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.
Files changed (70) hide show
  1. package/README.md +284 -86
  2. package/dist/OfficeConverter.d.ts +46 -0
  3. package/dist/OfficeConverter.js +72 -0
  4. package/dist/OfficeGenerator.d.ts +19 -0
  5. package/dist/OfficeGenerator.js +48 -0
  6. package/dist/OfficeParser.d.ts +6 -0
  7. package/dist/OfficeParser.js +55 -28
  8. package/dist/cli.d.ts +3 -1
  9. package/dist/cli.js +107 -22
  10. package/dist/defaults.d.ts +41 -0
  11. package/dist/defaults.js +172 -0
  12. package/dist/generators/BaseGenerator.d.ts +58 -0
  13. package/dist/generators/BaseGenerator.js +107 -0
  14. package/dist/generators/ChunkingGenerator.d.ts +81 -0
  15. package/dist/generators/ChunkingGenerator.js +683 -0
  16. package/dist/generators/CsvGenerator.d.ts +30 -0
  17. package/dist/generators/CsvGenerator.js +233 -0
  18. package/dist/generators/HtmlGenerator.d.ts +37 -0
  19. package/dist/generators/HtmlGenerator.js +1013 -0
  20. package/dist/generators/MarkdownGenerator.d.ts +59 -0
  21. package/dist/generators/MarkdownGenerator.js +481 -0
  22. package/dist/generators/PdfGenerator.d.ts +22 -0
  23. package/dist/generators/PdfGenerator.js +118 -0
  24. package/dist/generators/RtfGenerator.d.ts +15 -0
  25. package/dist/generators/RtfGenerator.js +208 -0
  26. package/dist/generators/TextGenerator.d.ts +13 -0
  27. package/dist/generators/TextGenerator.js +108 -0
  28. package/dist/index.d.ts +11 -3
  29. package/dist/index.js +17 -2
  30. package/dist/index.mjs +2 -2
  31. package/dist/officeparser.browser.d.ts +878 -5
  32. package/dist/officeparser.browser.iife.js +703 -49
  33. package/dist/officeparser.browser.mjs +703 -49
  34. package/dist/parsers/CsvParser.d.ts +9 -0
  35. package/dist/parsers/CsvParser.js +110 -0
  36. package/dist/parsers/ExcelParser.d.ts +2 -2
  37. package/dist/parsers/ExcelParser.js +145 -114
  38. package/dist/parsers/HtmlParser.d.ts +2 -0
  39. package/dist/parsers/HtmlParser.js +539 -0
  40. package/dist/parsers/MarkdownParser.d.ts +2 -0
  41. package/dist/parsers/MarkdownParser.js +360 -0
  42. package/dist/parsers/OpenOfficeParser.d.ts +2 -2
  43. package/dist/parsers/OpenOfficeParser.js +237 -128
  44. package/dist/parsers/PdfParser.d.ts +2 -2
  45. package/dist/parsers/PdfParser.js +52 -49
  46. package/dist/parsers/PowerPointParser.d.ts +2 -2
  47. package/dist/parsers/PowerPointParser.js +132 -123
  48. package/dist/parsers/RtfParser.d.ts +22 -2
  49. package/dist/parsers/RtfParser.js +1398 -1282
  50. package/dist/parsers/WordParser.d.ts +3 -2
  51. package/dist/parsers/WordParser.js +333 -115
  52. package/dist/sbom.cdx.json +103 -103
  53. package/dist/types.d.ts +833 -5
  54. package/dist/types.js +71 -0
  55. package/dist/utils/astUtils.d.ts +16 -0
  56. package/dist/utils/astUtils.js +32 -0
  57. package/dist/utils/configUtils.d.ts +26 -0
  58. package/dist/utils/configUtils.js +140 -0
  59. package/dist/utils/envUtils.js +56 -2
  60. package/dist/utils/errorUtils.d.ts +17 -29
  61. package/dist/utils/errorUtils.js +109 -52
  62. package/dist/utils/moduleLoader.js +15 -9
  63. package/dist/utils/ocrUtils.js +2 -1
  64. package/dist/utils/sheetUtils.d.ts +7 -0
  65. package/dist/utils/sheetUtils.js +35 -0
  66. package/dist/utils/styleMapper.d.ts +36 -0
  67. package/dist/utils/styleMapper.js +224 -0
  68. package/dist/utils/xmlUtils.d.ts +0 -8
  69. package/dist/utils/xmlUtils.js +2 -1
  70. 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 { OfficeParserAST, OfficeParserConfig } from '../types.js';
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: OfficeParserConfig) => Promise<OfficeParserAST>;
79
+ export declare const parseWord: (buffer: Buffer, config: FullOfficeParserConfig) => Promise<OfficeParserAST>;