docling 1.12.2__tar.gz → 1.13.1__tar.gz

{docling-1.12.2 → docling-1.13.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.12.2
+Version: 1.13.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -21,8 +21,8 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: examples
 Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: deepsearch-glm (>=0.21.0,<0.22.0)
-Requires-Dist: docling-core (>=1.3.0,<2.0.0)
+Requires-Dist: deepsearch-glm (>=0.21.1,<0.22.0)
+Requires-Dist: docling-core (>=1.5.0,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.2.0,<2.0.0)
 Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
@@ -122,7 +122,9 @@ from docling.document_converter import DocumentConverter
 source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
 converter = DocumentConverter()
 result = converter.convert_single(source)
+
 print(result.render_as_markdown())  # output: "## Docling Technical Report[...]"
+print(result.render_as_doctags())  # output: "<document><title><page_1><loc_20>..."
 ```
 
 ### Convert a batch of documents

{docling-1.12.2 → docling-1.13.1}/README.md

@@ -70,7 +70,9 @@ from docling.document_converter import DocumentConverter
 source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
 converter = DocumentConverter()
 result = converter.convert_single(source)
+
 print(result.render_as_markdown())  # output: "## Docling Technical Report[...]"
+print(result.render_as_doctags())  # output: "<document><title><page_1><loc_20>..."
 ```
 
 ### Convert a batch of documents

{docling-1.12.2 → docling-1.13.1}/docling/datamodel/document.py

@@ -368,20 +368,30 @@ class ConvertedDocument(BaseModel):
             "table",
             "figure",
         ],
-        page_tagging: bool = True,
-        location_tagging: bool = True,
-        location_dimensions: Tuple[int, int] = (100, 100),
-        add_new_line: bool = True,
+        xsize: int = 100,
+        ysize: int = 100,
+        add_location: bool = True,
+        add_content: bool = True,
+        add_page_index: bool = True,
+        # table specific flags
+        add_table_cell_location: bool = False,
+        add_table_cell_label: bool = True,
+        add_table_cell_text: bool = True,
     ) -> str:
         return self.output.export_to_document_tokens(
             delim=delim,
             main_text_start=main_text_start,
             main_text_stop=main_text_stop,
             main_text_labels=main_text_labels,
-            page_tagging=page_tagging,
-            location_tagging=location_tagging,
-            location_dimensions=location_dimensions,
-            add_new_line=add_new_line,
+            xsize=xsize,
+            ysize=ysize,
+            add_location=add_location,
+            add_content=add_content,
+            add_page_index=add_page_index,
+            # table specific flags
+            add_table_cell_location=add_table_cell_location,
+            add_table_cell_label=add_table_cell_label,
+            add_table_cell_text=add_table_cell_text,
         )
 
     def render_element_images(

{docling-1.12.2 → docling-1.13.1}/docling/utils/export.py

@@ -9,67 +9,6 @@ from docling.datamodel.document import ConversionResult, Page
 _log = logging.getLogger(__name__)
 
 
-def _export_table_to_html(table: Table):
-
-    # TODO: this is flagged as internal, because we will move it
-    # to the docling-core package.
-
-    def _get_tablecell_span(cell: TableCell, ix):
-        if cell.spans is None:
-            span = set()
-        else:
-            span = set([s[ix] for s in cell.spans])
-        if len(span) == 0:
-            return 1, None, None
-        return len(span), min(span), max(span)
-
-    body = ""
-    nrows = table.num_rows
-    ncols = table.num_cols
-
-    if table.data is None:
-        return ""
-    for i in range(nrows):
-        body += "<tr>"
-        for j in range(ncols):
-            cell: TableCell = table.data[i][j]
-
-            rowspan, rowstart, rowend = _get_tablecell_span(cell, 0)
-            colspan, colstart, colend = _get_tablecell_span(cell, 1)
-
-            if rowstart is not None and rowstart != i:
-                continue
-            if colstart is not None and colstart != j:
-                continue
-
-            if rowstart is None:
-                rowstart = i
-            if colstart is None:
-                colstart = j
-
-            content = cell.text.strip()
-            label = cell.obj_type
-            label_class = "body"
-            celltag = "td"
-            if label in ["row_header", "row_multi_header", "row_title"]:
-                label_class = "header"
-            elif label in ["col_header", "col_multi_header"]:
-                label_class = "header"
-                celltag = "th"
-
-            opening_tag = f"{celltag}"
-            if rowspan > 1:
-                opening_tag += f' rowspan="{rowspan}"'
-            if colspan > 1:
-                opening_tag += f' colspan="{colspan}"'
-
-            body += f"<{opening_tag}>{content}</{celltag}>"
-        body += "</tr>"
-    body = f"<table>{body}</table>"
-
-    return body
-
-
 def generate_multimodal_pages(
     doc_result: ConversionResult,
 ) -> Iterable[Tuple[str, str, List[Dict[str, Any]], List[Dict[str, Any]], Page]]:
@@ -129,7 +68,7 @@ def generate_multimodal_pages(
             }
 
             if isinstance(item, Table):
-                table_html = _export_table_to_html(item)
+                table_html = item.export_to_html()
                 new_segment["data"].append(
                     {
                         "html_seq": table_html,
@@ -172,7 +111,7 @@ def generate_multimodal_pages(
         )
         # No page-tagging since we only do 1 page at the time
         content_dt = doc.export_to_document_tokens(
-            main_text_start=start_ix, main_text_stop=end_ix, page_tagging=False
+            main_text_start=start_ix, main_text_stop=end_ix, add_page_index=False
         )
 
         return content_text, content_md, content_dt, page_cells, page_segments, page

{docling-1.12.2 → docling-1.13.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.12.2"  # DO NOT EDIT, updated automatically
+version = "1.13.1"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -23,9 +23,9 @@ packages = [{include = "docling"}]
 [tool.poetry.dependencies]
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^1.3.0"
+docling-core = "^1.5.0"
 docling-ibm-models = "^1.2.0"
-deepsearch-glm = "^0.21.0"
+deepsearch-glm = "^0.21.1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"