",
+]
license = "MIT"
readme = "README.md"
-repository = "https://github.com/DS4SD/docling"
-homepage = "https://github.com/DS4SD/docling"
-keywords= ["docling", "convert", "document", "pdf", "docx", "html", "markdown", "layout model", "segmentation", "table structure", "table former"]
- classifiers = [
- "License :: OSI Approved :: MIT License",
- "Operating System :: MacOS :: MacOS X",
- "Operating System :: POSIX :: Linux",
- "Development Status :: 5 - Production/Stable",
- "Intended Audience :: Developers",
- "Intended Audience :: Science/Research",
- "Topic :: Scientific/Engineering :: Artificial Intelligence",
- "Programming Language :: Python :: 3"
- ]
-packages = [{include = "docling"}]
+repository = "https://github.com/docling-project/docling"
+homepage = "https://github.com/docling-project/docling"
+keywords = [
+ "docling",
+ "convert",
+ "document",
+ "pdf",
+ "docx",
+ "html",
+ "markdown",
+ "layout model",
+ "segmentation",
+ "table structure",
+ "table former",
+]
+classifiers = [
+ "License :: OSI Approved :: MIT License",
+ "Operating System :: MacOS :: MacOS X",
+ "Operating System :: POSIX :: Linux",
+ "Development Status :: 5 - Production/Stable",
+ "Intended Audience :: Developers",
+ "Intended Audience :: Science/Research",
+ "Topic :: Scientific/Engineering :: Artificial Intelligence",
+ "Programming Language :: Python :: 3",
+]
+packages = [{ include = "docling" }]
[tool.poetry.dependencies]
######################
@@ -28,7 +48,7 @@ python = "^3.9"
pydantic = "^2.0.0"
docling-core = {extras = ["chunking"], version = "^2.23.0"}
docling-ibm-models = "^3.4.0"
-docling-parse = {git = "https://github.com/DS4SD/docling-parse", rev = "cau/api-move-to-docling-core"}
+docling-parse = {git = "https://github.com/DS4SD/docling-parse", rev = "main"}
filetype = "^1.2.0"
pypdfium2 = "^4.30.0"
pydantic-settings = "^2.3.0"
@@ -40,7 +60,7 @@ certifi = ">=2024.7.4"
rtree = "^1.3.0"
scipy = [
{ version = "^1.6.0", markers = "python_version >= '3.10'" },
- { version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" }
+ { version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" },
]
typer = "^0.12.5"
python-docx = "^1.1.2"
@@ -56,21 +76,22 @@ onnxruntime = [
# 1.19.2 is the last version with python3.9 support,
# see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0
{ version = ">=1.7.0,<1.20.0", optional = true, markers = "python_version < '3.10'" },
- { version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" }
+ { version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" },
]
transformers = [
- {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
- {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true }
+ { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
+ { markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true },
]
accelerate = [
- {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
+ { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
]
pillow = ">=10.0.0,<12.0.0"
tqdm = "^4.65.0"
+pylatexenc = "^2.10"
[tool.poetry.group.dev.dependencies]
-black = {extras = ["jupyter"], version = "^24.4.2"}
+black = { extras = ["jupyter"], version = "^24.4.2" }
pytest = "^7.2.2"
pre-commit = "^3.7.1"
mypy = "^1.10.1"
@@ -93,7 +114,7 @@ types-tqdm = "^4.67.0.20241221"
mkdocs-material = "^9.5.40"
mkdocs-jupyter = "^0.25.0"
mkdocs-click = "^0.8.1"
-mkdocstrings = {extras = ["python"], version = "^0.27.0"}
+mkdocstrings = { extras = ["python"], version = "^0.27.0" }
griffe-pydantic = "^1.1.0"
[tool.poetry.group.examples.dependencies]
@@ -108,8 +129,8 @@ optional = true
[tool.poetry.group.constraints.dependencies]
numpy = [
- { version = ">=1.24.4,<3.0.0", markers = 'python_version >= "3.10"' },
- { version = ">=1.24.4,<2.1.0", markers = 'python_version < "3.10"' },
+ { version = ">=1.24.4,<3.0.0", markers = 'python_version >= "3.10"' },
+ { version = ">=1.24.4,<2.1.0", markers = 'python_version < "3.10"' },
]
[tool.poetry.group.mac_intel]
@@ -117,12 +138,12 @@ optional = true
[tool.poetry.group.mac_intel.dependencies]
torch = [
- {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2"},
- {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2"}
+ { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2" },
+ { markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2" },
]
torchvision = [
- {markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0"},
- {markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2"}
+ { markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0" },
+ { markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2" },
]
[tool.poetry.extras]
@@ -147,7 +168,7 @@ include = '\.pyi?$'
[tool.isort]
profile = "black"
line_length = 88
-py_version=39
+py_version = 39
[tool.mypy]
pretty = true
@@ -158,18 +179,19 @@ python_version = "3.10"
[[tool.mypy.overrides]]
module = [
- "docling_parse.*",
- "pypdfium2.*",
- "networkx.*",
- "scipy.*",
- "filetype.*",
- "tesserocr.*",
- "docling_ibm_models.*",
- "easyocr.*",
- "ocrmac.*",
- "lxml.*",
- "huggingface_hub.*",
- "transformers.*",
+ "docling_parse.*",
+ "pypdfium2.*",
+ "networkx.*",
+ "scipy.*",
+ "filetype.*",
+ "tesserocr.*",
+ "docling_ibm_models.*",
+ "easyocr.*",
+ "ocrmac.*",
+ "lxml.*",
+ "huggingface_hub.*",
+ "transformers.*",
+ "pylatexenc.*",
]
ignore_missing_imports = true
diff --git a/tests/data/docx/equations.docx b/tests/data/docx/equations.docx
new file mode 100644
index 00000000..8ab71b96
Binary files /dev/null and b/tests/data/docx/equations.docx differ
diff --git a/tests/data/groundtruth/docling_v2/csv-comma-in-cell.csv.json b/tests/data/groundtruth/docling_v2/csv-comma-in-cell.csv.json
index 310d5c84..6c4f7f2a 100644
--- a/tests/data/groundtruth/docling_v2/csv-comma-in-cell.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-comma-in-cell.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -296,7 +296,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -308,7 +308,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -320,7 +320,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -332,7 +332,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/csv-comma.csv.json b/tests/data/groundtruth/docling_v2/csv-comma.csv.json
index 4e7f6df9..1b5d113d 100644
--- a/tests/data/groundtruth/docling_v2/csv-comma.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-comma.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -99,7 +99,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -111,7 +111,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -123,7 +123,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -135,7 +135,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -147,7 +147,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -159,7 +159,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -171,7 +171,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -183,7 +183,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -920,7 +920,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -932,7 +932,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -944,7 +944,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -956,7 +956,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -968,7 +968,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -980,7 +980,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -992,7 +992,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1004,7 +1004,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1016,7 +1016,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1028,7 +1028,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1040,7 +1040,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1052,7 +1052,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json b/tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json
index daa2844a..22ab07bc 100644
--- a/tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -284,7 +284,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -296,7 +296,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -308,7 +308,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
diff --git a/tests/data/groundtruth/docling_v2/csv-pipe.csv.json b/tests/data/groundtruth/docling_v2/csv-pipe.csv.json
index 753fa138..b4ffd643 100644
--- a/tests/data/groundtruth/docling_v2/csv-pipe.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-pipe.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -99,7 +99,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -111,7 +111,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -123,7 +123,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -135,7 +135,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -147,7 +147,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -159,7 +159,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -171,7 +171,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -183,7 +183,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -920,7 +920,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -932,7 +932,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -944,7 +944,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -956,7 +956,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -968,7 +968,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -980,7 +980,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -992,7 +992,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1004,7 +1004,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1016,7 +1016,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1028,7 +1028,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1040,7 +1040,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1052,7 +1052,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/csv-semicolon.csv.json b/tests/data/groundtruth/docling_v2/csv-semicolon.csv.json
index a429ceeb..4e654b10 100644
--- a/tests/data/groundtruth/docling_v2/csv-semicolon.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-semicolon.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -99,7 +99,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -111,7 +111,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -123,7 +123,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -135,7 +135,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -147,7 +147,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -159,7 +159,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -171,7 +171,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -183,7 +183,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -920,7 +920,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -932,7 +932,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -944,7 +944,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -956,7 +956,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -968,7 +968,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -980,7 +980,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -992,7 +992,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1004,7 +1004,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1016,7 +1016,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1028,7 +1028,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1040,7 +1040,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1052,7 +1052,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/csv-tab.csv.json b/tests/data/groundtruth/docling_v2/csv-tab.csv.json
index 5f6d4ac5..14ab073e 100644
--- a/tests/data/groundtruth/docling_v2/csv-tab.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-tab.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -99,7 +99,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -111,7 +111,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -123,7 +123,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -135,7 +135,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -147,7 +147,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -159,7 +159,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -171,7 +171,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -183,7 +183,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -920,7 +920,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -932,7 +932,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -944,7 +944,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -956,7 +956,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -968,7 +968,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -980,7 +980,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -992,7 +992,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1004,7 +1004,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1016,7 +1016,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1028,7 +1028,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1040,7 +1040,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1052,7 +1052,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/csv-too-few-columns.csv.json b/tests/data/groundtruth/docling_v2/csv-too-few-columns.csv.json
index e1275895..c17e6d28 100644
--- a/tests/data/groundtruth/docling_v2/csv-too-few-columns.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-too-few-columns.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -284,7 +284,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -296,7 +296,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -308,7 +308,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -320,7 +320,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/csv-too-many-columns.csv.json b/tests/data/groundtruth/docling_v2/csv-too-many-columns.csv.json
index 6df1ac90..6292b7a8 100644
--- a/tests/data/groundtruth/docling_v2/csv-too-many-columns.csv.json
+++ b/tests/data/groundtruth/docling_v2/csv-too-many-columns.csv.json
@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -308,7 +308,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -320,7 +320,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -332,7 +332,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -344,7 +344,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
diff --git a/tests/data/groundtruth/docling_v2/equations.docx.itxt b/tests/data/groundtruth/docling_v2/equations.docx.itxt
new file mode 100644
index 00000000..1412074d
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/equations.docx.itxt
@@ -0,0 +1,40 @@
+item-0 at level 0: unspecified: group _root_
+ item-1 at level 1: inline: group group
+ item-2 at level 2: paragraph: This is a word document and this is an inline equation:
+ item-3 at level 2: formula: A= \pi r^{2}
+ item-4 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
+ item-5 at level 1: paragraph:
+ item-6 at level 1: formula: a^{2}+b^{2}=c^{2} \text{ \texttimes } 23
+ item-7 at level 1: paragraph: And that is an equation by itself. Cheers!
+ item-8 at level 1: paragraph:
+ item-9 at level 1: paragraph: This is another equation:
+ item-10 at level 1: formula: f\left(x\right)=a_{0}+\sum_{n=1} ... })+b_{n}\sin(\frac{n \pi x}{L})\right)
+ item-11 at level 1: paragraph:
+ item-12 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
+ item-13 at level 1: paragraph:
+ item-14 at level 1: paragraph:
+ item-15 at level 1: inline: group group
+ item-16 at level 2: paragraph: This is a word document and this is an inline equation:
+ item-17 at level 2: formula: A= \pi r^{2}
+ item-18 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
+ item-19 at level 1: paragraph:
+ item-20 at level 1: formula: \left(x+a\right)^{n}=\sum_{k=0}^ ... ac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}
+ item-21 at level 1: paragraph:
+ item-22 at level 1: paragraph: And that is an equation by itself. Cheers!
+ item-23 at level 1: paragraph:
+ item-24 at level 1: paragraph: This is another equation:
+ item-25 at level 1: paragraph:
+ item-26 at level 1: formula: \left(1+x\right)^{n}=1+\frac{nx} ... ght)x^{2}}{2!}+ \text{ \textellipsis }
+ item-27 at level 1: paragraph:
+ item-28 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
+ item-29 at level 1: paragraph:
+ item-30 at level 1: paragraph:
+ item-31 at level 1: inline: group group
+ item-32 at level 2: paragraph: This is a word document and this is an inline equation:
+ item-33 at level 2: formula: A= \pi r^{2}
+ item-34 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
+ item-35 at level 1: paragraph:
+ item-36 at level 1: formula: e^{x}=1+\frac{x}{1!}+\frac{x^{2} ... xtellipsis } , - \infty < x < \infty
+ item-37 at level 1: paragraph:
+ item-38 at level 1: paragraph: And that is an equation by itself. Cheers!
+ item-39 at level 1: paragraph:
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/equations.docx.json b/tests/data/groundtruth/docling_v2/equations.docx.json
new file mode 100644
index 00000000..7880ce44
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/equations.docx.json
@@ -0,0 +1,616 @@
+{
+ "schema_name": "DoclingDocument",
+ "version": "1.2.0",
+ "name": "equations",
+ "origin": {
+ "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+ "binary_hash": 11121138535595486899,
+ "filename": "equations.docx"
+ },
+ "furniture": {
+ "self_ref": "#/furniture",
+ "children": [],
+ "content_layer": "furniture",
+ "name": "_root_",
+ "label": "unspecified"
+ },
+ "body": {
+ "self_ref": "#/body",
+ "children": [
+ {
+ "$ref": "#/groups/0"
+ },
+ {
+ "$ref": "#/texts/3"
+ },
+ {
+ "$ref": "#/texts/4"
+ },
+ {
+ "$ref": "#/texts/5"
+ },
+ {
+ "$ref": "#/texts/6"
+ },
+ {
+ "$ref": "#/texts/7"
+ },
+ {
+ "$ref": "#/texts/8"
+ },
+ {
+ "$ref": "#/texts/9"
+ },
+ {
+ "$ref": "#/texts/10"
+ },
+ {
+ "$ref": "#/texts/11"
+ },
+ {
+ "$ref": "#/texts/12"
+ },
+ {
+ "$ref": "#/groups/1"
+ },
+ {
+ "$ref": "#/texts/16"
+ },
+ {
+ "$ref": "#/texts/17"
+ },
+ {
+ "$ref": "#/texts/18"
+ },
+ {
+ "$ref": "#/texts/19"
+ },
+ {
+ "$ref": "#/texts/20"
+ },
+ {
+ "$ref": "#/texts/21"
+ },
+ {
+ "$ref": "#/texts/22"
+ },
+ {
+ "$ref": "#/texts/23"
+ },
+ {
+ "$ref": "#/texts/24"
+ },
+ {
+ "$ref": "#/texts/25"
+ },
+ {
+ "$ref": "#/texts/26"
+ },
+ {
+ "$ref": "#/texts/27"
+ },
+ {
+ "$ref": "#/groups/2"
+ },
+ {
+ "$ref": "#/texts/31"
+ },
+ {
+ "$ref": "#/texts/32"
+ },
+ {
+ "$ref": "#/texts/33"
+ },
+ {
+ "$ref": "#/texts/34"
+ },
+ {
+ "$ref": "#/texts/35"
+ }
+ ],
+ "content_layer": "body",
+ "name": "_root_",
+ "label": "unspecified"
+ },
+ "groups": [
+ {
+ "self_ref": "#/groups/0",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/0"
+ },
+ {
+ "$ref": "#/texts/1"
+ },
+ {
+ "$ref": "#/texts/2"
+ }
+ ],
+ "content_layer": "body",
+ "name": "group",
+ "label": "inline"
+ },
+ {
+ "self_ref": "#/groups/1",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/13"
+ },
+ {
+ "$ref": "#/texts/14"
+ },
+ {
+ "$ref": "#/texts/15"
+ }
+ ],
+ "content_layer": "body",
+ "name": "group",
+ "label": "inline"
+ },
+ {
+ "self_ref": "#/groups/2",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/28"
+ },
+ {
+ "$ref": "#/texts/29"
+ },
+ {
+ "$ref": "#/texts/30"
+ }
+ ],
+ "content_layer": "body",
+ "name": "group",
+ "label": "inline"
+ }
+ ],
+ "texts": [
+ {
+ "self_ref": "#/texts/0",
+ "parent": {
+ "$ref": "#/groups/0"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is a word document and this is an inline equation: ",
+ "text": "This is a word document and this is an inline equation: "
+ },
+ {
+ "self_ref": "#/texts/1",
+ "parent": {
+ "$ref": "#/groups/0"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "A= \\pi r^{2} ",
+ "text": "A= \\pi r^{2} "
+ },
+ {
+ "self_ref": "#/texts/2",
+ "parent": {
+ "$ref": "#/groups/0"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": ". If instead, I want an equation by line, I can do this:",
+ "text": ". If instead, I want an equation by line, I can do this:"
+ },
+ {
+ "self_ref": "#/texts/3",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/4",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
+ "text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
+ },
+ {
+ "self_ref": "#/texts/5",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "And that is an equation by itself. Cheers!",
+ "text": "And that is an equation by itself. Cheers!"
+ },
+ {
+ "self_ref": "#/texts/6",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/7",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is another equation:",
+ "text": "This is another equation:"
+ },
+ {
+ "self_ref": "#/texts/8",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
+ "text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
+ },
+ {
+ "self_ref": "#/texts/9",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/10",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
+ "text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
+ },
+ {
+ "self_ref": "#/texts/11",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/12",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/13",
+ "parent": {
+ "$ref": "#/groups/1"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is a word document and this is an inline equation: ",
+ "text": "This is a word document and this is an inline equation: "
+ },
+ {
+ "self_ref": "#/texts/14",
+ "parent": {
+ "$ref": "#/groups/1"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "A= \\pi r^{2} ",
+ "text": "A= \\pi r^{2} "
+ },
+ {
+ "self_ref": "#/texts/15",
+ "parent": {
+ "$ref": "#/groups/1"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": ". If instead, I want an equation by line, I can do this:",
+ "text": ". If instead, I want an equation by line, I can do this:"
+ },
+ {
+ "self_ref": "#/texts/16",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/17",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}",
+ "text": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}"
+ },
+ {
+ "self_ref": "#/texts/18",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/19",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "And that is an equation by itself. Cheers!",
+ "text": "And that is an equation by itself. Cheers!"
+ },
+ {
+ "self_ref": "#/texts/20",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/21",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is another equation:",
+ "text": "This is another equation:"
+ },
+ {
+ "self_ref": "#/texts/22",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/23",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis }",
+ "text": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis }"
+ },
+ {
+ "self_ref": "#/texts/24",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/25",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
+ "text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
+ },
+ {
+ "self_ref": "#/texts/26",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/27",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/28",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "This is a word document and this is an inline equation: ",
+ "text": "This is a word document and this is an inline equation: "
+ },
+ {
+ "self_ref": "#/texts/29",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "A= \\pi r^{2} ",
+ "text": "A= \\pi r^{2} "
+ },
+ {
+ "self_ref": "#/texts/30",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": ". If instead, I want an equation by line, I can do this:",
+ "text": ". If instead, I want an equation by line, I can do this:"
+ },
+ {
+ "self_ref": "#/texts/31",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/32",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "formula",
+ "prov": [],
+ "orig": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty",
+ "text": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty"
+ },
+ {
+ "self_ref": "#/texts/33",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ },
+ {
+ "self_ref": "#/texts/34",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "And that is an equation by itself. Cheers!",
+ "text": "And that is an equation by itself. Cheers!"
+ },
+ {
+ "self_ref": "#/texts/35",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "paragraph",
+ "prov": [],
+ "orig": "",
+ "text": ""
+ }
+ ],
+ "pictures": [],
+ "tables": [],
+ "key_value_items": [],
+ "form_items": [],
+ "pages": {}
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/equations.docx.md b/tests/data/groundtruth/docling_v2/equations.docx.md
new file mode 100644
index 00000000..a8253ebf
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/equations.docx.md
@@ -0,0 +1,29 @@
+This is a word document and this is an inline equation: $A= \pi r^{2} $ . If instead, I want an equation by line, I can do this:
+
+$$a^{2}+b^{2}=c^{2} \text{ \texttimes } 23$$
+
+And that is an equation by itself. Cheers!
+
+This is another equation:
+
+$$f\left(x\right)=a_{0}+\sum_{n=1}^{ \infty }\left(a_{n}\cos(\frac{n \pi x}{L})+b_{n}\sin(\frac{n \pi x}{L})\right)$$
+
+This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.
+
+This is a word document and this is an inline equation: $A= \pi r^{2} $ . If instead, I want an equation by line, I can do this:
+
+$$\left(x+a\right)^{n}=\sum_{k=0}^{n}\left(\genfrac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}$$
+
+And that is an equation by itself. Cheers!
+
+This is another equation:
+
+$$\left(1+x\right)^{n}=1+\frac{nx}{1!}+\frac{n\left(n-1\right)x^{2}}{2!}+ \text{ \textellipsis }$$
+
+This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.
+
+This is a word document and this is an inline equation: $A= \pi r^{2} $ . If instead, I want an equation by line, I can do this:
+
+$$e^{x}=1+\frac{x}{1!}+\frac{x^{2}}{2!}+\frac{x^{3}}{3!}+ \text{ \textellipsis } , - \infty < x < \infty$$
+
+And that is an equation by itself. Cheers!
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/example_03.html.json b/tests/data/groundtruth/docling_v2/example_03.html.json
index bdfaaebe..5d373296 100644
--- a/tests/data/groundtruth/docling_v2/example_03.html.json
+++ b/tests/data/groundtruth/docling_v2/example_03.html.json
@@ -344,7 +344,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -356,7 +356,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -368,7 +368,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -493,7 +493,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -505,7 +505,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -517,7 +517,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/example_04.html.json b/tests/data/groundtruth/docling_v2/example_04.html.json
index 23c38904..854ba4c6 100644
--- a/tests/data/groundtruth/docling_v2/example_04.html.json
+++ b/tests/data/groundtruth/docling_v2/example_04.html.json
@@ -68,7 +68,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -80,7 +80,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -181,7 +181,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -193,7 +193,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -205,7 +205,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/example_05.html.json b/tests/data/groundtruth/docling_v2/example_05.html.json
index 3c5c1f0e..3168a637 100644
--- a/tests/data/groundtruth/docling_v2/example_05.html.json
+++ b/tests/data/groundtruth/docling_v2/example_05.html.json
@@ -68,7 +68,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -80,7 +80,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -181,7 +181,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -193,7 +193,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -205,7 +205,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/example_07.html.itxt b/tests/data/groundtruth/docling_v2/example_07.html.itxt
new file mode 100644
index 00000000..675749eb
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/example_07.html.itxt
@@ -0,0 +1,22 @@
+item-0 at level 0: unspecified: group _root_
+ item-1 at level 1: list: group list
+ item-2 at level 2: list_item: Asia
+ item-3 at level 3: list: group list
+ item-4 at level 4: list_item: China
+ item-5 at level 4: list_item: Japan
+ item-6 at level 4: list_item: Thailand
+ item-7 at level 2: list_item: Europe
+ item-8 at level 3: list: group list
+ item-9 at level 4: list_item: UK
+ item-10 at level 4: list_item: Germany
+ item-11 at level 4: list_item: Switzerland
+ item-12 at level 5: list: group list
+ item-13 at level 6: list: group list
+ item-14 at level 7: list_item: Bern
+ item-15 at level 7: list_item: Aargau
+ item-16 at level 4: list_item: Italy
+ item-17 at level 5: list: group list
+ item-18 at level 6: list: group list
+ item-19 at level 7: list_item: Piedmont
+ item-20 at level 7: list_item: Liguria
+ item-21 at level 2: list_item: Africa
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/example_07.html.json b/tests/data/groundtruth/docling_v2/example_07.html.json
new file mode 100644
index 00000000..248a47bd
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/example_07.html.json
@@ -0,0 +1,374 @@
+{
+ "schema_name": "DoclingDocument",
+ "version": "1.2.0",
+ "name": "example_07",
+ "origin": {
+ "mimetype": "text/html",
+ "binary_hash": 623628706615267627,
+ "filename": "example_07.html"
+ },
+ "furniture": {
+ "self_ref": "#/furniture",
+ "children": [],
+ "content_layer": "furniture",
+ "name": "_root_",
+ "label": "unspecified"
+ },
+ "body": {
+ "self_ref": "#/body",
+ "children": [
+ {
+ "$ref": "#/groups/0"
+ }
+ ],
+ "content_layer": "body",
+ "name": "_root_",
+ "label": "unspecified"
+ },
+ "groups": [
+ {
+ "self_ref": "#/groups/0",
+ "parent": {
+ "$ref": "#/body"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/0"
+ },
+ {
+ "$ref": "#/texts/4"
+ },
+ {
+ "$ref": "#/texts/13"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ },
+ {
+ "self_ref": "#/groups/1",
+ "parent": {
+ "$ref": "#/texts/0"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/1"
+ },
+ {
+ "$ref": "#/texts/2"
+ },
+ {
+ "$ref": "#/texts/3"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ },
+ {
+ "self_ref": "#/groups/2",
+ "parent": {
+ "$ref": "#/texts/4"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/5"
+ },
+ {
+ "$ref": "#/texts/6"
+ },
+ {
+ "$ref": "#/texts/7"
+ },
+ {
+ "$ref": "#/texts/10"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ },
+ {
+ "self_ref": "#/groups/3",
+ "parent": {
+ "$ref": "#/texts/7"
+ },
+ "children": [
+ {
+ "$ref": "#/groups/4"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ },
+ {
+ "self_ref": "#/groups/4",
+ "parent": {
+ "$ref": "#/groups/3"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/8"
+ },
+ {
+ "$ref": "#/texts/9"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ },
+ {
+ "self_ref": "#/groups/5",
+ "parent": {
+ "$ref": "#/texts/10"
+ },
+ "children": [
+ {
+ "$ref": "#/groups/6"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ },
+ {
+ "self_ref": "#/groups/6",
+ "parent": {
+ "$ref": "#/groups/5"
+ },
+ "children": [
+ {
+ "$ref": "#/texts/11"
+ },
+ {
+ "$ref": "#/texts/12"
+ }
+ ],
+ "content_layer": "body",
+ "name": "list",
+ "label": "list"
+ }
+ ],
+ "texts": [
+ {
+ "self_ref": "#/texts/0",
+ "parent": {
+ "$ref": "#/groups/0"
+ },
+ "children": [
+ {
+ "$ref": "#/groups/1"
+ }
+ ],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Asia",
+ "text": "Asia",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/1",
+ "parent": {
+ "$ref": "#/groups/1"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "China",
+ "text": "China",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/2",
+ "parent": {
+ "$ref": "#/groups/1"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Japan",
+ "text": "Japan",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/3",
+ "parent": {
+ "$ref": "#/groups/1"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Thailand",
+ "text": "Thailand",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/4",
+ "parent": {
+ "$ref": "#/groups/0"
+ },
+ "children": [
+ {
+ "$ref": "#/groups/2"
+ }
+ ],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Europe",
+ "text": "Europe",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/5",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "UK",
+ "text": "UK",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/6",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Germany",
+ "text": "Germany",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/7",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [
+ {
+ "$ref": "#/groups/3"
+ }
+ ],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Switzerland",
+ "text": "Switzerland",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/8",
+ "parent": {
+ "$ref": "#/groups/4"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Bern",
+ "text": "Bern",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/9",
+ "parent": {
+ "$ref": "#/groups/4"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Aargau",
+ "text": "Aargau",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/10",
+ "parent": {
+ "$ref": "#/groups/2"
+ },
+ "children": [
+ {
+ "$ref": "#/groups/5"
+ }
+ ],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Italy",
+ "text": "Italy",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/11",
+ "parent": {
+ "$ref": "#/groups/6"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Piedmont",
+ "text": "Piedmont",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/12",
+ "parent": {
+ "$ref": "#/groups/6"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Liguria",
+ "text": "Liguria",
+ "enumerated": false,
+ "marker": "-"
+ },
+ {
+ "self_ref": "#/texts/13",
+ "parent": {
+ "$ref": "#/groups/0"
+ },
+ "children": [],
+ "content_layer": "body",
+ "label": "list_item",
+ "prov": [],
+ "orig": "Africa",
+ "text": "Africa",
+ "enumerated": false,
+ "marker": "-"
+ }
+ ],
+ "pictures": [],
+ "tables": [],
+ "key_value_items": [],
+ "form_items": [],
+ "pages": {}
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/example_07.html.md b/tests/data/groundtruth/docling_v2/example_07.html.md
new file mode 100644
index 00000000..0a4b9fac
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/example_07.html.md
@@ -0,0 +1,14 @@
+- Asia
+ - China
+ - Japan
+ - Thailand
+- Europe
+ - UK
+ - Germany
+ - Switzerland
+ - Bern
+ - Aargau
+ - Italy
+ - Piedmont
+ - Liguria
+- Africa
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json b/tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
index 6783cf3f..b24c46ed 100644
--- a/tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
+++ b/tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
@@ -960,7 +960,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 4,
"text": "Class1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -972,7 +972,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 7,
"text": "Class2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1385,7 +1385,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 4,
"text": "Class1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1397,7 +1397,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 4,
"text": "Class1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1409,7 +1409,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 4,
"text": "Class1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1421,7 +1421,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 7,
"text": "Class2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1433,7 +1433,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 7,
"text": "Class2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1445,7 +1445,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 7,
"text": "Class2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/tablecell.docx.json b/tests/data/groundtruth/docling_v2/tablecell.docx.json
index 51341f35..2a070468 100644
--- a/tests/data/groundtruth/docling_v2/tablecell.docx.json
+++ b/tests/data/groundtruth/docling_v2/tablecell.docx.json
@@ -176,7 +176,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Tab1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -188,7 +188,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Tab2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -200,7 +200,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Tab3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -289,7 +289,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Tab1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -301,7 +301,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Tab2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -313,7 +313,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Tab3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/test-01.xlsx.json b/tests/data/groundtruth/docling_v2/test-01.xlsx.json
index 19a701c5..173cd5fb 100644
--- a/tests/data/groundtruth/docling_v2/test-01.xlsx.json
+++ b/tests/data/groundtruth/docling_v2/test-01.xlsx.json
@@ -136,7 +136,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -148,7 +148,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "second ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -160,7 +160,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "third",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -393,7 +393,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -405,7 +405,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "second ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -417,7 +417,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "third",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -675,7 +675,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "col-1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -687,7 +687,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "col-2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -699,7 +699,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "col-3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -711,7 +711,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "col-4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1112,7 +1112,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "col-1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1124,7 +1124,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "col-2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1136,7 +1136,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "col-3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1148,7 +1148,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "col-4",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -1578,7 +1578,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "col-1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1590,7 +1590,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "col-2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1602,7 +1602,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "col-3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1763,7 +1763,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "col-1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1775,7 +1775,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "col-2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1787,7 +1787,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "col-3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -1969,7 +1969,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "col-1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1981,7 +1981,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "col-2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -1993,7 +1993,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "col-3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2154,7 +2154,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "col-1",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2166,7 +2166,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "col-2",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2178,7 +2178,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "col-3",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -2360,7 +2360,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2372,7 +2372,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "header",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2545,7 +2545,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2557,7 +2557,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "header",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2569,7 +2569,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "header",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -2583,7 +2583,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2827,7 +2827,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first (f)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -2839,7 +2839,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "header (f)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -3012,7 +3012,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first (f)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -3024,7 +3024,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "header (f)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -3036,7 +3036,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "header (f)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -3050,7 +3050,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "first (f)",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
diff --git a/tests/data/groundtruth/docling_v2/wiki_duck.html.json b/tests/data/groundtruth/docling_v2/wiki_duck.html.json
index 5a4928be..eb93fe29 100644
--- a/tests/data/groundtruth/docling_v2/wiki_duck.html.json
+++ b/tests/data/groundtruth/docling_v2/wiki_duck.html.json
@@ -7914,7 +7914,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -7950,7 +7950,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8130,7 +8130,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8159,7 +8159,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8171,7 +8171,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -8237,7 +8237,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8249,7 +8249,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -8445,7 +8445,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8457,7 +8457,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
@@ -8513,7 +8513,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8578,7 +8578,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -8590,7 +8590,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/word_sample.docx.json b/tests/data/groundtruth/docling_v2/word_sample.docx.json
index 2f5dfa32..1d305cbc 100644
--- a/tests/data/groundtruth/docling_v2/word_sample.docx.json
+++ b/tests/data/groundtruth/docling_v2/word_sample.docx.json
@@ -490,7 +490,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -502,7 +502,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Food",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -514,7 +514,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Calories per portion",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -639,7 +639,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -651,7 +651,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Food",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
},
@@ -663,7 +663,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Calories per portion",
- "column_header": false,
+ "column_header": true,
"row_header": false,
"row_section": false
}
diff --git a/tests/data/groundtruth/docling_v2/word_tables.docx.html b/tests/data/groundtruth/docling_v2/word_tables.docx.html
index 00a790c0..2dc087f7 100644
--- a/tests/data/groundtruth/docling_v2/word_tables.docx.html
+++ b/tests/data/groundtruth/docling_v2/word_tables.docx.html
@@ -71,19 +71,19 @@
Test with tables
A uniform table
-| Header 0.0 | Header 0.1 | Header 0.2 |
| Cell 1.0 | Cell 1.1 | Cell 1.2 |
| Cell 2.0 | Cell 2.1 | Cell 2.2 |
+| Header 0.0 | Header 0.1 | Header 0.2 |
|---|
| Cell 1.0 | Cell 1.1 | Cell 1.2 |
| Cell 2.0 | Cell 2.1 | Cell 2.2 |
A non-uniform table with horizontal spans
-| Header 0.0 | Header 0.1 | Header 0.2 |
| Cell 1.0 | Merged Cell 1.1 1.2 |
| Cell 2.0 | Merged Cell 2.1 2.2 |
+| Header 0.0 | Header 0.1 | Header 0.2 |
|---|
| Cell 1.0 | Merged Cell 1.1 1.2 |
| Cell 2.0 | Merged Cell 2.1 2.2 |
A non-uniform table with horizontal spans in inner columns
-| Header 0.0 | Header 0.1 | Header 0.2 | Header 0.3 |
| Cell 1.0 | Merged Cell 1.1 1.2 | Cell 1.3 |
| Cell 2.0 | Merged Cell 2.1 2.2 | Cell 2.3 |
+| Header 0.0 | Header 0.1 | Header 0.2 | Header 0.3 |
|---|
| Cell 1.0 | Merged Cell 1.1 1.2 | Cell 1.3 |
| Cell 2.0 | Merged Cell 2.1 2.2 | Cell 2.3 |
A non-uniform table with vertical spans
-| Header 0.0 | Header 0.1 | Header 0.2 |
| Cell 1.0 | Merged Cell 1.1 2.1 | Cell 1.2 |
| Cell 2.0 | Cell 2.2 |
| Cell 3.0 | Merged Cell 3.1 4.1 | Cell 3.2 |
| Cell 4.0 | Cell 4.2 |
+| Header 0.0 | Header 0.1 | Header 0.2 |
|---|
| Cell 1.0 | Merged Cell 1.1 2.1 | Cell 1.2 |
| Cell 2.0 | Cell 2.2 |
| Cell 3.0 | Merged Cell 3.1 4.1 | Cell 3.2 |
| Cell 4.0 | Cell 4.2 |
A non-uniform table with all kinds of spans and empty cells
-| Header 0.0 | Header 0.1 | Header 0.2 | | |
| Cell 1.0 | Merged Cell 1.1 2.1 | Cell 1.2 | | |
| Cell 2.0 | Cell 2.2 | | |
| Cell 3.0 | Merged Cell 3.1 4.1 | Cell 3.2 | | |
| Cell 4.0 | Cell 4.2 | Merged Cell 4.4 5.4 |
| | |
| | | | |
|
| | | | Cell 8.4 |
+| Header 0.0 | Header 0.1 | Header 0.2 | | |
|---|
| Cell 1.0 | Merged Cell 1.1 2.1 | Cell 1.2 | | |
| Cell 2.0 | Cell 2.2 | | |
| Cell 3.0 | Merged Cell 3.1 4.1 | Cell 3.2 | | |
| Cell 4.0 | Cell 4.2 | Merged Cell 4.4 5.4 |
| | |
| | | | |
|
| | | | Cell 8.4 |
+
+ 
![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ "