jentic-openapi-common 1.0.0a15__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
@@ -0,0 +1,4 @@
1
+ Jentic OpenAPI Tools
2
+ Copyright (c) 2025 Jentic
3
+ Jentic OpenAPI Tools is licensed under Apache 2.0 license.
4
+ Copy of the Apache 2.0 license can be found in `LICENSE` file.
@@ -0,0 +1,224 @@
1
+ Metadata-Version: 2.4
2
+ Name: jentic-openapi-common
3
+ Version: 1.0.0a15
4
+ Summary: Jentic OpenAPI Common
5
+ Author: Jentic
6
+ Author-email: Jentic <hello@jentic.com>
7
+ License-Expression: Apache-2.0
8
+ License-File: LICENSE
9
+ License-File: NOTICE
10
+ Requires-Python: >=3.11
11
+ Project-URL: Homepage, https://github.com/jentic/jentic-openapi-tools
12
+ Description-Content-Type: text/markdown
13
+
14
+ # jentic-openapi-common
15
+
16
+ Common utilities for OpenAPI tools packages. This package provides shared functionality using PEP 420 namespace packages as contribution points.
17
+
18
+ ## Installation
19
+
20
+ ```bash
21
+ uv add jentic-openapi-common
22
+ ```
23
+
24
+ ## Modules
25
+
26
+ ### uri
27
+
28
+ URI/URL/path utilities for working with OpenAPI document references.
29
+
30
+ **Available functions:**
31
+
32
+ - `is_uri_like(s: str | None) -> bool` - Check if a string looks like a URI/URL/path
33
+ - `is_http_https_url(s: str | None) -> bool` - Check if string is an HTTP(S) URL
34
+ - `is_file_uri(s: str | None) -> bool` - Check if string is a file:// URI
35
+ - `is_path(s: str | None) -> bool` - Check if string is a filesystem path (not a URL)
36
+ - `resolve_to_absolute(uri: str, base_uri: str | None = None) -> str` - Resolve relative URIs to absolute
37
+
38
+ **Exceptions:**
39
+
40
+ - `URIResolutionError` - Raised when URI resolution fails
41
+
42
+ ### path_security
43
+
44
+ Path security utilities for validating and securing filesystem access. Provides defense-in-depth protection against path traversal attacks, directory escapes, and unauthorized file access.
45
+
46
+ **Available functions:**
47
+
48
+ - `validate_path(path, *, allowed_base=None, allowed_extensions=None, resolve_symlinks=True, as_string=True) -> str | Path` - Validate and canonicalize a filesystem path with security checks. Returns `str` by default, or `Path` when `as_string=False`
49
+
50
+ **Exceptions:**
51
+
52
+ - `PathSecurityError` - Base exception for path security violations
53
+ - `PathTraversalError` - Path attempts to escape allowed base directory
54
+ - `InvalidExtensionError` - Path has disallowed file extension
55
+ - `SymlinkSecurityError` - Path contains symlinks when not allowed or symlink escapes boundary
56
+
57
+ ### subproc
58
+
59
+ Subprocess execution utilities with enhanced error handling and cross-platform support.
60
+
61
+ ## Usage Examples
62
+
63
+ ### URI Utilities
64
+
65
+ ```python
66
+ from jentic.apitools.openapi.common.uri import (
67
+ is_uri_like,
68
+ is_http_https_url,
69
+ is_file_uri,
70
+ is_path,
71
+ resolve_to_absolute,
72
+ URIResolutionError,
73
+ )
74
+
75
+ # Check URI types
76
+ is_uri_like("https://example.com/spec.yaml") # True
77
+ is_http_https_url("https://example.com/spec.yaml") # True
78
+ is_file_uri("file:///home/user/spec.yaml") # True
79
+ is_path("/home/user/spec.yaml") # True
80
+ is_path("https://example.com/spec.yaml") # False
81
+
82
+ # Resolve relative URIs
83
+ absolute = resolve_to_absolute("../spec.yaml", "/home/user/project/docs/")
84
+ # Returns: "/home/user/project/spec.yaml"
85
+
86
+ absolute = resolve_to_absolute("spec.yaml") # Resolves against current working directory
87
+ ```
88
+
89
+ ### Path Security
90
+
91
+ ```python
92
+ from pathlib import Path
93
+ from jentic.apitools.openapi.common.path_security import (
94
+ validate_path,
95
+ PathSecurityError,
96
+ PathTraversalError,
97
+ InvalidExtensionError,
98
+ SymlinkSecurityError,
99
+ )
100
+
101
+ # Basic validation - converts to absolute path (returns string by default)
102
+ safe_path = validate_path("./specs/openapi.yaml")
103
+ print(safe_path) # '/current/working/dir/specs/openapi.yaml'
104
+ print(type(safe_path)) # <class 'str'>
105
+
106
+ # Request Path object with as_string=False
107
+ safe_path_obj = validate_path("./specs/openapi.yaml", as_string=False)
108
+ print(safe_path_obj) # Path('/current/working/dir/specs/openapi.yaml')
109
+ print(type(safe_path_obj)) # <class 'pathlib.Path'>
110
+
111
+ # Return type control with as_string parameter
112
+ # - as_string=True (default): Returns str - best for subprocess commands
113
+ # - as_string=False: Returns Path - best for file operations with pathlib
114
+
115
+ # Example: Using with subprocess commands (default string return)
116
+ import subprocess
117
+ doc_path = validate_path("./specs/openapi.yaml")
118
+ subprocess.run(["cat", doc_path]) # Works directly, no str() conversion needed
119
+
120
+ # Example: Using with pathlib operations (Path return)
121
+ from pathlib import Path
122
+ doc_path = validate_path("./specs/openapi.yaml", as_string=False)
123
+ if doc_path.exists():
124
+ content = doc_path.read_text() # Path methods available
125
+
126
+ # Boundary enforcement - restrict access to specific directory
127
+ try:
128
+ safe_path = validate_path(
129
+ "/var/app/data/spec.yaml",
130
+ allowed_base="/var/app",
131
+ )
132
+ print(f"Access granted: {safe_path}")
133
+ except PathTraversalError as e:
134
+ print(f"Access denied: {e}")
135
+
136
+ # Block directory traversal attacks
137
+ try:
138
+ safe_path = validate_path(
139
+ "/var/app/../../../etc/passwd",
140
+ allowed_base="/var/app",
141
+ )
142
+ except PathTraversalError:
143
+ print("Path traversal attack blocked!")
144
+
145
+ # Extension validation - whitelist approach
146
+ try:
147
+ safe_path = validate_path(
148
+ "spec.yaml",
149
+ allowed_extensions=(".yaml", ".yml", ".json"),
150
+ )
151
+ print(f"Valid extension: {safe_path}")
152
+ except InvalidExtensionError:
153
+ print("Invalid file extension")
154
+
155
+ # Combined security checks (recommended for web services)
156
+ try:
157
+ safe_path = validate_path(
158
+ user_provided_path,
159
+ allowed_base="/var/app/uploads",
160
+ allowed_extensions=(".yaml", ".yml", ".json"),
161
+ resolve_symlinks=True, # Default: resolve and check symlinks
162
+ )
163
+ # Safe to use safe_path for file operations
164
+ with open(safe_path) as f:
165
+ content = f.read()
166
+ except PathSecurityError as e:
167
+ print(f"Security validation failed: {e}")
168
+ ```
169
+
170
+ ### Subprocess Execution
171
+
172
+ #### Basic Command Execution
173
+
174
+ ```python
175
+ from jentic.apitools.openapi.common.subproc import run_subprocess
176
+
177
+ # Simple command
178
+ result = run_subprocess(["echo", "hello"])
179
+ print(result.stdout) # "hello\n"
180
+ print(result.returncode) # 0
181
+
182
+ # Command with working directory
183
+ result = run_subprocess(["pwd"], cwd="/tmp")
184
+ print(result.stdout.strip()) # "/tmp"
185
+ ```
186
+
187
+ ### Error Handling
188
+
189
+ ```python
190
+ from jentic.apitools.openapi.common.subproc import (
191
+ run_subprocess,
192
+ SubprocessExecutionError
193
+ )
194
+
195
+ # Handle errors manually
196
+ result = run_subprocess(["false"]) # Command that exits with code 1
197
+ if result.returncode != 0:
198
+ print(f"Command failed with code {result.returncode}")
199
+
200
+ # Automatic error handling
201
+ try:
202
+ result = run_subprocess(["false"], fail_on_error=True)
203
+ except SubprocessExecutionError as e:
204
+ print(f"Command {e.cmd} failed: {e}")
205
+ ```
206
+
207
+ ### Advanced Usage
208
+
209
+ ```python
210
+ from jentic.apitools.openapi.common.subproc import (
211
+ run_subprocess,
212
+ SubprocessExecutionError
213
+ )
214
+
215
+ # Timeout handling
216
+ try:
217
+ result = run_subprocess(["sleep", "10"], timeout=1)
218
+ except SubprocessExecutionError as e:
219
+ print("Command timed out")
220
+
221
+ # Custom encoding
222
+ result = run_subprocess(["python", "-c", "print('ñ')"], encoding="utf-8")
223
+ print(result.stdout) # "ñ\n"
224
+ ```
@@ -0,0 +1,211 @@
1
+ # jentic-openapi-common
2
+
3
+ Common utilities for OpenAPI tools packages. This package provides shared functionality using PEP 420 namespace packages as contribution points.
4
+
5
+ ## Installation
6
+
7
+ ```bash
8
+ uv add jentic-openapi-common
9
+ ```
10
+
11
+ ## Modules
12
+
13
+ ### uri
14
+
15
+ URI/URL/path utilities for working with OpenAPI document references.
16
+
17
+ **Available functions:**
18
+
19
+ - `is_uri_like(s: str | None) -> bool` - Check if a string looks like a URI/URL/path
20
+ - `is_http_https_url(s: str | None) -> bool` - Check if string is an HTTP(S) URL
21
+ - `is_file_uri(s: str | None) -> bool` - Check if string is a file:// URI
22
+ - `is_path(s: str | None) -> bool` - Check if string is a filesystem path (not a URL)
23
+ - `resolve_to_absolute(uri: str, base_uri: str | None = None) -> str` - Resolve relative URIs to absolute
24
+
25
+ **Exceptions:**
26
+
27
+ - `URIResolutionError` - Raised when URI resolution fails
28
+
29
+ ### path_security
30
+
31
+ Path security utilities for validating and securing filesystem access. Provides defense-in-depth protection against path traversal attacks, directory escapes, and unauthorized file access.
32
+
33
+ **Available functions:**
34
+
35
+ - `validate_path(path, *, allowed_base=None, allowed_extensions=None, resolve_symlinks=True, as_string=True) -> str | Path` - Validate and canonicalize a filesystem path with security checks. Returns `str` by default, or `Path` when `as_string=False`
36
+
37
+ **Exceptions:**
38
+
39
+ - `PathSecurityError` - Base exception for path security violations
40
+ - `PathTraversalError` - Path attempts to escape allowed base directory
41
+ - `InvalidExtensionError` - Path has disallowed file extension
42
+ - `SymlinkSecurityError` - Path contains symlinks when not allowed or symlink escapes boundary
43
+
44
+ ### subproc
45
+
46
+ Subprocess execution utilities with enhanced error handling and cross-platform support.
47
+
48
+ ## Usage Examples
49
+
50
+ ### URI Utilities
51
+
52
+ ```python
53
+ from jentic.apitools.openapi.common.uri import (
54
+ is_uri_like,
55
+ is_http_https_url,
56
+ is_file_uri,
57
+ is_path,
58
+ resolve_to_absolute,
59
+ URIResolutionError,
60
+ )
61
+
62
+ # Check URI types
63
+ is_uri_like("https://example.com/spec.yaml") # True
64
+ is_http_https_url("https://example.com/spec.yaml") # True
65
+ is_file_uri("file:///home/user/spec.yaml") # True
66
+ is_path("/home/user/spec.yaml") # True
67
+ is_path("https://example.com/spec.yaml") # False
68
+
69
+ # Resolve relative URIs
70
+ absolute = resolve_to_absolute("../spec.yaml", "/home/user/project/docs/")
71
+ # Returns: "/home/user/project/spec.yaml"
72
+
73
+ absolute = resolve_to_absolute("spec.yaml") # Resolves against current working directory
74
+ ```
75
+
76
+ ### Path Security
77
+
78
+ ```python
79
+ from pathlib import Path
80
+ from jentic.apitools.openapi.common.path_security import (
81
+ validate_path,
82
+ PathSecurityError,
83
+ PathTraversalError,
84
+ InvalidExtensionError,
85
+ SymlinkSecurityError,
86
+ )
87
+
88
+ # Basic validation - converts to absolute path (returns string by default)
89
+ safe_path = validate_path("./specs/openapi.yaml")
90
+ print(safe_path) # '/current/working/dir/specs/openapi.yaml'
91
+ print(type(safe_path)) # <class 'str'>
92
+
93
+ # Request Path object with as_string=False
94
+ safe_path_obj = validate_path("./specs/openapi.yaml", as_string=False)
95
+ print(safe_path_obj) # Path('/current/working/dir/specs/openapi.yaml')
96
+ print(type(safe_path_obj)) # <class 'pathlib.Path'>
97
+
98
+ # Return type control with as_string parameter
99
+ # - as_string=True (default): Returns str - best for subprocess commands
100
+ # - as_string=False: Returns Path - best for file operations with pathlib
101
+
102
+ # Example: Using with subprocess commands (default string return)
103
+ import subprocess
104
+ doc_path = validate_path("./specs/openapi.yaml")
105
+ subprocess.run(["cat", doc_path]) # Works directly, no str() conversion needed
106
+
107
+ # Example: Using with pathlib operations (Path return)
108
+ from pathlib import Path
109
+ doc_path = validate_path("./specs/openapi.yaml", as_string=False)
110
+ if doc_path.exists():
111
+ content = doc_path.read_text() # Path methods available
112
+
113
+ # Boundary enforcement - restrict access to specific directory
114
+ try:
115
+ safe_path = validate_path(
116
+ "/var/app/data/spec.yaml",
117
+ allowed_base="/var/app",
118
+ )
119
+ print(f"Access granted: {safe_path}")
120
+ except PathTraversalError as e:
121
+ print(f"Access denied: {e}")
122
+
123
+ # Block directory traversal attacks
124
+ try:
125
+ safe_path = validate_path(
126
+ "/var/app/../../../etc/passwd",
127
+ allowed_base="/var/app",
128
+ )
129
+ except PathTraversalError:
130
+ print("Path traversal attack blocked!")
131
+
132
+ # Extension validation - whitelist approach
133
+ try:
134
+ safe_path = validate_path(
135
+ "spec.yaml",
136
+ allowed_extensions=(".yaml", ".yml", ".json"),
137
+ )
138
+ print(f"Valid extension: {safe_path}")
139
+ except InvalidExtensionError:
140
+ print("Invalid file extension")
141
+
142
+ # Combined security checks (recommended for web services)
143
+ try:
144
+ safe_path = validate_path(
145
+ user_provided_path,
146
+ allowed_base="/var/app/uploads",
147
+ allowed_extensions=(".yaml", ".yml", ".json"),
148
+ resolve_symlinks=True, # Default: resolve and check symlinks
149
+ )
150
+ # Safe to use safe_path for file operations
151
+ with open(safe_path) as f:
152
+ content = f.read()
153
+ except PathSecurityError as e:
154
+ print(f"Security validation failed: {e}")
155
+ ```
156
+
157
+ ### Subprocess Execution
158
+
159
+ #### Basic Command Execution
160
+
161
+ ```python
162
+ from jentic.apitools.openapi.common.subproc import run_subprocess
163
+
164
+ # Simple command
165
+ result = run_subprocess(["echo", "hello"])
166
+ print(result.stdout) # "hello\n"
167
+ print(result.returncode) # 0
168
+
169
+ # Command with working directory
170
+ result = run_subprocess(["pwd"], cwd="/tmp")
171
+ print(result.stdout.strip()) # "/tmp"
172
+ ```
173
+
174
+ ### Error Handling
175
+
176
+ ```python
177
+ from jentic.apitools.openapi.common.subproc import (
178
+ run_subprocess,
179
+ SubprocessExecutionError
180
+ )
181
+
182
+ # Handle errors manually
183
+ result = run_subprocess(["false"]) # Command that exits with code 1
184
+ if result.returncode != 0:
185
+ print(f"Command failed with code {result.returncode}")
186
+
187
+ # Automatic error handling
188
+ try:
189
+ result = run_subprocess(["false"], fail_on_error=True)
190
+ except SubprocessExecutionError as e:
191
+ print(f"Command {e.cmd} failed: {e}")
192
+ ```
193
+
194
+ ### Advanced Usage
195
+
196
+ ```python
197
+ from jentic.apitools.openapi.common.subproc import (
198
+ run_subprocess,
199
+ SubprocessExecutionError
200
+ )
201
+
202
+ # Timeout handling
203
+ try:
204
+ result = run_subprocess(["sleep", "10"], timeout=1)
205
+ except SubprocessExecutionError as e:
206
+ print("Command timed out")
207
+
208
+ # Custom encoding
209
+ result = run_subprocess(["python", "-c", "print('ñ')"], encoding="utf-8")
210
+ print(result.stdout) # "ñ\n"
211
+ ```
@@ -0,0 +1,27 @@
1
+ [project]
2
+ name = "jentic-openapi-common"
3
+ version = "1.0.0-alpha.15"
4
+ description = "Jentic OpenAPI Common"
5
+ readme = "README.md"
6
+ authors = [{ name = "Jentic", email = "hello@jentic.com" }]
7
+ license = "Apache-2.0"
8
+ license-files = ["LICENSE", "NOTICE"]
9
+ requires-python = ">=3.11"
10
+ dependencies = []
11
+
12
+ [tool.uv]
13
+ package = true
14
+
15
+ [tool.uv.build-backend]
16
+ namespace = true
17
+ module-name = "jentic.apitools.openapi.common"
18
+ module-root = "src/"
19
+
20
+ [project.urls]
21
+ Homepage = "https://github.com/jentic/jentic-openapi-tools"
22
+
23
+ [build-system]
24
+ requires = ["uv_build~=0.8.15"]
25
+ build-backend = "uv_build"
26
+
27
+
@@ -0,0 +1,176 @@
1
+ """Path security utilities for safe filesystem access."""
2
+
3
+ from pathlib import Path
4
+ from typing import Literal, overload
5
+
6
+
7
+ __all__ = [
8
+ "PathSecurityError",
9
+ "PathTraversalError",
10
+ "InvalidExtensionError",
11
+ "SymlinkSecurityError",
12
+ "validate_path",
13
+ ]
14
+
15
+
16
+ class PathSecurityError(Exception):
17
+ """Base exception for path security violations."""
18
+
19
+ pass
20
+
21
+
22
+ class PathTraversalError(PathSecurityError):
23
+ """Raised when a path attempts to escape the allowed base directory."""
24
+
25
+ pass
26
+
27
+
28
+ class InvalidExtensionError(PathSecurityError):
29
+ """Raised when a file has a disallowed extension."""
30
+
31
+ pass
32
+
33
+
34
+ class SymlinkSecurityError(PathSecurityError):
35
+ """Raised when a path contains symlinks when not allowed or symlink escapes boundary."""
36
+
37
+ pass
38
+
39
+
40
+ @overload
41
+ def validate_path(
42
+ path: str | Path,
43
+ *,
44
+ allowed_base: str | Path | None = None,
45
+ allowed_extensions: tuple[str, ...] | None = None,
46
+ resolve_symlinks: bool = True,
47
+ as_string: Literal[True] = True,
48
+ ) -> str: ...
49
+
50
+
51
+ @overload
52
+ def validate_path(
53
+ path: str | Path,
54
+ *,
55
+ allowed_base: str | Path | None = None,
56
+ allowed_extensions: tuple[str, ...] | None = None,
57
+ resolve_symlinks: bool = True,
58
+ as_string: Literal[False],
59
+ ) -> Path: ...
60
+
61
+
62
+ def validate_path(
63
+ path: str | Path,
64
+ *,
65
+ allowed_base: str | Path | None = None,
66
+ allowed_extensions: tuple[str, ...] | None = None,
67
+ resolve_symlinks: bool = True,
68
+ as_string: bool = True,
69
+ ) -> str | Path:
70
+ """
71
+ Validate and canonicalize a filesystem path with security checks.
72
+
73
+ This function provides defense-in-depth security for filesystem access by:
74
+ 1. Converting to absolute path and resolving `.` and `..` components
75
+ 2. Optionally resolving symlinks and checking they don't escape boundaries
76
+ 3. Enforcing boundary restrictions (path must be within allowed_base)
77
+ 4. Validating file extensions against a whitelist
78
+
79
+ Args:
80
+ path: The filesystem path to validate (string or Path object)
81
+ allowed_base: Optional base directory that path must be within.
82
+ If None, no boundary checking is performed.
83
+ allowed_extensions: Optional tuple of allowed file extensions (e.g., ('.yaml', '.json')).
84
+ Extensions are case-sensitive. If None, no extension checking is performed.
85
+ resolve_symlinks: If True (default), resolve symlinks using Path.resolve().
86
+ If False, use Path.absolute() to preserve symlinks.
87
+ as_string: If True (default), return str. If False, return Path object.
88
+
89
+ Returns:
90
+ Canonicalized path (str by default, or Path if as_string=False) that has passed all security checks.
91
+
92
+ Raises:
93
+ PathTraversalError: If the path attempts to escape the allowed_base directory
94
+ InvalidExtensionError: If the file extension is not in allowed_extensions
95
+ SymlinkSecurityError: If symlink resolution reveals a security issue
96
+
97
+ Examples:
98
+ >>> # Basic validation with boundary enforcement (returns str by default)
99
+ >>> validate_path("/var/app/data/file.yaml", allowed_base="/var/app")
100
+ '/var/app/data/file.yaml'
101
+
102
+ >>> # Return Path object when needed
103
+ >>> validate_path("/var/app/data/file.yaml", allowed_base="/var/app", as_string=False)
104
+ Path('/var/app/data/file.yaml')
105
+
106
+ >>> # Prevent directory traversal
107
+ >>> validate_path("/var/app/../etc/passwd", allowed_base="/var/app")
108
+ PathTraversalError: Path '/etc/passwd' is outside allowed base '/var/app'
109
+
110
+ >>> # Extension validation
111
+ >>> validate_path("file.txt", allowed_extensions=('.yaml', '.json'))
112
+ InvalidExtensionError: Path 'file.txt' has disallowed extension '.txt'
113
+ """
114
+ if not path:
115
+ raise PathSecurityError("Path cannot be empty or None")
116
+
117
+ # Convert to Path object
118
+ path_obj = Path(path)
119
+
120
+ # Canonicalize path (resolve . and ..)
121
+ if resolve_symlinks:
122
+ # Fully resolve including symlinks
123
+ try:
124
+ canonical_path = path_obj.resolve(strict=False)
125
+ except (OSError, RuntimeError) as e:
126
+ raise PathSecurityError(f"Failed to resolve path '{path}': {e}") from e
127
+ else:
128
+ # Convert to absolute but preserve symlinks
129
+ canonical_path = path_obj.absolute()
130
+
131
+ # Boundary enforcement
132
+ if allowed_base is not None:
133
+ allowed_base_path = Path(allowed_base)
134
+ if resolve_symlinks:
135
+ try:
136
+ canonical_base = allowed_base_path.resolve(strict=False)
137
+ except (OSError, RuntimeError) as e:
138
+ raise PathSecurityError(
139
+ f"Failed to resolve allowed_base '{allowed_base}': {e}"
140
+ ) from e
141
+ else:
142
+ canonical_base = allowed_base_path.absolute()
143
+
144
+ # Check if canonical_path is within canonical_base
145
+ try:
146
+ canonical_path.relative_to(canonical_base)
147
+ except ValueError:
148
+ raise PathTraversalError(
149
+ f"Path '{canonical_path}' is outside allowed base '{canonical_base}'"
150
+ ) from None
151
+
152
+ # Additional check: if resolve_symlinks is True, verify that no symlink in the path
153
+ # escapes the boundary. This is already handled by resolve() above, but we add
154
+ # an explicit check for symlinks that might have been followed
155
+ if resolve_symlinks and path_obj.is_symlink():
156
+ # If the original path was a symlink, verify the resolved target is still in bounds
157
+ try:
158
+ canonical_path.relative_to(canonical_base)
159
+ except ValueError:
160
+ raise SymlinkSecurityError(
161
+ f"Symlink '{path}' resolves to '{canonical_path}' which is outside allowed base '{canonical_base}'"
162
+ ) from None
163
+
164
+ # Extension validation
165
+ if allowed_extensions is not None:
166
+ if not canonical_path.suffix:
167
+ raise InvalidExtensionError(
168
+ f"Path '{canonical_path}' has no file extension. Allowed extensions: {allowed_extensions}"
169
+ )
170
+ if canonical_path.suffix not in allowed_extensions:
171
+ raise InvalidExtensionError(
172
+ f"Path '{canonical_path}' has disallowed extension '{canonical_path.suffix}'. "
173
+ f"Allowed extensions: {allowed_extensions}"
174
+ )
175
+
176
+ return str(canonical_path) if as_string else canonical_path
@@ -0,0 +1,114 @@
1
+ """Subprocess execution utilities for OpenAPI tools."""
2
+
3
+ import subprocess
4
+ from collections.abc import Sequence
5
+ from dataclasses import dataclass
6
+
7
+
8
+ __all__ = ["run_subprocess", "SubprocessExecutionResult", "SubprocessExecutionError"]
9
+
10
+
11
+ @dataclass
12
+ class SubprocessExecutionResult:
13
+ """Returned by a subprocess."""
14
+
15
+ returncode: int
16
+ stdout: str = ""
17
+ stderr: str = ""
18
+
19
+ def __init__(
20
+ self,
21
+ returncode: int,
22
+ stdout: str | None = None,
23
+ stderr: str | None = None,
24
+ ):
25
+ self.returncode = returncode
26
+ self.stdout = stdout if isinstance(stdout, str) else ""
27
+ self.stderr = stderr if isinstance(stderr, str) else ""
28
+
29
+
30
+ class SubprocessExecutionError(RuntimeError):
31
+ """Raised when a subprocess exits with non-zero return code."""
32
+
33
+ def __init__(
34
+ self,
35
+ cmd: Sequence[str],
36
+ returncode: int,
37
+ stdout: str | None = None,
38
+ stderr: str | None = None,
39
+ ):
40
+ self.cmd = list(cmd)
41
+ self.returncode = returncode
42
+ self.stdout = stdout if isinstance(stdout, str) else ""
43
+ self.stderr = stderr if isinstance(stderr, str) else ""
44
+ message = (
45
+ f"Command {self.cmd!r} failed with exit code {self.returncode}\n"
46
+ f"--- stdout ---\n{self.stdout}\n"
47
+ f"--- stderr ---\n{self.stderr}"
48
+ )
49
+ super().__init__(message)
50
+
51
+
52
+ def run_subprocess(
53
+ cmd: Sequence[str],
54
+ *,
55
+ fail_on_error: bool = False,
56
+ timeout: float | None = None,
57
+ encoding: str = "utf-8",
58
+ errors: str = "strict",
59
+ cwd: str | None = None,
60
+ ) -> SubprocessExecutionResult:
61
+ """
62
+ Run a subprocess command and return (stdout, stderr) as text.
63
+ Raises SubprocessExecutionError if the command fails.
64
+
65
+ Parameters
66
+ ----------
67
+ cmd : sequence of str
68
+ The command and its arguments.
69
+ fail_on_error : bool
70
+ If True, raises SubprocessExecutionError for non-zero return codes.
71
+ timeout : float | None
72
+ Seconds before timing out.
73
+ encoding : str
74
+ Passed to subprocess.run so stdout/stderr are decoded as text.
75
+ errors : str
76
+ Error handler for text decoding.
77
+ cwd : str | None
78
+ Working directory for the subprocess.
79
+
80
+ Returns
81
+ -------
82
+ (stdout, stderr, returncode): SubprocessExecutionResult
83
+ """
84
+ try:
85
+ completed_process = subprocess.run(
86
+ cmd,
87
+ check=False,
88
+ capture_output=True,
89
+ text=True,
90
+ shell=False,
91
+ encoding=encoding, # ensure the CompletedProcess has stdout/stderr
92
+ errors=errors,
93
+ timeout=timeout,
94
+ cwd=cwd,
95
+ )
96
+ except subprocess.TimeoutExpired as e:
97
+ stdout = e.stdout.decode(encoding, errors) if isinstance(e.stdout, bytes) else e.stdout
98
+ stderr = e.stderr.decode(encoding, errors) if isinstance(e.stderr, bytes) else e.stderr
99
+ raise SubprocessExecutionError(cmd, -1, stdout, stderr) from e
100
+ except OSError as e: # e.g., executable not found, permission denied
101
+ raise SubprocessExecutionError(cmd, -1, None, str(e)) from e
102
+
103
+ if completed_process.returncode != 0 and fail_on_error:
104
+ raise SubprocessExecutionError(
105
+ cmd,
106
+ completed_process.returncode,
107
+ completed_process.stdout,
108
+ completed_process.stderr,
109
+ )
110
+
111
+ # At this point CompletedProcess stdout/stderr are str due to text=True + encoding
112
+ return SubprocessExecutionResult(
113
+ completed_process.returncode, completed_process.stdout, completed_process.stderr
114
+ )
@@ -0,0 +1,341 @@
1
+ import os
2
+ import re
3
+ from pathlib import Path
4
+ from urllib.parse import urljoin, urlparse, urlsplit, urlunsplit
5
+ from urllib.request import url2pathname
6
+
7
+
8
+ __all__ = [
9
+ "URIResolutionError",
10
+ "is_uri_like",
11
+ "is_http_https_url",
12
+ "is_file_uri",
13
+ "is_scheme_relative_uri",
14
+ "is_absolute_uri",
15
+ "is_fragment_only_uri",
16
+ "is_path",
17
+ "resolve_to_absolute",
18
+ "file_uri_to_path",
19
+ ]
20
+
21
+
22
+ _WINDOWS_DRIVE_RE = re.compile(r"^[A-Za-z]:[\\/]")
23
+ _WINDOWS_UNC_RE = re.compile(r"^(?:\\\\|//)[^\\/]+[\\/][^\\/]+")
24
+
25
+ # Matches:
26
+ # - http://... or https://...
27
+ # - file://...
28
+ # - POSIX absolute: /path or just "/"
29
+ # - Windows UNC: \\server\share\...
30
+ # - Windows root-relative: \path\to (current drive root)
31
+ # - Windows drive-absolute: C:\path\to or C:/path/to
32
+ # - Relative paths: ./path, ../path, .\path, ..\path, or plain relative paths
33
+ _URI_LIKE_RE = re.compile(
34
+ r"""^(?:
35
+ https?://[^\r\n]+ |
36
+ file://[^\r\n]+ |
37
+ /[^\r\n]* |
38
+ \\\\[^\r\n]+ |
39
+ \\[^\r\n]+ |
40
+ [A-Za-z]:\\[^\r\n]+ |
41
+ [A-Za-z]:/[^\r\n]+ |
42
+ \./[^\r\n]* |
43
+ \.\\/[^\r\n]* |
44
+ \.\.[/\\][^\r\n]* |
45
+ \.\.\\[^\r\n]* |
46
+ [a-zA-Z_][a-zA-Z0-9_.-]*(?:[/\\][a-zA-Z0-9_.-]+)+ |
47
+ [a-zA-Z_][a-zA-Z0-9_.-]*\.[a-zA-Z0-9]+(?![}\])])
48
+ )$""",
49
+ re.VERBOSE,
50
+ )
51
+
52
+
53
+ class URIResolutionError(ValueError):
54
+ pass
55
+
56
+
57
+ def is_uri_like(uri: str | None) -> bool:
58
+ r"""
59
+ Heuristic check: is `s` a URI-like reference or absolute/relative path?
60
+ - Accepts http(s)://, file://
61
+ - Accepts absolute POSIX (/...) and Windows (\\..., \..., C:\..., C:/...) paths
62
+ - Accepts relative paths (./..., ../..., .\..., ..\...)
63
+ - Must be a single line (no '\\n' or '\\r').
64
+ Leading/trailing whitespace is ignored.
65
+ """
66
+ if not uri:
67
+ return False
68
+ uri = uri.strip()
69
+ # Enforce single line
70
+ if "\n" in uri or "\r" in uri:
71
+ return False
72
+ return bool(_URI_LIKE_RE.match(uri))
73
+
74
+
75
+ def is_path(s: str | None) -> bool:
76
+ """
77
+ Check if `s` is a filesystem path (not a URL or URI).
78
+
79
+ Returns True for:
80
+ - Absolute POSIX paths: /home/file.txt
81
+ - Absolute Windows paths: C:\\Windows\\file.txt, \\\\server\\share\\path
82
+ - Relative paths: ./config.yaml, ../parent/file.txt
83
+
84
+ Returns False for:
85
+ - HTTP(S) URLs: http://example.com
86
+ - File URIs: file:///home/file.txt
87
+ - Other URIs: mailto:test@example.com, data:text/plain, ftp://ftp.example.com
88
+ - Empty or None strings
89
+ """
90
+ if not s:
91
+ return False
92
+
93
+ s = s.strip()
94
+
95
+ # Must match the URI-like pattern first
96
+ if not is_uri_like(s):
97
+ return False
98
+
99
+ # Exclude HTTP(S) URLs
100
+ if is_http_https_url(s):
101
+ return False
102
+
103
+ # Exclude file:// URIs
104
+ if is_file_uri(s):
105
+ return False
106
+
107
+ # Exclude any other URI schemes (mailto:, data:, ftp:, etc.)
108
+ parsed = urlparse(s)
109
+ if parsed.scheme: # Has a scheme
110
+ return False
111
+
112
+ # It's a path!
113
+ return True
114
+
115
+
116
+ def is_http_https_url(url: str) -> bool:
117
+ p = urlparse(url)
118
+ return p.scheme in ("http", "https") and bool(p.netloc)
119
+
120
+
121
+ def is_file_uri(uri: str) -> bool:
122
+ return urlparse(uri).scheme == "file"
123
+
124
+
125
+ def is_scheme_relative_uri(uri: str) -> bool:
126
+ """
127
+ Check if `uri` is a scheme-relative URI (also called protocol-relative URI).
128
+
129
+ A scheme-relative URI starts with "//" followed by an authority component (netloc),
130
+ inheriting the scheme from the context (e.g., "//cdn.example.com/path").
131
+
132
+ This is defined in RFC 3986 section 4.2 as a network-path reference.
133
+ Per RFC 3986, a valid network-path reference must have an authority component.
134
+
135
+ Examples:
136
+ - "//cdn.example.com/x.yaml" -> True
137
+ - "//example.com/api" -> True
138
+ - "http://example.com" -> False (has scheme)
139
+ - "/path/to/file" -> False (single slash)
140
+ - "./relative" -> False (relative path)
141
+ - "//" -> False (no authority component)
142
+ - "///path" -> False (no authority component)
143
+
144
+ Args:
145
+ uri: The string to check
146
+
147
+ Returns:
148
+ True if the string is a valid scheme-relative URI with authority, False otherwise
149
+ """
150
+ if not uri.startswith("//"):
151
+ return False
152
+ p = urlparse(uri)
153
+ return bool(p.netloc)
154
+
155
+
156
+ def is_absolute_uri(uri: str) -> bool:
157
+ """
158
+ Check if `uri` is an absolute URI according to RFC 3986.
159
+
160
+ An absolute URI is defined as having a scheme (e.g., "http:", "https:", "ftp:", "file:").
161
+
162
+ Note: Scheme-relative URIs (starting with "//") are NOT considered absolute URIs.
163
+ According to RFC 3986 section 4.2, scheme-relative URIs are classified as
164
+ "relative references" (specifically, "network-path references").
165
+ Use `is_scheme_relative_uri()` to check for those separately.
166
+
167
+ Examples:
168
+ - "http://example.com" -> True
169
+ - "https://example.com/path" -> True
170
+ - "ftp://ftp.example.com" -> True
171
+ - "file:///path/to/file" -> True
172
+ - "//cdn.example.com/x.yaml" -> False (scheme-relative, use is_scheme_relative_uri)
173
+ - "/path/to/file" -> False (absolute path, not URI)
174
+ - "./relative" -> False
175
+ - "#fragment" -> False
176
+
177
+ Args:
178
+ uri: The string to check
179
+
180
+ Returns:
181
+ True if the string is an absolute URI (has a scheme), False otherwise
182
+ """
183
+ p = urlparse(uri)
184
+ return bool(p.scheme)
185
+
186
+
187
+ def is_fragment_only_uri(uri: str) -> bool:
188
+ """
189
+ Check if `uri` is a fragment-only reference.
190
+
191
+ A fragment-only reference consists solely of a fragment identifier (starts with "#").
192
+ These are used in JSON References and OpenAPI to refer to parts within the same document.
193
+
194
+ Note: This checks if the ENTIRE string is a fragment reference, not whether
195
+ a URI contains a fragment. For example, "http://example.com#section" would
196
+ return False because it's a full URI with a fragment, not fragment-only.
197
+
198
+ Examples:
199
+ - "#/definitions/User" -> True
200
+ - "#fragment" -> True
201
+ - "#" -> True (empty fragment identifier)
202
+ - "##" -> True (fragment identifier is "#")
203
+ - "http://example.com#section" -> False (full URI with fragment)
204
+ - "/path/to/file" -> False
205
+ - "./relative" -> False
206
+ - "" -> False
207
+
208
+ Args:
209
+ uri: The string to check
210
+
211
+ Returns:
212
+ True if the string is a fragment-only reference, False otherwise
213
+ """
214
+ return uri.startswith("#")
215
+
216
+
217
+ def resolve_to_absolute(value: str, base_uri: str | None = None) -> str:
218
+ """
219
+ Resolve `value` to either:
220
+ - an absolute URL (with scheme), OR
221
+ - an absolute filesystem path (no scheme)
222
+
223
+ • If `base_uri` is None AND `value` has no scheme (i.e., relative URI or path),
224
+ return an **absolute filesystem path** resolved against CWD.
225
+
226
+ Other rules:
227
+ • Absolute http(s) URLs ⇒ return absolute URL.
228
+ • file:// URIs ⇒ return absolute filesystem path.
229
+ • If `base_uri` is an http(s) URL, relative inputs resolve to absolute URLs.
230
+ • If `base_uri` is a path or file://, relative inputs resolve to absolute paths.
231
+ • Mixing a path-like `value` with an http(s) `base_uri` raises (ambiguous).
232
+ • Scheme-relative (“//host/path”) without a URL base ⇒ raises.
233
+ """
234
+ _guard_single_line(value)
235
+
236
+ if is_http_https_url(value):
237
+ return _normalize_url(value)
238
+
239
+ if is_file_uri(value):
240
+ return file_uri_to_path(value)
241
+
242
+ if _looks_like_windows_path(value):
243
+ return _resolve_path_like(value, base_uri)
244
+
245
+ parsed = urlparse(value)
246
+ # Scheme-relative without URL base is ambiguous
247
+ if value.startswith("//"):
248
+ if base_uri and is_http_https_url(base_uri):
249
+ return _normalize_url(urljoin(base_uri, value))
250
+ raise URIResolutionError("Scheme-relative URLs require a URL base_uri.")
251
+
252
+ # Any other explicit scheme (mailto:, data:, ftp:, etc.) → accept as-is
253
+ if parsed.scheme:
254
+ if parsed.scheme in ("http", "https"):
255
+ if not parsed.netloc:
256
+ raise URIResolutionError(f"Malformed URL (missing host): {value!r}")
257
+ return _normalize_url(value)
258
+ if parsed.scheme == "file":
259
+ # handled above
260
+ raise AssertionError("unreachable")
261
+ return value # leave non-file, non-http schemes untouched
262
+
263
+ # --- No scheme: relative URI or path ---
264
+ if base_uri:
265
+ if is_http_https_url(base_uri):
266
+ # Relative URI against URL base → absolute URL
267
+ return _normalize_url(urljoin(base_uri, value))
268
+ # base is file path or file:// → absolute path
269
+ return _resolve_path_like(value, base_uri)
270
+
271
+ # **Your rule**: no base + no scheme ⇒ absolute filesystem path
272
+ return _resolve_path_like(value, None)
273
+
274
+
275
+ def file_uri_to_path(file_uri: str) -> str:
276
+ """
277
+ Convert a file:// URI to an absolute filesystem path.
278
+
279
+ Args:
280
+ file_uri: A file:// URI string (e.g., "file:///path/to/file" or "file://server/share/path")
281
+
282
+ Returns:
283
+ Absolute filesystem path as a string
284
+
285
+ Raises:
286
+ URIResolutionError: If the input is not a valid file:// URI
287
+
288
+ Examples:
289
+ >>> file_uri_to_path("file:///home/user/doc.yaml")
290
+ '/home/user/doc.yaml'
291
+ >>> file_uri_to_path("file://localhost/etc/config.yaml")
292
+ '/etc/config.yaml'
293
+ """
294
+ parsed_uri = urlparse(file_uri)
295
+ if parsed_uri.scheme != "file":
296
+ raise URIResolutionError(f"Not a file URI: {file_uri!r}")
297
+ if parsed_uri.netloc and parsed_uri.netloc not in ("", "localhost"):
298
+ # UNC: \\server\share\path
299
+ unc = f"//{parsed_uri.netloc}{parsed_uri.path}"
300
+ return str(Path(url2pathname(unc)).resolve())
301
+ path = url2pathname(parsed_uri.path)
302
+ return str(Path(path).resolve())
303
+
304
+
305
+ def _guard_single_line(s: str) -> None:
306
+ if not isinstance(s, str) or ("\n" in s or "\r" in s):
307
+ raise URIResolutionError("Input must be a single-line string.")
308
+
309
+
310
+ def _looks_like_windows_path(s: str) -> bool:
311
+ return bool(_WINDOWS_DRIVE_RE.match(s) or _WINDOWS_UNC_RE.match(s))
312
+
313
+
314
+ def _normalize_url(s: str) -> str:
315
+ import posixpath
316
+
317
+ parts = urlsplit(s)
318
+ # Normalize the path component using posixpath (URLs always use forward slashes)
319
+ normalized_path = posixpath.normpath(parts.path) if parts.path else "/"
320
+ # Ensure root path is "/"
321
+ if normalized_path == ".":
322
+ normalized_path = "/"
323
+ return urlunsplit((parts.scheme, parts.netloc, normalized_path, parts.query, parts.fragment))
324
+
325
+
326
+ def _resolve_path_like(value: str, base_uri: str | None) -> str:
327
+ value = os.path.expandvars(os.path.expanduser(value))
328
+
329
+ if base_uri:
330
+ if is_file_uri(base_uri):
331
+ base_path = Path(url2pathname(urlparse(base_uri).path))
332
+ elif is_http_https_url(base_uri):
333
+ # Don't silently combine a local path with a URL base
334
+ raise URIResolutionError("Cannot resolve a local path against an HTTP(S) base_uri.")
335
+ else:
336
+ base_path = Path(os.path.expandvars(os.path.expanduser(base_uri)))
337
+ else:
338
+ base_path = Path.cwd()
339
+
340
+ p = Path(value)
341
+ return str(p.resolve() if p.is_absolute() else (base_path / p).resolve())