@pranavraut033/ats-checker 1.3.0 → 1.3.2

package/dist/index.mjs

@@ -54,15 +54,38 @@ var LEVEL_RANK = {
   fluent: 5,
   native: 6,
   "native speaker": 6,
-  bilingual: 6
+  bilingual: 6,
+  // German
+  grundkenntnisse: 1,
+  gering: 2,
+  gut: 3,
+  fortgeschritten: 4,
+  flie\u00DFend: 5,
+  muttersprache: 6,
+  muttersprachler: 6,
+  // French
+  "d\xE9butant": 1,
+  "\xE9l\xE9mentaire": 1,
+  "limit\xE9": 2,
+  "interm\xE9diaire": 3,
+  "avanc\xE9": 4,
+  courant: 5,
+  natif: 6,
+  "langue maternelle": 6,
+  bilingue: 6
 };
 var LANGUAGE_GROUP = KNOWN_LANGUAGES.join("|");
 var LEVEL_GROUP = Object.keys(LEVEL_RANK).sort((a, b) => b.length - a.length).map((l) => l.replace(/\s+/g, "\\s+")).join("|");
+var BOUNDARY_START = "(?:^|(?<=[^a-z\xE0-\xFF]))";
+var BOUNDARY_END = "(?:$|(?=[^a-z\xE0-\xFF]))";
 var LANGUAGE_LEVEL_RE = new RegExp(
-  `\\b(${LANGUAGE_GROUP})\\b(?:\\s*[\\(:\\-]?\\s*(${LEVEL_GROUP}|[abc][12]))?`,
+  `\\b(${LANGUAGE_GROUP})\\b(?:\\s*[\\(:\\-]?\\s*(${BOUNDARY_START}(?:${LEVEL_GROUP})${BOUNDARY_END}|[abc][12]))?`,
+  "gi"
+);
+var LEVEL_BEFORE_LANGUAGE_RE = new RegExp(
+  `${BOUNDARY_START}(${LEVEL_GROUP})${BOUNDARY_END}\\s+(?:in\\s+)?(${LANGUAGE_GROUP})\\b`,
   "gi"
 );
-var LEVEL_BEFORE_LANGUAGE_RE = new RegExp(`\\b(${LEVEL_GROUP})\\s+(?:in\\s+)?(${LANGUAGE_GROUP})\\b`, "gi");
 function canonicalLanguage(name) {
   const lower = name.toLowerCase();
   return LANGUAGE_ALIASES[lower] ?? lower;
@@ -112,9 +135,9 @@ function diffLanguages(resumeLanguages, requiredLanguages) {
 
 // src/core/parser/jd.parser.ts
 var DEGREE_VARIANTS = [
-  [/\b(?:bachelor(?:'s)?|b\.s\.?|bs\.?|bsc\.?)\b/i, "bachelor"],
-  [/\b(?:master(?:'s)?|m\.s\.?|ms\.?|msc\.?)\b/i, "master"],
-  [/\b(?:phd|ph\.d\.?|doctorate)\b/i, "phd"],
+  [/\b(?:bachelor(?:'s)?|b\.s\.?|bs\.?|bsc\.?|licence)\b/i, "bachelor"],
+  [/\b(?:master(?:'s)?|m\.s\.?|ms\.?|msc\.?|diplom)\b/i, "master"],
+  [/\b(?:phd|ph\.d\.?|doctorate|doktor|doctorat)\b/i, "phd"],
   [/\bmba\b/i, "mba"],
   [/\bassociate(?:'s)?\b/i, "associate"]
 ];
@@ -137,16 +160,15 @@ function extractPreferredSkills(lines) {
   return preferred;
 }
 function extractRoleKeywords(text) {
-  const roleMatch = text.match(/(engineer|developer|manager|scientist|analyst|designer|architect)/i);
-  const titleTokens = roleMatch ? roleMatch[0].split(/\s+/) : [];
-  return unique(tokenize(titleTokens.join(" ") || text.split(/\n/)[0] || ""));
+  const roleMatches = text.match(/(engineer|developer|manager|scientist|analyst|designer|architect|director|consultant|lead|vp)/gi) ?? [];
+  const fallback = roleMatches.length === 0 ? [text.split(/\n/)[0] ?? ""] : [];
+  return unique(tokenize([...roleMatches, ...fallback].join(" ")));
 }
 function extractMinExperience(text) {
-  const match = text.match(/(\d{1,2})\+?\s+(?:years|yrs)/i);
-  if (match) {
-    return Number.parseInt(match[1], 10);
-  }
-  return void 0;
+  const match = text.match(/(\d{1,2})\+?\s*(?:years?|yrs\.?|jahre?|ans?|années?)/i);
+  if (!match) return void 0;
+  const parsed = Number.parseInt(match[1], 10);
+  return parsed <= 60 ? parsed : void 0;
 }
 var SURFACE_TOKEN_RE = /[a-z0-9][a-z0-9.#+\-/]*[a-z0-9#+]/gi;
 function collectKeywordSurfaceForms(rawText, aliases) {
@@ -160,7 +182,16 @@ function collectKeywordSurfaceForms(rawText, aliases) {
   }
   return surfaceForms;
 }
-function extractEducationRequirements(text) {
+var LANG_SECTION_RE = /^\s*(?:languages?|sprache|langue)s?\s*[:\-–—]?\s*/i;
+var LANG_REQUIREMENT_HINT_RE = /\b(fluent|required|must|need|speak|proficient|native|conversational|intermediate|advanced|professional|[abc][12])\b/i;
+function isLanguageRequired(lang, jobDescription) {
+  return splitLines(jobDescription).some((line) => {
+    const lower = line.toLowerCase();
+    if (!lower.includes(lang.name)) return false;
+    return LANG_SECTION_RE.test(line) || LANG_REQUIREMENT_HINT_RE.test(line);
+  });
+}
+function extractDegreeLevels(text) {
   const found = /* @__PURE__ */ new Set();
   for (const [pattern, canonical] of DEGREE_VARIANTS) {
     if (pattern.test(text)) found.add(canonical);
@@ -198,11 +229,13 @@ function parseJobDescription(jobDescription, config) {
     roleKeywords,
     keywords,
     minExperienceYears: extractMinExperience(jobDescription),
-    educationRequirements: extractEducationRequirements(jobDescription),
+    educationRequirements: extractDegreeLevels(jobDescription),
     keywordSurfaceForms: collectKeywordSurfaceForms(jobDescription, config.skillAliases),
-    // ponytail: any language mention in the JD is treated as a requirement — good enough until
-    // JDs that merely *reference* a language (not require it) show up as false positives.
-    requiredLanguages: parseLanguageMentions(jobDescription)
+    // A language only counts as required if its mention carries a requirement/level cue
+    // or sits in a "Languages:" line — plain references ("our Berlin office") don't count.
+    requiredLanguages: parseLanguageMentions(jobDescription).filter(
+      (lang) => isLanguageRequired(lang, jobDescription)
+    )
   };
 }
 
@@ -231,11 +264,37 @@ var MONTHS = {
   nov: 11,
   november: 11,
   dec: 12,
-  december: 12
+  december: 12,
+  // German
+  januar: 1,
+  j\u00E4nner: 1,
+  februar: 2,
+  m\u00E4rz: 3,
+  maerz: 3,
+  mai: 5,
+  juni: 6,
+  juli: 7,
+  oktober: 10,
+  dezember: 12,
+  // French
+  janvier: 1,
+  f\u00E9vrier: 2,
+  fevrier: 2,
+  mars: 3,
+  avril: 4,
+  juin: 6,
+  juillet: 7,
+  ao\u00FBt: 8,
+  aout: 8,
+  septembre: 9,
+  octobre: 10,
+  novembre: 11,
+  d\u00E9cembre: 12,
+  decembre: 12
 };
 function parseDateToken(raw) {
   const cleaned = raw.trim().toLowerCase();
-  const monthMatch = cleaned.match(/([a-z]{3,9})\s*(\d{4})/i);
+  const monthMatch = cleaned.match(/([a-zà-ÿ]{3,9})\s*(\d{4})/i);
   if (monthMatch) {
     const monthName = monthMatch[1].toLowerCase();
     const year = Number.parseInt(monthMatch[2], 10);
@@ -267,14 +326,14 @@ function monthsBetween(start, end) {
 function parseDateRange(text, referenceDate) {
   const normalized = text.trim();
   const rangeMatch = normalized.match(
-    /(\d{1,2}\/\d{4}|[A-Za-z]{3,9}\s+\d{4}|\d{4})\s*(?:-|to|–|—)\s*(Present|Current|Now|\d{1,2}\/\d{4}|[A-Za-z]{3,9}\s+\d{4}|\d{4})/i
+    /(\d{1,2}\/\d{4}|[A-Za-zà-ÿ]{3,9}\s+\d{4}|\d{4})\s*(?:-|to|through|until|bis|jusqu'à|à|–|—)\s*(Present|Current|Now|Aktuell|Heute|Actuellement|Présent|\d{1,2}\/\d{4}|[A-Za-zà-ÿ]{3,9}\s+\d{4}|\d{4})/i
   );
   if (!rangeMatch) {
     return null;
   }
   const startToken = parseDateToken(rangeMatch[1]);
   const endRaw = rangeMatch[2];
-  const isPresent = /present|current|now/i.test(endRaw);
+  const isPresent = /present|current|now|aktuell|heute|actuellement|présent|actuel/i.test(endRaw);
   const endToken = isPresent ? void 0 : parseDateToken(endRaw);
   if (!startToken) {
     return null;
@@ -328,12 +387,21 @@ function sumExperienceYears(ranges) {
 
 // src/core/parser/resume.parser.ts
 var SECTION_ALIASES = {
-  summary: ["summary", "profile", "about"],
-  experience: ["experience", "work experience", "professional experience", "employment"],
-  skills: ["skills", "technical skills", "technologies"],
-  education: ["education", "academics", "academic background"],
-  projects: ["projects", "portfolio"],
-  certifications: ["certifications", "licenses"]
+  summary: ["summary", "profile", "about", "zusammenfassung", "profil", "r\xE9sum\xE9", "\xE0 propos"],
+  experience: [
+    "experience",
+    "work experience",
+    "professional experience",
+    "employment",
+    "erfahrung",
+    "berufserfahrung",
+    "exp\xE9rience",
+    "exp\xE9rience professionnelle"
+  ],
+  skills: ["skills", "technical skills", "technologies", "f\xE4higkeiten", "kenntnisse", "comp\xE9tences"],
+  education: ["education", "academics", "academic background", "ausbildung", "formation", "\xE9tudes"],
+  projects: ["projects", "portfolio", "projekte", "projets"],
+  certifications: ["certifications", "licenses", "zertifizierungen", "certifications professionnelles"]
 };
 var STRONG_VERBS = [
   "led",
@@ -411,7 +479,9 @@ function extractSections(text) {
 }
 function parseSkills(sectionContent, aliases) {
   if (!sectionContent) return [];
-  const raw = sectionContent.split(/[,;\n]/).map((skill) => skill.trim()).filter(Boolean);
+  const hasBullets = /[•·‣▪○●◦]/.test(sectionContent);
+  const normalized = hasBullets ? sectionContent.replace(/\n/g, " ") : sectionContent;
+  const raw = normalized.split(/[,;\n]|[•·‣▪○●◦]/).map((skill) => skill.trim().replace(/^[-•·‣▪○●◦\s]+|[-•·‣▪○●◦\s]+$/g, "").trim()).filter(Boolean);
   return normalizeSkills(raw, aliases);
 }
 function parseActionVerbs(text) {
@@ -444,7 +514,7 @@ function parseExperience(sectionContent, referenceDate) {
       }
       continue;
     }
-    const titleMatch = line.match(/^(Senior|Lead|Principal|Staff|Software|Full\s*Stack|Frontend|Backend|Engineer|Developer|Manager|Analyst)[^,-]*/i);
+    const titleMatch = line.match(/^(Senior|Lead|Principal|Staff|VP|Director|Consultant|Architect|Software|Full\s*Stack|Frontend|Backend|Engineer|Developer|Manager|Analyst)[^,-]*/i);
     if (titleMatch) {
       const title = titleMatch[0].trim();
       jobTitles.push(title.toLowerCase());
@@ -482,7 +552,8 @@ function parseResume(resumeText, config) {
     const textToScan = sections.summary ?? normalizedText;
     const yearsMatch = textToScan.match(/(\d{1,2})\+?\s*years?/i);
     if (yearsMatch) {
-      totalExperienceYears = Number.parseInt(yearsMatch[1], 10);
+      const parsed = Number.parseInt(yearsMatch[1], 10);
+      totalExperienceYears = parsed <= 60 ? parsed : 0;
     }
   }
   const requiredSections = ["summary", "experience", "skills", "education"];
@@ -718,10 +789,9 @@ function scoreEducation(resume, job) {
   if (job.educationRequirements.length === 0) {
     return 100;
   }
-  const resumeEducationText = resume.educationEntries.join(" ");
-  const normalizedEducation = resumeEducationText.toLowerCase();
+  const resumeDegreeLevels = extractDegreeLevels(resume.educationEntries.join(" "));
   const matched = job.educationRequirements.filter(
-    (requirement) => normalizedEducation.includes(requirement.toLowerCase())
+    (requirement) => resumeDegreeLevels.includes(requirement)
   );
   if (matched.length === 0) {
     return 0;