docling 2.53.0__py3-none-any.whl → 2.54.0__py3-none-any.whl

docling/datamodel/base_models.py

@@ -1,7 +1,6 @@
-import math
 from collections import defaultdict
 from enum import Enum
-from typing import TYPE_CHECKING, Dict, List, Optional, Type, Union
+from typing import TYPE_CHECKING, Optional, Type, Union
 
 import numpy as np
 from docling_core.types.doc import (
@@ -14,9 +13,7 @@ from docling_core.types.doc import (
 )
 from docling_core.types.doc.base import PydanticSerCtxKey, round_pydantic_float
 from docling_core.types.doc.page import SegmentedPdfPage, TextCell
-from docling_core.types.io import (
-    DocumentStream,
-)
+from docling_core.types.io import DocumentStream
 
 # DO NOT REMOVE; explicitly exposed from this location
 from PIL.Image import Image
@@ -71,6 +68,7 @@ class InputFormat(str, Enum):
     METS_GBS = "mets_gbs"
     JSON_DOCLING = "json_docling"
     AUDIO = "audio"
+    VTT = "vtt"
 
 
 class OutputFormat(str, Enum):
@@ -82,7 +80,7 @@ class OutputFormat(str, Enum):
     DOCTAGS = "doctags"
 
 
-FormatToExtensions: Dict[InputFormat, List[str]] = {
+FormatToExtensions: dict[InputFormat, list[str]] = {
     InputFormat.DOCX: ["docx", "dotx", "docm", "dotm"],
     InputFormat.PPTX: ["pptx", "potx", "ppsx", "pptm", "potm", "ppsm"],
     InputFormat.PDF: ["pdf"],
@@ -97,9 +95,10 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.METS_GBS: ["tar.gz"],
     InputFormat.JSON_DOCLING: ["json"],
     InputFormat.AUDIO: ["wav", "mp3"],
+    InputFormat.VTT: ["vtt"],
 }
 
-FormatToMimeType: Dict[InputFormat, List[str]] = {
+FormatToMimeType: dict[InputFormat, list[str]] = {
     InputFormat.DOCX: [
         "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
         "application/vnd.openxmlformats-officedocument.wordprocessingml.template",
@@ -130,6 +129,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
     InputFormat.METS_GBS: ["application/mets+xml"],
     InputFormat.JSON_DOCLING: ["application/json"],
     InputFormat.AUDIO: ["audio/x-wav", "audio/mpeg", "audio/wav", "audio/mp3"],
+    InputFormat.VTT: ["text/vtt"],
 }
 
 MimeTypeToFormat: dict[str, list[InputFormat]] = {
@@ -162,8 +162,8 @@ class Cluster(BaseModel):
     label: DocItemLabel
     bbox: BoundingBox
     confidence: float = 1.0
-    cells: List[TextCell] = []
-    children: List["Cluster"] = []  # Add child cluster support
+    cells: list[TextCell] = []
+    children: list["Cluster"] = []  # Add child cluster support
 
     @field_serializer("confidence")
     def _serialize(self, value: float, info: FieldSerializationInfo) -> float:
@@ -179,7 +179,7 @@ class BasePageElement(BaseModel):
 
 
 class LayoutPrediction(BaseModel):
-    clusters: List[Cluster] = []
+    clusters: list[Cluster] = []
 
 
 class VlmPredictionToken(BaseModel):
@@ -201,14 +201,14 @@ class ContainerElement(
 
 
 class Table(BasePageElement):
-    otsl_seq: List[str]
+    otsl_seq: list[str]
     num_rows: int = 0
     num_cols: int = 0
-    table_cells: List[TableCell]
+    table_cells: list[TableCell]
 
 
 class TableStructurePrediction(BaseModel):
-    table_map: Dict[int, Table] = {}
+    table_map: dict[int, Table] = {}
 
 
 class TextElement(BasePageElement):
@@ -216,7 +216,7 @@ class TextElement(BasePageElement):
 
 
 class FigureElement(BasePageElement):
-    annotations: List[PictureDataType] = []
+    annotations: list[PictureDataType] = []
     provenance: Optional[str] = None
     predicted_class: Optional[str] = None
     confidence: Optional[float] = None
@@ -234,12 +234,12 @@ class FigureElement(BasePageElement):
 
 class FigureClassificationPrediction(BaseModel):
     figure_count: int = 0
-    figure_map: Dict[int, FigureElement] = {}
+    figure_map: dict[int, FigureElement] = {}
 
 
 class EquationPrediction(BaseModel):
     equation_count: int = 0
-    equation_map: Dict[int, TextElement] = {}
+    equation_map: dict[int, TextElement] = {}
 
 
 class PagePredictions(BaseModel):
@@ -254,9 +254,9 @@ PageElement = Union[TextElement, Table, FigureElement, ContainerElement]
 
 
 class AssembledUnit(BaseModel):
-    elements: List[PageElement] = []
-    body: List[PageElement] = []
-    headers: List[PageElement] = []
+    elements: list[PageElement] = []
+    body: list[PageElement] = []
+    headers: list[PageElement] = []
 
 
 class ItemAndImageEnrichmentElement(BaseModel):
@@ -280,12 +280,12 @@ class Page(BaseModel):
         None  # Internal PDF backend. By default it is cleared during assembling.
     )
     _default_image_scale: float = 1.0  # Default image scale for external usage.
-    _image_cache: Dict[
+    _image_cache: dict[
         float, Image
     ] = {}  # Cache of images in different scales. By default it is cleared during assembling.
 
     @property
-    def cells(self) -> List[TextCell]:
+    def cells(self) -> list[TextCell]:
         """Return text cells as a read-only view of parsed_page.textline_cells."""
         if self.parsed_page is not None:
             return self.parsed_page.textline_cells
@@ -354,7 +354,7 @@ class OpenAiApiResponse(BaseModel):
 
     id: str
     model: Optional[str] = None  # returned by openai
-    choices: List[OpenAiResponseChoice]
+    choices: list[OpenAiResponseChoice]
     created: int
     usage: OpenAiResponseUsage
 
@@ -430,7 +430,7 @@ class PageConfidenceScores(BaseModel):
 
 
 class ConfidenceReport(PageConfidenceScores):
-    pages: Dict[int, PageConfidenceScores] = Field(
+    pages: dict[int, PageConfidenceScores] = Field(
         default_factory=lambda: defaultdict(PageConfidenceScores)
     )
 

docling/datamodel/document.py

@@ -394,6 +394,8 @@ class _DocumentConversionInput(BaseModel):
             mime = FormatToMimeType[InputFormat.PPTX][0]
         elif ext in FormatToExtensions[InputFormat.XLSX]:
             mime = FormatToMimeType[InputFormat.XLSX][0]
+        elif ext in FormatToExtensions[InputFormat.VTT]:
+            mime = FormatToMimeType[InputFormat.VTT][0]
 
         return mime
 

docling/document_converter.py

@@ -25,6 +25,7 @@ from docling.backend.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
 from docling.backend.noop_backend import NoOpBackend
+from docling.backend.webvtt_backend import WebVTTDocumentBackend
 from docling.backend.xml.jats_backend import JatsDocumentBackend
 from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend
 from docling.datamodel.base_models import (
@@ -170,6 +171,9 @@ def _get_default_option(format: InputFormat) -> FormatOption:
             pipeline_cls=SimplePipeline, backend=DoclingJSONBackend
         ),
         InputFormat.AUDIO: FormatOption(pipeline_cls=AsrPipeline, backend=NoOpBackend),
+        InputFormat.VTT: FormatOption(
+            pipeline_cls=SimplePipeline, backend=WebVTTDocumentBackend
+        ),
     }
     if (options := format_to_default_options.get(format)) is not None:
         return options

docling/models/table_structure_model.py

@@ -121,7 +121,7 @@ class TableStructureModel(BasePageModel):
 
         for table_element in tbl_list:
             x0, y0, x1, y1 = table_element.cluster.bbox.as_tuple()
-            y0 *= scale_x
+            y0 *= scale_y
             y1 *= scale_y
             x0 *= scale_x
             x1 *= scale_x
@@ -132,7 +132,7 @@ class TableStructureModel(BasePageModel):
                 x0, y0, x1, y1 = cell.rect.to_bounding_box().as_tuple()
                 x0 *= scale_x
                 x1 *= scale_x
-                y0 *= scale_x
+                y0 *= scale_y
                 y1 *= scale_y
 
                 draw.rectangle([(x0, y0), (x1, y1)], outline="green")
@@ -142,7 +142,7 @@ class TableStructureModel(BasePageModel):
                     x0, y0, x1, y1 = tc.bbox.as_tuple()
                     x0 *= scale_x
                     x1 *= scale_x
-                    y0 *= scale_x
+                    y0 *= scale_y
                     y1 *= scale_y
 
                     if tc.column_header:

{docling-2.53.0.dist-info → docling-2.54.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.53.0
+Version: 2.54.0
 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.
 Author-email: 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>, Panos Vagenas <pva@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 License-Expression: MIT
@@ -26,7 +26,7 @@ Requires-Python: <4.0,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pydantic<3.0.0,>=2.0.0
-Requires-Dist: docling-core[chunking]<3.0.0,>=2.48.0
+Requires-Dist: docling-core[chunking]<3.0.0,>=2.48.2
 Requires-Dist: docling-parse<5.0.0,>=4.4.0
 Requires-Dist: docling-ibm-models<4,>=3.9.1
 Requires-Dist: filetype<2.0.0,>=1.2.0
@@ -101,7 +101,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
 
 ## Features
 
-* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, images (PNG, TIFF, JPEG, ...), and more
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, VTT, images (PNG, TIFF, JPEG, ...), and more
 * 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more
 * 🧬 Unified, expressive [DoclingDocument][docling_document] representation format
 * ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON
@@ -117,13 +117,13 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 📤 Structured [information extraction][extraction] \[🧪 beta\]
 * 📑 New layout model (**Heron**) by default, for faster PDF parsing
 * 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications
+* 💬 Parsing of Web Video Text Tracks (WebVTT) files
 
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
 * 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
 * 📝 Complex chemistry understanding (Molecular structures)
-* 📝 Parsing of Web Video Text Tracks (WebVTT) files
 
 ## Installation
 

{docling-2.53.0.dist-info → docling-2.54.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/document_converter.py,sha256=CKMlobhTt8Y5yZ_tQOnPAP7_otBiddQ_klRGT5Bgwyo,15827
+docling/document_converter.py,sha256=gPyBrNegMgeBGxN7iebrjqEDm7zQQOmFNm8hVi-pFEQ,16013
 docling/document_extractor.py,sha256=-RbQRvLWLXF15HYqBbV_lJhh08Zl487UEQKhP-_FR8k,11969
 docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
 docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
@@ -15,10 +15,11 @@ docling/backend/md_backend.py,sha256=qCI7SD9hnWWGrkG_drpzQv2Z7DVBG4Tsq3hhTsYV790
 docling/backend/mets_gbs_backend.py,sha256=EA8sY6tbmGiysKGYPPZiNlK-i7Adn8bLTo-7Ym15hTU,12774
 docling/backend/msexcel_backend.py,sha256=5JRbPwOjR1r45AMeIts1rj6InbOgLBf_CtAhvNPVmsQ,19157
 docling/backend/mspowerpoint_backend.py,sha256=wJgB2JStEPfD7MPpWQlpPN7bffPxaHFUnKD4wj8SLxU,15114
-docling/backend/msword_backend.py,sha256=fKeAMGGR5ABimedo_ofCQAybzdqmqWA3A3mpLl7X6qY,49129
+docling/backend/msword_backend.py,sha256=kQI9hrx_lvHn__KdxW8MbvB78snoVzA_m4jXx6f_LJ8,54419
 docling/backend/noop_backend.py,sha256=EOPbD86FzZPX-K_DpNrJh0_lC0bZz--4DpG-OagDNGY,1688
 docling/backend/pdf_backend.py,sha256=Wcd1NSrAMjXK8VicTki5p-j-JLofklt07eF0kIG17_0,3361
 docling/backend/pypdfium2_backend.py,sha256=AYhWs9S8W_TkAK0-OkRmUNf4HUZl26FP7-XYjwU5zDk,14209
+docling/backend/webvtt_backend.py,sha256=9xPcfWVLuqhEAFrkv8aU36qHnSgjeINZAXT_C9C6XJA,19165
 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
@@ -36,8 +37,8 @@ docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/accelerator_options.py,sha256=wv6dOFTVAwr9onkE-0pfUqX_fDb6gX53iPPE6o8nKjI,2511
 docling/datamodel/asr_model_specs.py,sha256=Wg7z3zm_wXIWu122iPVy0RMECsA_JCFHrlFF-xxHoVQ,2187
-docling/datamodel/base_models.py,sha256=vOt895z0GsFirHkkI3hM23e9oyUuz9RXfcGFtoINLtw,12334
-docling/datamodel/document.py,sha256=ElY7G6FYJ6Bayyw433_tbnxyE47fnQRoBG_mygvOBrA,17370
+docling/datamodel/base_models.py,sha256=CQ6eThPzVeVD2Gq7BNz9Q5RDLwhe4NgMzk7tdLtk1c8,12382
+docling/datamodel/document.py,sha256=HyO3kdJcXIJ3wL95sPoL3zvsO4Rww3-qHH6IkL4I0q4,17483
 docling/datamodel/extraction.py,sha256=7dgvtK5SuvgfB8LHAwS1FwrW1kcMQJuJG0ol8uAQgoQ,1323
 docling/datamodel/layout_model_specs.py,sha256=GSkJ-Z_0PVgwWGi7C7TsxbzRjlrWS9ZrHJjHumv-Z5U,2339
 docling/datamodel/pipeline_options.py,sha256=28opZ3woXA8IKaG2-BHM-lmmi-gyuScCMHGxhlxGOsk,11290
@@ -61,7 +62,7 @@ docling/models/picture_description_base_model.py,sha256=kLthLhdlgwhootQ4_xhhcAk6
 docling/models/picture_description_vlm_model.py,sha256=Uja_BQSk7F-U1J2hm4yeLguirUzKYv1K8zRyw1IYomY,4150
 docling/models/rapid_ocr_model.py,sha256=anUVUwaj9Wubgu4FnHdYMuOVkQP_hJiLY1qRToelBoc,7700
 docling/models/readingorder_model.py,sha256=bZoXHaSwUsa8niSmJrbCuy784ixCeBXT-RQBUfgHJ4A,14925
-docling/models/table_structure_model.py,sha256=7vO8LisdoqCTsY8X8lsk9d-oD2hVjUtdaWlkMTQxEg0,12518
+docling/models/table_structure_model.py,sha256=7g_mFf1YzfF8PXQfefNu6XYZu7TzJAn86zKb6IEUdCg,12518
 docling/models/tesseract_ocr_cli_model.py,sha256=I3Gn28Y-LD8OfvyCElN9fLiNgpo2sT0uMkVt258253s,12881
 docling/models/tesseract_ocr_model.py,sha256=GdI5Cjfi87qcehVbM3wdKRvKkl_F9A4bwTUbjXZCJYA,10745
 docling/models/factories/__init__.py,sha256=x_EM5dDg_A3HBcBYzOoqwmA2AFLtJ1IzYDPX-R1A-Sg,868
@@ -99,9 +100,9 @@ docling/utils/orientation.py,sha256=jTyLxyT31FlOodZoBMlADHNQK2lAWKYVs5z7pXd_6Cg,
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.53.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.53.0.dist-info/METADATA,sha256=bpbaYrZCEppMQ3nPsq8wyn_Opp6IRK_P_rF5JQjCjr4,11247
-docling-2.53.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-docling-2.53.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
-docling-2.53.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
-docling-2.53.0.dist-info/RECORD,,
+docling-2.54.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.54.0.dist-info/METADATA,sha256=_GsdUYyPCv8XKeLeSO9Y0euAH8Eanr5i_y5kLvDEb1g,11252
+docling-2.54.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+docling-2.54.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
+docling-2.54.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
+docling-2.54.0.dist-info/RECORD,,