pdf-to-markdown/examples/The-Impact-of-Open-Access-Latin-American-Scholarship/detectHeaders.json
Johannes Zillmann 7f5f4d7071 Add DetectHeaders transformation
- This is mainly code from 2 years ago (was in the stash)
- The tests were green but failing now because of recent changes
- Plan is to first move all files to the root to then be able to debug the tests better
2024-03-26 10:23:15 -06:00

52 lines
4.1 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"pages": 16,
"items": 1242,
"groupedItems": 416,
"changes": 35,
"schema": [
{
"name": "line"
},
{
"name": "types"
},
{
"name": "x"
},
{
"name": "y"
},
{
"name": "width"
},
{
"name": "height"
},
{
"name": "str"
},
{
"name": "fontName"
},
{
"name": "dir"
}
],
"globals": {}
}
{"page":0,"change":"ContentChange","types":["H3"],"str":"Andrew W. Mellon Foundation ","dir":"ltr","width":"225.69","height":"15.96","transform":["15.96","0.00","0.00","15.96","78.02","245.69"],"fontName":"ABCDEE+Georgia,Italic","x":78.024,"y":245.69,"line":0}
{"page":0,"change":"ContentChange","types":["H3"],"str":"Grant 1711 - 05155","line":1,"x":78.024,"y":224.69,"width":"123.58","height":"15.96","fontName":["ABCDEE+Georgia,Italic"],"dir":["ltr"]}
{"page":0,"change":"ContentChange","types":["H3"],"str":"December 19 , 2019","line":2,"x":78.024,"y":203.57,"width":"127.25","height":"15.96","fontName":["ABCDEE+Georgia,Italic"],"dir":["ltr"]}
{"page":0,"change":"ContentChange","types":["H3"],"str":"John Kiplinger","dir":"ltr","width":"107.01","height":"15.96","transform":["15.96","0.00","0.00","15.96","80.66","138.14"],"fontName":"ABCDEE+Georgia,Italic","x":80.664,"y":138.14,"line":3}
{"page":0,"change":"ContentChange","types":["H3"],"str":"Valerie Yaw ","dir":"ltr","width":"91.40","height":"15.96","transform":["15.96","0.00","0.00","15.96","80.66","117.14"],"fontName":"ABCDEE+Georgia,Italic","x":80.664,"y":117.14,"line":4}
{"page":0,"change":"ContentChange","types":["H1"],"str":"The Impact of Open Access","dir":"ltr","width":"387.11","height":"36.00","transform":["36.00","0.00","0.00","36.00","75.02","461.11"],"fontName":"ABCDEE+Arial Narrow,Bold","x":75.024,"y":461.11,"line":5}
{"page":0,"change":"ContentChange","types":["H1"],"str":"Latin American Scholarship : ","line":6,"x":75.024,"y":413.59,"width":"416.70","height":"36.00","fontName":["ABCDEE+Arial Narrow,Bold"],"dir":["ltr"]}
{"page":0,"change":"ContentChange","types":["H2"],"str":"Digitizing the Backlist of El Colegio de ","line":7,"x":75.024,"y":373.63,"width":"424.66","height":"27.96","fontName":["ABCDEE+Arial Narrow,Bold"],"dir":["ltr"]}
{"page":0,"change":"ContentChange","types":["H2"],"str":"Méxicos Press","dir":"ltr","width":"165.77","height":"27.96","transform":["27.96","0.00","0.00","27.96","75.02","341.45"],"fontName":"ABCDEE+Arial Narrow,Bold","x":75.024,"y":341.45,"line":8}
{"page":0,"change":"ContentChange","types":["H2"],"str":"WHITE PAPER","dir":"ltr","width":"113.99","height":"20.04","transform":["20.04","0.00","0.00","20.04","74.90","534.79"],"fontName":"ABCDEE+Arial Narrow,Bold","x":74.904,"y":534.79,"line":9}
{"page":4,"change":"ContentChange","types":["H2"],"str":"Summary ","dir":"ltr","width":"95.16","height":"24.00","transform":["24.00","0.00","0.00","24.00","90.02","707.74"],"fontName":"ABCDEE+Arial Narrow,Bold","x":90.024,"y":707.74,"line":1}
{"page":4,"change":"ContentChange","types":["H2"],"str":"Introduction: History , Context , and ","line":26,"x":90.024,"y":254.81,"width":"324.60","height":"24.00","fontName":["ABCDEE+Arial Narrow,Bold"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","types":["H2"],"str":"Significance of the Collection ","dir":"ltr","width":"281.06","height":"24.00","transform":["24.00","0.00","0.00","24.00","90.02","227.21"],"fontName":"ABCDEE+Arial Narrow,Bold","x":90.024,"y":227.21,"line":27}
{"page":6,"change":"ContentChange","types":["H2"],"str":"Our Approach: Selection and Digitization ","dir":"ltr","width":"389.16","height":"24.00","transform":["24.00","0.00","0.00","24.00","90.02","707.74"],"fontName":"ABCDEE+Arial Narrow,Bold","x":90.024,"y":707.74,"line":1}
{"page":11,"change":"ContentChange","types":["H2"],"str":"Usage : W hat Weve Learned So Far ","line":1,"x":90.024,"y":676.06,"width":"335.81","height":"24.00","fontName":["ABCDEE+Arial Narrow,Bold","ABCDEE+Arial Narrow,Bold"],"dir":["ltr"]}
{"page":14,"change":"ContentChange","types":["H2"],"str":"Conclusion ","dir":"ltr","width":"112.54","height":"24.00","transform":["24.00","0.00","0.00","24.00","90.02","183.26"],"fontName":"ABCDEE+Arial Narrow,Bold","x":90.024,"y":183.26,"line":27}