docling-core 2.1.0__py3-none-any.whl → 2.2.0__py3-none-any.whl

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 = ""

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.dist-info → docling_core-2.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.1.0
+Version: 2.2.0
 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.dist-info → docling_core-2.2.0.dist-info}/RECORD

@@ -21,7 +21,7 @@ docling_core/types/__init__.py,sha256=MVRSgsk5focwGyAplh_TRR3dEecIXpd98g_u3zZ5HX
 docling_core/types/base.py,sha256=PusJskRVL19y-hq0BgXr5e8--QEqSqLnFNJ8UbOqW88,8318
 docling_core/types/doc/__init__.py,sha256=bEL4zKVOG7Wxm6xQrgF58mu-Teds9aSavuEAKVNhrTU,639
 docling_core/types/doc/base.py,sha256=zvx631U_yQCcJam83hNdDanXEYnO3eN-CCw9vDr6S-I,4442
-docling_core/types/doc/document.py,sha256=e_9oGlLm-QXBLsN3Lk24PeHIrI79DhbQgLVzAl9HFJo,51187
+docling_core/types/doc/document.py,sha256=RMG_iCgKJm71TFVRBrRKzST-Nb9DCgluji9O0BhPt4M,51373
 docling_core/types/doc/labels.py,sha256=mzmSd072A-qW3IThswHxwIHV8IoyTCbHHlNOrisinRA,1335
 docling_core/types/gen/__init__.py,sha256=C6TuCfvpSnSL5XDOFMcYHUY2-i08vvfOGRcdu6Af0pI,124
 docling_core/types/gen/generic.py,sha256=l4CZ4_Lb8ONG36WNJWbKX5hGKvTh_yU-hXp5hsm7uVU,844
@@ -44,13 +44,13 @@ docling_core/types/rec/statement.py,sha256=YwcV4CbVaAbzNwh14yJ_6Py3Ww0XnUJrEEUiK
 docling_core/types/rec/subject.py,sha256=PRCERGTMs4YhR3_Ne6jogkm41zYg8uUWb1yFpM7atm4,2572
 docling_core/utils/__init__.py,sha256=VauNNpWRHG0_ISKrsy5-gTxicrdQZSau6qMfuMl3iqk,120
 docling_core/utils/alias.py,sha256=B6Lqvss8CbaNARHLR4qSmNh9OkB6LvqTpxfsFmkLAFo,874
-docling_core/utils/file.py,sha256=VQgzjyvmJnAIHB6ex7ikcmbDAR4GA1ALreuO7Ubrp50,1895
+docling_core/utils/file.py,sha256=rZ3kaIpX2ZGxtaSXtqjcrivtXvsbeUolLXT-nntQ5yE,2388
 docling_core/utils/generate_docs.py,sha256=BdKAoduWXOc7YMvcmlhjoJOFlUxij1ybxglj6LZDtC8,2290
 docling_core/utils/generate_jsonschema.py,sha256=uNX1O5XnjyB5nA66XqZXTt3YbGuR2tyi_OhHepHYtZg,1654
 docling_core/utils/validate.py,sha256=3FmnxnKTDZC5J9OGxCL3U3DGRl0t0bBV1NcySXswdas,2031
 docling_core/utils/validators.py,sha256=azcrndLzhNkTWnbFSu9shJ5D3j_znnLrIFA5R8hzmGU,2798
-docling_core-2.1.0.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
-docling_core-2.1.0.dist-info/METADATA,sha256=m3L4hgCUX5V8F-09ihSHMn1wRt9qGFBSCGe3ewCQKRg,5432
-docling_core-2.1.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_core-2.1.0.dist-info/entry_points.txt,sha256=jIxlWv3tnO04irlZc0zfhqJIgz1bg9Hha4AkaLWSdUA,177
-docling_core-2.1.0.dist-info/RECORD,,
+docling_core-2.2.0.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
+docling_core-2.2.0.dist-info/METADATA,sha256=3iAaT-ENDYeRWqBtefYohekCqiiXM-AFkJw3lFi3s8o,5432
+docling_core-2.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_core-2.2.0.dist-info/entry_points.txt,sha256=jIxlWv3tnO04irlZc0zfhqJIgz1bg9Hha4AkaLWSdUA,177
+docling_core-2.2.0.dist-info/RECORD,,