humanizer-lint 0.2.4 → 1.2.0

package/rules/pt-slop.json

@@ -0,0 +1,190 @@
+{
+  "language": "pt",
+  "stopwords": [
+    "de",
+    "a",
+    "o",
+    "que",
+    "e",
+    "do",
+    "da",
+    "em",
+    "um",
+    "para",
+    "é",
+    "com",
+    "não",
+    "uma",
+    "os",
+    "no",
+    "se",
+    "na",
+    "por",
+    "mais"
+  ],
+  "patterns": [
+    {
+      "id": "PT001",
+      "type": "SLOP_PHRASE",
+      "pattern": "no\\s+mundo\\s+acelerado\\s+de\\s+hoje",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT002",
+      "type": "SLOP_PHRASE",
+      "pattern": "vale\\s+ressaltar\\s+que",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT003",
+      "type": "SLOP_PHRASE",
+      "pattern": "é\\s+importante\\s+notar\\s+que",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT004",
+      "type": "SLOP_PHRASE",
+      "pattern": "não\\s+há\\s+como\\s+negar",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT005",
+      "type": "SLOP_PHRASE",
+      "pattern": "em\\s+conclusão",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT006",
+      "type": "SLOP_PHRASE",
+      "pattern": "em\\s+resumo",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT007",
+      "type": "SLOP_PHRASE",
+      "pattern": "além\\s+disso",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT008",
+      "type": "SLOP_PHRASE",
+      "pattern": "desempenha\\s+um\\s+papel\\s+crucial",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT009",
+      "type": "SLOP_PHRASE",
+      "pattern": "uma\\s+tapeçaria\\s+de",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT010",
+      "type": "SLOP_PHRASE",
+      "pattern": "mergulhar\\s+fundo",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT011",
+      "type": "SLOP_PHRASE",
+      "pattern": "não\\s+apenas",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT012",
+      "type": "SLOP_PHRASE",
+      "pattern": "mas\\s+também",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT013",
+      "type": "SLOP_PHRASE",
+      "pattern": "na\\s+era\\s+digital",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT014",
+      "type": "SLOP_PHRASE",
+      "pattern": "é\\s+fundamental\\s+lembrar",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT015",
+      "type": "SLOP_PHRASE",
+      "pattern": "sem\\s+dúvida",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT016",
+      "type": "SLOP_PHRASE",
+      "pattern": "no\\s+cenário\\s+atual",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT017",
+      "type": "SLOP_PHRASE",
+      "pattern": "ao\\s+longo\\s+do\\s+tempo",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT018",
+      "type": "SLOP_PHRASE",
+      "pattern": "em\\s+última\\s+análise",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT019",
+      "type": "SLOP_PHRASE",
+      "pattern": "abrir\\s+caminho\\s+para",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT020",
+      "type": "SLOP_PHRASE",
+      "pattern": "mudar\\s+o\\s+jogo",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT021",
+      "type": "SLOP_PHRASE",
+      "pattern": "em\\s+um\\s+mundo\\s+em\\s+constante\\s+evolução",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT022",
+      "type": "SLOP_PHRASE",
+      "pattern": "uma\\s+abordagem\\s+holística",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT023",
+      "type": "SLOP_PHRASE",
+      "pattern": "insights\\s+valiosos",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT024",
+      "type": "SLOP_PHRASE",
+      "pattern": "de\\s+forma\\s+contínua",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT025",
+      "type": "SLOP_PHRASE",
+      "pattern": "vale\\s+a\\s+pena\\s+mencionar",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "PT026",
+      "type": "DEFINITIONAL_OPENING",
+      "pattern": "^(?:No contexto de|No âmbito de|No mundo de) [\\w\\s]+,",
+      "scope": "paragraph-start",
+      "fixInstruction": "Start with the specific subject or event instead of a generic framing clause."
+    },
+    {
+      "id": "PT027",
+      "type": "STRUCTURAL_CLICHE",
+      "pattern": "\\bnão\\s+apenas\\b[\\s\\S]{0,100}?\\bmas\\s+também\\b",
+      "fixInstruction": "State both claims directly without the stock paired construction."
+    }
+  ]
+}

package/rules/zh-slop.json

@@ -0,0 +1,190 @@
+{
+  "language": "zh",
+  "stopwords": [
+    "的",
+    "了",
+    "和",
+    "是",
+    "在",
+    "我",
+    "有",
+    "而",
+    "及",
+    "与",
+    "着",
+    "或",
+    "一个",
+    "没有",
+    "我们",
+    "你们",
+    "他们",
+    "这个",
+    "那个",
+    "因此"
+  ],
+  "patterns": [
+    {
+      "id": "ZH001",
+      "type": "SLOP_PHRASE",
+      "pattern": "在当今快节奏的世界中",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH002",
+      "type": "SLOP_PHRASE",
+      "pattern": "在数字化时代",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH003",
+      "type": "SLOP_PHRASE",
+      "pattern": "值得注意的是",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH004",
+      "type": "SLOP_PHRASE",
+      "pattern": "不可否认的是",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH005",
+      "type": "SLOP_PHRASE",
+      "pattern": "总而言之",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH006",
+      "type": "SLOP_PHRASE",
+      "pattern": "综上所述",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH007",
+      "type": "SLOP_PHRASE",
+      "pattern": "此外",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH008",
+      "type": "SLOP_PHRASE",
+      "pattern": "更重要的是",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH009",
+      "type": "SLOP_PHRASE",
+      "pattern": "扮演着至关重要的角色",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH010",
+      "type": "SLOP_PHRASE",
+      "pattern": "不仅",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH011",
+      "type": "SLOP_PHRASE",
+      "pattern": "而且",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH012",
+      "type": "SLOP_PHRASE",
+      "pattern": "深入探讨",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH013",
+      "type": "SLOP_PHRASE",
+      "pattern": "这不仅关乎",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH014",
+      "type": "SLOP_PHRASE",
+      "pattern": "见证了",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH015",
+      "type": "SLOP_PHRASE",
+      "pattern": "双刃剑",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH016",
+      "type": "SLOP_PHRASE",
+      "pattern": "在当前环境下",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH017",
+      "type": "SLOP_PHRASE",
+      "pattern": "毋庸置疑",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH018",
+      "type": "SLOP_PHRASE",
+      "pattern": "需要指出的是",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH019",
+      "type": "SLOP_PHRASE",
+      "pattern": "随着时代的发展",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH020",
+      "type": "SLOP_PHRASE",
+      "pattern": "从本质上讲",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH021",
+      "type": "SLOP_PHRASE",
+      "pattern": "在不断变化的格局中",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH022",
+      "type": "SLOP_PHRASE",
+      "pattern": "开启了新的篇章",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH023",
+      "type": "SLOP_PHRASE",
+      "pattern": "改变游戏规则",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH024",
+      "type": "SLOP_PHRASE",
+      "pattern": "无缝衔接",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH025",
+      "type": "SLOP_PHRASE",
+      "pattern": "全方位的方法",
+      "fixInstruction": "Replace this stock phrase with the concrete fact, actor, or action."
+    },
+    {
+      "id": "ZH026",
+      "type": "DEFINITIONAL_OPENING",
+      "pattern": "^(?:在.*?的背景下|在.*?领域中|在.*?世界里)，",
+      "scope": "paragraph-start",
+      "fixInstruction": "Start with the specific subject or event instead of a generic framing clause."
+    },
+    {
+      "id": "ZH027",
+      "type": "STRUCTURAL_CLICHE",
+      "pattern": "不仅[\\s\\S]{0,100}?而且",
+      "fixInstruction": "State both claims directly without the stock paired construction."
+    }
+  ]
+}

package/scripts/analyze.mjs

@@ -9,6 +9,12 @@ import { calculateMetrics } from './utils/metrics.mjs';
 const RULES = {
   id: JSON.parse(readFileSync(new URL('../rules/id-slop.json', import.meta.url), 'utf8')),
   en: JSON.parse(readFileSync(new URL('../rules/en-slop.json', import.meta.url), 'utf8')),
+  es: JSON.parse(readFileSync(new URL('../rules/es-slop.json', import.meta.url), 'utf8')),
+  ms: JSON.parse(readFileSync(new URL('../rules/ms-slop.json', import.meta.url), 'utf8')),
+  fr: JSON.parse(readFileSync(new URL('../rules/fr-slop.json', import.meta.url), 'utf8')),
+  de: JSON.parse(readFileSync(new URL('../rules/de-slop.json', import.meta.url), 'utf8')),
+  pt: JSON.parse(readFileSync(new URL('../rules/pt-slop.json', import.meta.url), 'utf8')),
+  zh: JSON.parse(readFileSync(new URL('../rules/zh-slop.json', import.meta.url), 'utf8')),
 };
 const DEFAULT_PROFILE = JSON.parse(readFileSync(new URL('../profiles/default-human.json', import.meta.url), 'utf8'));
 const { analyzeText } = createAnalyzer({ rules: RULES, defaultProfile: DEFAULT_PROFILE, calculateMetrics });
@@ -16,7 +22,7 @@ const { analyzeText } = createAnalyzer({ rules: RULES, defaultProfile: DEFAULT_P
 export { analyzeText };
 
 function formatHuman(result) {
-  const lines = [`Status: ${result.status}`, `Score: ${result.score}`, `Language: ${result.language}`];
+  const lines = [`Status: ${result.status}`, `Score: ${result.score}`, `Language: ${result.language}`, `Rule pack: ${result.rulePack}`];
   if (result.warning) lines.push(`Warning: ${result.warning}`);
   lines.push('', 'Metrics:');
   for (const [name, value] of Object.entries(result.metrics)) lines.push(`  ${name}: ${value}`);
@@ -50,11 +56,11 @@ export async function runAnalyzeCli(argv, io = {}) {
       allowPositionals: false,
     });
     if (values.help) {
-      stdout('Usage: humanizer-lint (--file <path> | --stdin) [--lang id|en|auto] [--profile <path>] [--json]\n');
+      stdout('Usage: humanizer-lint (--file <path> | --stdin) [--lang auto|universal|<ISO-639-1>] [--profile <path>] [--json]\n');
       return 0;
     }
     if (Boolean(values.file) === Boolean(values.stdin)) throw new Error('Choose exactly one input: --file or --stdin');
-    if (!['id', 'en', 'auto'].includes(values.lang)) throw new Error('--lang must be id, en, or auto');
+    if (!/^(?:auto|universal|[a-z]{2})$/u.test(values.lang)) throw new Error('--lang must be auto, universal, or an ISO 639-1 code');
     if (values.stdin && io.stdin == null && process.stdin.isTTY) throw new Error('--stdin requires piped input');
     const text = values.file ? await new Promise((resolve, reject) => readFile(values.file, 'utf8', (error, data) => error ? reject(error) : resolve(data))) : await stdin();
     const profile = values.profile ? JSON.parse(await new Promise((resolve, reject) => readFile(values.profile, 'utf8', (error, data) => error ? reject(error) : resolve(data)))) : undefined;

package/scripts/core/analyzer-core.mjs

@@ -1,23 +1,45 @@
 import { sanitizeMarkdown } from '../utils/sanitizer.mjs';
 import { mean, punctuationRates } from '../utils/metrics-core.mjs';
-import { tokenizeText } from '../utils/tokenizer.mjs';
+import { isCJKText, tokenizeText } from '../utils/tokenizer.mjs';
 
-const ID_WORDS = new Set(['yang', 'dan', 'di', 'ini', 'untuk', 'dengan', 'dari', 'pada', 'dalam', 'tidak', 'akan', 'atau', 'juga', 'oleh', 'adalah', 'sebagai', 'bahwa', 'dapat', 'karena', 'tersebut']);
-const EN_WORDS = new Set(['the', 'and', 'of', 'to', 'in', 'is', 'that', 'for', 'it', 'with', 'as', 'on', 'are', 'this', 'by', 'be', 'at', 'or', 'from', 'an']);
+const HAN = /[\u4e00-\u9fff]/gu;
+const KANA = /[\u3040-\u30ff]/u;
+const ARABIC = /[\u0600-\u06ff]/u;
+const ID_EXCLUSIVE_WORDS = new Set(['tidak', 'karena', 'bisa', 'seperti', 'dari', 'bahwa']);
+const MS_EXCLUSIVE_WORDS = new Set(['tak', 'kerana', 'boleh', 'bagi', 'daripada', 'bahawa', 'beliau']);
 
 function round(value, places = 4) {
   const factor = 10 ** places;
   return Math.round(value * factor) / factor;
 }
 
-function detectLanguage(words) {
-  let id = 0;
-  let en = 0;
-  for (const word of words) {
-    if (ID_WORDS.has(word)) id += 1;
-    if (EN_WORDS.has(word)) en += 1;
+function detectLanguage(text, words, rules) {
+  if (KANA.test(text)) return 'ja';
+  if (ARABIC.test(text)) return 'ar';
+  const hanCount = (text.match(HAN) ?? []).length;
+  if (hanCount > 0 && isCJKText(text)) return 'zh';
+
+  const scores = new Map();
+  for (const [language, rule] of Object.entries(rules)) {
+    let score = 0;
+    const stopwords = new Set(rule.stopwords ?? []);
+    for (const word of words) if (stopwords.has(word)) score += 1;
+    scores.set(language, score);
+  }
+  if (scores.has('id') && scores.has('ms')) {
+    const idExclusive = words.filter((word) => ID_EXCLUSIVE_WORDS.has(word)).length;
+    const msExclusive = words.filter((word) => MS_EXCLUSIVE_WORDS.has(word)).length;
+    scores.set('id', scores.get('id') + idExclusive * 2);
+    scores.set('ms', scores.get('ms') + msExclusive * 2);
   }
-  return en > id ? 'en' : 'id';
+
+  const [language, score] = [...scores.entries()].sort((left, right) => right[1] - left[1])[0] ?? ['universal', 0];
+  return score >= Math.max(2, Math.ceil(words.length * 0.04)) ? language : 'universal';
+}
+
+function mattrThreshold(thresholds, language, tokenized) {
+  if (typeof thresholds.mattr?.[language] === 'number') return thresholds.mattr[language];
+  return isCJKText(tokenized.words.join('')) ? 0.68 : 0.72;
 }
 
 function locationFor(sentence) {
@@ -29,6 +51,7 @@ function regexFor(pattern) {
 }
 
 function patternViolations(tokenized, rules, wordCount) {
+  if (!rules?.patterns) return [];
   const violations = [];
   for (const rule of rules.patterns) {
     const candidates = [];
@@ -122,7 +145,7 @@ function structuralViolations(tokenized, metrics) {
   return violations;
 }
 
-function statisticalViolations(metrics, thresholds, language) {
+function statisticalViolations(metrics, thresholds, mattrTarget) {
   const violations = [];
   const cvTarget = metrics.sentenceCount >= 8 ? thresholds.burstinessCVLong : thresholds.burstinessCVShort;
   if (metrics.burstinessCV < cvTarget) {
@@ -152,12 +175,12 @@ function statisticalViolations(metrics, thresholds, language) {
       fixInstruction: 'Change neighboring sentence lengths by splitting or merging only where the content allows it.',
     });
   }
-  if (metrics.mattr < thresholds.mattr[language]) {
+  if (metrics.mattr < mattrTarget) {
     violations.push({
       type: 'LOW_LEXICAL_DIVERSITY',
       location: 'Whole text',
       actual: round(metrics.mattr),
-      target: thresholds.mattr[language],
+      target: mattrTarget,
       fixInstruction: 'Replace repeated generic wording with precise terms already supported by the source.',
     });
   }
@@ -244,7 +267,7 @@ function voiceDeviation(metrics, tokenized, text, profile) {
   return result < 0.0005 ? 0 : result;
 }
 
-function scoreResult(metrics, violations, language, thresholds) {
+function scoreResult(metrics, violations, thresholds, mattrTarget) {
   const cvTarget = metrics.sentenceCount >= 8 ? thresholds.burstinessCVLong : thresholds.burstinessCVShort;
   let burstinessPenalty = metrics.burstinessCV < cvTarget ? Math.min(25, Math.round((cvTarget - metrics.burstinessCV) * 100)) : 0;
   if (metrics.sentenceCount >= 8 && (metrics.shortSentenceRatio < thresholds.shortSentenceRatio || metrics.longSentenceRatio < thresholds.longSentenceRatio)) {
@@ -259,7 +282,7 @@ function scoreResult(metrics, violations, language, thresholds) {
   const morphologyPenalty = Math.min(15,
     (violations.some((violation) => violation.type === 'EXCESSIVE_NOMINALIZATION') ? 7.5 : 0)
     + Math.min(15, violations.filter((violation) => violation.type === 'PASSIVE_BLOATING').length * 7.5));
-  const vocabularyPenalty = metrics.mattr < thresholds.mattr[language] ? 5 : 0;
+  const vocabularyPenalty = metrics.mattr < mattrTarget ? 5 : 0;
   const entropyPenalty = violations.some((violation) => ['LOW_ENTROPY_REPETITION', 'SYMMETRIC_PARAGRAPHS', 'REPETITIVE_STARTERS'].includes(violation.type)) ? 5 : 0;
   const profilePenalty = violations.some((violation) => violation.type === 'VOICE_PROFILE_DEVIATION') ? 5 : 0;
   const vocabularyAndProfilePenalty = Math.min(10, vocabularyPenalty + entropyPenalty + profilePenalty);
@@ -267,25 +290,27 @@ function scoreResult(metrics, violations, language, thresholds) {
 }
 
 export function createAnalyzer({ rules, defaultProfile, calculateMetrics, calculateMetricsAsync }) {
-  if (!rules?.id || !rules?.en || !defaultProfile || typeof calculateMetrics !== 'function') {
+  if (!rules || !defaultProfile || typeof calculateMetrics !== 'function') {
     throw new TypeError('createAnalyzer requires rules, defaultProfile, and calculateMetrics');
   }
 
   const prepare = (input, options) => {
     const sanitized = sanitizeMarkdown(input);
-    const initial = tokenizeText(sanitized, options.language ?? 'auto');
-    const language = options.language && options.language !== 'auto' ? options.language : detectLanguage(initial.words);
-    if (!rules[language]) throw new Error(`Unsupported language: ${language}`);
+    const requestedLanguage = String(options.language ?? 'auto').toLowerCase();
+    const initial = tokenizeText(sanitized, requestedLanguage);
+    const language = requestedLanguage === 'auto' ? detectLanguage(sanitized, initial.words, rules) : requestedLanguage;
     return {
       sanitized,
       language,
-      tokenized: language === (options.language ?? 'auto') ? initial : tokenizeText(sanitized, language),
+      rulePack: rules[language] ? language : 'universal',
+      tokenized: language === requestedLanguage ? initial : tokenizeText(sanitized, language),
     };
   };
 
-  const analyzePrepared = ({ sanitized, language, tokenized }, options, metrics) => {
+  const analyzePrepared = ({ sanitized, language, rulePack, tokenized }, options, metrics) => {
     const profile = options.profile ?? defaultProfile;
     const thresholds = { ...defaultProfile.thresholds, ...(profile.thresholds ?? {}) };
+    const mattrTarget = mattrThreshold(thresholds, language, tokenized);
     const patternMatches = patternViolations(tokenized, rules[language], metrics.wordCount);
 
     if (metrics.wordCount < thresholds.minimumWords || metrics.sentenceCount < thresholds.minimumSentences) {
@@ -294,13 +319,14 @@ export function createAnalyzer({ rules, defaultProfile, calculateMetrics, calcul
         status: 'SKIP',
         score: 100,
         language,
+        rulePack,
         warning: 'Text too short for statistical stylometry (< 3 sentences)',
         metrics: Object.fromEntries(Object.entries({ ...metrics, nominalizationRatio: 0, passiveRatio: 0, voiceProfileDeviation: 0 }).map(([key, value]) => [key, typeof value === 'number' ? round(value) : value])),
         violations,
       };
     }
 
-    const morphology = morphologyViolations(tokenized, rules[language].morphology);
+    const morphology = morphologyViolations(tokenized, rules[language]?.morphology);
     metrics.nominalizationRatio = morphology.nominalizationRatio;
     metrics.passiveRatio = morphology.passiveRatio;
     metrics.voiceProfileDeviation = voiceDeviation(metrics, tokenized, sanitized, profile);
@@ -319,9 +345,9 @@ export function createAnalyzer({ rules, defaultProfile, calculateMetrics, calcul
       ...structuralViolations(tokenized, metrics),
       ...morphology.violations,
       ...profileViolations,
-      ...statisticalViolations(metrics, thresholds, language),
+      ...statisticalViolations(metrics, thresholds, mattrTarget),
     ];
-    const score = scoreResult(metrics, violations, language, thresholds);
+    const score = scoreResult(metrics, violations, thresholds, mattrTarget);
     const cvTarget = metrics.sentenceCount >= 8 ? thresholds.burstinessCVLong : thresholds.burstinessCVShort;
     const forbidden = violations.some((violation) => violation.type === 'SLOP_PHRASE' || violation.type === 'DEFINITIONAL_OPENING');
     const rhythmPass = metrics.adjacentDelta >= thresholds.adjacentDelta;
@@ -332,6 +358,7 @@ export function createAnalyzer({ rules, defaultProfile, calculateMetrics, calcul
       status,
       score,
       language,
+      rulePack,
       metrics: Object.fromEntries(Object.entries(metrics).map(([key, value]) => [key, typeof value === 'number' ? round(value) : value])),
       violations,
     };