mirror of
https://github.com/docling-project/docling-core.git
synced 2026-11-18 20:27:00 +00:00
* Added ruff to dev dependencies Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Added ruff settings to pyproject.toml as in docling Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Cleanup uf pyproject.toml Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Copied settings for ruff pre-commit hooks from docling Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Excluded test/data/** from ruff formatting / linting Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * ruff format Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Added some ignore statements to pyproject.toml such that ruff check raises fewer issues Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * ruff check --fix Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Ignored some more rules Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Fixed the rest of the errors that would only concern 1 - 3 files Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Added another ignore related to df for DataFrame names Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Modified CONTRIBUTING.md such that black / isort are replaced by ruff Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Added UP045 to ignore list such that Optional[...] does not raise Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Moved .flake8 configs to pyproject.toml Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Moved autoflake to be used with ruff Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Moved all .flake8 settings to pyproject.toml to be compatible with ruff (i.e. no separate [tool.flake8] section Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Removed flake8 from .pre-commit hooks Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Applied ruff format (again); formatted some files as the line-length = 120 equals now what was set for the .flake8 settings Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Set max-complexity to 30 (as was originally) in the pyproject.toml as one linting check would fail Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Adding PD901 to ignore list such that pre-commit hooks run fully again Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * Replaced dtype | None syntax by Optional[dtype] in remaining places Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> * chore: fix 'test' ref in pyproject Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove typing List, Set, Tuple, Dict Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove UP015 check from ignore list Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove UP034 check from ignore list Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: normalize dashes in comments and docstrings Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove PD901 check from ignore list Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove C403 check from ignore list Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove C403, C413, C416 check from ignore list Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * style: remove E203, F811 check from ignore list Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> --------- Signed-off-by: Florian Schwarb <florian.schwarb@gmail.com> Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> Co-authored-by: Florian Schwarb <florian.schwarb@gmail.com> Co-authored-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
14 KiB
14 KiB
In [1]:
from docling_core.types.doc import (
DoclingDocument,
TableData,
TableCell,
RichTableCell,
DocItemLabel,
)
doc = DoclingDocument(name="")
doc.add_text(label=DocItemLabel.TITLE, text="Rich tables")
table_item = doc.add_table(
data=TableData(
num_rows=3,
num_cols=2,
),
)
rich_item = doc.add_list_group(parent=table_item)
doc.add_list_item(parent=rich_item, text="list item 1")
doc.add_list_item(parent=rich_item, text="list item 2")
for i in range(table_item.data.num_rows):
for j in range(table_item.data.num_cols):
if i == 1 and j == 1:
cell = RichTableCell(
start_row_offset_idx=i,
end_row_offset_idx=i + 1,
start_col_offset_idx=j,
end_col_offset_idx=j + 1,
ref=rich_item.get_ref(),
)
else:
cell = TableCell(
start_row_offset_idx=i,
end_row_offset_idx=i + 1,
start_col_offset_idx=j,
end_col_offset_idx=j + 1,
text=f"cell {i},{j}",
)
doc.add_table_cell(table_item=table_item, cell=cell)In [2]:
print(doc.export_to_markdown())# Rich tables | cell 0,0 | cell 0,1 | |------------|-----------------------------| | cell 1,0 | - list item 1 - list item 2 | | cell 2,0 | cell 2,1 |
In [3]:
print(doc.export_to_html()[-300:])em;
}
</style>
</head>
<body>
<div class='page'>
<h1>Rich tables</h1>
<table><tbody><tr><td>cell 0,0</td><td>cell 0,1</td></tr><tr><td>cell 1,0</td><td><ul>
<li>list item 1</li>
<li>list item 2</li>
</ul></td></tr><tr><td>cell 2,0</td><td>cell 2,1</td></tr></tbody></table>
</div>
</body>
</html>
In [4]:
print(doc.export_to_doctags())<doctag><title>Rich tables</title> <otsl><fcel>cell 0,0<fcel>cell 0,1<nl><fcel>cell 1,0<fcel><unordered_list><list_item>list item 1</list_item> <list_item>list item 2</list_item> </unordered_list><nl><fcel>cell 2,0<fcel>cell 2,1<nl></otsl> </doctag>
In [5]:
print(doc._export_to_indented_text())item-0 at level 0: unspecified: group _root_
item-1 at level 1: title: Rich tables
item-2 at level 1: table with [3x2]
item-3 at level 2: list: group group
item-4 at level 3: list_item: list item 1
item-5 at level 3: list_item: list item 2
In [6]:
print(doc.tables[0].export_to_markdown(doc=doc))| cell 0,0 | cell 0,1 | |------------|-----------------------------| | cell 1,0 | - list item 1 - list item 2 | | cell 2,0 | cell 2,1 |
In [7]:
print(doc.tables[0].export_to_html(doc=doc))<table><tbody><tr><td>cell 0,0</td><td>cell 0,1</td></tr><tr><td>cell 1,0</td><td><ul> <li>list item 1</li> <li>list item 2</li> </ul></td></tr><tr><td>cell 2,0</td><td>cell 2,1</td></tr></tbody></table>
In [8]:
print(doc.tables[0].export_to_doctags(doc=doc))<otsl><fcel>cell 0,0<fcel>cell 0,1<nl><fcel>cell 1,0<fcel><unordered_list><list_item>list item 1</list_item> <list_item>list item 2</list_item> </unordered_list><nl><fcel>cell 2,0<fcel>cell 2,1<nl></otsl>
In [9]:
print(doc.tables[0].export_to_otsl(doc=doc))<fcel>cell 0,0<fcel>cell 0,1<nl><fcel>cell 1,0<fcel><unordered_list><list_item>list item 1</list_item> <list_item>list item 2</list_item> </unordered_list><nl><fcel>cell 2,0<fcel>cell 2,1<nl>
In [10]:
display(doc.tables[0].export_to_dataframe(doc=doc))| 0 | 1 | |
|---|---|---|
| 0 | cell 0,0 | cell 0,1 |
| 1 | cell 1,0 | - list item 1\n- list item 2 |
| 2 | cell 2,0 | cell 2,1 |
In [11]:
print(doc.tables[0].export_to_markdown())Usage of TableItem.export_to_markdown() without `doc` argument is deprecated.
| cell 0,0 | cell 0,1 | |------------|--------------------| | cell 1,0 | <!-- rich cell --> | | cell 2,0 | cell 2,1 |
In [12]:
print(doc.tables[0].export_to_html())Usage of TableItem.export_to_html() without `doc` argument is deprecated.
In [13]:
display(doc.tables[0].export_to_dataframe())Usage of TableItem.export_to_dataframe() without `doc` argument is deprecated.
| 0 | 1 | |
|---|---|---|
| 0 | cell 0,0 | cell 0,1 |
| 1 | cell 1,0 | <!-- rich cell --> |
| 2 | cell 2,0 | cell 2,1 |
In [14]:
doc.tables[0].data.insert_row(
row_index=1,
after=False,
row=["foo", "bar"],
)
print(doc.export_to_markdown())# Rich tables | cell 0,0 | cell 0,1 | |------------|-----------------------------| | foo | bar | | cell 1,0 | - list item 1 - list item 2 | | cell 2,0 | cell 2,1 |
In [15]:
backup_doc = doc.model_copy(deep=True)In [16]:
_ = doc.tables[0].data.remove_row(row_index=2)When table contains rich cells, `doc` argument must be provided, otherwise rich cell content will be left dangling.
In [17]:
print(doc.export_to_markdown())# Rich tables | cell 0,0 | cell 0,1 | |------------|------------| | foo | bar | | cell 2,0 | cell 2,1 | - list item 1 - list item 2
In [18]:
backup_doc.tables[0].data.remove_row(row_index=2, doc=backup_doc)
print(backup_doc.export_to_markdown())# Rich tables | cell 0,0 | cell 0,1 | |------------|------------| | foo | bar | | cell 2,0 | cell 2,1 |
In [ ]: