@cosmocoder/mcp-web-docs 2.0.13 → 2.0.15

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 (57) hide show
  1. package/build/config.d.ts +0 -1
  2. package/build/config.js +0 -5
  3. package/build/config.js.map +1 -1
  4. package/build/config.test.js +1 -25
  5. package/build/config.test.js.map +1 -1
  6. package/build/crawler/base.test.js +1 -0
  7. package/build/crawler/base.test.js.map +1 -1
  8. package/build/crawler/content-extractor-types.d.ts +3 -0
  9. package/build/crawler/crawlee-crawler.js +14 -9
  10. package/build/crawler/crawlee-crawler.js.map +1 -1
  11. package/build/crawler/crawlee-crawler.test.js +58 -7
  12. package/build/crawler/crawlee-crawler.test.js.map +1 -1
  13. package/build/crawler/default-extractor.js +1 -0
  14. package/build/crawler/default-extractor.js.map +1 -1
  15. package/build/crawler/default-extractor.test.js +1 -0
  16. package/build/crawler/default-extractor.test.js.map +1 -1
  17. package/build/crawler/docs-crawler.test.js +18 -10
  18. package/build/crawler/docs-crawler.test.js.map +1 -1
  19. package/build/crawler/github-pages-extractor.js +2 -0
  20. package/build/crawler/github-pages-extractor.js.map +1 -1
  21. package/build/crawler/github-pages-extractor.test.js +2 -0
  22. package/build/crawler/github-pages-extractor.test.js.map +1 -1
  23. package/build/crawler/github.js +1 -0
  24. package/build/crawler/github.js.map +1 -1
  25. package/build/crawler/github.test.js +1 -0
  26. package/build/crawler/github.test.js.map +1 -1
  27. package/build/crawler/queue-manager.test.js +7 -0
  28. package/build/crawler/queue-manager.test.js.map +1 -1
  29. package/build/crawler/storybook-extractor.js +3 -0
  30. package/build/crawler/storybook-extractor.js.map +1 -1
  31. package/build/crawler/storybook-extractor.test.js +2 -0
  32. package/build/crawler/storybook-extractor.test.js.map +1 -1
  33. package/build/index.js +2 -10
  34. package/build/index.js.map +1 -1
  35. package/build/index.test.js +19 -5
  36. package/build/index.test.js.map +1 -1
  37. package/build/processor/markdown.d.ts +15 -6
  38. package/build/processor/markdown.js +7 -30
  39. package/build/processor/markdown.js.map +1 -1
  40. package/build/processor/markdown.test.js +39 -6
  41. package/build/processor/markdown.test.js.map +1 -1
  42. package/build/processor/processor.js +8 -26
  43. package/build/processor/processor.js.map +1 -1
  44. package/build/processor/processor.test.js +118 -172
  45. package/build/processor/processor.test.js.map +1 -1
  46. package/build/storage/storage.js +34 -34
  47. package/build/storage/storage.js.map +1 -1
  48. package/build/storage/storage.test.js +90 -3
  49. package/build/storage/storage.test.js.map +1 -1
  50. package/build/types.d.ts +4 -0
  51. package/package.json +2 -3
  52. package/build/processor/content.d.ts +0 -16
  53. package/build/processor/content.js +0 -287
  54. package/build/processor/content.js.map +0 -1
  55. package/build/processor/content.test.d.ts +0 -1
  56. package/build/processor/content.test.js +0 -369
  57. package/build/processor/content.test.js.map +0 -1
@@ -1 +1 @@
1
- {"version":3,"file":"processor.js","sourceRoot":"","sources":["../../src/processor/processor.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,kBAAkB,EAAE,MAAM,cAAc,CAAC;AAClD,OAAO,EAAE,sBAAsB,EAAE,uBAAuB,EAAE,MAAM,eAAe,CAAC;AAChF,OAAO,EAAE,cAAc,EAAE,MAAM,cAAc,CAAC;AAC9C,OAAO,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AAErD,gFAAgF;AAChF,MAAM,4BAA4B,GAAG;IACnC,oBAAoB;IACpB,sBAAsB;IACtB,kBAAkB,EAAE,2DAA2D;IAC/E,kDAAkD;CACnD,CAAC;AAEF;;GAEG;AACH,SAAS,uBAAuB,CAC9B,OAAe,EACf,YAA0D,EAC1D,SAAiB,EACjB,OAAe,EACf,MAAgB;IAEhB,MAAM,MAAM,GAAG,aAAa,CAAC,OAAO,CAAC,CAAC;IAEtC,OAAO;QACL,OAAO;QACP,SAAS;QACT,OAAO;QACP,MAAM;QACN,GAAG,EAAE,YAAY,CAAC,GAAG;QACrB,KAAK,EAAE,YAAY,CAAC,KAAK;QACzB,IAAI,EAAE,YAAY,CAAC,IAAI;QACvB,QAAQ,EAAE;YACR,IAAI,EAAE,MAAM,CAAC,WAAW;YACxB,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS;YACzD,UAAU,EAAE,MAAM,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC,SAAS;SACzE;KACF,CAAC;AACJ,CAAC;AAED,KAAK,SAAS,CAAC,CAAC,eAAe,CAC7B,OAAe,EACf,YAAoB,EACpB,UAA8B,EAC9B,QAIC;IAED,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAChC,OAAO;IACT,CAAC;IAED,wEAAwE;IACxE,MAAM,QAAQ,GAAG,OAAO,CAAC,KAAK,CAAC,eAAe,CAAC,CAAC;IAChD,IAAI,YAAY,GAAG,EAAE,CAAC;IACtB,IAAI,SAAS,GAAG,CAAC,CAAC;IAClB,IAAI,WAAW,GAAG,CAAC,CAAC;IACpB,IAAI,UAAU,GAAG,CAAC,CAAC;IAEnB,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAC/B,MAAM,YAAY,GAAG,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACzC,MAAM,WAAW,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;QAEnC,IAAI,WAAW,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC7B,WAAW,IAAI,YAAY,CAAC,MAAM,CAAC;YACnC,SAAS;QACX,CAAC;QAED,gEAAgE;QAChE,MAAM,aAAa,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAExD,kDAAkD;QAClD,IAAI,aAAa,GAAG,YAAY,EAAE,CAAC;YACjC,yCAAyC;YACzC,IAAI,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;gBACpD,MAAM,uBAAuB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,WAAW,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;gBACjG,YAAY,GAAG,EAAE,CAAC;YACpB,CAAC;YAED,mCAAmC;YACnC,MAAM,SAAS,GAAG,WAAW,CAAC,KAAK,CAAC,gBAAgB,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC;YACvE,IAAI,aAAa,GAAG,EAAE,CAAC;YACvB,IAAI,cAAc,GAAG,CAAC,CAAC;YAEvB,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;gBACjC,MAAM,UAAU,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;gBAElD,IAAI,cAAc,GAAG,UAAU,GAAG,YAAY,GAAG,CAAC,EAAE,CAAC;oBACnD,IAAI,aAAa,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;wBACpC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC;wBACrD,MAAM,uBAAuB,CAC3B,aAAa,CAAC,IAAI,EAAE,EACpB,QAAQ,EACR,WAAW,EACX,WAAW,GAAG,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,EAClD,MAAM,CACP,CAAC;oBACJ,CAAC;oBACD,aAAa,GAAG,QAAQ,CAAC;oBACzB,cAAc,GAAG,UAAU,CAAC;gBAC9B,CAAC;qBACI,CAAC;oBACJ,aAAa,IAAI,GAAG,GAAG,QAAQ,CAAC;oBAChC,cAAc,IAAI,UAAU,CAAC;gBAC/B,CAAC;YACH,CAAC;YAED,iCAAiC;YACjC,IAAI,aAAa,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC;gBACrD,MAAM,uBAAuB,CAC3B,aAAa,CAAC,IAAI,EAAE,EACpB,QAAQ,EACR,WAAW,EACX,WAAW,GAAG,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,EAClD,MAAM,CACP,CAAC;YACJ,CAAC;QACH,CAAC;QACD,8EAA8E;aACzE,IAAI,UAAU,GAAG,aAAa,GAAG,YAAY,GAAG,CAAC,EAAE,CAAC;YACvD,IAAI,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;gBACpD,MAAM,uBAAuB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,WAAW,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;YACnG,CAAC;YACD,YAAY,GAAG,WAAW,CAAC;YAC3B,UAAU,GAAG,aAAa,CAAC;YAC3B,SAAS,GAAG,WAAW,CAAC;QAC1B,CAAC;QACD,yCAAyC;aACpC,CAAC;YACJ,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC5B,YAAY,IAAI,MAAM,CAAC;YACzB,CAAC;YACD,YAAY,IAAI,WAAW,CAAC;YAC5B,UAAU,IAAI,aAAa,CAAC;QAC9B,CAAC;QAED,WAAW,IAAI,YAAY,CAAC,MAAM,CAAC;IACrC,CAAC;IAED,iCAAiC;IACjC,IAAI,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;QACpD,MAAM,uBAAuB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,WAAW,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;IACnG,CAAC;AACH,CAAC;AAED,MAAM,OAAO,oBAAoB;IAEZ;IACA;IAFnB,YACmB,UAA8B,EAC9B,eAAuB,IAAI;QAD3B,eAAU,GAAV,UAAU,CAAoB;QAC9B,iBAAY,GAAZ,YAAY,CAAe;IAC3C,CAAC;IAEJ,KAAK,CAAC,OAAO,CAAC,WAAwB;QACpC,MAAM,CAAC,KAAK,CAAC,qCAAqC,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;QACrE,MAAM,CAAC,KAAK,CAAC,0CAA0C,WAAW,CAAC,OAAO,CAAC,MAAM,QAAQ,CAAC,CAAC;QAC3F,MAAM,CAAC,KAAK,CAAC,0CAA0C,WAAW,CAAC,aAAa,IAAI,SAAS,EAAE,CAAC,CAAC;QAEjG,IAAI,CAAC;YACH,iDAAiD;YACjD,IAAI,gBAAgB,CAAC;YAErB,sEAAsE;YACtE,MAAM,kBAAkB,GAAG,WAAW,CAAC,aAAa,IAAI,4BAA4B,CAAC,QAAQ,CAAC,WAAW,CAAC,aAAa,CAAC,CAAC;YAEzH,IAAI,kBAAkB,EAAE,CAAC;gBACvB,gEAAgE;gBAChE,MAAM,CAAC,KAAK,CAAC,gEAAgE,WAAW,CAAC,aAAa,EAAE,CAAC,CAAC;gBAC1G,gBAAgB,GAAG,MAAM,uBAAuB,CAAC,WAAW,CAAC,CAAC;YAChE,CAAC;iBACI,IAAI,cAAc,CAAC,WAAW,CAAC,IAAI,CAAC,EAAE,CAAC;gBAC1C,oBAAoB;gBACpB,MAAM,CAAC,KAAK,CAAC,uDAAuD,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC;gBACxF,gBAAgB,GAAG,MAAM,sBAAsB,CAAC,WAAW,CAAC,CAAC;YAC/D,CAAC;iBACI,CAAC;gBACJ,2BAA2B;gBAC3B,MAAM,CAAC,KAAK,CAAC,mDAAmD,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC;gBACpF,gBAAgB,GAAG,MAAM,kBAAkB,CAAC,WAAW,CAAC,CAAC;YAC3D,CAAC;YAED,IAAI,CAAC,gBAAgB,EAAE,CAAC;gBACtB,MAAM,CAAC,KAAK,CAAC,+DAA+D,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;gBAC/F,MAAM,IAAI,KAAK,CAAC,kCAAkC,CAAC,CAAC;YACtD,CAAC;YAED,MAAM,CAAC,KAAK,CAAC,6DAA6D,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;YAC7F,MAAM,CAAC,KAAK,CAAC,gCAAgC,gBAAgB,CAAC,OAAO,CAAC,UAAU,CAAC,MAAM,aAAa,CAAC,CAAC;YACtG,MAAM,CAAC,KAAK,CAAC,8CAA8C,gBAAgB,CAAC,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC;YAE7F,MAAM,MAAM,GAAoB,EAAE,CAAC;YACnC,IAAI,WAAW,GAAG,CAAC,CAAC;YAEpB,MAAM,QAAQ,GAAG;gBACf,GAAG,EAAE,gBAAgB,CAAC,OAAO,CAAC,GAAG;gBACjC,KAAK,EAAE,gBAAgB,CAAC,OAAO,CAAC,KAAK;gBACrC,IAAI,EAAE,gBAAgB,CAAC,OAAO,CAAC,IAAI;aACpC,CAAC;YAEF,oCAAoC;YACpC,KAAK,MAAM,SAAS,IAAI,gBAAgB,CAAC,OAAO,CAAC,UAAU,EAAE,CAAC;gBAC5D,MAAM,CAAC,KAAK,CAAC,gDAAgD,SAAS,CAAC,KAAK,EAAE,CAAC,CAAC;gBAChF,MAAM,CAAC,KAAK,CAAC,iDAAiD,SAAS,CAAC,IAAI,CAAC,MAAM,QAAQ,CAAC,CAAC;gBAE7F,MAAM,gBAAgB,GAAG,GAAG,SAAS,CAAC,KAAK,OAAO,SAAS,CAAC,IAAI,EAAE,CAAC;gBACnE,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,eAAe,CAAC,gBAAgB,EAAE,IAAI,CAAC,YAAY,EAAE,IAAI,CAAC,UAAU,EAAE,QAAQ,CAAC,EAAE,CAAC;oBAC1G,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;oBACnB,WAAW,EAAE,CAAC;gBAChB,CAAC;YACH,CAAC;YAED,MAAM,CAAC,KAAK,CAAC,kCAAkC,WAAW,SAAS,CAAC,CAAC;YAErE,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBACxB,MAAM,CAAC,IAAI,CAAC,2DAA2D,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;gBAC1F,MAAM,CAAC,IAAI,CAAC,mDAAmD,WAAW,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;gBAC7F,MAAM,CAAC,IAAI,CAAC,oDAAoD,gBAAgB,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;gBACnG,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAC;YAClD,CAAC;YAED,MAAM,CAAC,KAAK,CAAC,iDAAiD,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;YACjF,OAAO;gBACL,QAAQ,EAAE;oBACR,GAAG,EAAE,WAAW,CAAC,GAAG;oBACpB,KAAK,EAAE,gBAAgB,CAAC,OAAO,CAAC,KAAK;oBACrC,WAAW,EAAE,IAAI,IAAI,EAAE;iBACxB;gBACD,MAAM;aACP,CAAC;QACJ,CAAC;QACD,OAAO,KAAK,EAAE,CAAC;YACb,MAAM,CAAC,KAAK,CAAC,2CAA2C,WAAW,CAAC,GAAG,GAAG,EAAE,KAAK,CAAC,CAAC;YACnF,MAAM,CAAC,KAAK,CAAC,uCAAuC,EAAE,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YACpG,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;CACF"}
1
+ {"version":3,"file":"processor.js","sourceRoot":"","sources":["../../src/processor/processor.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,sBAAsB,EAAE,uBAAuB,EAAE,MAAM,eAAe,CAAC;AAChF,OAAO,EAAE,MAAM,EAAE,MAAM,mBAAmB,CAAC;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AAErD;;GAEG;AACH,SAAS,uBAAuB,CAC9B,OAAe,EACf,YAA0D,EAC1D,SAAiB,EACjB,OAAe,EACf,MAAgB;IAEhB,MAAM,MAAM,GAAG,aAAa,CAAC,OAAO,CAAC,CAAC;IAEtC,OAAO;QACL,OAAO;QACP,SAAS;QACT,OAAO;QACP,MAAM;QACN,GAAG,EAAE,YAAY,CAAC,GAAG;QACrB,KAAK,EAAE,YAAY,CAAC,KAAK;QACzB,IAAI,EAAE,YAAY,CAAC,IAAI;QACvB,QAAQ,EAAE;YACR,IAAI,EAAE,MAAM,CAAC,WAAW;YACxB,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS;YACzD,UAAU,EAAE,MAAM,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC,SAAS;SACzE;KACF,CAAC;AACJ,CAAC;AAED,KAAK,SAAS,CAAC,CAAC,eAAe,CAC7B,OAAe,EACf,YAAoB,EACpB,UAA8B,EAC9B,QAIC;IAED,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAChC,OAAO;IACT,CAAC;IAED,wEAAwE;IACxE,MAAM,QAAQ,GAAG,OAAO,CAAC,KAAK,CAAC,eAAe,CAAC,CAAC;IAChD,IAAI,YAAY,GAAG,EAAE,CAAC;IACtB,IAAI,SAAS,GAAG,CAAC,CAAC;IAClB,IAAI,WAAW,GAAG,CAAC,CAAC;IACpB,IAAI,UAAU,GAAG,CAAC,CAAC;IAEnB,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAC/B,MAAM,YAAY,GAAG,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACzC,MAAM,WAAW,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;QAEnC,IAAI,WAAW,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC7B,WAAW,IAAI,YAAY,CAAC,MAAM,CAAC;YACnC,SAAS;QACX,CAAC;QAED,gEAAgE;QAChE,MAAM,aAAa,GAAG,IAAI,CAAC,IAAI,CAAC,WAAW,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAExD,kDAAkD;QAClD,IAAI,aAAa,GAAG,YAAY,EAAE,CAAC;YACjC,yCAAyC;YACzC,IAAI,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;gBACpD,MAAM,uBAAuB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,WAAW,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;gBACjG,YAAY,GAAG,EAAE,CAAC;YACpB,CAAC;YAED,mCAAmC;YACnC,MAAM,SAAS,GAAG,WAAW,CAAC,KAAK,CAAC,gBAAgB,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC;YACvE,IAAI,aAAa,GAAG,EAAE,CAAC;YACvB,IAAI,cAAc,GAAG,CAAC,CAAC;YAEvB,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;gBACjC,MAAM,UAAU,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;gBAElD,IAAI,cAAc,GAAG,UAAU,GAAG,YAAY,GAAG,CAAC,EAAE,CAAC;oBACnD,IAAI,aAAa,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;wBACpC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC;wBACrD,MAAM,uBAAuB,CAC3B,aAAa,CAAC,IAAI,EAAE,EACpB,QAAQ,EACR,WAAW,EACX,WAAW,GAAG,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,EAClD,MAAM,CACP,CAAC;oBACJ,CAAC;oBACD,aAAa,GAAG,QAAQ,CAAC;oBACzB,cAAc,GAAG,UAAU,CAAC;gBAC9B,CAAC;qBACI,CAAC;oBACJ,aAAa,IAAI,GAAG,GAAG,QAAQ,CAAC;oBAChC,cAAc,IAAI,UAAU,CAAC;gBAC/B,CAAC;YACH,CAAC;YAED,iCAAiC;YACjC,IAAI,aAAa,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC;gBACrD,MAAM,uBAAuB,CAC3B,aAAa,CAAC,IAAI,EAAE,EACpB,QAAQ,EACR,WAAW,EACX,WAAW,GAAG,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,EAClD,MAAM,CACP,CAAC;YACJ,CAAC;QACH,CAAC;QACD,8EAA8E;aACzE,IAAI,UAAU,GAAG,aAAa,GAAG,YAAY,GAAG,CAAC,EAAE,CAAC;YACvD,IAAI,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;gBACpD,MAAM,uBAAuB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,WAAW,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;YACnG,CAAC;YACD,YAAY,GAAG,WAAW,CAAC;YAC3B,UAAU,GAAG,aAAa,CAAC;YAC3B,SAAS,GAAG,WAAW,CAAC;QAC1B,CAAC;QACD,yCAAyC;aACpC,CAAC;YACJ,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC5B,YAAY,IAAI,MAAM,CAAC;YACzB,CAAC;YACD,YAAY,IAAI,WAAW,CAAC;YAC5B,UAAU,IAAI,aAAa,CAAC;QAC9B,CAAC;QAED,WAAW,IAAI,YAAY,CAAC,MAAM,CAAC;IACrC,CAAC;IAED,iCAAiC;IACjC,IAAI,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;QACpD,MAAM,uBAAuB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,WAAW,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC;IACnG,CAAC;AACH,CAAC;AAED,MAAM,OAAO,oBAAoB;IAEZ;IACA;IAFnB,YACmB,UAA8B,EAC9B,eAAuB,IAAI;QAD3B,eAAU,GAAV,UAAU,CAAoB;QAC9B,iBAAY,GAAZ,YAAY,CAAe;IAC3C,CAAC;IAEJ,KAAK,CAAC,OAAO,CAAC,WAAwB;QACpC,MAAM,CAAC,KAAK,CAAC,qCAAqC,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;QACrE,MAAM,CAAC,KAAK,CAAC,0CAA0C,WAAW,CAAC,OAAO,CAAC,MAAM,QAAQ,CAAC,CAAC;QAC3F,MAAM,CAAC,KAAK,CAAC,0CAA0C,WAAW,CAAC,aAAa,IAAI,SAAS,EAAE,CAAC,CAAC;QAEjG,IAAI,CAAC;YACH,MAAM,CAAC,KAAK,CAAC,gCAAgC,WAAW,CAAC,aAAa,kBAAkB,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC;YAC5G,IAAI,gBAAgB,CAAC;YACrB,QAAQ,WAAW,CAAC,aAAa,EAAE,CAAC;gBAClC,KAAK,UAAU;oBACb,gBAAgB,GAAG,MAAM,sBAAsB,CAAC,WAAW,CAAC,CAAC;oBAC7D,MAAM;gBACR,KAAK,MAAM;oBACT,gBAAgB,GAAG,MAAM,uBAAuB,CAAC,WAAW,CAAC,CAAC;oBAC9D,MAAM;YACV,CAAC;YAED,IAAI,CAAC,gBAAgB,EAAE,CAAC;gBACtB,MAAM,CAAC,KAAK,CAAC,+DAA+D,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;gBAC/F,MAAM,IAAI,KAAK,CAAC,kCAAkC,CAAC,CAAC;YACtD,CAAC;YAED,MAAM,CAAC,KAAK,CAAC,6DAA6D,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;YAC7F,MAAM,CAAC,KAAK,CAAC,gCAAgC,gBAAgB,CAAC,OAAO,CAAC,UAAU,CAAC,MAAM,aAAa,CAAC,CAAC;YACtG,MAAM,CAAC,KAAK,CAAC,8CAA8C,gBAAgB,CAAC,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC;YAE7F,MAAM,MAAM,GAAoB,EAAE,CAAC;YACnC,IAAI,WAAW,GAAG,CAAC,CAAC;YAEpB,MAAM,QAAQ,GAAG;gBACf,GAAG,EAAE,gBAAgB,CAAC,OAAO,CAAC,GAAG;gBACjC,KAAK,EAAE,gBAAgB,CAAC,OAAO,CAAC,KAAK;gBACrC,IAAI,EAAE,gBAAgB,CAAC,OAAO,CAAC,IAAI;aACpC,CAAC;YAEF,oCAAoC;YACpC,KAAK,MAAM,SAAS,IAAI,gBAAgB,CAAC,OAAO,CAAC,UAAU,EAAE,CAAC;gBAC5D,MAAM,CAAC,KAAK,CAAC,gDAAgD,SAAS,CAAC,KAAK,EAAE,CAAC,CAAC;gBAChF,MAAM,CAAC,KAAK,CAAC,iDAAiD,SAAS,CAAC,IAAI,CAAC,MAAM,QAAQ,CAAC,CAAC;gBAE7F,MAAM,gBAAgB,GAAG,GAAG,SAAS,CAAC,KAAK,OAAO,SAAS,CAAC,IAAI,EAAE,CAAC;gBACnE,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,eAAe,CAAC,gBAAgB,EAAE,IAAI,CAAC,YAAY,EAAE,IAAI,CAAC,UAAU,EAAE,QAAQ,CAAC,EAAE,CAAC;oBAC1G,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;oBACnB,WAAW,EAAE,CAAC;gBAChB,CAAC;YACH,CAAC;YAED,MAAM,CAAC,KAAK,CAAC,kCAAkC,WAAW,SAAS,CAAC,CAAC;YAErE,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBACxB,MAAM,CAAC,IAAI,CAAC,2DAA2D,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;gBAC1F,MAAM,CAAC,IAAI,CAAC,mDAAmD,WAAW,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;gBAC7F,MAAM,CAAC,IAAI,CAAC,oDAAoD,gBAAgB,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;gBACnG,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAC;YAClD,CAAC;YAED,MAAM,CAAC,KAAK,CAAC,iDAAiD,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC;YACjF,OAAO;gBACL,QAAQ,EAAE;oBACR,GAAG,EAAE,WAAW,CAAC,GAAG;oBACpB,KAAK,EAAE,gBAAgB,CAAC,OAAO,CAAC,KAAK;oBACrC,WAAW,EAAE,IAAI,IAAI,EAAE;iBACxB;gBACD,MAAM;aACP,CAAC;QACJ,CAAC;QACD,OAAO,KAAK,EAAE,CAAC;YACb,MAAM,CAAC,KAAK,CAAC,2CAA2C,WAAW,CAAC,GAAG,GAAG,EAAE,KAAK,CAAC,CAAC;YACnF,MAAM,CAAC,KAAK,CAAC,uCAAuC,EAAE,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YACpG,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;CACF"}
@@ -1,5 +1,7 @@
1
+ import { JSDOM } from 'jsdom';
1
2
  import { WebDocumentProcessor } from './processor.js';
2
3
  import { createMockEmbeddings, createFailingEmbeddings } from '../__mocks__/embeddings.js';
4
+ import { contentExtractors } from '../crawler/content-extractors.js';
3
5
  describe('WebDocumentProcessor', () => {
4
6
  let processor;
5
7
  let mockEmbeddings;
@@ -8,36 +10,11 @@ describe('WebDocumentProcessor', () => {
8
10
  processor = new WebDocumentProcessor(mockEmbeddings, 500);
9
11
  });
10
12
  describe('process', () => {
11
- it('should process HTML content', async () => {
12
- const crawlResult = {
13
- url: 'https://example.com/docs/page',
14
- path: '/docs/page',
15
- title: 'Test Page',
16
- content: `
17
- <html>
18
- <body>
19
- <main>
20
- <h1>Test Documentation</h1>
21
- <p>This is some test content for the documentation page.</p>
22
- <h2>Features</h2>
23
- <p>Here are some features of our product.</p>
24
- </main>
25
- </body>
26
- </html>
27
- `,
28
- };
29
- const result = await processor.process(crawlResult);
30
- expect(result).toBeDefined();
31
- expect(result.metadata.url).toBe(crawlResult.url);
32
- // Title may come from crawl result or H1, depending on processor logic
33
- expect(result.metadata.title).toBeTruthy();
34
- expect(result.chunks.length).toBeGreaterThan(0);
35
- expect(result.chunks[0].vector.length).toBe(mockEmbeddings.dimensions);
36
- });
37
13
  it('should process markdown content', async () => {
38
14
  const crawlResult = {
39
15
  url: 'https://example.com/docs/readme.md',
40
- path: '/docs/readme.md',
16
+ path: '/docs/readme.html',
17
+ contentFormat: 'markdown',
41
18
  title: 'README',
42
19
  content: `# Project README
43
20
 
@@ -62,75 +39,81 @@ Here's how to use the package.
62
39
  expect(result.metadata.title).toBeTruthy();
63
40
  expect(result.chunks.length).toBeGreaterThan(0);
64
41
  });
65
- it('should process pre-extracted content from Storybook', async () => {
66
- const crawlResult = {
67
- url: 'https://storybook.example.com/button',
68
- path: '/button',
69
- title: 'Button',
70
- content: `# Button Component
71
-
72
- A versatile button component.
73
-
74
- ## Props
75
-
76
- | Prop | Type |
77
- |------|------|
78
- | variant | string |
79
-
80
- ## Example
81
-
82
- \`\`\`jsx
83
- <Button variant="primary">Click</Button>
84
- \`\`\`
85
- `,
86
- extractorUsed: 'StorybookExtractor',
42
+ it('should treat extractorUsed as diagnostic-only', async () => {
43
+ const input = {
44
+ url: 'https://example.com/guide',
45
+ path: '/guide.html',
46
+ contentFormat: 'markdown',
47
+ title: 'Guide',
48
+ content: '# Explicit Markdown\n\n## Section\n\nBody',
49
+ extractorUsed: 'FirstExtractor',
87
50
  };
88
- const result = await processor.process(crawlResult);
89
- expect(result).toBeDefined();
90
- expect(result.metadata.title).toBe('Button Component');
91
- expect(result.chunks.length).toBeGreaterThan(0);
51
+ const first = await processor.process(input);
52
+ const second = await processor.process({ ...input, extractorUsed: 'RenamedExtractor' });
53
+ expect(second.metadata.title).toBe(first.metadata.title);
54
+ expect(second.chunks.map(({ content, title }) => ({ content, title }))).toEqual(first.chunks.map(({ content, title }) => ({ content, title })));
92
55
  });
93
- it('should process pre-extracted content from GitHub Pages', async () => {
94
- const crawlResult = {
95
- url: 'https://user.github.io/repo/',
96
- path: '/',
97
- title: 'GitHub Pages',
98
- content: `# Welcome to GitHub Pages
99
-
100
- This is documentation hosted on GitHub Pages.
101
-
102
- ## Getting Started
103
-
104
- Follow these steps to get started.
105
- `,
106
- extractorUsed: 'GithubPagesExtractor',
107
- };
108
- const result = await processor.process(crawlResult);
109
- expect(result).toBeDefined();
110
- expect(result.chunks.length).toBeGreaterThan(0);
56
+ it('should process actual Storybook extractor output', async () => {
57
+ const originalWindow = globalThis.window;
58
+ const storybookWindow = new JSDOM(`<main class="sbdocs-content">
59
+ <h1>Button Component</h1>
60
+ <table class="docblock-argstable">
61
+ <tr><th>Name</th><th>Type</th><th>Default</th></tr>
62
+ <tr><td>variant</td><td>string</td><td>primary</td></tr>
63
+ </table>
64
+ </main>`).window;
65
+ const storybookDocument = storybookWindow.document;
66
+ globalThis.window = storybookWindow;
67
+ storybookWindow.getComputedStyle = vi.fn().mockReturnValue({
68
+ display: 'block',
69
+ visibility: 'visible',
70
+ opacity: '1',
71
+ });
72
+ const storybook = contentExtractors.storybook;
73
+ const expandSpy = vi.spyOn(storybook, 'expandAllTypeValues').mockResolvedValue(undefined);
74
+ const apiSpy = vi.spyOn(storybook, 'waitForStorybookAPI').mockResolvedValue(undefined);
75
+ const contentSpy = vi.spyOn(storybook, 'waitForStorybookContent').mockResolvedValue(storybookDocument.querySelector('main'));
76
+ try {
77
+ const storybookContent = await storybook.extractContent(storybookDocument);
78
+ const storybookResult = await processor.process({
79
+ url: 'https://storybook.example.com/button',
80
+ path: '/button',
81
+ extractorUsed: contentExtractors.storybook.constructor.name,
82
+ ...storybookContent,
83
+ title: storybookContent.title || 'Button',
84
+ });
85
+ expect(storybookResult.metadata.title).toBe('Button Component');
86
+ expect(storybookResult.chunks[0].content).toContain('Button Component');
87
+ const propsChunk = storybookResult.chunks.find((chunk) => chunk.metadata.props?.length);
88
+ expect(propsChunk?.content).toContain('| variant | string | primary |');
89
+ expect(propsChunk?.metadata.props).toContainEqual(expect.objectContaining({ name: 'variant', type: 'string', defaultValue: 'primary' }));
90
+ }
91
+ finally {
92
+ contentSpy.mockRestore();
93
+ apiSpy.mockRestore();
94
+ expandSpy.mockRestore();
95
+ globalThis.window = originalWindow;
96
+ }
111
97
  });
112
98
  it('should create chunks with proper metadata', async () => {
113
99
  const crawlResult = {
114
100
  url: 'https://example.com/api',
115
101
  path: '/api',
102
+ contentFormat: 'markdown',
116
103
  title: 'API',
117
- content: `
118
- <html>
119
- <body>
120
- <main>
121
- <h1>API Reference</h1>
122
- <p>This document describes the API endpoints.</p>
123
- <h2>GET /users</h2>
124
- <p>Returns a list of users.</p>
125
- <pre><code>
104
+ content: `# API Reference
105
+
106
+ This document describes the API endpoints.
107
+
108
+ ## GET /users
109
+
110
+ Returns a list of users.
111
+
112
+ \`\`\`json
126
113
  {
127
114
  "users": [...]
128
115
  }
129
- </code></pre>
130
- </main>
131
- </body>
132
- </html>
133
- `,
116
+ \`\`\``,
134
117
  };
135
118
  const result = await processor.process(crawlResult);
136
119
  expect(result).toBeDefined();
@@ -145,45 +128,29 @@ Follow these steps to get started.
145
128
  it('should handle large content by creating multiple chunks', async () => {
146
129
  const longContent = Array(50)
147
130
  .fill(null)
148
- .map((_, i) => `
149
- <h2>Section ${i + 1}</h2>
150
- <p>This is the content for section ${i + 1}. It contains some text that will need to be chunked appropriately for the embedding model. Lorem ipsum dolor sit amet, consectetur adipiscing elit.</p>
151
- `)
152
- .join('\n');
131
+ .map((_, i) => `## Section ${i + 1}\n\nThis is the content for section ${i + 1}. It contains some text that will need to be chunked appropriately for the embedding model. Lorem ipsum dolor sit amet, consectetur adipiscing elit.`)
132
+ .join('\n\n');
153
133
  const crawlResult = {
154
134
  url: 'https://example.com/long',
155
135
  path: '/long',
136
+ contentFormat: 'markdown',
156
137
  title: 'Long Document',
157
- content: `
158
- <html>
159
- <body>
160
- <main>
161
- <h1>Long Document</h1>
162
- ${longContent}
163
- </main>
164
- </body>
165
- </html>
166
- `,
138
+ content: `# Long Document\n\n${longContent}`,
167
139
  };
168
140
  const result = await processor.process(crawlResult);
169
141
  expect(result).toBeDefined();
170
142
  expect(result.chunks.length).toBeGreaterThan(1);
171
143
  });
172
- it('should throw error for content that cannot be parsed', async () => {
144
+ it.each([
145
+ ['empty', ''],
146
+ ['whitespace-only', ' \n\n '],
147
+ ])('should throw error for %s content', async (_, content) => {
173
148
  const crawlResult = {
174
149
  url: 'https://example.com/empty',
175
150
  path: '/empty',
151
+ contentFormat: 'markdown',
176
152
  title: 'Empty',
177
- content: '', // Empty content
178
- };
179
- await expect(processor.process(crawlResult)).rejects.toThrow();
180
- });
181
- it('should throw error for whitespace-only content', async () => {
182
- const crawlResult = {
183
- url: 'https://example.com/whitespace',
184
- path: '/whitespace',
185
- title: 'Whitespace',
186
- content: ' \n\n ',
153
+ content,
187
154
  };
188
155
  await expect(processor.process(crawlResult)).rejects.toThrow();
189
156
  });
@@ -193,17 +160,9 @@ Follow these steps to get started.
193
160
  const crawlResult = {
194
161
  url: 'https://example.com/test',
195
162
  path: '/test',
163
+ contentFormat: 'text',
196
164
  title: 'Test',
197
- content: `
198
- <html>
199
- <body>
200
- <main>
201
- <h1>Test</h1>
202
- <p>Some content here.</p>
203
- </main>
204
- </body>
205
- </html>
206
- `,
165
+ content: 'Test\n\nSome content here.',
207
166
  };
208
167
  await expect(failingProcessor.process(crawlResult)).rejects.toThrow('Embeddings service unavailable');
209
168
  });
@@ -211,17 +170,9 @@ Follow these steps to get started.
211
170
  const crawlResult = {
212
171
  url: 'https://example.com/dated',
213
172
  path: '/dated',
173
+ contentFormat: 'text',
214
174
  title: 'Dated',
215
- content: `
216
- <html>
217
- <body>
218
- <main>
219
- <h1>Document</h1>
220
- <p>Content with date.</p>
221
- </main>
222
- </body>
223
- </html>
224
- `,
175
+ content: 'Document\n\nContent with date.',
225
176
  };
226
177
  const before = new Date();
227
178
  const result = await processor.process(crawlResult);
@@ -234,18 +185,13 @@ Follow these steps to get started.
234
185
  const crawlResult = {
235
186
  url: 'https://example.com/chunks',
236
187
  path: '/chunks',
188
+ contentFormat: 'text',
237
189
  title: 'Chunks',
238
- content: `
239
- <html>
240
- <body>
241
- <main>
242
- <h1>Document</h1>
243
- <p>This is a longer paragraph that should be split into multiple chunks when using a small chunk size. The semantic chunker should create appropriate boundaries.</p>
244
- <p>Another paragraph with additional content that needs to be processed and chunked appropriately.</p>
245
- </main>
246
- </body>
247
- </html>
248
- `,
190
+ content: `Document
191
+
192
+ This is a longer paragraph that should be split into multiple chunks when using a small chunk size. The semantic chunker should create appropriate boundaries.
193
+
194
+ Another paragraph with additional content that needs to be processed and chunked appropriately.`,
249
195
  };
250
196
  const result = await smallChunkProcessor.process(crawlResult);
251
197
  // With smaller chunk size, should create more chunks
@@ -255,6 +201,7 @@ Follow these steps to get started.
255
201
  const crawlResult = {
256
202
  url: 'https://example.com/docs/component.mdx',
257
203
  path: '/docs/component.mdx',
204
+ contentFormat: 'markdown',
258
205
  title: 'MDX Component',
259
206
  content: `# MDX Component
260
207
 
@@ -279,6 +226,7 @@ import { MyComponent } from 'library';
279
226
  const crawlResult = {
280
227
  url: 'https://example.com/default',
281
228
  path: '/default',
229
+ contentFormat: 'text',
282
230
  title: 'Default Extracted',
283
231
  content: `Page Title
284
232
 
@@ -298,22 +246,23 @@ Another section of content here.`,
298
246
  const crawlResult = {
299
247
  url: 'https://example.com/api-ref',
300
248
  path: '/api-ref',
249
+ contentFormat: 'markdown',
301
250
  title: 'API Reference',
302
- content: `
303
- <html>
304
- <body>
305
- <main>
306
- <h1>API Reference</h1>
307
- <h2>GET /api/users</h2>
308
- <p>Returns array of users</p>
309
- <h3>Parameters</h3>
310
- <p>limit: number - Maximum results</p>
311
- <h3>Response</h3>
312
- <pre><code>{"users": []}</code></pre>
313
- </main>
314
- </body>
315
- </html>
316
- `,
251
+ content: `# API Reference
252
+
253
+ ## GET /api/users
254
+
255
+ Returns array of users
256
+
257
+ ### Parameters
258
+
259
+ limit: number - Maximum results
260
+
261
+ ### Response
262
+
263
+ \`\`\`json
264
+ {"users": []}
265
+ \`\`\``,
317
266
  };
318
267
  const result = await processor.process(crawlResult);
319
268
  expect(result).toBeDefined();
@@ -325,26 +274,23 @@ Another section of content here.`,
325
274
  const crawlResult = {
326
275
  url: 'https://example.com/examples',
327
276
  path: '/examples',
277
+ contentFormat: 'markdown',
328
278
  title: 'Examples',
329
- content: `
330
- <html>
331
- <body>
332
- <main>
333
- <h1>Code Examples</h1>
334
- <h2>Basic Example</h2>
335
- <pre><code>
279
+ content: `# Code Examples
280
+
281
+ ## Basic Example
282
+
283
+ \`\`\`js
336
284
  const result = doSomething();
337
285
  console.log(result);
338
- </code></pre>
339
- <h2>Advanced Example</h2>
340
- <pre><code>
286
+ \`\`\`
287
+
288
+ ## Advanced Example
289
+
290
+ \`\`\`js
341
291
  const config = { advanced: true };
342
292
  const result = doSomething(config);
343
- </code></pre>
344
- </main>
345
- </body>
346
- </html>
347
- `,
293
+ \`\`\``,
348
294
  };
349
295
  const result = await processor.process(crawlResult);
350
296
  expect(result).toBeDefined();
@@ -1 +1 @@
1
- {"version":3,"file":"processor.test.js","sourceRoot":"","sources":["../../src/processor/processor.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,oBAAoB,EAAE,MAAM,gBAAgB,CAAC;AACtD,OAAO,EAAE,oBAAoB,EAAE,uBAAuB,EAAE,MAAM,4BAA4B,CAAC;AAI3F,QAAQ,CAAC,sBAAsB,EAAE,GAAG,EAAE;IACpC,IAAI,SAA+B,CAAC;IACpC,IAAI,cAAkC,CAAC;IAEvC,UAAU,CAAC,GAAG,EAAE;QACd,cAAc,GAAG,oBAAoB,EAAE,CAAC;QACxC,SAAS,GAAG,IAAI,oBAAoB,CAAC,cAAc,EAAE,GAAG,CAAC,CAAC;IAC5D,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,SAAS,EAAE,GAAG,EAAE;QACvB,EAAE,CAAC,6BAA6B,EAAE,KAAK,IAAI,EAAE;YAC3C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,+BAA+B;gBACpC,IAAI,EAAE,YAAY;gBAClB,KAAK,EAAE,WAAW;gBAClB,OAAO,EAAE;;;;;;;;;;;SAWR;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;YAClD,uEAAuE;YACvE,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,UAAU,EAAE,CAAC;YAC3C,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;YAChD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,cAAc,CAAC,UAAU,CAAC,CAAC;QACzE,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,iCAAiC,EAAE,KAAK,IAAI,EAAE;YAC/C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,oCAAoC;gBACzC,IAAI,EAAE,iBAAiB;gBACvB,KAAK,EAAE,QAAQ;gBACf,OAAO,EAAE;;;;;;;;;;;;;;;CAehB;aACM,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,yCAAyC;YACzC,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,UAAU,EAAE,CAAC;YAC3C,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,qDAAqD,EAAE,KAAK,IAAI,EAAE;YACnE,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,sCAAsC;gBAC3C,IAAI,EAAE,SAAS;gBACf,KAAK,EAAE,QAAQ;gBACf,OAAO,EAAE;;;;;;;;;;;;;;;CAehB;gBACO,aAAa,EAAE,oBAAoB;aACpC,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,kBAAkB,CAAC,CAAC;YACvD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,wDAAwD,EAAE,KAAK,IAAI,EAAE;YACtE,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,8BAA8B;gBACnC,IAAI,EAAE,GAAG;gBACT,KAAK,EAAE,cAAc;gBACrB,OAAO,EAAE;;;;;;;CAOhB;gBACO,aAAa,EAAE,sBAAsB;aACtC,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,2CAA2C,EAAE,KAAK,IAAI,EAAE;YACzD,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,yBAAyB;gBAC9B,IAAI,EAAE,MAAM;gBACZ,KAAK,EAAE,KAAK;gBACZ,OAAO,EAAE;;;;;;;;;;;;;;;;SAgBR;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE;gBAC9B,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;gBACxC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC;gBAC1C,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,YAAY,CAAC,cAAc,CAAC,UAAU,CAAC,CAAC;gBAC7D,MAAM,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,WAAW,EAAE,CAAC;gBACrC,MAAM,CAAC,CAAC,UAAU,EAAE,KAAK,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;YACjF,CAAC,CAAC,CAAC;QACL,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,yDAAyD,EAAE,KAAK,IAAI,EAAE;YACvE,MAAM,WAAW,GAAG,KAAK,CAAC,EAAE,CAAC;iBAC1B,IAAI,CAAC,IAAI,CAAC;iBACV,GAAG,CACF,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;sBACE,CAAC,GAAG,CAAC;6CACkB,CAAC,GAAG,CAAC;OAC3C,CACE;iBACA,IAAI,CAAC,IAAI,CAAC,CAAC;YAEd,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,0BAA0B;gBAC/B,IAAI,EAAE,OAAO;gBACb,KAAK,EAAE,eAAe;gBACtB,OAAO,EAAE;;;;;kBAKC,WAAW;;;;SAIpB;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,sDAAsD,EAAE,KAAK,IAAI,EAAE;YACpE,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,2BAA2B;gBAChC,IAAI,EAAE,QAAQ;gBACd,KAAK,EAAE,OAAO;gBACd,OAAO,EAAE,EAAE,EAAE,gBAAgB;aAC9B,CAAC;YAEF,MAAM,MAAM,CAAC,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC;QACjE,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,gDAAgD,EAAE,KAAK,IAAI,EAAE;YAC9D,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,gCAAgC;gBACrC,IAAI,EAAE,aAAa;gBACnB,KAAK,EAAE,YAAY;gBACnB,OAAO,EAAE,YAAY;aACtB,CAAC;YAEF,MAAM,MAAM,CAAC,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC;QACjE,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,6CAA6C,EAAE,KAAK,IAAI,EAAE;YAC3D,MAAM,iBAAiB,GAAG,uBAAuB,EAAE,CAAC;YACpD,MAAM,gBAAgB,GAAG,IAAI,oBAAoB,CAAC,iBAAiB,EAAE,GAAG,CAAC,CAAC;YAE1E,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,0BAA0B;gBAC/B,IAAI,EAAE,OAAO;gBACb,KAAK,EAAE,MAAM;gBACb,OAAO,EAAE;;;;;;;;;SASR;aACF,CAAC;YAEF,MAAM,MAAM,CAAC,gBAAgB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,gCAAgC,CAAC,CAAC;QACxG,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,6BAA6B,EAAE,KAAK,IAAI,EAAE;YAC3C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,2BAA2B;gBAChC,IAAI,EAAE,QAAQ;gBACd,KAAK,EAAE,OAAO;gBACd,OAAO,EAAE;;;;;;;;;SASR;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YAC1B,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YACpD,MAAM,KAAK,GAAG,IAAI,IAAI,EAAE,CAAC;YAEzB,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,WAAW,CAAC,OAAO,EAAE,CAAC,CAAC,sBAAsB,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC,CAAC;YACvF,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,WAAW,CAAC,OAAO,EAAE,CAAC,CAAC,mBAAmB,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;QACrF,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,uCAAuC,EAAE,KAAK,IAAI,EAAE;YACrD,MAAM,mBAAmB,GAAG,IAAI,oBAAoB,CAAC,cAAc,EAAE,GAAG,CAAC,CAAC;YAE1E,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,4BAA4B;gBACjC,IAAI,EAAE,SAAS;gBACf,KAAK,EAAE,QAAQ;gBACf,OAAO,EAAE;;;;;;;;;;SAUR;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,mBAAmB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAE9D,qDAAqD;YACrD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,sBAAsB,CAAC,CAAC,CAAC,CAAC;QACzD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,yBAAyB,EAAE,KAAK,IAAI,EAAE;YACvC,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,wCAAwC;gBAC7C,IAAI,EAAE,qBAAqB;gBAC3B,KAAK,EAAE,eAAe;gBACtB,OAAO,EAAE;;;;;;;;;;;;;CAahB;aACM,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC;QACtD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,yCAAyC,EAAE,KAAK,IAAI,EAAE;YACvD,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,6BAA6B;gBAClC,IAAI,EAAE,UAAU;gBAChB,KAAK,EAAE,mBAAmB;gBAC1B,OAAO,EAAE;;;;;iCAKgB;gBACzB,aAAa,EAAE,kBAAkB;aAClC,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,0BAA0B,EAAE,GAAG,EAAE;QACxC,EAAE,CAAC,gCAAgC,EAAE,KAAK,IAAI,EAAE;YAC9C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,6BAA6B;gBAClC,IAAI,EAAE,UAAU;gBAChB,KAAK,EAAE,eAAe;gBACtB,OAAO,EAAE;;;;;;;;;;;;;;SAcR;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,oCAAoC;YACpC,oDAAoD;YACpD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,oCAAoC,EAAE,KAAK,IAAI,EAAE;YAClD,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,8BAA8B;gBACnC,IAAI,EAAE,WAAW;gBACjB,KAAK,EAAE,UAAU;gBACjB,OAAO,EAAE;;;;;;;;;;;;;;;;;;SAkBR;aACF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,oCAAoC;YACpC,MAAM,cAAc,GAAG,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC;YACpF,MAAM,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACpC,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}
1
+ {"version":3,"file":"processor.test.js","sourceRoot":"","sources":["../../src/processor/processor.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,EAAE,MAAM,OAAO,CAAC;AAC9B,OAAO,EAAE,oBAAoB,EAAE,MAAM,gBAAgB,CAAC;AACtD,OAAO,EAAE,oBAAoB,EAAE,uBAAuB,EAAE,MAAM,4BAA4B,CAAC;AAG3F,OAAO,EAAE,iBAAiB,EAAE,MAAM,kCAAkC,CAAC;AAErE,QAAQ,CAAC,sBAAsB,EAAE,GAAG,EAAE;IACpC,IAAI,SAA+B,CAAC;IACpC,IAAI,cAAkC,CAAC;IAEvC,UAAU,CAAC,GAAG,EAAE;QACd,cAAc,GAAG,oBAAoB,EAAE,CAAC;QACxC,SAAS,GAAG,IAAI,oBAAoB,CAAC,cAAc,EAAE,GAAG,CAAC,CAAC;IAC5D,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,SAAS,EAAE,GAAG,EAAE;QACvB,EAAE,CAAC,iCAAiC,EAAE,KAAK,IAAI,EAAE;YAC/C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,oCAAoC;gBACzC,IAAI,EAAE,mBAAmB;gBACzB,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,QAAQ;gBACf,OAAO,EAAE;;;;;;;;;;;;;;;CAehB;aACM,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,yCAAyC;YACzC,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,UAAU,EAAE,CAAC;YAC3C,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,+CAA+C,EAAE,KAAK,IAAI,EAAE;YAC7D,MAAM,KAAK,GAAgB;gBACzB,GAAG,EAAE,2BAA2B;gBAChC,IAAI,EAAE,aAAa;gBACnB,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,OAAO;gBACd,OAAO,EAAE,2CAA2C;gBACpD,aAAa,EAAE,gBAAgB;aAChC,CAAC;YAEF,MAAM,KAAK,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;YAC7C,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,EAAE,GAAG,KAAK,EAAE,aAAa,EAAE,kBAAkB,EAAE,CAAC,CAAC;YAExF,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;YACzD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,CAAC,OAAO,CAC7E,KAAK,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,CAAC,CAC/D,CAAC;QACJ,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,kDAAkD,EAAE,KAAK,IAAI,EAAE;YAChE,MAAM,cAAc,GAAG,UAAU,CAAC,MAAM,CAAC;YACzC,MAAM,eAAe,GAAG,IAAI,KAAK,CAAC;;;;;;cAM1B,CAAC,CAAC,MAAM,CAAC;YACjB,MAAM,iBAAiB,GAAG,eAAe,CAAC,QAAQ,CAAC;YACnD,UAAU,CAAC,MAAM,GAAG,eAAsD,CAAC;YAC3E,eAAe,CAAC,gBAAgB,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC,eAAe,CAAC;gBACzD,OAAO,EAAE,OAAO;gBAChB,UAAU,EAAE,SAAS;gBACrB,OAAO,EAAE,GAAG;aACb,CAAuD,CAAC;YAEzD,MAAM,SAAS,GAAG,iBAAiB,CAAC,SAKnC,CAAC;YACF,MAAM,SAAS,GAAG,EAAE,CAAC,KAAK,CAAC,SAAS,EAAE,qBAAqB,CAAC,CAAC,iBAAiB,CAAC,SAAS,CAAC,CAAC;YAC1F,MAAM,MAAM,GAAG,EAAE,CAAC,KAAK,CAAC,SAAS,EAAE,qBAAqB,CAAC,CAAC,iBAAiB,CAAC,SAAS,CAAC,CAAC;YACvF,MAAM,UAAU,GAAG,EAAE,CAAC,KAAK,CAAC,SAAS,EAAE,yBAAyB,CAAC,CAAC,iBAAiB,CAAC,iBAAiB,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC;YAE7H,IAAI,CAAC;gBACH,MAAM,gBAAgB,GAAG,MAAM,SAAS,CAAC,cAAc,CAAC,iBAAiB,CAAC,CAAC;gBAC3E,MAAM,eAAe,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC;oBAC9C,GAAG,EAAE,sCAAsC;oBAC3C,IAAI,EAAE,SAAS;oBACf,aAAa,EAAE,iBAAiB,CAAC,SAAS,CAAC,WAAW,CAAC,IAAI;oBAC3D,GAAG,gBAAgB;oBACnB,KAAK,EAAE,gBAAgB,CAAC,KAAK,IAAI,QAAQ;iBAC1C,CAAC,CAAC;gBACH,MAAM,CAAC,eAAe,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,kBAAkB,CAAC,CAAC;gBAChE,MAAM,CAAC,eAAe,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,SAAS,CAAC,kBAAkB,CAAC,CAAC;gBACxE,MAAM,UAAU,GAAG,eAAe,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;gBACxF,MAAM,CAAC,UAAU,EAAE,OAAO,CAAC,CAAC,SAAS,CAAC,gCAAgC,CAAC,CAAC;gBACxE,MAAM,CAAC,UAAU,EAAE,QAAQ,CAAC,KAAK,CAAC,CAAC,cAAc,CAC/C,MAAM,CAAC,gBAAgB,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,IAAI,EAAE,QAAQ,EAAE,YAAY,EAAE,SAAS,EAAE,CAAC,CACtF,CAAC;YACJ,CAAC;oBACO,CAAC;gBACP,UAAU,CAAC,WAAW,EAAE,CAAC;gBACzB,MAAM,CAAC,WAAW,EAAE,CAAC;gBACrB,SAAS,CAAC,WAAW,EAAE,CAAC;gBACxB,UAAU,CAAC,MAAM,GAAG,cAAc,CAAC;YACrC,CAAC;QACH,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,2CAA2C,EAAE,KAAK,IAAI,EAAE;YACzD,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,yBAAyB;gBAC9B,IAAI,EAAE,MAAM;gBACZ,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,KAAK;gBACZ,OAAO,EAAE;;;;;;;;;;;;OAYV;aACA,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE;gBAC9B,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;gBACxC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC;gBAC1C,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,YAAY,CAAC,cAAc,CAAC,UAAU,CAAC,CAAC;gBAC7D,MAAM,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,WAAW,EAAE,CAAC;gBACrC,MAAM,CAAC,CAAC,UAAU,EAAE,KAAK,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;YACjF,CAAC,CAAC,CAAC;QACL,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,yDAAyD,EAAE,KAAK,IAAI,EAAE;YACvE,MAAM,WAAW,GAAG,KAAK,CAAC,EAAE,CAAC;iBAC1B,IAAI,CAAC,IAAI,CAAC;iBACV,GAAG,CACF,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CACP,cAAc,CAAC,GAAG,CAAC,uCAAuC,CAAC,GAAG,CAAC,sJAAsJ,CACxN;iBACA,IAAI,CAAC,MAAM,CAAC,CAAC;YAEhB,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,0BAA0B;gBAC/B,IAAI,EAAE,OAAO;gBACb,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,eAAe;gBACtB,OAAO,EAAE,sBAAsB,WAAW,EAAE;aAC7C,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,IAAI,CAAC;YACN,CAAC,OAAO,EAAE,EAAE,CAAC;YACb,CAAC,iBAAiB,EAAE,YAAY,CAAC;SAClC,CAAC,CAAC,mCAAmC,EAAE,KAAK,EAAE,CAAC,EAAE,OAAO,EAAE,EAAE;YAC3D,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,2BAA2B;gBAChC,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,OAAO;gBACd,OAAO;aACR,CAAC;YAEF,MAAM,MAAM,CAAC,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC;QACjE,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,6CAA6C,EAAE,KAAK,IAAI,EAAE;YAC3D,MAAM,iBAAiB,GAAG,uBAAuB,EAAE,CAAC;YACpD,MAAM,gBAAgB,GAAG,IAAI,oBAAoB,CAAC,iBAAiB,EAAE,GAAG,CAAC,CAAC;YAE1E,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,0BAA0B;gBAC/B,IAAI,EAAE,OAAO;gBACb,aAAa,EAAE,MAAM;gBACrB,KAAK,EAAE,MAAM;gBACb,OAAO,EAAE,4BAA4B;aACtC,CAAC;YAEF,MAAM,MAAM,CAAC,gBAAgB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,gCAAgC,CAAC,CAAC;QACxG,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,6BAA6B,EAAE,KAAK,IAAI,EAAE;YAC3C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,2BAA2B;gBAChC,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,MAAM;gBACrB,KAAK,EAAE,OAAO;gBACd,OAAO,EAAE,gCAAgC;aAC1C,CAAC;YAEF,MAAM,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YAC1B,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YACpD,MAAM,KAAK,GAAG,IAAI,IAAI,EAAE,CAAC;YAEzB,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,WAAW,CAAC,OAAO,EAAE,CAAC,CAAC,sBAAsB,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC,CAAC;YACvF,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,WAAW,CAAC,OAAO,EAAE,CAAC,CAAC,mBAAmB,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;QACrF,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,uCAAuC,EAAE,KAAK,IAAI,EAAE;YACrD,MAAM,mBAAmB,GAAG,IAAI,oBAAoB,CAAC,cAAc,EAAE,GAAG,CAAC,CAAC;YAE1E,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,4BAA4B;gBACjC,IAAI,EAAE,SAAS;gBACf,aAAa,EAAE,MAAM;gBACrB,KAAK,EAAE,QAAQ;gBACf,OAAO,EAAE;;;;gGAI+E;aACzF,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,mBAAmB,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAE9D,qDAAqD;YACrD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,sBAAsB,CAAC,CAAC,CAAC,CAAC;QACzD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,yBAAyB,EAAE,KAAK,IAAI,EAAE;YACvC,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,wCAAwC;gBAC7C,IAAI,EAAE,qBAAqB;gBAC3B,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,eAAe;gBACtB,OAAO,EAAE;;;;;;;;;;;;;CAahB;aACM,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC;QACtD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,yCAAyC,EAAE,KAAK,IAAI,EAAE;YACvD,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,6BAA6B;gBAClC,IAAI,EAAE,UAAU;gBAChB,aAAa,EAAE,MAAM;gBACrB,KAAK,EAAE,mBAAmB;gBAC1B,OAAO,EAAE;;;;;iCAKgB;gBACzB,aAAa,EAAE,kBAAkB;aAClC,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IAEH,QAAQ,CAAC,0BAA0B,EAAE,GAAG,EAAE;QACxC,EAAE,CAAC,gCAAgC,EAAE,KAAK,IAAI,EAAE;YAC9C,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,6BAA6B;gBAClC,IAAI,EAAE,UAAU;gBAChB,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,eAAe;gBACtB,OAAO,EAAE;;;;;;;;;;;;;;OAcV;aACA,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,oCAAoC;YACpC,oDAAoD;YACpD,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;QAClD,CAAC,CAAC,CAAC;QAEH,EAAE,CAAC,oCAAoC,EAAE,KAAK,IAAI,EAAE;YAClD,MAAM,WAAW,GAAgB;gBAC/B,GAAG,EAAE,8BAA8B;gBACnC,IAAI,EAAE,WAAW;gBACjB,aAAa,EAAE,UAAU;gBACzB,KAAK,EAAE,UAAU;gBACjB,OAAO,EAAE;;;;;;;;;;;;;;OAcV;aACA,CAAC;YAEF,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC;YAEpD,MAAM,CAAC,MAAM,CAAC,CAAC,WAAW,EAAE,CAAC;YAC7B,oCAAoC;YACpC,MAAM,cAAc,GAAG,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC;YACpF,MAAM,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACpC,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}
@@ -38,6 +38,26 @@ function preprocessQuery(query) {
38
38
  logger.debug('[QueryPreprocess] Processed query:', result);
39
39
  return result;
40
40
  }
41
+ function buildExactUrlCondition(urls) {
42
+ return `url IN (${urls.map((url) => `'${escapeFilterValue(url)}'`).join(', ')})`;
43
+ }
44
+ function buildSearchWhereClause(visibilityFilter, options, tagFilteredUrls) {
45
+ const conditions = [`(${visibilityFilter})`];
46
+ if (options.filterByType) {
47
+ conditions.push(`type = '${escapeFilterValue(options.filterByType)}'`);
48
+ }
49
+ if (options.filterUrl) {
50
+ const escapedUrl = escapeFilterValue(options.filterUrl).replace(/\\/g, '\\\\').replace(/%/g, '\\%').replace(/_/g, '\\_');
51
+ conditions.push(`url LIKE '${escapedUrl}%'`);
52
+ }
53
+ if (options.filterUrls) {
54
+ conditions.push(buildExactUrlCondition(options.filterUrls));
55
+ }
56
+ if (tagFilteredUrls) {
57
+ conditions.push(buildExactUrlCondition(tagFilteredUrls));
58
+ }
59
+ return conditions.join(' AND ');
60
+ }
41
61
  export class DocumentStore {
42
62
  dbPath;
43
63
  vectorDbPath;
@@ -778,15 +798,19 @@ export class DocumentStore {
778
798
  if (!this.lanceTable) {
779
799
  throw new Error('Storage not initialized');
780
800
  }
781
- const { limit = 10, includeVectors = false, filterByType, filterByTags, textQuery } = options;
801
+ const { limit = 10, includeVectors = false, filterByType, filterUrls, filterByTags, textQuery } = options;
782
802
  logger.debug(`[DocumentStore] Searching documents with vector:`, {
783
803
  dimensions: queryVector.length,
784
804
  limit,
785
805
  includeVectors,
786
806
  filterByType,
807
+ filterUrls,
787
808
  filterByTags,
788
809
  hasTextQuery: !!textQuery,
789
810
  });
811
+ if (filterUrls?.length === 0) {
812
+ return [];
813
+ }
790
814
  // Add validation for query vector
791
815
  if (queryVector.length === 0 && !textQuery) {
792
816
  logger.debug('[DocumentStore] Empty query vector and no text query provided');
@@ -835,17 +859,9 @@ export class DocumentStore {
835
859
  }
836
860
  logger.debug(`[DocumentStore] Tag filter matched ${tagFilteredUrls.length} documents for vector search`);
837
861
  }
838
- // Build WHERE conditions
839
862
  const visibilityFilter = await this.getJournalVisibilityFilter();
840
- const conditions = [`(${visibilityFilter})`];
841
- if (filterByType) {
842
- conditions.push(`type = '${escapeFilterValue(filterByType)}'`);
843
- }
844
- if (tagFilteredUrls && tagFilteredUrls.length > 0) {
845
- const urlConditions = tagFilteredUrls.map((u) => `url = '${escapeFilterValue(u)}'`).join(' OR ');
846
- conditions.push(`(${urlConditions})`);
847
- }
848
- const query = this.lanceTable.search(queryVector).where(conditions.join(' AND ')).limit(limit);
863
+ const whereClause = buildSearchWhereClause(visibilityFilter, options, tagFilteredUrls);
864
+ const query = this.lanceTable.search(queryVector).where(whereClause).limit(limit);
849
865
  const results = await query.toArray();
850
866
  logger.debug(`[DocumentStore] Found ${results.length} results`);
851
867
  // Log the first result for debugging if available
@@ -919,7 +935,7 @@ export class DocumentStore {
919
935
  try {
920
936
  logger.debug('[DocumentStore] Creating FTS index on content field...');
921
937
  await this.lanceTable.createIndex('content', {
922
- config: lancedb.Index.fts(),
938
+ config: lancedb.Index.fts({ withPosition: true }),
923
939
  replace: true, // Replace existing index to prevent accumulation
924
940
  });
925
941
  this.ftsIndexCreated = true;
@@ -953,8 +969,10 @@ export class DocumentStore {
953
969
  logger.debug(`[DocumentStore] Returning cached results`);
954
970
  return cached;
955
971
  }
956
- const { limit = 10, filterByType, filterUrl, filterByTags } = options;
957
- const visibilityFilter = await this.getJournalVisibilityFilter();
972
+ const { limit = 10, filterUrls, filterByTags } = options;
973
+ if (filterUrls?.length === 0) {
974
+ return [];
975
+ }
958
976
  // If filtering by tags, get the list of URLs that have all those tags
959
977
  let tagFilteredUrls;
960
978
  if (filterByTags && filterByTags.length > 0) {
@@ -967,26 +985,8 @@ export class DocumentStore {
967
985
  }
968
986
  logger.debug(`[DocumentStore] Tag filter matched ${tagFilteredUrls.length} documents`);
969
987
  }
970
- // Build WHERE clause for filtering (using escaped values to prevent injection)
971
- const buildWhereClause = () => {
972
- const conditions = [`(${visibilityFilter})`];
973
- if (filterByType) {
974
- conditions.push(`type = '${escapeFilterValue(filterByType)}'`);
975
- }
976
- if (filterUrl) {
977
- // Filter by base URL - use LIKE to match URLs that start with the base URL
978
- // Escape the filterUrl and also escape LIKE wildcards within the value
979
- const escapedUrl = escapeFilterValue(filterUrl).replace(/\\/g, '\\\\').replace(/%/g, '\\%').replace(/_/g, '\\_');
980
- conditions.push(`url LIKE '${escapedUrl}%'`);
981
- }
982
- if (tagFilteredUrls && tagFilteredUrls.length > 0) {
983
- // Filter to only include URLs that match the tag filter
984
- const urlConditions = tagFilteredUrls.map((u) => `url = '${escapeFilterValue(u)}'`).join(' OR ');
985
- conditions.push(`(${urlConditions})`);
986
- }
987
- return conditions.join(' AND ');
988
- };
989
- const whereClause = buildWhereClause();
988
+ const visibilityFilter = await this.getJournalVisibilityFilter();
989
+ const whereClause = buildSearchWhereClause(visibilityFilter, options, tagFilteredUrls);
990
990
  try {
991
991
  if (!this.lanceTable) {
992
992
  throw new Error('Storage not initialized');