init rust skill_tree repo

.gitignore

+target/
+.vscode
+.idea
+.DS_Store
+__pycache__
+*.pyc
+*.zip
+*.out
+Cargo.lock
\ No newline at end of file

README.md

 # skill_tree_rust
 
 Rust 技能树
+
+## 初始化技能树
+
+技能树合成和id生成脚本目前用Python脚本统一处理
+
+```bash
+pip install -r requirement.txt
+```
+
+
+## 目录结构说明
+
+* 技能树`骨架文件`：
+    * 位置：`data/tree.json` 
+    * 说明：该文件是执行 `python main.py` 生成的，请勿人工编辑
+* 技能树`根节点`配置文件：
+    * 位置：`data/config.json`
+    * 说明：可编辑配置关键词等字段，其中 `node_id` 字段是生成的，请勿编辑
+* 技能树`难度节点`：
+    * 位置：`data/xxx`，例如: `data/1.rust初阶`
+    * 说明：
+        * 每个技能树有 3 个等级，目录前的序号是**必要**的，用来保持文件夹目录的顺序
+        * 每个目录下有一个 `config.json` 可配置关键词信息，其中 `node_id` 字段是生成的，请勿编辑
+* 技能树`章节点`：
+    * 位置：`data/xxx/xxx`，例如：`data/1.rust初阶/1.预备知识`
+    * 说明：
+        * 每个技能树的每个难度等级有 n 个章节，目录前的序号是**必要**的，用来保持文件夹目录的顺序
+        * 每个目录下有一个 `config.json` 可配置关键词信息，其中 `node_id` 字段是生成的，请勿编辑
+* 技能树`知识节点`：
+    * 位置：`data/xxx/xxx`，例如：`data/1.rust初阶/1.预备知识/1.rust简介`
+    * 说明：
+        * 每个技能树的每章有 n 个知识节点，目录前的序号是必要的，用来保持文件夹目录的顺序
+        * 每个目录下有一个 `config.json`
+            * 其中 `node_id` 字段是生成的，请勿编辑
+            * 其中 `keywords` 可配置关键字字段
+            * 其中 `children` 可配置该`知识节点`下的子树结构信息，参考后面描述
+            * 其中 `export` 可配置该`知识节点`下的导出习题信息，参考后面描述
+
+
+## `知识节点` 子树信息结构
+
+例如 `data/1.rust初阶/1.预备知识/1.rust简介/config.json` 里配置对该知识节点子树信息结构，用来增加技能树服务在该知识节点上的深度数据匹配：
+
+```json
+{
+    // ...
+
+    "children": [
+        {
+            "Rust的起源": {
+                "keywords": [
+                    "Rust的起源",
+                    "起源",
+                    "Rust"
+                ],
+                "children": []
+            }
+        }
+    ],
+}
+```
+
+
+## `知识节点` 的导出习题编辑
+
+例如 `data/1.rust初阶/1.预备知识/1.rust简介/config.json` 里配置对该知识节点导出的习题
+
+```json
+{
+    // ...
+    "export": [
+        "helloworld.json",
+        // ...
+    ]
+}
+```
+
+在 `export` 字段中，我们列出习题定义的`json`文件列表 ，下面我们了解如何编写习题。
+
+## `知识节点` 的导出习题选项配置编辑
+
+目前我们支持使用 markdown 语法直接编辑习题和各选项。
+
+如前文内容，我们在知识节点下增加习题 `helloworld`的定义文件，即在`data/1.rust初阶/1.预备知识/1.rust简介` 目录增加一个`helloworld.json`文件：
+
+```json
+{
+    "type": "code_options",
+    "author": "幻灰龙",
+    "source": "helloworld.md",
+    "notebook_enable": true
+}
+```
+
+其中
+
+* `type` 字段目前都固定是 `code_options`，
+* `notebook_enable` 字段决定这个习题是否生成对应的 `notebook` 
+* `source` 字段代表习题编辑的 `markdwon` 文件。
+
+现在我们新建一个 `helloworld.md` 并编辑为：
+
+````markdown
+# Hello World
+
+编写一个输出 "Hello,World!" 的 Rust 程序，以下错误的是？
+
+## 答案
+
+```rust
+fn main() {
+    let str1 = "Hello,";
+    let str2 = "World!";
+    println!("{}", str1+str2);
+}
+```
+
+## 选项
+
+### 直接打印
+
+```rust
+fn main() {
+    let str = "Hello,World!";
+    println!("{}", str);
+}
+```
+
+### 使用格式划宏拼接
+
+```rust
+fn main() {
+    let str = "Hello";
+    let str = format!("{},World", str);
+    println!("{}", str);
+}
+```
+
+### 使用 String::from
+
+```rust
+fn main() {
+    let str1 = String::from("Hello");
+    let str2 = String::from("World");
+    let str = format!("{},{}!", str1, str2);
+    println!("{}", str);
+}
+
+```
+
+### 使用mut+push_str
+
+```rust
+fn main() {
+    let mut str1 = String::from("Hello,");
+    let str2 = String::from("World!");
+    str1.push_str(str2.as_str());
+    println!("{}", str1);
+}
+```
+````
+
+这是一个最基本的习题结构，它包含标题、答案、选项，注意这几个一级和二级标题必须填写正确，解释器会读取这几个标题。而选项的标题会被直接忽略掉，在
+最终生成的习题中不包含选项的三级标题，所以这个标题可以用来标注一些编辑信息，例如“使用mut+push_str”，“使用格式划宏拼接”等等。
+
+## 可选的习题源代码项目
+
+编辑习题中，为了测试方便，可以直接在知识点目录下创建对应的 `rust源代码项目目录`
+
+例如 `data/1.rust初阶/1.预备知识/1.rust简介/helloworld/`，就是通过`cargo new helloworld` 创建的测试 `helloworld.md` 里描述的习题用的 rust 源代码项目。执行命令 `cargo build` 和 `cargo run` 可以便利地测试程序。
+
+
+## 技能树合成
+
+在根目录下执行 `python main.py` 会合成技能树文件，合成的技能树文件: `data/tree.json`
+
+* 合成过程中，会自动检查每个目录下 `config.json` 里的 `node_id` 是否存在，不存在则生成
+* 合成过程中，会自动检查每个知识点目录下 `config.json` 里的 `export` 里导出的习题配置，检查是否存在`exercise_id` 字段，如果不存在则生成

data/1.rust初阶/1.预备知识/1.rust简介/config.json

+{
+  "node_id": "rust-7c394f164d8f44519521f03db08a1321",
+  "keywords": [],
+  "children": [],
+  "export": []
+}
\ No newline at end of file

data/1.rust初阶/1.预备知识/1.rust简介/helloworld/Cargo.toml

+[package]
+name = "helloworld"
+version = "0.1.0"
+authors = ["feilong <fanfeilong@outlook.com>"]
+edition = "2018"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]

data/1.rust初阶/1.预备知识/1.rust简介/helloworld/src/main.rs

+fn main() {
+    let mut str1 = String::from("Hello,");
+    let str2 = String::from("World!");
+    str1.push_str(str2.as_str());
+    println!("{}", str1);
+}

data/1.rust初阶/1.预备知识/2.rust安装/config.json

+{
+  "node_id": "rust-502b3cef4dbc41fdad069522470f3662",
+  "keywords": [],
+  "children": [],
+  "export": []
+}
\ No newline at end of file

data/1.rust初阶/1.预备知识/3.认识rust工具链/config.json

+{
+  "node_id": "rust-0d9e5f9449b94aa692a363f21a66c8af",
+  "keywords": [],
+  "children": [],
+  "export": []
+}
\ No newline at end of file

data/1.rust初阶/1.预备知识/config.json

+{
+  "node_id": "rust-c3878925dc9d4ad6b45e244beceb5c87",
+  "keywords": []
+}
\ No newline at end of file

data/1.rust初阶/2.rust基本概念/config.json

+{
+  "node_id": "rust-2cea732119294abab6f2887a364b242a",
+  "keywords": []
+}
\ No newline at end of file

data/1.rust初阶/config.json

+{
+  "node_id": "rust-e2292238ccbf403d85fb20dd7b4c85ad",
+  "keywords": []
+}
\ No newline at end of file

data/2.rust中阶/config.json

+{
+  "node_id": "rust-7377966439734497b91f3d775f9b0e0d",
+  "keywords": []
+}
\ No newline at end of file

data/3.rust高阶/config.json

+{
+  "node_id": "rust-981f4f37a8e547abb135f54592ac52a5",
+  "keywords": []
+}
\ No newline at end of file

data/config.json

+{
+  "tree_name": "rust",
+  "keywords": [],
+  "node_id": "rust-bab5ea3c37134f5a8fc69630792d9adb"
+}
\ No newline at end of file

data/tree.json

+{
+  "rust": {
+    "node_id": "rust-bab5ea3c37134f5a8fc69630792d9adb",
+    "keywords": [],
+    "children": [
+      {
+        "rust初阶": {
+          "node_id": "rust-e2292238ccbf403d85fb20dd7b4c85ad",
+          "keywords": [],
+          "children": [
+            {
+              "预备知识": {
+                "node_id": "rust-c3878925dc9d4ad6b45e244beceb5c87",
+                "keywords": [],
+                "children": [
+                  {
+                    "rust简介": {
+                      "node_id": "rust-7c394f164d8f44519521f03db08a1321",
+                      "keywords": [],
+                      "children": []
+                    }
+                  },
+                  {
+                    "rust安装": {
+                      "node_id": "rust-502b3cef4dbc41fdad069522470f3662",
+                      "keywords": [],
+                      "children": []
+                    }
+                  },
+                  {
+                    "认识rust工具链": {
+                      "node_id": "rust-0d9e5f9449b94aa692a363f21a66c8af",
+                      "keywords": [],
+                      "children": []
+                    }
+                  }
+                ]
+              }
+            },
+            {
+              "rust基本概念": {
+                "node_id": "rust-2cea732119294abab6f2887a364b242a",
+                "keywords": [],
+                "children": []
+              }
+            }
+          ]
+        }
+      },
+      {
+        "rust中阶": {
+          "node_id": "rust-7377966439734497b91f3d775f9b0e0d",
+          "keywords": [],
+          "children": []
+        }
+      },
+      {
+        "rust高阶": {
+          "node_id": "rust-981f4f37a8e547abb135f54592ac52a5",
+          "keywords": [],
+          "children": []
+        }
+      }
+    ]
+  }
+}
\ No newline at end of file

main.py

+from json import load
+from src.tree import TreeWalker, load_json, dump_json
+
+import os
+import re
+
+if __name__ == '__main__':
+    walker = TreeWalker("data", "rust", "rust")
+    walker.walk()

src/tree.py

+import logging
+from genericpath import exists
+import json
+import os
+import uuid
+import sys
+import re
+
+id_set = set()
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+handler = logging.StreamHandler(sys.stdout)
+formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
+handler.setFormatter(formatter)
+logger.addHandler(handler)
+
+
+def load_json(p):
+    with open(p, 'r') as f:
+        return json.loads(f.read())
+
+
+def dump_json(p, j, exist_ok=False, override=False):
+    if os.path.exists(p):
+        if exist_ok:
+            if not override:
+                return
+        else:
+            logger.error(f"{p} already exist")
+            sys.exit(0)
+
+    with open(p, 'w+') as f:
+        f.write(json.dumps(j, indent=2, ensure_ascii=False))
+
+
+def ensure_config(path):
+    config_path = os.path.join(path, "config.json")
+    if not os.path.exists(config_path):
+        node = {"keywords": []}
+        dump_json(config_path, node, exist_ok=True, override=False)
+        return node
+    else:
+        return load_json(config_path)
+
+
+def parse_no_name(d):
+    p = r'(\d+)\.(.*)'
+    m = re.search(p, d)
+
+    try:
+        no = int(m.group(1))
+        dir_name = m.group(2)
+    except:
+        sys.exit(0)
+
+    return no, dir_name
+
+
+def check_export(base, cfg):
+    flag = False
+    exports = []
+    for export in cfg.get('export', []):
+        ecfg_path = os.path.join(base, export)
+        if os.path.exists(ecfg_path):
+            exports.append(export)
+        else:
+            flag = True
+    if flag:
+        cfg["export"] = exports
+    return flag
+
+
+def gen_node_id():
+    return "oceanbase-" + uuid.uuid4().hex
+
+
+class TreeWalker:
+    def __init__(self, root, tree_name, title=None, log=None):
+        self.name = tree_name
+        self.root = root
+        self.title = tree_name if title is None else title
+        self.tree = {}
+        self.logger = logger if log is None else log
+
+    def walk(self):
+        root = self.load_root()
+        root_node = {
+            "node_id": root["node_id"],
+            "keywords": root["keywords"],
+            "children": []
+        }
+        self.tree[root["tree_name"]] = root_node
+        self.load_levels(root_node)
+        self.load_chapters(self.root, root_node)
+        for index, level in enumerate(root_node["children"]):
+            level_title = list(level.keys())[0]
+            level_node = list(level.values())[0]
+            level_path = os.path.join(self.root, f"{index+1}.{level_title}")
+            self.load_chapters(level_path, level_node)
+            for index, chapter in enumerate(level_node["children"]):
+                chapter_title = list(chapter.keys())[0]
+                chapter_node = list(chapter.values())[0]
+                chapter_path = os.path.join(
+                    level_path, f"{index+1}.{chapter_title}")
+                self.load_sections(chapter_path, chapter_node)
+                for index, section_node in enumerate(chapter_node["children"]):
+                    section_title = list(section_node.keys())[0]
+                    full_path = os.path.join(
+                        chapter_path, f"{index}.{section_title}")
+                    if os.path.isdir(full_path):
+                        self.ensure_exercises(full_path)
+
+        tree_path = os.path.join(self.root, "tree.json")
+        dump_json(tree_path, self.tree, exist_ok=True, override=True)
+        return self.tree
+
+    def load_levels(self, root_node):
+        levels = []
+        for level in os.listdir(self.root):
+            if not os.path.isdir(level):
+                continue
+            level_path = os.path.join(self.root, level)
+            num, config = self.load_level_node(level_path)
+            levels.append((num, config))
+        levels.sort(key=lambda item: item[0])
+        root_node["children"] = [item[1] for item in levels]
+        return root_node
+
+    def load_level_node(self, level_path):
+        config = self.ensure_level_config(level_path)
+        num, name = self.extract_node_env(level_path)
+
+        result = {
+            name: {
+                "node_id": config["node_id"],
+                "keywords": config["keywords"],
+                "children": [],
+            }
+        }
+
+        return num, result
+
+    def load_chapters(self, base, level_node):
+        chapters = []
+        for name in os.listdir(base):
+            full_name = os.path.join(base, name)
+            if os.path.isdir(full_name):
+                num, chapter = self.load_chapter_node(full_name)
+                chapters.append((num, chapter))
+
+        chapters.sort(key=lambda item: item[0])
+        level_node["children"] = [item[1] for item in chapters]
+        return level_node
+
+    def load_sections(self, base, chapter_node):
+        sections = []
+        for name in os.listdir(base):
+            full_name = os.path.join(base, name)
+            if os.path.isdir(full_name):
+                num, section = self.load_section_node(full_name)
+                sections.append((num, section))
+
+        sections.sort(key=lambda item: item[0])
+        chapter_node["children"] = [item[1] for item in sections]
+        return chapter_node
+
+    def ensure_chapters(self):
+        for subdir in os.listdir(self.root):
+            self.ensure_level_config(subdir)
+
+    def load_root(self):
+        config_path = os.path.join(self.root, "config.json")
+        if not os.path.exists(config_path):
+            config = {
+                "tree_name": self.name,
+                "keywords": [],
+                "node_id": self.gen_node_id(),
+            }
+            dump_json(config_path, config, exist_ok=True, override=True)
+        else:
+            config = load_json(config_path)
+            flag, result = self.ensure_node_id(config)
+            if flag:
+                dump_json(config_path, result, exist_ok=True, override=True)
+
+        return config
+
+    def ensure_level_config(self, path):
+        config_path = os.path.join(path, "config.json")
+        if not os.path.exists(config_path):
+            config = {
+                "node_id": self.gen_node_id()
+            }
+            dump_json(config_path, config, exist_ok=True, override=True)
+        else:
+            config = load_json(config_path)
+            flag, result = self.ensure_node_id(config)
+            if flag:
+                dump_json(config_path, config, exist_ok=True, override=True)
+        return config
+
+    def ensure_chapter_config(self, path):
+        config_path = os.path.join(path, "config.json")
+        if not os.path.exists(config_path):
+            config = {
+                "node_id": self.gen_node_id(),
+                "keywords": []
+            }
+            dump_json(config_path, config, exist_ok=True, override=True)
+        else:
+            config = load_json(config_path)
+            flag, result = self.ensure_node_id(config)
+            if flag:
+                dump_json(config_path, config, exist_ok=True, override=True)
+        return config
+
+    def ensure_section_config(self, path):
+        config_path = os.path.join(path, "config.json")
+        if not os.path.exists(config_path):
+            config = {
+                "node_id": self.gen_node_id(),
+                "keywords": [],
+                "children": [],
+                "export": []
+            }
+            dump_json(config_path, config, exist_ok=True, override=True)
+        else:
+            config = load_json(config_path)
+            flag, result = self.ensure_node_id(config)
+            if flag:
+                dump_json(config_path, config, exist_ok=True, override=True)
+        return config
+
+    def ensure_node_id(self, config):
+        if "node_id" not in config:
+            config["node_id"] = self.gen_node_id()
+            return True, config
+        else:
+            return False, config
+
+    def gen_node_id(self):
+        return f"{self.name}-{uuid.uuid4().hex}"
+
+    def extract_node_env(self, path):
+        try:
+            _, dir = os.path.split(path)
+            self.logger.info(path)
+            number, title = dir.split(".", 1)
+            return int(number), title
+        except Exception as error:
+            self.logger.error(f"目录 [{path}] 解析失败，结构不合法，可能是缺少序号")
+            sys.exit(1)
+
+    def load_chapter_node(self, full_name):
+        config = self.ensure_chapter_config(full_name)
+        num, name = self.extract_node_env(full_name)
+        result = {
+            name: {
+                "node_id": config["node_id"],
+                "keywords": config["keywords"],
+                "children": [],
+            }
+        }
+        return num, result
+
+    def load_section_node(self, full_name):
+        config = self.ensure_section_config(full_name)
+        num, name = self.extract_node_env(full_name)
+        result = {
+            name: {
+                "node_id": config["node_id"],
+                "keywords": config["keywords"],
+                "children": config.get("children", [])
+            }
+        }
+        # if "children" in config:
+        #     result["children"] = config["children"]
+        return num, result
+
+    def ensure_exercises(self, section_path):
+        config = self.ensure_section_config(section_path)
+        for e in config.get("export", []):
+            full_name = os.path.join(section_path, e)
+            exercise = load_json(full_name)
+            if "exercise_id" not in exercise:
+                exercise["exercise_id"] = uuid.uuid4().hex
+                dump_json(full_name, exercise)