parser

type AttributeRemoveTransform struct {
	AttributeName string
}

type AttributeSetTransform struct {
	AttributeName  string
	AttributeValue string
}

type ClassAddTransform struct {
	ClassName string
}

type ClassRemoveTransform struct {
	ClassName string
}

type ContentExtractor struct {
	FieldExtractor
	Clean      []string                 // Selectors to remove
	Transforms map[string]TransformFunc // Element transformations
}

type CustomExtractor struct {
	Domain        string
	Title         FieldExtractor
	Author        FieldExtractor
	Content       ContentExtractor
	DatePublished FieldExtractor
	LeadImageURL  FieldExtractor
	Dek           FieldExtractor
	NextPageURL   FieldExtractor
	Excerpt       FieldExtractor
	Extend        map[string]FieldExtractor
}

type CustomFunctionTransform struct {
	TransformName     string
	TransformFunction func(*goquery.Selection) *goquery.Selection
}

type ErrorCollection struct {
	Errors []*ParseError `json:"errors"`
}

type Extractor interface {
	Extract(doc *goquery.Document, url string, opts *ExtractorOptions) (*Result, error)
	GetDomain() string
}

type ExtractorFunc func(*goquery.Document, string) (interface{}, error)

type ExtractorOptions struct {
	URL         string
	HTML        string
	MetaCache   map[string]string
	Fallback    bool
	ContentType string
}

type FieldExtractor struct {
	Selectors       SelectorList  // Type-safe CSS selectors (replaces []interface{})
	SelectorsLegacy []interface{} `json:"selectors,omitempty"` // Deprecated: use Selectors instead
	AllowMultiple   bool
	DefaultCleaner  bool
}

type Hermes struct {
	// contains filtered or unexported fields
}

type ParseError struct {
	URL       string    `json:"url"`                // URL being parsed when error occurred
	Phase     string    `json:"phase"`              // Parse phase: "fetch", "extract", "clean", etc.
	Err       error     `json:"error"`              // Underlying error
	Timestamp time.Time `json:"timestamp"`          // When the error occurred
	Field     string    `json:"field,omitempty"`    // Specific field being extracted (if applicable)
	Selector  string    `json:"selector,omitempty"` // CSS selector being processed (if applicable)
	Message   string    `json:"message,omitempty"`  // Additional context message
}

type ParseErrorType string

type Parser interface {
	Parse(url string, opts *ParserOptions) (*Result, error)
	ParseHTML(html string, url string, opts *ParserOptions) (*Result, error)
}

type ParserOptions struct {
	FetchAllPages        bool                     // Fetch and merge multi-page articles
	Fallback             bool                     // Use generic extractor as fallback
	ContentType          string                   // Output format: "html", "markdown", "text"
	Headers              map[string]string        // Custom HTTP headers
	CustomExtractor      *CustomExtractor         // Custom extraction rules
	Extend               map[string]ExtractorFunc // Extended fields
	HTTPClient           *http.Client             // HTTP client to use for requests
	AllowPrivateNetworks bool                     // Allow SSRF to private networks (default: false)
}

type PoolStats struct {
	// All fields are deprecated and return zero values
	ResultsCreated int64
	ResultsReused  int64
	BuffersCreated int64
	BuffersReused  int64
	ParsersCreated int64
	ParsersReused  int64
	LastReset      time.Time
}

type Result struct {
	Title         string                 `json:"title"`
	Content       string                 `json:"content"`
	Author        string                 `json:"author"`
	DatePublished *time.Time             `json:"date_published"`
	LeadImageURL  string                 `json:"lead_image_url"`
	Dek           string                 `json:"dek"`
	NextPageURL   string                 `json:"next_page_url"`
	URL           string                 `json:"url"`
	Domain        string                 `json:"domain"`
	Excerpt       string                 `json:"excerpt"`
	WordCount     int                    `json:"word_count"`
	Direction     string                 `json:"direction"`
	TotalPages    int                    `json:"total_pages"`
	RenderedPages int                    `json:"rendered_pages"`
	ExtractorUsed string                 `json:"extractor_used,omitempty"`
	Extended      map[string]interface{} `json:"extended,omitempty"`

	// Site metadata fields
	SiteName    string `json:"site_name"`
	SiteTitle   string `json:"site_title"`
	SiteImage   string `json:"site_image"`
	Favicon     string `json:"favicon"`
	Description string `json:"description"`
	Language    string `json:"language"`
	ThemeColor  string `json:"theme_color,omitempty"`

	// Video metadata fields
	VideoURL      string                 `json:"video_url,omitempty"`
	VideoMetadata map[string]interface{} `json:"video_metadata,omitempty"`

	// Error handling fields for JS compatibility
	Error   bool   `json:"error,omitempty"`
	Message string `json:"message,omitempty"`
}

type SelectorConfig struct {
	// CSS selector string (e.g., "h1.title", ".article-body")
	Selector string

	// Optional attribute to extract (e.g., "content", "datetime", "href")
	// If empty, extracts text content
	Attribute string

	// Optional index for multiple matches (0-based, -1 for all)
	Index int
}

type SelectorList []SelectorConfig

type TagRenameTransform struct {
	OriginalTag string
	NewTag      string
}

type TextReplaceTransform struct {
	OldText string
	NewText string
}

type Transform interface {
	// Transform applies the transformation to the given selection
	Transform(selection *goquery.Selection) *goquery.Selection

	// Name returns the name/type of this transform
	Name() string
}

type TransformFunc func(*goquery.Selection) string

type TransformRegistry map[string]Transform