mirrors/k-skill
2
0
Fork 0
mirror of https://github.com/NomaDamas/k-skill.git synced 2026-06-24 02:04:11 +00:00
Code Issues Projects Releases Packages Wiki Activity

Preserve documented Korean count semantics in edge-case inputs

Browse source 
The NEIS compatibility path was treating mark-only graphemes as Hangul,
and the CLI accepted repeated input flags by silently overwriting earlier
values. Tighten the Hangul branch to require an actual Hangul-script code
point and reject any second input-source flag, then lock both fixes with
helper and CLI regressions.

Constraint: Must preserve the published default and NEIS counting contracts without new dependencies
Rejected: Doc-only clarification | would leave the shipped behavior incorrect
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep the NEIS 3-byte branch limited to graphemes that actually contain Hangul script code points
Tested: node --test scripts/skill-docs.test.js scripts/test_korean_character_count.js; node scripts/korean_character_count.js --text '가나다' --format json; node scripts/korean_character_count.js --file <tmpfile> --profile neis --format text; printf '한\r\n나' | node scripts/korean_character_count.js --stdin --format json; mark-only NEIS and duplicate-input repros; npm test; npm run ci
Not-tested: repeated --stdin as a separate committed regression case
This commit is contained in:
Jeffrey (Dongkyu) Kim 2026-04-08 23:28:42 +09:00
commit 488a9f129e
2 changed files with 22 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

7
korean-character-count/scripts/korean_character_count.js
View file

@ -4,7 +4,8 @@
const fs = require("node:fs");
const LINE_BREAK_PATTERN = /\r\n|[\n\r\u2028\u2029]/gu;
const HANGUL_PATTERN = /^[\p{Script=Hangul}\p{Mark}]+$/u;
const HANGUL_OR_MARK_PATTERN = /^[\p{Script=Hangul}\p{Mark}]+$/u;
const HAS_HANGUL_PATTERN = /\p{Script=Hangul}/u;
const WHITESPACE_ONLY_PATTERN = /^\s+$/u;
const ASCII_ONLY_PATTERN = /^[\x00-\x7F]+$/;
@ -60,7 +61,7 @@ function countNeisGraphemeBytes(grapheme) {
return 1;
}
if (HANGUL_PATTERN.test(grapheme)) {
if (HANGUL_OR_MARK_PATTERN.test(grapheme) && HAS_HANGUL_PATTERN.test(grapheme)) {
return 3;
}
@ -171,7 +172,7 @@ function parseArgs(argv, stdinIsTTY = process.stdin.isTTY) {
}
function setInputMode(options, nextMode) {
if (options.inputMode && options.inputMode !== nextMode) {
if (options.inputMode) {
throw new Error("Provide exactly one input source with --text, --file, or --stdin.");
}

18
scripts/test_korean_character_count.js
View file

@ -41,6 +41,12 @@ test("countNeisBytes applies Hangul 3-byte, ASCII 1-byte, and newline 2-byte rul
assert.equal(countNeisBytes("한글"), 6);
});
test("countNeisBytes falls back to UTF-8 bytes for non-Hangul graphemes", () => {
assert.equal(countUtf8Bytes("\u0301"), 2);
assert.equal(countNeisBytes("\u0301"), 2);
assert.equal(countNeisBytes("🙂"), countUtf8Bytes("🙂"));
});
test("parseArgs enforces one input source and validates the profile", () => {
assert.deepEqual(parseArgs(["--text", "가나다"]), {
format: "json",
@ -50,6 +56,7 @@ test("parseArgs enforces one input source and validates the profile", () => {
});
assert.throws(() => parseArgs(["--text", "가", "--file", "sample.txt"]), /exactly one input source/i);
assert.throws(() => parseArgs(["--text", "가", "--text", "나"]), /exactly one input source/i);
assert.throws(() => parseArgs(["--profile", "legacy", "--text", "가"]), /unknown profile/i);
});
@ -88,6 +95,17 @@ test("CLI accepts text, file, and stdin input", () => {
);
assert.equal(stdinOutput.profile, "neis");
assert.equal(stdinOutput.counts.bytes, countNeisBytes("가나다\nABC"));
const duplicateText = childProcess.spawnSync(
"node",
["scripts/korean_character_count.js", "--text", "가나다", "--text", "라마바", "--format", "json"],
{
cwd: repoRoot,
encoding: "utf8",
},
);
assert.notEqual(duplicateText.status, 0);
assert.match(duplicateText.stderr, /exactly one input source/i);
} finally {
fs.rmSync(tempDir, { recursive: true, force: true });
}