@doccloak/core 0.11.0 → 0.12.1

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 (60) hide show
  1. package/CHANGELOG.md +148 -2
  2. package/README.md +252 -19
  3. package/dist/doc.d.ts +68 -1
  4. package/dist/doc.js +447 -62
  5. package/dist/dom/docx.d.ts +135 -7
  6. package/dist/dom/docx.js +752 -125
  7. package/dist/dom/drawingml.d.ts +59 -0
  8. package/dist/dom/drawingml.js +176 -0
  9. package/dist/dom/errors.d.ts +35 -0
  10. package/dist/dom/errors.js +24 -0
  11. package/dist/dom/index.d.ts +3 -0
  12. package/dist/dom/index.js +6 -0
  13. package/dist/dom/office.d.ts +56 -0
  14. package/dist/dom/office.js +76 -23
  15. package/dist/dom/opc.d.ts +135 -7
  16. package/dist/dom/opc.js +407 -14
  17. package/dist/dom/package-policy.d.ts +137 -0
  18. package/dist/dom/package-policy.js +355 -0
  19. package/dist/dom/xlsx.d.ts +64 -6
  20. package/dist/dom/xlsx.js +130 -20
  21. package/dist/engine.d.ts +18 -0
  22. package/dist/engine.js +37 -13
  23. package/dist/env.d.ts +21 -1
  24. package/dist/index.d.ts +8 -6
  25. package/dist/index.js +10 -5
  26. package/dist/model-loader.d.ts +61 -6
  27. package/dist/model-loader.js +122 -17
  28. package/dist/pipeline.d.ts +87 -8
  29. package/dist/pipeline.js +249 -50
  30. package/dist/providers/bardsai.d.ts +8 -1
  31. package/dist/providers/bardsai.js +22 -2
  32. package/dist/providers/gliner-base.d.ts +8 -1
  33. package/dist/providers/gliner-base.js +22 -2
  34. package/dist/providers/gliner.d.ts +8 -1
  35. package/dist/providers/gliner.js +22 -2
  36. package/dist/regex/loader.d.ts +2 -0
  37. package/dist/regex/loader.js +2 -0
  38. package/dist/regex/rules.data.js +15 -14
  39. package/dist/regex/types.d.ts +6 -0
  40. package/dist/session.d.ts +101 -3
  41. package/dist/session.js +397 -43
  42. package/dist/surrogates.js +57 -45
  43. package/dist/worker-protocol.d.ts +13 -1
  44. package/dist/worker-protocol.js +164 -12
  45. package/package.json +1 -1
  46. package/rules/at.json +1 -1
  47. package/rules/be.json +1 -1
  48. package/rules/ch.json +1 -1
  49. package/rules/de.json +1 -1
  50. package/rules/dk.json +1 -1
  51. package/rules/es.json +1 -1
  52. package/rules/fi.json +1 -1
  53. package/rules/fr.json +1 -1
  54. package/rules/it.json +1 -1
  55. package/rules/no.json +1 -1
  56. package/rules/pl.json +1 -1
  57. package/rules/pt.json +1 -1
  58. package/rules/schema.json +4 -0
  59. package/rules/se.json +1 -1
  60. package/rules/universal.json +2 -1
package/rules/schema.json CHANGED
@@ -86,6 +86,10 @@
86
86
  "description": "Name of a post-match validation function in the runtime validator registry",
87
87
  "type": "string",
88
88
  "pattern": "^[a-z][a-zA-Z0-9]*$"
89
+ },
90
+ "multiline": {
91
+ "description": "When true the rule runs against the whole document; when false or absent it runs line by line (detectWithRegex splits on newlines, so a match can never span a line break). Only rules whose match legitimately crosses lines (PEM key blocks) set this.",
92
+ "type": "boolean"
89
93
  }
90
94
  }
91
95
  }
package/rules/se.json CHANGED
@@ -86,7 +86,7 @@
86
86
  {
87
87
  "id": "regex:se:postal",
88
88
  "entityType": "ADDRESS",
89
- "pattern": "\\b\\d{3}\\s?\\d{2}\\s+[\\p{L}][\\p{L}\\s-]+\\b",
89
+ "pattern": "\\b\\d{3}\\s?\\d{2}\\s+[\\p{L}][\\p{L}\\s-]*[\\p{L}](?![\\p{L}\\p{N}])",
90
90
  "flags": "gu",
91
91
  "confidence": 0.8,
92
92
  "domains": [
@@ -262,7 +262,7 @@
262
262
  {
263
263
  "id": "regex:universal:postal_city",
264
264
  "entityType": "ADDRESS",
265
- "pattern": "\\b\\d{2,5}[-\\s]?\\d{2,4}\\s+[\\p{L}][\\p{L}]+\\b",
265
+ "pattern": "\\b\\d{2,5}[-\\s]?\\d{2,4}\\s+[\\p{L}][\\p{L}]+(?![\\p{L}\\p{N}])",
266
266
  "flags": "gu",
267
267
  "confidence": 0.65,
268
268
  "domains": [
@@ -369,6 +369,7 @@
369
369
  "entityType": "SECRET",
370
370
  "pattern": "-----BEGIN (?:[A-Z]+ )*PRIVATE KEY(?: BLOCK)?-----[\\s\\S]*?-----END (?:[A-Z]+ )*PRIVATE KEY(?: BLOCK)?-----",
371
371
  "flags": "g",
372
+ "multiline": true,
372
373
  "confidence": 0.99,
373
374
  "domains": [
374
375
  "technical"