Update and sort zh difficulty JSON file

The latest coct file removed 43 location names

pyproject.toml

@@ -19,7 +19,7 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-dev = ["mypy", "ruff", "requests"]
+dev = ["mypy", "ruff", "requests", "types-requests"]
 
 [project.scripts]
 proficiency = "proficiency.main:main"

src/proficiency/zh/README.md

@@ -4,11 +4,11 @@
 
 - [kaikki.org](https://kaikki.org/dictionary/Chinese/index.html)
 
-- [Corpus of Contemporary Taiwanese Mandarin](https://coct.naer.edu.tw/download/tech_report)
+- [華語文能力基準 三等七級詞語表(2022-11-14)](https://coct.naer.edu.tw/file/files/臺灣華語文能力基準詞語表_111-11-14.ods)
 
 ## Convert difficulty level
 
-- P1, 1, 1+, 2, 2+, 3, 3+ -> 5
+- 1, 1\*, 2, 2\*, 3, 3\* -> 5
 
 - 4 -> 4
 

src/proficiency/zh/convert_naer.py

@@ -4,20 +4,18 @@
 import re
 
 
-def convert_difficulty(level: str) -> int:
-    match level:
-        case "第P1級" | "第1級" | "第1+級" | "第2級" | "第2+級" | "第3級" | "第3+級":
+def convert_difficulty(level_str: str) -> int:
+    match int(level_str[1]):
+        case 1 | 2 | 3:
             return 5
-        case "第4級":
+        case 4:
             return 4
-        case "第5級":
+        case 5:
             return 3
-        case "第6級":
+        case 6:
             return 2
-        case "第7級":
-            return 1
         case _:
-            return -1
+            return 1
 
 
 def main() -> None:
@@ -55,7 +53,7 @@ def main() -> None:
                 words[word] = difficulty
 
     with open("difficulty.json", "w") as f:
-        json.dump(words, f, indent=2, ensure_ascii=False)
+        json.dump(words, f, indent=2, ensure_ascii=False, sort_keys=True)
 
 
 if __name__ == "__main__":