ADFA-989 add tier 1 and tier 2 tooltips to new documentation sqlite db (#9)

* Snapshot of tooltips from Elissa
* Support for import of Elissa's tooltip xlsx file; TODO: Alex's tooltips
* Add tooltips to publish db workflow

Author: hal-eisen-adfa

.github/workflows/publish-doc-db.yaml

@@ -60,6 +60,10 @@ jobs:
             PYTHONPATH=scripts uv run python scripts/ingest.py -p build/documentation-${{ github.ref_name }}.sqlite -d "$dir"
           done
 
+      - name: Store tooltips
+        run: |
+          PYTHONPATH=scripts uv run python scripts/import_tooltips.py -i SourceDocs/Tooltips/tooltips.xlsx -d build/documentation-${{ github.ref_name }}.sqlite
+
       - name: Verify database
         run: |
           if [ ! -f "build/documentation-${{ github.ref_name }}.sqlite" ]; then

.gitignore

@@ -9,4 +9,6 @@ ProcessDocs/ProcessKotlinDocs/KotlinLLMScratch/openaikey.txt
 ProcessDocs/ProcessAndroidDevSite/DevsiteLLMScratch/openaikey.txt
 __pycache__/
 *.py[cod]
-*$py.class
+*$py.class
+*.db
+*.sqlite

SourceDocs/Tooltips/tooltips.xlsx

@@ -3,3 +3,4 @@ lxml
 faker
 brotli
 Pillow
+openpyxl

requirements.txt

@@ -59,14 +59,6 @@ class DocumentationDatabase:
         value TEXT NOT NULL UNIQUE,
         compression TEXT NOT NULL
     );
-
-    CREATE TABLE IF NOT EXISTS ide_tooltip_table (
-        id INTEGER PRIMARY KEY AUTOINCREMENT,
-        path TEXT NOT NULL,
-        languageID INTEGER NOT NULL,
-        content TEXT NOT NULL,
-        FOREIGN KEY (languageID) REFERENCES Languages(id)
-    );
     """
 
     def __init__(self, database_path):
@@ -87,12 +79,20 @@ def __init__(self, database_path):
                 cursor = connection.cursor()
                 cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
                 tables = cursor.fetchall()
-                expected_tables = {'ide_tooltip_table', 'Content', 'Languages', 'ContentTypes'}
+                # Core tables that must exist
+                required_tables = {'Content', 'Languages', 'ContentTypes'}
+                # Optional tables that may exist
+                optional_tables = {'ide_tooltip_table'}
                 existing_tables = {table[0] for table in tables}
                 # Ignore any tables that start with 'sqlite_'
                 filtered_tables = {table for table in existing_tables if not table.startswith('sqlite_')}
-                if filtered_tables != expected_tables:
-                    raise ValueError("Database schema does not match the expected schema")
+                # Check if all required tables exist
+                if not required_tables.issubset(filtered_tables):
+                    raise ValueError("Database schema is missing required tables")
+                # Check if there are any unexpected tables
+                unexpected_tables = filtered_tables - required_tables - optional_tables
+                if unexpected_tables:
+                    raise ValueError(f"Database schema contains unexpected tables: {unexpected_tables}")
 
     @contextlib.contextmanager
     def get_connection(self):
@@ -131,12 +131,14 @@ def populate_languages(self, cursor):
         cursor.execute("INSERT INTO Languages (value) VALUES ('en-US');")
 
     def normalize_path(self, path):
-        """Remove leading ../ and ./ sequences from a path."""
+        """Remove leading ../, ./ sequences and 'SourceDocs' from a path."""
         while path.startswith('../') or path.startswith('./'):
             if path.startswith('../'):
                 path = path[3:]
             elif path.startswith('./'):
                 path = path[2:]
+        if path.startswith('SourceDocs/'):
+            path = path[11:]  # Remove 'SourceDocs/' (11 characters)
         return path
 
     def add_file(self, path, content, language):

scripts/DocumentationDatabase.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+
+import sys
+import os
+import argparse
+from tooltips import TooltipDatabase
+import openpyxl
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Import tooltips from Excel file to SQLite database',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+    
+    parser.add_argument('-i', '--import',
+                      dest='xlsx_file',
+                      required=True,
+                      help='Path to the Excel file containing tooltips')
+    
+    parser.add_argument('-d', '--database',
+                      dest='sqlite_db',
+                      required=True,
+                      help='Path to the SQLite database file to create/update')
+    
+    args = parser.parse_args()
+    
+    # Validate input files
+    if not os.path.exists(args.xlsx_file):
+        parser.error(f"Excel file '{args.xlsx_file}' does not exist")
+    
+    if not args.xlsx_file.endswith('.xlsx'):
+        parser.error(f"'{args.xlsx_file}' is not an Excel file")
+    
+    # Create database directory if it doesn't exist
+    db_dir = os.path.dirname(args.sqlite_db)
+    if db_dir and not os.path.exists(db_dir):
+        os.makedirs(db_dir)
+    
+    try:
+        # Create database and import data
+        db = TooltipDatabase(args.sqlite_db, args.xlsx_file)
+        result = db.read_xlsx()
+        
+        # Print summary
+        print(f"\nImport Summary:")
+        print(f"Total rows in Excel: {result['total_rows']}")
+        print(f"Successfully processed: {result['processed_rows']}")
+        print(f"Skipped rows: {len(result['skipped_rows'])}")
+        
+        if result['skipped_rows']:
+            print("\nSkipped rows details:")
+            for row_num, error in result['skipped_rows']:
+                print(f"Row {row_num}: {error}")
+        
+        print(f"\nSuccessfully imported tooltips from '{args.xlsx_file}' to '{args.sqlite_db}'")
+        
+    except Exception as e:
+        parser.error(f"Error importing tooltips: {str(e)}")
+
+if __name__ == '__main__':
+    main()