Analyzing the Godot Engine Codebase: Millions of Lines of Code

#!/bin/bash
# analyze_codebase.sh - Count lines of code by language

# Usage:
#   ./analyze_codebase.sh                           # Analyze current directory
#   ./analyze_codebase.sh <git-url>                 # Download and analyze repo
# Example: ./analyze_codebase.sh https://github.com/godotengine/godot.git

if [ $# -eq 0 ]; then
    # No arguments - analyze current directory
    echo "Analyzing current directory: $(pwd)"
    ANALYSIS_DIR="."
else
    # Git URL provided - clone and analyze
    REPO_URL="$1"
    REPO_NAME=$(basename "$REPO_URL" .git)
    ANALYSIS_DIR="${REPO_NAME}-analysis"

    echo "Cloning $REPO_NAME from $REPO_URL..."
    git clone --depth 1 "$REPO_URL" "$ANALYSIS_DIR"
    cd "$ANALYSIS_DIR"
fi

echo -e "\n=== CODEBASE ANALYSIS ==="

# Count total lines
echo -e "\nCounting total lines..."
TOTAL=$(find . -type f -not -path "./.git/*" \
        -exec cat {} + 2>/dev/null | wc -l)
echo "Total lines in repository: $(printf "%'d" $TOTAL)"

# Count by major languages
echo -e "\nLines of code by language:"
echo "=========================="

# Define extensions and their labels
declare -A languages=(
    ["cpp"]="C++ source"
    ["h"]="C/C++ headers"
    ["c"]="C source"
    ["cc"]="C++ source"
    ["cxx"]="C++ source"
    ["hpp"]="C++ headers"
    ["hh"]="C++ headers"
    ["hxx"]="C++ headers"
    ["inl"]="C++ inline"
    ["inc"]="Include files"
    ["ipp"]="C++ inline"
    ["ixx"]="C++ modules"
    ["tcc"]="Template impl"
    ["tpp"]="Template impl"
    ["cs"]="C#"
    ["java"]="Java"
    ["py"]="Python"
    ["gd"]="GDScript"
    ["js"]="JavaScript"
    ["glsl"]="GLSL shaders"
    ["xml"]="XML"
)

# Get all extensions in the codebase
all_extensions=$(find . -type f -name "*.*" -not -path "./.git/*" | \
                sed 's/.*\.//' | sort -u)

# Count known languages
declare -A counted_extensions
for ext in "${!languages[@]}"; do
    count=$(find . -name "*.$ext" -type f -not -path "./.git/*" \
            -exec cat {} + 2>/dev/null | wc -l)
    if [ $count -gt 0 ]; then
        printf "%-15s %'10d lines\n" "${languages[$ext]}:" $count
        counted_extensions[$ext]=1
    fi
done | sort -k2 -nr

# Count unknown extensions
echo -e "\nUnknown file types:"
echo "==================="
unknown_total=0
for ext in $all_extensions; do
    if [[ ! ${counted_extensions[$ext]} ]] && [[ ! ${languages[$ext]} ]]; then
        count=$(find . -name "*.$ext" -type f -not -path "./.git/*" \
                -exec cat {} + 2>/dev/null | wc -l)
        if [ $count -gt 0 ]; then
            printf "%-15s %'10d lines\n" "*.$ext files:" $count
            unknown_total=$((unknown_total + count))
        fi
    fi
done | sort -k2 -nr

if [ $unknown_total -gt 0 ]; then
    echo "----------------------------------------"
    printf "%-15s %'10d lines\n" "Unknown total:" $unknown_total
fi

echo -e "\nTop 10 file types by count:"
find . -type f -name "*.*" -not -path "./.git/*" | sed 's/.*\.//' | \
     sort | uniq -c | sort -nr | head -10