engine

type Article struct {
	// Title is the article title.
	Title string `json:"title"`
	// Byline identifies the article author.
	Byline string `json:"byline"`
	// Dir is the text direction, such as "ltr" or "rtl".
	Dir string `json:"dir"`
	// Lang is the article language from the document metadata.
	Lang string `json:"lang"`
	// Content is the processed inner HTML of Node. It is not sanitized.
	Content string `json:"content"`
	// Node is the processed article element. Its inner HTML is Content when the
	// package returns the Article. Node is not included in JSON because an
	// html.Node contains cyclic links.
	Node *html.Node `json:"-"`
	// TextContent is the article text. It uses one space for each normal
	// whitespace sequence. It retains whitespace in preformatted elements.
	TextContent string `json:"textContent"`
	// Length is the length of TextContent in UTF-16 code units.
	Length int `json:"length"`
	// Excerpt is the article description or a short extract from the content.
	Excerpt string `json:"excerpt"`
	// SiteName is the name of the source site.
	SiteName string `json:"siteName"`
	// PublishedTime is the publication time from the document metadata. The
	// package does not change its source format.
	PublishedTime string `json:"publishedTime"`
}

type Options struct {
	// MaxElemsToParse is the maximum number of HTML elements that extraction
	// accepts. Zero removes the limit.
	MaxElemsToParse int
	// NbTopCandidates is the number of top article candidates to compare.
	NbTopCandidates int
	// CharThreshold is the minimum result length in UTF-16 code units. The
	// package retries extraction if the result is shorter. Each retry uses less
	// strict cleanup rules. If all results are too short, the package returns the
	// longest nonempty result. Zero prevents retries.
	CharThreshold int
	// ClassesToPreserve lists the CSS classes to retain during class cleanup.
	// This field has no effect when KeepClasses is true.
	ClassesToPreserve []string
	// KeepClasses retains all CSS classes when it is true.
	KeepClasses bool
	// DisableJSONLD prevents metadata extraction from JSON-LD when it is true.
	DisableJSONLD bool
	// AllowedVideoRegex identifies video URLs that cleanup can retain. A nil
	// value selects the built-in allowlist.
	AllowedVideoRegex *regexp.Regexp
	// LinkDensityModifier changes the link-density limits that the cleanup rules
	// use to remove a candidate.
	LinkDensityModifier float64
	// Logger receives extraction log records. A nil value turns logs off. The
	// package does not use the global slog logger.
	Logger *slog.Logger
	// Debug enables additional verbose log records. Logger must be non-nil to
	// receive these records.
	Debug bool
}

type ReaderableOptions struct {
	// MinScore is the score that the document must exceed.
	MinScore float64
	// MinContentLength is the minimum candidate length in UTF-16 code units.
	MinContentLength int
}

type TooManyElementsError struct {
	// Count is the number of elements in the document.
	Count int
	// Max is the configured maximum number of elements.
	Max int
}