mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 21:28:17 +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

52
tests/data/groundtruth/docling_v1/multi_page.json vendored
View File

@@ -233,7 +233,7 @@
"page": 1,
"span": [
0,
248
246
],
"__ref_s3_data": null
}
@@ -256,7 +256,7 @@
"page": 1,
"span": [
0,
205
203
],
"__ref_s3_data": null
}
@@ -348,7 +348,7 @@
"page": 1,
"span": [
0,
201
199
],
"__ref_s3_data": null
}
@@ -371,7 +371,7 @@
"page": 1,
"span": [
0,
214
212
],
"__ref_s3_data": null
}
@@ -463,7 +463,7 @@
"page": 2,
"span": [
0,
155
153
],
"__ref_s3_data": null
}
@@ -486,7 +486,7 @@
"page": 2,
"span": [
0,
135
133
],
"__ref_s3_data": null
}
@@ -509,7 +509,7 @@
"page": 2,
"span": [
0,
197
195
],
"__ref_s3_data": null
}
@@ -647,7 +647,7 @@
"page": 3,
"span": [
0,
365
363
],
"__ref_s3_data": null
}
@@ -670,7 +670,7 @@
"page": 3,
"span": [
0,
253
251
],
"__ref_s3_data": null
}
@@ -693,7 +693,7 @@
"page": 3,
"span": [
0,
300
298
],
"__ref_s3_data": null
}
@@ -762,7 +762,7 @@
"page": 3,
"span": [
0,
140
137
],
"__ref_s3_data": null
}
@@ -785,7 +785,7 @@
"page": 3,
"span": [
0,
116
113
],
"__ref_s3_data": null
}
@@ -808,7 +808,7 @@
"page": 3,
"span": [
0,
114
111
],
"__ref_s3_data": null
}
@@ -831,7 +831,7 @@
"page": 3,
"span": [
0,
142
139
],
"__ref_s3_data": null
}
@@ -854,7 +854,7 @@
"page": 3,
"span": [
0,
170
167
],
"__ref_s3_data": null
}
@@ -923,7 +923,7 @@
"page": 4,
"span": [
0,
222
220
],
"__ref_s3_data": null
}
@@ -946,7 +946,7 @@
"page": 4,
"span": [
0,
242
240
],
"__ref_s3_data": null
}
@@ -969,7 +969,7 @@
"page": 4,
"span": [
0,
226
224
],
"__ref_s3_data": null
}
@@ -1038,7 +1038,7 @@
"page": 4,
"span": [
0,
290
287
],
"__ref_s3_data": null
}
@@ -1061,7 +1061,7 @@
"page": 4,
"span": [
0,
278
275
],
"__ref_s3_data": null
}
@@ -1084,7 +1084,7 @@
"page": 4,
"span": [
0,
253
250
],
"__ref_s3_data": null
}
@@ -1107,7 +1107,7 @@
"page": 4,
"span": [
0,
215
212
],
"__ref_s3_data": null
}
@@ -1130,7 +1130,7 @@
"page": 4,
"span": [
0,
206
203
],
"__ref_s3_data": null
}
@@ -1199,7 +1199,7 @@
"page": 4,
"span": [
0,
155
153
],
"__ref_s3_data": null
}
@@ -1222,7 +1222,7 @@
"page": 4,
"span": [
0,
184
182
],
"__ref_s3_data": null
}
@@ -1245,7 +1245,7 @@
"page": 4,
"span": [
0,
158
156
],
"__ref_s3_data": null
}