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

68
tests/data/groundtruth/docling_v1/2206.01062.json vendored
View File

@@ -649,7 +649,7 @@
"page": 2,
"span": [
0,
149
145
],
"__ref_s3_data": null
}
@@ -672,7 +672,7 @@
"page": 2,
"span": [
0,
109
105
],
"__ref_s3_data": null
}
@@ -695,7 +695,7 @@
"page": 2,
"span": [
0,
180
176
],
"__ref_s3_data": null
}
@@ -718,7 +718,7 @@
"page": 2,
"span": [
0,
115
111
],
"__ref_s3_data": null
}
@@ -787,7 +787,7 @@
"page": 2,
"span": [
0,
280
276
],
"__ref_s3_data": null
}
@@ -1506,7 +1506,7 @@
"page": 5,
"span": [
0,
202
198
],
"__ref_s3_data": null
}
@@ -1529,7 +1529,7 @@
"page": 5,
"span": [
0,
208
204
],
"__ref_s3_data": null
}
@@ -1552,7 +1552,7 @@
"page": 5,
"span": [
0,
82
78
],
"__ref_s3_data": null
}
@@ -1575,7 +1575,7 @@
"page": 5,
"span": [
0,
70
66
],
"__ref_s3_data": null
}
@@ -1598,7 +1598,7 @@
"page": 5,
"span": [
0,
53
49
],
"__ref_s3_data": null
}
@@ -1621,7 +1621,7 @@
"page": 5,
"span": [
0,
160
156
],
"__ref_s3_data": null
}
@@ -2502,7 +2502,7 @@
"page": 8,
"span": [
0,
191
187
],
"__ref_s3_data": null
}
@@ -2525,7 +2525,7 @@
"page": 8,
"span": [
0,
279
275
],
"__ref_s3_data": null
}
@@ -2548,7 +2548,7 @@
"page": 8,
"span": [
0,
213
209
],
"__ref_s3_data": null
}
@@ -2571,7 +2571,7 @@
"page": 8,
"span": [
0,
251
247
],
"__ref_s3_data": null
}
@@ -2594,7 +2594,7 @@
"page": 8,
"span": [
0,
261
257
],
"__ref_s3_data": null
}
@@ -2617,7 +2617,7 @@
"page": 8,
"span": [
0,
235
231
],
"__ref_s3_data": null
}
@@ -2640,7 +2640,7 @@
"page": 8,
"span": [
0,
316
312
],
"__ref_s3_data": null
}
@@ -2663,7 +2663,7 @@
"page": 8,
"span": [
0,
172
168
],
"__ref_s3_data": null
}
@@ -2686,7 +2686,7 @@
"page": 8,
"span": [
0,
271
267
],
"__ref_s3_data": null
}
@@ -2709,7 +2709,7 @@
"page": 8,
"span": [
0,
149
144
],
"__ref_s3_data": null
}
@@ -2732,7 +2732,7 @@
"page": 8,
"span": [
0,
227
222
],
"__ref_s3_data": null
}
@@ -2755,7 +2755,7 @@
"page": 8,
"span": [
0,
192
187
],
"__ref_s3_data": null
}
@@ -2778,7 +2778,7 @@
"page": 8,
"span": [
0,
305
300
],
"__ref_s3_data": null
}
@@ -2875,7 +2875,7 @@
"page": 9,
"span": [
0,
153
148
],
"__ref_s3_data": null
}
@@ -2898,7 +2898,7 @@
"page": 9,
"span": [
0,
190
185
],
"__ref_s3_data": null
}
@@ -2921,7 +2921,7 @@
"page": 9,
"span": [
0,
132
127
],
"__ref_s3_data": null
}
@@ -2944,7 +2944,7 @@
"page": 9,
"span": [
0,
219
214
],
"__ref_s3_data": null
}
@@ -2967,7 +2967,7 @@
"page": 9,
"span": [
0,
100
95
],
"__ref_s3_data": null
}
@@ -2990,7 +2990,7 @@
"page": 9,
"span": [
0,
339
334
],
"__ref_s3_data": null
}
@@ -3013,7 +3013,7 @@
"page": 9,
"span": [
0,
336
331
],
"__ref_s3_data": null
}
@@ -3036,7 +3036,7 @@
"page": 9,
"span": [
0,
188
183
],
"__ref_s3_data": null
}
@@ -3059,7 +3059,7 @@
"page": 9,
"span": [
0,
290
285
],
"__ref_s3_data": null
}
@@ -3082,7 +3082,7 @@
"page": 9,
"span": [
0,
138
133
],
"__ref_s3_data": null
}