website-htmx-rustelo-code/scripts/content/old/build-localized-content.nu

#!/usr/bin/env nu

# Build Localized Content Script - Updated to use Rust content_processor
# Delegates to the comprehensive content_processor.rs for all content generation

# Simple wrapper that calls the Rust content processor
def main [
    --content-type (-t): string    # Content type to process (blog, recipes, etc.)
    --language (-l): string        # Language to process (en, es, etc.) 
    --category (-c): string        # Specific category to process
    --file (-f): string           # Specific file pattern to process
    --watch (-w)                  # Enable watch mode for hot updates
    --help (-h)                   # Show help
] {
    if $help {
        print $"
(ansi green)📚 Build Localized Content - Rust Content Processor Wrapper(ansi reset)

(ansi blue)USAGE:(ansi reset)
    nu scripts/content/build-localized-content.nu [OPTIONS]

(ansi blue)OPTIONS:(ansi reset)
    --content-type, -t   Content type to process (blog, recipes, etc.)
    --language, -l       Language to process (en, es, etc.)
    --category, -c       Specific category to process
    --file, -f          Specific file pattern to process
    --watch, -w         Enable watch mode for hot updates
    --help, -h          Show this help

(ansi blue)EXAMPLES:(ansi reset)
    # Process all blog content
    nu scripts/content/build-localized-content.nu --content-type blog
    
    # Process English blog content only
    nu scripts/content/build-localized-content.nu --content-type blog --language en
    
    # Process specific category
    nu scripts/content/build-localized-content.nu --content-type blog --category rust
    
    # Process specific file
    nu scripts/content/build-localized-content.nu --file \"rust-web-development-2024\"
    
    # Enable watch mode
    nu scripts/content/build-localized-content.nu --content-type blog --watch

(ansi yellow)NOTE:(ansi reset) This script now delegates to the Rust content_processor for all operations.
Use 'nu scripts/content/build-content-enhanced.nu' for advanced features and statistics.
"
        return
    }

    print $"(ansi green)🚀 Delegating to Rust content processor...(ansi reset)"
    
    mut cmd_args = []
    
    if ($content_type | is-not-empty) {
        $cmd_args = ($cmd_args | append ["--content-type" $content_type])
    }
    
    if ($language | is-not-empty) {
        $cmd_args = ($cmd_args | append ["--language" $language])
    }
    
    if ($category | is-not-empty) {
        $cmd_args = ($cmd_args | append ["--category" $category])
    }
    
    if ($file | is-not-empty) {
        $cmd_args = ($cmd_args | append ["--file" $file])
    }
    
    if $watch {
        $cmd_args = ($cmd_args | append ["--watch"])
    }
    
    # Execute the Rust content processor
    if ($cmd_args | length) > 0 {
        run-external "cargo" "run" "--features=content-static" "--bin" "content_processor" "--" ...$cmd_args
    } else {
        run-external "cargo" "run" "--features=content-static" "--bin" "content_processor"
    }
}

# Load environment variables from .env file
def load_env_from_file [] {
    let env_file = ".env"
    if ($env_file | path exists) {
        let env_content = (open $env_file | lines)
        for line in $env_content {
            # Skip comments and empty lines
            if not ($line | str trim | str starts-with "#") and not ($line | str trim | is-empty) {
                # Parse KEY=VALUE format with variable expansion
                if ($line | str contains "=") {
                    let parts = ($line | split column "=" key value)
                    if ($parts | length) >= 2 {
                        let key = ($parts | first | get key | str trim)
                        let value = ($parts | first | get value | str trim)
                        # Remove quotes and expand ${VARIABLE} patterns
                        let clean_value = ($value | str replace -a '"' '' | str replace -a "'" '')
                        let expanded_value = expand_env_variables $clean_value
                        # Set environment variable
                        load-env {($key): $expanded_value}
                    }
                }
            }
        }
    }
}

# Expand ${VARIABLE} patterns in environment values
def expand_env_variables [value: string] {
    mut result = $value
    
    # Simple ${VAR} expansion
    let var_pattern = '\\$\\{([A-Z_][A-Z0-9_]*)\\}'
    let matches = ($result | parse --regex $var_pattern)
    
    for match in $matches {
        if "capture0" in ($match | columns) {
            let var_name = ($match | get capture0)
            if $var_name in $env {
                let var_value = ($env | get $var_name)
                $result = ($result | str replace $"\\${${var_name}}" $var_value)
            }
        }
    }
    
    $result
}

# Get environment variable with fallback
def get_env_var [var_name: string, default_value: string] {
    if $var_name in $env {
        return ($env | get $var_name)
    }
    return $default_value
}

def main [
    --help(-h)                    # Show help message
    --content-type(-t): string    # Process specific content type only
    --language(-l): string        # Process specific language only
    --use-rust-processor          # Use the new Rust content processor (recommended)
] {
    # Show help if requested
    if $help {
        print $"
(ansi blue)Build Localized Content Script(ansi reset)
Legacy Nushell content processor - DEPRECATED

(ansi yellow)⚠️  DEPRECATION NOTICE:(ansi reset)
This script is deprecated. Please use the new enhanced scripts:
  - scripts/content/build-content.nu (Nushell)
  - scripts/content/build-content.sh (Bash)
  - scripts/content/content-processor.nu (Advanced wrapper)

(ansi green)MIGRATION:(ansi reset)
  Old: ./build-localized-content.nu
  New: ./build-content.nu

The new scripts use the Rust content_processor for better performance,
reliability, and granular processing options.

(ansi green)OPTIONS:(ansi reset)
  -h, --help                Show this help message
  -t, --content-type TYPE   Process specific content type only
  -l, --language LANG       Process specific language only
  --use-rust-processor      Use the new Rust processor (recommended)

(ansi green)EXAMPLES:(ansi reset)
  # Use new Rust processor (recommended)
  ./build-localized-content.nu --use-rust-processor

  # Use new enhanced script instead
  ./build-content.nu --help
        "
        return
    }
    
    # Use Rust processor if requested
    if $use_rust_processor {
        print $"(ansi blue)🚀 Using new Rust content processor...(ansi reset)"
        
        mut cmd = ["cargo", "run", "--features=content-static", "--bin", "content_processor", "--"]
        
        if $content_type != null {
            $cmd = ($cmd | append ["--content-type", $content_type])
        }
        
        if $language != null {
            $cmd = ($cmd | append ["--language", $language])
        }
        
        print $"(ansi blue)🔧 Running: ($cmd | str join ' ')(ansi reset)"
        run-external $cmd.0 ...$cmd.1
        
        print $"(ansi green)✅ Content processing completed!(ansi reset)"
        print $"(ansi yellow)💡 Consider migrating to ./build-content.nu for full features(ansi reset)"
        return
    }
    
    # Legacy processing (kept for compatibility but show deprecation warning)
    print $"(ansi yellow)⚠️  WARNING: Using legacy content processor!(ansi reset)"
    print $"(ansi yellow)   Consider using --use-rust-processor or migrating to ./build-content.nu(ansi reset)"
    
    # Load environment variables
    load_env_from_file
    
    # Configuration from environment
    let content_dir = (get_env_var "SITE_CONTENT_PATH" "site/content")
    let server_content_root = (get_env_var "SITE_SERVER_ROOT_CONTENT" "site/static-content")
    let public_target = $"public/($server_content_root | path basename)"
    let languages = ["en", "es"]
    
    print $"(ansi blue)🌍 Building frontmatter-only content to HTML...(ansi reset)"
    print $"(ansi blue)📁 Source: ($content_dir) - markdown + frontmatter only(ansi reset)"
    print $"(ansi blue)📂 Target: ($public_target) - generated HTML + JSON only(ansi reset)"
    
    # Get enabled content types
    let content_types = get_enabled_content_types $content_dir
    print $"(ansi blue)📋 Content types: ($content_types | str join ', ')(ansi reset)"
    
    # Filter content types if specified
    let filtered_content_types = if $content_type != null {
        $content_types | where $it == $content_type
    } else {
        $content_types
    }
    
    # Filter languages if specified
    let filtered_languages = if $language != null {
        [$language]
    } else {
        $languages
    }
    
    # Build the markdown converter
    build_markdown_converter
    
    # Clean and create target directories
    clean_and_create_target_directories $public_target $filtered_content_types
    
    # Process content for each type and language
    process_all_content $filtered_content_types $filtered_languages $content_dir $public_target
    
    # Create backward compatibility links
    create_compatibility_links $public_target $filtered_content_types
    
    # Generate content statistics and manifest
    generate_content_statistics $filtered_content_types $filtered_languages $content_dir $public_target
    generate_content_manifest $public_target $filtered_content_types $filtered_languages $content_dir
    
    show_completion_summary $public_target $filtered_content_types
}

# Get enabled content types from content-kinds.toml
def get_enabled_content_types [content_dir: string] {
    let content_kinds_file = $"($content_dir)/content-kinds.toml"
    
    if not ($content_kinds_file | path exists) {
        print $"(ansi yellow)⚠️  Warning: content-kinds.toml not found, using defaults(ansi reset)"
        return ["blog", "recipes"]
    }
    
    mut enabled_types = []
    let toml_content = open $content_kinds_file
    
    if "content_kinds" in $toml_content {
        for content_kind in $toml_content.content_kinds {
            if $content_kind.enabled {
                let dir_path = $"($content_dir)/($content_kind.directory)"
                if ($dir_path | path exists) {
                    $enabled_types = ($enabled_types | append $content_kind.directory)
                    print $"(ansi green)✅ Content type '($content_kind.name)' -> '($content_kind.directory)' enabled(ansi reset)"
                } else {
                    print $"(ansi yellow)⚠️  WARNING: Content type '($content_kind.name)' enabled but directory missing - SKIPPING(ansi reset)"
                }
            }
        }
    }
    
    if ($enabled_types | is-empty) {
        print $"(ansi yellow)⚠️  No enabled content types, using defaults(ansi reset)"
        return ["blog", "recipes"]
    }
    
    $enabled_types
}

# Build the markdown converter
def build_markdown_converter [] {
    print $"(ansi blue)🔧 Building markdown converter...(ansi reset)"
    
    try {
        cargo build --bin markdown_converter --features content-static --quiet
        print $"(ansi green)✅ Markdown converter built(ansi reset)"
    } catch {
        print $"(ansi red)❌ Failed to build markdown converter(ansi reset)"
        exit 1
    }
}

# Clean and create target directories
def clean_and_create_target_directories [target_dir: string, content_types: list<string>] {
    print $"(ansi blue)🧹 Cleaning and creating target directories...(ansi reset)"
    
    # Clean existing generated content
    if ($target_dir | path exists) {
        rm -rf $target_dir
    }
    
    # Create fresh target directories
    mkdir $target_dir
    for content_type in $content_types {
        let dir_path = $"($target_dir)/($content_type)"
        mkdir $dir_path
        print $"(ansi blue)📁 Created: ($dir_path)(ansi reset)"
    }
}

# Process all content for each type and language
def process_all_content [content_types: list<string>, languages: list<string>, content_dir: string, target_dir: string] {
    print $"(ansi blue)📝 Processing frontmatter-only content...(ansi reset)"
    
    for content_type in $content_types {
        print $"(ansi blue)🔄 Processing: ($content_type)(ansi reset)"
        
        for lang in $languages {
            let content_source = $"($content_dir)/($content_type)/($lang)"
            let content_target = $"($target_dir)/($content_type)/($lang)"
            
            if ($content_source | path exists) {
                print $"(ansi yellow)  - Processing ($content_type) for ($lang)(ansi reset)"
                mkdir $content_target
                
                # Convert markdown files with frontmatter
                convert_frontmatter_content $content_source $content_target $lang $content_type
                
                # Generate content index from frontmatter
                generate_content_index_from_frontmatter $content_source $content_target $content_type $lang
                
                # Generate filter index for search/filtering
                generate_filter_index $content_type $lang $content_source $content_target
                
                # NOTE: meta.json generation handled by Rust content converter
                
                let html_count = (glob $"($content_target)/**/*.html" | length)
                print $"(ansi green)    ✅ Converted ($html_count) ($content_type) items for ($lang)(ansi reset)"
            } else {
                print $"(ansi yellow)    ⚠️  No ($content_type) content for ($lang)(ansi reset)"
            }
        }
    }
}

# Convert markdown files with frontmatter
def convert_frontmatter_content [content_source: string, content_target: string, lang: string, content_type: string] {
    let converter = "./target/debug/markdown_converter"
    
    # Convert top-level markdown files
    let top_level_files = (glob $"($content_source)/*.md")
    for md_file in $top_level_files {
        let filename = ($md_file | path basename | path parse | get stem)
        let html_file = $"($content_target)/($filename).html"
        convert_single_markdown $md_file $html_file $converter
    }
    
    # Process category directories
    let category_dirs = (ls $content_source | where type == dir | get name)
    for category_dir in $category_dirs {
        let category = ($category_dir | path basename)
        let category_target = $"($content_target)/($category)"
        mkdir $category_target
        
        print $"(ansi blue)    📁 Processing category: ($category)(ansi reset)"
        
        # Convert markdown files in category
        let category_files = (glob $"($category_dir)/*.md")
        for md_file in $category_files {
            let filename = ($md_file | path basename | path parse | get stem)
            let html_file = $"($category_target)/($filename).html"
            convert_single_markdown $md_file $html_file $converter
        }
        
        # Generate category index from frontmatter
        let category_posts = (glob $"($category_dir)/*.md" | length)
        if $category_posts > 0 {
            generate_category_index_from_frontmatter $category_dir $category_target $category $content_type $lang
        }
    }
}

# Convert a single markdown file 
def convert_single_markdown [input_file: string, output_file: string, converter: string] {
    let input_basename = ($input_file | path basename)
    let output_basename = ($output_file | path basename)
    
    print $"(ansi yellow)    Converting: ($input_basename) -> ($output_basename)(ansi reset)"
    
    let output_dir = ($output_file | path dirname)
    mkdir $output_dir
    
    try {
        ^$converter $input_file -o $output_file
    } catch {
        print $"(ansi yellow)    ⚠️  Warning: Failed to convert ($input_file)(ansi reset)"
    }
}

# Generate content index from frontmatter data
def generate_content_index_from_frontmatter [content_source: string, content_target: string, content_type: string, lang: string] {
    let index_file = $"($content_target)/index.json"
    let generated_at = (date now | format date "%Y-%m-%dT%H:%M:%SZ")
    
    print $"(ansi blue)  - Generating content index from frontmatter...(ansi reset)"
    
    mut posts = []
    
    # Process all markdown files
    let md_files = (glob $"($content_source)/**/*.md")
    for md_file in $md_files {
        let frontmatter = extract_frontmatter $md_file
        let filename = ($md_file | path basename | path parse | get stem)
        
        # Extract frontmatter fields
        let title = (extract_from_frontmatter $frontmatter "title" $filename)
        let published = (extract_from_frontmatter $frontmatter "published" "true")
        let category = (extract_from_frontmatter $frontmatter "category" "general")
        let tags_raw = (extract_from_frontmatter $frontmatter "tags" "[]")
        let excerpt = (extract_from_frontmatter $frontmatter "excerpt" "")
        let date = (extract_from_frontmatter $frontmatter "date" "")
        let author = (extract_from_frontmatter $frontmatter "author" "")
        let featured = (extract_from_frontmatter $frontmatter "featured" "false")
        
        # Only include published content
        if $published == "true" {
            # Determine HTML path relative to category
            let relative_path = ($md_file | str replace $"($content_source)/" "")
            let html_path = ($relative_path | str replace ".md" ".html")
            
            $posts = ($posts | append {
                id: $filename,
                title: $title,
                category: $category,
                tags: $tags_raw,
                excerpt: $excerpt,
                date: $date,
                author: $author,
                featured: ($featured == "true"),
                html_file: $html_path
            })
        }
    }
    
    let content_index = {
        generated_at: $generated_at,
        content_type: $content_type,
        language: $lang,
        ($content_type): $posts
    }
    
    $content_index | to json | save --force $index_file
    print $"(ansi green)  ✅ Generated content index: ($index_file)(ansi reset)"
}

# Generate category index from frontmatter
def generate_category_index_from_frontmatter [category_dir: string, category_target: string, category: string, content_type: string, lang: string] {
    let index_file = $"($category_target)/index.json"
    let generated_at = (date now | format date "%Y-%m-%dT%H:%M:%SZ")
    
    print $"(ansi blue)      🔍 Generating category index: ($category)(ansi reset)"
    
    mut posts = []
    let md_files = (glob $"($category_dir)/*.md")
    
    for md_file in $md_files {
        let frontmatter = extract_frontmatter $md_file
        let filename = ($md_file | path basename | path parse | get stem)
        
        let title = (extract_from_frontmatter $frontmatter "title" $filename)
        let published = (extract_from_frontmatter $frontmatter "published" "true")
        let sort_order = (extract_from_frontmatter $frontmatter "sort_order" "0")
        let css_class = (extract_from_frontmatter $frontmatter "css_class" "")
        
        if $published == "true" {
            $posts = ($posts | append {
                id: $filename,
                title: $title,
                css_class: $css_class,
                sort_order: ($sort_order | into int),
                html_file: $"($filename).html"
            })
        }
    }
    
    # Sort by sort_order
    $posts = ($posts | sort-by sort_order)
    
    let category_index = {
        generated_at: $generated_at,
        content_type: $content_type,
        language: $lang,
        category: $category,
        title: ($category | str title-case),
        posts: $posts
    }
    
    $category_index | to json | save --force $index_file
    print $"(ansi green)      ✅ Category index: ($index_file)(ansi reset)"
}

# Using frontmatter functions from modular library (lib/frontmatter.nu)

# Generate filter index for search functionality
def generate_filter_index [content_type: string, lang: string, source_dir: string, target_dir: string] {
    let filter_index_file = $"($target_dir)/filter-index.json"
    let generated_at = (date now | format date "%Y-%m-%dT%H:%M:%SZ")
    
    print $"(ansi blue)  - Generating filter index for ($content_type) ($lang)...(ansi reset)"
    
    # Count total published files from frontmatter
    mut total_files = 0
    mut tags = []
    mut categories = []
    
    let md_files = (glob $"($source_dir)/**/*.md")
    for md_file in $md_files {
        let frontmatter = extract_frontmatter $md_file
        let published = (extract_from_frontmatter $frontmatter "published" "true")
        
        if $published == "true" {
            $total_files = ($total_files + 1)
            
            # Collect tags and categories for filtering
            let category = (extract_from_frontmatter $frontmatter "category" "")
            if not ($category | is-empty) and $category not-in $categories {
                $categories = ($categories | append $category)
            }
            
            let tags_raw = (extract_from_frontmatter $frontmatter "tags" "")
            # Simple tags extraction (could be improved for complex arrays)
            if not ($tags_raw | is-empty) {
                let extracted_tags = ($tags_raw | str replace -a '[' '' | str replace -a ']' '' | str replace -a '"' '' | split row ',' | each {|tag| $tag | str trim})
                for tag in $extracted_tags {
                    if not ($tag | is-empty) and $tag not-in $tags {
                        $tags = ($tags | append $tag)
                    }
                }
            }
        }
    }
    
    let filter_index = {
        generated_at: $generated_at,
        content_type: $content_type,
        language: $lang,
        total_posts: $total_files,
        tags: $tags,
        categories: $categories
    }
    
    $filter_index | to json | save --force $filter_index_file
    print $"(ansi green)    ✅ Filter index: ($filter_index_file)(ansi reset)"
}

# NOTE: meta.json generation now handled by Rust content converter

# Create backward compatibility links
def create_compatibility_links [target_dir: string, content_types: list<string>] {
    print $"(ansi blue)🔗 Creating backward compatibility links...(ansi reset)"
    
    for content_type in $content_types {
        let en_index = $"($target_dir)/($content_type)/en/index.json"
        let fallback_index = $"($target_dir)/($content_type)/index.json"
        
        if ($en_index | path exists) {
            try {
                if ($fallback_index | path exists) {
                    rm $fallback_index
                }
                ln -s "en/index.json" $fallback_index
                print $"(ansi green)  ✅ Created fallback ($content_type) index(ansi reset)"
            } catch {
                print $"(ansi yellow)  ⚠️  Failed to create symlink for ($content_type)(ansi reset)"
            }
        }
    }
}

# Generate content statistics
def generate_content_statistics [content_types: list<string>, languages: list<string>, content_dir: string, target_dir: string] {
    print $"(ansi blue)📊 Content Statistics:(ansi reset)"
    
    for lang in $languages {
        print $"(ansi blue)  Language: ($lang)(ansi reset)"
        for content_type in $content_types {
            let html_count = (glob $"($target_dir)/($content_type)/($lang)/**/*.html" | length)
            let md_count = (glob $"($content_dir)/($content_type)/($lang)/**/*.md" | length)
            print $"(ansi yellow)    📝 ($content_type): ($md_count) MD → ($html_count) HTML(ansi reset)"
        }
    }
}

# Generate content manifest
def generate_content_manifest [target_dir: string, content_types: list<string>, languages: list<string>, content_dir: string] {
    let manifest_file = $"($target_dir)/content-manifest.json"
    let generated_at = (date now | format date "%Y-%m-%dT%H:%M:%SZ")
    
    print $"(ansi blue)📋 Generating content manifest...(ansi reset)"
    
    mut structure = {}
    for content_type in $content_types {
        mut lang_data = {}
        for lang in $languages {
            let html_count = (glob $"($target_dir)/($content_type)/($lang)/**/*.html" | length)
            let md_count = (glob $"($content_dir)/($content_type)/($lang)/**/*.md" | length)
            let has_index = ($"($target_dir)/($content_type)/($lang)/index.json" | path exists)
            
            $lang_data = ($lang_data | upsert $lang {
                html_count: $html_count,
                markdown_count: $md_count,
                has_index: $has_index
            })
        }
        $structure = ($structure | upsert $content_type $lang_data)
    }
    
    let manifest = {
        generated_at: $generated_at,
        version: "2.0",
        approach: "frontmatter-only",
        languages: $languages,
        content_types: $content_types,
        content_source_path: $content_dir,
        content_target_path: $target_dir,
        build_info: {
            source_format: "markdown + yaml frontmatter",
            output_format: "html + json indexes",
            converter: "rustelo_markdown_converter",
            features: ["frontmatter-extraction", "syntax-highlighting", "localization"]
        },
        structure: $structure
    }
    
    $manifest | to json | save --force $manifest_file
    print $"(ansi green)  ✅ Content manifest: ($manifest_file)(ansi reset)"
}

# Show completion summary
def show_completion_summary [target_dir: string, content_types: list<string>] {
    print ""
    print $"(ansi green)🎉 Frontmatter-only content build complete!(ansi reset)"
    print ""
    print $"(ansi blue)✅ Clean separation achieved:(ansi reset)"
    print $"  📝 Source: Only .md files with frontmatter metadata"
    print $"  🌐 Generated: Only .html + .json files in ($target_dir)"
    print ""
    print $"(ansi blue)📁 Generated structure:(ansi reset)"
    for content_type in $content_types {
        print $"  📄 ($target_dir)/($content_type)/{{lang}}/*.html"
        print $"  📋 ($target_dir)/($content_type)/{{lang}}/index.json"
        print $"  🔍 ($target_dir)/($content_type)/{{lang}}/filter-index.json"
    }
    print $"  📊 ($target_dir)/content-manifest.json"
    print ""
    print $"(ansi green)🔄 To rebuild: Run this script after content changes(ansi reset)"
}