sync tree.py script

src/tree.py

@@ -2,10 +2,11 @@ import json
 import logging
 import os
 import re
+import subprocess
 import sys
 import uuid
 import re
-import git
+
 
 id_set = set()
 logger = logging.getLogger(__name__)
@@ -14,10 +15,25 @@ handler = logging.StreamHandler(sys.stdout)
 formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
 handler.setFormatter(formatter)
 logger.addHandler(handler)
-repo = git.Repo(".")
 
-def user_name():
-    return repo.config_reader().get_value("user", "name")
+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)
 
 def load_json(p):
     with open(p, 'r') as f:
@@ -75,7 +91,18 @@ def check_export(base, cfg):
 
 
 class TreeWalker:
-    def __init__(self, root, tree_name, title=None, log=None):
+    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
         self.name = tree_name
         self.root = root
         self.title = tree_name if title is None else title
@@ -87,7 +114,9 @@ class TreeWalker:
         root_node = {
             "node_id": root["node_id"],
             "keywords": root["keywords"],
-            "children": []
+            "children": [],
+            "keywords_must": root["keywords_must"],
+            "keywords_forbid": root["keywords_forbid"]
         }
         self.tree[root["tree_name"]] = root_node
         self.load_levels(root_node)
@@ -100,11 +129,13 @@ class TreeWalker:
             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}")
+                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 + 1}.{section_title}")
+                    full_path = os.path.join(
+                        chapter_path, f"{index + 1}.{section_title}")
                     if os.path.isdir(full_path):
                         self.check_section_keywords(full_path)
                         self.ensure_exercises(full_path)
@@ -140,6 +171,8 @@ class TreeWalker:
                 "node_id": config["node_id"],
                 "keywords": config["keywords"],
                 "children": [],
+                "keywords_must": config["keywords_must"],
+                "keywords_forbid": config["keywords_forbid"]
             }
         }
 
@@ -191,6 +224,8 @@ class TreeWalker:
                 "tree_name": self.name,
                 "keywords": [],
                 "node_id": self.gen_node_id(),
+                "keywords_must": [],
+                "keywords_forbid": []
             }
             dump_json(config_path, config, exist_ok=True, override=True)
         else:
@@ -220,7 +255,9 @@ class TreeWalker:
         if not os.path.exists(config_path):
             config = {
                 "node_id": self.gen_node_id(),
-                "keywords": []
+                "keywords": [],
+                "keywords_must": [],
+                "keywords_forbid": []
             }
             dump_json(config_path, config, exist_ok=True, override=True)
         else:
@@ -286,6 +323,8 @@ class TreeWalker:
                 "node_id": config["node_id"],
                 "keywords": config["keywords"],
                 "children": [],
+                "keywords_must": config["keywords_must"],
+                "keywords_forbid": config["keywords_forbid"]
             }
         }
         return num, result
@@ -297,7 +336,9 @@ class TreeWalker:
             name: {
                 "node_id": config["node_id"],
                 "keywords": config["keywords"],
-                "children": config.get("children", [])
+                "children": config.get("children", []),
+                "keywords_must": config["keywords_must"],
+                "keywords_forbid": config["keywords_forbid"]
             }
         }
         # if "children" in config:
@@ -314,7 +355,8 @@ class TreeWalker:
                 continue
             mfile = base + ".json"
             meta_path = os.path.join(section_path, mfile)
-            self.ensure_exercises_meta(meta_path, source)
+            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)
@@ -322,7 +364,8 @@ class TreeWalker:
                 config["export"] = export
 
         if flag:
-            dump_json(os.path.join(section_path, "config.json"), config, True, True)
+            dump_json(os.path.join(section_path, "config.json"),
+                      config, True, True)
 
         for e in config.get("export", []):
             full_name = os.path.join(section_path, e)
@@ -334,7 +377,7 @@ class TreeWalker:
             else:
                 id_set.add(exercise["exercise_id"])
 
-    def ensure_exercises_meta(self, meta_path, source):
+    def ensure_exercises_meta(self, meta_path, source, md_file):
         _, mfile = os.path.split(meta_path)
         meta = None
         if os.path.exists(meta_path):
@@ -349,26 +392,31 @@ class TreeWalker:
                 if "source" not in meta:
                     meta["source"] = source
                 if "author" not in meta:
-                    meta["author"] = user_name()
+                    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(),
-                    "source": source,
-                    "notebook_enable": self.default_notebook(),
-                    "exercise_id": uuid.uuid4().hex
-                }
+
+        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")