fix: complete language version IDs for all platforms (#350)

## Problem

`LANGUAGE_VERSIONS` only covered cpp and python. Several platform IDs
were wrong — CodeChef used `C++ 17`/`Python 3` (correct: `C++`/`PYTH
3`), USACO listed nonexistent c++20/c++23 options, and CSES only had
C++17.

## Solution

Verify every platform's submit page and update all language ID tables.
Add java and rust entries where supported, fix incorrect CodeChef and
USACO IDs, and expand CSES `CSES_LANGUAGES` dict with
C++11/C++20/PyPy3/Java/Rust variants.

doc/cp.nvim.txt

@@ -1056,13 +1056,13 @@ Set {version} globally or per-platform:
 <
 Available versions per platform ~
 
-  Platform    cpp              python
+  Platform    cpp              python           java    rust
-  AtCoder     c++23            python3
+  AtCoder     c++20/23         python3, pypy3   java    rust
-  Codeforces  c++17/20/23      python3, pypy3
+  Codeforces  c++17/20/23      python3, pypy3   -       -
-  CSES        c++17            python3
+  CSES        c++11/17/20      python3, pypy3   java    rust2018/2021
-  Kattis      c++17/20/23      python3
+  Kattis      c++17/20/23      python3          java    rust
-  USACO       c++17/20/23      python3
+  USACO       c++11/17         python3          java    -
-  CodeChef    c++17            python3
+  CodeChef    c++20            python3, pypy3   java    rust
 
 Using a raw platform ID ~
 

lua/cp/constants.lua

@@ -74,21 +74,39 @@ M.signal_codes = {
 }
 
 M.LANGUAGE_VERSIONS = {
-  atcoder = { cpp = { ['c++23'] = '6017' }, python = { python3 = '6082' } },
+  atcoder = {
+    cpp = { ['c++20'] = '6054', ['c++23'] = '6017' },
+    python = { python3 = '6082', pypy3 = '6083' },
+    java = { java = '6056' },
+    rust = { rust = '6088' },
+  },
   codeforces = {
     cpp = { ['c++17'] = '54', ['c++20'] = '89', ['c++23'] = '91' },
     python = { python3 = '31', pypy3 = '70' },
   },
-  cses = { cpp = { ['c++17'] = 'C++17' }, python = { python3 = 'Python3' } },
+  cses = {
+    cpp = { ['c++11'] = 'C++11', ['c++17'] = 'C++17', ['c++20'] = 'C++20' },
+    python = { python3 = 'Python3', pypy3 = 'PyPy3' },
+    java = { java = 'Java' },
+    rust = { rust2018 = 'Rust2018', rust2021 = 'Rust2021' },
+  },
   kattis = {
     cpp = { ['c++17'] = 'C++', ['c++20'] = 'C++', ['c++23'] = 'C++' },
     python = { python3 = 'Python 3' },
+    java = { java = 'Java' },
+    rust = { rust = 'Rust' },
   },
   usaco = {
-    cpp = { ['c++17'] = 'cpp', ['c++20'] = 'cpp', ['c++23'] = 'cpp' },
+    cpp = { ['c++11'] = 'cpp', ['c++17'] = 'cpp' },
     python = { python3 = 'python' },
+    java = { java = 'java' },
+  },
+  codechef = {
+    cpp = { ['c++20'] = 'C++' },
+    python = { python3 = 'PYTH 3', pypy3 = 'PYPY3' },
+    java = { java = 'JAVA' },
+    rust = { rust = 'rust' },
   },
-  codechef = { cpp = { ['c++17'] = 'C++ 17' }, python = { python3 = 'Python 3' } },
 }
 
 M.DEFAULT_VERSIONS = { cpp = 'c++20', python = 'python3' }

scrapers/cses.py

@@ -31,13 +31,25 @@ HEADERS = {
 CONNECTIONS = 8
 
 CSES_LANGUAGES: dict[str, dict[str, str]] = {
+    "C++11": {"name": "C++", "option": "C++11"},
     "C++17": {"name": "C++", "option": "C++17"},
-    "Python3": {"name": "Python", "option": "CPython3"},
+    "C++20": {"name": "C++", "option": "C++20"},
+    "Python3": {"name": "Python3", "option": "CPython3"},
+    "PyPy3": {"name": "Python3", "option": "PyPy3"},
+    "Java": {"name": "Java", "option": "Java"},
+    "Rust2018": {"name": "Rust", "option": "2018"},
+    "Rust2021": {"name": "Rust", "option": "2021"},
 }
 
 EXTENSIONS: dict[str, str] = {
+    "C++11": "cpp",
     "C++17": "cpp",
+    "C++20": "cpp",
     "Python3": "py",
+    "PyPy3": "py",
+    "Java": "java",
+    "Rust2018": "rs",
+    "Rust2021": "rs",
 }
 
 

scrapers/language_ids.py

@@ -2,6 +2,8 @@ LANGUAGE_IDS = {
     "atcoder": {
         "cpp": "6017",
         "python": "6082",
+        "java": "6056",
+        "rust": "6088",
     },
     "codeforces": {
         "cpp": "89",
@@ -10,18 +12,25 @@ LANGUAGE_IDS = {
     "cses": {
         "cpp": "C++17",
         "python": "Python3",
+        "java": "Java",
+        "rust": "Rust2021",
     },
     "usaco": {
         "cpp": "cpp",
         "python": "python",
+        "java": "java",
     },
     "kattis": {
         "cpp": "C++",
         "python": "Python 3",
+        "java": "Java",
+        "rust": "Rust",
     },
     "codechef": {
-        "cpp": "C++ 17",
+        "cpp": "C++",
-        "python": "Python 3",
+        "python": "PYTH 3",
+        "java": "JAVA",
+        "rust": "rust",
     },
 }
 

tests/test_scrapers.py

@@ -1,6 +1,6 @@
 import pytest
 
-from scrapers.language_ids import LANGUAGE_IDS, get_language_id
+from scrapers.language_ids import LANGUAGE_IDS
 from scrapers.models import (
     ContestListResult,
     MetadataResult,
@@ -140,26 +140,17 @@ def test_scraper_metadata_error(run_scraper_offline, scraper, contest_id):
     assert objs[-1].get("error")
 
 
-EXPECTED_PLATFORMS = {"atcoder", "codeforces", "cses", "usaco", "kattis", "codechef"}
-EXPECTED_LANGUAGES = {"cpp", "python"}
-
-
 def test_language_ids_coverage():
-    assert set(LANGUAGE_IDS.keys()) == EXPECTED_PLATFORMS
+    expected_platforms = {
+        "atcoder",
+        "codeforces",
+        "cses",
+        "usaco",
+        "kattis",
+        "codechef",
+    }
+    assert set(LANGUAGE_IDS.keys()) == expected_platforms
     for platform, langs in LANGUAGE_IDS.items():
-        assert set(langs.keys()) == EXPECTED_LANGUAGES, f"{platform} missing languages"
+        assert {"cpp", "python"} <= set(langs.keys()), f"{platform} missing cpp/python"
         for lang, lid in langs.items():
             assert isinstance(lid, str) and lid, f"{platform}/{lang} empty ID"
-
-
-@pytest.mark.parametrize("platform", EXPECTED_PLATFORMS)
-@pytest.mark.parametrize("language", EXPECTED_LANGUAGES)
-def test_get_language_id(platform, language):
-    result = get_language_id(platform, language)
-    assert result is not None, f"No ID for {platform}/{language}"
-    assert result == LANGUAGE_IDS[platform][language]
-
-
-def test_get_language_id_unknown():
-    assert get_language_id("nonexistent", "cpp") is None
-    assert get_language_id("codeforces", "rust") is None