docling 1.1.2__tar.gz → 1.2.1__tar.gz

{docling-1.1.2 → docling-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.1.2
+Version: 1.2.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -21,9 +21,11 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: easyocr
 Provides-Extra: ocr
+Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.19.0,<1)
 Requires-Dist: docling-core (>=1.1.2,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.1.0,<2.0.0)
+Requires-Dist: docling-parse (>=0.0.1,<0.0.2)
 Requires-Dist: easyocr (>=1.7,<2.0) ; extra == "easyocr" or extra == "ocr"
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -92,17 +94,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:

{docling-1.1.2 → docling-1.2.1}/README.md

@@ -56,17 +56,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:

{docling-1.1.2 → docling-1.2.1}/docling/backend/abstract_backend.py

@@ -35,7 +35,7 @@ class PdfPageBackend(ABC):
 
 class PdfDocumentBackend(ABC):
     @abstractmethod
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         pass
 
     @abstractmethod

docling-1.2.1/docling/backend/docling_parse_backend.py

@@ -0,0 +1,172 @@
+import random
+from io import BytesIO
+from pathlib import Path
+from typing import Iterable, List, Optional, Union
+
+import pypdfium2 as pdfium
+from docling_parse.docling_parse import pdf_parser
+from PIL import Image, ImageDraw
+from pypdfium2 import PdfPage
+
+from docling.backend.abstract_backend import PdfDocumentBackend, PdfPageBackend
+from docling.datamodel.base_models import BoundingBox, Cell, CoordOrigin, PageSize
+
+
+class DoclingParsePageBackend(PdfPageBackend):
+    def __init__(self, page_obj: PdfPage, docling_page_obj):
+        super().__init__(page_obj)
+        self._ppage = page_obj
+        self._dpage = docling_page_obj
+        self.text_page = None
+
+    def get_text_in_rect(self, bbox: BoundingBox) -> str:
+        # Find intersecting cells on the page
+        text_piece = ""
+        page_size = self.get_size()
+        parser_width = self._dpage["width"]
+        parser_height = self._dpage["height"]
+
+        scale = (
+            1  # FIX - Replace with param in get_text_in_rect across backends (optional)
+        )
+
+        for i in range(len(self._dpage["cells"])):
+            rect = self._dpage["cells"][i]["box"]["device"]
+            x0, y0, x1, y1 = rect
+            cell_bbox = BoundingBox(
+                l=x0 * scale * page_size.width / parser_width,
+                b=y0 * scale * page_size.height / parser_height,
+                r=x1 * scale * page_size.width / parser_width,
+                t=y1 * scale * page_size.height / parser_height,
+                coord_origin=CoordOrigin.BOTTOMLEFT,
+            ).to_top_left_origin(page_size.height * scale)
+
+            overlap_frac = cell_bbox.intersection_area_with(bbox) / cell_bbox.area()
+
+            if overlap_frac > 0.5:
+                if len(text_piece) > 0:
+                    text_piece += " "
+                text_piece += self._dpage["cells"][i]["content"]["rnormalized"]
+
+        return text_piece
+
+    def get_text_cells(self) -> Iterable[Cell]:
+        cells = []
+        cell_counter = 0
+
+        page_size = self.get_size()
+
+        parser_width = self._dpage["width"]
+        parser_height = self._dpage["height"]
+
+        for i in range(len(self._dpage["cells"])):
+            rect = self._dpage["cells"][i]["box"]["device"]
+            x0, y0, x1, y1 = rect
+            text_piece = self._dpage["cells"][i]["content"]["rnormalized"]
+            cells.append(
+                Cell(
+                    id=cell_counter,
+                    text=text_piece,
+                    bbox=BoundingBox(
+                        # l=x0, b=y0, r=x1, t=y1,
+                        l=x0 * page_size.width / parser_width,
+                        b=y0 * page_size.height / parser_height,
+                        r=x1 * page_size.width / parser_width,
+                        t=y1 * page_size.height / parser_height,
+                        coord_origin=CoordOrigin.BOTTOMLEFT,
+                    ).to_top_left_origin(page_size.height),
+                )
+            )
+            cell_counter += 1
+
+        def draw_clusters_and_cells():
+            image = self.get_page_image()
+            draw = ImageDraw.Draw(image)
+            for c in cells:
+                x0, y0, x1, y1 = c.bbox.as_tuple()
+                cell_color = (
+                    random.randint(30, 140),
+                    random.randint(30, 140),
+                    random.randint(30, 140),
+                )
+                draw.rectangle([(x0, y0), (x1, y1)], outline=cell_color)
+            image.show()
+
+        # before merge:
+        # draw_clusters_and_cells()
+
+        # cells = merge_horizontal_cells(cells)
+
+        # after merge:
+        # draw_clusters_and_cells()
+
+        return cells
+
+    def get_page_image(
+        self, scale: int = 1, cropbox: Optional[BoundingBox] = None
+    ) -> Image.Image:
+
+        page_size = self.get_size()
+
+        if not cropbox:
+            cropbox = BoundingBox(
+                l=0,
+                r=page_size.width,
+                t=0,
+                b=page_size.height,
+                coord_origin=CoordOrigin.TOPLEFT,
+            )
+            padbox = BoundingBox(
+                l=0, r=0, t=0, b=0, coord_origin=CoordOrigin.BOTTOMLEFT
+            )
+        else:
+            padbox = cropbox.to_bottom_left_origin(page_size.height)
+            padbox.r = page_size.width - padbox.r
+            padbox.t = page_size.height - padbox.t
+
+        image = (
+            self._ppage.render(
+                scale=scale * 1.5,
+                rotation=0,  # no additional rotation
+                crop=padbox.as_tuple(),
+            )
+            .to_pil()
+            .resize(size=(round(cropbox.width * scale), round(cropbox.height * scale)))
+        )  # We resize the image from 1.5x the given scale to make it sharper.
+
+        return image
+
+    def get_size(self) -> PageSize:
+        return PageSize(width=self._ppage.get_width(), height=self._ppage.get_height())
+
+    def unload(self):
+        self._ppage = None
+        self._dpage = None
+        self.text_page = None
+
+
+class DoclingParseDocumentBackend(PdfDocumentBackend):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
+        super().__init__(path_or_stream)
+        self._pdoc = pdfium.PdfDocument(path_or_stream)
+        # Parsing cells with docling_parser call
+        if isinstance(path_or_stream, BytesIO):
+            raise NotImplemented("This backend does not support byte streams yet.")
+        parser = pdf_parser()
+        self._parser_doc = parser.find_cells(str(path_or_stream))
+
+    def page_count(self) -> int:
+        return len(self._parser_doc["pages"])
+
+    def load_page(self, page_no: int) -> PdfPage:
+        return DoclingParsePageBackend(
+            self._pdoc[page_no], self._parser_doc["pages"][page_no]
+        )
+
+    def is_valid(self) -> bool:
+        return self.page_count() > 0
+
+    def unload(self):
+        self._pdoc.close()
+        self._pdoc = None
+        self._parser_doc = None

{docling-1.1.2 → docling-1.2.1}/docling/backend/pypdfium2_backend.py

@@ -199,7 +199,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
 
 
 class PyPdfiumDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
 

{docling-1.1.2 → docling-1.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.1.2"  # DO NOT EDIT, updated automatically
+version = "1.2.1"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -32,6 +32,8 @@ pydantic-settings = "^2.3.0"
 huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = { version = "^1.7", optional = true }
+docling-parse = "^0.0.1"
+certifi = ">=2024.7.4"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}