Check stac version format, v3.10.1, update to pyproject.toml (#268)

* check stac version format

* v3.10.2, update to pyproject

Author: jonhealy1

.github/workflows/publish.yml

@@ -21,11 +21,11 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install setuptools wheel twine
+          pip install setuptools wheel twine build
 
       - name: Build package
         run: |
-          python setup.py sdist bdist_wheel
+          python -m build
 
       - name: Publish package to PyPI
         env:

.github/workflows/test-runner.yml

@@ -29,7 +29,7 @@ jobs:
         if: matrix.python-version == '3.12'
         run: |
           pip install .
-          pip install -r requirements-dev.txt
+          pip install -e .[dev]
           mypy stac_validator/
 
       - name: Run pre-commit

CHANGELOG.md

@@ -6,6 +6,14 @@ The format is (loosely) based on [Keep a Changelog](http://keepachangelog.com/)
 
 ## [Unreleased]
 
+## [v3.10.2] - 2025-11-16
+
+### Fixed
+- Added validation for STAC version format to provide clear error messages when stac_version field is missing, empty, or incorrectly formatted (e.g., "1.1" instead of "1.1.0"). [#268](https://github.com/stac-utils/stac-validator/pull/268)
+
+### Changed
+- Migrated from `setup.py` to modern `pyproject.toml` packaging (PEP 621), removing legacy `requirements-dev.txt` file. [#268](https://github.com/stac-utils/stac-validator/pull/268)
+
 ## [v3.10.1] - 2025-07-26
 
 ### Fixed
@@ -302,7 +310,8 @@ The format is (loosely) based on [Keep a Changelog](http://keepachangelog.com/)
 - With the newest version - 1.0.0-beta.2 - items will run through jsonchema validation before the PySTAC validation. The reason for this is that jsonschema will give more informative error messages. This should be addressed better in the future. This is not the case with the --recursive option as time can be a concern here with larger collections.
 - Logging. Various additions were made here depending on the options selected. This was done to help assist people to update their STAC collections.
 
-[Unreleased]: https://github.com/sparkgeo/stac-validator/compare/v3.10.1..main
+[Unreleased]: https://github.com/sparkgeo/stac-validator/compare/v3.10.2..main
+[v3.10.2]: https://github.com/sparkgeo/stac-validator/compare/v3.10.1..v3.10.2
 [v3.10.1]: https://github.com/sparkgeo/stac-validator/compare/v3.10.0..v3.10.1
 [v3.10.0]: https://github.com/sparkgeo/stac-validator/compare/v3.9.3..v3.10.0
 [v3.9.3]: https://github.com/sparkgeo/stac-validator/compare/v3.9.2..v3.9.3

pyproject.toml

@@ -1,8 +1,62 @@
 [build-system]
-requires = [
-    "requests",
-    "jsonschema",
-    "click",
-    "setuptools"
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "stac_validator"
+version = "3.10.2"
+description = "A package to validate STAC files"
+authors = [
+    {name = "James Banting"},
+    {name = "Jonathan Healy", email = "[email protected]"}
 ]
-build-backend = "setuptools.build_meta"
+license = {text = "Apache-2.0"}
+classifiers = [
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.8",
+    "Topic :: Scientific/Engineering :: GIS",
+]
+keywords = ["STAC", "validation", "raster"]
+requires-python = ">=3.8"
+dependencies = [
+    "requests>=2.32.3",
+    "jsonschema>=4.23.0",
+    "click>=8.1.8",
+    "referencing>=0.35.1",
+    "pyYAML>=6.0.1",
+]
+optional-dependencies.dev = [
+    "black",
+    "pytest",
+    "pytest-mypy",
+    "pre-commit",
+    "requests-mock",
+    "types-setuptools",
+    "stac-pydantic>=3.3.0",
+    "mypy",
+    "types-attrs",
+    "types-requests",
+    "types-jsonschema"
+]
+optional-dependencies.pydantic = [
+    "stac-pydantic>=3.3.0"
+]
+
+[project.urls]
+Homepage = "https://github.com/stac-utils/stac-validator"
+Repository = "https://github.com/stac-utils/stac-validator"
+
+[project.readme]
+file = "README.md"
+content-type = "text/markdown"
+
+[tool.setuptools]
+packages = ["stac_validator"]
+
+[project.scripts]
+stac-validator = "stac_validator.stac_validator:main"
+
+[tool.setuptools.package-data]
+stac_validator = ["*.yaml"]

requirements-dev.txt

@@ -2,7 +2,7 @@
 import json
 import os
 import ssl
-from typing import Dict, Optional
+from typing import Dict, Optional, Tuple
 from urllib.parse import urlparse
 from urllib.request import Request, urlopen
 
@@ -25,6 +25,71 @@
 ]
 
 
+def validate_stac_version_field(stac_content: Dict) -> Tuple[bool, str, str]:
+    """Validate the stac_version field in STAC content.
+
+    Args:
+        stac_content (dict): The STAC content dictionary.
+
+    Returns:
+        Tuple[bool, str, str]: (is_valid, error_type, error_message)
+            - is_valid: True if the version is valid
+            - error_type: Error type string if invalid, empty string if valid
+            - error_message: Error message if invalid, empty string if valid
+    """
+    version = stac_content.get("stac_version", "")
+
+    # Check if version is present and not empty
+    if not version or not isinstance(version, str) or version.strip() == "":
+        error_type = "MissingSTACVersion"
+        error_msg = (
+            "The 'stac_version' field is missing or empty. "
+            "Please ensure your STAC object includes a valid 'stac_version' field "
+            "(e.g., '1.0.0', '1.1.0'). This field is required for proper schema validation."
+        )
+        return False, error_type, error_msg
+
+    # Validate version format
+    format_valid, format_error = validate_version_format(version)
+    if not format_valid:
+        return False, "InvalidSTACVersionFormat", format_error
+
+    return True, "", ""
+
+
+def validate_version_format(version: str) -> Tuple[bool, str]:
+    """Validate that a STAC version string has the correct format.
+
+    Args:
+        version (str): The version string to validate.
+
+    Returns:
+        Tuple[bool, str]: (is_valid, error_message)
+            - is_valid: True if the version format is valid
+            - error_message: Description of the issue if invalid, empty string if valid
+
+    Valid formats:
+        - Standard semver: "1.0.0", "1.1.0", "0.9.0"
+        - Pre-release versions: "1.0.0-beta.1", "1.0.0-rc.1"
+    """
+    if not version:
+        return False, "Version is empty"
+
+    import re
+
+    # Regex for semantic versioning: major.minor.patch with optional pre-release
+    semver_pattern = r"^\d+\.\d+\.\d+(-[\w\.\-]+)?$"
+
+    if not re.match(semver_pattern, version):
+        return False, (
+            f"Version '{version}' does not match expected format. "
+            "STAC versions should be in semantic versioning format (e.g., '1.0.0', '1.1.0', '1.0.0-beta.1'). "
+            "Please check your 'stac_version' field."
+        )
+
+    return True, ""
+
+
 def is_url(url: str) -> bool:
     """Checks whether the input string is a valid URL.
 

setup.py

@@ -18,6 +18,7 @@
     link_request,
     load_schema_config,
     set_schema_addr,
+    validate_stac_version_field,
     validate_with_ref_resolver,
 )
 
@@ -247,6 +248,7 @@ def create_err_msg(
         err_msg: str,
         error_obj: Optional[Exception] = None,
         schema_uri: str = "",
+        version: Optional[str] = None,
     ) -> Dict[str, Union[str, bool, List[str], Dict[str, Any]]]:
         """
         Create a standardized error message dictionary and mark validation as failed.
@@ -256,6 +258,7 @@ def create_err_msg(
             err_msg (str): The error message.
             error_obj (Optional[Exception]): The raw exception object for verbose details.
             schema_uri (str, optional): The URI of the schema that failed validation.
+            version (Optional[str]): Override version to use in the error message.
 
         Returns:
             dict: Dictionary containing error information.
@@ -268,9 +271,16 @@ def create_err_msg(
         if not isinstance(err_msg, str):
             err_msg = str(err_msg)
 
+        # Use provided version or fall back to self.version
+        version_to_use = (
+            version
+            if version is not None
+            else (str(self.version) if hasattr(self, "version") else "")
+        )
+
         # Initialize the message with common fields
         message: Dict[str, Any] = {
-            "version": str(self.version) if hasattr(self, "version") else "",
+            "version": version_to_use,
             "path": str(self.stac_file) if hasattr(self, "stac_file") else "",
             "schema": (
                 [self._original_schema_paths.get(self.schema, self.schema)]
@@ -306,7 +316,7 @@ def create_err_msg(
 
         # Initialize the error message with common fields
         error_message: Dict[str, Union[str, bool, List[str], Dict[str, Any]]] = {
-            "version": str(self.version) if self.version is not None else "",
+            "version": version_to_use,
             "path": str(self.stac_file) if self.stac_file is not None else "",
             "schema": schema_field,  # All schemas that were checked
             "valid_stac": False,
@@ -950,7 +960,25 @@ def run(self) -> bool:
                 self.stac_content = fetch_and_parse_file(self.stac_file, self.headers)
 
             stac_type = get_stac_type(self.stac_content).upper()
-            self.version = self.stac_content["stac_version"]
+            version = self.stac_content.get("stac_version", "")
+
+            # Validate stac_version field comprehensively
+            version_valid, version_error_type, version_error_msg = (
+                validate_stac_version_field(self.stac_content)
+            )
+            if not version_valid:
+                message.update(
+                    self.create_err_msg(
+                        err_type=version_error_type,
+                        err_msg=version_error_msg,
+                        schema_uri="",
+                        version=version,  # Pass the version we extracted
+                    )
+                )
+                self.message.append(message)
+                return self.valid
+
+            self.version = version
 
             if self.core:
                 message = self.create_message(stac_type, "core")