Bug/py icu

.github/workflows/update_scribe_data.yml

@@ -43,10 +43,10 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
 
-      - name: Set up Python 3.11
+      - name: Set up Python 3.12
         uses: actions/setup-python@v4
         with:
-          python-version: "3.11"
+          python-version: "3.12"
 
       - name: Install system dependencies
         run: |
@@ -60,6 +60,15 @@ jobs:
         id: run_script
         run: ./update_data.sh true
 
+      - name: Verify SQLite output
+        run: |
+          DB="./packs/sqlite/ENLanguageData.sqlite"
+          echo "Tables in $DB:"
+          sqlite3 "$DB" ".tables"
+          echo ""
+          echo "Sample row from emoji_keywords:"
+          sqlite3 "$DB" "SELECT * FROM emoji_keywords LIMIT 1;"
+
       - name: Create deployment package
         run: |
           if [ ! -d "./packs/sqlite" ]; then

update_data.sh

@@ -17,7 +17,7 @@ PROJECT_ROOT=$(pwd)
 
 # Define target languages and data types.
 TARGET_LANGUAGES=("english" "french" "german" "italian" "spanish" "portuguese" "russian" "swedish")
-DATA_TYPES=("nouns" "verbs")
+DATA_TYPES=("nouns" "verbs" "emoji_keywords")
 
 RED='\033[0;31m'
 GREEN='\033[0;32m'
@@ -100,6 +100,15 @@ if ! command -v pip &> /dev/null && ! command -v pip3 &> /dev/null; then
     success "pip installed successfully"
 fi
 
+# MARK: System Dependencies
+
+log "🔧 Installing system dependencies for PyICU..."
+sudo apt-get install -y libicu-dev pkg-config g++ python3-dev || {
+    error "Failed to install system dependencies"
+    exit 1
+}
+success "System dependencies installed"
+
 # MARK: Make Venv
 
 log "🧪 Setting up virtual environment..."
@@ -130,6 +139,13 @@ pip install -e . || {
 }
 success "Dependencies installed successfully"
 
+log "🔧 Building PyICU from source against local ICU..."
+pip install --force-reinstall --no-binary :all: PyICU || {
+    error "Failed to build PyICU from source"
+    exit 1
+}
+success "PyICU built from source successfully"
+
 # MARK: Download Wikidata Dump First
 
 DUMP_DIR="./scribe_data_wikidata_dumps_export"