mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(HTML): concatenation of child strings in table cells and list items (#1981)

Browse Source 
fix(HTML): ensure correct concatenation of child strings in table cells and list items

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-07-24 11:19:25 +02:00
committed by GitHub
parent 7b5f86098d
commit 5132f061a8
5 changed files with 162 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

102
tests/data/groundtruth/docling_v2/wiki_duck.html.json vendored
View File

@@ -8410,7 +8410,7 @@
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
"text": "Duck",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8422,7 +8422,7 @@
"end_row_offset_idx": 2,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "\n",
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8434,7 +8434,7 @@
"end_row_offset_idx": 3,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Bufflehead\n(Bucephala albeola)\n",
"text": "Bufflehead\n(Bucephala albeola)",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8446,7 +8446,7 @@
"end_row_offset_idx": 4,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
"text": "Scientific classification",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8458,7 +8458,7 @@
"end_row_offset_idx": 5,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Domain:\n",
"text": "Domain:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8470,7 +8470,7 @@
"end_row_offset_idx": 5,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Eukaryota\n",
"text": "Eukaryota",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8482,7 +8482,7 @@
"end_row_offset_idx": 6,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Kingdom:\n",
"text": "Kingdom:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8494,7 +8494,7 @@
"end_row_offset_idx": 6,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Animalia\n",
"text": "Animalia",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8506,7 +8506,7 @@
"end_row_offset_idx": 7,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Phylum:\n",
"text": "Phylum:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8518,7 +8518,7 @@
"end_row_offset_idx": 7,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Chordata\n",
"text": "Chordata",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8530,7 +8530,7 @@
"end_row_offset_idx": 8,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Class:\n",
"text": "Class:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8542,7 +8542,7 @@
"end_row_offset_idx": 8,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Aves\n",
"text": "Aves",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8554,7 +8554,7 @@
"end_row_offset_idx": 9,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Order:\n",
"text": "Order:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8566,7 +8566,7 @@
"end_row_offset_idx": 9,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Anseriformes\n",
"text": "Anseriformes",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8578,7 +8578,7 @@
"end_row_offset_idx": 10,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Superfamily:\n",
"text": "Superfamily:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8590,7 +8590,7 @@
"end_row_offset_idx": 10,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Anatoidea\n",
"text": "Anatoidea",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8602,7 +8602,7 @@
"end_row_offset_idx": 11,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Family:\n",
"text": "Family:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8614,7 +8614,7 @@
"end_row_offset_idx": 11,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Anatidae\n",
"text": "Anatidae",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8626,7 +8626,7 @@
"end_row_offset_idx": 12,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
"text": "Subfamilies",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8638,7 +8638,7 @@
"end_row_offset_idx": 13,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "\nSee text\n\n",
"text": "See text",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8655,7 +8655,7 @@
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
"text": "Duck",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8667,7 +8667,7 @@
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
"text": "Duck",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8681,7 +8681,7 @@
"end_row_offset_idx": 2,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "\n",
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8693,7 +8693,7 @@
"end_row_offset_idx": 2,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "\n",
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8707,7 +8707,7 @@
"end_row_offset_idx": 3,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Bufflehead\n(Bucephala albeola)\n",
"text": "Bufflehead\n(Bucephala albeola)",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8719,7 +8719,7 @@
"end_row_offset_idx": 3,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Bufflehead\n(Bucephala albeola)\n",
"text": "Bufflehead\n(Bucephala albeola)",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8733,7 +8733,7 @@
"end_row_offset_idx": 4,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
"text": "Scientific classification",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8745,7 +8745,7 @@
"end_row_offset_idx": 4,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
"text": "Scientific classification",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8759,7 +8759,7 @@
"end_row_offset_idx": 5,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Domain:\n",
"text": "Domain:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8771,7 +8771,7 @@
"end_row_offset_idx": 5,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Eukaryota\n",
"text": "Eukaryota",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8785,7 +8785,7 @@
"end_row_offset_idx": 6,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Kingdom:\n",
"text": "Kingdom:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8797,7 +8797,7 @@
"end_row_offset_idx": 6,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Animalia\n",
"text": "Animalia",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8811,7 +8811,7 @@
"end_row_offset_idx": 7,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Phylum:\n",
"text": "Phylum:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8823,7 +8823,7 @@
"end_row_offset_idx": 7,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Chordata\n",
"text": "Chordata",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8837,7 +8837,7 @@
"end_row_offset_idx": 8,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Class:\n",
"text": "Class:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8849,7 +8849,7 @@
"end_row_offset_idx": 8,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Aves\n",
"text": "Aves",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8863,7 +8863,7 @@
"end_row_offset_idx": 9,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Order:\n",
"text": "Order:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8875,7 +8875,7 @@
"end_row_offset_idx": 9,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Anseriformes\n",
"text": "Anseriformes",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8889,7 +8889,7 @@
"end_row_offset_idx": 10,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Superfamily:\n",
"text": "Superfamily:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8901,7 +8901,7 @@
"end_row_offset_idx": 10,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Anatoidea\n",
"text": "Anatoidea",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8915,7 +8915,7 @@
"end_row_offset_idx": 11,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Family:\n",
"text": "Family:",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8927,7 +8927,7 @@
"end_row_offset_idx": 11,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Anatidae\n",
"text": "Anatidae",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8941,7 +8941,7 @@
"end_row_offset_idx": 12,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
"text": "Subfamilies",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8953,7 +8953,7 @@
"end_row_offset_idx": 12,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
"text": "Subfamilies",
"column_header": true,
"row_header": false,
"row_section": false
@@ -8967,7 +8967,7 @@
"end_row_offset_idx": 13,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "\nSee text\n\n",
"text": "See text",
"column_header": false,
"row_header": false,
"row_section": false
@@ -8979,7 +8979,7 @@
"end_row_offset_idx": 13,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "\nSee text\n\n",
"text": "See text",
"column_header": false,
"row_header": false,
"row_section": false
@@ -9010,7 +9010,7 @@
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
"text": "Authority control databases",
"column_header": true,
"row_header": false,
"row_section": false
@@ -9034,7 +9034,7 @@
"end_row_offset_idx": 2,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "United StatesFranceBnF dataJapanLatviaIsrael",
"text": "United States France BnF data Japan Latvia Israel",
"column_header": false,
"row_header": false,
"row_section": false
@@ -9075,7 +9075,7 @@
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
"text": "Authority control databases",
"column_header": true,
"row_header": false,
"row_section": false
@@ -9087,7 +9087,7 @@
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
"text": "Authority control databases",
"column_header": true,
"row_header": false,
"row_section": false
@@ -9113,7 +9113,7 @@
"end_row_offset_idx": 2,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "United StatesFranceBnF dataJapanLatviaIsrael",
"text": "United States France BnF data Japan Latvia Israel",
"column_header": false,
"row_header": false,
"row_section": false