extern/pdf-to-markdown
1
0
Fork 0
mirror of https://github.com/jzillmann/pdf-to-markdown.git synced 2024-12-04 13:43:49 +01:00
Code Issues Packages Projects Releases Wiki Activity
d5523fb1d4
pdf-to-markdown/examples/ExamplePdf/compactLines.json

102 lines
16 KiB
JSON
Raw Normal View History

Add Test infrastructure for example PDFs
2021-03-13 08:46:22 +01:00
{
"pages": 7,
"items": 300,
"groupedItems": 123,
"changes": 69,
"schema": [
{
"name": "line",
"annotation": "ADDED"
},
{
"name": "x"
},
{
"name": "y"
},
{
"name": "str"
},
{
"name": "fontName"
},
{
"name": "dir"
},
{
"name": "width"
},
{
"name": "height"
}
]
}
Stabilize font display in tests * If multiple PDF are tested after another their font ids change (e.g. `g_d0_f1` becomes `g_d1_f1`)
2021-03-13 19:38:47 +01:00
{"page":0,"change":"Addition","data":{"str":"Dies ist eine Test-PDF . 1","line":2,"x":240,"y":585,"width":115.75483370400003,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":0,"change":"Addition","data":{"str":"Für’s Testen des Markdown Parsers .","line":3,"x":208,"y":572,"width":178.53879999999998,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":0,"change":"Addition","data":{"str":" In Deutsch. 1","line":4,"x":57,"y":59,"width":62.777733704000006,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":0,"change":"Addition","data":{"str":"\u0000 1","line":5,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":1,"change":"Addition","data":{"str":"\u0000 2","line":0,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":"Das ist ein Paragraph. Ein einfacher Paragraph mit Schrift in Normalgröße . Damit wir sehen wie 2","line":1,"x":57,"y":740,"width":472.9941337039999,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":"ultrices magna. Sed egestas mi nec rutrum iaculis. Phasellus condimentum , urna sit amet sodales 3","line":14,"x":57,"y":545,"width":483.42653370399995,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":"Und jetzt einfach nochmal Text um die Fussnoten in zweistellige Bereiche vorranzutreiben! 4 5 6","line":20,"x":57,"y":428,"width":452.2859011120001,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":" Was immer auch ‘normal’ ist... 2","line":21,"x":57,"y":164,"width":155.471433704,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":" Nicht zu verwechseln mit ‘condimenta’. Meine Lateinkenntnisse sind zwar schon so alt das ich 3","line":22,"x":57,"y":141,"width":467.54253370399965,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":" Hier & Jetzt! 4","line":24,"x":57,"y":105,"width":67.04133370399998,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":" Nicht viel mehr als ein Satz. 5","line":25,"x":57,"y":82,"width":142.85773370400005,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":" Weil dann wird's komplizierter! 6","line":26,"x":57,"y":59,"width":155.149133704,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":2,"change":"Addition","data":{"str":"\u0000 3","line":27,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Etwas kursiv ist auch nicht schlecht. Fett ist auch interessant. Und was ist mit ","line":1,"x":57,"y":740,"width":380.25900000000007,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"FETTUNDKURSIV ?","line":2,"x":57,"y":727,"width":102.05800000000002,"height":11,"fontName":["JUJONH+Helvetica-BoldOblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Interessant wird's wenn mehrere Wörter hintereinanderweg formatiert sind. Und dann noch über ","line":3,"x":57,"y":701,"width":469.85729999999995,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Zeilenbrüche hinweg .","line":4,"x":57,"y":688,"width":104.57040000000005,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Fies könnte es werden mit abwechselnden Formaten . Und das ganze dann noch über mehrere ","line":5,"x":57,"y":662,"width":470.24780000000015,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Zeilen hinweg.","line":6,"x":57,"y":649,"width":70.8862,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Und weil es so schön ist, fangen wir jetzt in dieser Zeile mit einem Schriftschnitt, nämlich kursiv an. ","line":7,"x":57,"y":623,"width":483.5973999999999,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"es dann Mitte der 3ten Zeile ausklingen.","line":9,"x":57,"y":597,"width":196.28619999999998,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Und nun kursiv Und Fett Zusammen Ge Mixt . Ohne Leerzeichen...","line":10,"x":57,"y":571,"width":312.422,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Eine Zeile, die mit kursiv anfing und endet mit fett.","line":11,"x":57,"y":545,"width":245.17239999999998,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Beende die Zeile mit fett.","line":12,"x":57,"y":519,"width":123.50580000000005,"height":11,"fontName":["JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Kursiv ist dann die nachfolgende!","line":13,"x":57,"y":506,"width":162.0608,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Eine Liste mit unterschiedlich formatierten Wörtern - Etwas Kursiv - Etwas Fett - Etwas Unterstrichen 7","line":14,"x":56.69069,"y":441,"width":478.82633370400004,"height":13.2,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"- Etwas Durchgestrichen - Und noch ein Link: http://pdf2md.morethan.io","line":15,"x":56.69069,"y":415,"width":341.4268000000001,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Ne Zeile die kursiv endet,","line":16,"x":57,"y":389,"width":124.1394,"height":11,"fontName":["JBRMKS+Helvetica","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"und in ner (fast) komplett lasziven, eh, kursiven Zeile endet.","line":17,"x":57,"y":376,"width":290.43300000000005,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Und gemixt .","line":21,"x":57,"y":311,"width":61.7364,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"interessiert mich ein kursiver Text Block! ;) ","line":24,"x":57,"y":259,"width":208.25969999999992,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"Und ein kursiver Setzt der einen eingeschlossen Link, nämlich http://pdf2md.morethan.io , hat.","line":26,"x":57,"y":207,"width":455.5342000000001,"height":11,"fontName":["SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":" Fussnote in einer Liste 7","line":27,"x":57,"y":59,"width":117.80853370400004,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":3,"change":"Addition","data":{"str":"\u0000 4","line":28,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"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":644.2490999999997,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"Also los! - Eintrag 3","line":3,"x":56.69069,"y":675,"width":89.9976,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"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":596.7796999999997,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"es ja nicht. Also los! - Sub Eintrag 1.2 - Eintrag 2 - Sub Eintrag 2.1","line":6,"x":56.69069,"y":558,"width":305.48650000000004,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"• Eintrage 1","line":8,"x":56.69069,"y":517.7268,"width":53.994600000000005,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"• Eintrage 2","line":9,"x":56.69069,"y":504.7268,"width":53.994600000000005,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"Gemixt: - Eintrage 1","line":10,"x":56.69069,"y":467,"width":92.43520000000001,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"• Eintrage 2","line":11,"x":56.69069,"y":452.7268,"width":53.994600000000005,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"1. Eins","line":13,"x":56.69069,"y":414.7268,"width":30.5778,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"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":474.2154999999997,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"3. Drei","line":17,"x":56.69069,"y":362.7268,"width":29.3458,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"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":460.0463999999998,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"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":577.7892999999997,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"ja nicht. Also los! - Eintrag 3","line":22,"x":80.69069,"y":246,"width":130.3621,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"- Erste 1 - Erste 2","line":24,"x":56.69069,"y":181,"width":78.48280000000001,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"- Zwote 1 - Zwote 2","line":25,"x":56.69069,"y":142,"width":87.01440000000001,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":4,"change":"Addition","data":{"str":"\u0000 5","line":26,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"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":632.8068999999997,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"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":616.3387999999998,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"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":447.4371000000001,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"str":"1. Eintrag 1 - Eintrag 1.1 - Eintrag 1.2","line":6,"x":56.69069,"y":528,"width":168.39679999999998,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"str":"2. Eintrag 2","line":7,"x":56.69069,"y":514.7268,"width":53.20479999999999,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"str":"der Parser das sauber trennen kann: - Eintrag 1 - Eintrag 2","line":9,"x":56.69069,"y":450,"width":276.0164,"height":13.2,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":5,"change":"Addition","data":{"str":"\u0000 6","line":11,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"Quotes & Spezielle Einschübe 8","line":0,"x":165,"y":767,"width":264.7308000000001,"height":18,"fontName":["OMUGKQ+Helvetica-Bold"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"spiegelt dann ein leerer Schreibtisch wider? - Albert Einstein","line":4,"x":151,"y":688,"width":292.8937,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"Phantasie ist wichtiger als Wissen , denn Wissen ist begrenzt . - Albert Einstein 9 10","line":6,"x":101,"y":623,"width":392.95923444560003,"height":11,"fontName":["JBRMKS+Helvetica","OMUGKQ+Helvetica-Bold","SVUOCV+Helvetica-Oblique"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"Die größte Macht hat das richtige Wort zur richtigen Zeit. - Mark Twain","line":8,"x":127,"y":558,"width":341.3520000000001,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"überflüssig werden . - Ingrid Bergman   ","line":10,"x":207,"y":519,"width":186.48520000000005,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica","QACXPP+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"Das Schicksal wird schon seine Gründe haben. - Voltaire","line":11,"x":159,"y":493,"width":276.99210000000005,"height":11,"fontName":["SVUOCV+Helvetica-Oblique","JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":" Eine Überschrifts-Fussnote... so was gibts auch! 8","line":16,"x":57,"y":105,"width":244.35253370400002,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":" Wisse, dass ist eine Fussnote in einem Zitat! 9","line":17,"x":57,"y":82,"width":224.783533704,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":" Der Albert Einstein (Fussnote im Zitat, am Ende der Zeile) 10","line":18,"x":57,"y":59,"width":293.05870074160003,"height":11,"fontName":["JBRMKS+Helvetica"],"dir":["ltr"]}}
{"page":6,"change":"Addition","data":{"str":"\u0000 7","line":19,"x":294,"y":45,"width":6.672000000000001,"height":12,"fontName":["QACXPP+Helvetica","JBRMKS+Helvetica"],"dir":["ltr"]}}
Reference in New Issue Copy Permalink