Git action for project structure

.github/workflows/check_project_structure.yaml

@@ -0,0 +1,23 @@
+name: Check Project Structure
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+    types: [opened, reopened, synchronize]
+
+jobs:
+  structure-check:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Run check_project_structure.py
+        working-directory: ./src/scribe_data/check
+        run: python check_project_structure.py
+
+      - name: Post-run status
+        if: failure()
+        run: echo "Project structure check failed. Please fix the reported errors."

.github/workflows/check_query_identifiers.yaml

@@ -1,4 +1,4 @@
-name: check_query_identifiers
+name: Check Query Identifiers
 on:
   push:
     branches: [main]

.github/workflows/pr_ci.yaml

@@ -1,4 +1,4 @@
-name: pr_ci
+name: CI
 on:
   push:
     branches: [main]

.github/workflows/pr_maintainer_checklist.yaml

@@ -1,4 +1,4 @@
-name: pr_maintainer_checklist
+name: PR Maintainer Checklist
 on:
   pull_request_target:
     branches:

src/scribe_data/check/check_project_structure.py

@@ -0,0 +1,162 @@
+import os
+
+# Expected languages and data types.
+LANGUAGES = {
+    "Arabic",
+    "English",
+    "Greek",
+    "Italian",
+    "Malayalam",
+    "Russian",
+    "Tamil",
+    "Basque",
+    "Esperanto",
+    "Hausa",
+    "Japanese",
+    "Norwegian",
+    "Slovak",
+    "Ukrainian",
+    "Bengali",
+    "Estonian",
+    "Hebrew",
+    "Korean",
+    "Pidgin",
+    "Spanish",
+    "Yoruba",
+    "Chinese",
+    "Finnish",
+    "Hindustani",
+    "Kurmanji",
+    "Polish",
+    "Swahili",
+    "Czech",
+    "French",
+    "Indonesian",
+    "Latin",
+    "Portuguese",
+    "Swedish",
+    "Danish",
+    "German",
+    "Malay",
+    "Punjabi",
+    "Tajik",
+}
+
+DATA_TYPES = {
+    "adjectives",
+    "adverbs",
+    "articles",
+    "autosuggestions",
+    "conjunctions",
+    "emoji_keywords",
+    "nouns",
+    "personal_pronouns",
+    "postpositions",
+    "prepositions",
+    "pronouns",
+    "proper_nouns",
+    "verbs",
+}
+
+# Sub-subdirectories expected for specific languages.
+SUB_DIRECTORIES = {
+    "Chinese": ["Mandarin"],
+    "Hindustani": ["Urdu", "Hindi"],
+    "Norwegian": ["Nynorsk", "Bokmål"],
+    "Pidgin": ["Nigerian"],
+    "Punjabi": ["Shahmukhi", "Gurmukhi"],
+}
+
+
+# Base directory path.
+BASE_DIR = "../language_data_extraction"
+
+
+def validate_project_structure():
+    """
+    Validate that all directories follow the expected project structure and check for unexpected files and directories."""
+    errors = []
+
+    if not os.path.exists(BASE_DIR):
+        print(f"Error: Base directory '{BASE_DIR}' does not exist.")
+        exit(1)
+
+    # Check for unexpected files in BASE_DIR
+    for item in os.listdir(BASE_DIR):
+        item_path = os.path.join(BASE_DIR, item)
+        if os.path.isfile(item_path) and item != "__init__.py":
+            errors.append(f"Unexpected file found in BASE_DIR: {item}")
+
+    # Iterate through the language directories
+    for language in os.listdir(BASE_DIR):
+        language_path = os.path.join(BASE_DIR, language)
+
+        if not os.path.isdir(language_path) or language == "__init__.py":
+            continue
+
+        if language not in LANGUAGES:
+            errors.append(f"Unexpected language directory: {language}")
+            continue
+
+        # Check for unexpected files in language directory
+        for item in os.listdir(language_path):
+            item_path = os.path.join(language_path, item)
+            if os.path.isfile(item_path) and item != "__init__.py":
+                errors.append(f"Unexpected file found in {language} directory: {item}")
+
+        found_subdirs = {
+            item
+            for item in os.listdir(language_path)
+            if os.path.isdir(os.path.join(language_path, item))
+            and item != "__init__.py"
+        }
+
+        if language in SUB_DIRECTORIES:
+            expected_subdirs = set(SUB_DIRECTORIES[language])
+            unexpected_subdirs = found_subdirs - expected_subdirs
+            missing_subdirs = expected_subdirs - found_subdirs
+
+            if unexpected_subdirs:
+                errors.append(
+                    f"Unexpected sub-subdirectories in '{language}': {unexpected_subdirs}"
+                )
+            if missing_subdirs:
+                errors.append(
+                    f"Missing sub-subdirectories in '{language}': {missing_subdirs}"
+                )
+
+            # Check contents of expected sub-subdirectories
+            for subdir in expected_subdirs:
+                subdir_path = os.path.join(language_path, subdir)
+                if os.path.exists(subdir_path):
+                    for item in os.listdir(subdir_path):
+                        item_path = os.path.join(subdir_path, item)
+                        if os.path.isfile(item_path) and item != "__init__.py":
+                            errors.append(
+                                f"Unexpected file found in {language}/{subdir}: {item}"
+                            )
+
+                        elif os.path.isdir(item_path) and item not in DATA_TYPES:
+                            errors.append(
+                                f"Unexpected directory found in {language}/{subdir}: {item}"
+                            )
+
+        elif unexpected_data_types := found_subdirs - DATA_TYPES:
+            errors.append(
+                f"Unexpected subdirectories in '{language}': {unexpected_data_types}"
+            )
+
+    if errors:
+        print("Errors found:")
+        for error in errors:
+            print(f" - {error}")
+        exit(1)
+
+    else:
+        print(
+            "All directories and files are correctly named and organized, and no unexpected files or directories were found."
+        )
+
+
+if __name__ == "__main__":
+    validate_project_structure()

src/scribe_data/language_data_extraction/Hausa/Emoji_keywords/generate_emoji_keywords.py → src/scribe_data/language_data_extraction/Hausa/emoji_keywords/generate_emoji_keywords.py

@@ -1,4 +1,3 @@
-
 """
 Generates keyword-emoji relationships from a selection of Hausa words.