hottub/src/providers/rule34video.rs

use crate::DbPool;
use crate::api::ClientVersion;
use crate::providers::{Provider, requester_or_default, slug_dashed};
use crate::status::*;
use crate::util::cache::VideoCache;
use crate::util::discord::send_discord_error_report;
use crate::util::parse_abbreviated_number;
use crate::util::time::parse_time_to_seconds;
use crate::videos::{ServerOptions, VideoItem};
use async_trait::async_trait;
use error_chain::error_chain;
use htmlentity::entity::{ICodedDataTrait, decode};
use scraper::{Html, Selector};
use std::collections::HashMap;
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
use percent_encoding::{NON_ALPHANUMERIC, utf8_percent_encode};
use std::vec;

/// Hands out `/proxy/rule34video/` URLs instead of the page URLs. Switched off;
/// the proxy and resolver stay in place (`proxies/rule34video.rs`).
const USE_MEDIA_PROXY: bool = false;
const TARGET_TTL: Duration = Duration::from_secs(6 * 60 * 60);
const TARGET_CACHE_SIZE: usize = 2000;
/// A probed archive smaller than this loses to keyword search: "elf girl" is a
/// one-video tag, while the search finds hundreds.
const MIN_PROBED_ARCHIVE_ITEMS: usize = 4;

pub const CHANNEL_METADATA: crate::providers::ProviderChannelMetadata =
    crate::providers::ProviderChannelMetadata {
        group_id: "hentai-animation",
        tags: &["rule34", "animation", "fandom"],
    };

error_chain! {
    foreign_links {
        Io(std::io::Error);
        HttpRequest(wreq::Error);
    }
    errors {
        ParsingError(t: String) {
            description("html parsing error")
            display("HTML parsing error: '{}'", t)
        }
    }
}

/// What a request resolves to. Artists live under `/models/`, franchises and
/// genres under `/categories/`, characters and everything else under `/tags/`.
#[derive(Debug, Clone, PartialEq, Eq)]
enum Target {
    Latest,
    Search(String),
    Artist(String),
    Category(String),
    Tag(String),
}

impl Target {
    /// Archive path (`models/{slug}`, ...) for the archive targets.
    fn archive_path(&self) -> Option<String> {
        match self {
            Target::Artist(slug) => Some(format!("models/{slug}")),
            Target::Category(slug) => Some(format!("categories/{slug}")),
            Target::Tag(slug) => Some(format!("tags/{slug}")),
            _ => None,
        }
    }
}

#[derive(Clone)]
pub struct Rule34videoProvider {
    url: String,
    /// Bare query -> resolved target, so later pages skip the archive probes.
    targets: Arc<Mutex<HashMap<String, (Instant, Target)>>>,
}

impl Rule34videoProvider {
    pub fn new() -> Self {
        Rule34videoProvider {
            url: "https://rule34video.com".to_string(),
            targets: Arc::new(Mutex::new(HashMap::new())),
        }
    }

    fn remembered_target(&self, query: &str) -> Option<Target> {
        let targets = self.targets.lock().ok()?;
        let (time, target) = targets.get(&slug_dashed(query))?;
        (time.elapsed() < TARGET_TTL).then(|| target.clone())
    }

    fn remember_target(&self, query: &str, target: &Target) {
        if let Ok(mut targets) = self.targets.lock() {
            if targets.len() >= TARGET_CACHE_SIZE {
                targets.retain(|_, (time, _)| time.elapsed() < TARGET_TTL);
                if targets.len() >= TARGET_CACHE_SIZE {
                    targets.clear();
                }
            }
            targets.insert(slug_dashed(query), (Instant::now(), target.clone()));
        }
    }

    fn build_channel(&self, _clientversion: ClientVersion) -> Channel {
        Channel {
            id: "rule34video".to_string(),
            name: "Rule34Video".to_string(),
            description: "If it exists, there is porn".to_string(),
            premium: false,
            favicon: "https://www.google.com/s2/favicons?sz=64&domain=rule34video.com".to_string(),
            status: "active".to_string(),
            categories: vec![],
            options: vec![ChannelOption {
                id: "sort".to_string(),
                title: "Sort".to_string(),
                description: "Sort the Videos".to_string(),
                systemImage: "list.number".to_string(),
                colorName: "blue".to_string(),
                options: vec![
                    FilterOption {
                        id: "post_date".to_string(),
                        title: "Newest".to_string(),
                    },
                    FilterOption {
                        id: "video_viewed".to_string(),
                        title: "Most Viewed".to_string(),
                    },
                    FilterOption {
                        id: "rating".to_string(),
                        title: "Top Rated".to_string(),
                    },
                    FilterOption {
                        id: "duration".to_string(),
                        title: "Longest".to_string(),
                    },
                    FilterOption {
                        id: "pseudo_random".to_string(),
                        title: "Random".to_string(),
                    },
                ],
                multiSelect: false,
            }],
            nsfw: true,
            cacheDuration: Some(1800),
            ytdlpCommand: Some("yt-dlp --impersonate chrome-120".to_string())
        }
    }

    /// Explicit `artist:` / `category:` / `tag:` style prefixes (the server has
    /// already stripped a leading `#`).
    fn parse_prefixed(query: &str) -> Option<Target> {
        let (kind, value) = query.trim().split_once(':')?;
        let slug = slug_dashed(value);
        if slug.is_empty() {
            return None;
        }
        match kind.trim().to_ascii_lowercase().as_str() {
            "artist" | "artists" | "model" | "models" | "author" | "creator" | "uploader" => {
                Some(Target::Artist(slug))
            }
            "cat" | "category" | "categories" | "franchise" | "series" | "game" => {
                Some(Target::Category(slug))
            }
            "tag" | "tags" | "character" | "char" => Some(Target::Tag(slug)),
            _ => None,
        }
    }

    /// Titles of the tags offered by `/search_ajax.php?tag=`.
    fn parse_tag_suggestions(html: &str) -> Vec<String> {
        let document = Html::parse_fragment(html);
        let Ok(selector) = Selector::parse("input[data-title]") else {
            return vec![];
        };
        document
            .select(&selector)
            .filter_map(|input| input.value().attr("data-title"))
            .map(|title| title.trim().to_string())
            .filter(|title| !title.is_empty())
            .collect()
    }

    /// The suggested tag whose name (ignoring a trailing "(franchise)") equals
    /// the query, e.g. "samus aran" -> "samus aran (metroid)".
    fn best_tag_title(titles: &[String], query: &str) -> Option<String> {
        let wanted = slug_dashed(query);
        if wanted.is_empty() {
            return None;
        }
        let mut exact = titles.iter().filter(|title| {
            let base = title.split('(').next().unwrap_or(title);
            slug_dashed(base) == wanted || slug_dashed(title) == wanted
        });
        let first = exact.next()?;
        // Several franchises share a character name: ambiguous, leave it to search.
        exact.next().is_none().then(|| first.clone())
    }

    /// A free-form query that names an artist, category or tag goes to that
    /// archive (probed on the site; unknown names 404), else keyword search.
    /// The second value is false when a probe failed (rate limit, outage) and
    /// the answer must not be remembered.
    async fn resolve_keyword(&self, query: &str, options: &ServerOptions) -> (Target, bool) {
        let slug = slug_dashed(query);
        if slug.is_empty() {
            return (Target::Search(query.trim().to_string()), true);
        }
        // Artist slugs are inconsistent on the site: "general-butch" but "biggreen".
        let mut candidates = vec![Target::Artist(slug.clone())];
        if slug.contains('-') {
            candidates.push(Target::Artist(slug.replace('-', "")));
        }
        candidates.push(Target::Category(slug.clone()));
        candidates.push(Target::Tag(slug));
        let mut requester = requester_or_default(options, "rule34video", "resolve_keyword");
        let referer = format!("{}/", self.url);
        let mut conclusive = true;
        for candidate in &candidates {
            let Some(path) = candidate.archive_path() else {
                continue;
            };
            let url = format!("{}/{path}/", self.url);
            let headers = vec![("Referer".to_string(), referer.clone())];
            match requester.get_probe(&url, headers).await {
                Ok(Some(body)) => {
                    let items = self.get_video_items_from_html(body).len();
                    if items >= MIN_PROBED_ARCHIVE_ITEMS {
                        return (candidate.clone(), true);
                    }
                }
                Ok(None) => {}
                Err(_) => conclusive = false,
            }
        }

        // Characters are tagged "name (franchise)": ask the site's own tag search.
        let suggest_url = format!(
            "{}/search_ajax.php?tag={}",
            self.url,
            utf8_percent_encode(query.trim(), NON_ALPHANUMERIC)
        );
        let headers = vec![
            ("Referer".to_string(), referer),
            ("X-Requested-With".to_string(), "XMLHttpRequest".to_string()),
        ];
        match requester.get_probe(&suggest_url, headers).await {
            Ok(Some(body)) => {
                let titles = Self::parse_tag_suggestions(&body);
                if let Some(title) = Self::best_tag_title(&titles, query) {
                    return (Target::Tag(slug_dashed(&title)), conclusive);
                }
            }
            Ok(None) => {}
            Err(_) => conclusive = false,
        }
        (Target::Search(query.trim().to_string()), conclusive)
    }

    async fn resolve_target(&self, query: Option<&str>, options: &ServerOptions) -> Target {
        let Some(query) = query.map(str::trim).filter(|q| !q.is_empty()) else {
            return Target::Latest;
        };
        if let Some(target) = Self::parse_prefixed(query) {
            return target;
        }
        if let Some(target) = self.remembered_target(query) {
            return target;
        }
        let (target, conclusive) = self.resolve_keyword(query, options).await;
        if conclusive {
            self.remember_target(query, &target);
        }
        target
    }

    async fn archive(
        &self,
        cache: VideoCache,
        target: &Target,
        page: u8,
        sort: &str,
        options: ServerOptions,
    ) -> Result<Vec<VideoItem>> {
        let Some(path) = target.archive_path() else {
            return Ok(vec![]);
        };
        let sort_val = match sort {
            "post_date" | "video_viewed" | "rating" | "duration" | "pseudo_random" => sort,
            _ => "post_date",
        };
        let index = format!("rule34video:{path}:{page}:{sort_val}");
        if sort_val != "pseudo_random" {
            if let Some((time, items)) = cache.get(&index) {
                if time.elapsed().unwrap_or_default().as_secs() < 300 {
                    return Ok(items.clone());
                }
            }
        }

        let mut requester = options.requester.clone().ok_or("Requester missing")?;
        let url = format!(
            "{}/{path}/?mode=async&function=get_block&block_id=custom_list_videos_common_videos&sort_by={sort_val}&from={page}",
            self.url
        );
        let headers = vec![("Referer".to_string(), format!("{}/{path}/", self.url))];
        let stale = || cache.get(&index).map(|(_, items)| items).unwrap_or_default();
        let text = match requester.get_probe(&url, headers).await {
            Ok(Some(text)) => text,
            // A 404 is an unknown archive (or a page past the end).
            Ok(None) => return Ok(vec![]),
            Err(e) => {
                eprintln!("rule34video archive fetch failed for {url}: {e}");
                return Ok(stale());
            }
        };
        let video_items = self.get_video_items_from_html(text);
        let video_items = Self::proxy_items(video_items, &options);
        if video_items.is_empty() {
            return Ok(stale());
        }
        cache.insert(index, video_items.clone());
        Ok(video_items)
    }

    /// `/search/{q}/` takes dashes for spaces. A raw `/` splits the path (404),
    /// `%20` is refused (403) and `&` cuts the query short, so keep only words.
    fn search_path_segment(query: &str) -> String {
        slug_dashed(query)
            .split('-')
            .map(|word| utf8_percent_encode(word, NON_ALPHANUMERIC).to_string())
            .collect::<Vec<_>>()
            .join("-")
    }

    /// Helper to safely extract a string between two delimiters
    fn extract_between<'a>(content: &'a str, start_pat: &str, end_pat: &str) -> Option<&'a str> {
        let start_idx = content.find(start_pat)? + start_pat.len();
        let sub = &content[start_idx..];
        let end_idx = sub.find(end_pat)?;
        Some(&sub[..end_idx])
    }

    async fn get(
        &self,
        cache: VideoCache,
        page: u8,
        sort: &str,
        options: ServerOptions,
    ) -> Result<Vec<VideoItem>> {
        let timestamp_millis = SystemTime::now()
            .duration_since(UNIX_EPOCH)
            .map(|d| d.as_millis())
            .unwrap_or(0);

        let expected_sorts = vec![
            "post_date",
            "video_viewed",
            "rating",
            "duration",
            "pseudo_random",
        ];
        let sort_val = if expected_sorts.contains(&sort) {
            sort
        } else {
            "post_date"
        };

        let index = format!("rule34video:{}:{}", page, sort_val);

        if sort_val != "pseudo_random" {
            if let Some((time, items)) = cache.get(&index) {
                if time.elapsed().unwrap_or_default().as_secs() < 300 {
                    return Ok(items.clone());
                }
            }
        }

        let mut requester = options.requester.clone().ok_or("Requester missing")?;
        let url = format!(
            "{}/?mode=async&function=get_block&block_id=custom_list_videos_most_recent_videos&tag_ids=&sort_by={}&from={}&_={}",
            self.url, sort_val, page, timestamp_millis
        );

        let text = requester.get(&url, None).await.unwrap_or_else(|e| {
            eprintln!("Error fetching rule34video URL {}: {}", url, e);
            let _ = send_discord_error_report(
                e.to_string(),
                None,
                Some(&url),
                None,
                file!(),
                line!(),
                module_path!(),
            );
            "".to_string()
        });
        let video_items = self.get_video_items_from_html(text);
        let video_items = Self::proxy_items(video_items, &options);

        if !video_items.is_empty() {
            cache.insert(index, video_items.clone());
            Ok(video_items)
        } else {
            // Return empty or old items if available
            Ok(cache
                .get(&index)
                .map(|(_, items)| items)
                .unwrap_or_default())
        }
    }

    async fn query(
        &self,
        cache: VideoCache,
        page: u8,
        query: &str,
        sort: &str,
        options: ServerOptions,
    ) -> Result<Vec<VideoItem>> {
        let timestamp_millis = SystemTime::now()
            .duration_since(UNIX_EPOCH)
            .map(|d| d.as_millis())
            .unwrap_or(0);

        let expected_sorts = vec![
            "post_date",
            "video_viewed",
            "rating",
            "duration",
            "pseudo_random",
        ];
        let sort_val = if expected_sorts.contains(&sort) {
            sort
        } else {
            "post_date"
        };

        let index = format!("rule34video:{}:{}:{}", page, sort_val, query);

        if let Some((time, items)) = cache.get(&index) {
            if time.elapsed().unwrap_or_default().as_secs() < 300 {
                return Ok(items.clone());
            }
        }

        let mut requester = options.requester.clone().ok_or("Requester missing")?;
        let url = format!(
            "{}/search/{}/?mode=async&function=get_block&block_id=custom_list_videos_videos_list_search&tag_ids=&sort_by={}&from_videos={}&from_albums={}&_={}",
            self.url,
            Self::search_path_segment(query),
            sort_val,
            page,
            page,
            timestamp_millis
        );

        let text = requester.get(&url, None).await.unwrap_or_else(|e| {
            eprintln!("Error fetching rule34video URL {}: {}", url, e);
            let _ = send_discord_error_report(
                e.to_string(),
                None,
                Some(&url),
                None,
                file!(),
                line!(),
                module_path!(),
            );
            "".to_string()
        });
        let video_items = self.get_video_items_from_html(text);
        let video_items = Self::proxy_items(video_items, &options);

        if !video_items.is_empty() {
            cache.insert(index, video_items.clone());
            Ok(video_items)
        } else {
            Ok(cache
                .get(&index)
                .map(|(_, items)| items)
                .unwrap_or_default())
        }
    }

    /// Playback resolves the video page on demand through `/proxy/rule34video/`,
    /// instead of fetching every listed page up front (which ran into 429s).
    fn proxy_items(mut items: Vec<VideoItem>, options: &ServerOptions) -> Vec<VideoItem> {
        if !USE_MEDIA_PROXY {
            return items;
        }
        for item in &mut items {
            if let Some(path) = item.url.split("/video/").nth(1).filter(|p| !p.is_empty()) {
                item.url = crate::providers::build_proxy_url(options, "rule34video", path);
            }
        }
        items
    }

    fn get_video_items_from_html(&self, html: String) -> Vec<VideoItem> {
        if html.is_empty() {
            return vec![];
        }

        // Isolate the video listing section. A result that fits on one page has
        // no pagination block, so the listing then runs to the end.
        let Some(start) = html.find("id=\"custom_list_videos") else {
            return vec![];
        };
        let video_listing = &html[start..];
        let video_listing = video_listing
            .find("<div class=\"pagination\"")
            .map_or(video_listing, |end| &video_listing[..end]);

        let mut items = Vec::new();
        // Skip the first split result as it's the preamble
        let raw_videos = video_listing
            .split("<div class=\"item thumb video_")
            .skip(1);

        for video_segment in raw_videos {
            if video_segment.contains("title=\"Advertisement\"") {
                continue;
            }

            // Title extraction
            let title_raw =
                Self::extract_between(video_segment, "<div class=\"thumb_title\">", "<")
                    .unwrap_or("Unknown");
            let title = decode(title_raw.as_bytes())
                .to_string()
                .unwrap_or_else(|_| title_raw.to_string());

            // ID extraction
            let id = Self::extract_between(video_segment, "https://rule34video.com/video/", "/")
                .unwrap_or("0")
                .to_string();

            // Duration extraction
            let raw_duration =
                Self::extract_between(video_segment, "<div class=\"time\">", "<").unwrap_or("0:00");
            let duration = parse_time_to_seconds(raw_duration).unwrap_or(0) as u32;

            // Views extraction: `<div class="views video-views-count ..."
            // title="Views: 13K">`. The sibling `views` div is the comment
            // count, so match the title rather than the bare class.
            let views = Self::extract_between(video_segment, "title=\"Views: ", "\"")
                .and_then(|v| parse_abbreviated_number(v.trim()))
                .or_else(|| {
                    Self::extract_between(video_segment, "<div class=\"views\">", "</div>")
                        .map(|s| s.rsplit("</svg>").next().unwrap_or(s))
                        .and_then(|v| parse_abbreviated_number(v.trim()))
                })
                .unwrap_or(0);

            // Rating extraction: `72% (47)` inside the rating div.
            let rating = Self::extract_between(video_segment, "custom-thumbs-up", "</div>")
                .and_then(|s| s.rsplit("</svg>").next())
                .and_then(|s| s.trim().split('%').next())
                .and_then(|s| s.trim().parse::<f32>().ok());

            // Thumbnail extraction: the site dropped `data-original`. Lazy
            // cards are `<img class="thumb rd-lz" src="data:image/gif..."
            // data-rd-src="...">`; eager ones carry the real `src`.
            let thumb = Self::extract_between(video_segment, "<img class=\"thumb", ">")
                .and_then(|tag| {
                    Self::extract_between(tag, "data-rd-src=\"", "\"")
                        .or_else(|| {
                            Self::extract_between(tag, " src=\"", "\"")
                                .filter(|src| src.starts_with("http"))
                        })
                        .or_else(|| Self::extract_between(tag, "data-rd-jpg=\"", "\""))
                })
                .or_else(|| Self::extract_between(video_segment, "data-original=\"", "\""))
                .unwrap_or("")
                .to_string();

            // URL extraction
            let url =
                Self::extract_between(video_segment, "<a class=\"th js-open-popup\" href=\"", "\"")
                    .unwrap_or("")
                    .to_string();

            let mut item =
                VideoItem::new(id, title, url, "Rule34video".to_string(), thumb, duration)
                    .views(views);
            if let Some(rating) = rating {
                item = item.rating(rating);
            }
            items.push(item);
        }
        items
    }
}

#[async_trait]
impl Provider for Rule34videoProvider {
    async fn get_videos(
        &self,
        cache: VideoCache,
        _pool: DbPool,
        sort: String,
        query: Option<String>,
        page: String,
        _per_page: String,
        options: ServerOptions,
    ) -> Vec<VideoItem> {
        let page_num = page.parse::<u8>().unwrap_or(1);

        let target = self.resolve_target(query.as_deref(), &options).await;
        let result = match &target {
            Target::Latest => self.get(cache, page_num, &sort, options).await,
            Target::Search(q) => self.query(cache, page_num, q, &sort, options).await,
            archive => self.archive(cache, archive, page_num, &sort, options).await,
        };

        match result {
            Ok(v) => v,
            Err(e) => {
                eprintln!("Error fetching videos: {}", e);
                vec![]
            }
        }
    }

    fn get_channel(&self, clientversion: ClientVersion) -> Option<Channel> {
        Some(self.build_channel(clientversion))
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn parses_card_thumb_from_img_src_and_skips_ads() {
        let html = r#"<div id="custom_list_videos_x"><div class="item thumb video_1   " data-video-card-id="42">
<a class="th js-open-popup" href="https://rule34video.com/video/42/some-title/"  title="Some Title">
<div class="img wrap_image"><img class="thumb" src="https://rule34video.com/contents/videos_screenshots/0/42/336x189/3.jpg" data-rd-jpg="x" alt="a">
<div class="time">1:28</div></div><div class="thumb_title">Some Title</div>
<div class="rating"><svg class="custom-svg custom-thumbs-up"></svg> 72% (47) </div>
<div class="views video-comments-count" title="Comments: 0"><svg></svg> 0 </div>
<div class="views video-views-count" title="Views: 6.9K"><svg></svg> 6.9K </div></a></div>
<div class="item thumb video_3"><a class="th js-open-popup" href="https://rule34video.com/video/43/lazy/" title="Lazy">
<div class="img wrap_image"><img class="thumb rd-lz" src="data:image/gif;base64,R0lG" data-rd-src="https://rule34video.com/contents/videos_screenshots/0/43/336x189/3.jpg" alt="b">
<div class="time">0:30</div></div><div class="thumb_title">Lazy</div></a></div>
<div class="item thumb video_2"><a class="th" href="https://ads" title="Advertisement"></a></div>
<div class="pagination" id="p">"#;
        let items = Rule34videoProvider::new().get_video_items_from_html(html.to_string());
        assert_eq!(items.len(), 2);
        assert_eq!(items[0].id, "42");
        assert_eq!(items[0].views, Some(6900));
        assert_eq!(items[0].rating, Some(72.0));
        assert_eq!(
            items[1].thumb,
            "https://rule34video.com/contents/videos_screenshots/0/43/336x189/3.jpg"
        );
        assert_eq!(
            items[0].thumb,
            "https://rule34video.com/contents/videos_screenshots/0/42/336x189/3.jpg"
        );
        assert_eq!(items[0].duration, 88);
    }

    #[test]
    fn parses_prefixed_queries() {
        assert_eq!(
            Rule34videoProvider::parse_prefixed("artist:General Butch"),
            Some(Target::Artist("general-butch".into()))
        );
        assert_eq!(
            Rule34videoProvider::parse_prefixed("category:Super Smash Bros"),
            Some(Target::Category("super-smash-bros".into()))
        );
        assert_eq!(
            Rule34videoProvider::parse_prefixed("tag:black widow (marvel)"),
            Some(Target::Tag("black-widow-marvel".into()))
        );
        assert_eq!(Rule34videoProvider::parse_prefixed("samus aran"), None);
    }

    #[test]
    fn picks_the_unambiguous_character_tag() {
        let titles = vec![
            "samus aran (metroid)".to_string(),
            "samus aran's mother".to_string(),
        ];
        assert_eq!(
            Rule34videoProvider::best_tag_title(&titles, "samus aran").as_deref(),
            Some("samus aran (metroid)")
        );
        let ambiguous = vec!["peach (mario)".to_string(), "peach (pokemon)".to_string()];
        assert_eq!(Rule34videoProvider::best_tag_title(&ambiguous, "peach"), None);
    }

    #[test]
    fn parses_tag_suggestions() {
        let suggest = r#"<div class="item checkbox-container"><input id="tag_143" type="checkbox" value="143" data-title="samus aran (metroid)"/></div>"#;
        assert_eq!(
            Rule34videoProvider::parse_tag_suggestions(suggest),
            vec!["samus aran (metroid)".to_string()]
        );
    }

    #[test]
    fn parses_a_single_page_listing_without_pagination() {
        let html = r#"<div id="custom_list_videos_common_videos_items">
<div class="item thumb video_7"><a class="th js-open-popup" href="https://rule34video.com/video/7/elf/">
<img class="thumb" src="https://rule34video.com/t/7.jpg"><div class="time">0:30</div>
<div class="thumb_title">Elf</div></a></div></div></div>"#;
        let items = Rule34videoProvider::new().get_video_items_from_html(html.to_string());
        assert_eq!(items.len(), 1);
        assert_eq!(items[0].id, "7");
    }

    #[test]
    fn search_segment_uses_dashes_and_drops_path_breaking_punctuation() {
        assert_eq!(Rule34videoProvider::search_path_segment("elf  girl"), "elf-girl");
        assert_eq!(Rule34videoProvider::search_path_segment("2b/9s"), "2b-9s");
        assert_eq!(Rule34videoProvider::search_path_segment("Tifa & Aerith"), "tifa-aerith");
        assert_eq!(Rule34videoProvider::search_path_segment("Pokémon"), "pok%C3%A9mon");
    }

    #[test]
    fn remembers_resolved_targets_by_slug() {
        let provider = Rule34videoProvider::new();
        provider.remember_target("Samus Aran", &Target::Tag("samus-aran-metroid".into()));
        assert_eq!(
            provider.remembered_target("samus  aran"),
            Some(Target::Tag("samus-aran-metroid".into()))
        );
        assert_eq!(provider.remembered_target("samus"), None);
    }
}