[issue-388] Update CLI tools for the new parsers/writers

README.md

@@ -58,34 +58,22 @@ This is the result of an initial GSoC contribution by @[ah450](https://github.co
 
 ## Command-line usage:
 
-1. **PARSER** (for parsing any format):
+1. **PARSING/VALIDATING** (for parsing any format):
 
-* Use `pyspdxtools_parser --file <filename>` where `<filename>` is the location of the file.              
-If you are using a source distribution, try running: `pyspdxtools_parser --file tests/data/formats/SPDXRdfExample.rdf`.
+* Use `pyspdxtools -i <filename>` where `<filename>` is the location of the file.              
+  If you are using a source distribution, try running: `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json`.
 
-* Or you can use `pyspdxtools_parser` only, and it will automatically prompt/ask for `filename`.
+* Or you can use `pyspdxtools` only, and it will automatically prompt/ask for the `input file path`.
 
-* For help use `pyspdxtools_parser --help`
+2. **CONVERTING** (for converting one format to another):
 
+* Use `pyspdxtools -i <input_file> -o <output_file>` where `<input_file>` is the location of the file to be converted
+  and `<output_file>` is the location of the output file. The output format is inferred automatically from the file ending.
+  If you are using a source distribution, try running : `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json -o output.tag` 
 
-2. **CONVERTOR** (for converting one format to another):
-
-* If I/O formats are known:
-
-    * Use `pyspdxtools_convertor --infile/-i <input_file> --outfile/-o <output_file>` where `<input_file>` is the location of the file to be converted
-    and `<output_file>` is the location of the output file.  
-    If you are using a source distribution, try running : `pyspdxtools_convertor --infile tests/data/formats/SPDXRdfExample.rdf --outfile output.json` 
-
-* If I/O formats are not known:
-
-    * Use `pyspdxtools_convertor --from/-f <input_format> <input_file> --to/-t <output_format> <output_file>` where `<input_format>` is the manually entered format of the input file
-    and `<out_format>` is the manually entered format of the output file. 
-    If you are using a source distribution, try running : `pyspdxtools_convertor --from tag tests/data/formats/SPDXTagExample.in --to yaml output.out` 
-
-* If one of the formats is known and the other is not, you can use a mixture of the above two points.  
-Example (if you are using a source distribution): `pyspdxtools_convertor -f rdf tests/data/formats/SPDXRdfExample.xyz -o output.xml`
-
-* For help use `pyspdxtools_convertor --help`
+* If you want to skip the validation process, provide the `--novalidation` flag, like so:  
+  `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json -o output.tag --novalidation`
+* For help use `pyspdxtools --help`
 
 # Installation
 

pyproject.toml

@@ -31,8 +31,7 @@ dynamic = ["version"]
 test = ["pytest"]
 
 [project.scripts]
-pyspdxtools_convertor = "src.clitools.convertor:main"
-pyspdxtools_parser = "src.clitools.parser:main"
+pyspdxtools = "src.clitools.pyspdxtools:main"
 
 [tool.setuptools]
 zip-safe = false  # because of the uses of __file__: https://github.com/spdx/tools-python/issues/257

src/clitools/pyspdxtools.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+
+# Copyright (c) 2020 Yash Varshney
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#    http://www.apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import sys
+from typing import List
+
+import click
+
+from src.model.document import Document
+from src.parser.parse_anything import parse_file
+from src.validation.document_validator import validate_full_spdx_document
+from src.validation.validation_message import ValidationMessage
+from src.writer.tagvalue import tagvalue_writer
+from src.writer.write_anything import write_file
+
+
+@click.command()
+@click.option("--infile", "-i", prompt="input file path", help="The file containing the document to be validated or converted.")
+@click.option("--outfile", "-o", help="The file to write the converted document to (write a dash for output to stdout or omit for no conversion).")
+@click.option("--version", help='The SPDX version to be used during parsing and validation (format "SPDX-2.3").', default="SPDX-2.3")
+@click.option("--novalidation", is_flag=True, help="Don't validate the provided document.")
+def main(infile: str, outfile: str, version: str, novalidation: bool):
+    """
+    CLI-tool for validating SPDX documents and converting between RDF, TAG-VALUE, JSON, YAML and XML formats.
+    Formats are determined by the file endings.
+    To use, run: 'pyspdxtools --infile <input file name> --outfile <output file name>'
+    """
+    try:
+        document: Document = parse_file(infile)
+
+        if outfile == "-":
+            tagvalue_writer.write_document(document, sys.stdout)
+            print("")
+
+        if not novalidation:
+            validation_messages: List[ValidationMessage] = validate_full_spdx_document(document, version)
+            if validation_messages:
+                print("The document is invalid. The following issues have been found:")
+                for message in validation_messages:
+                    print(message.validation_message)
+                sys.exit(1)
+            else:
+                print("The document is valid.")
+
+        if outfile and outfile != "-":
+            write_file(document, outfile, validate=False)
+
+    except NotImplementedError as err:
+        print(err.args[0])
+        print("Please note that this project is currently undergoing a major refactoring and therefore missing "
+              "a few features which will be added in time (refer to https://github.com/spdx/tools-python/issues "
+              "for insights into the current status).\n"
+              "In the meantime, please use the PyPI release version 0.7.0.")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

src/formats.py

@@ -0,0 +1,36 @@
+#  Copyright (c) 2022 spdx contributors
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#      http://www.apache.org/licenses/LICENSE-2.0
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+from enum import Enum, auto
+
+from src.parser.error import SPDXParsingError
+
+
+class FileFormat(Enum):
+    JSON = auto()
+    YAML = auto()
+    XML = auto()
+    TAG_VALUE = auto()
+    RDF_XML = auto()
+
+
+def file_name_to_format(file_name: str) -> FileFormat:
+    if file_name.endswith(".rdf") or file_name.endswith(".rdf.xml"):
+        return FileFormat.RDF_XML
+    elif file_name.endswith(".tag") or file_name.endswith(".spdx"):
+        return FileFormat.TAG_VALUE
+    elif file_name.endswith(".json"):
+        return FileFormat.JSON
+    elif file_name.endswith(".xml"):
+        return FileFormat.XML
+    elif file_name.endswith(".yaml") or file_name.endswith(".yml"):
+        return FileFormat.YAML
+    else:
+        raise SPDXParsingError(["Unsupported SPDX file type: " + str(file_name)])

src/parser/parse_anything.py

@@ -0,0 +1,26 @@
+# Copyright (c) spdx contributors
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#     http://www.apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from src.formats import file_name_to_format, FileFormat
+from src.parser.json.json_parser import JsonParser
+
+
+def parse_file(file_name: str):
+    input_format = file_name_to_format(file_name)
+    if input_format == FileFormat.RDF_XML:
+        raise NotImplementedError("Currently, the rdf parser is not implemented")
+    elif input_format == FileFormat.TAG_VALUE:
+        raise NotImplementedError("Currently, the tag-value parser is not implemented")
+    elif input_format == FileFormat.JSON:
+        return JsonParser().parse(file_name)
+    elif input_format == FileFormat.XML:
+        raise NotImplementedError("Currently, the xml parser is not implemented")
+    elif input_format == FileFormat.YAML:
+        raise NotImplementedError("Currently, the yaml parser is not implemented")

src/writer/write_anything.py

@@ -0,0 +1,28 @@
+#  Copyright (c) 2022 spdx contributors
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#      http://www.apache.org/licenses/LICENSE-2.0
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+from src.formats import file_name_to_format, FileFormat
+from src.model.document import Document
+from src.writer.json import json_writer
+from src.writer.tagvalue import tagvalue_writer
+
+
+def write_file(document: Document, file_name: str, validate: bool = True):
+    output_format = file_name_to_format(file_name)
+    if output_format == FileFormat.JSON:
+        json_writer.write_document(document, file_name, validate)
+    elif output_format == FileFormat.YAML:
+        raise NotImplementedError("Currently, the yaml writer is not implemented")
+    elif output_format == FileFormat.XML:
+        raise NotImplementedError("Currently, the xml writer is not implemented")
+    elif output_format == FileFormat.TAG_VALUE:
+        tagvalue_writer.write_document_to_file(document, file_name)
+    elif output_format == FileFormat.RDF_XML:
+        raise NotImplementedError("Currently, the rdf writer is not implemented")