Skip to content

Commit

Permalink
Merge branch 'main' into nli/performance_main
Browse files Browse the repository at this point in the history 
Signed-off-by: Nikos Livathinos <[email protected]>
  • Loading branch information
@nikos-livathinos
nikos-livathinos committed Dec 13, 2024
2 parents 30dbab5 + 365a1e7 commit 6209cf3
Show file tree
Hide file tree
Showing 17 changed files with 575 additions and 884 deletions.
27 changes: 27 additions & 0 deletions CHANGELOG.md
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,30 @@
## [v2.11.0](https://github.com/DS4SD/docling/releases/tag/v2.11.0) - 2024-12-12

### Feature

* Add timeout limit to document parsing job. DS4SD#270 ([#552](https://github.com/DS4SD/docling/issues/552)) ([`3da166e`](https://github.com/DS4SD/docling/commit/3da166eafa3c119de961510341cb92397652c222))

### Fix

* Do not import python modules from deepsearch-glm ([#569](https://github.com/DS4SD/docling/issues/569)) ([`aee9c0b`](https://github.com/DS4SD/docling/commit/aee9c0b324a07190ad03ad3a6266e76c465d4cdf))
* Handle no result from RapidOcr reader ([#558](https://github.com/DS4SD/docling/issues/558)) ([`f45499c`](https://github.com/DS4SD/docling/commit/f45499ce9349fe55538dfb36d74c395e9193d9b1))
* Make enum serializable with human-readable value ([#555](https://github.com/DS4SD/docling/issues/555)) ([`a7df337`](https://github.com/DS4SD/docling/commit/a7df337654fa5fa7633af8740fb5e4cc4a06f250))

### Documentation

* Update chunking usage docs, minor reorg ([#550](https://github.com/DS4SD/docling/issues/550)) ([`d0c9e8e`](https://github.com/DS4SD/docling/commit/d0c9e8e508d7edef5e733be6cdea2cea0a9a0695))

## [v2.10.0](https://github.com/DS4SD/docling/releases/tag/v2.10.0) - 2024-12-09

### Feature

* Docling-parse v2 as default PDF backend ([#549](https://github.com/DS4SD/docling/issues/549)) ([`aca57f0`](https://github.com/DS4SD/docling/commit/aca57f0527dddcc027dc1ee840e2e492ab997170))

### Fix

* Call into docling-core for legacy document transform ([#551](https://github.com/DS4SD/docling/issues/551)) ([`7972d47`](https://github.com/DS4SD/docling/commit/7972d47f88604f02d6a32527116c4d78eb1005e2))
* Introduce Image format options in CLI. Silence the tqdm downloading messages. ([#544](https://github.com/DS4SD/docling/issues/544)) ([`78f61a8`](https://github.com/DS4SD/docling/commit/78f61a8522d3a19ecc1d605e8441fb543ca0fa96))

## [v2.9.0](https://github.com/DS4SD/docling/releases/tag/v2.9.0) - 2024-12-09

### Feature
Expand Down
26 changes: 10 additions & 16 deletions docling/cli/main.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,10 @@
AcceleratorDevice,
AcceleratorOptions,
EasyOcrOptions,
OcrEngine,
OcrMacOptions,
OcrOptions,
PdfBackend,
PdfPipelineOptions,
RapidOcrOptions,
TableFormerMode,
Expand Down Expand Up @@ -70,22 +72,6 @@ def version_callback(value: bool):
raise typer.Exit()


# Define an enum for the backend options
class PdfBackend(str, Enum):
PYPDFIUM2 = "pypdfium2"
DLPARSE_V1 = "dlparse_v1"
DLPARSE_V2 = "dlparse_v2"


# Define an enum for the ocr engines
class OcrEngine(str, Enum):
EASYOCR = "easyocr"
TESSERACT_CLI = "tesseract_cli"
TESSERACT = "tesseract"
OCRMAC = "ocrmac"
RAPIDOCR = "rapidocr"


def export_documents(
conv_results: Iterable[ConversionResult],
output_dir: Path,
Expand Down Expand Up @@ -266,6 +252,13 @@ def convert(
help="Show version information.",
),
] = None,
document_timeout: Annotated[
Optional[float],
typer.Option(
...,
help="The timeout for processing each document, in seconds.",
),
] = None,
num_threads: Annotated[int, typer.Option(..., help="Number of threads")] = 4,
device: Annotated[
AcceleratorDevice, typer.Option(..., help="Accelerator device")
Expand Down Expand Up @@ -355,6 +348,7 @@ def convert(
do_ocr=ocr,
ocr_options=ocr_options,
do_table_structure=True,
document_timeout=document_timeout,
)
pipeline_options.table_structure_options.do_cell_matching = (
True # do_cell_matching
Expand Down
24 changes: 12 additions & 12 deletions docling/datamodel/base_models.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -19,12 +19,12 @@


class ConversionStatus(str, Enum):
PENDING = auto()
STARTED = auto()
FAILURE = auto()
SUCCESS = auto()
PARTIAL_SUCCESS = auto()
SKIPPED = auto()
PENDING = "pending"
STARTED = "started"
FAILURE = "failure"
SUCCESS = "success"
PARTIAL_SUCCESS = "partial_success"
SKIPPED = "skipped"


class InputFormat(str, Enum):
Expand Down Expand Up @@ -89,15 +89,15 @@ class OutputFormat(str, Enum):


class DocInputType(str, Enum):
PATH = auto()
STREAM = auto()
PATH = "path"
STREAM = "stream"


class DoclingComponentType(str, Enum):
DOCUMENT_BACKEND = auto()
MODEL = auto()
DOC_ASSEMBLER = auto()
USER_INPUT = auto()
DOCUMENT_BACKEND = "document_backend"
MODEL = "model"
DOC_ASSEMBLER = "doc_assembler"
USER_INPUT = "user_input"


class ErrorItem(BaseModel):
Expand Down
255 changes: 2 additions & 253 deletions docling/datamodel/document.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@
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

Expand Down Expand Up @@ -191,259 +192,7 @@ 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):
Expand Down
Loading

0 comments on commit 6209cf3

Please sign in to comment.