docling 2.15.0__py3-none-any.whl → 2.16.0__py3-none-any.whl

docling/models/base_model.py

@@ -1,9 +1,10 @@
 from abc import ABC, abstractmethod
-from typing import Any, Iterable
+from typing import Any, Generic, Iterable, Optional
 
-from docling_core.types.doc import DoclingDocument, NodeItem
+from docling_core.types.doc import BoundingBox, DoclingDocument, NodeItem, TextItem
+from typing_extensions import TypeVar
 
-from docling.datamodel.base_models import Page
+from docling.datamodel.base_models import ItemAndImageEnrichmentElement, Page
 from docling.datamodel.document import ConversionResult
 
 
@@ -15,14 +16,69 @@ class BasePageModel(ABC):
         pass
 
 
-class BaseEnrichmentModel(ABC):
+EnrichElementT = TypeVar("EnrichElementT", default=NodeItem)
+
+
+class GenericEnrichmentModel(ABC, Generic[EnrichElementT]):
 
     @abstractmethod
     def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
         pass
 
+    @abstractmethod
+    def prepare_element(
+        self, conv_res: ConversionResult, element: NodeItem
+    ) -> Optional[EnrichElementT]:
+        pass
+
     @abstractmethod
     def __call__(
-        self, doc: DoclingDocument, element_batch: Iterable[NodeItem]
-    ) -> Iterable[Any]:
+        self, doc: DoclingDocument, element_batch: Iterable[EnrichElementT]
+    ) -> Iterable[NodeItem]:
         pass
+
+
+class BaseEnrichmentModel(GenericEnrichmentModel[NodeItem]):
+
+    def prepare_element(
+        self, conv_res: ConversionResult, element: NodeItem
+    ) -> Optional[NodeItem]:
+        if self.is_processable(doc=conv_res.document, element=element):
+            return element
+        return None
+
+
+class BaseItemAndImageEnrichmentModel(
+    GenericEnrichmentModel[ItemAndImageEnrichmentElement]
+):
+
+    images_scale: float
+    expansion_factor: float = 0.0
+
+    def prepare_element(
+        self, conv_res: ConversionResult, element: NodeItem
+    ) -> Optional[ItemAndImageEnrichmentElement]:
+        if not self.is_processable(doc=conv_res.document, element=element):
+            return None
+
+        assert isinstance(element, TextItem)
+        element_prov = element.prov[0]
+
+        bbox = element_prov.bbox
+        width = bbox.r - bbox.l
+        height = bbox.t - bbox.b
+
+        # TODO: move to a utility in the BoundingBox class
+        expanded_bbox = BoundingBox(
+            l=bbox.l - width * self.expansion_factor,
+            t=bbox.t + height * self.expansion_factor,
+            r=bbox.r + width * self.expansion_factor,
+            b=bbox.b - height * self.expansion_factor,
+            coord_origin=bbox.coord_origin,
+        )
+
+        page_ix = element_prov.page_no - 1
+        cropped_image = conv_res.pages[page_ix].get_image(
+            scale=self.images_scale, cropbox=expanded_bbox
+        )
+        return ItemAndImageEnrichmentElement(item=element, image=cropped_image)

docling/models/base_ocr_model.py

@@ -8,7 +8,7 @@ import numpy as np
 from docling_core.types.doc import BoundingBox, CoordOrigin
 from PIL import Image, ImageDraw
 from rtree import index
-from scipy.ndimage import find_objects, label
+from scipy.ndimage import binary_dilation, find_objects, label
 
 from docling.datamodel.base_models import Cell, OcrCell, Page
 from docling.datamodel.document import ConversionResult
@@ -43,6 +43,12 @@ class BaseOcrModel(BasePageModel):
 
             np_image = np.array(image)
 
+            # Dilate the image by 10 pixels to merge nearby bitmap rectangles
+            structure = np.ones(
+                (20, 20)
+            )  # Create a 20x20 structure element (10 pixels in all directions)
+            np_image = binary_dilation(np_image > 0, structure=structure)
+
             # Find the connected components
             labeled_image, num_features = label(
                 np_image > 0
@@ -72,7 +78,7 @@ class BaseOcrModel(BasePageModel):
             bitmap_rects = []
         coverage, ocr_rects = find_ocr_rects(page.size, bitmap_rects)
 
-        # return full-page rectangle if sufficiently covered with bitmaps
+        # return full-page rectangle if page is dominantly covered with bitmaps
         if self.options.force_full_page_ocr or coverage > max(
             BITMAP_COVERAGE_TRESHOLD, self.options.bitmap_area_threshold
         ):
@@ -85,17 +91,11 @@ class BaseOcrModel(BasePageModel):
                     coord_origin=CoordOrigin.TOPLEFT,
                 )
             ]
-        # return individual rectangles if the bitmap coverage is smaller
-        else:  # coverage <= BITMAP_COVERAGE_TRESHOLD:
-
-            # skip OCR if the bitmap area on the page is smaller than the options threshold
-            ocr_rects = [
-                rect
-                for rect in ocr_rects
-                if rect.area() / (page.size.width * page.size.height)
-                > self.options.bitmap_area_threshold
-            ]
+        # return individual rectangles if the bitmap coverage is above the threshold
+        elif coverage > self.options.bitmap_area_threshold:
             return ocr_rects
+        else:  # overall coverage of bitmaps is too low, drop all bitmap rectangles.
+            return []
 
     # Filters OCR cells by dropping any OCR cell that intersects with an existing programmatic cell.
     def _filter_ocr_cells(self, ocr_cells, programmatic_cells):
@@ -162,6 +162,9 @@ class BaseOcrModel(BasePageModel):
             x0 *= scale_x
             x1 *= scale_x
 
+            if y1 <= y0:
+                y1, y0 = y0, y1
+
             color = "gray"
             if isinstance(tc, OcrCell):
                 color = "magenta"

docling/models/code_formula_model.py

@@ -0,0 +1,245 @@
+import re
+from pathlib import Path
+from typing import Iterable, List, Literal, Optional, Tuple, Union
+
+from docling_core.types.doc import (
+    CodeItem,
+    DocItemLabel,
+    DoclingDocument,
+    NodeItem,
+    TextItem,
+)
+from docling_core.types.doc.labels import CodeLanguageLabel
+from PIL import Image
+from pydantic import BaseModel
+
+from docling.datamodel.base_models import ItemAndImageEnrichmentElement
+from docling.datamodel.pipeline_options import AcceleratorOptions
+from docling.models.base_model import BaseItemAndImageEnrichmentModel
+from docling.utils.accelerator_utils import decide_device
+
+
+class CodeFormulaModelOptions(BaseModel):
+    """
+    Configuration options for the CodeFormulaModel.
+
+    Attributes
+    ----------
+    kind : str
+        Type of the model. Fixed value "code_formula".
+    do_code_enrichment : bool
+        True if code enrichment is enabled, False otherwise.
+    do_formula_enrichment : bool
+        True if formula enrichment is enabled, False otherwise.
+    """
+
+    kind: Literal["code_formula"] = "code_formula"
+    do_code_enrichment: bool = True
+    do_formula_enrichment: bool = True
+
+
+class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
+    """
+    Model for processing and enriching documents with code and formula predictions.
+
+    Attributes
+    ----------
+    enabled : bool
+        True if the model is enabled, False otherwise.
+    options : CodeFormulaModelOptions
+        Configuration options for the CodeFormulaModel.
+    code_formula_model : CodeFormulaPredictor
+        The predictor model for code and formula processing.
+
+    Methods
+    -------
+    __init__(self, enabled, artifacts_path, accelerator_options, code_formula_options)
+        Initializes the CodeFormulaModel with the given configuration options.
+    is_processable(self, doc, element)
+        Determines if a given element in a document can be processed by the model.
+    __call__(self, doc, element_batch)
+        Processes the given batch of elements and enriches them with predictions.
+    """
+
+    images_scale = 1.66  # = 120 dpi, aligned with training data resolution
+    expansion_factor = 0.03
+
+    def __init__(
+        self,
+        enabled: bool,
+        artifacts_path: Optional[Union[Path, str]],
+        options: CodeFormulaModelOptions,
+        accelerator_options: AcceleratorOptions,
+    ):
+        """
+        Initializes the CodeFormulaModel with the given configuration.
+
+        Parameters
+        ----------
+        enabled : bool
+            True if the model is enabled, False otherwise.
+        artifacts_path : Path
+            Path to the directory containing the model artifacts.
+        options : CodeFormulaModelOptions
+            Configuration options for the model.
+        accelerator_options : AcceleratorOptions
+            Options specifying the device and number of threads for acceleration.
+        """
+        self.enabled = enabled
+        self.options = options
+
+        if self.enabled:
+            device = decide_device(accelerator_options.device)
+
+            from docling_ibm_models.code_formula_model.code_formula_predictor import (
+                CodeFormulaPredictor,
+            )
+
+            if artifacts_path is None:
+                artifacts_path = self.download_models_hf()
+            else:
+                artifacts_path = Path(artifacts_path)
+
+            self.code_formula_model = CodeFormulaPredictor(
+                artifacts_path=artifacts_path,
+                device=device,
+                num_threads=accelerator_options.num_threads,
+            )
+
+    @staticmethod
+    def download_models_hf(
+        local_dir: Optional[Path] = None, force: bool = False
+    ) -> Path:
+        from huggingface_hub import snapshot_download
+        from huggingface_hub.utils import disable_progress_bars
+
+        disable_progress_bars()
+        download_path = snapshot_download(
+            repo_id="ds4sd/CodeFormula",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v1.0.0",
+        )
+
+        return Path(download_path)
+
+    def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
+        """
+        Determines if a given element in a document can be processed by the model.
+
+        Parameters
+        ----------
+        doc : DoclingDocument
+            The document being processed.
+        element : NodeItem
+            The element within the document to check.
+
+        Returns
+        -------
+        bool
+            True if the element can be processed, False otherwise.
+        """
+        return self.enabled and (
+            (isinstance(element, CodeItem) and self.options.do_code_enrichment)
+            or (
+                isinstance(element, TextItem)
+                and element.label == DocItemLabel.FORMULA
+                and self.options.do_formula_enrichment
+            )
+        )
+
+    def _extract_code_language(self, input_string: str) -> Tuple[str, Optional[str]]:
+        """Extracts a programming language from the beginning of a string.
+
+        This function checks if the input string starts with a pattern of the form
+        ``<_some_language_>``. If it does, it extracts the language string and returns
+        a tuple of (remainder, language). Otherwise, it returns the original string
+        and `None`.
+
+        Args:
+            input_string (str): The input string, which may start with ``<_language_>``.
+
+        Returns:
+            Tuple[str, Optional[str]]:
+                A tuple where:
+                - The first element is either:
+                    - The remainder of the string (everything after ``<_language_>``),
+                    if a match is found; or
+                    - The original string, if no match is found.
+                - The second element is the extracted language if a match is found;
+                otherwise, `None`.
+        """
+        pattern = r"^<_([^>]+)_>\s*(.*)"
+        match = re.match(pattern, input_string, flags=re.DOTALL)
+        if match:
+            language = str(match.group(1))  # the captured programming language
+            remainder = str(match.group(2))  # everything after the <_language_>
+            return remainder, language
+        else:
+            return input_string, None
+
+    def _get_code_language_enum(self, value: Optional[str]) -> CodeLanguageLabel:
+        """
+        Converts a string to a corresponding `CodeLanguageLabel` enum member.
+
+        If the provided string does not match any value in `CodeLanguageLabel`,
+        it defaults to `CodeLanguageLabel.UNKNOWN`.
+
+        Args:
+            value (Optional[str]): The string representation of the code language or None.
+
+        Returns:
+            CodeLanguageLabel: The corresponding enum member if the value is valid,
+            otherwise `CodeLanguageLabel.UNKNOWN`.
+        """
+        if not isinstance(value, str):
+            return CodeLanguageLabel.UNKNOWN
+
+        try:
+            return CodeLanguageLabel(value)
+        except ValueError:
+            return CodeLanguageLabel.UNKNOWN
+
+    def __call__(
+        self,
+        doc: DoclingDocument,
+        element_batch: Iterable[ItemAndImageEnrichmentElement],
+    ) -> Iterable[NodeItem]:
+        """
+        Processes the given batch of elements and enriches them with predictions.
+
+        Parameters
+        ----------
+        doc : DoclingDocument
+            The document being processed.
+        element_batch : Iterable[ItemAndImageEnrichmentElement]
+            A batch of elements to be processed.
+
+        Returns
+        -------
+        Iterable[Any]
+            An iterable of enriched elements.
+        """
+        if not self.enabled:
+            for element in element_batch:
+                yield element.item
+            return
+
+        labels: List[str] = []
+        images: List[Image.Image] = []
+        elements: List[TextItem] = []
+        for el in element_batch:
+            assert isinstance(el.item, TextItem)
+            elements.append(el.item)
+            labels.append(el.item.label)
+            images.append(el.image)
+
+        outputs = self.code_formula_model.predict(images, labels)
+
+        for item, output in zip(elements, outputs):
+            if isinstance(item, CodeItem):
+                output, code_language = self._extract_code_language(output)
+                item.code_language = self._get_code_language_enum(code_language)
+            item.text = output
+
+            yield item

docling/models/document_picture_classifier.py

@@ -0,0 +1,187 @@
+from pathlib import Path
+from typing import Iterable, List, Literal, Optional, Tuple, Union
+
+from docling_core.types.doc import (
+    DoclingDocument,
+    NodeItem,
+    PictureClassificationClass,
+    PictureClassificationData,
+    PictureItem,
+)
+from PIL import Image
+from pydantic import BaseModel
+
+from docling.datamodel.pipeline_options import AcceleratorOptions
+from docling.models.base_model import BaseEnrichmentModel
+from docling.utils.accelerator_utils import decide_device
+
+
+class DocumentPictureClassifierOptions(BaseModel):
+    """
+    Options for configuring the DocumentPictureClassifier.
+
+    Attributes
+    ----------
+    kind : Literal["document_picture_classifier"]
+        Identifier for the type of classifier.
+    """
+
+    kind: Literal["document_picture_classifier"] = "document_picture_classifier"
+
+
+class DocumentPictureClassifier(BaseEnrichmentModel):
+    """
+    A model for classifying pictures in documents.
+
+    This class enriches document pictures with predicted classifications
+    based on a predefined set of classes.
+
+    Attributes
+    ----------
+    enabled : bool
+        Whether the classifier is enabled for use.
+    options : DocumentPictureClassifierOptions
+        Configuration options for the classifier.
+    document_picture_classifier : DocumentPictureClassifierPredictor
+        The underlying prediction model, loaded if the classifier is enabled.
+
+    Methods
+    -------
+    __init__(enabled, artifacts_path, options, accelerator_options)
+        Initializes the classifier with specified configurations.
+    is_processable(doc, element)
+        Checks if the given element can be processed by the classifier.
+    __call__(doc, element_batch)
+        Processes a batch of elements and adds classification annotations.
+    """
+
+    images_scale = 2
+
+    def __init__(
+        self,
+        enabled: bool,
+        artifacts_path: Optional[Union[Path, str]],
+        options: DocumentPictureClassifierOptions,
+        accelerator_options: AcceleratorOptions,
+    ):
+        """
+        Initializes the DocumentPictureClassifier.
+
+        Parameters
+        ----------
+        enabled : bool
+            Indicates whether the classifier is enabled.
+        artifacts_path : Optional[Union[Path, str]],
+            Path to the directory containing model artifacts.
+        options : DocumentPictureClassifierOptions
+            Configuration options for the classifier.
+        accelerator_options : AcceleratorOptions
+            Options for configuring the device and parallelism.
+        """
+        self.enabled = enabled
+        self.options = options
+
+        if self.enabled:
+            device = decide_device(accelerator_options.device)
+            from docling_ibm_models.document_figure_classifier_model.document_figure_classifier_predictor import (
+                DocumentFigureClassifierPredictor,
+            )
+
+            if artifacts_path is None:
+                artifacts_path = self.download_models_hf()
+            else:
+                artifacts_path = Path(artifacts_path)
+
+            self.document_picture_classifier = DocumentFigureClassifierPredictor(
+                artifacts_path=artifacts_path,
+                device=device,
+                num_threads=accelerator_options.num_threads,
+            )
+
+    @staticmethod
+    def download_models_hf(
+        local_dir: Optional[Path] = None, force: bool = False
+    ) -> Path:
+        from huggingface_hub import snapshot_download
+        from huggingface_hub.utils import disable_progress_bars
+
+        disable_progress_bars()
+        download_path = snapshot_download(
+            repo_id="ds4sd/DocumentFigureClassifier",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v1.0.0",
+        )
+
+        return Path(download_path)
+
+    def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
+        """
+        Determines if the given element can be processed by the classifier.
+
+        Parameters
+        ----------
+        doc : DoclingDocument
+            The document containing the element.
+        element : NodeItem
+            The element to be checked.
+
+        Returns
+        -------
+        bool
+            True if the element is a PictureItem and processing is enabled; False otherwise.
+        """
+        return self.enabled and isinstance(element, PictureItem)
+
+    def __call__(
+        self,
+        doc: DoclingDocument,
+        element_batch: Iterable[NodeItem],
+    ) -> Iterable[NodeItem]:
+        """
+        Processes a batch of elements and enriches them with classification predictions.
+
+        Parameters
+        ----------
+        doc : DoclingDocument
+            The document containing the elements to be processed.
+        element_batch : Iterable[NodeItem]
+            A batch of pictures to classify.
+
+        Returns
+        -------
+        Iterable[NodeItem]
+            An iterable of NodeItem objects after processing. The field
+            'data.classification' is added containing the classification for each picture.
+        """
+        if not self.enabled:
+            for element in element_batch:
+                yield element
+            return
+
+        images: List[Image.Image] = []
+        elements: List[PictureItem] = []
+        for el in element_batch:
+            assert isinstance(el, PictureItem)
+            elements.append(el)
+            img = el.get_image(doc)
+            assert img is not None
+            images.append(img)
+
+        outputs = self.document_picture_classifier.predict(images)
+
+        for element, output in zip(elements, outputs):
+            element.annotations.append(
+                PictureClassificationData(
+                    provenance="DocumentPictureClassifier",
+                    predicted_classes=[
+                        PictureClassificationClass(
+                            class_name=pred[0],
+                            confidence=pred[1],
+                        )
+                        for pred in output
+                    ],
+                )
+            )
+
+            yield element