pdf-to-markdown/examples/Tragedy-Of-The-Commons/detectListItems.json
Johannes Zillmann 7abafc61e7 Improve word boundary detection
- sometimes a word is provided with multiple items. E.g: "T his is a sen tence"
- use x-axis distance to not put whitespaces in the middle of a word
- also tweak the line detection a bit (for Alice)
2024-05-20 00:22:24 -06:00

61 lines
5.6 KiB
JSON

{
"pages": 7,
"items": 6779,
"groupedItems": 1102,
"changes": 201,
"schema": [
{
"name": "line"
},
{
"name": "token types"
},
{
"name": "types"
},
{
"name": "x"
},
{
"name": "y"
},
{
"name": "width"
},
{
"name": "height"
},
{
"name": "str"
},
{
"name": "fontName"
},
{
"name": "dir"
}
],
"globals": {}
}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"1. J. B. Wiesner and H. F. York, Sci. Amer.","line":101,"x":392.9999999999999,"y":573.5400000000005,"width":"112.38","height":"8.50","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"2. G. Hardin, J. Hered. 50, 68 (1959); S. von","line":103,"x":392.28,"y":559.2000000000005,"width":"114.84","height":"9.60","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"3. J. von Neumann and 0. Morgenstern, Theory","line":105,"x":392.28,"y":544.8000000000005,"width":"131.52","height":"9.40","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"4. J. H. Fremlin, New Sci., No. 415 (1964), p. 285.","line":108,"x":392.4000000000001,"y":523.6200000000005,"width":"129.06","height":"9.20","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"5. A. Smith, The Wealth of Nations (Modem","line":109,"x":392.2800000000002,"y":516.6000000000004,"width":"121.50","height":"8.70","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"6. W. F. Lloyd, Two Lectures on the Checks to","line":111,"x":392.40000000000026,"y":502.2600000000004,"width":"122.52","height":"8.80","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"7. A. N. Whitehead, Science and the Modern","line":116,"x":392.8800000000003,"y":466.7400100000005,"width":"121.80","height":"8.60","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"8. G. Hardin, Ed. Population, Evolution, and","line":118,"x":392.88000000000045,"y":452.5800000000005,"width":"125.04","height":"9.40","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"9. S. McVay, Sci. Amer. 216 (No. 8>, 13 (1966).","line":121,"x":392.8800000000004,"y":431.4000000000005,"width":"122.82","height":"9.60","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"10. J. Fletcher, Situation Ethics (Westminster,","line":122,"x":390.12000000000046,"y":424.4400000000005,"width":"130.02","height":"9.40","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"11. D. Lack, The Natural Regulation of Animal","line":124,"x":390.12000000000035,"y":410.0400000000005,"width":"130.50","height":"9.50","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"12. H. Girvetz, From Wealth to Welfare (Stan-","line":126,"x":390.2400000000004,"y":395.99999000000054,"width":"126.18","height":"9.20","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"13. G. Hardin, Perspec. Biol. Med. 6, 366 (1963).","line":128,"x":390.36000000000047,"y":381.84000000000054,"width":"131.40","height":"10.00","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"14. U. Thant, Int. Planned Parenthood News, No.","line":129,"x":390.2400000000005,"y":374.5800000000006,"width":"136.20","height":"9.60","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"15. K. Davis, Science 158, 730 (1967).","line":131,"x":390.2400000000005,"y":360.6000000000006,"width":"102.48","height":"9.20","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"16. S. Tax, Ed., Evolution after Darwin (Univ.","line":132,"x":390.2400000000005,"y":353.4600000000006,"width":"126.84","height":"10.00","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"469.","dir":"ltr","width":"12.12","height":"8.30","transform":["5.05","0.00","0.00","8.30","402.12","339.42"],"fontName":"Courier","x":402.1200000000006,"y":339.4200100000006,"line":134}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"17. G. Bateson, D. D. Jackson, J. Haley, J. Weak-","line":135,"x":390.7200000000006,"y":332.2800000000006,"width":"133.44","height":"9.10","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"18. P. Goodman, New York Rev. Books 10(8),","line":137,"x":390.6000000000005,"y":317.8800000000007,"width":"125.64","height":"10.20","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"19. A. Comfort, The Anxiety Makers (Nelson,","line":139,"x":390.9600000000005,"y":303.7200000000006,"width":"127.62","height":"9.90","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"20. C. Frankel, The Case for Modern Man (Har-","line":141,"x":390.7200000000006,"y":289.5600000000006,"width":"131.70","height":"10.00","fontName":["Courier"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","types":["NUMBERED_LIST"],"str":"21. J. D. Roslansky, Genetics and the Future of","line":143,"x":390.9600000000006,"y":275.34000000000066,"width":"127.44","height":"9.80","fontName":["Courier"],"dir":["ltr"]}