Merge pull request #41 from E-ARK-Software/integration

Integration

.github/workflows/python-publish.yml

@@ -20,13 +20,33 @@ jobs:
 
     steps:
     - uses: actions/[email protected]
+      with:
+        fetch-depth: 0
     - name: Set up Python
       uses: actions/[email protected]
       with:
         python-version: '3.10'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
+        pip install ".[testing]"
+    - name: Install python package
+      run: |
+        pip install --editable ".[testing]"
+    - name: Static Pylint code QA
+      run: |
+        pylint --errors-only eark_validator
+    - name: Run pre-commit tests
+      run: pre-commit run --all-files --verbose
+    - name: Test with pytest
+      run: |
+        pytest
+    - name: Test setuptools-git-versioning versioning
+      run: |
+        python -m pip install setuptools_git_versioning
+        python -m setuptools_git_versioning
+    - name: Install build utils
+      run: |
         pip install build
     - name: Build package
       run: python -m build

.github/workflows/python-test.yml

@@ -20,13 +20,16 @@ jobs:
   build:
 
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["pypy3.10", "3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v3
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
       with:
-        python-version: "3.10"
+        python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

README.md

@@ -11,10 +11,10 @@ website of the Digital Information LifeCycle Interoperability Standards Board (D
 
 ### Pre-requisites
 
-You must be running either a Debian/Ubuntu Linux distribution or Windows Subsystem for Linux on Windows to follow these commands.
+Python 3.10 or later is required to run the E-ARK Python Information Package Validator.
 
+You must be running either a Debian/Ubuntu Linux distribution or Windows Subsystem for Linux on Windows to follow these commands.
 If you are running a different Linux distribution you must change the apt commands to your package manager.
-
 For getting Windows Subsystem for Linux up and running, please follow the guide further down and then come back to this step.
 
 ### Getting up and running with the E-ARK Python Information Package Validator
@@ -88,7 +88,7 @@ pip install -U pip
 pip install .
 ```
 
-You are now able to run the application "ip-check". It will validate an Information Package for you.
+You are now able to run the application "eark-validator". It will validate an Information Package for you.
 
 
 #### Testing a valid package.
@@ -111,10 +111,10 @@ Delete the .zip-file you just downloaded:
 rm mets-xml_metsHdr_agent_TYPE_exist.zip
 ```
 
-Run the ip-check:
+Run the eark-validator:
 
 ```shell
-ip-check mets-xml_metsHdr_agent_TYPE_exist/
+eark-validator mets-xml_metsHdr_agent_TYPE_exist/
 ```
 
 Result:
@@ -146,7 +146,7 @@ user@machine:~$ tree input
 
 If you do not have Linux and have not previously used WSL please perform the following steps. You must either be logged in as Administrator on the machine or as a user with Administrator rights on the machine.
 
-Start er command prompt (cmd.exe) and then enter the following command:
+Start a command prompt (cmd.exe) and then enter the following command:
 
 ```shell
 wsl --install
@@ -199,4 +199,4 @@ pip install --editable ".[testing]"
 
 ### Running tests
 
-You can run unit tests from the project root: `pytest ./tests/`, or generate test coverage figures by: `pytest --cov=ip_validation ./tests/`. If you want to see which parts of your code aren't tested then: `pytest --cov=ip_validation --cov-report=html ./tests/`. After this you can open the file [`<projectRoot>/htmlcov/index.html`](./htmlcov/index.html) in your browser and survey the gory details.
+You can run unit tests from the project root: `pytest ./tests/`, or generate test coverage figures by: `pytest --cov=eark_validator ./tests/`. If you want to see which parts of your code aren't tested then: `pytest --cov=eark_validator --cov-report=html ./tests/`. After this you can open the file [`<projectRoot>/htmlcov/index.html`](./htmlcov/index.html) in your browser and survey the gory details.

eark_validator/__init__.py

@@ -26,5 +26,3 @@
 E-ARK : Python information package validation
 
 """
-
-__version__ = '1.1.1'

eark_validator/cli/app.py

@@ -26,49 +26,75 @@
 E-ARK : Information package validation
         Command line validation application
 """
-import argparse
-from pprint import pprint
+import json
 import os.path
+from pathlib import Path
 import sys
+from typing import Optional, Tuple
+import importlib.metadata
+
+import argparse
 
-import eark_validator.structure as STRUCT
+from eark_validator.model import ValidationReport
+import eark_validator.packages as PACKAGES
+from eark_validator.infopacks.package_handler import PackageHandler
+from eark_validator.specifications.specification import SpecificationVersion
 
-__version__ = '0.1.0'
+__version__ = importlib.metadata.version('eark_validator')
 
 defaults = {
-    'description': """E-ARK Information Package validation (ip-check).
-ip-check is a command-line tool to analyse and validate the structure and
+    'description': """E-ARK Information Package validation (eark-validator).
+eark-validator is a command-line tool to analyse and validate the structure and
 metadata against the E-ARK Information Package specifications.
 It is designed for simple integration into automated work-flows.""",
     'epilog': """
 DILCIS Board (http://dilcis.eu)
 See LICENSE for license information.
-GitHub: https://github.com/E-ARK-Software/py-rest-ip-validator
-Author: Carl Wilson (OPF), 2020-2023
-Maintainer: Carl Wilson (OPF), 2020-2023"""
+GitHub: https://github.com/E-ARK-Software/eark-validator
+Author: Carl Wilson (OPF), 2020-2024
+Maintainer: Carl Wilson (OPF), 2020-2024"""
 }
 
 # Create PARSER
-PARSER = argparse.ArgumentParser(description=defaults['description'], epilog=defaults['epilog'])
+PARSER = argparse.ArgumentParser(prog='eark-validator',
+                                 description=defaults['description'],
+                                 epilog=defaults['epilog'])
 
 def parse_command_line():
     """Parse command line arguments."""
     # Add arguments
     PARSER.add_argument('-r', '--recurse',
                         action='store_true',
                         dest='inputRecursiveFlag',
-                        default=True,
+                        default=False,
                         help='When analysing an information package recurse into representations.')
     PARSER.add_argument('-c', '--checksum',
                         action='store_true',
                         dest='inputChecksumFlag',
                         default=False,
-                        help='Calculate and verify file checksums in packages.')
+                        help='Calculate and verify package checksums.')
+    PARSER.add_argument('-m', '--manifest',
+                        action='store_true',
+                        dest='inputManifestFlag',
+                        default=False,
+                        help='Display package manifest information.')
     PARSER.add_argument('-v', '--verbose',
                         action='store_true',
                         dest='outputVerboseFlag',
                         default=False,
-                        help='report results in verbose format')
+                        help='Verbose reporting for selected output options.')
+    PARSER.add_argument('--schema',
+                        action='store_true',
+                        dest='output_schema',
+                        default=False,
+                        help='Request display of the JSON schema of the output report.')
+    PARSER.add_argument('-s', '--specification_version',
+                        nargs='?',
+                        dest='specification_version',
+                        default=SpecificationVersion.V2_1_0,
+                        type=SpecificationVersion,
+                        choices=list(SpecificationVersion),
+                        help='Specification version used for validation. Default is %(default)s.')
     PARSER.add_argument('--version',
                         action='version',
                         version=__version__)
@@ -89,37 +115,48 @@ def main():
     # Get input from command line
     args = parse_command_line()
     # If no target files or folders specified then print usage and exit
-    if not args.files:
+    if _is_show_help(args):
         PARSER.print_help()
 
+    if args.output_schema:
+        print(json.dumps(ValidationReport.model_json_schema(), indent=2))
+        sys.exit(0)
+
     # Iterate the file arguments
     for file_arg in args.files:
-        _loop_exit, _ = _validate_ip(file_arg)
+        _loop_exit, _ = _validate_ip(file_arg, args.specification_version)
         _exit = _loop_exit if (_loop_exit > 0) else _exit
     sys.exit(_exit)
 
-def _validate_ip(info_pack):
-    ret_stat = _check_path(info_pack)
-    struct_details = STRUCT.validate_package_structure(info_pack)
-    pprint('Path {}, struct result is: {}'.format(info_pack,
-                                                         struct_details.status))
-    for error in struct_details.errors:
-        pprint(error.to_json())
+def _validate_ip(path: str, version: SpecificationVersion) -> Tuple[int, Optional[ValidationReport]]:
+    ret_stat, checked_path = _check_path(path)
+    if ret_stat > 0:
+        return ret_stat, None
+    report = PACKAGES.PackageValidator(checked_path, version).validation_report
+    print(f'Path {checked_path}, struct result is: {report.structure.status.value}')
+    # for message in report.structure.messages:
+    print(report.model_dump_json())
 
-    return ret_stat, struct_details
+    return ret_stat, report
 
-def _check_path(path):
+def _check_path(path: str) -> Tuple[int, Optional[Path]]:
     if not os.path.exists(path):
         # Skip files that don't exist
-        pprint('Path {} does not exist'.format(path))
-        return 1
+        print(_format_check_path_message(path, 'does not exist'))
+        return 1, None
     if os.path.isfile(path):
         # Check if file is a archive format
-        if not STRUCT.ArchivePackageHandler.is_archive(path):
+        if not PackageHandler.is_archive(path):
             # If not we can't process so report and iterate
-            pprint('Path {} is not a file we can process.'.format(path))
-            return 2
-    return 0
+            print(_format_check_path_message(path, 'is not an archive file or directory'))
+            return 2, None
+    return 0, Path(path)
+
+def _format_check_path_message(path: Path, message: str) -> str:
+    return f'Processing terminated, path: {path} {message}.'
+
+def _is_show_help(args) -> bool:
+    return not args.files and not args.output_schema
 
 # def _test_case_schema_checks():
 if __name__ == '__main__':

eark_validator/const.py

@@ -28,7 +28,7 @@
 E-ARK (https://e-ark4all.eu/)
 Open Preservation Foundation (http://www.openpreservation.org)
 See LICENSE for license information.
-Author: Carl Wilson (OPF), 2016-17
+Author: Carl Wilson (OPF), 2016-24
 This work was funded by the European commission project funded
 as grant number LC-01390244 CEF-TC-2019-3 E-ARK3 under
 CONNECTING EUROPE FACILITY (CEF) - TELECOMMUNICATIONS SECTOR