Skip to content

GitLab

Unverified Commit b912797a authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #913 from DTwz/dev 

Modify the test directory
parents 1e37e199 a09d9e8c
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 450438 deletions
tests/assets/more_para_test_samples/scihub_files.txt deleted 100644 → 0
View file @ 1e37e199
scihub/scihub_00500000/libgen.scimag00527000-00527999.zip_10.1002/app.25178
scihub/scihub_07400000/libgen.scimag07481000-07481999.zip_10.1007/s003960050343
scihub/scihub_11400000/libgen.scimag11451000-11451999.zip_10.1017/s0009838811000231
scihub/scihub_24400000/libgen.scimag24401000-24401999.zip_10.1016/j.toxicon.2014.02.018
scihub/scihub_27400000/libgen.scimag27441000-27441999.zip_10.2307/30122482
scihub/scihub_28400000/libgen.scimag28413000-28413999.zip_10.2307/1316224
scihub/scihub_31200000/libgen.scimag31207000-31207999.zip_10.1080/03639040600920622
scihub/scihub_31800000/libgen.scimag31824000-31824999.zip_10.1109/med.2012.6265668
scihub/scihub_32500000/libgen.scimag32539000-32539999.zip_10.1080/09540121003721000
scihub/scihub_42500000/libgen.scimag42522000-42522999.zip_10.1016/S1365-6937(15)30162-3
scihub/scihub_45900000/libgen.scimag45914000-45914999.zip_10.1055/s-0030-1256333
scihub/scihub_50900000/libgen.scimag50902000-50902999.zip_10.1007/s12274-016-1035-8
scihub/scihub_63900000/libgen.scimag63921000-63921999.zip_10.1063/1.4938050
scihub/scihub_65800000/libgen.scimag65832000-65832999.zip_10.1016/s0166-4115(08)62165-2
scihub/scihub_67300000/libgen.scimag67369000-67369999.zip_10.1096/fj.201700997R
scihub/scihub_67900000/libgen.scimag67967000-67967999.zip_10.1038/s41598-018-21867-z
scihub/scihub_77400000/libgen.scimag77447000-77447999.zip_10.1016/j.jid.2019.06.094
tests/assets/paper/images_tables_equations.json deleted 100644 → 0
View file @ 1e37e199
{
"pageID_imageBboxs": [
[
[
37.5,
651.3200073242188,
557.5,
790.8300170898438
]
],
[
[
69,
771,
119,
789
]
],
[],
[
[
152.16000366210938,
188.3996124267578,
458.8800048828125,
330.4796142578125
],
[
200.57258064516128,
499.0322580645161,
339.67863247863244,
627.5418803418803
]
],
[
[
88.29032258064515,
246.63709677419354,
288.822792022792,
608.8307692307692
]
],
[
[
168.42338709677418,
118.04032258064515,
439.9509971509971,
246.60284900284898
],
[
155.94758064516128,
341.1653225806451,
452.4250712250712,
434.67350427350425
]
],
[],
[]
],
"pageID_tableBboxs": [
[],
[],
[],
[],
[],
[
[
71.9758064516129,
534.0604838709677,
520.5527065527065,
717.7390313390313
]
],
[
[
71.01612903225806,
296.5403225806451,
525.3504273504273,
392.45356125356125
],
[
79.17338709677419,
503.8306451612903,
517.674074074074,
736.4501424501424
]
],
[]
],
"pageID_equationBboxs": [
[],
[],
[
[
247.59677419354836,
511.9879032258064,
524.8706552706552,
525.8301994301994
],
[
222.16532258064515,
588.7620967741935,
524.3908831908832,
608.8307692307692
]
],
[],
[],
[],
[],
[]
]
}
\ No newline at end of file
tests/assets/paper/paper_recogPara.json deleted 100644 → 0
View file @ 1e37e199
This diff is collapsed.
tests/assets/paper/pdf_dic.json deleted 100644 → 0
View file @ 1e37e199
This diff is collapsed.
tests/assets/paras_test.json deleted 100644 → 0
View file @ 1e37e199
{
"page_0":{
"para_blocks": [
{
"block_id": 0,
"bbox": [39.0, 34.719993591308594, 347.1359558105469, 51.2079963684082],
"text": "IOP Conference Series: Earth and Environmental Science",
"dir": [1.0, 0.0],
"X0": 39.0,
"X1": 347.1359558105469,
"avg_char_width": 6.4194990793863935,
"avg_char_height": 16.48800277709961,
"block_font_type": "Helvetica",
"block_font_size": 12.0,
"is_segmented": 1,
"paras": [
{
"para_id": 0,
"bbox": [39.0, 34.719993591308594, 347.1359558105469, 51.2079963684082],
"text": "IOP Conference Series: Earth and Environmental Science",
"is_matched": 1,
"is_title": 0,
"font_type": "Helvetica",
"font_size": 12.0,
"font_color": 0,
"neighbor_paras": [null, null]
}
],
"bboxes_para": [[39.0, 34.719993591308594, 347.1359558105469, 51.2079963684082]]
},
{
"block_id": 1,
"bbox": [39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625],
"text": "PAPER • OPEN ACCESS",
"dir": [1.0, 0.0],
"X0": 39.0,
"X1": 143.67001342773438,
"avg_char_width": 6.541875839233398,
"avg_char_height": 12.392997741699219,
"block_font_type": "Helvetica-Bold",
"block_font_size": 9.0,
"is_segmented": 1,
"paras": [
{
"para_id": 0,
"bbox": [39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625],
"text": "PAPER • OPEN ACCESS",
"is_matched": 1,
"is_title": 0,
"font_type": "Helvetica-Bold",
"font_size": 9.0,
"font_color": 0,
"neighbor_paras": [null, null]
},
{
"para_id": 1,
"bbox": [39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625],
"text": "PAPER • OPEN ACCESS",
"is_matched": 1,
"is_title": 0,
"font_type": "Helvetica-Bold",
"font_size": 9.0,
"font_color": 0,
"neighbor_paras": [null, null]
}
],
"bboxes_para": [[39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625]]
}
],
"line_blocks":[
{
"number": 0,
"type": 0,
"bbox": [
428.93170166015625,
744.921142578125,
541.5675048828125,
757.8131713867188
],
"lines": [
{
"spans": [
{
"size": 11.0,
"flags": 20,
"font": "UniversNextPro-BoldCond",
"color": 0,
"ascender": 0.9490000009536743,
"descender": -0.22300000488758087,
"text": "3",
"origin": [
536.37548828125,
755.3601684570312
],
"bbox": [
536.37548828125,
744.921142578125,
541.5675048828125,
757.8131713867188
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
536.37548828125,
744.921142578125,
541.5675048828125,
757.8131713867188
]
},
{
"spans": [
{
"size": 8.0,
"flags": 20,
"font": "UniversNextPro-BoldCond",
"color": 0,
"ascender": 0.9490000009536743,
"descender": -0.22300000488758087,
"text": "Spektrum ",
"origin": [
428.93170166015625,
755.3601684570312
],
"bbox": [
428.93170166015625,
747.7681884765625,
458.7516174316406,
757.1441650390625
]
},
{
"size": 8.0,
"flags": 4,
"font": "UniversNextPro-Cond",
"color": 0,
"ascender": 0.9359999895095825,
"descender": -0.21400000154972076,
"text": "der Wissenschaft ",
"origin": [
458.431884765625,
755.3601684570312
],
"bbox": [
458.431884765625,
747.8721923828125,
508.0399169921875,
757.0721435546875
]
},
{
"size": 8.0,
"flags": 4,
"font": "UniversNextPro-Regular",
"color": 0,
"ascender": 0.9290000200271606,
"descender": -0.22200000286102295,
"text": "7.21",
"origin": [
510.2349853515625,
755.3601684570312
],
"bbox": [
510.2349853515625,
747.9281616210938,
524.5621948242188,
757.1361694335938
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
428.93170166015625,
747.7681884765625,
524.5621948242188,
757.1441650390625
]
}
]
}
],
"images":[
{
"image_bbox":[0,0,1,1],
"image_path":"path/to/image.jpg"
},
{
"image_bbox":[1,2,3,4],
"image_path":"path/to/image.jpg"
}
],
"tables":[
{
"table_bbox":[0,0,1,1],
"image_path":"path/to/image.jpg"
},
{
"table_bbox":[1,2,3,4],
"image_path":"path/to/image.jpg"
}
],
"interline_equations":[
{
"equation_bbox":[0,0,1,1],
"image_path":"path/to/equation.jpg"
},
{
"equation_bbox":[1,2,3,4],
"image_path":"path/to/equation.jpg"
}
],
"inline_equations":[
{
"equation_bbox":[0,0,1,1],
"image_path":"path/to/equation.jpg"
},
{
"equation_bbox":[1,2,3,4],
"image_path":"path/to/equation.jpg"
}
],
"layout_bboxes":[
{
"layout_bbox": [0,0, 1,1],
"layout_label":"V|H|B"
},
{
"layout_bbox": [1,2,3,4],
"layout_label":"V|H|B"
}
],
"pymu_raw_blocks":[],
"global_statistic":{
},
"droped_text_block":[
],
"droped_image_block":[
],
"droped_table_block":[
],
"image_backup":[
],
"table_backup":[
]
},
"page_1":{
}
}
\ No newline at end of file
tests/assets/pdf_text_example/vertical_blocks.json deleted 100644 → 0
View file @ 1e37e199
[
{
"number": 0,
"type": 0,
"bbox": [
133.7009735107422,
71.23444366455078,
241.90069580078125,
105.01055908203125
],
"lines": [
{
"spans": [
{
"size": 25.81100082397461,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "调虎离山",
"origin": [
133.7009735107422,
98.15451049804688
],
"bbox": [
133.7009735107422,
71.23444366455078,
241.90069580078125,
105.01055908203125
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
133.7009735107422,
71.23444366455078,
241.90069580078125,
105.01055908203125
]
}
]
},
{
"number": 1,
"type": 0,
"bbox": [
45.990631103515625,
298.78173828125,
93.81614685058594,
314.27288818359375
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "【译文】",
"origin": [
45.990631103515625,
311.12841796875
],
"bbox": [
45.990631103515625,
298.78173828125,
93.81614685058594,
314.27288818359375
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
45.990631103515625,
298.78173828125,
93.81614685058594,
314.27288818359375
]
}
]
},
{
"number": 2,
"type": 0,
"bbox": [
76.05915069580078,
323.13250732421875,
324.24285888671875,
338.6236572265625
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "等待客观条件对敌方不利时再去围困它，用人为",
"origin": [
76.05915069580078,
335.47918701171875
],
"bbox": [
76.05915069580078,
323.13250732421875,
324.24285888671875,
338.6236572265625
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
76.05915069580078,
323.13250732421875,
324.24285888671875,
338.6236572265625
]
}
]
},
{
"number": 3,
"type": 0,
"bbox": [
51.968841552734375,
347.19915771484375,
324.2073669433594,
362.6903076171875
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "的因素去诱惑调动它。向前进攻有危险时，就想办法",
"origin": [
51.968841552734375,
359.54583740234375
],
"bbox": [
51.968841552734375,
347.19915771484375,
324.2073669433594,
362.6903076171875
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
51.968841552734375,
347.19915771484375,
324.2073669433594,
362.6903076171875
]
}
]
},
{
"number": 4,
"type": 0,
"bbox": [
51.933349609375,
371.36053466796875,
159.9906005859375,
386.8516540527344
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "让敌人返过来攻我。",
"origin": [
51.933349609375,
383.7071838378906
],
"bbox": [
51.933349609375,
371.36053466796875,
159.9906005859375,
386.8516540527344
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
51.933349609375,
371.36053466796875,
159.9906005859375,
386.8516540527344
]
}
]
},
{
"number": 5,
"type": 0,
"bbox": [
45.884117126464844,
402.60101318359375,
93.70964050292969,
418.0921325683594
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "【溯源】",
"origin": [
45.884117126464844,
414.9476623535156
],
"bbox": [
45.884117126464844,
402.60101318359375,
93.70964050292969,
418.0921325683594
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
45.884117126464844,
402.60101318359375,
93.70964050292969,
418.0921325683594
]
}
]
},
{
"number": 6,
"type": 0,
"bbox": [
75.95264434814453,
426.9517822265625,
324.14825439453125,
442.4429016113281
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "调虎离山，此计用在军事上，是一种调动敌人的",
"origin": [
75.95264434814453,
439.2984313964844
],
"bbox": [
75.95264434814453,
426.9517822265625,
324.14825439453125,
442.4429016113281
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
75.95264434814453,
426.9517822265625,
324.14825439453125,
442.4429016113281
]
}
]
},
{
"number": 7,
"type": 0,
"bbox": [
169.9068603515625,
447.10321044921875,
205.61537170410156,
459.161376953125
],
"lines": [
{
"spans": [
{
"size": 8.829999923706055,
"flags": 4,
"font": "DY2+ZJSBrL-2",
"color": 0,
"ascender": 0.800000011920929,
"descender": -0.20000000298023224,
"text": "!",
"origin": [
185.62425231933594,
456.81591796875
],
"bbox": [
185.62425231933594,
449.7519226074219,
190.03924560546875,
458.5819091796875
]
},
{
"size": 8.829999923706055,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": " —",
"origin": [
190.03924560546875,
456.81591796875
],
"bbox": [
190.03924560546875,
447.10321044921875,
205.61537170410156,
459.161376953125
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
185.62425231933594,
447.10321044921875,
205.61537170410156,
459.161376953125
]
},
{
"spans": [
{
"size": 8.829999923706055,
"flags": 0,
"font": "ËÎÌå",
"color": 0,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "—",
"origin": [
169.9068603515625,
456.3126220703125
],
"bbox": [
169.9068603515625,
447.10321044921875,
178.7368621826172,
458.6580810546875
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
169.9068603515625,
447.10321044921875,
178.7368621826172,
458.6580810546875
]
}
]
},
{
"number": 8,
"type": 0,
"bbox": [
106.35260009765625,
11.284072875976562,
238.4646453857422,
26.775205612182617
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 16777215,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "图说案例本三十六计全书",
"origin": [
106.35260009765625,
23.6307373046875
],
"bbox": [
106.35260009765625,
11.284072875976562,
238.4646453857422,
26.775205612182617
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
106.35260009765625,
11.284072875976562,
238.4646453857422,
26.775205612182617
]
}
]
},
{
"number": 9,
"type": 0,
"bbox": [
338.5431213378906,
231.63661193847656,
350.3811340332031,
283.2099609375
],
"lines": [
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 16777215,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "第",
"origin": [
338.5431213378906,
243.9832763671875
],
"bbox": [
338.5431213378906,
231.63661193847656,
350.3811340332031,
247.12774658203125
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
338.5431213378906,
231.63661193847656,
350.3811340332031,
247.12774658203125
]
},
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 16777215,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "十",
"origin": [
338.5431213378906,
256.01068115234375
],
"bbox": [
338.5431213378906,
243.6640167236328,
350.3811340332031,
259.1551513671875
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
338.5431213378906,
243.6640167236328,
350.3811340332031,
259.1551513671875
]
},
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 16777215,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "五",
"origin": [
338.5431213378906,
268.0380859375
],
"bbox": [
338.5431213378906,
255.69142150878906,
350.3811340332031,
271.18255615234375
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
338.5431213378906,
255.69142150878906,
350.3811340332031,
271.18255615234375
]
},
{
"spans": [
{
"size": 11.838000297546387,
"flags": 0,
"font": "ËÎÌå",
"color": 16777215,
"ascender": 1.04296875,
"descender": -0.265625,
"text": "计",
"origin": [
338.5431213378906,
280.06549072265625
],
"bbox": [
338.5431213378906,
267.71881103515625,
350.3811340332031,
283.2099609375
]
}
],
"wmode": 0,
"dir": [
1.0,
0.0
],
"bbox": [
338.5431213378906,
267.71881103515625,
350.3811340332031,
283.2099609375
]
}
]
}
]
\ No newline at end of file
tests/assets/pdf_text_example/vertical_en_blocks.json deleted 100644 → 0
View file @ 1e37e199
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment