tree.py 14.4 KB
Newer Older
F
feilong 已提交
1
import json
L
luxin 已提交
2
import logging
F
feilong 已提交
3
import os
L
luxin 已提交
4 5
import re
import subprocess
F
feilong 已提交
6
import sys
L
luxin 已提交
7
import uuid
F
feilong 已提交
8 9 10 11 12 13 14 15 16 17 18
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)


L
luxin 已提交
19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
def search_author(author_dict, username):
    for key in author_dict:
        names = author_dict[key]
        if username in names:
            return key
    return username


def user_name(md_file, author_dict):
    ret = subprocess.Popen([
        "git", "log", md_file
    ], stdout=subprocess.PIPE)
    lines = list(map(lambda l: l.decode(), ret.stdout.readlines()))
    author_lines = []
    for line in lines:
        if line.startswith('Author'):
            author_lines.append(line.split(' ')[1])
    author_nick_name = author_lines[-1]
    return search_author(author_dict, author_nick_name)


F
feilong 已提交
40
def load_json(p):
L
luxin 已提交
41
    with open(p, 'r', encoding="utf-8") as f:
F
feilong 已提交
42 43 44 45 46 47 48 49 50 51 52 53
        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)

L
luxin 已提交
54
    with open(p, 'w+', encoding="utf8") as f:
F
feilong 已提交
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
        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


class TreeWalker:
L
luxin 已提交
96 97 98 99 100 101 102 103 104 105 106 107
    def __init__(
            self, root,
            tree_name,
            title=None,
            log=None,
            authors=None,
            enable_notebook=None,
            ignore_keywords=False
    ):
        self.ignore_keywords = ignore_keywords
        self.authors = authors if authors else {}
        self.enable_notebook = enable_notebook
F
feilong 已提交
108 109 110 111 112 113 114 115 116 117 118
        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"],
L
luxin 已提交
119 120 121
            "children": [],
            "keywords_must": root["keywords_must"],
            "keywords_forbid": root["keywords_forbid"]
F
feilong 已提交
122 123 124 125 126 127 128
        }
        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]
L
luxin 已提交
129
            level_path = os.path.join(self.root, f"{index + 1}.{level_title}")
F
feilong 已提交
130 131 132 133 134
            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(
L
luxin 已提交
135
                    level_path, f"{index + 1}.{chapter_title}")
F
feilong 已提交
136 137 138 139
                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(
L
luxin 已提交
140
                        chapter_path, f"{index + 1}.{section_title}")
F
feilong 已提交
141
                    if os.path.isdir(full_path):
L
luxin 已提交
142
                        self.check_section_keywords(full_path)
F
feilong 已提交
143 144 145 146 147 148
                        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

L
luxin 已提交
149 150 151 152 153
    def sort_dir_list(self, dirs):
        result = [self.extract_node_env(dir) for dir in dirs]
        result.sort(key=lambda item: item[0])
        return result

F
feilong 已提交
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175
    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 = self.resort_children(self.root, levels)
        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": [],
L
luxin 已提交
176 177
                "keywords_must": config["keywords_must"],
                "keywords_forbid": config["keywords_forbid"]
F
feilong 已提交
178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211
            }
        }

        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 = self.resort_children(base, chapters)
        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 = self.resort_children(base, sections)
        chapter_node["children"] = [item[1] for item in sections]
        return chapter_node

    def resort_children(self, base, children):
        children.sort(key=lambda item: item[0])
        for index, [number, element] in enumerate(children):
            title = list(element.keys())[0]
            origin = os.path.join(base, f"{number}.{title}")
L
luxin 已提交
212
            posted = os.path.join(base, f"{index + 1}.{title}")
F
feilong 已提交
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
            if origin != posted:
                self.logger.info(f"rename [{origin}] to [{posted}]")
            os.rename(origin, posted)
        return children

    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(),
L
luxin 已提交
229 230
                "keywords_must": [],
                "keywords_forbid": []
F
feilong 已提交
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
            }
            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(),
L
luxin 已提交
260 261 262
                "keywords": [],
                "keywords_must": [],
                "keywords_forbid": []
F
feilong 已提交
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
            }
            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:
L
luxin 已提交
286
                dump_json(config_path, result, exist_ok=True, override=True)
F
feilong 已提交
287 288 289
        return config

    def ensure_node_id(self, config):
L
luxin 已提交
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
        flag = False
        if "node_id" not in config or \
                not config["node_id"].startswith(f"{self.name}-") or \
                config["node_id"] in id_set:
            new_id = self.gen_node_id()
            id_set.add(new_id)
            config["node_id"] = new_id
            flag = True

        for child in config.get("children", []):
            child_node = list(child.values())[0]
            f, _ = self.ensure_node_id(child_node)
            flag = flag or f

        return flag, config
F
feilong 已提交
305 306 307 308 309 310 311 312 313 314 315 316

    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")
L
luxin 已提交
317 318
            # sys.exit(1)
            raise error
F
feilong 已提交
319 320 321 322 323 324 325 326 327

    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": [],
L
luxin 已提交
328 329
                "keywords_must": config["keywords_must"],
                "keywords_forbid": config["keywords_forbid"]
F
feilong 已提交
330 331 332 333 334 335 336 337 338 339 340
            }
        }
        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"],
L
luxin 已提交
341 342 343
                "children": config.get("children", []),
                "keywords_must": config["keywords_must"],
                "keywords_forbid": config["keywords_forbid"]
F
feilong 已提交
344 345 346 347 348 349 350 351
            }
        }
        # if "children" in config:
        #     result["children"] = config["children"]
        return num, result

    def ensure_exercises(self, section_path):
        config = self.ensure_section_config(section_path)
L
luxin 已提交
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
        flag = False
        for e in os.listdir(section_path):
            base, ext = os.path.splitext(e)
            _, source = os.path.split(e)
            if ext != ".md":
                continue
            mfile = base + ".json"
            meta_path = os.path.join(section_path, mfile)
            md_file = os.path.join(section_path, e)
            self.ensure_exercises_meta(meta_path, source, md_file)
            export = config.get("export", [])
            if mfile not in export and self.name != "algorithm":
                export.append(mfile)
                flag = True
                config["export"] = export

        if flag:
            dump_json(os.path.join(section_path, "config.json"),
                      config, True, True)

F
feilong 已提交
372 373 374
        for e in config.get("export", []):
            full_name = os.path.join(section_path, e)
            exercise = load_json(full_name)
L
luxin 已提交
375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425
            if "exercise_id" not in exercise or exercise.get("exercise_id") in id_set:
                eid = uuid.uuid4().hex
                exercise["exercise_id"] = eid
                dump_json(full_name, exercise, True, True)
            else:
                id_set.add(exercise["exercise_id"])

    def ensure_exercises_meta(self, meta_path, source, md_file):
        _, mfile = os.path.split(meta_path)
        meta = None
        if os.path.exists(meta_path):
            with open(meta_path) as f:
                content = f.read()
            if content:
                meta = json.loads(content)
                if "exercise_id" not in meta:
                    meta["exercise_id"] = uuid.uuid4().hex
                if "notebook_enable" not in meta:
                    meta["notebook_enable"] = self.default_notebook()
                if "source" not in meta:
                    meta["source"] = source
                if "author" not in meta:
                    meta["author"] = user_name(md_file, self.authors)
                if "type" not in meta:
                    meta["type"] = "code_options"

        if meta is None:
            meta = {
                "type": "code_options",
                "author": user_name(md_file, self.authors),
                "source": source,
                "notebook_enable": self.default_notebook(),
                "exercise_id": uuid.uuid4().hex
            }
        dump_json(meta_path, meta, True, True)

    def default_notebook(self):
        if self.enable_notebook is not None:
            return self.enable_notebook
        if self.name in ["python", "java", "c"]:
            return True
        else:
            return False

    def check_section_keywords(self, full_path):
        if self.ignore_keywords:
            return
        config = self.ensure_section_config(full_path)
        if not config.get("keywords", []):
            self.logger.error(f"节点 [{full_path}] 的关键字为空,请修改配置文件写入关键字")
            sys.exit(1)