extern/pdf-to-markdown
1
0
Fork 0
mirror of https://github.com/jzillmann/pdf-to-markdown.git synced 2025-08-13 07:27:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fine tune line detection

Browse Source 
* Before lines where assembled that really separate lines
This commit is contained in:
Johannes Zillmann
2021-07-18 13:07:06 -06:00
parent e261583c65
commit 46234417ad
55 changed files with 2542 additions and 1882 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
examples/ExamplePdf/compactLines.json
View File

@ -1,8 +1,8 @@
{
"pages": 7,
"items": 282,
"groupedItems": 122,
"changes": 68,
"groupedItems": 152,
"changes": 86,
"schema": [
{
"name": "line",
@ -69,38 +69,56 @@
{"page":3,"change":"Addition","str":"Eine Zeile, die mit kursiv anfing und endet mit fett.","line":11,"x":57,"y":545,"width":"245.17","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Beende die Zeile mit fett.","line":12,"x":57,"y":519,"width":"123.51","height":"11.00","fontName":["JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Kursiv ist dann die nachfolgende!","line":13,"x":57,"y":506,"width":"162.06","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Eine Liste mit unterschiedlich formatierten Wörtern - Etwas Kursiv - Etwas Fett - Etwas Unterstrichen 7","line":14,"x":56.69069,"y":441,"width":"478.83","height":"13.20","fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"- Etwas Durchgestrichen - Und noch ein Link: http://pdf2md.morethan.io","line":15,"x":56.69069,"y":415,"width":"341.43","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Ne Zeile die kursiv endet,","line":16,"x":57,"y":389,"width":"124.14","height":"11.00","fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"und in ner (fast) komplett lasziven, eh, kursiven Zeile endet.","line":17,"x":57,"y":376,"width":"290.43","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Und gemixt .","line":21,"x":57,"y":311,"width":"58.68","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Und ein kursiver Setzt der einen eingeschlossen Link, nämlich http://pdf2md.morethan.io , hat.","line":26,"x":57,"y":207,"width":"455.53","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Fussnote in einer Liste 7","line":27,"x":57,"y":59,"width":"114.75","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"\u0000 4","line":28,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"Nun eine Liste mit dash’s: - Eintrag 1 - Eintrag 2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. Na ","line":1,"x":56.69069,"y":714,"width":"644.25","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"Also los! - Eintrag 3","line":3,"x":56.69069,"y":675,"width":"90.00","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"Und Untergruppen: - Eintrag 1 - Sub Eintrag 1.1, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du ","line":4,"x":56.69069,"y":623,"width":"596.78","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"es ja nicht. Also los! - Sub Eintrag 1.2 - Eintrag 2 - Sub Eintrag 2.1","line":6,"x":56.69069,"y":558,"width":"305.49","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"• Eintrage 1","line":8,"x":56.69069,"y":517.7268,"width":"53.99","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"• Eintrage 2","line":9,"x":56.69069,"y":504.7268,"width":"53.99","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"Gemixt: - Eintrage 1","line":10,"x":56.69069,"y":467,"width":"92.44","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"• Eintrage 2","line":11,"x":56.69069,"y":452.7268,"width":"53.99","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"1. Eins","line":13,"x":56.69069,"y":414.7268,"width":"30.58","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"2. Zwei, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. Na los. ","line":14,"x":56.69069,"y":401.7268,"width":"474.22","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"3. Drei","line":17,"x":56.69069,"y":362.7268,"width":"29.35","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"4. Vier. Und auch hier wieder ein etwas längerer Text, so dass der Eintrag über mehrere Zeilen ","line":18,"x":56.69069,"y":349.7268,"width":"460.05","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"Zentrierte Liste: - Eintrag 1 - Eintrag 2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. ","line":20,"x":57,"y":285,"width":"577.79","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"ja nicht. Also los! - Eintrag 3","line":22,"x":80.69069,"y":246,"width":"130.36","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Erste 1 - Erste 2","line":24,"x":56.69069,"y":181,"width":"78.48","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Zwote 1 - Zwote 2","line":25,"x":56.69069,"y":142,"width":"87.01","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"\u0000 5","line":26,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"Liste mit drei Levels: - Erster Level 1 - Zwoter Level 1.1, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du ","line":0,"x":56.69069,"y":723,"width":"632.81","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"es ja nicht. Also los! - 3ter Level 1.1.1 - 3ter Level 1.1.2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche ","line":2,"x":80.69069,"y":671,"width":"616.34","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"kann es ja nicht. Also los! - Zwoter Level 1.2 - Zwoter Level 1.3 - 3ter Level 1.3.1 - Erster Level 2","line":4,"x":56.69069,"y":593,"width":"447.44","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"1. Eintrag 1 - Eintrag 1.1 - Eintrag 1.2","line":6,"x":56.69069,"y":528,"width":"168.40","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"2. Eintrag 2","line":7,"x":56.69069,"y":514.7268,"width":"53.20","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"der Parser das sauber trennen kann: - Eintrag 1 - Eintrag 2","line":9,"x":56.69069,"y":450,"width":"276.02","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"\u0000 6","line":11,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"- Etwas Kursiv","line":15,"x":56.69069,"y":467,"width":"67.97","height":"13.20","fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"- Etwas Fett","line":16,"x":56.69069,"y":454,"width":"57.57","height":"13.20","fontName":["JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"- Etwas Unterstrichen 7","line":17,"x":56.69069,"y":441,"width":"106.90","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"- Etwas Durchgestrichen","line":18,"x":56.69069,"y":428,"width":"117.50","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"- Und noch ein Link: http://pdf2md.morethan.io","line":19,"x":56.69069,"y":415,"width":"223.92","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Ne Zeile die kursiv endet,","line":20,"x":57,"y":389,"width":"124.14","height":"11.00","fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"und in ner (fast) komplett lasziven, eh, kursiven Zeile endet.","line":21,"x":57,"y":376,"width":"290.43","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Und gemixt .","line":25,"x":57,"y":311,"width":"58.68","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Und ein kursiver Setzt der einen eingeschlossen Link, nämlich http://pdf2md.morethan.io , hat.","line":30,"x":57,"y":207,"width":"455.53","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"Fussnote in einer Liste 7","line":31,"x":57,"y":59,"width":"114.75","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Addition","str":"\u0000 4","line":32,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 1","line":2,"x":56.69069,"y":727,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. Na ","line":3,"x":56.69069,"y":714,"width":"470.06","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 3","line":6,"x":56.69069,"y":675,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 1","line":8,"x":56.69069,"y":636,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Sub Eintrag 1.1, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du ","line":9,"x":68.69069,"y":623,"width":"454.79","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Sub Eintrag 1.2","line":12,"x":68.69069,"y":584,"width":"80.23","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 2","line":13,"x":56.69069,"y":571,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Sub Eintrag 2.1","line":14,"x":68.69069,"y":558,"width":"80.23","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"• Eintrage 1","line":16,"x":56.69069,"y":517.7268,"width":"53.99","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"• Eintrage 2","line":17,"x":56.69069,"y":504.7268,"width":"53.99","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrage 1","line":19,"x":56.69069,"y":467,"width":"54.54","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"• Eintrage 2","line":20,"x":56.69069,"y":452.7268,"width":"53.99","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"1. Eins","line":22,"x":56.69069,"y":414.7268,"width":"30.58","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"2. Zwei, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. Na los. ","line":23,"x":56.69069,"y":401.7268,"width":"474.22","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"3. Drei","line":26,"x":56.69069,"y":362.7268,"width":"29.35","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"4. Vier. Und auch hier wieder ein etwas längerer Text, so dass der Eintrag über mehrere Zeilen ","line":27,"x":56.69069,"y":349.7268,"width":"460.05","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 1","line":30,"x":80.69069,"y":298,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. ","line":31,"x":80.69069,"y":285,"width":"452.94","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Eintrag 3","line":34,"x":80.69069,"y":246,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Erste 1","line":36,"x":56.69069,"y":194,"width":"39.24","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Erste 2","line":37,"x":56.69069,"y":181,"width":"39.24","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Zwote 1","line":38,"x":56.69069,"y":155,"width":"43.51","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"- Zwote 2","line":39,"x":56.69069,"y":142,"width":"43.51","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Addition","str":"\u0000 5","line":40,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Erster Level 1","line":1,"x":56.69069,"y":736,"width":"72.26","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Zwoter Level 1.1, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du ","line":2,"x":68.69069,"y":723,"width":"460.28","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- 3ter Level 1.1.1","line":5,"x":80.69069,"y":684,"width":"80.23","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- 3ter Level 1.1.2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche ","line":6,"x":80.69069,"y":671,"width":"439.50","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Zwoter Level 1.2","line":9,"x":68.69069,"y":632,"width":"85.71","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Zwoter Level 1.3","line":10,"x":68.69069,"y":619,"width":"85.71","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- 3ter Level 1.3.1","line":11,"x":80.69069,"y":606,"width":"80.23","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Erster Level 2","line":12,"x":56.69069,"y":593,"width":"72.26","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"1. Eintrag 1","line":14,"x":56.69069,"y":553.7268,"width":"53.20","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Eintrag 1.1","line":15,"x":68.69069,"y":541,"width":"57.60","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Eintrag 1.2","line":16,"x":68.69069,"y":528,"width":"57.60","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"2. Eintrag 2","line":17,"x":56.69069,"y":514.7268,"width":"53.20","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Eintrag 1","line":20,"x":56.69069,"y":463,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"- Eintrag 2","line":21,"x":56.69069,"y":450,"width":"48.42","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Addition","str":"\u0000 6","line":23,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":6,"change":"Addition","str":"Quotes & Spezielle Einschübe 8","line":0,"x":165,"y":767,"width":"264.73","height":"18.00","fontName":["OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}
{"page":6,"change":"Addition","str":"spiegelt dann ein leerer Schreibtisch wider? - Albert Einstein","line":4,"x":151,"y":688,"width":"292.89","height":"11.00","fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":6,"change":"Addition","str":"Phantasie ist wichtiger als Wissen , denn Wissen ist begrenzt . - Albert Einstein 9 10","line":6,"x":101,"y":623,"width":"392.96","height":"11.00","fontName":["JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}

2
examples/ExamplePdf/detectTOC.json
View File

@ -1,7 +1,7 @@
{
"pages": 6,
"items": 268,
"groupedItems": 115,
"groupedItems": 145,
"changes": 0,
"schema": [
{

8
examples/ExamplePdf/removeRepetitiveItems.json
View File

@ -1,7 +1,7 @@
{
"pages": 7,
"items": 282,
"groupedItems": 122,
"groupedItems": 152,
"changes": 21,
"schema": [
{
@ -45,7 +45,7 @@
{"page":0,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 1","line":5,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":1,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 2","line":0,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":2,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 3","line":27,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 4","line":28,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 5","line":26,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 6","line":11,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 4","line":32,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 5","line":40,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 6","line":23,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":6,"change":"Removal","score":"2.00: (1.00 + 1.00)","str":"\u0000 7","line":18,"x":294,"y":45,"width":"6.67","height":"12.00","fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}

22
examples/ExamplePdf/sortbyX.json
View File

@ -1,8 +1,8 @@
{
"pages": 7,
"items": 282,
"groupedItems": 122,
"changes": 131,
"groupedItems": 152,
"changes": 54,
"schema": [
{
"name": "line"
@ -52,23 +52,7 @@
{"page":2,"change":"ContentChange","str":"4 Hier & Jetzt!","line":24,"x":57,"y":105,"width":"63.98","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":2,"change":"ContentChange","str":"5 Nicht viel mehr als ein Satz.","line":25,"x":57,"y":82,"width":"139.80","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":2,"change":"ContentChange","str":"6 Weil dann wird's komplizierter!","line":26,"x":57,"y":59,"width":"152.09","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"ContentChange","str":"- - - Eine Liste mit unterschiedlich formatierten Wörtern Etwas Etwas Etwas Kursiv Fett Unterstrichen 7","line":14,"x":56.69069,"y":441,"width":"478.83","height":"13.20","fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}
{"page":3,"change":"ContentChange","str":"- - Etwas Und noch ein Link: http://pdf2md.morethan.io Durchgestrichen","line":15,"x":56.69069,"y":415,"width":"341.43","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"ContentChange","str":"7 Fussnote in einer Liste","line":27,"x":57,"y":59,"width":"114.75","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- - Nun eine Liste mit dash’s: Eintrag 1 Eintrag 2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. Na ","line":1,"x":56.69069,"y":714,"width":"644.25","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- Also los! Eintrag 3","line":3,"x":56.69069,"y":675,"width":"90.00","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- Und Untergruppen: - Eintrag 1 Sub Eintrag 1.1, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du ","line":4,"x":56.69069,"y":623,"width":"596.78","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- - - Eintrag 2 es ja nicht. Also los! Sub Eintrag 1.2 Sub Eintrag 2.1","line":6,"x":56.69069,"y":558,"width":"305.49","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- Gemixt: Eintrage 1","line":10,"x":56.69069,"y":467,"width":"92.44","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"Zentrierte Liste: - - Eintrag 1 Eintrag 2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du Zeile. ","line":20,"x":57,"y":285,"width":"577.79","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- ja nicht. Also los! Eintrag 3","line":22,"x":80.69069,"y":246,"width":"130.36","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- - Erste 1 Erste 2","line":24,"x":56.69069,"y":181,"width":"78.48","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":4,"change":"ContentChange","str":"- - Zwote 1 Zwote 2","line":25,"x":56.69069,"y":142,"width":"87.01","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","str":"- Liste mit drei Levels: - Erster Level 1 Zwoter Level 1.1, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche du ","line":0,"x":56.69069,"y":723,"width":"632.81","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","str":"- - es ja nicht. Also los! 3ter Level 1.1.1 3ter Level 1.1.2, aber mit so langem Text, das er umbricht. Wirklich, wirklich lang. Breche ","line":2,"x":80.69069,"y":671,"width":"616.34","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","str":"- - - Erster Level 2 - Zwoter Level 1.2 Zwoter Level 1.3 kann es ja nicht. Also los! 3ter Level 1.3.1","line":4,"x":56.69069,"y":593,"width":"447.44","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","str":"1. - - Eintrag 1 Eintrag 1.1 Eintrag 1.2","line":6,"x":56.69069,"y":528,"width":"168.40","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":5,"change":"ContentChange","str":"- - der Parser das sauber trennen kann: Eintrag 1 Eintrag 2","line":9,"x":56.69069,"y":450,"width":"276.02","height":"13.20","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":3,"change":"ContentChange","str":"7 Fussnote in einer Liste","line":31,"x":57,"y":59,"width":"114.75","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":6,"change":"ContentChange","str":"Phantasie ist wichtiger als Wissen , denn Wissen 9 ist begrenzt . - Albert Einstein 10","line":6,"x":101,"y":623,"width":"392.96","height":"11.00","fontName":["JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}
{"page":6,"change":"ContentChange","str":"8 Eine Überschrifts-Fussnote... so was gibts auch!","line":15,"x":57,"y":105,"width":"241.29","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}
{"page":6,"change":"ContentChange","str":"9 Wisse, dass ist eine Fussnote in einem Zitat!","line":16,"x":57,"y":82,"width":"221.73","height":"11.00","fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}