//! `comments <number> [--limit N | --tail N]` — list comments on an
//! issue or PR. Replaces the curl fallback; `--tail`
//! handles the paging-for-long-threads
//! awkwardness).
//!
//! - `--limit N` (default 50, Forgejo's cap) returns the first N
//!   comments — same shape this verb has always had.
//! - `--tail N` returns the *last* N comments in chronological
//!   order. Reads the issue's `comments` count first to compute
//!   which page contains the tail, then fetches only `ceil(N/50) +
//!   1` pages. No upstream cap — the work is bounded by `N`, not
//!   by the thread's length, so it stays cheap even on threads with
//!   thousands of comments. Use this for "what was the conclusion
//!   on this long thread?" without scrolling through the whole
//!   history.
//!
//! For PRs, review *bodies* (the summary text submitted with an
//! approve / request-changes / comment review) are merged in too:
//! they live in the `pulls/<n>/reviews` object, NOT the
//! issues/comments thread, so plain comment listings used to miss
//! them entirely and reviewers/authors silently lost feedback —
//! the gap this fix closes. They're always included regardless of
//! `--limit`/`--tail`
//! (reviews are few + high-signal) and tagged `[review: STATE]` so
//! they're distinguishable from issue-thread comments.
//!
//! Use the global `--json` flag for JSON output.

use anyhow::Result;
use clap::Args as ClapArgs;
use forgejo_api::structs::IssueGetCommentsQuery;
use serde_json::{Value, json};

use crate::client::{Client, index};
use crate::notify;
use crate::verbs::{print_json, rfc3339};

/// Forgejo's per-page comment cap. The API caps `limit` at 50 even
/// if a higher value is requested; pin it explicitly so the math
/// downstream doesn't depend on a hidden default.
const PAGE_SIZE: usize = 50;

#[derive(ClapArgs)]
pub struct Args {
    /// Issue or PR number.
    pub(crate) number: u64,
    /// Number of comments from the start of the thread (max 50).
    /// Mutually exclusive with `--tail`.
    #[arg(long, default_value_t = 50, conflicts_with = "tail")]
    limit: u64,
    /// Return the last `N` comments (chronological). Mutually exclusive
    /// with `--limit`.
    #[arg(long)]
    tail: Option<usize>,
}

pub fn run(client: &Client, args: Args) -> Result<()> {
    let repo = client.repo();
    let thread = match args.tail {
        Some(n) => fetch_tail(client, args.number, n)?,
        None => fetch_head(client, args.number, args.limit)?,
    };
    // Merge in PR review bodies (empty for issues — degrades to a
    // no-op) so review feedback isn't silently dropped.
    let comments = merge_chronological(thread, fetch_review_bodies(client, args.number));
    // Reading the thread clears its unread notification so the
    // read-before-comment guard (in `comment`) lets a reply through.
    notify::mark_read_best_effort(client, repo, args.number);
    if client.json_mode() {
        let trimmed: Vec<Value> = comments
            .iter()
            .map(|c| {
                json!({
                    "id": c.get("id"),
                    "user": c.get("user").and_then(|u| u.get("login")),
                    "created_at": c.get("created_at"),
                    "updated_at": c.get("updated_at"),
                    "body": c.get("body"),
                    "url": c.get("html_url"),
                    "kind": c.get("kind").and_then(Value::as_str).unwrap_or("comment"),
                    "state": c.get("state"),
                })
            })
            .collect();
        print_json(&Value::Array(trimmed))
    } else {
        for c in &comments {
            let user = c
                .get("user")
                .and_then(|u| u.get("login"))
                .and_then(Value::as_str)
                .unwrap_or("?");
            let ts = c.get("created_at").and_then(Value::as_str).unwrap_or("?");
            let body = c.get("body").and_then(Value::as_str).unwrap_or("");
            if c.get("kind").and_then(Value::as_str) == Some("review") {
                let state = c.get("state").and_then(Value::as_str).unwrap_or("?");
                println!("**{user} @ {ts}** [review: {state}]: {body}");
            } else {
                println!("**{user} @ {ts}**: {body}");
            }
            println!();
        }
        Ok(())
    }
}

/// Serialize a typed comment page back to the JSON `Value` shape the
/// merge + render pipeline works on (the structs serialize to the API
/// wire shape, so downstream field access is unchanged).
fn to_values<T: serde::Serialize>(items: Vec<T>) -> Result<Vec<Value>> {
    items
        .into_iter()
        .map(|c| serde_json::to_value(&c).map_err(Into::into))
        .collect()
}

/// Fetch a PR's review *bodies* and normalise them to the comment
/// shape so they merge alongside issue-thread comments.
///
/// Review summaries live in the `pulls/<n>/reviews` object, not the
/// issues/comments thread, so the plain comment listing misses them
/// — the review-body gap this fixes. Best-effort: returns empty on
/// any error — notably when
/// `number` is an issue (no reviews endpoint) — so callers degrade
/// gracefully. Skips PENDING reviews (not yet visible to others) and
/// empty-body reviews (a bare approval adds nothing to the thread).
/// `created_at` is synthesised from the review's `submitted_at` so
/// the chronological merge sorts uniformly; `kind:"review"` + the
/// review `state` tag the entry for display.
fn fetch_review_bodies(client: &Client, number: u64) -> Vec<Value> {
    let Ok((owner, name)) = client.owner_repo() else {
        return Vec::new();
    };
    let Ok(idx) = index(number) else {
        return Vec::new();
    };
    let reviews = client
        .api()
        .repo_list_pull_reviews(owner, name, idx)
        .send()
        .map(|(_, reviews)| reviews)
        .unwrap_or_default();
    reviews
        .into_iter()
        .filter_map(|r| {
            let state = r.state.as_deref().unwrap_or("").to_owned();
            if state == "PENDING" {
                return None;
            }
            if r.body.as_deref().unwrap_or("").trim().is_empty() {
                return None;
            }
            let submitted = rfc3339(r.submitted_at);
            Some(json!({
                "id": r.id,
                "user": r.user,
                "created_at": submitted,
                "updated_at": submitted,
                "body": r.body,
                "html_url": r.html_url,
                "kind": "review",
                "state": state,
            }))
        })
        .collect()
}

/// Merge issue-thread comments with review bodies and sort the
/// combined list chronologically by `created_at`. ISO-8601 timestamps
/// sort lexicographically in time order, so a plain string compare is
/// correct; the sort is stable, so same-timestamp entries keep fetch
/// order.
fn merge_chronological(mut items: Vec<Value>, reviews: Vec<Value>) -> Vec<Value> {
    items.extend(reviews);
    items.sort_by(|a, b| {
        let ka = a.get("created_at").and_then(Value::as_str).unwrap_or("");
        let kb = b.get("created_at").and_then(Value::as_str).unwrap_or("");
        ka.cmp(kb)
    });
    items
}

/// Fetch the first page's worth of comments (existing behaviour).
fn fetch_head(client: &Client, number: u64, limit: u64) -> Result<Vec<Value>> {
    let (owner, name) = client.owner_repo()?;
    let (_, comments) = client
        .api()
        .issue_get_comments(
            owner,
            name,
            index(number)?,
            IssueGetCommentsQuery::default(),
        )
        .page_size(u32::try_from(limit).unwrap_or(u32::MAX))
        .send()?;
    to_values(comments)
}

/// Fetch the last `n` comments on an issue/PR in chronological order.
///
/// Forgejo orders `/issues/<n>/comments` oldest-first and has no
/// `direction=desc` knob, so naive "page everything and slice" pages
/// from the WRONG end on long threads — the first 1000 comments
/// instead of the last `n`. Fix: read the issue's `comments` count
/// first to know how many exist, then start paginating from the
/// page that contains item `total - n`. Work is bounded by
/// `ceil(n/50) + 1` page fetches, regardless of thread length.
fn fetch_tail(client: &Client, number: u64, n: usize) -> Result<Vec<Value>> {
    if n == 0 {
        return Ok(Vec::new());
    }
    let (owner, name) = client.owner_repo()?;
    let idx = index(number)?;
    let issue = client.api().issue_get_issue(owner, name, idx).send()?;
    let total = issue
        .comments
        .and_then(|c| usize::try_from(c).ok())
        .unwrap_or(0);
    if total == 0 {
        return Ok(Vec::new());
    }
    // Cap `n` at the actual total so the math below stays in range
    // when the caller asks for more comments than exist.
    let n = n.min(total);
    let page_size = PAGE_SIZE;
    // 0-based index of the first comment we want; integer-divide to
    // get the 1-based page that contains it.
    let start_idx = total - n;
    let start_page = (start_idx / page_size) + 1;
    let last_page = (total - 1) / page_size + 1;
    let mut merged: Vec<Value> = Vec::with_capacity(n + page_size);
    for page in start_page..=last_page {
        let (_, arr) = client
            .api()
            .issue_get_comments(owner, name, idx, IssueGetCommentsQuery::default())
            .page(u32::try_from(page).unwrap_or(u32::MAX))
            .page_size(u32::try_from(PAGE_SIZE).unwrap_or(u32::MAX))
            .send()?;
        if arr.is_empty() {
            // Page came back empty — either we miscounted (comments
            // deleted between the issue GET and now) or upstream's
            // playing tricks. Stop rather than spin.
            break;
        }
        merged.extend(to_values(arr)?);
    }
    // The first fetched page contains items from `start_page` × 50
    // back; we overshoot by `start_idx % 50` items. Slice the tail
    // to exactly `n` (or fewer if the count shrank under us).
    let overshoot = merged.len().saturating_sub(n);
    Ok(merged.into_iter().skip(overshoot).collect())
}

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

    /// Pure helper mirroring the page-arithmetic in `fetch_tail`:
    /// given a total comment count + requested tail size, return
    /// the (`start_page`, `last_page`) pair the network loop would
    /// walk. Lets us pin the pagination plan — the part that's
    /// easy to off-by-one — without touching the network.
    fn tail_plan(total: usize, n: usize) -> (usize, usize) {
        let n = n.min(total);
        let page_size = PAGE_SIZE;
        let start_idx = total - n;
        let start_page = (start_idx / page_size) + 1;
        let last_page = (total - 1) / page_size + 1;
        (start_page, last_page)
    }

    #[test]
    fn tail_plan_small_thread() {
        // 5 total, tail 2 → page 1 covers everything; trim happens
        // via the merged.len() - n overshoot calculation, not pages.
        assert_eq!(tail_plan(5, 2), (1, 1));
    }

    #[test]
    fn tail_plan_exact_page_boundary() {
        // 50 total, tail 3 → all on page 1 (items 1..50).
        assert_eq!(tail_plan(50, 3), (1, 1));
    }

    #[test]
    fn tail_plan_crosses_page_boundary() {
        // 51 total, tail 3 → start_idx=48 lives on page 1, item 51
        // lives on page 2; fetch both.
        assert_eq!(tail_plan(51, 3), (1, 2));
    }

    #[test]
    fn tail_plan_large_thread_bounded_pages() {
        // 5000 total, tail 3 → start_idx=4997 lives on page 100,
        // last_page=100. ONE page fetch on a 5000-comment thread —
        // the whole point of swapping to count-then-page (vs the
        // old "page everything, then slice the wrong end").
        assert_eq!(tail_plan(5000, 3), (100, 100));
    }

    #[test]
    fn tail_plan_large_thread_spans_two_pages() {
        // 5000 total, tail 60 → start_idx=4940 on page 99, item 5000
        // on page 100. Two fetches even for n > PAGE_SIZE.
        assert_eq!(tail_plan(5000, 60), (99, 100));
    }

    #[test]
    fn tail_plan_n_exceeds_total() {
        // 5 total, tail 100 → cap n at total; same plan as the
        // small-thread case above.
        assert_eq!(tail_plan(5, 100), (1, 1));
    }

    #[test]
    fn merge_interleaves_reviews_by_timestamp() {
        // A review submitted between two comments must land between
        // them, not appended at the end — that's the whole fix.
        let comments = vec![
            json!({"created_at": "2026-06-29T01:00:00Z", "body": "c1"}),
            json!({"created_at": "2026-06-29T01:20:00Z", "body": "c2"}),
        ];
        let reviews =
            vec![json!({"created_at": "2026-06-29T01:10:00Z", "body": "r1", "kind": "review"})];
        let merged = merge_chronological(comments, reviews);
        let bodies: Vec<&str> = merged
            .iter()
            .map(|v| v.get("body").and_then(Value::as_str).unwrap())
            .collect();
        assert_eq!(bodies, vec!["c1", "r1", "c2"]);
    }

    #[test]
    fn merge_with_no_reviews_is_identity() {
        // Issues have no reviews → fetch_review_bodies returns empty →
        // the merge must leave the comment thread untouched.
        let comments = vec![
            json!({"created_at": "2026-06-29T01:00:00Z", "body": "c1"}),
            json!({"created_at": "2026-06-29T01:20:00Z", "body": "c2"}),
        ];
        let merged = merge_chronological(comments, vec![]);
        let bodies: Vec<&str> = merged
            .iter()
            .map(|v| v.get("body").and_then(Value::as_str).unwrap())
            .collect();
        assert_eq!(bodies, vec!["c1", "c2"]);
    }
}