Validate YAML syntax in license dump tests

src/licensedcode/license_db.py

@@ -17,6 +17,7 @@
 
 import click
 import saneyaml
+import yaml
 
 from commoncode.cliutils import MISC_GROUP
 from commoncode.cliutils import PluggableCommandLineOption
@@ -29,6 +30,16 @@
 TEMPLATES_DIR = os.path.join(dirname(__file__), 'templates')
 STATIC_DIR = os.path.join(dirname(__file__), 'static')
 
+def check_yaml_syntax(yaml_content, identifier):
+    """
+    Ensure the generated YAML can be parsed strictly by PyYAML.
+    """
+    try:
+        yaml.safe_load(yaml_content)
+    except yaml.YAMLError as e:
+        raise ValueError(f"Unable to parse generated YAML for {identifier}: {e}")
+
+
 
 def write_file(path, filename, content):
     path.joinpath(filename).open("w").write(content)
@@ -96,10 +107,13 @@ def generate_indexes(output_path, environment, licenses, test=False):
         "index.json",
         json.dumps(index, indent=2, sort_keys=False)
     )
+    index_yaml_content = saneyaml.dump(index, indent=2)
+    check_yaml_syntax(index_yaml_content, "index.yml")
+
     write_file(
         output_path,
         "index.yml",
-        saneyaml.dump(index, indent=2)
+        index_yaml_content
     )
     return len(index)
 
@@ -131,10 +145,14 @@ def generate_details(output_path, environment, licenses, test=False):
             license_data=license_data,
         )
         write_file(output_path, f"{lic.key}.html", html)
+
+        yaml_content = saneyaml.dump(license_data_with_text, indent=2)
+        check_yaml_syntax(yaml_content, f"license: {lic.key}")
+
         write_file(
             output_path,
             f"{lic.key}.yml",
-            saneyaml.dump(license_data_with_text, indent=2)
+            yaml_content
         )
         write_file(
             output_path,

tests/licensedcode/data/license_db/license_dump/bash-exception-gpl.LICENSE

@@ -1,20 +1,20 @@
----
-key: bash-exception-gpl
-short_name: Bash exception to GPL
-name: Bash exception to GPL
-category: Copyleft
-owner: Free Software Foundation (FSF)
-notes: this used with GPL 1.0 and 2.0. It was removed from the V3 text https://git.savannah.gnu.org/cgit/bash.git/commit/COPYING?id=3185942a5234e26ab13fa02f9c51d340cec514f8
-is_exception: yes
-spdx_license_key: LicenseRef-scancode-bash-exception-gpl-2.0
-text_urls:
-    - https://git.savannah.gnu.org/cgit/bash.git/plain/COPYING?h=bash-3.0-rc1&id=dd9e6dfa23d0dae4888f11fb8c6a27bc36d1b283
----
-
-The Free Software Foundation has exempted Bash from the requirement of
-Paragraph 2c of the General Public License.  This is to say, there is
-no requirement for Bash to print a notice when it is started
-interactively in the usual way.  We made this exception because users
-and standards expect shells not to print such messages.  This
-exception applies to any program that serves as a shell and that is
+---
+key: bash-exception-gpl
+short_name: Bash exception to GPL
+name: Bash exception to GPL
+category: Copyleft
+owner: Free Software Foundation (FSF)
+notes: this used with GPL 1.0 and 2.0. It was removed from the V3 text https://git.savannah.gnu.org/cgit/bash.git/commit/COPYING?id=3185942a5234e26ab13fa02f9c51d340cec514f8
+is_exception: yes
+spdx_license_key: LicenseRef-scancode-bash-exception-gpl-2.0
+text_urls:
+    - https://git.savannah.gnu.org/cgit/bash.git/plain/COPYING?h=bash-3.0-rc1&id=dd9e6dfa23d0dae4888f11fb8c6a27bc36d1b283
+---
+
+The Free Software Foundation has exempted Bash from the requirement of
+Paragraph 2c of the General Public License.  This is to say, there is
+no requirement for Bash to print a notice when it is started
+interactively in the usual way.  We made this exception because users
+and standards expect shells not to print such messages.  This
+exception applies to any program that serves as a shell and that is
 based primarily on Bash as opposed to other GNU software.