extern/pdf-to-markdown
1
0
Fork 0
mirror of https://github.com/jzillmann/pdf-to-markdown.git synced 2024-12-12 17:40:58 +01:00
Code Issues Packages Projects Releases Wiki Activity
932a79a3e9
pdf-to-markdown/examples/Closed-Syllables/removeRepetitiveItems.json

100 lines
14 KiB
JSON
Raw Normal View History

Very basic removal of repetitive elements
2021-03-14 12:15:37 +01:00
{
"pages": 19,
Remove empty items
2021-03-16 05:36:41 +01:00
"items": 1503,
"groupedItems": 1234,
"changes": 133,
Very basic removal of repetitive elements
2021-03-14 12:15:37 +01:00
"schema": [
{
"name": "line"
},
{
"name": "x"
},
{
"name": "y"
},
{
"name": "str"
},
{
"name": "fontName"
},
{
"name": "dir"
},
{
"name": "width"
},
{
"name": "height"
}
Cover globals in tests
2021-03-28 10:58:24 +02:00
],
"globals": {
Find page mapping during statistics calculation
2021-03-28 23:45:26 +02:00
"maxHeight": 18,
"minX": 72.024,
"maxX": 534.58,
"minY": 63.144,
"maxY": 745.56,
"pageMapping": {
"pageFactor": 1,
"detectedOnPage": true
Fix previous commit and re-use page mapping
2021-03-29 07:24:20 +02:00
}
Cover globals in tests
2021-03-28 10:58:24 +02:00
}
Very basic removal of repetitive elements
2021-03-14 12:15:37 +01:00
}
Track evaluation score (optionally) Makes it easier to see how a value got classified
2021-04-01 18:16:42 +02:00
{"page":0,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 1","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":0,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":0,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":1,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 2","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":1,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":1,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":2,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 3","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":2,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":2,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":3,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 4","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":3,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":3,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":4,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 5","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":4,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":4,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":5,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 6","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":5,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":5,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":6,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 7","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":6,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":6,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":7,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 8","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":7,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":7,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":8,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 9","line":0,"x":420.79,"y":745.56,"width":"119.31","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":8,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":8,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":9,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 10","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":9,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":9,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":10,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 11","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":10,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":10,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":11,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 12","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":11,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":11,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":12,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 13","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":12,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":12,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":13,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 14","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":13,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":13,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":14,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 15","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":14,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":14,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":15,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 16","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":15,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":15,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":16,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 17","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":16,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":16,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":17,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 18","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":17,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":17,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
{"page":18,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"Closed syllable word lists 19","line":0,"x":415.27,"y":745.56,"width":"124.75","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":18,"change":"Removal","score":"1.05: (0.05 + 1.00)","str":"Phonics word lists by Susan Jones licensed under Creative Commons Attribution 4.0 International ","line":1,"x":106.22,"y":76.584,"width":"436.20","height":"11.04","fontName":["ABCDEE+Calibri"],"dir":["ltr"]}
{"page":18,"change":"Removal","score":"1.00: (0.00 + 1.00)","str":"License","dir":"ltr","width":"32.99","height":"11.04","transform":["11.04","0.00","0.00","11.04","507.22","63.14"],"fontName":"ABCDEE+Calibri","x":507.22,"y":63.144,"line":2}
Reference in New Issue Copy Permalink