docling-core 2.1.0__tar.gz → 2.2.1__tar.gz

{docling_core-2.1.0 → docling_core-2.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.1.0
+Version: 2.2.1
 Summary: A python library to define and validate data types in Docling.
 Home-page: https://ds4sd.github.io/
 License: MIT

{docling_core-2.1.0 → docling_core-2.2.1}/docling_core/types/doc/document.py

@@ -591,7 +591,13 @@ class TableItem(FloatingItem):
         for row in self.data.grid:
             tmp = []
             for col in row:
-                tmp.append(col.text)
+
+                # make sure that md tables are not broken
+                # due to newline chars in the text
+                text = col.text
+                text = text.replace("\n", " ")
+                tmp.append(text)
+
             table.append(tmp)
 
         md_table = ""
@@ -1285,6 +1291,18 @@ class DoclingDocument(BaseModel):
         mdtext = re.sub(
             r"\n\n\n+", "\n\n", mdtext
         )  # remove cases of double or more empty lines.
+
+        # Our export markdown doesn't contain any emphasis styling:
+        # Bold, Italic, or Bold-Italic
+        # Hence, any underscore that we print into Markdown is coming from document text
+        # That means we need to escape it, to properly reflect content in the markdown
+        def escape_underscores(text):
+            # Replace "_" with "\_" only if it's not already escaped
+            escaped_text = re.sub(r"(?<!\\)_", r"\_", text)
+            return escaped_text
+
+        mdtext = escape_underscores(mdtext)
+
         return mdtext
 
     def export_to_text(  # noqa: C901

{docling_core-2.1.0 → docling_core-2.2.1}/docling_core/utils/file.py

@@ -5,15 +5,18 @@
 
 """File-related utilities."""
 
+import importlib
 import tempfile
 from pathlib import Path
-from typing import Union
+from typing import Dict, Optional, Union
 
 import requests
 from pydantic import AnyHttpUrl, TypeAdapter, ValidationError
 
 
-def resolve_file_source(source: Union[Path, AnyHttpUrl, str]) -> Path:
+def resolve_file_source(
+    source: Union[Path, AnyHttpUrl, str], headers: Optional[Dict[str, str]] = None
+) -> Path:
     """Resolves the source (URL, path) of a file to a local file path.
 
     If a URL is provided, the content is first downloaded to a temporary local file.
@@ -29,7 +32,17 @@ def resolve_file_source(source: Union[Path, AnyHttpUrl, str]) -> Path:
     """
     try:
         http_url: AnyHttpUrl = TypeAdapter(AnyHttpUrl).validate_python(source)
-        res = requests.get(http_url, stream=True)
+
+        # make all header keys lower case
+        _headers = headers or {}
+        req_headers = {k.lower(): v for k, v in _headers.items()}
+        # add user-agent is not set
+        if "user-agent" not in req_headers:
+            agent_name = f"docling-core/{importlib.metadata.version('docling-core')}"
+            req_headers["user-agent"] = agent_name
+
+        # fetch the page
+        res = requests.get(http_url, stream=True, headers=req_headers)
         res.raise_for_status()
         fname = None
         # try to get filename from response header
@@ -41,7 +54,7 @@ def resolve_file_source(source: Union[Path, AnyHttpUrl, str]) -> Path:
                     break
         # otherwise, use name from URL:
         if fname is None:
-            fname = Path(http_url.path or "file").name
+            fname = Path(http_url.path or "").name or "file"
         local_path = Path(tempfile.mkdtemp()) / fname
         with open(local_path, "wb") as f:
             for chunk in res.iter_content(chunk_size=1024):  # using 1-KB chunks

{docling_core-2.1.0 → docling_core-2.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-core"
-version = "2.1.0"
+version = "2.2.1"
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 authors = [