#!/usr/bin/env bash
# Collect project structure for /explore analysis.
# Usage: Run from project root, or pass project path as argument.
# Output: Structured text with directory tree, file counts, language distribution.

set -euo pipefail

PROJECT_DIR="${1:-.}"
cd "$PROJECT_DIR"

echo "=== PROJECT STRUCTURE ==="
echo ""

# Directory tree (depth 3, exclude common noise)
echo "--- Directory Tree (depth 3) ---"
if command -v tree &>/dev/null; then
    tree -L 3 \
        -I "node_modules|vendor|.git|dist|build|out|.venv|__pycache__|*.egg-info|coverage|.nyc_output" \
        --dirsfirst
elif command -v find &>/dev/null; then
    find . -maxdepth 3 \
        -not -path "./.git/*" \
        -not -path "./node_modules/*" \
        -not -path "./vendor/*" \
        -not -path "./dist/*" \
        -not -path "./build/*" \
        -not -path "./out/*" \
        -not -path "./.venv/*" \
        -not -path "*/__pycache__/*" \
        -not -path "*/.egg-info/*" \
        -not -path "*/coverage/*" \
        -not -path "./.nyc_output/*" \
        -print | head -100 | sort
fi

echo ""
echo "=== FILE COUNTS ==="
echo ""

# Count files by extension (top 10)
echo "--- Top 10 File Types ---"
find . -type f \
    -not -path "./.git/*" \
    -not -path "./node_modules/*" \
    -not -path "./vendor/*" \
    -not -path "./dist/*" \
    -not -path "./build/*" \
    -not -path "./out/*" \
    -not -path "./.venv/*" \
    -not -path "*/__pycache__/*" \
    -printf '%f\n' | \
    sed 's/.*\.//' | \
    grep -v '^\.[^/]*$' | \
    sort | uniq -c | sort -rn | head -10

echo ""
echo "=== TOTAL FILE COUNT ==="
echo ""

# Total files (excluding noise)
total=$(find . -type f \
    -not -path "./.git/*" \
    -not -path "./node_modules/*" \
    -not -path "./vendor/*" \
    -not -path "./dist/*" \
    -not -path "./build/*" \
    -not -path "./out/*" \
    -not -path "./.venv/*" \
    | wc -l)
echo "Total source files: $total"

echo ""
echo "=== DEPENDENCY FILES ==="
echo ""

# List dependency declaration files found
for dep_file in "package.json" "requirements.txt" "pyproject.toml" "setup.py" "go.mod" "go.sum" "Cargo.toml" "Cargo.lock" "pom.xml" "build.gradle" "Gemfile" "Gemfile.lock" "composer.json"; do
    if [ -f "$dep_file" ]; then
        echo "FOUND: $dep_file"
    fi
done

# Check for workspace/monorepo configs
echo ""
echo "=== WORKSPACE / MONOREPO ==="
echo ""

for ws_file in "turbo.json" "nx.json" "lerna.json" "pnpm-workspace.yaml" "go.work"; do
    if [ -f "$ws_file" ]; then
        echo "FOUND: $ws_file"
    fi
done

# Check Cargo.toml for workspace
if [ -f "Cargo.toml" ] && grep -q '\[workspace\]' Cargo.toml 2>/dev/null; then
    echo "FOUND: Cargo.toml [workspace]"
fi

echo ""
echo "=== ENTRY POINTS ==="
echo ""

# Try to identify entry points
if [ -f "package.json" ]; then
    main=$(node -e "try{const p=require('./package.json');console.log(p.main||'');}catch(e){}" 2>/dev/null || echo "")
    bin=$(node -e "try{const p=require('./package.json');console.log(typeof p.bin==='string'?p.bin:JSON.stringify(p.bin));}catch(e){}" 2>/dev/null || echo "")
    dev=$(node -e "try{const p=require('./package.json');console.log(p.scripts?.dev||p.scripts?.start||'');}catch(e){}" 2>/dev/null || echo "")
    [ -n "$main" ] && echo "package.json main: $main"
    [ -n "$bin" ] && echo "package.json bin: $bin"
    [ -n "$dev" ] && echo "package.json dev/start: $dev"
fi

for entry in "src/main.ts" "src/main.tsx" "src/main.js" "src/main.jsx" "src/index.ts" "src/index.js" "src/main.py" "app/main.py" "main.go" "src/main.rs" "app.py" "index.js" "index.ts"; do
    if [ -f "$entry" ]; then
        echo "FOUND: $entry"
    fi
done

echo ""
echo "=== COLLECTED ==="