ai-document-parser 0.1.101

package/dist/parse/formats.js

@@ -0,0 +1,23 @@
+/**
+ * Clean-room rules for contributors (also summarized in AGENTS.md):
+ *
+ * 1. Implement parsers/converters from public format specs and public API behavior
+ *    (tests + docs/API.md) — do not copy code from historical derived engines.
+ * 2. Prefer extending src/edit, src/write, src/parse over large opaque backends.
+ * 3. New format support lands behind parseDocument / convertDocument only.
+ */
+/** Normalized format ids returned by detect / parseDocument. */
+export const CORE_PARSE_FORMATS = [
+    'docx',
+    'xlsx',
+    'xls',
+    'pdf',
+    'md',
+    'html',
+    'csv',
+    'doc',
+    'pptx',
+];
+export const CORE_PARSE_FORMAT_SET = new Set(CORE_PARSE_FORMATS);
+export const CORE_FORMATS_HELP = 'docx, xlsx, xls, pptx, pdf, md, html, csv, legacy doc';
+//# sourceMappingURL=formats.js.map

package/dist/parse/formats.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"formats.js","sourceRoot":"","sources":["../../src/parse/formats.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,gEAAgE;AAChE,MAAM,CAAC,MAAM,kBAAkB,GAAG;IAChC,MAAM;IACN,MAAM;IACN,KAAK;IACL,KAAK;IACL,IAAI;IACJ,MAAM;IACN,KAAK;IACL,KAAK;IACL,MAAM;CACE,CAAC;AAIX,MAAM,CAAC,MAAM,qBAAqB,GAAG,IAAI,GAAG,CAAS,kBAAkB,CAAC,CAAC;AAEzE,MAAM,CAAC,MAAM,iBAAiB,GAC5B,uDAAuD,CAAC"}

package/dist/parse/index.d.ts

@@ -0,0 +1,4 @@
+export { parseDocument, convertDocToDocx } from './router.js';
+export { readLegacyDoc, readLegacyDocBuffer, } from './legacy-doc.js';
+export { readPptxStructured, readPptxStructuredFromBuffer, } from './pptx.js';
+//# sourceMappingURL=index.d.ts.map

package/dist/parse/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/parse/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,gBAAgB,EAAE,MAAM,aAAa,CAAC;AAC9D,OAAO,EACL,aAAa,EACb,mBAAmB,GACpB,MAAM,iBAAiB,CAAC;AACzB,OAAO,EACL,kBAAkB,EAClB,4BAA4B,GAC7B,MAAM,WAAW,CAAC"}

package/dist/parse/index.js

@@ -0,0 +1,4 @@
+export { parseDocument, convertDocToDocx } from './router.js';
+export { readLegacyDoc, readLegacyDocBuffer, } from './legacy-doc.js';
+export { readPptxStructured, readPptxStructuredFromBuffer, } from './pptx.js';
+//# sourceMappingURL=index.js.map

package/dist/parse/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/parse/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,gBAAgB,EAAE,MAAM,aAAa,CAAC;AAC9D,OAAO,EACL,aAAa,EACb,mBAAmB,GACpB,MAAM,iBAAiB,CAAC;AACzB,OAAO,EACL,kBAAkB,EAClB,4BAA4B,GAC7B,MAAM,WAAW,CAAC"}

package/dist/parse/legacy-doc.d.ts

@@ -0,0 +1,15 @@
+export declare function readLegacyDocBuffer(buf: Buffer): Promise<{
+    text: string;
+    paragraphs: string[];
+    source: 'ai-document-parser-doc-binary';
+}>;
+export declare function readLegacyDoc(filePath: string): Promise<{
+    text: string;
+    paragraphs: string[];
+    source: 'ai-document-parser-doc-binary';
+}>;
+export declare function convertDocToDocx(docPath: string, docxPath?: string): Promise<{
+    docxPath: string;
+    paragraphCount: number;
+}>;
+//# sourceMappingURL=legacy-doc.d.ts.map

package/dist/parse/legacy-doc.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"legacy-doc.d.ts","sourceRoot":"","sources":["../../src/parse/legacy-doc.ts"],"names":[],"mappings":"AAwFA,wBAAsB,mBAAmB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC;IAC9D,IAAI,EAAE,MAAM,CAAC;IACb,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,MAAM,EAAE,+BAA+B,CAAC;CACzC,CAAC,CAKD;AAED,wBAAsB,aAAa,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;IAC7D,IAAI,EAAE,MAAM,CAAC;IACb,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,MAAM,EAAE,+BAA+B,CAAC;CACzC,CAAC,CAGD;AAED,wBAAsB,gBAAgB,CACpC,OAAO,EAAE,MAAM,EACf,QAAQ,CAAC,EAAE,MAAM,GAChB,OAAO,CAAC;IAAE,QAAQ,EAAE,MAAM,CAAC;IAAC,cAAc,EAAE,MAAM,CAAA;CAAE,CAAC,CAavD"}

package/dist/parse/legacy-doc.js

@@ -0,0 +1,100 @@
+import { readFile } from 'node:fs/promises';
+import path from 'node:path';
+import * as CFB from 'cfb';
+import { DocumentError } from '../utils/errors.js';
+import { writeDocx } from '../write/docx.js';
+const MIN_STRING_LEN = 3;
+function extractUtf16Strings(buf, minChars = MIN_STRING_LEN) {
+    const out = [];
+    let i = 0;
+    while (i < buf.length - 1) {
+        const chars = [];
+        const start = i;
+        while (i < buf.length - 1) {
+            const code = buf.readUInt16LE(i);
+            const ok = code >= 0x20 &&
+                code !== 0x7f &&
+                (code < 0xd800 || code > 0xdfff) &&
+                code !== 0xfffe &&
+                code !== 0xffff;
+            if (!ok)
+                break;
+            chars.push(String.fromCharCode(code));
+            i += 2;
+        }
+        if (chars.length >= minChars) {
+            const s = chars.join('').trim();
+            if (s && !/^[\x00-\x1f]+$/.test(s))
+                out.push(s);
+        }
+        if (i === start)
+            i += 2;
+    }
+    return out;
+}
+function extractAsciiStrings(buf, minLen = MIN_STRING_LEN) {
+    const out = [];
+    const re = /[\x20-\x7e\u00a0-\u024f]{4,}/g;
+    const latin = buf.toString('latin1');
+    let m;
+    while ((m = re.exec(latin)) !== null) {
+        const s = m[0].trim();
+        if (s.length >= minLen && !/^W\0o\0r\0d/.test(s))
+            out.push(s);
+    }
+    return out;
+}
+function dedupeOrdered(parts) {
+    const seen = new Set();
+    const result = [];
+    for (const p of parts) {
+        const key = p.replace(/\s+/g, ' ').trim();
+        if (key.length < MIN_STRING_LEN || seen.has(key))
+            continue;
+        seen.add(key);
+        result.push(key);
+    }
+    return result;
+}
+function extractTextFromWordDocument(data) {
+    const parts = dedupeOrdered([
+        ...extractUtf16Strings(data),
+        ...extractAsciiStrings(data),
+    ]);
+    if (parts.length === 0) {
+        throw new DocumentError('PARSE_FAILED', 'Could not extract text from .doc (empty or encrypted file)');
+    }
+    return parts.join('\n');
+}
+function parseCfbBuffer(buf) {
+    const cfb = CFB.read(new Uint8Array(buf), { type: 'array' });
+    const entry = CFB.find(cfb, 'WordDocument');
+    if (!entry?.content) {
+        throw new DocumentError('UNSUPPORTED_FORMAT', 'File is not a Word 97–2003 .doc (missing WordDocument stream)');
+    }
+    const content = entry.content;
+    return Buffer.isBuffer(content)
+        ? content
+        : Buffer.from(content);
+}
+export async function readLegacyDocBuffer(buf) {
+    const data = parseCfbBuffer(buf);
+    const text = extractTextFromWordDocument(data);
+    const paragraphs = text.split(/\n+/).filter((p) => p.trim().length > 0);
+    return { text, paragraphs, source: 'ai-document-parser-doc-binary' };
+}
+export async function readLegacyDoc(filePath) {
+    const buf = await readFile(filePath);
+    return readLegacyDocBuffer(buf);
+}
+export async function convertDocToDocx(docPath, docxPath) {
+    const { text } = await readLegacyDoc(docPath);
+    const out = docxPath ??
+        path.join(path.dirname(docPath), `${path.basename(docPath, path.extname(docPath))}.docx`);
+    await writeDocx(out, text);
+    return {
+        docxPath: out,
+        paragraphCount: text.split(/\n+/).filter(Boolean).length,
+    };
+}
+//# sourceMappingURL=legacy-doc.js.map

package/dist/parse/legacy-doc.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"legacy-doc.js","sourceRoot":"","sources":["../../src/parse/legacy-doc.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,IAAI,MAAM,WAAW,CAAC;AAC7B,OAAO,KAAK,GAAG,MAAM,KAAK,CAAC;AAC3B,OAAO,EAAE,aAAa,EAAE,MAAM,oBAAoB,CAAC;AACnD,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAE7C,MAAM,cAAc,GAAG,CAAC,CAAC;AAEzB,SAAS,mBAAmB,CAAC,GAAW,EAAE,QAAQ,GAAG,cAAc;IACjE,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,IAAI,CAAC,GAAG,CAAC,CAAC;IACV,OAAO,CAAC,GAAG,GAAG,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC1B,MAAM,KAAK,GAAa,EAAE,CAAC;QAC3B,MAAM,KAAK,GAAG,CAAC,CAAC;QAChB,OAAO,CAAC,GAAG,GAAG,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC1B,MAAM,IAAI,GAAG,GAAG,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;YACjC,MAAM,EAAE,GACN,IAAI,IAAI,IAAI;gBACZ,IAAI,KAAK,IAAI;gBACb,CAAC,IAAI,GAAG,MAAM,IAAI,IAAI,GAAG,MAAM,CAAC;gBAChC,IAAI,KAAK,MAAM;gBACf,IAAI,KAAK,MAAM,CAAC;YAClB,IAAI,CAAC,EAAE;gBAAE,MAAM;YACf,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC,CAAC;YACtC,CAAC,IAAI,CAAC,CAAC;QACT,CAAC;QACD,IAAI,KAAK,CAAC,MAAM,IAAI,QAAQ,EAAE,CAAC;YAC7B,MAAM,CAAC,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;YAChC,IAAI,CAAC,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,CAAC,CAAC;gBAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC;QACD,IAAI,CAAC,KAAK,KAAK;YAAE,CAAC,IAAI,CAAC,CAAC;IAC1B,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,mBAAmB,CAAC,GAAW,EAAE,MAAM,GAAG,cAAc;IAC/D,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,MAAM,EAAE,GAAG,+BAA+B,CAAC;IAC3C,MAAM,KAAK,GAAG,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC;IACrC,IAAI,CAAyB,CAAC;IAC9B,OAAO,CAAC,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACrC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QACtB,IAAI,CAAC,CAAC,MAAM,IAAI,MAAM,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC;YAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IAChE,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,aAAa,CAAC,KAAe;IACpC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,MAAM,MAAM,GAAa,EAAE,CAAC;IAC5B,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACtB,MAAM,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;QAC1C,IAAI,GAAG,CAAC,MAAM,GAAG,cAAc,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;YAAE,SAAS;QAC3D,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QACd,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IACnB,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,2BAA2B,CAAC,IAAY;IAC/C,MAAM,KAAK,GAAG,aAAa,CAAC;QAC1B,GAAG,mBAAmB,CAAC,IAAI,CAAC;QAC5B,GAAG,mBAAmB,CAAC,IAAI,CAAC;KAC7B,CAAC,CAAC;IACH,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,MAAM,IAAI,aAAa,CACrB,cAAc,EACd,4DAA4D,CAC7D,CAAC;IACJ,CAAC;IACD,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED,SAAS,cAAc,CAAC,GAAW;IACjC,MAAM,GAAG,GAAG,GAAG,CAAC,IAAI,CAAC,IAAI,UAAU,CAAC,GAAG,CAAC,EAAE,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC;IAC7D,MAAM,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,GAAG,EAAE,cAAc,CAAC,CAAC;IAC5C,IAAI,CAAC,KAAK,EAAE,OAAO,EAAE,CAAC;QACpB,MAAM,IAAI,aAAa,CACrB,oBAAoB,EACpB,+DAA+D,CAChE,CAAC;IACJ,CAAC;IACD,MAAM,OAAO,GAAG,KAAK,CAAC,OAAO,CAAC;IAC9B,OAAO,MAAM,CAAC,QAAQ,CAAC,OAAO,CAAC;QAC7B,CAAC,CAAC,OAAO;QACT,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,OAA4B,CAAC,CAAC;AAChD,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAC,GAAW;IAKnD,MAAM,IAAI,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC;IACjC,MAAM,IAAI,GAAG,2BAA2B,CAAC,IAAI,CAAC,CAAC;IAC/C,MAAM,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IACxE,OAAO,EAAE,IAAI,EAAE,UAAU,EAAE,MAAM,EAAE,+BAA+B,EAAE,CAAC;AACvE,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,aAAa,CAAC,QAAgB;IAKlD,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,CAAC,CAAC;IACrC,OAAO,mBAAmB,CAAC,GAAG,CAAC,CAAC;AAClC,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,gBAAgB,CACpC,OAAe,EACf,QAAiB;IAEjB,MAAM,EAAE,IAAI,EAAE,GAAG,MAAM,aAAa,CAAC,OAAO,CAAC,CAAC;IAC9C,MAAM,GAAG,GACP,QAAQ;QACR,IAAI,CAAC,IAAI,CACP,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,EACrB,GAAG,IAAI,CAAC,QAAQ,CAAC,OAAO,EAAE,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,OAAO,CACxD,CAAC;IACJ,MAAM,SAAS,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IAC3B,OAAO;QACL,QAAQ,EAAE,GAAG;QACb,cAAc,EAAE,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM;KACzD,CAAC;AACJ,CAAC"}

package/dist/parse/pdf.d.ts

@@ -0,0 +1,8 @@
+/**
+ * Extract plain text from a PDF using pdfjs-dist (public PDF.js API).
+ */
+export declare function extractPdfText(input: string | Buffer): Promise<{
+    text: string;
+    format: 'pdf';
+}>;
+//# sourceMappingURL=pdf.d.ts.map

package/dist/parse/pdf.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"pdf.d.ts","sourceRoot":"","sources":["../../src/parse/pdf.ts"],"names":[],"mappings":"AAGA;;GAEG;AACH,wBAAsB,cAAc,CAClC,KAAK,EAAE,MAAM,GAAG,MAAM,GACrB,OAAO,CAAC;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,KAAK,CAAA;CAAE,CAAC,CA4B1C"}

package/dist/parse/pdf.js

@@ -0,0 +1,34 @@
+import { readFile } from 'node:fs/promises';
+import { DocumentError, wrapError } from '../utils/errors.js';
+/**
+ * Extract plain text from a PDF using pdfjs-dist (public PDF.js API).
+ */
+export async function extractPdfText(input) {
+    try {
+        const data = typeof input === 'string' ? new Uint8Array(await readFile(input)) : new Uint8Array(input);
+        const pdfjs = await import('pdfjs-dist/legacy/build/pdf.mjs');
+        const loadingTask = pdfjs.getDocument({
+            data,
+            useSystemFonts: true,
+        });
+        const pdf = await loadingTask.promise;
+        const parts = [];
+        for (let pageNum = 1; pageNum <= pdf.numPages; pageNum++) {
+            const page = await pdf.getPage(pageNum);
+            const content = await page.getTextContent();
+            const line = content.items
+                .map((item) => ('str' in item && typeof item.str === 'string' ? item.str : ''))
+                .filter(Boolean)
+                .join(' ');
+            if (line.trim())
+                parts.push(line);
+        }
+        return { text: parts.join('\n').trim(), format: 'pdf' };
+    }
+    catch (err) {
+        if (err instanceof DocumentError)
+            throw err;
+        throw wrapError('PARSE_FAILED', 'Failed to parse PDF', err);
+    }
+}
+//# sourceMappingURL=pdf.js.map

package/dist/parse/pdf.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"pdf.js","sourceRoot":"","sources":["../../src/parse/pdf.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,aAAa,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAE9D;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAClC,KAAsB;IAEtB,IAAI,CAAC;QACH,MAAM,IAAI,GACR,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,IAAI,UAAU,CAAC,MAAM,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,UAAU,CAAC,KAAK,CAAC,CAAC;QAE5F,MAAM,KAAK,GAAG,MAAM,MAAM,CAAC,iCAAiC,CAAC,CAAC;QAC9D,MAAM,WAAW,GAAG,KAAK,CAAC,WAAW,CAAC;YACpC,IAAI;YACJ,cAAc,EAAE,IAAI;SACrB,CAAC,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,WAAW,CAAC,OAAO,CAAC;QACtC,MAAM,KAAK,GAAa,EAAE,CAAC;QAE3B,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,IAAI,GAAG,CAAC,QAAQ,EAAE,OAAO,EAAE,EAAE,CAAC;YACzD,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;YACxC,MAAM,OAAO,GAAG,MAAM,IAAI,CAAC,cAAc,EAAE,CAAC;YAC5C,MAAM,IAAI,GAAG,OAAO,CAAC,KAAK;iBACvB,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,KAAK,IAAI,IAAI,IAAI,OAAO,IAAI,CAAC,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;iBAC9E,MAAM,CAAC,OAAO,CAAC;iBACf,IAAI,CAAC,GAAG,CAAC,CAAC;YACb,IAAI,IAAI,CAAC,IAAI,EAAE;gBAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACpC,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;IAC1D,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,IAAI,GAAG,YAAY,aAAa;YAAE,MAAM,GAAG,CAAC;QAC5C,MAAM,SAAS,CAAC,cAAc,EAAE,qBAAqB,EAAE,GAAG,CAAC,CAAC;IAC9D,CAAC;AACH,CAAC"}

package/dist/parse/pptx.d.ts

@@ -0,0 +1,7 @@
+import type { PptxStructured } from '../types.js';
+export declare function readPptxStructured(filePath: string): Promise<PptxStructured>;
+export declare function readPptxStructuredFromBuffer(buf: Buffer): Promise<PptxStructured>;
+/** Flatten slides to paragraphs (for text / convert emit). */
+export declare function pptxToParagraphs(structured: PptxStructured): string[];
+export declare function pptxToText(structured: PptxStructured): string;
+//# sourceMappingURL=pptx.d.ts.map

package/dist/parse/pptx.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"pptx.d.ts","sourceRoot":"","sources":["../../src/parse/pptx.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAmElD,wBAAsB,kBAAkB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,cAAc,CAAC,CAQlF;AAED,wBAAsB,4BAA4B,CAChD,GAAG,EAAE,MAAM,GACV,OAAO,CAAC,cAAc,CAAC,CAQzB;AAED,8DAA8D;AAC9D,wBAAgB,gBAAgB,CAAC,UAAU,EAAE,cAAc,GAAG,MAAM,EAAE,CAUrE;AAED,wBAAgB,UAAU,CAAC,UAAU,EAAE,cAAc,GAAG,MAAM,CAQ7D"}

package/dist/parse/pptx.js

@@ -0,0 +1,107 @@
+import { readFile } from 'node:fs/promises';
+import JSZip from 'jszip';
+import { DocumentError, wrapError } from '../utils/errors.js';
+function decodeXmlEntities(s) {
+    return s
+        .replace(/&lt;/g, '<')
+        .replace(/&gt;/g, '>')
+        .replace(/&quot;/g, '"')
+        .replace(/&apos;/g, "'")
+        .replace(/&amp;/g, '&');
+}
+/** Extract visible text runs from a PPTX slide DrawingML fragment. */
+function extractSlideTexts(xml) {
+    const texts = [];
+    const paraRegex = /<a:p[\s\S]*?<\/a:p>/g;
+    let pm;
+    while ((pm = paraRegex.exec(xml)) !== null) {
+        const parts = [];
+        const tRegex = /<a:t(?:\s[^>]*)?>([^<]*)<\/a:t>/g;
+        let tm;
+        while ((tm = tRegex.exec(pm[0])) !== null) {
+            parts.push(decodeXmlEntities(tm[1]));
+        }
+        const line = parts.join('').trim();
+        if (line)
+            texts.push(line);
+    }
+    // Fallback: any a:t outside well-formed a:p (rare)
+    if (texts.length === 0) {
+        const tRegex = /<a:t(?:\s[^>]*)?>([^<]*)<\/a:t>/g;
+        let tm;
+        while ((tm = tRegex.exec(xml)) !== null) {
+            const line = decodeXmlEntities(tm[1]).trim();
+            if (line)
+                texts.push(line);
+        }
+    }
+    return texts;
+}
+function listSlidePaths(zip) {
+    return Object.keys(zip.files)
+        .filter((n) => /^ppt\/slides\/slide\d+\.xml$/i.test(n) && !zip.files[n].dir)
+        .sort((a, b) => {
+        const na = Number(/slide(\d+)/i.exec(a)?.[1] ?? 0);
+        const nb = Number(/slide(\d+)/i.exec(b)?.[1] ?? 0);
+        return na - nb;
+    });
+}
+async function readPptxFromZip(zip) {
+    if (!zip.file('ppt/presentation.xml') && listSlidePaths(zip).length === 0) {
+        throw new DocumentError('PARSE_FAILED', 'Invalid pptx: missing ppt/presentation.xml / slides');
+    }
+    const slides = [];
+    for (const path of listSlidePaths(zip)) {
+        const file = zip.file(path);
+        if (!file)
+            continue;
+        const xml = await file.async('string');
+        slides.push(extractSlideTexts(xml));
+    }
+    return { format: 'pptx', slides };
+}
+export async function readPptxStructured(filePath) {
+    try {
+        const buf = await readFile(filePath);
+        return readPptxStructuredFromBuffer(buf);
+    }
+    catch (err) {
+        if (err instanceof DocumentError)
+            throw err;
+        throw wrapError('PARSE_FAILED', `Failed to parse pptx ${filePath}`, err);
+    }
+}
+export async function readPptxStructuredFromBuffer(buf) {
+    try {
+        const zip = await JSZip.loadAsync(buf);
+        return readPptxFromZip(zip);
+    }
+    catch (err) {
+        if (err instanceof DocumentError)
+            throw err;
+        throw wrapError('PARSE_FAILED', 'Failed to parse pptx buffer', err);
+    }
+}
+/** Flatten slides to paragraphs (for text / convert emit). */
+export function pptxToParagraphs(structured) {
+    const out = [];
+    structured.slides.forEach((texts, i) => {
+        if (texts.length === 0) {
+            out.push(`Slide ${i + 1}`);
+            return;
+        }
+        for (const t of texts)
+            out.push(t);
+    });
+    return out;
+}
+export function pptxToText(structured) {
+    return structured.slides
+        .map((texts, i) => {
+        const body = texts.join('\n');
+        return body ? `## Slide ${i + 1}\n${body}` : `## Slide ${i + 1}`;
+    })
+        .join('\n\n')
+        .trim();
+}
+//# sourceMappingURL=pptx.js.map

package/dist/parse/pptx.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"pptx.js","sourceRoot":"","sources":["../../src/parse/pptx.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,EAAE,aAAa,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAG9D,SAAS,iBAAiB,CAAC,CAAS;IAClC,OAAO,CAAC;SACL,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC;SACrB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC;SACvB,OAAO,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;AAC5B,CAAC;AAED,sEAAsE;AACtE,SAAS,iBAAiB,CAAC,GAAW;IACpC,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,MAAM,SAAS,GAAG,sBAAsB,CAAC;IACzC,IAAI,EAA0B,CAAC;IAC/B,OAAO,CAAC,EAAE,GAAG,SAAS,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAC3C,MAAM,KAAK,GAAa,EAAE,CAAC;QAC3B,MAAM,MAAM,GAAG,kCAAkC,CAAC;QAClD,IAAI,EAA0B,CAAC;QAC/B,OAAO,CAAC,EAAE,GAAG,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YAC1C,KAAK,CAAC,IAAI,CAAC,iBAAiB,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;QACvC,CAAC;QACD,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QACnC,IAAI,IAAI;YAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC7B,CAAC;IACD,mDAAmD;IACnD,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,MAAM,MAAM,GAAG,kCAAkC,CAAC;QAClD,IAAI,EAA0B,CAAC;QAC/B,OAAO,CAAC,EAAE,GAAG,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YACxC,MAAM,IAAI,GAAG,iBAAiB,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;YAC7C,IAAI,IAAI;gBAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAC7B,CAAC;IACH,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,cAAc,CAAC,GAAU;IAChC,OAAO,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC;SAC1B,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,+BAA+B,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC;SAC3E,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;QACb,MAAM,EAAE,GAAG,MAAM,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC;QACnD,MAAM,EAAE,GAAG,MAAM,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC;QACnD,OAAO,EAAE,GAAG,EAAE,CAAC;IACjB,CAAC,CAAC,CAAC;AACP,CAAC;AAED,KAAK,UAAU,eAAe,CAAC,GAAU;IACvC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,sBAAsB,CAAC,IAAI,cAAc,CAAC,GAAG,CAAC,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC1E,MAAM,IAAI,aAAa,CACrB,cAAc,EACd,qDAAqD,CACtD,CAAC;IACJ,CAAC;IAED,MAAM,MAAM,GAAe,EAAE,CAAC;IAC9B,KAAK,MAAM,IAAI,IAAI,cAAc,CAAC,GAAG,CAAC,EAAE,CAAC;QACvC,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAC5B,IAAI,CAAC,IAAI;YAAE,SAAS;QACpB,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;QACvC,MAAM,CAAC,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,CAAC,CAAC;IACtC,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC;AACpC,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,kBAAkB,CAAC,QAAgB;IACvD,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,QAAQ,CAAC,CAAC;QACrC,OAAO,4BAA4B,CAAC,GAAG,CAAC,CAAC;IAC3C,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,IAAI,GAAG,YAAY,aAAa;YAAE,MAAM,GAAG,CAAC;QAC5C,MAAM,SAAS,CAAC,cAAc,EAAE,wBAAwB,QAAQ,EAAE,EAAE,GAAG,CAAC,CAAC;IAC3E,CAAC;AACH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,4BAA4B,CAChD,GAAW;IAEX,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC;QACvC,OAAO,eAAe,CAAC,GAAG,CAAC,CAAC;IAC9B,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,IAAI,GAAG,YAAY,aAAa;YAAE,MAAM,GAAG,CAAC;QAC5C,MAAM,SAAS,CAAC,cAAc,EAAE,6BAA6B,EAAE,GAAG,CAAC,CAAC;IACtE,CAAC;AACH,CAAC;AAED,8DAA8D;AAC9D,MAAM,UAAU,gBAAgB,CAAC,UAA0B;IACzD,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,UAAU,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,CAAC,EAAE,EAAE;QACrC,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,GAAG,CAAC,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;YAC3B,OAAO;QACT,CAAC;QACD,KAAK,MAAM,CAAC,IAAI,KAAK;YAAE,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACrC,CAAC,CAAC,CAAC;IACH,OAAO,GAAG,CAAC;AACb,CAAC;AAED,MAAM,UAAU,UAAU,CAAC,UAA0B;IACnD,OAAO,UAAU,CAAC,MAAM;SACrB,GAAG,CAAC,CAAC,KAAK,EAAE,CAAC,EAAE,EAAE;QAChB,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAC9B,OAAO,IAAI,CAAC,CAAC,CAAC,YAAY,CAAC,GAAG,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,YAAY,CAAC,GAAG,CAAC,EAAE,CAAC;IACnE,CAAC,CAAC;SACD,IAAI,CAAC,MAAM,CAAC;SACZ,IAAI,EAAE,CAAC;AACZ,CAAC"}

package/dist/parse/router.d.ts

@@ -0,0 +1,7 @@
+import type { DocumentInput, DocumentResult, ParseOptions } from '../types.js';
+/**
+ * Parse a document into text, structured JSON (agent edit path), AST, or chunks.
+ */
+export declare function parseDocument(input: DocumentInput, options?: ParseOptions): Promise<DocumentResult>;
+export { convertDocToDocx } from './legacy-doc.js';
+//# sourceMappingURL=router.d.ts.map

package/dist/parse/router.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"router.d.ts","sourceRoot":"","sources":["../../src/parse/router.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EACV,aAAa,EACb,cAAc,EACd,YAAY,EACb,MAAM,aAAa,CAAC;AAqErB;;GAEG;AACH,wBAAsB,aAAa,CACjC,KAAK,EAAE,aAAa,EACpB,OAAO,GAAE,YAAiB,GACzB,OAAO,CAAC,cAAc,CAAC,CA8KzB;AA4FD,OAAO,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC"}

package/dist/parse/router.js

@@ -0,0 +1,286 @@
+import { DocumentError, wrapError } from '../utils/errors.js';
+import { isPathLike } from '../utils/paths.js';
+import { readLegacyDoc, readLegacyDocBuffer } from './legacy-doc.js';
+import { readDocxStructured, readDocxStructuredFromBuffer, } from '../edit/docx-ooxml.js';
+import { readSpreadsheetStructuredAsync, readSpreadsheetStructuredFromBuffer, spreadsheetToText, } from '../edit/spreadsheet.js';
+import { assertSupportedParse, detectFormatFromBuffer, detectFormatFromText, formatFromExt, isZipBuffer, refineZipFormat, } from './detect.js';
+import { extractPdfText } from './pdf.js';
+import { pptxToParagraphs, pptxToText, readPptxStructured, readPptxStructuredFromBuffer, } from './pptx.js';
+import { parseCsv, parseHtml, parseMarkdown, readTextFile, } from './text-formats.js';
+import { chunkText } from '../convert/emit.js';
+function toBuffer(input) {
+    if (typeof input === 'string')
+        return null;
+    if (Buffer.isBuffer(input))
+        return input;
+    if (input instanceof ArrayBuffer)
+        return Buffer.from(input);
+    if (input instanceof Uint8Array)
+        return Buffer.from(input);
+    return null;
+}
+async function resolveFormat(input, buf, filePath) {
+    const fromExt = formatFromExt(filePath);
+    if (fromExt && fromExt !== 'unknown')
+        return fromExt;
+    if (buf) {
+        const guessed = detectFormatFromBuffer(buf);
+        if (guessed === 'docx' && isZipBuffer(buf)) {
+            return refineZipFormat(buf);
+        }
+        if (guessed)
+            return guessed;
+    }
+    if (typeof input === 'string' && !isPathLike(input)) {
+        return detectFormatFromText(input);
+    }
+    throw new DocumentError('UNSUPPORTED_FORMAT', 'Could not detect document format. Pass a path with a known extension.');
+}
+/**
+ * Parse a document into text, structured JSON (agent edit path), AST, or chunks.
+ */
+export async function parseDocument(input, options = {}) {
+    const output = options.output ?? 'text';
+    const buf = toBuffer(input);
+    const filePath = typeof input === 'string' && isPathLike(input) ? input : undefined;
+    try {
+        const format = await resolveFormat(input, buf, filePath);
+        assertSupportedParse(format);
+        // Legacy .doc
+        if (format === 'doc') {
+            const legacy = filePath
+                ? await readLegacyDoc(filePath)
+                : await readLegacyDocBuffer(buf);
+            if (output === 'structured') {
+                const structured = {
+                    format: 'doc',
+                    paragraphs: legacy.paragraphs,
+                    source: legacy.source,
+                };
+                const text = JSON.stringify(structured, null, 2);
+                return {
+                    format: 'doc',
+                    text,
+                    charCount: text.length,
+                    path: filePath,
+                    structured,
+                    warnings: [
+                        {
+                            code: 'LEGACY_DOC_LOW_FIDELITY',
+                            message: 'Legacy .doc extraction is heuristic; formatting is not preserved.',
+                        },
+                    ],
+                };
+            }
+            return finish(format, legacy.text, filePath, output, {
+                paragraphs: legacy.paragraphs,
+            });
+        }
+        // DOCX
+        if (format === 'docx') {
+            try {
+                const structured = filePath
+                    ? await readDocxStructured(filePath)
+                    : await readDocxStructuredFromBuffer(buf);
+                const text = structured.paragraphs.join('\n');
+                if (output === 'structured') {
+                    const payload = JSON.stringify(structured, null, 2);
+                    return {
+                        format: 'docx',
+                        text: payload,
+                        charCount: payload.length,
+                        path: filePath,
+                        structured,
+                    };
+                }
+                return finish('docx', text, filePath, output, {
+                    paragraphs: structured.paragraphs,
+                });
+            }
+            catch (err) {
+                // ZIP might be xlsx/pptx without a reliable extension
+                if (buf && isZipBuffer(buf)) {
+                    try {
+                        const refined = await refineZipFormat(buf);
+                        if (refined === 'pptx') {
+                            const structured = await readPptxStructuredFromBuffer(buf);
+                            return pptxResult(structured, filePath, output);
+                        }
+                        if (refined === 'xlsx') {
+                            const structured = readSpreadsheetStructuredFromBuffer(buf, 'xlsx');
+                            return spreadsheetResult(structured, filePath, output);
+                        }
+                    }
+                    catch {
+                        /* fall through */
+                    }
+                    try {
+                        const structured = readSpreadsheetStructuredFromBuffer(buf, 'xlsx');
+                        return spreadsheetResult(structured, filePath, output);
+                    }
+                    catch {
+                        /* fall through */
+                    }
+                }
+                throw err;
+            }
+        }
+        // PPTX
+        if (format === 'pptx') {
+            const structured = filePath
+                ? await readPptxStructured(filePath)
+                : await readPptxStructuredFromBuffer(buf);
+            return pptxResult(structured, filePath, output);
+        }
+        // Spreadsheets
+        if (format === 'xlsx' || format === 'xls') {
+            const structured = filePath
+                ? await readSpreadsheetStructuredAsync(filePath)
+                : readSpreadsheetStructuredFromBuffer(buf, format);
+            return spreadsheetResult(structured, filePath, output);
+        }
+        // PDF
+        if (format === 'pdf') {
+            const { text } = await extractPdfText(filePath ?? buf);
+            return finish('pdf', text, filePath, output, { paragraphs: text.split(/\n+/) });
+        }
+        // MD / HTML / CSV
+        if (format === 'md' || format === 'html' || format === 'csv') {
+            const raw = filePath != null
+                ? await readTextFile(filePath)
+                : buf
+                    ? buf.toString('utf8')
+                    : typeof input === 'string'
+                        ? input
+                        : '';
+            if (format === 'md') {
+                const parsed = parseMarkdown(raw);
+                if (output === 'structured') {
+                    const structured = { format: 'md', paragraphs: parsed.paragraphs };
+                    const payload = JSON.stringify(structured, null, 2);
+                    return {
+                        format: 'md',
+                        text: payload,
+                        charCount: payload.length,
+                        path: filePath,
+                        structured,
+                    };
+                }
+                return finish('md', parsed.text, filePath, output, {
+                    paragraphs: parsed.paragraphs,
+                });
+            }
+            if (format === 'html') {
+                const parsed = parseHtml(raw);
+                if (output === 'structured') {
+                    const structured = { format: 'html', paragraphs: parsed.paragraphs };
+                    const payload = JSON.stringify(structured, null, 2);
+                    return {
+                        format: 'html',
+                        text: payload,
+                        charCount: payload.length,
+                        path: filePath,
+                        structured,
+                    };
+                }
+                return finish('html', parsed.text, filePath, output, {
+                    paragraphs: parsed.paragraphs,
+                });
+            }
+            const parsed = parseCsv(raw);
+            if (output === 'structured') {
+                const structured = { format: 'csv', rows: parsed.rows };
+                const payload = JSON.stringify(structured, null, 2);
+                return {
+                    format: 'csv',
+                    text: payload,
+                    charCount: payload.length,
+                    path: filePath,
+                    structured,
+                };
+            }
+            return finish('csv', parsed.text, filePath, output, { rows: parsed.rows });
+        }
+        throw new DocumentError('UNSUPPORTED_FORMAT', `Unsupported format: ${format}`);
+    }
+    catch (err) {
+        if (err instanceof DocumentError)
+            throw err;
+        throw wrapError('PARSE_FAILED', 'Failed to parse document', err);
+    }
+}
+function pptxResult(structured, filePath, output) {
+    if (output === 'structured') {
+        const payload = JSON.stringify(structured, null, 2);
+        return {
+            format: 'pptx',
+            text: payload,
+            charCount: payload.length,
+            path: filePath,
+            structured,
+        };
+    }
+    const text = pptxToText(structured);
+    return finish('pptx', text, filePath, output, {
+        slides: structured.slides,
+        paragraphs: pptxToParagraphs(structured),
+    });
+}
+function spreadsheetResult(structured, filePath, output) {
+    if (output === 'structured') {
+        const payload = JSON.stringify(structured, null, 2);
+        return {
+            format: structured.format,
+            text: payload,
+            charCount: payload.length,
+            path: filePath,
+            structured,
+        };
+    }
+    const text = spreadsheetToText(structured);
+    return finish(structured.format, text, filePath, output, {
+        sheets: structured.sheets,
+    });
+}
+function finish(format, text, filePath, output, shape) {
+    if (output === 'ast') {
+        return {
+            format,
+            text: '',
+            charCount: 0,
+            path: filePath,
+            ast: { type: format, ...shape },
+        };
+    }
+    if (output === 'chunks') {
+        const chunks = chunkText(text);
+        const payload = JSON.stringify(chunks, null, 2);
+        return {
+            format,
+            text: payload,
+            charCount: payload.length,
+            path: filePath,
+            chunks,
+        };
+    }
+    // structured already handled by callers when needed
+    if (output === 'structured') {
+        const structured = { format, ...shape };
+        const payload = JSON.stringify(structured, null, 2);
+        return {
+            format,
+            text: payload,
+            charCount: payload.length,
+            path: filePath,
+            structured,
+        };
+    }
+    return {
+        format,
+        text,
+        charCount: text.length,
+        path: filePath,
+    };
+}
+export { convertDocToDocx } from './legacy-doc.js';
+//# sourceMappingURL=router.js.map