隐藏token

.gitignore

@@ -11,3 +11,4 @@ data_source/dailycode
 test.cpp
 test.py
 test.java
+tree_algorithm_view.xlsx
\ No newline at end of file

helper.py

@@ -6,6 +6,8 @@ import collections
 import uuid
 import json
 import shutil
+import pandas as pd
+from pyparsing import match_previous_expr
 
 
 def get_files_path(file_dir, filetype='.txt'):
@@ -518,4 +520,46 @@ def auto_gen_increment_exercises_template():
                     f.write(solution_md_data)
 
 
-auto_gen_increment_exercises_template()
\ No newline at end of file
+from fuzzywuzzy import fuzz
+
+def add_skilltree_leaf_link():
+    data = pd.read_excel('tree_algorithm_view.xlsx')
+
+    dir_list = ['data/1.dailycode初阶', 'data/2.dailycode中阶', 'data/3.dailycode高阶']
+    languages = ['1.cpp', '2.java', '3.python']
+    cout = 0
+    for dir in dir_list:
+        for language in languages:
+            dest_dir = os.path.join(dir, language)
+            exercises_dirs_ = os.listdir(dest_dir)
+            exercises_dirs = []
+            for tem_dir in exercises_dirs_:
+                tem_dir = os.path.join(dest_dir, tem_dir)
+                if os.path.isdir(tem_dir):
+                    solution_md_path = os.path.join(tem_dir, 'solution.md')
+                    with open(solution_md_path, 'r') as f:
+                        solution_md_data = f.read()
+                    title = re.findall(r'^# (.*)\n', solution_md_data)[0]
+
+                    match_res = []
+                    for idx, item in data.iterrows():
+                        text = item[2] + '-' + item[3]
+                        link = 'https://edu.csdn.net/skill/algorithm/{}'.format(item[4])
+                        match_score = fuzz.partial_ratio(title, text)
+                        match_res.append(match_score)
+                    max_score = max(match_res)
+                    index = match_res.index(max_score)
+                    target = data.loc[index][3]
+                    link = 'https://edu.csdn.net/skill/algorithm/{}'.format(data.loc[index][4])
+
+                    solution_json_path = os.path.join(tem_dir, 'solution.json')
+                    solution_json_data = load_json(solution_json_path)
+                    solution_json_data['skilltree_link'] = link
+                    dump_json(solution_json_path, solution_json_data)
+
+                    print("query: ", title, "target: ", target, "max_score: ", max_score)
+                    print(link)
+
+
+
+add_skilltree_leaf_link()
\ No newline at end of file