sitemapb

//// Sitemap XML!
//// <https://www.sitemaps.org/protocol.html>

import gleam/float
import gleam/list
import gleam/option.{type Option}
import gleam/string_tree
import gleam/time/calendar
import gleam/time/timestamp.{type Timestamp}
import xmb.{type Xml, text, x}

pub type Url {
  Url(
    /// URL of the page. This URL must begin with the protocol (such as http)
    /// and end with a trailing slash, if your web server requires it. This
    /// value must be less than 2,048 characters.
    ///
    location: String,
    /// The date of last modification of the page.
    ///
    /// Note that the date must be set to the date the linked page was last
    /// modified, not when the sitemap is generated.
    ///
    /// Note also that this tag is separate from the If-Modified-Since (304)
    /// header the server can return, and search engines may use the
    /// information from both sources differently.
    ///
    last_modified: option.Option(Timestamp),
    /// How frequently the page is likely to change. This value provides
    /// general information to search engines and may not correlate exactly to
    /// how often they crawl the page.
    ///
    /// Please note that the value of this tag is considered a hint and not a
    /// command. Even though search engine crawlers may consider this information
    /// when making decisions, they may crawl pages marked "hourly" less
    /// frequently than that, and they may crawl pages marked "yearly" more
    /// frequently than that. Crawlers may periodically crawl pages marked
    /// "never" so that they can handle unexpected changes to those pages.
    ///
    change_frequency: option.Option(ChangeFrequency),
    /// The priority of this URL relative to other URLs on your site. Valid
    /// values range from 0.0 to 1.0. This value does not affect how your pages
    /// are compared to pages on other sites—it only lets the search engines
    /// know which pages you deem most important for the crawlers.
    ///
    /// Values outside of the range of 0.0 to 1.0 will be replaced with 0.0 or
    /// 1.0.
    ///
    /// If not specified then the priority of a page is considered to be 0.5.
    ///
    /// Please note that the priority you assign to a page is not likely to
    /// influence the position of your URLs in a search engine's result pages.
    /// Search engines may use this information when selecting between URLs on
    /// the same site, so you can use this tag to increase the likelihood that
    /// your most important pages are present in a search index.
    ///
    /// Also, please note that assigning a high priority to all of the URLs on
    /// your site is not likely to help you. Since the priority is relative, it
    /// is only used to select between URLs on your site.
    ///
    priority: option.Option(Float),
  )
}

/// How frequently a page is likely to change. This value provides general
/// information to search engines and may not correlate exactly to how often
/// they crawl the page.
///
/// The value "always" should be used to describe documents that change each
/// time they are accessed. The value "never" should be used to describe
/// archived URLs.
///
pub type ChangeFrequency {
  Always
  Hourly
  Daily
  Weekly
  Monthly
  Yearly
  Never
}

const namespace = #("xmlns", "http://www.sitemaps.org/schemas/sitemap/0.9")

/// Render an XML sitemap.
///
/// This function lets you specify all the properties of each page.
///
pub fn render(site: List(Url)) -> string_tree.StringTree {
  let url = fn(url) {
    let Url(location:, last_modified:, change_frequency:, priority:) = url
    x("url", [], [
      x("loc", [], [text(location)]),
      maybe("lastmod", last_modified, render_timestamp),
      maybe("changefreq", change_frequency, render_change_frequency),
      maybe("priority", priority, render_priority),
    ])
  }

  x("urlset", [namespace], list.map(site, url))
  |> list.wrap
  |> xmb.render
}

/// Render an XML sitemap.
///
/// This function takes only URLs. Use the `render` function if you want to
/// specify the other properties for eaech page.
///
pub fn render_basic(site: List(String)) -> string_tree.StringTree {
  let url = fn(url) { x("url", [], [x("loc", [], [text(url)])]) }

  x("urlset", [namespace], list.map(site, url))
  |> list.wrap
  |> xmb.render
}

fn render_priority(priority: Float) -> Xml {
  priority
  |> float.clamp(min: 0.0, max: 1.0)
  |> float.to_string
  |> text
}

fn render_timestamp(timestamp: Timestamp) -> Xml {
  text(timestamp.to_rfc3339(timestamp, calendar.utc_offset))
}

fn render_change_frequency(frequency: ChangeFrequency) -> Xml {
  text(case frequency {
    Always -> "always"
    Hourly -> "hourly"
    Daily -> "daily"
    Weekly -> "weekly"
    Monthly -> "monthly"
    Yearly -> "yearly"
    Never -> "never"
  })
}

fn maybe(tag: String, item: Option(a), render: fn(a) -> Xml) -> Xml {
  case item {
    option.Some(value) -> x(tag, [], [render(value)])
    option.None -> xmb.nothing()
  }
}