hanja: add single-character dictionary data

tests/mkhanja_test.py

@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+IMPORT = ROOT / "map" / "libhangul2hanja"
+GENERATE = ROOT / "map" / "mkhanja"
+
+
+def run(program, source):
+    return subprocess.run(
+        [sys.executable, "-B", str(program), str(source)],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+
+
+class MkhanjaTest(unittest.TestCase):
+    def source(self, text):
+        tmp = tempfile.TemporaryDirectory()
+        path = Path(tmp.name) / "hanja.txt"
+        path.write_text(text, encoding="utf-8")
+        self.addCleanup(tmp.cleanup)
+        return path
+
+    def test_imports_single_bmp_hanja_rows(self):
+        result = run(
+            IMPORT,
+            self.source(
+                "# Copyright holder\n"
+                "# BSD license\n"
+                "한:漢:first\n"
+                "가:㐀:extension A\n"
+                "김:金:compatibility\n"
+                "방학:放:word reading\n"
+                "학:學校:word value\n"
+                "한:𠀀:astral\n"
+                "ㄱ:加:jamo\n"
+            ),
+        )
+        self.assertEqual(result.returncode, 0, result.stderr)
+        lines = result.stdout.splitlines()
+        self.assertEqual(lines[:2], ["# Copyright holder", "# BSD license"])
+        self.assertEqual(lines[2:], ["", "漢\t한", "㐀\t가", "金\t김"])
+
+    def test_import_rejects_malformed_and_duplicate_rows(self):
+        bad = [
+            "한 漢\n",
+            "한:漢:first\n한:漢:again\n",
+        ]
+        for text in bad:
+            with self.subTest(text=repr(text)):
+                self.assertEqual(run(IMPORT, self.source(text)).returncode, 1)
+
+    def test_groups_readings_and_preserves_order(self):
+        result = run(
+            GENERATE,
+            self.source(
+                "# Copyright holder\n"
+                "# BSD license\n"
+                "漢\t한\n"
+                "韓\t한\n"
+                "㐀\t가\n"
+                "家\t가\n"
+                "金\t금\n"
+            ),
+        )
+        self.assertEqual(result.returncode, 0, result.stderr)
+        self.assertEqual(
+            result.stdout.splitlines(),
+            [
+                ";; Copyright holder",
+                ";; BSD license",
+                "",
+                "한\t漢 韓",
+                "가\t㐀 家",
+                "금\t金",
+            ],
+        )
+
+    def test_generator_rejects_bad_rows(self):
+        bad = [
+            "漢韓\t한\n",
+            "漢\t한자\n",
+            "𠀀\t한\n",
+            "漢\t한\n漢\t한\n",
+            "漢 한\n",
+        ]
+        for text in bad:
+            with self.subTest(text=repr(text)):
+                self.assertEqual(run(GENERATE, self.source(text)).returncode, 1)
+
+    def test_generator_keeps_runtime_candidate_limit(self):
+        rows = "".join(f"{chr(0x4E00 + n)}\t한\n" for n in range(33))
+        result = run(GENERATE, self.source(rows))
+        self.assertEqual(result.returncode, 0, result.stderr)
+        candidates = result.stdout.rstrip().split("\t", 1)[1].split()
+        self.assertEqual(len(candidates), 32)
+        self.assertEqual(candidates[-1], chr(0x4E00 + 31))
+
+
+if __name__ == "__main__":
+    unittest.main()