docling 1.12.2__tar.gz → 1.13.0__tar.gz

{docling-1.12.2 → docling-1.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.12.2
+Version: 1.13.0
 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 (>=1.4.0,<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)

{docling-1.12.2 → docling-1.13.0}/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,

{docling-1.12.2 → docling-1.13.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.12.2"  # DO NOT EDIT, updated automatically
+version = "1.13.0"  # 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 = "^1.4.0"
 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"