officeparser 5.2.2 → 6.0.2
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 +411 -163
- package/dist/OfficeParser.d.ts +90 -0
- package/dist/OfficeParser.js +217 -0
- package/dist/index.d.ts +51 -0
- package/dist/index.js +108 -0
- package/dist/officeparser.browser.js +152 -0
- package/dist/officeparser.browser.js.map +7 -0
- package/dist/parsers/ExcelParser.d.ts +33 -0
- package/dist/parsers/ExcelParser.js +643 -0
- package/dist/parsers/OpenOfficeParser.d.ts +32 -0
- package/dist/parsers/OpenOfficeParser.js +1399 -0
- package/dist/parsers/PdfParser.d.ts +68 -0
- package/dist/parsers/PdfParser.js +850 -0
- package/dist/parsers/PowerPointParser.d.ts +33 -0
- package/dist/parsers/PowerPointParser.js +778 -0
- package/dist/parsers/RtfParser.d.ts +164 -0
- package/dist/parsers/RtfParser.js +1641 -0
- package/dist/parsers/WordParser.d.ts +79 -0
- package/dist/parsers/WordParser.js +787 -0
- package/dist/types.d.ts +615 -0
- package/dist/types.js +2 -0
- package/dist/utils/chartUtils.d.ts +7 -0
- package/dist/utils/chartUtils.js +255 -0
- package/dist/utils/errorUtils.d.ts +58 -0
- package/dist/utils/errorUtils.js +120 -0
- package/dist/utils/imageUtils.d.ts +67 -0
- package/dist/utils/imageUtils.js +133 -0
- package/dist/utils/ocrUtils.d.ts +39 -0
- package/dist/utils/ocrUtils.js +61 -0
- package/dist/utils/xmlUtils.d.ts +83 -0
- package/dist/utils/xmlUtils.js +158 -0
- package/dist/utils/zipUtils.d.ts +74 -0
- package/dist/utils/zipUtils.js +112 -0
- package/package.json +44 -17
- package/officeParser.js +0 -790
- package/typings/officeParser.d.ts +0 -33
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* PowerPoint Presentation (PPTX) Parser
|
|
3
|
+
*
|
|
4
|
+
* **PPTX Format Overview:**
|
|
5
|
+
* PPTX is the default format for Microsoft PowerPoint since Office 2007, based on OOXML.
|
|
6
|
+
*
|
|
7
|
+
* **File Structure:**
|
|
8
|
+
* - `ppt/presentation.xml` - Presentation structure and slide list
|
|
9
|
+
* - `ppt/slides/slide1.xml` - Individual slide content
|
|
10
|
+
* - `ppt/notesSlides/notesSlide1.xml` - Speaker notes
|
|
11
|
+
* - `ppt/slideLayouts/*` - Slide layout definitions
|
|
12
|
+
* - `ppt/media/*` - Embedded images and media
|
|
13
|
+
*
|
|
14
|
+
* **Key Elements:**
|
|
15
|
+
* - `<p:sld>` - Slide
|
|
16
|
+
* - `<p:txBody>` - Text body containing paragraphs
|
|
17
|
+
* - `<a:p>` - Paragraph
|
|
18
|
+
* - `<a:r>` - Text run with formatting
|
|
19
|
+
* - `<a:t>` - Text content
|
|
20
|
+
*
|
|
21
|
+
* @module PowerPointParser
|
|
22
|
+
* @see https://www.ecma-international.org/publications-and-standards/standards/ecma-376/
|
|
23
|
+
*/
|
|
24
|
+
/// <reference types="node" />
|
|
25
|
+
import { OfficeParserAST, OfficeParserConfig } from '../types';
|
|
26
|
+
/**
|
|
27
|
+
* Parses a PowerPoint presentation (.pptx) and extracts slides and notes.
|
|
28
|
+
*
|
|
29
|
+
* @param buffer - The PPTX file as a Buffer
|
|
30
|
+
* @param config - Parser configuration
|
|
31
|
+
* @returns A promise resolving to the parsed AST
|
|
32
|
+
*/
|
|
33
|
+
export declare const parsePowerPoint: (buffer: Buffer, config: OfficeParserConfig) => Promise<OfficeParserAST>;
|