/** * Word 97-2003 Binary (.doc) Parser * * Pure TypeScript implementation that reads .doc files by: * 1. Using the OLE2 reader to extract WordDocument + Table streams * 2. Parsing the FIB (File Information Block) to locate text and formatting * 3. Reading the piece table (CLX) to reconstruct document text * 4. Parsing paragraph properties (PAPX) to detect paragraphs, headings, and tables * 5. Reading the stylesheet (STSH) to identify heading styles * 6. Returning a valid OfficeParserAST * * Ported from the algorithms in: * - ref/poi/poi-scratchpad/src/main/java/org/apache/poi/hwpf/ (Apache 2.0) * Specifically: HWPFDocument.java, FileInformationBlock.java, * TextPieceTable.java, PAPBinTable.java, StyleSheet.java, * Paragraph.java, CharacterRun.java, NotesTables.java * * @module doc */ /// import { OfficeParserAST, OfficeParserConfig } from '../../types'; /** * Parse a Word 97-2003 (.doc) file and return an OfficeParserAST. * * @param fileBuffer - Buffer containing the .doc file * @param config - OfficeParser configuration * @returns Parsed AST with paragraphs, headings, tables, and lists */ export declare function parseDoc(fileBuffer: Buffer, config: Required): Promise;