@dev-pi2pie/word-counter 0.1.4-canary.1 → 0.1.5-canary.1

package/README.md

@@ -151,8 +151,10 @@ word-counter --path ./examples/test-case-multi-files-support --jobs 4
 Quick policy:
 
 - no `--jobs` and `--jobs 1` are equivalent baseline behavior.
-- `--jobs > 1` enables concurrent `load+count`.
+- `--jobs 1`: async main-thread `load+count` baseline.
+- `--jobs > 1`: worker `load+count` with async fallback when workers are unavailable.
 - if requested `--jobs` exceeds host `suggestedMaxJobs` (from `--print-jobs-limit`), the CLI warns and runs with the suggested limit as a safety cap.
+- use `--quiet-warnings` to suppress non-fatal warning lines (for example jobs-limit advisory and worker-fallback warning).
 
 Inspect host jobs diagnostics:
 
@@ -160,6 +162,35 @@ Inspect host jobs diagnostics:
 word-counter --print-jobs-limit
 ```
 
+`--print-jobs-limit` must be used alone (no other inputs or runtime flags).
+
+### Doctor (`doctor`)
+
+Use `doctor` to verify whether the current host can run `word-counter` reliably:
+
+```bash
+word-counter doctor
+word-counter doctor --format json
+word-counter doctor --format json --pretty
+```
+
+Doctor scope in v1:
+
+- checks runtime support policy against Node.js `>=20`
+- verifies `Intl.Segmenter` availability plus word/grapheme constructor health
+- reports batch jobs host limits using the same heuristics as `--print-jobs-limit`
+- reports worker-route preflight signals and the worker-disable env toggle that affects worker availability
+
+Doctor output contract:
+
+- default output is human-readable text
+- `--format json` prints compact machine-readable JSON
+- `--format json --pretty` prints indented JSON
+- doctor exits with code `0` for `ok` / `warn`, `1` for invalid doctor usage, and `2` for runtime `fail`
+- doctor does not accept counting inputs, `--path`, `--jobs`, or other counting/debug flags
+
+For a field-by-field explanation of doctor text and JSON output, see [`docs/doctor-usage-guide.md`](docs/doctor-usage-guide.md).
+
 For full policy details, JSON parity expectations (`--misc`, `--total-of whitespace,words`), and benchmark standards, see [`docs/batch-jobs-usage-guide.md`](docs/batch-jobs-usage-guide.md).
 
 ### Stable Path Resolution Contract
@@ -220,6 +251,8 @@ For additional usage details and troubleshooting, see [`docs/regex-usage-guide.m
 
 ### Debugging Diagnostics (`--debug`)
 
+Noise policy: default output shows errors + warnings; `--debug` enables diagnostics; `--verbose` enables per-item diagnostics; `--quiet-warnings` suppresses warnings.
+
 `--debug` remains the diagnostics gate and now defaults to `compact` event volume:
 
 - lifecycle/stage timing events
@@ -252,7 +285,7 @@ word-counter --path ./examples/test-case-multi-files-support --debug --debug-rep
 word-counter --path ./examples/test-case-multi-files-support --debug --debug-report ./logs/debug.jsonl --debug-tee
 ```
 
-Skip details stay debug-gated and can still be suppressed with `--quiet-skips`.
+Skip details stay debug-gated and can be suppressed with `--quiet-skips`.
 
 ## How It Works
 
@@ -491,8 +524,9 @@ Example (trimmed):
   "frontmatterType": "yaml",
   "total": 7,
   "items": [
-    { "name": "content", "source": "frontmatter", "result": { "total": 3 } },
-    { "name": "content", "source": "content", "result": { "total": 4 } }
+    { "name": "content", "source": "frontmatter", "result": { "total": 4 } },
+    { "name": "content", "source": "frontmatter", "result": { "total": 2 } },
+    { "name": "content", "source": "content", "result": { "total": 5 } }
   ]
 }
 ```
@@ -585,7 +619,7 @@ word-counter --include-whitespace "Hi\tthere\n"
 word-counter --misc "Hi\tthere\n"
 ```
 
-In the CLI, `--include-whitespace` implies with `--non-words` (same behavior as `--misc`). `--non-words` alone does not include whitespace. When enabled, whitespace counts appear under `nonWords.whitespace`, and `total = words + nonWords` (emoji + symbols + punctuation + whitespace). JSON output also includes top-level `counts` when `nonWords` is enabled. See `docs/schemas/whitespace-categories.md` for how whitespace is categorized.
+In the CLI, `--include-whitespace` implies `--non-words` (same behavior as `--misc`). `--non-words` alone does not include whitespace. When enabled, whitespace counts appear under `nonWords.whitespace`, and `total = words + nonWords` (emoji + symbols + punctuation + whitespace). JSON output also includes top-level `counts` when `nonWords` is enabled. See `docs/schemas/whitespace-categories.md` for how whitespace is categorized.
 
 Example JSON (trimmed):
 

package/dist/cjs/index.cjs

@@ -1,5 +1,4 @@
 let yaml = require("yaml");
-
 //#region src/wc/segmenter.ts
 const segmenterCache = /* @__PURE__ */ new Map();
 const graphemeSegmenterCache = /* @__PURE__ */ new Map();
@@ -33,13 +32,11 @@ function countCharsForLocale(text, locale) {
 	for (const _segment of segmenter.segment(text)) count++;
 	return count;
 }
-
 //#endregion
 //#region src/utils/append-all.ts
 function appendAll(target, source) {
 	for (const item of source) target.push(item);
 }
-
 //#endregion
 //#region src/wc/non-words.ts
 const emojiRegex = /(?:\p{Extended_Pictographic}|\p{Emoji_Presentation})/u;
@@ -153,7 +150,6 @@ function createWhitespaceCounts() {
 		other: 0
 	};
 }
-
 //#endregion
 //#region src/wc/analyze.ts
 function analyzeChunk(chunk, collectNonWords, includeWhitespace) {
@@ -253,7 +249,6 @@ function aggregateByLocale(chunks) {
 	}
 	return order.map((locale) => map.get(locale));
 }
-
 //#endregion
 //#region src/wc/mode.ts
 const MODE_ALIASES = {
@@ -321,10 +316,7 @@ function normalizeMode(input) {
 function resolveMode(input, fallback = "chunk") {
 	return normalizeMode(input) ?? fallback;
 }
-
-//#endregion
-//#region src/wc/latin-hints.ts
-const DEFAULT_LATIN_HINT_RULES_SOURCE = [
+const DEFAULT_LATIN_HINT_RULES = Object.freeze([
 	{
 		tag: "de",
 		pattern: "[äöüÄÖÜß]"
@@ -361,13 +353,10 @@ const DEFAULT_LATIN_HINT_RULES_SOURCE = [
 		tag: "is",
 		pattern: "[ðÐþÞ]"
 	}
-];
-const DEFAULT_LATIN_HINT_RULES = Object.freeze(DEFAULT_LATIN_HINT_RULES_SOURCE.map((rule) => Object.freeze({ ...rule })));
-
+].map((rule) => Object.freeze({ ...rule })));
 //#endregion
 //#region src/wc/locale-detect.ts
 const DEFAULT_LOCALE = "und-Latn";
-const DEFAULT_HAN_TAG = "und-Hani";
 const MAX_LATIN_HINT_PATTERN_LENGTH = 256;
 const regex = {
 	hiragana: /\p{Script=Hiragana}/u,
@@ -483,18 +472,17 @@ function detectLocaleForChar(char, previousLocale, options = {}, context = resol
 	if (regex.thai.test(char)) return "th";
 	if (regex.han.test(char)) {
 		if (allowJapaneseHanCarry && previousLocale && previousLocale.startsWith("ja")) return previousLocale;
-		return context.hanHint ?? DEFAULT_HAN_TAG;
+		return context.hanHint ?? "und-Hani";
 	}
 	if (regex.latin.test(char)) {
 		const hintedLocale = detectLatinLocale(char, context);
-		if (hintedLocale !== DEFAULT_LOCALE) return hintedLocale;
-		if (allowLatinLocaleCarry && previousLocale && isLatinLocale(previousLocale, context) && previousLocale !== DEFAULT_LOCALE) return previousLocale;
+		if (hintedLocale !== "und-Latn") return hintedLocale;
+		if (allowLatinLocaleCarry && previousLocale && isLatinLocale(previousLocale, context) && previousLocale !== "und-Latn") return previousLocale;
 		if (context.latinHint) return context.latinHint;
 		return DEFAULT_LOCALE;
 	}
 	return null;
 }
-
 //#endregion
 //#region src/wc/segment.ts
 const HARD_BOUNDARY_REGEX = /[\r\n,.!?;:，、。！？；：．｡､]/u;
@@ -531,7 +519,7 @@ function segmentTextByLocale(text, options = {}) {
 			continue;
 		}
 		if (targetLocale !== currentLocale && detected !== null) {
-			if (currentLocale === DEFAULT_LOCALE && isLatinLocale(targetLocale, context)) {
+			if (currentLocale === "und-Latn" && isLatinLocale(targetLocale, context)) {
 				const promotionBreakIndex = findLastLatinPromotionBreakIndex(buffer);
 				if (promotionBreakIndex === -1) {
 					currentLocale = targetLocale;
@@ -598,7 +586,6 @@ function mergeAdjacentChunks(chunks) {
 	merged.push(last);
 	return merged;
 }
-
 //#endregion
 //#region src/wc/wc.ts
 function wordCounter(text, options = {}) {
@@ -713,11 +700,9 @@ function collectNonWordsAggregate(analyzed, enabled) {
 	}
 	return collection;
 }
-
 //#endregion
 //#region src/wc/index.ts
 var wc_default = wordCounter;
-
 //#endregion
 //#region src/markdown/toml/arrays.ts
 function ensureArrayContainer(result, key) {
@@ -733,7 +718,6 @@ function flattenArrayTables(result) {
 		result[key] = value.map((entry) => Object.entries(entry).map(([entryKey, entryValue]) => `${entryKey}=${entryValue}`).join(", ")).join(" | ");
 	}
 }
-
 //#endregion
 //#region src/markdown/toml/keys.ts
 function stripKeyQuotes(key) {
@@ -752,7 +736,6 @@ function normalizeKeyPath(key) {
 	if (segments.some((segment) => !segment)) return null;
 	return segments.join(".");
 }
-
 //#endregion
 //#region src/markdown/toml/strings.ts
 function stripInlineComment(line) {
@@ -801,7 +784,6 @@ function parseStringLiteral(value) {
 	if (value.startsWith("'") && value.endsWith("'")) return value.slice(1, -1);
 	return null;
 }
-
 //#endregion
 //#region src/markdown/toml/values.ts
 function parsePrimitive(raw) {
@@ -959,7 +941,6 @@ function toPlainText(value) {
 	if (Array.isArray(value)) return value.map((item) => String(item)).join(", ");
 	return String(value);
 }
-
 //#endregion
 //#region src/markdown/toml/parse-frontmatter.ts
 function parseTomlFrontmatter(frontmatter) {
@@ -1043,7 +1024,6 @@ function parseTomlFrontmatter(frontmatter) {
 	flattenArrayTables(result);
 	return result;
 }
-
 //#endregion
 //#region src/markdown/parse-markdown.ts
 const FENCE_TO_TYPE = {
@@ -1178,7 +1158,6 @@ function parseMarkdown(input) {
 		frontmatterType: openingType
 	};
 }
-
 //#endregion
 //#region src/markdown/section-count.ts
 function normalizeText(value) {
@@ -1243,13 +1222,11 @@ function countSections(input, section, options = {}) {
 		items
 	};
 }
-
 //#endregion
 //#region src/utils/show-singular-or-plural-word.ts
 function showSingularOrPluralWord(count, word) {
 	return `${count} ${word}${count === 1 ? "" : "s"}`;
 }
-
 //#endregion
 //#region src/index.cjs.ts
 const cjsExports = Object.assign(wc_default, {
@@ -1263,6 +1240,6 @@ const cjsExports = Object.assign(wc_default, {
 	showSingularOrPluralWord
 });
 module.exports = cjsExports;
-
 //#endregion
+
 //# sourceMappingURL=index.cjs.map