NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Call into docling-core for legacy document transform (#551)

Browse Source 
Call into docling-core for legacy document transform

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2024-12-09 17:06:47 +01:00 committed by GitHub
parent 78f61a8522
commit 7972d47f88
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 12 additions and 258 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

255
docling/datamodel/document.py
View File

@ -33,6 +33,7 @@ from docling_core.types.legacy_doc.document import (
from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
from docling_core.utils.file import resolve_source_to_stream
from docling_core.utils.legacy import docling_document_to_legacy
from pydantic import BaseModel
from typing_extensions import deprecated
@ -189,259 +190,7 @@ class ConversionResult(BaseModel):
@property
@deprecated("Use document instead.")
def legacy_document(self):
reverse_label_mapping = {
DocItemLabel.CAPTION.value: "Caption",
DocItemLabel.FOOTNOTE.value: "Footnote",
DocItemLabel.FORMULA.value: "Formula",
DocItemLabel.LIST_ITEM.value: "List-item",
DocItemLabel.PAGE_FOOTER.value: "Page-footer",
DocItemLabel.PAGE_HEADER.value: "Page-header",
DocItemLabel.PICTURE.value: "Picture", # low threshold adjust to capture chemical structures for examples.
DocItemLabel.SECTION_HEADER.value: "Section-header",
DocItemLabel.TABLE.value: "Table",
DocItemLabel.TEXT.value: "Text",
DocItemLabel.TITLE.value: "Title",
DocItemLabel.DOCUMENT_INDEX.value: "Document Index",
DocItemLabel.CODE.value: "Code",
DocItemLabel.CHECKBOX_SELECTED.value: "Checkbox-Selected",
DocItemLabel.CHECKBOX_UNSELECTED.value: "Checkbox-Unselected",
DocItemLabel.FORM.value: "Form",
DocItemLabel.KEY_VALUE_REGION.value: "Key-Value Region",
DocItemLabel.PARAGRAPH.value: "paragraph",
}
title = ""
desc = DsDocumentDescription(logs=[])
page_hashes = [
PageReference(
hash=create_hash(self.input.document_hash + ":" + str(p.page_no - 1)),
page=p.page_no,
model="default",
)
for p in self.document.pages.values()
]
file_info = DsFileInfoObject(
filename=self.input.file.name,
document_hash=self.input.document_hash,
num_pages=self.input.page_count,
page_hashes=page_hashes,
)
main_text = []
tables = []
figures = []
equations = []
footnotes = []
page_headers = []
page_footers = []
embedded_captions = set()
for ix, (item, level) in enumerate(
self.document.iterate_items(self.document.body)
):
if isinstance(item, (TableItem, PictureItem)) and len(item.captions) > 0:
caption = item.caption_text(self.document)
if caption:
embedded_captions.add(caption)
for item, level in self.document.iterate_items():
if isinstance(item, DocItem):
item_type = item.label
if isinstance(item, (TextItem, ListItem, SectionHeaderItem)):
if isinstance(item, ListItem) and item.marker:
text = f"{item.marker} {item.text}"
else:
text = item.text
# Can be empty.
prov = [
Prov(
bbox=p.bbox.as_tuple(),
page=p.page_no,
span=[0, len(item.text)],
)
for p in item.prov
]
main_text.append(
BaseText(
text=text,
obj_type=layout_label_to_ds_type.get(item.label),
name=reverse_label_mapping[item.label],
prov=prov,
)
)
# skip captions of they are embedded in the actual
# floating object
if item_type == DocItemLabel.CAPTION and text in embedded_captions:
continue
elif isinstance(item, TableItem) and item.data:
index = len(tables)
ref_str = f"#/tables/{index}"
main_text.append(
Ref(
name=reverse_label_mapping[item.label],
obj_type=layout_label_to_ds_type.get(item.label),
ref=ref_str,
),
)
# Initialise empty table data grid (only empty cells)
table_data = [
[
TableCell(
text="",
# bbox=[0,0,0,0],
spans=[[i, j]],
obj_type="body",
)
for j in range(item.data.num_cols)
]
for i in range(item.data.num_rows)
]
# Overwrite cells in table data for which there is actual cell content.
for cell in item.data.table_cells:
for i in range(
min(cell.start_row_offset_idx, item.data.num_rows),
min(cell.end_row_offset_idx, item.data.num_rows),
):
for j in range(
min(cell.start_col_offset_idx, item.data.num_cols),
min(cell.end_col_offset_idx, item.data.num_cols),
):
celltype = "body"
if cell.column_header:
celltype = "col_header"
elif cell.row_header:
celltype = "row_header"
elif cell.row_section:
celltype = "row_section"
def make_spans(cell):
for rspan in range(
min(
cell.start_row_offset_idx,
item.data.num_rows,
),
min(
cell.end_row_offset_idx, item.data.num_rows
),
):
for cspan in range(
min(
cell.start_col_offset_idx,
item.data.num_cols,
),
min(
cell.end_col_offset_idx,
item.data.num_cols,
),
):
yield [rspan, cspan]
spans = list(make_spans(cell))
table_data[i][j] = GlmTableCell(
text=cell.text,
bbox=(
cell.bbox.as_tuple()
if cell.bbox is not None
else None
), # check if this is bottom-left
spans=spans,
obj_type=celltype,
col=j,
row=i,
row_header=cell.row_header,
row_section=cell.row_section,
col_header=cell.column_header,
row_span=[
cell.start_row_offset_idx,
cell.end_row_offset_idx,
],
col_span=[
cell.start_col_offset_idx,
cell.end_col_offset_idx,
],
)
# Compute the caption
caption = item.caption_text(self.document)
tables.append(
DsSchemaTable(
text=caption,
num_cols=item.data.num_cols,
num_rows=item.data.num_rows,
obj_type=layout_label_to_ds_type.get(item.label),
data=table_data,
prov=[
Prov(
bbox=p.bbox.as_tuple(),
page=p.page_no,
span=[0, 0],
)
for p in item.prov
],
)
)
elif isinstance(item, PictureItem):
index = len(figures)
ref_str = f"#/figures/{index}"
main_text.append(
Ref(
name=reverse_label_mapping[item.label],
obj_type=layout_label_to_ds_type.get(item.label),
ref=ref_str,
),
)
# Compute the caption
caption = item.caption_text(self.document)
figures.append(
Figure(
prov=[
Prov(
bbox=p.bbox.as_tuple(),
page=p.page_no,
span=[0, len(caption)],
)
for p in item.prov
],
obj_type=layout_label_to_ds_type.get(item.label),
text=caption,
# data=[[]],
)
)
page_dimensions = [
PageDimensions(page=p.page_no, height=p.size.height, width=p.size.width)
for p in self.document.pages.values()
]
ds_doc = DsDocument(
name=title,
description=desc,
file_info=file_info,
main_text=main_text,
equations=equations,
footnotes=footnotes,
page_headers=page_headers,
page_footers=page_footers,
tables=tables,
figures=figures,
page_dimensions=page_dimensions,
)
return ds_doc
return docling_document_to_legacy(self.document)
class _DummyBackend(AbstractDocumentBackend):

13
poetry.lock generated
View File

@ -888,13 +888,13 @@ files = [
[[package]]
name = "docling-core"
version = "2.8.0"
version = "2.9.0"
description = "A python library to define and validate data types in Docling."
optional = false
python-versions = "<4.0,>=3.9"
files = [
{file = "docling_core-2.8.0-py3-none-any.whl", hash = "sha256:392aad49e25f5fd1d279410118fbd91d9aaab9dd92d043738d20c10c57193d86"},
{file = "docling_core-2.8.0.tar.gz", hash = "sha256:6ac5cbc6f0abcbdf599c2a4b1a3f7b52fd8baebf3c4ebf94d7b7e2ee061a654e"},
{file = "docling_core-2.9.0-py3-none-any.whl", hash = "sha256:b44b077db5d2ac8a900f30a15abe329c165b1f2eb7f1c90d1275c423c1c3d668"},
{file = "docling_core-2.9.0.tar.gz", hash = "sha256:1bf12fe67ee4852330e9bac33fe62b45598ff885481e03a88fa8e1bf48252424"},
]
[package.dependencies]
@ -6061,6 +6061,11 @@ files = [
{file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f60021ec1574e56632be2a36b946f8143bf4e5e6af4a06d85281adc22938e0dd"},
{file = "scikit_learn-1.5.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:394397841449853c2290a32050382edaec3da89e35b3e03d6cc966aebc6a8ae6"},
{file = "scikit_learn-1.5.2-cp312-cp312-win_amd64.whl", hash = "sha256:57cc1786cfd6bd118220a92ede80270132aa353647684efa385a74244a41e3b1"},
{file = "scikit_learn-1.5.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e9a702e2de732bbb20d3bad29ebd77fc05a6b427dc49964300340e4c9328b3f5"},
{file = "scikit_learn-1.5.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:b0768ad641981f5d3a198430a1d31c3e044ed2e8a6f22166b4d546a5116d7908"},
{file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:178ddd0a5cb0044464fc1bfc4cca5b1833bfc7bb022d70b05db8530da4bb3dd3"},
{file = "scikit_learn-1.5.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f7284ade780084d94505632241bf78c44ab3b6f1e8ccab3d2af58e0e950f9c12"},
{file = "scikit_learn-1.5.2-cp313-cp313-win_amd64.whl", hash = "sha256:b7b0f9a0b1040830d38c39b91b3a44e1b643f4b36e36567b80b7c6bd2202a27f"},
{file = "scikit_learn-1.5.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:757c7d514ddb00ae249832fe87100d9c73c6ea91423802872d9e74970a0e40b9"},
{file = "scikit_learn-1.5.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:52788f48b5d8bca5c0736c175fa6bdaab2ef00a8f536cda698db61bd89c551c1"},
{file = "scikit_learn-1.5.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:643964678f4b5fbdc95cbf8aec638acc7aa70f5f79ee2cdad1eec3df4ba6ead8"},
@ -7597,4 +7602,4 @@ tesserocr = ["tesserocr"]
[metadata]
lock-version = "2.0"
python-versions = "^3.9"
content-hash = "621f8de238fd1f82cfd783531b6ab7c1598378a499c0dcfac323d66bc7ab32ea"
content-hash = "3e66a54bd0433581e4909003124e2b79b42bdd1fb90d17c037f3294aeff56aa9"

2
pyproject.toml
View File

@ -25,7 +25,7 @@ packages = [{include = "docling"}]
# actual dependencies:
######################
python = "^3.9"
docling-core = { version = "^2.8.0", extras = ["chunking"] }
docling-core = { version = "^2.9.0", extras = ["chunking"] }
pydantic = "^2.0.0"
docling-ibm-models = "^2.0.6"
deepsearch-glm = "^1.0.0"