@utilix-tech/sdk 0.75.0 → 0.77.0

package/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 Full release notes for all Utilix surfaces (browser tools, REST API, SDKs, MCP server) live at [utilix.tech/changelog](https://utilix.tech/changelog). This file tracks just this package.
 
+## 0.77.0
+- Add `readPdfOutline` (pdf-outline-extractor): walk a PDF's /Outlines bookmark tree (the Root -> Outlines -> First/Next/First chain) and list every bookmark's title, nesting level, and link target, in document order.
+- Add `scoreSecurityHeaders` (security-headers-scorecard): score a pasted block of raw HTTP response headers against commonly recommended security headers (CSP, HSTS, X-Content-Type-Options, X-Frame-Options, Referrer-Policy, Permissions-Policy, Cross-Origin-*), with an overall 0-100 score and A-F letter grade.
+
+## 0.76.0
+- Add `detectWordyPhrases` (wordy-phrase-detector): scan text against a curated table of wordy/redundant phrases ("due to the fact that", "in order to") and flag each occurrence with a suggested concise replacement, an occurrence count, and character offsets.
+- Add `checkOxfordCommaConsistency` (oxford-comma-checker): scan a document for comma-before-and/or usage in three-or-more-item lists and flag documents that mix Oxford comma styles.
+
 ## 0.75.0
 - Add `verifyWebhookSignature` (webhook-signature-verifier): recompute an HMAC over a raw webhook payload and compare it to a provided signature, supporting the `sha256=` prefix style (Stripe/GitHub-style webhooks) plus raw hex or base64 encoding.
 - Add `calculateTransferTime` and `calculateRequiredBandwidth` (data-transfer-time-estimator): estimate the theoretical time to transfer a file over a connection of a given speed, or the reverse: the bandwidth required to hit a target time.

package/README.md

@@ -1,6 +1,6 @@
 # @utilix-tech/sdk
 
-**702 developer utility functions for Node.js: runs locally, no API key required.**
+**705 developer utility functions for Node.js: runs locally, no API key required.**
 
 [![npm version](https://img.shields.io/npm/v/@utilix-tech/sdk?style=flat-square&color=cb3837)](https://www.npmjs.com/package/@utilix-tech/sdk)
 [![npm downloads](https://img.shields.io/npm/dm/@utilix-tech/sdk?style=flat-square)](https://www.npmjs.com/package/@utilix-tech/sdk)
@@ -152,7 +152,8 @@ generateEtag("console.log(1)");
 ```ts
 import { convertCase, slugify, countWords, generateWords, generateParagraphs,
          escapeString, htmlToMarkdown, applyOps, detectPassiveVoice, scoreReadability,
-         detectFillerWords, calculateStringDistance, analyzeSentenceLengths,
+         detectFillerWords, detectWordyPhrases, checkOxfordCommaConsistency,
+         calculateStringDistance, analyzeSentenceLengths,
          analyzeKeywordDensity, searchEmoji, getEmojiByShortcode } from "@utilix-tech/sdk/text";
 
 convertCase("hello world", "camelCase");   // "helloWorld"
@@ -183,6 +184,14 @@ scoreReadability("The cat sat on the mat. It was a sunny day.");
 detectFillerWords("At the end of the day, I just really think we should circle back.");
 // { totalMatches: 4, fillerCount: 2, clicheCount: 2, density: 28.6, matches: [...] }
 
+// Flag wordy/redundant phrases with a suggested concise replacement
+detectWordyPhrases("Due to the fact that it was late, we decided, in order to save time, to skip the meeting.");
+// { totalMatches: 2, density: 10.5, matches: [{ phrase: "due to the fact that", suggestion: "because", ... }, ...] }
+
+// Flag a document that mixes Oxford-comma and non-Oxford-comma lists
+checkOxfordCommaConsistency("I bought apples, bananas, and pears. Then I bought milk, eggs and bread.");
+// { totalLists: 2, withOxfordComma: 1, withoutOxfordComma: 1, consistent: false, instances: [...] }
+
 // Levenshtein edit distance + similarity ratio; pass mode: "damerau" to count a transposition as 1 edit
 calculateStringDistance("kitten", "sitting");
 // { distance: 3, similarity: 0.5714, maxLength: 7, mode: "levenshtein" }
@@ -701,6 +710,11 @@ buildRobotsMetaTag({ flags: ["noindex", "nofollow"], name: "googlebot" });
 // Cookie header byte-size budget: per-cookie and total sizes against RFC 6265's 4096-byte limit
 calculateCookieSizeBudget("session=abc123; theme=dark; cart=42");
 // { cookieCount: 3, totalBytes: 35, budgetBytes: 4096, exceedsBudget: false, cookies: [...] }
+
+// Score pasted response headers against commonly recommended security headers
+import { scoreSecurityHeaders } from "@utilix-tech/sdk/network";
+scoreSecurityHeaders("Content-Security-Policy: default-src 'self'\nStrict-Transport-Security: max-age=63072000");
+// { score: 22, grade: "F", passCount: 2, warningCount: 0, missingCount: 7, totalChecks: 9, checks: [...] }
 ```
 
 ---
@@ -901,10 +915,10 @@ analyzeString("café");          // { length: 4, codePoints: [...], ... }
 
 ---
 
-### `/media`: Image Header Parsing, EXIF, PDF Metadata & Page Dimensions, WAV, ID3, ICO, FLAC, Video, GIF & MIDI Metadata
+### `/media`: Image Header Parsing, EXIF, PDF Metadata, Page Dimensions & Outlines, WAV, ID3, ICO, FLAC, Video, GIF & MIDI Metadata
 
 ```ts
-import { readImageInfo, readExifData, readPdfMetadata, readPdfPageDimensions, readWavInfo, readId3Tags, readIcoInfo, readFlacInfo, readVideoInfo, inspectGifFrames, readMidiInfo } from "@utilix-tech/sdk/media";
+import { readImageInfo, readExifData, readPdfMetadata, readPdfPageDimensions, readPdfOutline, readWavInfo, readId3Tags, readIcoInfo, readFlacInfo, readVideoInfo, inspectGifFrames, readMidiInfo } from "@utilix-tech/sdk/media";
 
 // Reads format, dimensions, bit depth, and alpha channel straight from
 // file bytes: no decoding, no canvas, no image library.
@@ -930,6 +944,12 @@ readPdfMetadata(new Uint8Array(pdfBytes));
 readPdfPageDimensions(new Uint8Array(pdfBytes));
 // { version: "1.7", pageCount: 12, pages: [{ pageNumber: 1, widthPt: 612, heightPt: 792, rotation: 0, orientation: "portrait", paperSize: "Letter" }, ...] }
 
+// Walks a PDF's /Outlines bookmark tree (Root -> Outlines -> First/Next/
+// First chain) to list every bookmark's title, nesting level, and link
+// target, in document order: no PDF rendering library required.
+readPdfOutline(new Uint8Array(pdfBytes));
+// { version: "1.7", bookmarkCount: 3, bookmarks: [{ title: "Chapter 1", level: 0, destType: "page", target: "3 0 R" }, ...] }
+
 // Reads sample rate, channels, bit depth, and duration from a WAV file's
 // RIFF/fmt/data chunk headers: no audio library required.
 const wavBytes = await fs.promises.readFile("recording.wav");

package/dist/{chunk-CXUOV672.js → chunk-KWS4ZCYG.js}

@@ -72,6 +72,7 @@ __export(network_exports, {
   parseVaryHeader: () => parseVaryHeader,
   parseXContentTypeOptionsHeader: () => parseXContentTypeOptionsHeader,
   parseXRobotsTag: () => parseXRobotsTag,
+  scoreSecurityHeaders: () => scoreSecurityHeaders,
   searchHeaders: () => searchHeaders,
   searchStatusCodes: () => searchStatusCodes,
   splitSitemap: () => splitSitemap,
@@ -3511,5 +3512,122 @@ function calculateCookieSizeBudget(cookieHeader, budgetBytes = DEFAULT_COOKIE_BU
     exceedsBudget: totalBytes > budgetBytes
   };
 }
+function parseRawHeaderBlock(raw) {
+  const map = /* @__PURE__ */ new Map();
+  for (const line of raw.split(/\r?\n/)) {
+    const trimmed = line.trim();
+    if (!trimmed) continue;
+    const idx = trimmed.indexOf(":");
+    if (idx === -1) continue;
+    const name = trimmed.slice(0, idx).trim().toLowerCase();
+    const value = trimmed.slice(idx + 1).trim();
+    if (!map.has(name)) map.set(name, value);
+  }
+  return map;
+}
+var SECURITY_HEADER_CHECKS = [
+  {
+    header: "Content-Security-Policy",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without a CSP, an injected script runs with full page privileges." };
+      if (/unsafe-inline|unsafe-eval/i.test(v)) return { status: "warning", note: "Contains unsafe-inline or unsafe-eval, which weakens XSS protection." };
+      return { status: "pass", note: "Present. Use the CSP Header Builder tool to validate its directives in depth." };
+    }
+  },
+  {
+    header: "Strict-Transport-Security",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without HSTS, a user's first visit (and any later downgrade) can be sent over plain HTTP." };
+      const maxAgeMatch = v.match(/max-age\s*=\s*(\d+)/i);
+      if (!maxAgeMatch) return { status: "warning", note: "Present but missing a max-age directive." };
+      const maxAge = Number(maxAgeMatch[1]);
+      if (maxAge < 31536e3) return { status: "warning", note: "max-age is below the recommended 1 year (31536000 seconds)." };
+      return { status: "pass", note: "Present with a max-age of at least 1 year." };
+    }
+  },
+  {
+    header: "X-Content-Type-Options",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without this header, browsers may MIME-sniff a response into an unintended content type." };
+      if (v.trim().toLowerCase() !== "nosniff") return { status: "warning", note: `"nosniff" is the only valid value; this value won't take effect.` };
+      return { status: "pass", note: "Set to the only valid value, nosniff." };
+    }
+  },
+  {
+    header: "X-Frame-Options",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without this (or a CSP frame-ancestors directive), the page can be framed by another site for clickjacking." };
+      const upper = v.trim().toUpperCase();
+      if (upper === "DENY" || upper === "SAMEORIGIN") return { status: "pass", note: `Framing restricted (${upper}).` };
+      if (upper.startsWith("ALLOW-FROM")) return { status: "warning", note: "ALLOW-FROM is deprecated and ignored by most modern browsers." };
+      return { status: "warning", note: "Unrecognized value." };
+    }
+  },
+  {
+    header: "Referrer-Policy",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without this header, the browser's default referrer behavior applies, which can leak full URLs to third parties." };
+      if (v.trim().toLowerCase() === "unsafe-url") return { status: "warning", note: "unsafe-url leaks the full URL, including path and query string, to every destination." };
+      return { status: "pass", note: "Present." };
+    }
+  },
+  {
+    header: "Permissions-Policy",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without this header, embedded content can use powerful browser features (camera, geolocation, etc.) unless restricted another way." };
+      return { status: "pass", note: "Present." };
+    }
+  },
+  {
+    header: "Cross-Origin-Opener-Policy",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without COOP, this page can be put in the same browsing context group as a malicious opener window." };
+      const lower = v.trim().toLowerCase();
+      if (lower === "same-origin") return { status: "pass", note: "Set to same-origin, the strongest isolation value." };
+      return { status: "warning", note: `Set to "${v.trim()}", which is weaker than same-origin.` };
+    }
+  },
+  {
+    header: "Cross-Origin-Embedder-Policy",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Required alongside COOP for cross-origin isolation (e.g. to use SharedArrayBuffer)." };
+      const lower = v.trim().toLowerCase();
+      if (lower === "require-corp" || lower === "credentialless") return { status: "pass", note: `Set to ${lower}.` };
+      return { status: "warning", note: `Unrecognized value "${v.trim()}".` };
+    }
+  },
+  {
+    header: "Cross-Origin-Resource-Policy",
+    evaluate: (v) => {
+      if (!v) return { status: "missing", note: "Without CORP, this resource can be loaded cross-origin by any site that knows its URL." };
+      const lower = v.trim().toLowerCase();
+      if (lower === "same-origin" || lower === "same-site") return { status: "pass", note: `Set to ${lower}.` };
+      if (lower === "cross-origin") return { status: "warning", note: "Set to cross-origin, which allows any site to load this resource." };
+      return { status: "warning", note: `Unrecognized value "${v.trim()}".` };
+    }
+  }
+];
+function scoreSecurityHeaders(rawHeaders) {
+  if (typeof rawHeaders !== "string" || !rawHeaders.trim()) {
+    return { error: 'Paste one or more response headers, one per line in "Name: value" form' };
+  }
+  const headerMap = parseRawHeaderBlock(rawHeaders);
+  if (headerMap.size === 0) {
+    return { error: 'Could not parse any "Name: value" header lines from the input' };
+  }
+  const checks = SECURITY_HEADER_CHECKS.map((def) => {
+    const value = headerMap.get(def.header.toLowerCase()) ?? null;
+    const { status, note } = def.evaluate(value);
+    return { header: def.header, status, value, note };
+  });
+  const passCount = checks.filter((c) => c.status === "pass").length;
+  const warningCount = checks.filter((c) => c.status === "warning").length;
+  const missingCount = checks.filter((c) => c.status === "missing").length;
+  const totalChecks = checks.length;
+  const points = passCount + warningCount * 0.5;
+  const score = Math.round(points / totalChecks * 100);
+  const grade = score >= 90 ? "A" : score >= 75 ? "B" : score >= 60 ? "C" : score >= 40 ? "D" : "F";
+  return { checks, score, grade, passCount, warningCount, missingCount, totalChecks };
+}
 
-export { CLIENT_HINTS, DNS_RECORD_TYPES, HTTP_HEADERS, LINK_REL_VALUES, PERMISSIONS_POLICY_FEATURES, REFERRER_POLICY_VALUES, STATUS_CODES, X_CONTENT_TYPE_OPTIONS_HEADER, analyzeEmailHeaders, assessContentTypeRisk, buildAcceptLanguage, buildCacheControl, buildClientHints, buildContentDisposition, buildDnsQueryUrl, buildGeoUrl, buildHsts, buildLinkHeader, buildMapUrl, buildPermissionsPolicy, buildPreferHeader, buildPriorityHeader, buildRangeHeader, buildReferrerPolicy, buildRetryAfterHeader, buildRobotsMetaTag, buildVaryHeader, buildXContentTypeOptionsHeader, buildXRobotsTag, calculateCookieSizeBudget, checkSetCookieHeader, countryCodeToFlag, extractMultipartBoundary, formatCoordinates, formatTtl, getByCategory, getHeader, getHeadersByCategory, getStatusByCategory, getStatusCode, isClientError, isServerError, isSuccess, isValidIp, isValidIpv4, isValidIpv6, listCloseCodes, listOpcodes, lookupCloseCode, lookupOpcode, network_exports, parseAcceptLanguage, parseClientHintHeaders, parseContentDisposition, parseContentRangeHeader, parseDnsResponse, parseGeoResponse, parseHar, parseHsts, parseIpv6Address, parseMultipartFormData, parsePermissionsPolicy, parsePreferHeader, parsePriorityHeader, parseRetryAfterHeader, parseRobotsMetaTag, parseUserAgent, parseVaryHeader, parseXContentTypeOptionsHeader, parseXRobotsTag, searchHeaders, searchStatusCodes, splitSitemap, statusCodeToText, typeNumberToLabel, validateDomain, validateHeaderName, validateHeaderValue, validateManifest, validateRobotsTxt, validateSitemap };
+export { CLIENT_HINTS, DNS_RECORD_TYPES, HTTP_HEADERS, LINK_REL_VALUES, PERMISSIONS_POLICY_FEATURES, REFERRER_POLICY_VALUES, STATUS_CODES, X_CONTENT_TYPE_OPTIONS_HEADER, analyzeEmailHeaders, assessContentTypeRisk, buildAcceptLanguage, buildCacheControl, buildClientHints, buildContentDisposition, buildDnsQueryUrl, buildGeoUrl, buildHsts, buildLinkHeader, buildMapUrl, buildPermissionsPolicy, buildPreferHeader, buildPriorityHeader, buildRangeHeader, buildReferrerPolicy, buildRetryAfterHeader, buildRobotsMetaTag, buildVaryHeader, buildXContentTypeOptionsHeader, buildXRobotsTag, calculateCookieSizeBudget, checkSetCookieHeader, countryCodeToFlag, extractMultipartBoundary, formatCoordinates, formatTtl, getByCategory, getHeader, getHeadersByCategory, getStatusByCategory, getStatusCode, isClientError, isServerError, isSuccess, isValidIp, isValidIpv4, isValidIpv6, listCloseCodes, listOpcodes, lookupCloseCode, lookupOpcode, network_exports, parseAcceptLanguage, parseClientHintHeaders, parseContentDisposition, parseContentRangeHeader, parseDnsResponse, parseGeoResponse, parseHar, parseHsts, parseIpv6Address, parseMultipartFormData, parsePermissionsPolicy, parsePreferHeader, parsePriorityHeader, parseRetryAfterHeader, parseRobotsMetaTag, parseUserAgent, parseVaryHeader, parseXContentTypeOptionsHeader, parseXRobotsTag, scoreSecurityHeaders, searchHeaders, searchStatusCodes, splitSitemap, statusCodeToText, typeNumberToLabel, validateDomain, validateHeaderName, validateHeaderValue, validateManifest, validateRobotsTxt, validateSitemap };

package/dist/{chunk-P7TXG7CI.js → chunk-QVOK3BXM.js}

@@ -18,6 +18,7 @@ __export(text_exports, {
   applyOps: () => applyOps,
   calculateStringDistance: () => calculateStringDistance,
   centerText: () => centerText,
+  checkOxfordCommaConsistency: () => checkOxfordCommaConsistency,
   convertAll: () => convertAll,
   convertCase: () => convertCase,
   countWords: () => countWords,
@@ -26,6 +27,7 @@ __export(text_exports, {
   detectDelimiter: () => detectDelimiter,
   detectFillerWords: () => detectFillerWords,
   detectPassiveVoice: () => detectPassiveVoice,
+  detectWordyPhrases: () => detectWordyPhrases,
   diffLines: () => diffLines,
   diffLinesSimple: () => diffLinesSimple,
   diffStats: () => diffStats,
@@ -3095,5 +3097,99 @@ function getEmojiByCategory(category) {
 function getEmojiCategories() {
   return Array.from(new Set(EMOJI_TABLE.map((e) => e.category)));
 }
+var WORDY_PHRASES = [
+  { phrase: "due to the fact that", suggestion: "because" },
+  { phrase: "in spite of the fact that", suggestion: "although" },
+  { phrase: "despite the fact that", suggestion: "although" },
+  { phrase: "in order to", suggestion: "to" },
+  { phrase: "for the purpose of", suggestion: "for" },
+  { phrase: "in the event that", suggestion: "if" },
+  { phrase: "in the near future", suggestion: "soon" },
+  { phrase: "at this point in time", suggestion: "now" },
+  { phrase: "at the present time", suggestion: "now" },
+  { phrase: "on a daily basis", suggestion: "daily" },
+  { phrase: "on a regular basis", suggestion: "regularly" },
+  { phrase: "in a timely manner", suggestion: "promptly" },
+  { phrase: "with regard to", suggestion: "regarding" },
+  { phrase: "with respect to", suggestion: "regarding" },
+  { phrase: "in regards to", suggestion: "regarding" },
+  { phrase: "with the exception of", suggestion: "except" },
+  { phrase: "in close proximity to", suggestion: "near" },
+  { phrase: "take into consideration", suggestion: "consider" },
+  { phrase: "give consideration to", suggestion: "consider" },
+  { phrase: "make a decision", suggestion: "decide" },
+  { phrase: "is able to", suggestion: "can" },
+  { phrase: "are able to", suggestion: "can" },
+  { phrase: "a large number of", suggestion: "many" },
+  { phrase: "a majority of", suggestion: "most" },
+  { phrase: "each and every", suggestion: "each" },
+  { phrase: "first and foremost", suggestion: "first" },
+  { phrase: "last but not least", suggestion: "finally" },
+  { phrase: "null and void", suggestion: "void" },
+  { phrase: "whether or not", suggestion: "whether" },
+  { phrase: "the reason why", suggestion: "the reason" },
+  { phrase: "end result", suggestion: "result" },
+  { phrase: "future plans", suggestion: "plans" },
+  { phrase: "past history", suggestion: "history" },
+  { phrase: "basic fundamentals", suggestion: "fundamentals" },
+  { phrase: "absolutely essential", suggestion: "essential" },
+  { phrase: "it is important to note that", suggestion: "(often removable)" },
+  { phrase: "as a matter of fact", suggestion: "in fact" },
+  { phrase: "in the process of", suggestion: "(often removable)" }
+];
+function _wordyRegex(phrase) {
+  const tokens = phrase.split(/\s+/).map((t) => t.replace(/[.*+?^${}()|[\]\\]/g, "\\$&"));
+  return new RegExp("\\b" + tokens.join("\\s+") + "\\b", "gi");
+}
+function detectWordyPhrases(text) {
+  const totalWords = (text.match(/[A-Za-z0-9']+/g) ?? []).length;
+  const matches = [];
+  for (const entry of WORDY_PHRASES) {
+    const re = _wordyRegex(entry.phrase);
+    const indices = [];
+    let m;
+    while ((m = re.exec(text)) !== null) {
+      indices.push(m.index);
+      if (m.index === re.lastIndex) re.lastIndex++;
+    }
+    if (indices.length > 0) {
+      matches.push({ phrase: entry.phrase, suggestion: entry.suggestion, count: indices.length, indices });
+    }
+  }
+  matches.sort((a, b) => b.count - a.count || a.phrase.localeCompare(b.phrase));
+  const totalMatches = matches.reduce((s, m) => s + m.count, 0);
+  const density = totalWords > 0 ? Math.round(totalMatches / totalWords * 1e3) / 10 : 0;
+  return { totalWords, totalMatches, density, matches };
+}
+var _OXFORD_CONJ_RE = /(,)?\s+\b(?:and|or)\b\s+/gi;
+function checkOxfordCommaConsistency(text) {
+  const instances = [];
+  _OXFORD_CONJ_RE.lastIndex = 0;
+  let m;
+  while ((m = _OXFORD_CONJ_RE.exec(text)) !== null) {
+    const matchStart = m.index;
+    const hasCommaBefore = !!m[1];
+    let clauseStart = -1;
+    for (const ch of [".", "!", "?", "\n"]) {
+      const idx = text.lastIndexOf(ch, matchStart - 1);
+      if (idx > clauseStart) clauseStart = idx;
+    }
+    clauseStart += 1;
+    const clause = text.slice(clauseStart, matchStart);
+    const commaCount = (clause.match(/,/g) ?? []).length;
+    if (commaCount < 1) continue;
+    const snippetStart = Math.max(clauseStart, matchStart - 60);
+    const afterConjEnd = _OXFORD_CONJ_RE.lastIndex;
+    const tail = text.slice(afterConjEnd);
+    const boundaryOffset = tail.search(/[.!?\n,]/);
+    const snippetEnd = boundaryOffset === -1 ? Math.min(text.length, afterConjEnd + 40) : afterConjEnd + boundaryOffset;
+    const snippet = text.slice(snippetStart, snippetEnd).trim();
+    instances.push({ snippet, hasOxfordComma: hasCommaBefore, index: matchStart });
+  }
+  const withOxfordComma = instances.filter((i) => i.hasOxfordComma).length;
+  const withoutOxfordComma = instances.length - withOxfordComma;
+  const consistent = withOxfordComma === 0 || withoutOxfordComma === 0;
+  return { totalLists: instances.length, withOxfordComma, withoutOxfordComma, consistent, instances };
+}
 
-export { CASE_FORMATS, DEFAULT_CONVERT_OPTIONS, EMOJI_TABLE, ESCAPE_MODES, LINE_OPS, MORSE_CODE, addBorder, analyzeKeywordDensity, analyzeSentenceLengths, analyzeText, applyOp, applyOps, calculateStringDistance, centerText, convertAll, convertCase, countWords, csvToHtml, csvToMarkdown, detectDelimiter, detectFillerWords, detectPassiveVoice, diffLines, diffLinesSimple, diffStats, escapeAll, escapeString, extractHeadings, formatReadingTime, generate, generateDiff, generateHtmlTable, generateMarkdownTable, generateParagraphs, generateSentences, generateWords, getAvailableFonts, getEmojiByCategory, getEmojiByChar, getEmojiByShortcode, getEmojiCategories, getMorseForChar, getMorseTiming, htmlToMarkdown, isValidMorse, markdownToHtml, morseToText, numberToOrdinal, numberToRoman, numberToWords, ordinalWords, parseDiff, parseTableData, readabilityScore, renderMarkdown, romanToNumber, scoreReadability, searchEmoji, sentenceCount, slugify, slugifyAll, syllableCount, textToAscii, textToMorse, text_exports, unescapeString, wordFrequency };
+export { CASE_FORMATS, DEFAULT_CONVERT_OPTIONS, EMOJI_TABLE, ESCAPE_MODES, LINE_OPS, MORSE_CODE, addBorder, analyzeKeywordDensity, analyzeSentenceLengths, analyzeText, applyOp, applyOps, calculateStringDistance, centerText, checkOxfordCommaConsistency, convertAll, convertCase, countWords, csvToHtml, csvToMarkdown, detectDelimiter, detectFillerWords, detectPassiveVoice, detectWordyPhrases, diffLines, diffLinesSimple, diffStats, escapeAll, escapeString, extractHeadings, formatReadingTime, generate, generateDiff, generateHtmlTable, generateMarkdownTable, generateParagraphs, generateSentences, generateWords, getAvailableFonts, getEmojiByCategory, getEmojiByChar, getEmojiByShortcode, getEmojiCategories, getMorseForChar, getMorseTiming, htmlToMarkdown, isValidMorse, markdownToHtml, morseToText, numberToOrdinal, numberToRoman, numberToWords, ordinalWords, parseDiff, parseTableData, readabilityScore, renderMarkdown, romanToNumber, scoreReadability, searchEmoji, sentenceCount, slugify, slugifyAll, syllableCount, textToAscii, textToMorse, text_exports, unescapeString, wordFrequency };

package/dist/{chunk-PT4N4UBL.js → chunk-ZWFZRDQ4.js}

@@ -11,6 +11,7 @@ __export(media_exports, {
   readImageInfo: () => readImageInfo,
   readMidiInfo: () => readMidiInfo,
   readPdfMetadata: () => readPdfMetadata,
+  readPdfOutline: () => readPdfOutline,
   readPdfPageDimensions: () => readPdfPageDimensions,
   readVideoInfo: () => readVideoInfo,
   readWavInfo: () => readWavInfo
@@ -581,6 +582,74 @@ function readPdfPageDimensions(bytes) {
   if (out.length === 0) return { error: "Could not locate any page objects in this PDF" };
   return { version, pageCount: out.length, pages: out };
 }
+function parsePdfOutlineDest(dict) {
+  const directRef = dict.match(/\/Dest\s*\[\s*(\d+)\s+(\d+)\s+R/);
+  if (directRef) return { destType: "page", target: `${directRef[1]} ${directRef[2]} R` };
+  const directName = dict.match(/\/Dest\s*\/([^\s/()<>[\]]+)/);
+  if (directName) return { destType: "named", target: directName[1] };
+  const directString = dict.match(/\/Dest\s*\(((?:\\.|[^\\()])*)\)/);
+  if (directString) return { destType: "named", target: decodePdfString(directString[1], false) };
+  const actionUri = dict.match(/\/S\s*\/URI[\s\S]*?\/URI\s*\(((?:\\.|[^\\()])*)\)/);
+  if (actionUri) return { destType: "uri", target: decodePdfString(actionUri[1], false) };
+  const actionGotoRef = dict.match(/\/S\s*\/GoTo[\s\S]*?\/D\s*\[\s*(\d+)\s+(\d+)\s+R/);
+  if (actionGotoRef) return { destType: "page", target: `${actionGotoRef[1]} ${actionGotoRef[2]} R` };
+  const actionGotoName = dict.match(/\/S\s*\/GoTo[\s\S]*?\/D\s*\/([^\s/()<>[\]]+)/);
+  if (actionGotoName) return { destType: "named", target: actionGotoName[1] };
+  return { destType: "none", target: null };
+}
+function walkPdfOutlineChain(objMap, startRef, level, visited, out) {
+  let ref = startRef;
+  while (ref) {
+    if (visited.has(ref)) break;
+    visited.add(ref);
+    const body = objMap.get(ref);
+    if (!body) break;
+    const titleRaw = extractDictField(body, "Title");
+    const { destType, target } = parsePdfOutlineDest(body);
+    out.push({ title: titleRaw ?? "(untitled)", level, destType, target });
+    const firstMatch = body.match(/\/First\s+(\d+)\s+(\d+)\s+R/);
+    if (firstMatch) walkPdfOutlineChain(objMap, `${firstMatch[1]} ${firstMatch[2]}`, level + 1, visited, out);
+    const nextMatch = body.match(/\/Next\s+(\d+)\s+(\d+)\s+R/);
+    ref = nextMatch ? `${nextMatch[1]} ${nextMatch[2]}` : null;
+  }
+}
+function readPdfOutline(bytes) {
+  if (bytes.length < 8) return { error: "File too small to be a PDF" };
+  const header = bytesToLatin1(bytes.subarray(0, 16));
+  const versionMatch = header.match(/%PDF-(\d\.\d)/);
+  if (!versionMatch) return { error: "Not a valid PDF file (missing %PDF header)" };
+  const version = versionMatch[1];
+  const text = bytesToLatin1(bytes);
+  const objBlocks = [...text.matchAll(/(\d+)\s+(\d+)\s+obj([\s\S]*?)endobj/g)];
+  const objMap = /* @__PURE__ */ new Map();
+  for (const b of objBlocks) objMap.set(`${b[1]} ${b[2]}`, b[3]);
+  let outlinesBody = null;
+  const trailerMatches = [...text.matchAll(/trailer\s*<<([\s\S]*?)>>/g)];
+  if (trailerMatches.length > 0) {
+    const trailer = trailerMatches[trailerMatches.length - 1][1];
+    const rootRef = trailer.match(/\/Root\s+(\d+)\s+(\d+)\s+R/);
+    if (rootRef) {
+      const catalogBody = objMap.get(`${rootRef[1]} ${rootRef[2]}`);
+      const outlinesRef = catalogBody?.match(/\/Outlines\s+(\d+)\s+(\d+)\s+R/);
+      if (outlinesRef) outlinesBody = objMap.get(`${outlinesRef[1]} ${outlinesRef[2]}`) ?? null;
+    }
+  }
+  if (!outlinesBody) {
+    for (const b of objBlocks) {
+      if (/\/Type\s*\/Outlines\b/.test(b[3])) {
+        outlinesBody = b[3];
+        break;
+      }
+    }
+  }
+  if (!outlinesBody) return { error: "No /Outlines bookmark tree found in this PDF" };
+  const out = [];
+  const firstMatch = outlinesBody.match(/\/First\s+(\d+)\s+(\d+)\s+R/);
+  if (firstMatch) {
+    walkPdfOutlineChain(objMap, `${firstMatch[1]} ${firstMatch[2]}`, 0, /* @__PURE__ */ new Set(), out);
+  }
+  return { version, bookmarkCount: out.length, bookmarks: out };
+}
 var AUDIO_FORMAT_LABELS = {
   1: "PCM",
   3: "IEEE float",
@@ -1438,4 +1507,4 @@ function readMidiInfo(bytes) {
   };
 }
 
-export { inspectGifFrames, media_exports, readExifData, readFlacInfo, readIcoInfo, readId3Tags, readImageInfo, readMidiInfo, readPdfMetadata, readPdfPageDimensions, readVideoInfo, readWavInfo };
+export { inspectGifFrames, media_exports, readExifData, readFlacInfo, readIcoInfo, readId3Tags, readImageInfo, readMidiInfo, readPdfMetadata, readPdfOutline, readPdfPageDimensions, readVideoInfo, readWavInfo };