone.md) : 仅使用红石方块特性，不使用墙电，水电，树电，脚电等其他特性的模块。 +- 测试 tag + - 只是用来测试的 + - 别名 + - 测试1