docling-core 2.21.1__py3-none-any.whl → 2.22.0__py3-none-any.whl

docling_core/transforms/chunker/hybrid_chunker.py

@@ -73,7 +73,7 @@ class HybridChunker(BaseChunker):
             for t in text:
                 total += self._count_text_tokens(t)
             return total
-        return len(self._tokenizer.tokenize(text, max_length=None))
+        return len(self._tokenizer.tokenize(text))
 
     class _ChunkLengthInfo(BaseModel):
         total_len: int
@@ -82,7 +82,7 @@ class HybridChunker(BaseChunker):
 
     def _count_chunk_tokens(self, doc_chunk: DocChunk):
         ser_txt = self.serialize(chunk=doc_chunk)
-        return len(self._tokenizer.tokenize(text=ser_txt, max_length=None))
+        return len(self._tokenizer.tokenize(text=ser_txt))
 
     def _doc_chunk_length(self, doc_chunk: DocChunk):
         text_length = self._count_text_tokens(doc_chunk.text)

docling_core/types/doc/document.py

@@ -4,6 +4,7 @@ import base64
 import copy
 import hashlib
 import html
+import itertools
 import json
 import logging
 import mimetypes
@@ -37,7 +38,7 @@ from pydantic import (
     model_validator,
 )
 from tabulate import tabulate
-from typing_extensions import Annotated, Self
+from typing_extensions import Annotated, Self, deprecated
 
 from docling_core.search.package import VERSION_PATTERN
 from docling_core.types.base import _JSON_POINTER_REGEX
@@ -522,6 +523,49 @@ class ImageRef(BaseModel):
         )
 
 
+class DocTagsPage(BaseModel):
+    """DocTagsPage."""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    tokens: str
+    image: Optional[PILImage.Image] = None
+
+
+class DocTagsDocument(BaseModel):
+    """DocTagsDocument."""
+
+    pages: List[DocTagsPage] = []
+
+    @classmethod
+    def from_doctags_and_image_pairs(
+        cls, doctags: List[Union[Path, str]], images: List[Union[Path, PILImage.Image]]
+    ):
+        """from_doctags_and_image_pairs."""
+        if len(doctags) != len(images):
+            raise ValueError("Number of page doctags must be equal to page images!")
+        doctags_doc = cls()
+
+        pages = []
+        for dt, img in zip(doctags, images):
+            if isinstance(dt, Path):
+                with dt.open("r") as fp:
+                    dt = fp.read()
+            elif isinstance(dt, str):
+                pass
+
+            if isinstance(img, Path):
+                img = PILImage.open(img)
+            elif isinstance(dt, PILImage.Image):
+                pass
+
+            page = DocTagsPage(tokens=dt, image=img)
+            pages.append(page)
+
+        doctags_doc.pages = pages
+        return doctags_doc
+
+
 class ProvenanceItem(BaseModel):
     """ProvenanceItem."""
 
@@ -800,7 +844,7 @@ class CodeItem(FloatingItem, TextItem):
         :param add_content: bool:  (Default value = True)
 
         """
-        body = f"<{self.label.value}{new_line}"
+        body = f"<{self.label.value}>{new_line}"
 
         if add_location:
             body += self.get_location_tokens(
@@ -813,7 +857,7 @@ class CodeItem(FloatingItem, TextItem):
         if add_content and self.text is not None:
             body += f"<_{self.code_language.value}_>{self.text}{new_line}"
 
-        body += f"</{self.label.value}\n"
+        body += f"</{self.label.value}>\n"
 
         return body
 
@@ -1003,6 +1047,20 @@ class PictureItem(FloatingItem):
             predicted_class = classifications[0].predicted_classes[0].class_name
             body += DocumentToken.get_picture_classification_token(predicted_class)
 
+        smiles_annotations = [
+            ann for ann in self.annotations if isinstance(ann, PictureMoleculeData)
+        ]
+        if len(smiles_annotations) > 0:
+            body += (
+                "<"
+                + DocumentToken.SMILES.value
+                + ">"
+                + smiles_annotations[0].smi
+                + "</"
+                + DocumentToken.SMILES.value
+                + ">"
+            )
+
         if add_caption and len(self.captions):
             text = self.caption_text(doc)
 
@@ -2487,7 +2545,6 @@ class DoclingDocument(BaseModel):
                         is_inline_scope=is_inline_scope,
                         visited=visited,
                     )
-                    # NOTE: assumes unordered (flag & marker currently in ListItem)
                     indent_str = list_level * indent * " "
                     is_ol = item.label == GroupLabel.ORDERED_LIST
                     text = "\n".join(
@@ -2501,7 +2558,12 @@ class DoclingDocument(BaseModel):
                             for i, c in enumerate(comps)
                         ]
                     )
-                    _ingest_text(text=text)
+                    _ingest_text(
+                        text=text,
+                        # special chars have already been escaped as needed
+                        do_escape_html=False,
+                        do_escape_underscores=False,
+                    )
                 elif item.label == GroupLabel.INLINE:
                     comps = self._get_markdown_components(
                         node=item,
@@ -2520,7 +2582,13 @@ class DoclingDocument(BaseModel):
                         is_inline_scope=True,
                         visited=visited,
                     )
-                    _ingest_text(" ".join(comps))
+                    text = " ".join(comps)
+                    _ingest_text(
+                        text=text,
+                        # special chars have already been escaped as needed
+                        do_escape_html=False,
+                        do_escape_underscores=False,
+                    )
                 else:
                     continue
 
@@ -2838,7 +2906,7 @@ class DoclingDocument(BaseModel):
 
                 # Building a math equation in MathML format
                 # ref https://www.w3.org/TR/wai-aria-1.1/#math
-                elif formula_to_mathml:
+                elif formula_to_mathml and len(math_formula) > 0:
                     try:
                         mathml_element = latex2mathml.converter.convert_to_element(
                             math_formula, display="block"
@@ -2860,7 +2928,7 @@ class DoclingDocument(BaseModel):
                             and img_fallback is not None
                         ):
                             text = img_fallback
-                        elif len(math_formula) > 0:
+                        else:
                             text = f"<pre>{math_formula}</pre>"
 
                 elif math_formula != "":
@@ -2926,7 +2994,378 @@ class DoclingDocument(BaseModel):
 
         return html_text
 
-    def save_as_document_tokens(
+    def load_from_doctags(  # noqa: C901
+        self,
+        doctag_document: DocTagsDocument,
+    ) -> "DoclingDocument":
+        r"""Load Docling document from lists of DocTags and Images."""
+        # Maps the recognized tag to a Docling label.
+        # Code items will be given DocItemLabel.CODE
+        tag_to_doclabel = {
+            "title": DocItemLabel.TITLE,
+            "document_index": DocItemLabel.DOCUMENT_INDEX,
+            "otsl": DocItemLabel.TABLE,
+            "section_header_level_1": DocItemLabel.SECTION_HEADER,
+            "checkbox_selected": DocItemLabel.CHECKBOX_SELECTED,
+            "checkbox_unselected": DocItemLabel.CHECKBOX_UNSELECTED,
+            "text": DocItemLabel.TEXT,
+            "page_header": DocItemLabel.PAGE_HEADER,
+            "page_footer": DocItemLabel.PAGE_FOOTER,
+            "formula": DocItemLabel.FORMULA,
+            "caption": DocItemLabel.CAPTION,
+            "picture": DocItemLabel.PICTURE,
+            "list_item": DocItemLabel.LIST_ITEM,
+            "footnote": DocItemLabel.FOOTNOTE,
+            "code": DocItemLabel.CODE,
+        }
+
+        def extract_bounding_box(text_chunk: str) -> Optional[BoundingBox]:
+            """Extract <loc_...> coords from the chunk, normalized by / 500."""
+            coords = re.findall(r"<loc_(\d+)>", text_chunk)
+            if len(coords) == 4:
+                l, t, r, b = map(float, coords)
+                return BoundingBox(l=l / 500, t=t / 500, r=r / 500, b=b / 500)
+            return None
+
+        def extract_inner_text(text_chunk: str) -> str:
+            """Strip all <...> tags inside the chunk to get the raw text content."""
+            return re.sub(r"<.*?>", "", text_chunk, flags=re.DOTALL).strip()
+
+        def otsl_parse_texts(texts, tokens):
+            split_word = TableToken.OTSL_NL.value
+            split_row_tokens = [
+                list(y)
+                for x, y in itertools.groupby(tokens, lambda z: z == split_word)
+                if not x
+            ]
+            table_cells = []
+            r_idx = 0
+            c_idx = 0
+
+            def count_right(tokens, c_idx, r_idx, which_tokens):
+                span = 0
+                c_idx_iter = c_idx
+                while tokens[r_idx][c_idx_iter] in which_tokens:
+                    c_idx_iter += 1
+                    span += 1
+                    if c_idx_iter >= len(tokens[r_idx]):
+                        return span
+                return span
+
+            def count_down(tokens, c_idx, r_idx, which_tokens):
+                span = 0
+                r_idx_iter = r_idx
+                while tokens[r_idx_iter][c_idx] in which_tokens:
+                    r_idx_iter += 1
+                    span += 1
+                    if r_idx_iter >= len(tokens):
+                        return span
+                return span
+
+            for i, text in enumerate(texts):
+                cell_text = ""
+                if text in [
+                    TableToken.OTSL_FCEL.value,
+                    TableToken.OTSL_ECEL.value,
+                    TableToken.OTSL_CHED.value,
+                    TableToken.OTSL_RHED.value,
+                    TableToken.OTSL_SROW.value,
+                ]:
+                    row_span = 1
+                    col_span = 1
+                    right_offset = 1
+                    if text != TableToken.OTSL_ECEL.value:
+                        cell_text = texts[i + 1]
+                        right_offset = 2
+
+                    # Check next element(s) for lcel / ucel / xcel,
+                    # set properly row_span, col_span
+                    next_right_cell = ""
+                    if i + right_offset < len(texts):
+                        next_right_cell = texts[i + right_offset]
+
+                    next_bottom_cell = ""
+                    if r_idx + 1 < len(split_row_tokens):
+                        if c_idx < len(split_row_tokens[r_idx + 1]):
+                            next_bottom_cell = split_row_tokens[r_idx + 1][c_idx]
+
+                    if next_right_cell in [
+                        TableToken.OTSL_LCEL.value,
+                        TableToken.OTSL_XCEL.value,
+                    ]:
+                        # we have horisontal spanning cell or 2d spanning cell
+                        col_span += count_right(
+                            split_row_tokens,
+                            c_idx + 1,
+                            r_idx,
+                            [TableToken.OTSL_LCEL.value, TableToken.OTSL_XCEL.value],
+                        )
+                    if next_bottom_cell in [
+                        TableToken.OTSL_UCEL.value,
+                        TableToken.OTSL_XCEL.value,
+                    ]:
+                        # we have a vertical spanning cell or 2d spanning cell
+                        row_span += count_down(
+                            split_row_tokens,
+                            c_idx,
+                            r_idx + 1,
+                            [TableToken.OTSL_UCEL.value, TableToken.OTSL_XCEL.value],
+                        )
+
+                    table_cells.append(
+                        TableCell(
+                            text=cell_text.strip(),
+                            row_span=row_span,
+                            col_span=col_span,
+                            start_row_offset_idx=r_idx,
+                            end_row_offset_idx=r_idx + row_span,
+                            start_col_offset_idx=c_idx,
+                            end_col_offset_idx=c_idx + col_span,
+                        )
+                    )
+                if text in [
+                    TableToken.OTSL_FCEL.value,
+                    TableToken.OTSL_ECEL.value,
+                    TableToken.OTSL_CHED.value,
+                    TableToken.OTSL_RHED.value,
+                    TableToken.OTSL_SROW.value,
+                    TableToken.OTSL_LCEL.value,
+                    TableToken.OTSL_UCEL.value,
+                    TableToken.OTSL_XCEL.value,
+                ]:
+                    c_idx += 1
+                if text == TableToken.OTSL_NL.value:
+                    r_idx += 1
+                    c_idx = 0
+            return table_cells, split_row_tokens
+
+        def otsl_extract_tokens_and_text(s: str):
+            # Pattern to match anything enclosed by < >
+            # (including the angle brackets themselves)
+            pattern = r"(<[^>]+>)"
+            # Find all tokens (e.g. "<otsl>", "<loc_140>", etc.)
+            tokens = re.findall(pattern, s)
+            # Remove any tokens that start with "<loc_"
+            tokens = [
+                token
+                for token in tokens
+                if not (
+                    token.startswith(rf"<{DocumentToken.LOC.value}")
+                    or token
+                    in [
+                        rf"<{DocumentToken.OTSL.value}>",
+                        rf"</{DocumentToken.OTSL.value}>",
+                    ]
+                )
+            ]
+            # Split the string by those tokens to get the in-between text
+            text_parts = re.split(pattern, s)
+            text_parts = [
+                token
+                for token in text_parts
+                if not (
+                    token.startswith(rf"<{DocumentToken.LOC.value}")
+                    or token
+                    in [
+                        rf"<{DocumentToken.OTSL.value}>",
+                        rf"</{DocumentToken.OTSL.value}>",
+                    ]
+                )
+            ]
+            # Remove any empty or purely whitespace strings from text_parts
+            text_parts = [part for part in text_parts if part.strip()]
+
+            return tokens, text_parts
+
+        def parse_table_content(otsl_content: str) -> TableData:
+            tokens, mixed_texts = otsl_extract_tokens_and_text(otsl_content)
+            table_cells, split_row_tokens = otsl_parse_texts(mixed_texts, tokens)
+
+            return TableData(
+                num_rows=len(split_row_tokens),
+                num_cols=(
+                    max(len(row) for row in split_row_tokens) if split_row_tokens else 0
+                ),
+                table_cells=table_cells,
+            )
+
+        # doc = DoclingDocument(name="Document")
+        for pg_idx, doctag_page in enumerate(doctag_document.pages):
+            page_doctags = doctag_page.tokens
+            image = doctag_page.image
+
+            page_no = pg_idx + 1
+            # bounding_boxes = []
+
+            if image is not None:
+                pg_width = image.width
+                pg_height = image.height
+            else:
+                pg_width = 1
+                pg_height = 1
+
+            """
+            1. Finds all <tag>...</tag>
+               blocks in the entire string (multi-line friendly)
+               in the order they appear.
+            2. For each chunk, extracts bounding box (if any) and inner text.
+            3. Adds the item to a DoclingDocument structure with the right label.
+            4. Tracks bounding boxes+color in a separate list for later visualization.
+            """
+
+            # Regex for root level recognized tags
+            tag_pattern = (
+                rf"<(?P<tag>{DocItemLabel.TITLE}|{DocItemLabel.DOCUMENT_INDEX}|"
+                rf"{DocItemLabel.CHECKBOX_UNSELECTED}|{DocItemLabel.CHECKBOX_SELECTED}|"
+                rf"{DocItemLabel.TEXT}|{DocItemLabel.PAGE_HEADER}|"
+                rf"{DocItemLabel.PAGE_FOOTER}|{DocItemLabel.FORMULA}|"
+                rf"{DocItemLabel.CAPTION}|{DocItemLabel.PICTURE}|"
+                rf"{DocItemLabel.FOOTNOTE}|{DocItemLabel.CODE}|"
+                rf"{DocItemLabel.SECTION_HEADER}_level_1|"
+                rf"{DocumentToken.ORDERED_LIST.value}|"
+                rf"{DocumentToken.UNORDERED_LIST.value}|"
+                rf"{DocumentToken.OTSL.value})>.*?</(?P=tag)>"
+            )
+
+            # DocumentToken.OTSL
+            pattern = re.compile(tag_pattern, re.DOTALL)
+
+            # Go through each match in order
+            for match in pattern.finditer(page_doctags):
+                full_chunk = match.group(0)
+                tag_name = match.group("tag")
+
+                bbox = extract_bounding_box(full_chunk) if image else None
+                doc_label = tag_to_doclabel.get(tag_name, DocItemLabel.PARAGRAPH)
+
+                if tag_name == DocumentToken.OTSL.value:
+                    table_data = parse_table_content(full_chunk)
+                    bbox = extract_bounding_box(full_chunk) if image else None
+
+                    if bbox:
+                        prov = ProvenanceItem(
+                            bbox=bbox.resize_by_scale(pg_width, pg_height),
+                            charspan=(0, 0),
+                            page_no=page_no,
+                        )
+                        self.add_table(data=table_data, prov=prov)
+                    else:
+                        self.add_table(data=table_data)
+
+                elif tag_name == DocItemLabel.PICTURE:
+                    text_caption_content = extract_inner_text(full_chunk)
+                    if image:
+                        if bbox:
+                            im_width, im_height = image.size
+
+                            crop_box = (
+                                int(bbox.l * im_width),
+                                int(bbox.t * im_height),
+                                int(bbox.r * im_width),
+                                int(bbox.b * im_height),
+                            )
+                            cropped_image = image.crop(crop_box)
+                            pic = self.add_picture(
+                                parent=None,
+                                image=ImageRef.from_pil(image=cropped_image, dpi=72),
+                                prov=(
+                                    ProvenanceItem(
+                                        bbox=bbox.resize_by_scale(pg_width, pg_height),
+                                        charspan=(0, 0),
+                                        page_no=page_no,
+                                    )
+                                ),
+                            )
+                            # If there is a caption to an image, add it as well
+                            if len(text_caption_content) > 0:
+                                caption_item = self.add_text(
+                                    label=DocItemLabel.CAPTION,
+                                    text=text_caption_content,
+                                    parent=None,
+                                )
+                                pic.captions.append(caption_item.get_ref())
+                    else:
+                        if bbox:
+                            # In case we don't have access to an binary of an image
+                            self.add_picture(
+                                parent=None,
+                                prov=ProvenanceItem(
+                                    bbox=bbox, charspan=(0, 0), page_no=page_no
+                                ),
+                            )
+                            # If there is a caption to an image, add it as well
+                            if len(text_caption_content) > 0:
+                                caption_item = self.add_text(
+                                    label=DocItemLabel.CAPTION,
+                                    text=text_caption_content,
+                                    parent=None,
+                                )
+                                pic.captions.append(caption_item.get_ref())
+                elif tag_name in [
+                    DocumentToken.ORDERED_LIST.value,
+                    DocumentToken.UNORDERED_LIST.value,
+                ]:
+                    list_label = GroupLabel.LIST
+                    enum_marker = ""
+                    enum_value = 0
+                    if tag_name == DocumentToken.ORDERED_LIST.value:
+                        list_label = GroupLabel.ORDERED_LIST
+
+                    list_item_pattern = (
+                        rf"<(?P<tag>{DocItemLabel.LIST_ITEM})>.*?</(?P=tag)>"
+                    )
+                    li_pattern = re.compile(list_item_pattern, re.DOTALL)
+                    # Add list group:
+                    new_list = self.add_group(label=list_label, name="list")
+                    # Pricess list items
+                    for li_match in li_pattern.finditer(full_chunk):
+                        enum_value += 1
+                        if tag_name == DocumentToken.ORDERED_LIST.value:
+                            enum_marker = str(enum_value) + "."
+
+                        li_full_chunk = li_match.group(0)
+                        li_bbox = extract_bounding_box(li_full_chunk) if image else None
+                        text_content = extract_inner_text(li_full_chunk)
+                        # Add list item
+                        self.add_list_item(
+                            marker=enum_marker,
+                            enumerated=(tag_name == DocumentToken.ORDERED_LIST.value),
+                            parent=new_list,
+                            text=text_content,
+                            prov=(
+                                ProvenanceItem(
+                                    bbox=li_bbox.resize_by_scale(pg_width, pg_height),
+                                    charspan=(0, len(text_content)),
+                                    page_no=page_no,
+                                )
+                                if li_bbox
+                                else None
+                            ),
+                        )
+                else:
+                    # For everything else, treat as text
+                    text_content = extract_inner_text(full_chunk)
+                    self.add_text(
+                        label=doc_label,
+                        text=text_content,
+                        prov=(
+                            ProvenanceItem(
+                                bbox=bbox.resize_by_scale(pg_width, pg_height),
+                                charspan=(0, len(text_content)),
+                                page_no=page_no,
+                            )
+                            if bbox
+                            else None
+                        ),
+                    )
+        return self
+
+    @deprecated("Use save_as_doctags instead.")
+    def save_as_document_tokens(self, *args, **kwargs):
+        r"""Save the document content to a DocumentToken format."""
+        return self.save_as_doctags(*args, **kwargs)
+
+    def save_as_doctags(
         self,
         filename: Path,
         delim: str = "",
@@ -2942,7 +3381,7 @@ class DoclingDocument(BaseModel):
         add_table_cell_location: bool = False,
         add_table_cell_text: bool = True,
     ):
-        r"""Save the document content to a DocumentToken format."""
+        r"""Save the document content to DocTags format."""
         out = self.export_to_document_tokens(
             delim=delim,
             from_element=from_element,

docling_core/types/doc/tokens.py

@@ -50,6 +50,7 @@ class DocumentToken(Enum):
     UNORDERED_LIST = "unordered_list"
     LOC = "loc_"
     PAGE_BREAK = "page_break"
+    SMILES = "smiles"
 
     @classmethod
     def get_special_tokens(

{docling_core-2.21.1.dist-info → docling_core-2.22.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.21.1
+Version: 2.22.0
 Summary: A python library to define and validate data types in Docling.
 Home-page: https://ds4sd.github.io/
 License: MIT

{docling_core-2.21.1.dist-info → docling_core-2.22.0.dist-info}/RECORD

@@ -19,14 +19,14 @@ docling_core/transforms/__init__.py,sha256=P81y_oqkiTN4Ld5crh1gQ6BbHqqR6C6nBt9AC
 docling_core/transforms/chunker/__init__.py,sha256=YdizSKXLmmK9eyYBsarHWr8Mx_AoA0PT7c0absibZMk,306
 docling_core/transforms/chunker/base.py,sha256=BSWTiFOsF5YaZaZJZY8nwIdOXb9uufJMRIds7LxRNh8,2546
 docling_core/transforms/chunker/hierarchical_chunker.py,sha256=MStDUDtzFGc6j8v9AkcAnnSHTDxdoiVrp8FTmRdGqU8,8138
-docling_core/transforms/chunker/hybrid_chunker.py,sha256=kokjDdxjc_gygOokQwYFVnHv2NjWTgf9uex8o0ole7w,9876
+docling_core/transforms/chunker/hybrid_chunker.py,sha256=v-HpFg-HvQLi0gQtHm-6KlMfcMWupkBjwr5qF-rfr4E,9842
 docling_core/types/__init__.py,sha256=MVRSgsk5focwGyAplh_TRR3dEecIXpd98g_u3zZ5HXo,260
 docling_core/types/base.py,sha256=PusJskRVL19y-hq0BgXr5e8--QEqSqLnFNJ8UbOqW88,8318
 docling_core/types/doc/__init__.py,sha256=bysJn2iwjAHwThSWDPXEdVUUij7p_ax12_nx2_0CMdg,653
 docling_core/types/doc/base.py,sha256=22U1qDlD-2ICmgzbdZrjNayoPHnq4S1ks1GRoqB7y1Q,12542
-docling_core/types/doc/document.py,sha256=P8dx5lP3oVrdlrXJx-Y-nk-UM7llDF6ZwOqs046HAM4,110451
+docling_core/types/doc/document.py,sha256=CBNAWaR9UkwmU60N9MYJoygu8fNlTXT-taBRaAURyEo,128879
 docling_core/types/doc/labels.py,sha256=0J9Gsqz-jQ4FP2yxs9wOxoTr3qg97BniFX7MJVziUmk,5684
-docling_core/types/doc/tokens.py,sha256=i73PXkmqXCLsQ5SddnJX8L9e_Ub2_K_DYSE-VE8NDq0,3925
+docling_core/types/doc/tokens.py,sha256=Z2FuzHWinYQzWZdTvOBsEQACAKPcBiSf777w5S9NJms,3947
 docling_core/types/doc/utils.py,sha256=SaiQD-WMMooFm1bMqwatU-IGhtG048iKJb-ppnJit_k,2250
 docling_core/types/gen/__init__.py,sha256=C6TuCfvpSnSL5XDOFMcYHUY2-i08vvfOGRcdu6Af0pI,124
 docling_core/types/gen/generic.py,sha256=l4CZ4_Lb8ONG36WNJWbKX5hGKvTh_yU-hXp5hsm7uVU,844
@@ -56,8 +56,8 @@ docling_core/utils/generate_jsonschema.py,sha256=uNX1O5XnjyB5nA66XqZXTt3YbGuR2ty
 docling_core/utils/legacy.py,sha256=SqNQAxl97aHfoJEsC9vZcMJg5FNkmqKPFi-wdSrnfI0,24442
 docling_core/utils/validate.py,sha256=aQ11UbFyl8iD_N7yTTZmm_VVeXz8KcCyn3GLXgkfYRM,2049
 docling_core/utils/validators.py,sha256=azcrndLzhNkTWnbFSu9shJ5D3j_znnLrIFA5R8hzmGU,2798
-docling_core-2.21.1.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
-docling_core-2.21.1.dist-info/METADATA,sha256=qz2AeXj0vfiBu24oWyMDiQSPvKM0yUn1Rj85JaUd7Yg,5803
-docling_core-2.21.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_core-2.21.1.dist-info/entry_points.txt,sha256=oClcdb2L2RKx4jdqUykY16Kum_f0_whwWhGzIodyidc,216
-docling_core-2.21.1.dist-info/RECORD,,
+docling_core-2.22.0.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
+docling_core-2.22.0.dist-info/METADATA,sha256=NlaL99G-0wcPzYLzYF6W3X-rgt0SXe1DeYuaCYDLQGU,5803
+docling_core-2.22.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_core-2.22.0.dist-info/entry_points.txt,sha256=oClcdb2L2RKx4jdqUykY16Kum_f0_whwWhGzIodyidc,216
+docling_core-2.22.0.dist-info/RECORD,,