docling 2.33.0__py3-none-any.whl → 2.35.0__py3-none-any.whl

docling/backend/docling_parse_backend.py

@@ -60,7 +60,7 @@ class DoclingParsePageBackend(PdfPageBackend):
                 coord_origin=CoordOrigin.BOTTOMLEFT,
             ).to_top_left_origin(page_height=page_size.height * scale)
 
-            overlap_frac = cell_bbox.intersection_area_with(bbox) / cell_bbox.area()
+            overlap_frac = cell_bbox.intersection_over_self(bbox)
 
             if overlap_frac > 0.5:
                 if len(text_piece) > 0:

docling/backend/docling_parse_v2_backend.py

@@ -71,7 +71,7 @@ class DoclingParseV2PageBackend(PdfPageBackend):
                 coord_origin=CoordOrigin.BOTTOMLEFT,
             ).to_top_left_origin(page_height=page_size.height * scale)
 
-            overlap_frac = cell_bbox.intersection_area_with(bbox) / cell_bbox.area()
+            overlap_frac = cell_bbox.intersection_over_self(bbox)
 
             if overlap_frac > 0.5:
                 if len(text_piece) > 0:

docling/backend/docling_parse_v4_backend.py

@@ -46,7 +46,7 @@ class DoclingParseV4PageBackend(PdfPageBackend):
                 .scaled(scale)
             )
 
-            overlap_frac = cell_bbox.intersection_area_with(bbox) / cell_bbox.area()
+            overlap_frac = cell_bbox.intersection_over_self(bbox)
 
             if overlap_frac > 0.5:
                 if len(text_piece) > 0:

docling/cli/main.py

@@ -12,6 +12,12 @@ from typing import Annotated, Dict, List, Optional, Type
 
 import rich.table
 import typer
+from docling_core.transforms.serializer.html import (
+    HTMLDocSerializer,
+    HTMLOutputStyle,
+    HTMLParams,
+)
+from docling_core.transforms.visualizer.layout_visualizer import LayoutVisualizer
 from docling_core.types.doc import ImageRefMode
 from docling_core.utils.file import resolve_source_to_path
 from pydantic import TypeAdapter
@@ -156,6 +162,7 @@ def export_documents(
     export_json: bool,
     export_html: bool,
     export_html_split_page: bool,
+    show_layout: bool,
     export_md: bool,
     export_txt: bool,
     export_doctags: bool,
@@ -189,9 +196,27 @@ def export_documents(
             if export_html_split_page:
                 fname = output_dir / f"{doc_filename}.html"
                 _log.info(f"writing HTML output to {fname}")
-                conv_res.document.save_as_html(
-                    filename=fname, image_mode=image_export_mode, split_page_view=True
-                )
+                if show_layout:
+                    ser = HTMLDocSerializer(
+                        doc=conv_res.document,
+                        params=HTMLParams(
+                            image_mode=image_export_mode,
+                            output_style=HTMLOutputStyle.SPLIT_PAGE,
+                        ),
+                    )
+                    visualizer = LayoutVisualizer()
+                    visualizer.params.show_label = False
+                    ser_res = ser.serialize(
+                        visualizer=visualizer,
+                    )
+                    with open(fname, "w") as fw:
+                        fw.write(ser_res.text)
+                else:
+                    conv_res.document.save_as_html(
+                        filename=fname,
+                        image_mode=image_export_mode,
+                        split_page_view=True,
+                    )
 
             # Export Text format:
             if export_txt:
@@ -250,6 +275,13 @@ def convert(  # noqa: C901
     to_formats: List[OutputFormat] = typer.Option(
         None, "--to", help="Specify output formats. Defaults to Markdown."
     ),
+    show_layout: Annotated[
+        bool,
+        typer.Option(
+            ...,
+            help="If enabled, the page images will show the bounding-boxes of the items.",
+        ),
+    ] = False,
     headers: str = typer.Option(
         None,
         "--headers",
@@ -596,6 +628,7 @@ def convert(  # noqa: C901
             export_json=export_json,
             export_html=export_html,
             export_html_split_page=export_html_split_page,
+            show_layout=show_layout,
             export_md=export_md,
             export_txt=export_txt,
             export_doctags=export_doctags,

docling/datamodel/base_models.py

@@ -1,6 +1,9 @@
+import math
+from collections import defaultdict
 from enum import Enum
-from typing import TYPE_CHECKING, Dict, List, Optional, Union
+from typing import TYPE_CHECKING, Annotated, Dict, List, Literal, Optional, Union
 
+import numpy as np
 from docling_core.types.doc import (
     BoundingBox,
     DocItemLabel,
@@ -16,7 +19,7 @@ from docling_core.types.io import (
     DocumentStream,
 )
 from PIL.Image import Image
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field, computed_field
 
 if TYPE_CHECKING:
     from docling.backend.pdf_backend import PdfPageBackend
@@ -298,3 +301,97 @@ class OpenAiApiResponse(BaseModel):
     choices: List[OpenAiResponseChoice]
     created: int
     usage: OpenAiResponseUsage
+
+
+# Create a type alias for score values
+ScoreValue = float
+
+
+class QualityGrade(str, Enum):
+    POOR = "poor"
+    FAIR = "fair"
+    GOOD = "good"
+    EXCELLENT = "excellent"
+    UNSPECIFIED = "unspecified"
+
+
+class PageConfidenceScores(BaseModel):
+    parse_score: ScoreValue = np.nan
+    layout_score: ScoreValue = np.nan
+    table_score: ScoreValue = np.nan
+    ocr_score: ScoreValue = np.nan
+
+    def _score_to_grade(self, score: ScoreValue) -> QualityGrade:
+        if score < 0.5:
+            return QualityGrade.POOR
+        elif score < 0.8:
+            return QualityGrade.FAIR
+        elif score < 0.9:
+            return QualityGrade.GOOD
+        elif score >= 0.9:
+            return QualityGrade.EXCELLENT
+
+        return QualityGrade.UNSPECIFIED
+
+    @computed_field  # type: ignore
+    @property
+    def mean_grade(self) -> QualityGrade:
+        return self._score_to_grade(self.mean_score)
+
+    @computed_field  # type: ignore
+    @property
+    def low_grade(self) -> QualityGrade:
+        return self._score_to_grade(self.low_score)
+
+    @computed_field  # type: ignore
+    @property
+    def mean_score(self) -> ScoreValue:
+        return ScoreValue(
+            np.nanmean(
+                [
+                    self.ocr_score,
+                    self.table_score,
+                    self.layout_score,
+                    self.parse_score,
+                ]
+            )
+        )
+
+    @computed_field  # type: ignore
+    @property
+    def low_score(self) -> ScoreValue:
+        return ScoreValue(
+            np.nanquantile(
+                [
+                    self.ocr_score,
+                    self.table_score,
+                    self.layout_score,
+                    self.parse_score,
+                ],
+                q=0.05,
+            )
+        )
+
+
+class ConfidenceReport(PageConfidenceScores):
+    pages: Dict[int, PageConfidenceScores] = Field(
+        default_factory=lambda: defaultdict(PageConfidenceScores)
+    )
+
+    @computed_field  # type: ignore
+    @property
+    def mean_score(self) -> ScoreValue:
+        return ScoreValue(
+            np.nanmean(
+                [c.mean_score for c in self.pages.values()],
+            )
+        )
+
+    @computed_field  # type: ignore
+    @property
+    def low_score(self) -> ScoreValue:
+        return ScoreValue(
+            np.nanmean(
+                [c.low_score for c in self.pages.values()],
+            )
+        )

docling/datamodel/document.py

@@ -47,7 +47,7 @@ from docling_core.types.legacy_doc.document import (
 )
 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 pydantic import BaseModel, Field
 from typing_extensions import deprecated
 
 from docling.backend.abstract_backend import (
@@ -56,6 +56,7 @@ from docling.backend.abstract_backend import (
 )
 from docling.datamodel.base_models import (
     AssembledUnit,
+    ConfidenceReport,
     ConversionStatus,
     DocumentStream,
     ErrorItem,
@@ -201,6 +202,7 @@ class ConversionResult(BaseModel):
     pages: List[Page] = []
     assembled: AssembledUnit = AssembledUnit()
     timings: Dict[str, ProfilingItem] = {}
+    confidence: ConfidenceReport = Field(default_factory=ConfidenceReport)
 
     document: DoclingDocument = _EMPTY_DOCLING_DOC
 
@@ -332,9 +334,9 @@ class _DocumentConversionInput(BaseModel):
     ) -> Optional[InputFormat]:
         """Guess the input format of a document by checking part of its content."""
         input_format: Optional[InputFormat] = None
-        content_str = content.decode("utf-8")
 
         if mime == "application/xml":
+            content_str = content.decode("utf-8")
             match_doctype = re.search(r"<!DOCTYPE [^>]+>", content_str)
             if match_doctype:
                 xml_doctype = match_doctype.group()
@@ -356,6 +358,7 @@ class _DocumentConversionInput(BaseModel):
                     input_format = InputFormat.XML_JATS
 
         elif mime == "text/plain":
+            content_str = content.decode("utf-8")
             if InputFormat.XML_USPTO in formats and content_str.startswith("PATN\r\n"):
                 input_format = InputFormat.XML_USPTO
 
@@ -409,7 +412,11 @@ class _DocumentConversionInput(BaseModel):
             else:
                 return "application/xml"
 
-        if re.match(r"<!doctype\s+html|<html|<head|<body", content_str):
+        if re.match(
+            r"(<script.*?>.*?</script>\s*)?(<!doctype\s+html|<html|<head|<body)",
+            content_str,
+            re.DOTALL,
+        ):
             return "text/html"
 
         p = re.compile(

docling/models/layout_model.py

@@ -5,6 +5,7 @@ from collections.abc import Iterable
 from pathlib import Path
 from typing import Optional
 
+import numpy as np
 from docling_core.types.doc import DocItemLabel
 from docling_ibm_models.layoutmodel.layout_predictor import LayoutPredictor
 from PIL import Image
@@ -184,6 +185,24 @@ class LayoutModel(BasePageModel):
                     ).postprocess()
                     # processed_clusters, processed_cells = clusters, page.cells
 
+                    with warnings.catch_warnings():
+                        warnings.filterwarnings(
+                            "ignore",
+                            "Mean of empty slice|invalid value encountered in scalar divide",
+                            RuntimeWarning,
+                            "numpy",
+                        )
+
+                        conv_res.confidence.pages[page.page_no].layout_score = float(
+                            np.mean([c.confidence for c in processed_clusters])
+                        )
+
+                        conv_res.confidence.pages[page.page_no].ocr_score = float(
+                            np.mean(
+                                [c.confidence for c in processed_cells if c.from_ocr]
+                            )
+                        )
+
                     page.cells = processed_cells
                     page.predictions.layout = LayoutPrediction(
                         clusters=processed_clusters

docling/models/page_assemble_model.py

@@ -3,6 +3,7 @@ import re
 from collections.abc import Iterable
 from typing import List
 
+import numpy as np
 from pydantic import BaseModel
 
 from docling.datamodel.base_models import (

docling/models/page_preprocessing_model.py

@@ -1,7 +1,10 @@
+import re
+import warnings
 from collections.abc import Iterable
 from pathlib import Path
 from typing import Optional
 
+import numpy as np
 from PIL import ImageDraw
 from pydantic import BaseModel
 
@@ -21,6 +24,14 @@ class PagePreprocessingModel(BasePageModel):
     def __init__(self, options: PagePreprocessingOptions):
         self.options = options
 
+        # Pre-compiled regex patterns for efficiency
+        self.GLYPH_RE = re.compile(r"GLYPH<[0-9A-Fa-f]+>")
+        self.SLASH_G_RE = re.compile(r"(?:/G\d+){2,}")
+        self.FRAG_RE = re.compile(r"\b[A-Za-z](?:/[a-z]{1,3}\.[a-z]{1,3}){2,}\b")
+        self.SLASH_NUMBER_GARBAGE_RE = re.compile(
+            r"(?:/\w+\s*){2,}"
+        )  # Two or more "/token " sequences
+
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
@@ -60,6 +71,22 @@ class PagePreprocessingModel(BasePageModel):
         if self.options.create_parsed_page:
             page.parsed_page = page._backend.get_segmented_page()
 
+        # Rate the text quality from the PDF parser, and aggregate on page
+        text_scores = []
+        for c in page.cells:
+            score = self.rate_text_quality(c.text)
+            text_scores.append(score)
+
+        with warnings.catch_warnings():
+            warnings.filterwarnings(
+                "ignore", "Mean of empty slice", RuntimeWarning, "numpy"
+            )
+            conv_res.confidence.pages[page.page_no].parse_score = float(
+                np.nanquantile(
+                    text_scores, q=0.10
+                )  # To emphasise problems in the parse_score, we take the 10% percentile score of all text cells.
+            )
+
         # DEBUG code:
         def draw_text_boxes(image, cells, show: bool = False):
             draw = ImageDraw.Draw(image)
@@ -88,3 +115,30 @@ class PagePreprocessingModel(BasePageModel):
             draw_text_boxes(page.get_image(scale=1.0), page.cells)
 
         return page
+
+    def rate_text_quality(self, text: str) -> float:
+        # Hard errors: if any of these patterns are found, return 0.0 immediately.
+        blacklist_chars = ["�"]
+        if (
+            any(text.find(c) >= 0 for c in blacklist_chars)
+            or self.GLYPH_RE.search(text)
+            or self.SLASH_G_RE.search(text)
+            or self.SLASH_NUMBER_GARBAGE_RE.match(
+                text
+            )  # Check if text is mostly slash-number pattern
+        ):
+            return 0.0
+
+        penalty = 0.0
+
+        # Apply a penalty only if the fragmented words pattern occurs at least three times.
+        frag_matches = self.FRAG_RE.findall(text)
+        if len(frag_matches) >= 3:
+            penalty += 0.1 * len(frag_matches)
+
+        # Additional heuristic: if the average token length is below 2, add a penalty.
+        # tokens = text.split()
+        # if tokens and (sum(map(len, tokens)) / len(tokens)) < 2:
+        #    penalty += 0.2
+
+        return max(1.0 - penalty, 0.0)

docling/models/tesseract_ocr_cli_model.py

@@ -2,6 +2,7 @@ import csv
 import io
 import logging
 import os
+import subprocess
 import tempfile
 from collections.abc import Iterable
 from pathlib import Path
@@ -10,7 +11,7 @@ from typing import List, Optional, Tuple, Type
 
 import pandas as pd
 from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_core.types.doc.page import BoundingRectangle, TextCell
+from docling_core.types.doc.page import TextCell
 
 from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
@@ -21,7 +22,11 @@ from docling.datamodel.pipeline_options import (
 )
 from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.ocr_utils import map_tesseract_script
+from docling.utils.ocr_utils import (
+    map_tesseract_script,
+    parse_tesseract_orientation,
+    tesseract_box_to_bounding_rectangle,
+)
 from docling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
@@ -49,6 +54,7 @@ class TesseractOcrCliModel(BaseOcrModel):
         self._version: Optional[str] = None
         self._tesseract_languages: Optional[List[str]] = None
         self._script_prefix: Optional[str] = None
+        self._is_auto: bool = "auto" in self.options.lang
 
         if self.enabled:
             try:
@@ -93,14 +99,13 @@ class TesseractOcrCliModel(BaseOcrModel):
 
         return name, version
 
-    def _run_tesseract(self, ifilename: str):
+    def _run_tesseract(self, ifilename: str, osd: pd.DataFrame):
         r"""
         Run tesseract CLI
         """
         cmd = [self.options.tesseract_cmd]
-
-        if "auto" in self.options.lang:
-            lang = self._detect_language(ifilename)
+        if self._is_auto:
+            lang = self._parse_language(osd)
             if lang is not None:
                 cmd.append("-l")
                 cmd.append(lang)
@@ -115,13 +120,12 @@ class TesseractOcrCliModel(BaseOcrModel):
         cmd += [ifilename, "stdout", "tsv"]
         _log.info("command: {}".format(" ".join(cmd)))
 
-        proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
-        output, _ = proc.communicate()
+        output = subprocess.run(cmd, stdout=PIPE, stderr=DEVNULL, check=True)
 
         # _log.info(output)
 
         # Decode the byte string to a regular string
-        decoded_data = output.decode("utf-8")
+        decoded_data = output.stdout.decode("utf-8")
         # _log.info(decoded_data)
 
         # Read the TSV file generated by Tesseract
@@ -139,22 +143,24 @@ class TesseractOcrCliModel(BaseOcrModel):
 
         return df_filtered
 
-    def _detect_language(self, ifilename: str):
+    def _perform_osd(self, ifilename: str) -> pd.DataFrame:
         r"""
         Run tesseract in PSM 0 mode to detect the language
         """
-        assert self._tesseract_languages is not None
 
         cmd = [self.options.tesseract_cmd]
         cmd.extend(["--psm", "0", "-l", "osd", ifilename, "stdout"])
         _log.info("command: {}".format(" ".join(cmd)))
-        proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
-        output, _ = proc.communicate()
-        decoded_data = output.decode("utf-8")
+        output = subprocess.run(cmd, capture_output=True, check=True)
+        decoded_data = output.stdout.decode("utf-8")
         df_detected = pd.read_csv(
             io.StringIO(decoded_data), sep=":", header=None, names=["key", "value"]
         )
-        scripts = df_detected.loc[df_detected["key"] == "Script"].value.tolist()
+        return df_detected
+
+    def _parse_language(self, df_osd: pd.DataFrame) -> Optional[str]:
+        assert self._tesseract_languages is not None
+        scripts = df_osd.loc[df_osd["key"] == "Script"].value.tolist()
         if len(scripts) == 0:
             _log.warning("Tesseract cannot detect the script of the page")
             return None
@@ -182,9 +188,8 @@ class TesseractOcrCliModel(BaseOcrModel):
         cmd = [self.options.tesseract_cmd]
         cmd.append("--list-langs")
         _log.info("command: {}".format(" ".join(cmd)))
-        proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
-        output, _ = proc.communicate()
-        decoded_data = output.decode("utf-8")
+        output = subprocess.run(cmd, stdout=PIPE, stderr=DEVNULL, check=True)
+        decoded_data = output.stdout.decode("utf-8")
         df_list = pd.read_csv(io.StringIO(decoded_data), header=None)
         self._tesseract_languages = df_list[0].tolist()[1:]
 
@@ -203,7 +208,7 @@ class TesseractOcrCliModel(BaseOcrModel):
             yield from page_batch
             return
 
-        for page in page_batch:
+        for page_i, page in enumerate(page_batch):
             assert page._backend is not None
             if not page._backend.is_valid():
                 yield page
@@ -212,7 +217,7 @@ class TesseractOcrCliModel(BaseOcrModel):
                     ocr_rects = self.get_ocr_rects(page)
 
                     all_ocr_cells = []
-                    for ocr_rect in ocr_rects:
+                    for ocr_rect_i, ocr_rect in enumerate(ocr_rects):
                         # Skip zero area boxes
                         if ocr_rect.area() == 0:
                             continue
@@ -225,8 +230,42 @@ class TesseractOcrCliModel(BaseOcrModel):
                             ) as image_file:
                                 fname = image_file.name
                                 high_res_image.save(image_file)
-
-                            df_result = self._run_tesseract(fname)
+                            doc_orientation = 0
+                            try:
+                                df_osd = self._perform_osd(fname)
+                                doc_orientation = _parse_orientation(df_osd)
+                            except subprocess.CalledProcessError as exc:
+                                _log.error(
+                                    "OSD failed (doc %s, page: %s, "
+                                    "OCR rectangle: %s, processed image file %s):\n %s",
+                                    conv_res.input.file,
+                                    page_i,
+                                    ocr_rect_i,
+                                    image_file,
+                                    exc.stderr,
+                                )
+                                # Skipping if OSD fail when in auto mode, otherwise proceed
+                                # to OCR in the hope OCR will succeed while OSD failed
+                                if self._is_auto:
+                                    continue
+                            if doc_orientation != 0:
+                                high_res_image = high_res_image.rotate(
+                                    -doc_orientation, expand=True
+                                )
+                                high_res_image.save(fname)
+                            try:
+                                df_result = self._run_tesseract(fname, df_osd)
+                            except subprocess.CalledProcessError as exc:
+                                _log.error(
+                                    "tesseract OCR failed (doc %s, page: %s, "
+                                    "OCR rectangle: %s, processed image file %s):\n %s",
+                                    conv_res.input.file,
+                                    page_i,
+                                    ocr_rect_i,
+                                    image_file,
+                                    exc.stderr,
+                                )
+                                continue
                         finally:
                             if os.path.exists(fname):
                                 os.remove(fname)
@@ -238,31 +277,30 @@ class TesseractOcrCliModel(BaseOcrModel):
                             text = row["text"]
                             conf = row["conf"]
 
-                            l = float(row["left"])  # noqa: E741
-                            b = float(row["top"])
-                            w = float(row["width"])
-                            h = float(row["height"])
-
-                            t = b + h
-                            r = l + w
-
+                            left, top = float(row["left"]), float(row["top"])
+                            right = left + float(row["width"])
+                            bottom = top + row["height"]
+                            bbox = BoundingBox(
+                                l=left,
+                                t=top,
+                                r=right,
+                                b=bottom,
+                                coord_origin=CoordOrigin.TOPLEFT,
+                            )
+                            rect = tesseract_box_to_bounding_rectangle(
+                                bbox,
+                                original_offset=ocr_rect,
+                                scale=self.scale,
+                                orientation=doc_orientation,
+                                im_size=high_res_image.size,
+                            )
                             cell = TextCell(
                                 index=ix,
                                 text=str(text),
                                 orig=str(text),
                                 from_ocr=True,
                                 confidence=conf / 100.0,
-                                rect=BoundingRectangle.from_bounding_box(
-                                    BoundingBox.from_tuple(
-                                        coord=(
-                                            (l / self.scale) + ocr_rect.l,
-                                            (b / self.scale) + ocr_rect.t,
-                                            (r / self.scale) + ocr_rect.l,
-                                            (t / self.scale) + ocr_rect.t,
-                                        ),
-                                        origin=CoordOrigin.TOPLEFT,
-                                    )
-                                ),
+                                rect=rect,
                             )
                             all_ocr_cells.append(cell)
 
@@ -278,3 +316,9 @@ class TesseractOcrCliModel(BaseOcrModel):
     @classmethod
     def get_options_type(cls) -> Type[OcrOptions]:
         return TesseractCliOcrOptions
+
+
+def _parse_orientation(df_osd: pd.DataFrame) -> int:
+    orientations = df_osd.loc[df_osd["key"] == "Orientation in degrees"].value.tolist()
+    orientation = parse_tesseract_orientation(orientations[0].strip())
+    return orientation

docling/models/tesseract_ocr_model.py

@@ -1,12 +1,11 @@
 from __future__ import annotations
 
 import logging
-from collections.abc import Iterable
 from pathlib import Path
-from typing import Optional, Type
+from typing import Iterable, Optional, Type
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_core.types.doc.page import BoundingRectangle, TextCell
+from docling_core.types.doc.page import TextCell
 
 from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
@@ -17,7 +16,11 @@ from docling.datamodel.pipeline_options import (
 )
 from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
-from docling.utils.ocr_utils import map_tesseract_script
+from docling.utils.ocr_utils import (
+    map_tesseract_script,
+    parse_tesseract_orientation,
+    tesseract_box_to_bounding_rectangle,
+)
 from docling.utils.profiling import TimeRecorder
 
 _log = logging.getLogger(__name__)
@@ -38,7 +41,7 @@ class TesseractOcrModel(BaseOcrModel):
             accelerator_options=accelerator_options,
         )
         self.options: TesseractOcrOptions
-
+        self._is_auto: bool = "auto" in self.options.lang
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
         self.reader = None
         self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
@@ -95,13 +98,13 @@ class TesseractOcrModel(BaseOcrModel):
 
             if lang == "auto":
                 self.reader = tesserocr.PyTessBaseAPI(**tesserocr_kwargs)
-                self.osd_reader = tesserocr.PyTessBaseAPI(
-                    **{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
-                )
             else:
                 self.reader = tesserocr.PyTessBaseAPI(
                     **{"lang": lang} | tesserocr_kwargs,
                 )
+            self.osd_reader = tesserocr.PyTessBaseAPI(
+                **{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
+            )
             self.reader_RIL = tesserocr.RIL
 
     def __del__(self):
@@ -118,19 +121,20 @@ class TesseractOcrModel(BaseOcrModel):
             yield from page_batch
             return
 
-        for page in page_batch:
+        for page_i, page in enumerate(page_batch):
             assert page._backend is not None
             if not page._backend.is_valid():
                 yield page
             else:
                 with TimeRecorder(conv_res, "ocr"):
                     assert self.reader is not None
+                    assert self.osd_reader is not None
                     assert self._tesserocr_languages is not None
 
                     ocr_rects = self.get_ocr_rects(page)
 
                     all_ocr_cells = []
-                    for ocr_rect in ocr_rects:
+                    for ocr_rect_i, ocr_rect in enumerate(ocr_rects):
                         # Skip zero area boxes
                         if ocr_rect.area() == 0:
                             continue
@@ -139,16 +143,27 @@ class TesseractOcrModel(BaseOcrModel):
                         )
 
                         local_reader = self.reader
-                        if "auto" in self.options.lang:
-                            assert self.osd_reader is not None
-
-                            self.osd_reader.SetImage(high_res_image)
-                            osd = self.osd_reader.DetectOrientationScript()
-
-                            # No text, probably
-                            if osd is None:
+                        self.osd_reader.SetImage(high_res_image)
+                        osd = self.osd_reader.DetectOrientationScript()
+                        # No text, or Orientation and Script detection failure
+                        if osd is None:
+                            _log.error(
+                                "OSD failed for doc (doc %s, page: %s, "
+                                "OCR rectangle: %s)",
+                                conv_res.input.file,
+                                page_i,
+                                ocr_rect_i,
+                            )
+                            # Skipping if OSD fail when in auto mode, otherwise proceed
+                            # to OCR in the hope OCR will succeed while OSD failed
+                            if self._is_auto:
                                 continue
-
+                        doc_orientation = parse_tesseract_orientation(osd["orient_deg"])
+                        if doc_orientation != 0:
+                            high_res_image = high_res_image.rotate(
+                                -doc_orientation, expand=True
+                            )
+                        if self._is_auto:
                             script = osd["script_name"]
                             script = map_tesseract_script(script)
                             lang = f"{self.script_prefix}{script}"
@@ -188,11 +203,23 @@ class TesseractOcrModel(BaseOcrModel):
                             # Extract text within the bounding box
                             text = local_reader.GetUTF8Text().strip()
                             confidence = local_reader.MeanTextConf()
-                            left = box["x"] / self.scale
-                            bottom = box["y"] / self.scale
-                            right = (box["x"] + box["w"]) / self.scale
-                            top = (box["y"] + box["h"]) / self.scale
-
+                            left, top = box["x"], box["y"]
+                            right = left + box["w"]
+                            bottom = top + box["h"]
+                            bbox = BoundingBox(
+                                l=left,
+                                t=top,
+                                r=right,
+                                b=bottom,
+                                coord_origin=CoordOrigin.TOPLEFT,
+                            )
+                            rect = tesseract_box_to_bounding_rectangle(
+                                bbox,
+                                original_offset=ocr_rect,
+                                scale=self.scale,
+                                orientation=doc_orientation,
+                                im_size=high_res_image.size,
+                            )
                             cells.append(
                                 TextCell(
                                     index=ix,
@@ -200,12 +227,7 @@ class TesseractOcrModel(BaseOcrModel):
                                     orig=text,
                                     from_ocr=True,
                                     confidence=confidence,
-                                    rect=BoundingRectangle.from_bounding_box(
-                                        BoundingBox.from_tuple(
-                                            coord=(left, top, right, bottom),
-                                            origin=CoordOrigin.TOPLEFT,
-                                        ),
-                                    ),
+                                    rect=rect,
                                 )
                             )
 

docling/pipeline/standard_pdf_pipeline.py

@@ -3,6 +3,7 @@ import warnings
 from pathlib import Path
 from typing import Optional, cast
 
+import numpy as np
 from docling_core.types.doc import DocItem, ImageRef, PictureItem, TableItem
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
@@ -54,13 +55,15 @@ class StandardPdfPipeline(PaginatedPipeline):
                 "When defined, it must point to a folder containing all models required by the pipeline."
             )
 
-        self.keep_images = (
-            self.pipeline_options.generate_page_images
-            or self.pipeline_options.generate_picture_images
-            or self.pipeline_options.generate_table_images
-        )
+        with warnings.catch_warnings():  # deprecated generate_table_images
+            warnings.filterwarnings("ignore", category=DeprecationWarning)
+            self.keep_images = (
+                self.pipeline_options.generate_page_images
+                or self.pipeline_options.generate_picture_images
+                or self.pipeline_options.generate_table_images
+            )
 
-        self.glm_model = ReadingOrderModel(options=ReadingOrderOptions())
+        self.reading_order_model = ReadingOrderModel(options=ReadingOrderOptions())
 
         ocr_model = self.get_ocr_model(artifacts_path=artifacts_path)
 
@@ -197,7 +200,7 @@ class StandardPdfPipeline(PaginatedPipeline):
                 elements=all_elements, headers=all_headers, body=all_body
             )
 
-            conv_res.document = self.glm_model(conv_res)
+            conv_res.document = self.reading_order_model(conv_res)
 
             # Generate page images in the output
             if self.pipeline_options.generate_page_images:
@@ -209,40 +212,74 @@ class StandardPdfPipeline(PaginatedPipeline):
                     )
 
             # Generate images of the requested element types
-            if (
-                self.pipeline_options.generate_picture_images
-                or self.pipeline_options.generate_table_images
-            ):
-                scale = self.pipeline_options.images_scale
-                for element, _level in conv_res.document.iterate_items():
-                    if not isinstance(element, DocItem) or len(element.prov) == 0:
-                        continue
-                    if (
-                        isinstance(element, PictureItem)
-                        and self.pipeline_options.generate_picture_images
-                    ) or (
-                        isinstance(element, TableItem)
-                        and self.pipeline_options.generate_table_images
-                    ):
-                        page_ix = element.prov[0].page_no - 1
-                        page = next(
-                            (p for p in conv_res.pages if p.page_no == page_ix),
-                            cast("Page", None),
+            with warnings.catch_warnings():  # deprecated generate_table_images
+                warnings.filterwarnings("ignore", category=DeprecationWarning)
+                if (
+                    self.pipeline_options.generate_picture_images
+                    or self.pipeline_options.generate_table_images
+                ):
+                    scale = self.pipeline_options.images_scale
+                    for element, _level in conv_res.document.iterate_items():
+                        if not isinstance(element, DocItem) or len(element.prov) == 0:
+                            continue
+                        if (
+                            isinstance(element, PictureItem)
+                            and self.pipeline_options.generate_picture_images
+                        ) or (
+                            isinstance(element, TableItem)
+                            and self.pipeline_options.generate_table_images
+                        ):
+                            page_ix = element.prov[0].page_no - 1
+                            page = next(
+                                (p for p in conv_res.pages if p.page_no == page_ix),
+                                cast("Page", None),
+                            )
+                            assert page is not None
+                            assert page.size is not None
+                            assert page.image is not None
+
+                            crop_bbox = (
+                                element.prov[0]
+                                .bbox.scaled(scale=scale)
+                                .to_top_left_origin(
+                                    page_height=page.size.height * scale
+                                )
+                            )
+
+                            cropped_im = page.image.crop(crop_bbox.as_tuple())
+                            element.image = ImageRef.from_pil(
+                                cropped_im, dpi=int(72 * scale)
+                            )
+
+            # Aggregate confidence values for document:
+            if len(conv_res.pages) > 0:
+                with warnings.catch_warnings():
+                    warnings.filterwarnings(
+                        "ignore",
+                        category=RuntimeWarning,
+                        message="Mean of empty slice|All-NaN slice encountered",
+                    )
+                    conv_res.confidence.layout_score = float(
+                        np.nanmean(
+                            [c.layout_score for c in conv_res.confidence.pages.values()]
                         )
-                        assert page is not None
-                        assert page.size is not None
-                        assert page.image is not None
-
-                        crop_bbox = (
-                            element.prov[0]
-                            .bbox.scaled(scale=scale)
-                            .to_top_left_origin(page_height=page.size.height * scale)
+                    )
+                    conv_res.confidence.parse_score = float(
+                        np.nanquantile(
+                            [c.parse_score for c in conv_res.confidence.pages.values()],
+                            q=0.1,  # parse score should relate to worst 10% of pages.
                         )
-
-                        cropped_im = page.image.crop(crop_bbox.as_tuple())
-                        element.image = ImageRef.from_pil(
-                            cropped_im, dpi=int(72 * scale)
+                    )
+                    conv_res.confidence.table_score = float(
+                        np.nanmean(
+                            [c.table_score for c in conv_res.confidence.pages.values()]
                         )
+                    )
+                    conv_res.confidence.ocr_score = float(
+                        np.nanmean(
+                            [c.ocr_score for c in conv_res.confidence.pages.values()]
+                        )
+                    )
 
         return conv_res
 

docling/utils/layout_postprocessor.py

@@ -90,17 +90,12 @@ class SpatialClusterIndex:
         containment_threshold: float,
     ) -> bool:
         """Check if two bboxes overlap sufficiently."""
-        area1, area2 = bbox1.area(), bbox2.area()
-        if area1 <= 0 or area2 <= 0:
+        if bbox1.area() <= 0 or bbox2.area() <= 0:
             return False
 
-        overlap_area = bbox1.intersection_area_with(bbox2)
-        if overlap_area <= 0:
-            return False
-
-        iou = overlap_area / (area1 + area2 - overlap_area)
-        containment1 = overlap_area / area1
-        containment2 = overlap_area / area2
+        iou = bbox1.intersection_over_union(bbox2)
+        containment1 = bbox1.intersection_over_self(bbox2)
+        containment2 = bbox2.intersection_over_self(bbox1)
 
         return (
             iou > overlap_threshold
@@ -321,11 +316,9 @@ class LayoutPostprocessor:
         for special in special_clusters:
             contained = []
             for cluster in self.regular_clusters:
-                overlap = cluster.bbox.intersection_area_with(special.bbox)
-                if overlap > 0:
-                    containment = overlap / cluster.bbox.area()
-                    if containment > 0.8:
-                        contained.append(cluster)
+                containment = cluster.bbox.intersection_over_self(special.bbox)
+                if containment > 0.8:
+                    contained.append(cluster)
 
             if contained:
                 # Sort contained clusters by minimum cell ID:
@@ -379,9 +372,7 @@ class LayoutPostprocessor:
             for regular in self.regular_clusters:
                 if regular.label == DocItemLabel.TABLE:
                     # Calculate overlap
-                    overlap = regular.bbox.intersection_area_with(wrapper.bbox)
-                    wrapper_area = wrapper.bbox.area()
-                    overlap_ratio = overlap / wrapper_area
+                    overlap_ratio = wrapper.bbox.intersection_over_self(regular.bbox)
 
                     conf_diff = wrapper.confidence - regular.confidence
 
@@ -421,8 +412,7 @@ class LayoutPostprocessor:
         # Rule 2: CODE vs others
         if candidate.label == DocItemLabel.CODE:
             # Calculate how much of the other cluster is contained within the CODE cluster
-            overlap = other.bbox.intersection_area_with(candidate.bbox)
-            containment = overlap / other.bbox.area()
+            containment = other.bbox.intersection_over_self(candidate.bbox)
             if containment > 0.8:  # other is 80% contained within CODE
                 return True
 
@@ -586,11 +576,9 @@ class LayoutPostprocessor:
                 if cell.rect.to_bounding_box().area() <= 0:
                     continue
 
-                overlap = cell.rect.to_bounding_box().intersection_area_with(
+                overlap_ratio = cell.rect.to_bounding_box().intersection_over_self(
                     cluster.bbox
                 )
-                overlap_ratio = overlap / cell.rect.to_bounding_box().area()
-
                 if overlap_ratio > best_overlap:
                     best_overlap = overlap_ratio
                     best_cluster = cluster

docling/utils/ocr_utils.py

@@ -1,3 +1,11 @@
+from typing import Optional, Tuple
+
+from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle
+
+from docling.utils.orientation import CLIPPED_ORIENTATIONS, rotate_bounding_box
+
+
 def map_tesseract_script(script: str) -> str:
     r""" """
     if script == "Katakana" or script == "Hiragana":
@@ -7,3 +15,55 @@ def map_tesseract_script(script: str) -> str:
     elif script == "Korean":
         script = "Hangul"
     return script
+
+
+def parse_tesseract_orientation(orientation: str) -> int:
+    # Tesseract orientation is [0, 90, 180, 270] clockwise, bounding rectangle angles
+    # are [0, 360[ counterclockwise
+    parsed = int(orientation)
+    if parsed not in CLIPPED_ORIENTATIONS:
+        msg = (
+            f"invalid tesseract document orientation {orientation}, "
+            f"expected orientation: {sorted(CLIPPED_ORIENTATIONS)}"
+        )
+        raise ValueError(msg)
+    parsed = -parsed
+    parsed %= 360
+    return parsed
+
+
+def tesseract_box_to_bounding_rectangle(
+    bbox: BoundingBox,
+    *,
+    original_offset: Optional[BoundingBox] = None,
+    scale: float,
+    orientation: int,
+    im_size: Tuple[int, int],
+) -> BoundingRectangle:
+    # box is in the top, left, height, width format, top left coordinates
+    rect = rotate_bounding_box(bbox, angle=-orientation, im_size=im_size)
+    rect = BoundingRectangle(
+        r_x0=rect.r_x0 / scale,
+        r_y0=rect.r_y0 / scale,
+        r_x1=rect.r_x1 / scale,
+        r_y1=rect.r_y1 / scale,
+        r_x2=rect.r_x2 / scale,
+        r_y2=rect.r_y2 / scale,
+        r_x3=rect.r_x3 / scale,
+        r_y3=rect.r_y3 / scale,
+        coord_origin=CoordOrigin.TOPLEFT,
+    )
+    if original_offset is not None:
+        if original_offset.coord_origin is not CoordOrigin.TOPLEFT:
+            msg = f"expected coordinate origin to be {CoordOrigin.TOPLEFT.value}"
+            raise ValueError(msg)
+        if original_offset is not None:
+            rect.r_x0 += original_offset.l
+            rect.r_x1 += original_offset.l
+            rect.r_x2 += original_offset.l
+            rect.r_x3 += original_offset.l
+            rect.r_y0 += original_offset.t
+            rect.r_y1 += original_offset.t
+            rect.r_y2 += original_offset.t
+            rect.r_y3 += original_offset.t
+    return rect

docling/utils/orientation.py

@@ -0,0 +1,71 @@
+from typing import Tuple
+
+from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle
+
+CLIPPED_ORIENTATIONS = [0, 90, 180, 270]
+
+
+def rotate_bounding_box(
+    bbox: BoundingBox, angle: int, im_size: Tuple[int, int]
+) -> BoundingRectangle:
+    # The box is left top width height in TOPLEFT coordinates
+    # Bounding rectangle start with r_0 at the bottom left whatever the
+    # coordinate system. Then other corners are found rotating counterclockwise
+    bbox = bbox.to_top_left_origin(im_size[1])
+    left, top, width, height = bbox.l, bbox.t, bbox.width, bbox.height
+    im_h, im_w = im_size
+    angle = angle % 360
+    if angle == 0:
+        r_x0 = left
+        r_y0 = top + height
+        r_x1 = r_x0 + width
+        r_y1 = r_y0
+        r_x2 = r_x0 + width
+        r_y2 = r_y0 - height
+        r_x3 = r_x0
+        r_y3 = r_y0 - height
+    elif angle == 90:
+        r_x0 = im_w - (top + height)
+        r_y0 = left
+        r_x1 = r_x0
+        r_y1 = r_y0 + width
+        r_x2 = r_x0 + height
+        r_y2 = r_y0 + width
+        r_x3 = r_x0
+        r_y3 = r_y0 + width
+    elif angle == 180:
+        r_x0 = im_h - left
+        r_y0 = im_w - (top + height)
+        r_x1 = r_x0 - width
+        r_y1 = r_y0
+        r_x2 = r_x0 - width
+        r_y2 = r_y0 + height
+        r_x3 = r_x0
+        r_y3 = r_y0 + height
+    elif angle == 270:
+        r_x0 = top + height
+        r_y0 = im_h - left
+        r_x1 = r_x0
+        r_y1 = r_y0 - width
+        r_x2 = r_x0 - height
+        r_y2 = r_y0 - width
+        r_x3 = r_x0 - height
+        r_y3 = r_y0
+    else:
+        msg = (
+            f"invalid orientation {angle}, expected values in:"
+            f" {sorted(CLIPPED_ORIENTATIONS)}"
+        )
+        raise ValueError(msg)
+    return BoundingRectangle(
+        r_x0=r_x0,
+        r_y0=r_y0,
+        r_x1=r_x1,
+        r_y1=r_y1,
+        r_x2=r_x2,
+        r_y2=r_y2,
+        r_x3=r_x3,
+        r_y3=r_y3,
+        coord_origin=CoordOrigin.TOPLEFT,
+    )

{docling-2.33.0.dist-info → docling-2.35.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.33.0
+Version: 2.35.0
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/docling-project/docling
 License: MIT
@@ -29,7 +29,7 @@ Requires-Dist: accelerate (>=1.2.1,<2.0.0) ; (sys_platform != "darwin" or platfo
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: click (<8.2.0)
-Requires-Dist: docling-core[chunking] (>=2.29.0,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.31.2,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.4.0,<4.0.0)
 Requires-Dist: docling-parse (>=4.0.0,<5.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)

{docling-2.33.0.dist-info → docling-2.35.0.dist-info}/RECORD

@@ -3,9 +3,9 @@ docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/abstract_backend.py,sha256=1lNxzwDTn303aXduPDVmTyXn-5ZIoWMLYqNxANGWmQQ,1658
 docling/backend/asciidoc_backend.py,sha256=W-4MRcID6AU9Ax23q8FwDwGG-OOCrBoqcNf2Ch_WPUc,14041
 docling/backend/csv_backend.py,sha256=2g9famYG2W-ID9jEdZPxc6O8QGv1vWQfjN8pL-QMBE0,4536
-docling/backend/docling_parse_backend.py,sha256=V_CsUdN5RkGQBBq7A_ReAiUW4CQVh0-1Ur157Ozurdg,8017
-docling/backend/docling_parse_v2_backend.py,sha256=6fokgqb1hMbZua33gL46EFamrwPTC7ms6ZuEHw-Dv28,9395
-docling/backend/docling_parse_v4_backend.py,sha256=-WJZs0IsdN6blhkvTS1eh_qhujYLyJ3XcOMqS6AaXxg,6282
+docling/backend/docling_parse_backend.py,sha256=bVSPmmiVXdCVfe-eLtDhbPQKBjkFR8rZJoRxdWIMdYU,7998
+docling/backend/docling_parse_v2_backend.py,sha256=R4YPCEs72GYg-Xc9VfizPv8QjtGmKOsQzVPNAU2RIK0,9376
+docling/backend/docling_parse_v4_backend.py,sha256=aWh-fd-lnuRGVGC_DG17QUptIsArv5V1gJo8QFbB5Ys,6263
 docling/backend/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/docx/latex/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/docx/latex/latex_dict.py,sha256=tFJp4ScT_AkY2ON7nLEa560p601Jq2glcZvMKxxjn7w,6593
@@ -24,12 +24,12 @@ docling/backend/xml/jats_backend.py,sha256=ghGi9bHjx3BvaOtmzLw86-wZy4UxpQPOPQL4e
 docling/backend/xml/uspto_backend.py,sha256=nyAMr5ht7dclxkVDwsKNeiOhLQrUtRLS8JdscB2AVJg,70924
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=D7WEY4x6pQCVFRy3peK9KUDOb0Y5IVc-vTDqPnHPK00,26138
+docling/cli/main.py,sha256=KARZ1OJx4HvHb1D_95GPIAhKaIlhcYYSBa0t4PM-Xfk,27339
 docling/cli/models.py,sha256=9yLGp6QRJGpR86U3SjmWAXDt3MvBaJLLY4xDVdsu3O8,4160
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=3BmGoV2HLXOWFuRHFAa42YnWceh-JEpcLXzfFz9AD9Y,7943
-docling/datamodel/document.py,sha256=rxu5SqUppgNtYWwIbBoLlZvYAn_w2cGn5uq4AsvouSc,15907
+docling/datamodel/base_models.py,sha256=QJlzGJKUAO0kqM6DO2RZKlFi-lL2MpY8qt3Wdm02Slw,10460
+docling/datamodel/document.py,sha256=vPwiVU5zWCKbVYMq-TSmb7LTjijrqJq0FyAgDBa0XGA,16154
 docling/datamodel/pipeline_options.py,sha256=uwjBvK4egrgcF1_w4B5EDxpGnl4IgBzmxP7dJ7zm394,13400
 docling/datamodel/settings.py,sha256=ajMz7Ao2m0ZGYkfArqTDDbiF89O408mtgeh06PUi0MA,1900
 docling/document_converter.py,sha256=PRRr65nigQ3LZDl4G2fBMkOtJyswT7xyGt7fpUeDO3w,13849
@@ -47,10 +47,10 @@ docling/models/factories/ocr_factory.py,sha256=G5RkmkKvkl-ihpo6qSj8WC77VdlVSQ1s0
 docling/models/factories/picture_description_factory.py,sha256=Ru3-TnVVEKf5O07C_UpGf2HCOHc7j20AJzfficw3agM,385
 docling/models/hf_mlx_model.py,sha256=B_B4hFU-jU0g_DQtQD8w4Ejorn10mkDuFI93wR_WhGk,4897
 docling/models/hf_vlm_model.py,sha256=SiPMTLghMUjJ66dA2yN4UujpLO6PiOhLEPInWtXV_5s,6912
-docling/models/layout_model.py,sha256=0fiJXJ4aPmcMsYY7rbN9LJ2mZ0_8G0ODY9kyNTAN3Ws,7823
+docling/models/layout_model.py,sha256=1LLDS3hBfdJXA16L_PrjA_1rM_A2r5rNFkHVbLBCl_8,8639
 docling/models/ocr_mac_model.py,sha256=A3TlEbvvwhkWiq9YARos3Y9yNcpPYQ7JGc_4hFtAK-8,5370
-docling/models/page_assemble_model.py,sha256=GO7JI1D6T6EkSW94cLQobPGNQUahkxQqTPRwj5CnmFE,6304
-docling/models/page_preprocessing_model.py,sha256=6pOGXiFQ-oz06UmJdcaYMdVyfZ0YVLWS6efGcx7Mxws,3105
+docling/models/page_assemble_model.py,sha256=TvN1naez7dUodLxpUUBzpuMCpqZBTf6YSpewxgjzmrg,6323
+docling/models/page_preprocessing_model.py,sha256=8cdhR9n3zcC8JxDen8WdPBx_GNk_5VICeHJo1-kP518,5186
 docling/models/picture_description_api_model.py,sha256=kCuAFOGEuI5QsRul7Pc1LccxWN7WIvIUhXEmSICYegw,2332
 docling/models/picture_description_base_model.py,sha256=FbBVXzAOB87xpJN28tuGCxoAdcf6mZNUOqJR7ljUg5g,2946
 docling/models/picture_description_vlm_model.py,sha256=DiTjnehVy1n0N04xPUvZl8rx4TiNHzHn9Cnzy_ePGts,4177
@@ -59,12 +59,12 @@ docling/models/plugins/defaults.py,sha256=qslXGnRX07Z3GGttNriqaox0v0vXp4zs4KLurH
 docling/models/rapid_ocr_model.py,sha256=Tq_1Egu5Hjx7Y69Vox17QTtRXztSyflB1fhN08CWQwY,5894
 docling/models/readingorder_model.py,sha256=S9ru2ApY9sE-Uue3hptWHmbmElwo36bUbAikxCFpHYs,14574
 docling/models/table_structure_model.py,sha256=1gxLaooK0IKMrnmS8nT1BItKqt1GAKghfpmLKb3i53g,12566
-docling/models/tesseract_ocr_cli_model.py,sha256=LXYUCMQAPxQA2pY3zs9wcPSrAHHorTffSmIIWgltoaw,10234
-docling/models/tesseract_ocr_model.py,sha256=72009TJL_7tXTEnhlsGRiw_KibrQ0LjZlCBtW8NtwUc,9339
+docling/models/tesseract_ocr_cli_model.py,sha256=e55MkaDdsseKcfX5lxIt0iv5jR6pDFBzWBZHTvl2Jws,12653
+docling/models/tesseract_ocr_model.py,sha256=vS4And5NHe_uLNb6ZBi2CQzWUITBdc1E1zlsojrSZpM,10561
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_pipeline.py,sha256=DnuxAf7EQusdSRae0QUVth-0f2mSff8JZjX-2vazk00,8751
 docling/pipeline/simple_pipeline.py,sha256=TXZOwR7hZRji462ZTIpte0VJjzbxvNVE8dbLFANDhSU,2253
-docling/pipeline/standard_pdf_pipeline.py,sha256=iNZMMGiHTwV6I4u_jjqXhVJ_DiPn_O9qnnee3PQxidc,10773
+docling/pipeline/standard_pdf_pipeline.py,sha256=itCZPj7nMFAQtAlStfmWthpCIHZFUm9W5uTgvVi6PkQ,12738
 docling/pipeline/vlm_pipeline.py,sha256=ZW1WGd6jeLqTCWR0S0cj6H_qVMUXELaFCrJVpvZp6Co,9684
 docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -72,15 +72,16 @@ docling/utils/accelerator_utils.py,sha256=ONNRrC8fH-8E93WUCNhfOq1t7WrQ1T7-YsmExT
 docling/utils/api_image_request.py,sha256=_CgdzmPqdsyXmyYUFGLZcXcoH586qC6A1p5vsNbj1Q0,1416
 docling/utils/export.py,sha256=VwVUnYDk3mhGmISDbVm306fwpGNnoojouStBD4UajXI,4673
 docling/utils/glm_utils.py,sha256=TKOWQqWAHsX_w4fvoAA7_2xCi_urhnp1DsmjY8_sk5w,12274
-docling/utils/layout_postprocessor.py,sha256=x7exVG3HYzV9M_O78FfyoG43Y2L7PPMMydvSNwjqh8s,24528
+docling/utils/layout_postprocessor.py,sha256=3WCmkPsPJ80xfWzAUeWb5L9BmuwJ79ztctvbbUs8AfI,24068
 docling/utils/locks.py,sha256=RzqQtD5UispgV71pGN_nU6GYfeN11BN0Sh_Dq9ycqGo,52
 docling/utils/model_downloader.py,sha256=ocvud3G3qlBQhzMo69Q3RJMnvq5HPZ2DwNbMuEp8RCs,4142
-docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
+docling/utils/ocr_utils.py,sha256=AOaDAHr5S74d-IRVR_LKhKynUTIurAwLJ3wNeY58gPA,2326
+docling/utils/orientation.py,sha256=xXlOfowL54FKwjsTFrM7y3ogk1wChLNn_-u74tYIf1s,2011
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.33.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.33.0.dist-info/METADATA,sha256=FXLSejKn7Fc1pY2Fl8YvLP1PYvldoQ76d6zcupzghDo,10138
-docling-2.33.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.33.0.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
-docling-2.33.0.dist-info/RECORD,,
+docling-2.35.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.35.0.dist-info/METADATA,sha256=SMuVHjV5ouB773e4tFnu7fqpvEdygq3ksNbESerk0Ao,10138
+docling-2.35.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.35.0.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
+docling-2.35.0.dist-info/RECORD,,