officeparser 6.1.0 → 7.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +284 -86
- package/dist/OfficeConverter.d.ts +46 -0
- package/dist/OfficeConverter.js +72 -0
- package/dist/OfficeGenerator.d.ts +19 -0
- package/dist/OfficeGenerator.js +48 -0
- package/dist/OfficeParser.d.ts +6 -0
- package/dist/OfficeParser.js +55 -28
- package/dist/cli.d.ts +3 -1
- package/dist/cli.js +107 -22
- package/dist/defaults.d.ts +41 -0
- package/dist/defaults.js +172 -0
- package/dist/generators/BaseGenerator.d.ts +58 -0
- package/dist/generators/BaseGenerator.js +107 -0
- package/dist/generators/ChunkingGenerator.d.ts +81 -0
- package/dist/generators/ChunkingGenerator.js +683 -0
- package/dist/generators/CsvGenerator.d.ts +30 -0
- package/dist/generators/CsvGenerator.js +233 -0
- package/dist/generators/HtmlGenerator.d.ts +37 -0
- package/dist/generators/HtmlGenerator.js +1013 -0
- package/dist/generators/MarkdownGenerator.d.ts +59 -0
- package/dist/generators/MarkdownGenerator.js +481 -0
- package/dist/generators/PdfGenerator.d.ts +22 -0
- package/dist/generators/PdfGenerator.js +118 -0
- package/dist/generators/RtfGenerator.d.ts +15 -0
- package/dist/generators/RtfGenerator.js +208 -0
- package/dist/generators/TextGenerator.d.ts +13 -0
- package/dist/generators/TextGenerator.js +108 -0
- package/dist/index.d.ts +11 -3
- package/dist/index.js +17 -2
- package/dist/index.mjs +2 -2
- package/dist/officeparser.browser.d.ts +878 -5
- package/dist/officeparser.browser.iife.js +703 -49
- package/dist/officeparser.browser.mjs +703 -49
- package/dist/parsers/CsvParser.d.ts +9 -0
- package/dist/parsers/CsvParser.js +110 -0
- package/dist/parsers/ExcelParser.d.ts +2 -2
- package/dist/parsers/ExcelParser.js +145 -114
- package/dist/parsers/HtmlParser.d.ts +2 -0
- package/dist/parsers/HtmlParser.js +539 -0
- package/dist/parsers/MarkdownParser.d.ts +2 -0
- package/dist/parsers/MarkdownParser.js +360 -0
- package/dist/parsers/OpenOfficeParser.d.ts +2 -2
- package/dist/parsers/OpenOfficeParser.js +237 -128
- package/dist/parsers/PdfParser.d.ts +2 -2
- package/dist/parsers/PdfParser.js +52 -49
- package/dist/parsers/PowerPointParser.d.ts +2 -2
- package/dist/parsers/PowerPointParser.js +132 -123
- package/dist/parsers/RtfParser.d.ts +22 -2
- package/dist/parsers/RtfParser.js +1398 -1282
- package/dist/parsers/WordParser.d.ts +3 -2
- package/dist/parsers/WordParser.js +333 -115
- package/dist/sbom.cdx.json +103 -103
- package/dist/types.d.ts +833 -5
- package/dist/types.js +71 -0
- package/dist/utils/astUtils.d.ts +16 -0
- package/dist/utils/astUtils.js +32 -0
- package/dist/utils/configUtils.d.ts +26 -0
- package/dist/utils/configUtils.js +140 -0
- package/dist/utils/envUtils.js +56 -2
- package/dist/utils/errorUtils.d.ts +17 -29
- package/dist/utils/errorUtils.js +109 -52
- package/dist/utils/moduleLoader.js +15 -9
- package/dist/utils/ocrUtils.js +2 -1
- package/dist/utils/sheetUtils.d.ts +7 -0
- package/dist/utils/sheetUtils.js +35 -0
- package/dist/utils/styleMapper.d.ts +36 -0
- package/dist/utils/styleMapper.js +224 -0
- package/dist/utils/xmlUtils.d.ts +0 -8
- package/dist/utils/xmlUtils.js +2 -1
- package/package.json +28 -9
|
@@ -39,6 +39,7 @@
|
|
|
39
39
|
* - `<w:p>` - Paragraph
|
|
40
40
|
* - `<w:r>` - Run (contiguous text with same formatting)
|
|
41
41
|
* - `<w:t>` - Text content
|
|
42
|
+
* - `<w:br>` - Line or page break
|
|
42
43
|
* - `<w:b>`, `<w:i>`, `<w:u>` - Bold, italic, underline
|
|
43
44
|
* - `<w:pStyle>` - Paragraph style (for headings)
|
|
44
45
|
* - `<w:numPr>` - List numbering properties
|
|
@@ -58,7 +59,7 @@
|
|
|
58
59
|
* @see https://www.ecma-international.org/publications-and-standards/standards/ecma-376/ OOXML Standard
|
|
59
60
|
* @see https://learn.microsoft.com/en-us/openspecs/office_standards/ms-docx/ [MS-DOCX] Specification
|
|
60
61
|
*/
|
|
61
|
-
import {
|
|
62
|
+
import { FullOfficeParserConfig, OfficeParserAST } from '../types.js';
|
|
62
63
|
/**
|
|
63
64
|
* Parses a Word document (.docx) and extracts content, formatting, and metadata.
|
|
64
65
|
*
|
|
@@ -75,4 +76,4 @@ import { OfficeParserAST, OfficeParserConfig } from '../types.js';
|
|
|
75
76
|
* @param config - Parser configuration options
|
|
76
77
|
* @returns A promise resolving to the parsed AST
|
|
77
78
|
*/
|
|
78
|
-
export declare const parseWord: (buffer: Buffer, config:
|
|
79
|
+
export declare const parseWord: (buffer: Buffer, config: FullOfficeParserConfig) => Promise<OfficeParserAST>;
|