Test speaker names

Author: hugovk

.github/workflows/ci.yml

@@ -1,21 +1,22 @@
 name: CI
 
-on:
-  push:
-    branches: main
-  pull_request:
+on: [push, pull_request, workflow_dispatch]
+
+env:
+  FORCE_COLOR: 1
+  PIP_DISABLE_PIP_VERSION_CHECK: 1
 
 jobs:
   test:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
 
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
-        python-version: 3.12
+        python-version: 3.x
 
     - name: Install
       run: make install-deps

.schemas/pathschema

@@ -18,7 +18,6 @@ tools/
 
 .gitignore
 .editorconfig
-.travis.yml
 CONTRIBUTING.rst
 CONTRIBUTORS_WITHOUT_COMMITS.rst
 LICENSE

.tests/requirements.txt

@@ -4,4 +4,5 @@ jsonschema
 pathschema
 pygments
 six
+termcolor
 unidecode

.tests/speaker_names.py

@@ -0,0 +1,50 @@
+import argparse
+import json
+import sys
+
+from termcolor import colored, cprint
+
+from tools.utils import get_json_files
+
+
+def check_speaker_names(data_root, verbose=False):
+    _, video_paths = get_json_files(data_root)
+
+    invalid_names = []
+    # Map of disallowed speaker names to their correct replacements
+    replacements = {
+        "Glyph Lefkowitz": "Glyph",
+    }
+
+    for video_path in video_paths:
+        with open(video_path, encoding="UTF-8") as fp:
+            video_blob = json.load(fp)
+            speakers = video_blob.get("speakers", [])
+
+            for speaker in speakers:
+                if speaker in replacements:
+                    invalid_names.append((video_path, speaker, replacements[speaker]))
+
+    if invalid_names:
+        cprint("Disallowed speaker names found:", "red")
+        for path, speaker, replacement in invalid_names:
+            speaker = colored(speaker, "red")
+            print(f"\t{path}: {speaker}")
+            print(f"\t\tUse {colored(replacement, 'green')} instead of {speaker}")
+        sys.exit(1)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-d", "--data-root",
+                        help="directory to search for JSON files")
+    parser.add_argument("-v", "--verbose",
+                        type=int,
+                        help="increase output verbosity")
+    args = parser.parse_args()
+
+    check_speaker_names(args.data_root, verbose=args.verbose)
+
+
+if __name__ == '__main__':
+    main()

.travis.yml

@@ -25,7 +25,7 @@ help:
 	@echo '                                                                   '
 
 .venv:
-	python3 -m venv $(VENV)
+	python3 -m venv $(VENV) --upgrade-deps
 
 install-deps: .venv
 	$(BIN)/pip install -r $(TESTSDIR)/requirements.txt
@@ -54,6 +54,9 @@ test-languages: install-deps
 test-filename-length: install-deps
 	$(PYTHON) $(TESTSDIR)/filename_length.py -d $(BASEDIR) -v $(VERBOSE)
 
-test: test-directory-schemas test-schemas test-ids-unique test-slugs-unique test-render-rest test-languages test-filename-length
+test-speaker-names: install-deps
+	$(PYTHON) $(TESTSDIR)/speaker_names.py -d $(BASEDIR) -v $(VERBOSE)
 
-.PHONY: help test test-directory-schemas test-schemas test-ids-unique test-slugs-unique test-render-rest test-shape test-languages
+test: test-directory-schemas test-schemas test-ids-unique test-slugs-unique test-render-rest test-languages test-filename-length test-speaker-names
+
+.PHONY: help test test-directory-schemas test-schemas test-ids-unique test-slugs-unique test-render-rest test-shape test-languages test-speaker-names