#!/bin/bash

# Download and process REMnux documentation for offline use
# This script creates a searchable database of all tools and their usage

set -e

DOCS_DIR="/opt/remnux-docs"
TOOLS_DB="/opt/remnux-docs/tools.db"

echo "📚 Downloading REMnux Documentation..."

# Create documentation directory
mkdir -p "$DOCS_DIR"

# Download key documentation files from REMnux docs
BASE_URL="https://docs.remnux.org"

# Categories of tools to download
CATEGORIES=(
    "analyze+documents/pdf"
    "analyze+documents/general" 
    "analyze+documents/microsoft+office"
    "analyze+documents/email+messages"
    "examine+static+properties/general"
    "statically+analyze+code/general"
    "statically+analyze+code/scripts"
    "dynamically+reverse-engineer+code/general"
    "gather+and+analyze+data"
    "view+or+edit+files"
    "general+utilities"
)

# Function to download and process a documentation page
download_category() {
    local category="$1"
    local filename=$(echo "$category" | sed 's/+/_/g' | sed 's/\//_/g')
    
    echo "Downloading: $category"
    if curl -s "$BASE_URL/discover-the-tools/$category.md" -o "$DOCS_DIR/${filename}.md"; then
        echo "✓ Downloaded $filename.md"
    else
        echo "⚠ Failed to download $category"
    fi
}

# Download all categories
for category in "${CATEGORIES[@]}"; do
    download_category "$category"
done

# Create a consolidated tools database
echo "🔍 Creating searchable tools database..."

# Function to extract tool information from markdown files
create_tools_db() {
    echo "# REMnux Tools Database" > "$TOOLS_DB"
    echo "# Format: TOOL_NAME|DESCRIPTION|CATEGORY|USAGE_HINTS" >> "$TOOLS_DB"
    echo "" >> "$TOOLS_DB"
    
    for md_file in "$DOCS_DIR"/*.md; do
        if [[ -f "$md_file" ]]; then
            local category=$(basename "$md_file" .md | sed 's/_/ /g')
            
            # Extract tool entries (they start with ##)
            awk -v cat="$category" '
                /^## / { 
                    if (tool_name != "") {
                        print tool_name "|" description "|" cat "|" usage
                    }
                    tool_name = substr($0, 4)  # Remove "## "
                    description = ""
                    usage = ""
                    in_tool = 1
                    next
                }
                /^#/ && !/^## / { in_tool = 0; next }
                in_tool && /^[A-Z]/ && description == "" { 
                    description = $0 
                    next
                }
                in_tool && /^\*\*Website/ { 
                    usage = usage $0 " "
                    next
                }
                in_tool && /^\*\*Notes/ { 
                    usage = usage $0 " "
                    next
                }
                END {
                    if (tool_name != "") {
                        print tool_name "|" description "|" cat "|" usage
                    }
                }
            ' "$md_file" >> "$TOOLS_DB"
        fi
    done
}

create_tools_db

# Add our custom tools to the database
echo "" >> "$TOOLS_DB"
echo "# Additional Tools Added to Container" >> "$TOOLS_DB"
echo "capa|Malware capability detection tool from Mandiant|malware analysis|Analyze executable files to identify capabilities" >> "$TOOLS_DB"
echo "box-js|JavaScript sandbox for malware analysis|malware analysis|box-js sample.js to analyze JavaScript in sandbox" >> "$TOOLS_DB"
echo "visidata|Interactive data exploration tool|data analysis|vd filename.csv to explore data interactively" >> "$TOOLS_DB"
echo "unfurl_cli.py|URL analysis and extraction tool|data analysis|unfurl_cli.py URL to analyze and extract components" >> "$TOOLS_DB"

echo "✅ Documentation download complete!"
echo "📊 Tools database created at: $TOOLS_DB"

# Count tools
TOOL_COUNT=$(grep -c "^[^#]" "$TOOLS_DB" | head -1)
echo "🔧 Indexed $TOOL_COUNT tools"

echo ""
echo "Usage: Use 'find-tool' command to search through all available tools"