pdf-to-markdown/examples/compressed.tracemonkey-pldi-09/removeRepetitiveItems.json
Johannes Zillmann 55ae236928 Improve header detection
- fix tests
- still run header detection based on heights even if TOC headlines have been identified
2024-03-28 11:39:34 -06:00

46 lines
722 B
JSON

{
"pages": 14,
"items": 2430,
"groupedItems": 1499,
"changes": 0,
"schema": [
{
"name": "line"
},
{
"name": "x"
},
{
"name": "y"
},
{
"name": "width"
},
{
"name": "height"
},
{
"name": "str"
},
{
"name": "fontName"
},
{
"name": "dir"
}
],
"globals": {
"maxHeight": 17.9328,
"mostUsedHeight": 8.9664,
"mostUsedDistance": 9.96,
"mostUsedFont": "KUYGUP+NimbusRomNo9L-Regu",
"minX": 53.99990000000005,
"maxX": 553.8755000000001,
"minY": 68.44329999999982,
"maxY": 713.7734000000003,
"pageMapping": {
"pageFactor": 1,
"detectedOnPage": false
}
}
}