mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 13:18:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Integrate ListItemMarkerProcessor into document assembly (#1825)

Browse Source 
* Integrate ListItemMarkerProcessor into document assembly

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update to final version

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update all test cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Upgrade deps

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-07-01 10:04:58 +02:00
committed by GitHub
parent bdfee4e2d0
commit 56a0e104f7
24 changed files with 739 additions and 1675 deletions
Download Patch File Download Diff File Expand all files Collapse all files

120
tests/data/groundtruth/docling_v1/2203.01017v2.json vendored
View File

@@ -321,7 +321,7 @@
"page": 1,
"span": [
0,
68
65
],
"__ref_s3_data": null
}
@@ -344,7 +344,7 @@
"page": 1,
"span": [
0,
38
35
],
"__ref_s3_data": null
}
@@ -543,7 +543,7 @@
"page": 2,
"span": [
0,
166
164
],
"__ref_s3_data": null
}
@@ -566,7 +566,7 @@
"page": 2,
"span": [
0,
181
179
],
"__ref_s3_data": null
}
@@ -589,7 +589,7 @@
"page": 2,
"span": [
0,
106
104
],
"__ref_s3_data": null
}
@@ -612,7 +612,7 @@
"page": 2,
"span": [
0,
131
129
],
"__ref_s3_data": null
}
@@ -2550,7 +2550,7 @@
"page": 8,
"span": [
0,
121
117
],
"__ref_s3_data": null
}
@@ -2596,7 +2596,7 @@
"page": 9,
"span": [
0,
165
161
],
"__ref_s3_data": null
}
@@ -2619,7 +2619,7 @@
"page": 9,
"span": [
0,
125
121
],
"__ref_s3_data": null
}
@@ -2642,7 +2642,7 @@
"page": 9,
"span": [
0,
216
212
],
"__ref_s3_data": null
}
@@ -2665,7 +2665,7 @@
"page": 9,
"span": [
0,
236
232
],
"__ref_s3_data": null
}
@@ -2688,7 +2688,7 @@
"page": 9,
"span": [
0,
194
190
],
"__ref_s3_data": null
}
@@ -2711,7 +2711,7 @@
"page": 9,
"span": [
0,
165
161
],
"__ref_s3_data": null
}
@@ -2734,7 +2734,7 @@
"page": 9,
"span": [
0,
273
269
],
"__ref_s3_data": null
}
@@ -2757,7 +2757,7 @@
"page": 9,
"span": [
0,
170
166
],
"__ref_s3_data": null
}
@@ -2780,7 +2780,7 @@
"page": 9,
"span": [
0,
226
221
],
"__ref_s3_data": null
}
@@ -2803,7 +2803,7 @@
"page": 9,
"span": [
0,
239
234
],
"__ref_s3_data": null
}
@@ -2826,7 +2826,7 @@
"page": 9,
"span": [
0,
240
235
],
"__ref_s3_data": null
}
@@ -2849,7 +2849,7 @@
"page": 9,
"span": [
0,
283
278
],
"__ref_s3_data": null
}
@@ -2872,7 +2872,7 @@
"page": 9,
"span": [
0,
142
137
],
"__ref_s3_data": null
}
@@ -2895,7 +2895,7 @@
"page": 9,
"span": [
0,
127
122
],
"__ref_s3_data": null
}
@@ -2918,7 +2918,7 @@
"page": 9,
"span": [
0,
287
282
],
"__ref_s3_data": null
}
@@ -2941,7 +2941,7 @@
"page": 9,
"span": [
0,
156
151
],
"__ref_s3_data": null
}
@@ -2964,7 +2964,7 @@
"page": 9,
"span": [
0,
407
402
],
"__ref_s3_data": null
}
@@ -2987,7 +2987,7 @@
"page": 9,
"span": [
0,
328
323
],
"__ref_s3_data": null
}
@@ -3010,7 +3010,7 @@
"page": 9,
"span": [
0,
229
224
],
"__ref_s3_data": null
}
@@ -3033,7 +3033,7 @@
"page": 9,
"span": [
0,
315
310
],
"__ref_s3_data": null
}
@@ -3056,7 +3056,7 @@
"page": 9,
"span": [
0,
592
587
],
"__ref_s3_data": null
}
@@ -3079,7 +3079,7 @@
"page": 9,
"span": [
0,
322
317
],
"__ref_s3_data": null
}
@@ -3102,7 +3102,7 @@
"page": 9,
"span": [
0,
224
219
],
"__ref_s3_data": null
}
@@ -3125,7 +3125,7 @@
"page": 9,
"span": [
0,
229
224
],
"__ref_s3_data": null
}
@@ -3171,7 +3171,7 @@
"page": 10,
"span": [
0,
302
297
],
"__ref_s3_data": null
}
@@ -3194,7 +3194,7 @@
"page": 10,
"span": [
0,
308
303
],
"__ref_s3_data": null
}
@@ -3217,7 +3217,7 @@
"page": 10,
"span": [
0,
183
178
],
"__ref_s3_data": null
}
@@ -3240,7 +3240,7 @@
"page": 10,
"span": [
0,
275
270
],
"__ref_s3_data": null
}
@@ -3263,7 +3263,7 @@
"page": 10,
"span": [
0,
251
246
],
"__ref_s3_data": null
}
@@ -3286,7 +3286,7 @@
"page": 10,
"span": [
0,
366
361
],
"__ref_s3_data": null
}
@@ -3309,7 +3309,7 @@
"page": 10,
"span": [
0,
221
216
],
"__ref_s3_data": null
}
@@ -3332,7 +3332,7 @@
"page": 10,
"span": [
0,
217
212
],
"__ref_s3_data": null
}
@@ -3355,7 +3355,7 @@
"page": 10,
"span": [
0,
190
185
],
"__ref_s3_data": null
}
@@ -3378,7 +3378,7 @@
"page": 10,
"span": [
0,
220
215
],
"__ref_s3_data": null
}
@@ -3401,7 +3401,7 @@
"page": 10,
"span": [
0,
280
275
],
"__ref_s3_data": null
}
@@ -3424,7 +3424,7 @@
"page": 10,
"span": [
0,
106
101
],
"__ref_s3_data": null
}
@@ -3470,7 +3470,7 @@
"page": 10,
"span": [
0,
221
216
],
"__ref_s3_data": null
}
@@ -3714,7 +3714,7 @@
"page": 11,
"span": [
0,
373
370
],
"__ref_s3_data": null
}
@@ -3737,7 +3737,7 @@
"page": 11,
"span": [
0,
573
570
],
"__ref_s3_data": null
}
@@ -3760,7 +3760,7 @@
"page": 11,
"span": [
0,
195
192
],
"__ref_s3_data": null
}
@@ -3783,7 +3783,7 @@
"page": 11,
"span": [
0,
218
215
],
"__ref_s3_data": null
}
@@ -3806,7 +3806,7 @@
"page": 11,
"span": [
0,
238
235
],
"__ref_s3_data": null
}
@@ -3903,7 +3903,7 @@
"page": 12,
"span": [
0,
61
59
],
"__ref_s3_data": null
}
@@ -3926,7 +3926,7 @@
"page": 12,
"span": [
0,
77
75
],
"__ref_s3_data": null
}
@@ -4018,7 +4018,7 @@
"page": 12,
"span": [
0,
173
170
],
"__ref_s3_data": null
}
@@ -4041,7 +4041,7 @@
"page": 12,
"span": [
0,
187
184
],
"__ref_s3_data": null
}
@@ -4064,7 +4064,7 @@
"page": 12,
"span": [
0,
97
94
],
"__ref_s3_data": null
}
@@ -4110,7 +4110,7 @@
"page": 12,
"span": [
0,
169
166
],
"__ref_s3_data": null
}
@@ -4179,7 +4179,7 @@
"page": 12,
"span": [
0,
110
107
],
"__ref_s3_data": null
}
@@ -4202,7 +4202,7 @@
"page": 12,
"span": [
0,
91
88
],
"__ref_s3_data": null
}
@@ -4225,7 +4225,7 @@
"page": 12,
"span": [
0,
471
468
],
"__ref_s3_data": null
}
@@ -4248,7 +4248,7 @@
"page": 12,
"span": [
0,
311
308
],
"__ref_s3_data": null
}
@@ -4271,7 +4271,7 @@
"page": 12,
"span": [
0,
503
500
],
"__ref_s3_data": null
}