fix: issues with string destination handling in `{Graph,Result}.seria…

…lize`

Change `{Graph,Result}.serialize` to only handle string destinations as URIs if
the schema is `file` and to treat it as operating system paths in all
other cases.

This is for the following reasons:
- `Result.serialize` was treating URI paths as OS paths which only works
  for some cases, for special charachters and percentage encoding it
  does not work.
- Many valid Unix and Windows paths parse using `urlparse` and have no netloc, e.g. `C:\some\path`
  and `some:/path`, however they should be treated as paths and not as URIs.
- `Graph` and `Result` should behave consistently.

Some caveats in this change:
- non-file URIs will now be treated as OS paths which may result in
  slightly confusing error messages, such as
  `FileNotFoundError: [Errno 2] No such file or directory: 'http://example.com/'`
  if http://example.com/ is passed.
- some valid file URIs (e.g. `file:/path/to/file` from https://datatracker.ietf.org/doc/html/rfc8089)
  are also valid Posix paths but will be treated as file-URIs instead of
  Posix paths. For `Graph.serialize` this ambiguity can be avoided by
  using `pathlib.Path`, but for `Result.serialize` there is currently no
  way to avoid it, though I will work on #1834
  soon and in that provide a way to avoid the ambiguity there also.

CHANGELOG.md

@@ -159,6 +159,30 @@ and will be removed for release.
 <!-- -->
 <!-- -->
 
+
+<!-- -->
+<!-- -->
+<!-- CHANGE BARRIER: START #2068 -->
+<!-- -->
+<!-- -->
+
+- Improve file-URI and path handling in `Graph.serialize` and `Result.serialize` to
+  address problems with windows path handling in `Result.serialize` and to make
+  the behavior between `Graph.serialize` and `Result.serialie` more consistent.
+  Closed [issue #2067](https://github.com/RDFLib/rdflib/issues/2067).
+  [PR #2068](https://github.com/RDFLib/rdflib/pull/2068).
+  - If the destination is a string then it will only be handled as a URI if
+    it has a file schema, in all other cases string values will be
+    treated as operating system paths. This change is done primarily because
+    Windows paths (e.g. `C:\some\path`) and some unix paths (e.g. `some:/path`) look like valid URIs with valid schemas but should not be treated as operating system paths.
+  - Simplified file writing to avoid a temporary file.
+
+<!-- -->
+<!-- -->
+<!-- CHANGE BARRIER: END #2068 -->
+<!-- -->
+<!-- -->
+
 <!-- -->
 <!-- -->
 <!-- CHANGE BARRIER: START -->

rdflib/graph.py

@@ -1,9 +1,6 @@
 import logging
-import os
 import pathlib
 import random
-import shutil
-import tempfile
 from io import BytesIO
 from typing import (
     IO,
@@ -1201,20 +1198,20 @@ def serialize(
             serializer.serialize(stream, base=base, encoding=encoding, **args)
         else:
             if isinstance(destination, pathlib.PurePath):
-                location = str(destination)
+                os_path = str(destination)
             else:
                 location = cast(str, destination)
-            scheme, netloc, path, params, _query, fragment = urlparse(location)
-            if netloc != "":
-                raise ValueError(
-                    f"destination {destination} is not a local file reference"
-                )
-            fd, name = tempfile.mkstemp()
-            stream = os.fdopen(fd, "wb")
-            serializer.serialize(stream, base=base, encoding=encoding, **args)
-            stream.close()
-            dest = url2pathname(path) if scheme == "file" else location
-            shutil.move(name, dest)
+                scheme, netloc, path, params, query, fragment = urlparse(location)
+                if scheme == "file":
+                    if netloc != "":
+                        raise ValueError(
+                            f"the file URI {location!r} has an authority component which is not supported"
+                        )
+                    os_path = url2pathname(path)
+                else:
+                    os_path = location
+            with open(os_path, "wb") as stream:
+                serializer.serialize(stream, encoding=encoding, **args)
         return self
 
     def print(self, format="turtle", encoding="utf-8", out=None):
@@ -1276,7 +1273,7 @@ def parse(
         ...   </rdf:Description>
         ... </rdf:RDF>
         ... '''
-        >>> import tempfile
+        >>> import os, tempfile
         >>> fd, file_name = tempfile.mkstemp()
         >>> f = os.fdopen(fd, "w")
         >>> dummy = f.write(my_data)  # Returns num bytes written

rdflib/query.py

@@ -1,12 +1,10 @@
 import itertools
-import os
-import shutil
-import tempfile
 import types
 import warnings
 from io import BytesIO
 from typing import IO, TYPE_CHECKING, List, Optional, Union, cast
 from urllib.parse import urlparse
+from urllib.request import url2pathname
 
 __all__ = [
     "Processor",
@@ -267,16 +265,16 @@ def serialize(
         else:
             location = cast(str, destination)
             scheme, netloc, path, params, query, fragment = urlparse(location)
-            if netloc != "":
-                print(
-                    "WARNING: not saving as location" + "is not a local file reference"
-                )
-                return None
-            fd, name = tempfile.mkstemp()
-            stream = os.fdopen(fd, "wb")
-            serializer.serialize(stream, encoding=encoding, **args)
-            stream.close()
-            shutil.move(name, path)
+            if scheme == "file":
+                if netloc != "":
+                    raise ValueError(
+                        f"the file URI {location!r} has an authority component which is not supported"
+                    )
+                os_path = url2pathname(path)
+            else:
+                os_path = location
+            with open(os_path, "wb") as stream:
+                serializer.serialize(stream, encoding=encoding, **args)
         return None
 
     def __len__(self):

requirements.flake8.txt

@@ -1,3 +1,3 @@
 flake8
-flakeheaven; python_version >= '3.8.0'
+flakeheaven >= 2.1.3; python_version >= '3.8.0'
 pep8-naming

setup.py

@@ -33,7 +33,7 @@
     "dev": [
         "black==22.6.0",
         "flake8",
-        "flakeheaven; python_version >= '3.8.0'",
+        "flakeheaven >= 2.1.3; python_version >= '3.8.0'",
         "isort",
         "mypy",
         "pep8-naming",