docling-core 2.78.0__tar.gz → 2.78.1__tar.gz

{docling_core-2.78.0 → docling_core-2.78.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling-core
-Version: 2.78.0
+Version: 2.78.1
 Summary: A python library to define and validate data types in Docling.
 Author-email: Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 Maintainer-email: Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>
@@ -47,7 +47,8 @@ Requires-Dist: tree-sitter-python>=0.23.6; extra == "chunking"
 Requires-Dist: tree-sitter-c>=0.23.4; extra == "chunking"
 Requires-Dist: tree-sitter-javascript>=0.23.1; extra == "chunking"
 Requires-Dist: tree-sitter-typescript>=0.23.2; extra == "chunking"
-Requires-Dist: transformers<6.0.0,>=4.34.0; extra == "chunking"
+Requires-Dist: transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,<5.9.0,>=4.34.0; sys_platform == "darwin" and extra == "chunking"
+Requires-Dist: transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,<6.0.0,>=4.34.0; sys_platform != "darwin" and extra == "chunking"
 Provides-Extra: chunking-openai
 Requires-Dist: semchunk<4.0.0,>=2.2.0; extra == "chunking-openai"
 Requires-Dist: tree-sitter<0.27.0,>=0.25.0; extra == "chunking-openai"

{docling_core-2.78.0 → docling_core-2.78.1}/docling_core/utils/file.py

@@ -182,6 +182,10 @@ def resolve_source_to_stream(
         stream = BytesIO(res.content)
         doc_stream = DocumentStream(name=fname, stream=stream)
     except ValidationError:
+        if isinstance(source, str) and "://" in source:
+            scheme = source.split("://", 1)[0].lower()
+            if scheme not in ("http", "https"):
+                raise ValueError(f"Unsupported URL scheme: '{scheme}'. Only http:// and https:// are supported.")
         try:
             local_path = TypeAdapter(Path).validate_python(source)
             stream = BytesIO(local_path.read_bytes())

{docling_core-2.78.0 → docling_core-2.78.1}/docling_core.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling-core
-Version: 2.78.0
+Version: 2.78.1
 Summary: A python library to define and validate data types in Docling.
 Author-email: Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 Maintainer-email: Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>
@@ -47,7 +47,8 @@ Requires-Dist: tree-sitter-python>=0.23.6; extra == "chunking"
 Requires-Dist: tree-sitter-c>=0.23.4; extra == "chunking"
 Requires-Dist: tree-sitter-javascript>=0.23.1; extra == "chunking"
 Requires-Dist: tree-sitter-typescript>=0.23.2; extra == "chunking"
-Requires-Dist: transformers<6.0.0,>=4.34.0; extra == "chunking"
+Requires-Dist: transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,<5.9.0,>=4.34.0; sys_platform == "darwin" and extra == "chunking"
+Requires-Dist: transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,<6.0.0,>=4.34.0; sys_platform != "darwin" and extra == "chunking"
 Provides-Extra: chunking-openai
 Requires-Dist: semchunk<4.0.0,>=2.2.0; extra == "chunking-openai"
 Requires-Dist: tree-sitter<0.27.0,>=0.25.0; extra == "chunking-openai"

{docling_core-2.78.0 → docling_core-2.78.1}/docling_core.egg-info/requires.txt

@@ -18,7 +18,6 @@ tree-sitter-python>=0.23.6
 tree-sitter-c>=0.23.4
 tree-sitter-javascript>=0.23.1
 tree-sitter-typescript>=0.23.2
-transformers<6.0.0,>=4.34.0
 
 [chunking-openai]
 semchunk<4.0.0,>=2.2.0
@@ -29,6 +28,12 @@ tree-sitter-javascript>=0.23.1
 tree-sitter-typescript>=0.23.2
 tiktoken<0.13.0,>=0.9.0
 
+[chunking:sys_platform != "darwin"]
+transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,<6.0.0,>=4.34.0
+
+[chunking:sys_platform == "darwin"]
+transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,<5.9.0,>=4.34.0
+
 [examples]
 datasets>=4.0.0
 matplotlib>=3.7.0

{docling_core-2.78.0 → docling_core-2.78.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-core"
-version = "2.78.0"  # DO NOT EDIT, updated automatically
+version = "2.78.1"  # DO NOT EDIT, updated automatically
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 license-files = ["LICENSE"]
@@ -77,7 +77,9 @@ chunking = [
     'tree-sitter-typescript >=0.23.2',
 
     # specific:
-    'transformers (>=4.34.0,<6.0.0)',
+    # temporary solution until huggingface/transformers#46159 is resolved
+    'transformers (>=4.34.0,<5.9.0,!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*) ; sys_platform == "darwin"',
+    'transformers (>=4.34.0,<6.0.0,!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*) ; sys_platform != "darwin"',
 ]
 chunking-openai = [
     # common:

{docling_core-2.78.0 → docling_core-2.78.1}/test/test_utils.py

@@ -218,9 +218,10 @@ def test_is_safe_url_rejects_private_networks():
 
 def test_resolve_remote_filename_sanitizes_content_disposition(monkeypatch):
     """Test filename normalization from Content-Disposition."""
-    from docling_core.utils.file import resolve_source_to_stream
     from requests import Response
 
+    from docling_core.utils.file import resolve_source_to_stream
+
     def get_response(*args, **kwargs):
         r = Response()
         r.status_code = 200
@@ -236,9 +237,10 @@ def test_resolve_remote_filename_sanitizes_content_disposition(monkeypatch):
 
 def test_resolve_source_rejects_non_public_urls(monkeypatch):
     """Test that non-public URLs are rejected."""
-    from docling_core.utils.file import resolve_source_to_stream
     import pytest
 
+    from docling_core.utils.file import resolve_source_to_stream
+
     with pytest.raises(ValueError, match="URL is not allowed"):
         resolve_source_to_stream("http://127.0.0.1/file")
 
@@ -252,11 +254,22 @@ def test_resolve_source_rejects_non_public_urls(monkeypatch):
         resolve_source_to_stream("http://169.254.169.254/latest/meta-data/")
 
 
+def test_resolve_source_rejects_unsupported_scheme():
+    """Test that unsupported URL schemes are rejected before file fallback."""
+    import pytest
+
+    from docling_core.utils.file import resolve_source_to_stream
+
+    with pytest.raises(ValueError, match="Unsupported URL scheme"):
+        resolve_source_to_stream("ftp://some-server/file.pdf")
+
+
 def test_resolve_source_to_path_sanitizes_filename(monkeypatch, tmp_path):
     """Test that saved filenames stay within the target directory."""
-    from docling_core.utils.file import resolve_source_to_path
     from requests import Response
 
+    from docling_core.utils.file import resolve_source_to_path
+
     def get_response(*args, **kwargs):
         r = Response()
         r.status_code = 200
@@ -280,8 +293,9 @@ def test_resolve_source_to_path_sanitizes_filename(monkeypatch, tmp_path):
 
 def test_redirect_limit_enforced(monkeypatch):
     """Test that redirect limits are configured on the session."""
+    from requests import Response, Session
+
     from docling_core.utils.file import _MAX_REDIRECTS
-    from requests import Session, Response
 
     session_created = []
 
@@ -313,23 +327,21 @@ def test_redirect_limit_enforced(monkeypatch):
     assert session.max_redirects == _MAX_REDIRECTS
 
 
-
 def test_redirect_to_non_public_ip_rejected(monkeypatch):
     """Test that redirects to non-public addresses are rejected."""
-    from docling_core.utils.file import resolve_source_to_stream
-    from requests import Response, Session
     import pytest
+    from requests import Response, Session
 
-    original_get = Session.get
+    from docling_core.utils.file import resolve_source_to_stream
 
     def mock_get_with_redirect(self, *args, **kwargs):
         r = Response()
         r.status_code = 302
-        r.headers['location'] = 'http://192.168.1.1/private-file'
-        r.url = args[0] if args else kwargs.get('url', 'http://example.com')
+        r.headers["location"] = "http://192.168.1.1/private-file"
+        r.url = args[0] if args else kwargs.get("url", "http://example.com")
 
-        if hasattr(self, 'hooks') and 'response' in self.hooks:
-            for hook in self.hooks['response']:
+        if hasattr(self, "hooks") and "response" in self.hooks:
+            for hook in self.hooks["response"]:
                 hook(r)
 
         return r