model

type AggregateRating struct {
	ReviewCount int     `json:"reviewCount,omitempty"`
	RatingCount int     `json:"ratingCount,omitempty"`
	RatingValue float64 `json:"ratingValue,omitempty"`
	BestRating  int     `json:"bestRating,omitempty"`
	WorstRating int     `json:"worstRating,omitempty"`
}

type Allergen struct {
	Name        string `json:"name,omitempty"`
	Description string `json:"description,omitempty"`
	TracesOf    bool   `json:"tracesOf,omitempty"`
}

type DataInput struct {
	Url            string
	Text           string
	RootNode       *html.Node           `json:"-"`
	Document       *goquery.Document    `json:"-"`
	Schemas        *microdata.Microdata `json:"-"`
	RequestOptions RequestOptions       `json:"-"`
}

type DiscoveredFeed struct {
	// Source describes how the feed was discovered.
	Source DiscoverySource `json:"source"`
	// Selector holds the source-specific locator:
	// - "rss-link": the absolute RSS/Atom feed URL
	// - "sitemap": the sitemap URL that was fetched
	// - "dom-container": the structural CSS-path key of the container containing recipe links
	Selector string `json:"selector,omitempty"`
	// UrlPattern is the common path prefix shared by discovered recipe URLs, e.g. "/recipes/".
	UrlPattern string `json:"urlPattern,omitempty"`
	// ConfidenceScore is the scoring result for dom-container source (0.0–1.0).
	ConfidenceScore float64 `json:"confidenceScore,omitempty"`
}

type DiscoverySource string

type Feed struct {
	Name        string         `json:"name,omitempty"`
	Url         string         `json:"url,omitempty"`
	Description string         `json:"description,omitempty"`
	Language    string         `json:"inLanguage,omitempty"`
	Images      []*ImageObject `json:"image,omitempty"`
	Publisher   *Organization  `json:"publisher,omitempty"`
	Entries     []*Recipe      `json:"entries,omitempty"`
	// Discovered is populated when the universal discovery strategy was used.
	// Persist and pass back via FeedOptions.Discovered for faster subsequent calls.
	Discovered *DiscoveredFeed `json:"discovered,omitempty"`
}

type FeedOptions struct {
	ScrapeOptions
	RecipeFilter

	// Skip parsing feed meta tags.
	SkipFeedMeta bool
	// Skip parsing RSS feeds.
	SkipRSSScraper bool
	// Skip the universal discovery strategy.
	SkipDiscoveryScraper bool
	// If > 0, sample up to this many URLs per candidate group during DOM discovery.
	// Failed groups are skipped; confirmed entries are not re-fetched later.
	DiscoverySampleSize int
	// Skip scraping individual entries; useful for quick runs.
	SkipEntriesScrape bool
	// Max entries to scrape individually; 0 = default (20), negative = no cap.
	MaxEntriesForScrape int
	// If non-nil, skip discovery and reuse a previously discovered container/feed.
	// Populate from a prior Feed.Discovered value.
	Discovered *DiscoveredFeed

	// Confidence score above which a DOM container is accepted without sampling (default 0.70).
	DOMAcceptThreshold float64
	// Confidence score above which a DOM container requires sampling before acceptance (default 0.55).
	DOMSampleThreshold float64
	// Minimum number of links a finalized DOM container group must have (default 3).
	DOMMinGroupSize int
	// Minimum number of sibling child groups required before they are merged into one container (default 3).
	DOMMinSiblingsToMerge int
	// Maximum number of candidate DOM groups to validate via sampling (default 3).
	DOMMaxGroupsCheck int
}

type FeedScraper = func(data *DataInput, feed *Feed) error

type HTTPClient interface {
	Do(req *http.Request) (*http.Response, error)
}

type HowToSection struct {
	HowToStep              // because it's optional to have a group, we have to embed `HowToStep` here
	Steps     []*HowToStep `json:"itemListElement,omitempty"`
}

type HowToStep struct {
	Name  string `json:"name,omitempty"`
	Text  string `json:"text,omitempty"`
	Url   string `json:"url,omitempty"`
	Image string `json:"image,omitempty"`
	Video string `json:"video,omitempty"`
}

type HowToTool struct {
	Name        string `json:"name,omitempty"`
	Description string `json:"description,omitempty"`
	Url         string `json:"url,omitempty"`
	Image       string `json:"image,omitempty"`
	Quantity    string `json:"requiredQuantity,omitempty"`
}

type ImageObject struct {
	Url     string `json:"url,omitempty"`
	Width   int    `json:"width,omitempty"`
	Height  int    `json:"height,omitempty"`
	Caption string `json:"caption,omitempty"`
}

type NutritionInformation struct {
	ServingSize           string   `json:"servingSize,omitempty"`           // The serving size, in terms of the number of volume or mass.
	Calories              *float64 `json:"calories,omitempty"`              // The number of calories.
	CarbohydrateContent   *float64 `json:"carbohydrateContent,omitempty"`   // The number of grams of carbohydrates.
	CholesterolContent    *float64 `json:"cholesterolContent,omitempty"`    // The number of milligrams of cholesterol.
	FatContent            *float64 `json:"fatContent,omitempty"`            // The number of grams of fat.
	FiberContent          *float64 `json:"fiberContent,omitempty"`          // The number of grams of fiber.
	ProteinContent        *float64 `json:"proteinContent,omitempty"`        // The number of grams of protein.
	SaturatedFatContent   *float64 `json:"saturatedFatContent,omitempty"`   // The number of grams of saturated fat.
	SodiumContent         *float64 `json:"sodiumContent,omitempty"`         // The number of milligrams of sodium.
	SugarContent          *float64 `json:"sugarContent,omitempty"`          // The number of grams of sugar.
	TransFatContent       *float64 `json:"transFatContent,omitempty"`       // The number of grams of trans fat.
	UnsaturatedFatContent *float64 `json:"unsaturatedFatContent,omitempty"` // The number of grams of unsaturated fat.
	// other minerals commonly found in recipes, not covered by schema.org
	SaltContent      *float64 `json:"saltContent,omitempty"`      // The number of grams of salt.
	IronContent      *float64 `json:"ironContent,omitempty"`      // The number of milligrams of iron.
	PotassiumContent *float64 `json:"potassiumContent,omitempty"` // The number of milligrams of potassium.
	CalciumContent   *float64 `json:"calciumContent,omitempty"`   // The number of milligrams of calcium.
}

type Organization struct {
	Name        string `json:"name,omitempty"`
	Description string `json:"description,omitempty"`
	Url         string `json:"url,omitempty"`
	Logo        string `json:"logo,omitempty"`
}

type Person struct {
	Name        string   `json:"name,omitempty"`
	JobTitle    string   `json:"jobTitle,omitempty"`
	Description string   `json:"description,omitempty"`
	KnowsAbout  []string `json:"knowsAbout,omitempty"`
	Url         string   `json:"url,omitempty"`
	Image       string   `json:"image,omitempty"`
}

type PropertyValue struct {
	Value       string `json:"value,omitempty"` // The quantitative value of the property, e.g. "2", "1/2", "a pinch"
	MaxValue    string `json:"maxValue,omitempty"`
	MinValue    string `json:"minValue,omitempty"`
	UnitText    string `json:"unitText,omitempty"` // The unit of measurement, e.g. "g", "cup", "teaspoon"
	UnitCode    string `json:"unitCode,omitempty"`
	Name        string `json:"name,omitempty"` // The name of the property, e.g. "sugar", "flour", "salt"
	Image       string `json:"image,omitempty"`
	Url         string `json:"url,omitempty"`
	Description string `json:"description,omitempty"`
	// extra fields not covered by schema.org
	Category      string      `json:"category,omitempty"`
	Pantry        bool        `json:"pantry,omitempty"`
	EstimatedCost string      `json:"estimatedCost,omitempty"`
	Allergens     []*Allergen `json:"allergens,omitempty"`
}

type Recipe struct {
	Url           string                `json:"url,omitempty"`
	Name          string                `json:"name,omitempty"`
	Description   string                `json:"description,omitempty"`
	Language      string                `json:"inLanguage,omitempty"`
	Images        []*ImageObject        `json:"image,omitempty"`
	Author        *Person               `json:"author,omitempty"`
	Publisher     *Organization         `json:"publisher,omitempty"`
	Text          string                `json:"text,omitempty"`
	PrepTime      string                `json:"prepTime,omitempty"`
	CookTime      string                `json:"cookTime,omitempty"` // alias `performTime`
	TotalTime     string                `json:"totalTime,omitempty"`
	Difficulty    string                `json:"educationalLevel,omitempty"` // `difficulty` is not a part of Recipe schema https://github.com/schemaorg/schemaorg/issues/3130
	CookingMethod string                `json:"cookingMethod,omitempty"`
	Diets         []string              `json:"suitableForDiet,omitempty"`
	Categories    []string              `json:"recipeCategory,omitempty"`
	Cuisines      []string              `json:"recipeCuisine,omitempty"`
	Keywords      []string              `json:"keywords,omitempty"`
	Yield         string                `json:"recipeYield,omitempty"`        // alias `yield`
	Ingredients   []*PropertyValue      `json:"recipeIngredient,omitempty"`   // alias `supply`
	Equipment     []*HowToTool          `json:"tool,omitempty"`               // alias `tool`, `recipeEquipment` is not a part of Recipe schema https://github.com/schemaorg/schemaorg/issues/3132
	Instructions  []*HowToSection       `json:"recipeInstructions,omitempty"` // alias `step`
	Nutrition     *NutritionInformation `json:"nutrition,omitempty"`
	Rating        *AggregateRating      `json:"aggregateRating,omitempty"`
	CommentCount  int                   `json:"commentCount,omitempty"`
	Video         *VideoObject          `json:"video,omitempty"`
	Links         []string              `json:"sameAs,omitempty"` // maybe not the cleanest name, but we can store additional links here
	EstimatedCost string                `json:"estimatedCost,omitempty"`
	Allergens     []*Allergen           `json:"allergens,omitempty"` // not a part of Recipe schema
	DateModified  *time.Time            `json:"dateModified,omitempty"`
	DatePublished *time.Time            `json:"datePublished,omitempty"`

	// Scraped marks that this recipe went through a full Scrape pass, as opposed to being
	// a stub populated only from a feed listing (title/image/URL).
	Scraped bool `json:"-"`
}

type RecipeFilter struct {
	// Accept recipes without images.
	OptionalImage bool
	// Accept recipes without a publisher.
	OptionalPublisher bool
	// Accept recipes without ingredients.
	OptionalIngredients bool
	// Reject recipes with fewer than this many ingredients; 0 = disabled.
	// Useful to filter out prepared/frozen food recipes.
	MinIngredients int
	// Accept recipes without instructions.
	OptionalInstructions bool
}

type RequestOptions struct {
	// Cancellation context; defaults to context.Background().
	Context context.Context
	// Headers merged with defaults; custom values take priority.
	Headers http.Header
	// HTTP client to use; defaults to a 30s-timeout client.
	HttpClient HTTPClient
}

type ScrapeOptions struct {
	RequestOptions

	// Skip scraping the URL from meta tags; uses the input URL instead.
	SkipMetaUrl bool
	// Skip parsing microdata (primary data source, used by schema and OpenGraph scrapers).
	SkipMicrodata bool
	// Skip parsing schemas.
	SkipSchemaScraper bool
	// Skip parsing OpenGraph tags.
	SkipOpenGraphScraper bool
	// Skip custom scrapers.
	SkipCustomScrapers bool
}

type Scraper = func(data *DataInput, recipe *Recipe) error

type VideoObject struct {
	Name         string     `json:"name,omitempty"`
	Description  string     `json:"description,omitempty"`
	Duration     string     `json:"duration,omitempty"`
	EmbedUrl     string     `json:"embedUrl,omitempty"`
	ContentUrl   string     `json:"contentUrl,omitempty"`
	ThumbnailUrl string     `json:"thumbnailUrl,omitempty"`
	UploadDate   *time.Time `json:"uploadDate,omitempty"`
}