| 1 | //! Which commit last changed each line of a file. |
| 2 | //! |
| 3 | //! History is walked newest first, as `git blame` does: a line still present, |
| 4 | //! unchanged, in one of a commit's parents is handed to that parent; a line in |
| 5 | //! none of them was written by the commit. Following every parent, not just |
| 6 | //! the first, matters here: catch-up merges bring the default branch into a |
| 7 | //! pull request, and their lines belong to whoever wrote them on that branch. |
| 8 | //! |
| 9 | //! Reading is what costs: each commit's file is found by reading the trees |
| 10 | //! on the way to it, and each read is a round trip to the store or its cache. |
| 11 | //! So the walk reads ahead: the trees of the next [`READ_AHEAD`] commits, |
| 12 | //! level by level and each level at once, and then, at once, the texts of the |
| 13 | //! versions it will compare. The walk stops when every line has its commit, |
| 14 | //! after [`MAX_COMMITS`] commits, before more than the caller's reads of the |
| 15 | //! store, or once the caller's time is up; stopped early, a line goes to the |
| 16 | //! oldest commit the walk reached it in, and the answer is marked partial. |
| 17 | //! |
| 18 | //! A blame of a commit and path never changes, so `lib.rs` keeps the answer |
| 19 | //! by repository, commit and path ([`cache_url`]). |
| 20 | |
| 21 | use std::collections::{HashMap, HashSet}; |
| 22 | use std::rc::Rc; |
| 23 | |
| 24 | use g1t_contracts::repos::{Blame, BlameRange, Commit, EntryKind, TreeEntry}; |
| 25 | use similar::{ChangeTag, TextDiff}; |
| 26 | use worker::Result; |
| 27 | |
| 28 | use crate::store::GitRepo; |
| 29 | |
| 30 | /// How far back the history is searched. Lines older than this are given to |
| 31 | /// the oldest commit reached, and the answer is marked partial. |
| 32 | pub const MAX_COMMITS: u32 = 400; |
| 33 | /// Files larger than this are not blamed. |
| 34 | const MAX_FILE_BYTES: usize = 512 * 1024; |
| 35 | /// Commits whose trees and texts are read together, ahead of the walk. |
| 36 | const READ_AHEAD: usize = 32; |
| 37 | /// Reads of the store one blame makes at most. Each costs up to three |
| 38 | /// subrequests (a Cache API look, the store, a Cache API put), so this keeps |
| 39 | /// a call well inside the 10,000 a Worker invocation may make. |
| 40 | pub const MAX_READS: u32 = 2_500; |
| 41 | |
| 42 | /// Where a blame is kept: by repository, the commit it was read at, and a |
| 43 | /// hash of the path. `v1`: a change to how lines are credited moves it. |
| 44 | pub fn cache_url(repo_id: &str, head: &str, path: &str) -> String { |
| 45 | format!("https://blame.g1t.internal/v1/{repo_id}/{head}/{}", g1t_secrets::sha256_hex(path)) |
| 46 | } |
| 47 | |
| 48 | /// How long a blame is kept. One that ran to its end (the first commit, or |
| 49 | /// [`MAX_COMMITS`]) is the same every time, so for good; one cut short by |
| 50 | /// time or reads could do better on a quieter store, so briefly. |
| 51 | pub fn cache_control(blamed: &Blamed) -> &'static str { |
| 52 | if blamed.cut_short { "max-age=600" } else { "max-age=31536000, immutable" } |
| 53 | } |
| 54 | |
| 55 | /// A blame, and whether time or reads cut it short. |
| 56 | #[derive(Debug)] |
| 57 | pub struct Blamed { |
| 58 | pub blame: Blame, |
| 59 | pub cut_short: bool, |
| 60 | } |
| 61 | |
| 62 | /// A version of the file: its lines, each ended by a newline, as the diff |
| 63 | /// compares them, and how many there are. |
| 64 | struct Text { |
| 65 | joined: String, |
| 66 | lines: usize, |
| 67 | } |
| 68 | |
| 69 | impl Text { |
| 70 | fn of(text: &str) -> Text { |
| 71 | let mut joined = String::with_capacity(text.len() + 1); |
| 72 | let mut lines = 0; |
| 73 | // Every line ends in a newline, so a last line matches the same line elsewhere. |
| 74 | for line in text.lines() { |
| 75 | joined.push_str(line); |
| 76 | joined.push('\n'); |
| 77 | lines += 1; |
| 78 | } |
| 79 | Text { joined, lines } |
| 80 | } |
| 81 | } |
| 82 | |
| 83 | /// Reads files out of commits, remembering trees and texts already read: |
| 84 | /// most commits share most of their trees. |
| 85 | struct Reader<'a, R: GitRepo> { |
| 86 | repo: &'a R, |
| 87 | trees: HashMap<String, Option<Vec<TreeEntry>>>, |
| 88 | texts: HashMap<String, Option<Rc<Text>>>, |
| 89 | /// Reads of the store so far, trees, texts and history. |
| 90 | reads: u32, |
| 91 | } |
| 92 | |
| 93 | impl<'a, R: GitRepo> Reader<'a, R> { |
| 94 | /// Reads the trees not read yet, all at once. |
| 95 | async fn read_trees(&mut self, hashes: Vec<String>) -> Result<()> { |
| 96 | let wanted: Vec<String> = hashes |
| 97 | .into_iter() |
| 98 | .filter(|hash| !self.trees.contains_key(hash)) |
| 99 | .collect::<HashSet<_>>() |
| 100 | .into_iter() |
| 101 | .collect(); |
| 102 | self.reads += wanted.len() as u32; |
| 103 | let found = futures_util::future::join_all(wanted.iter().map(|hash| self.repo.read_tree(hash))).await; |
| 104 | for (hash, tree) in wanted.into_iter().zip(found) { |
| 105 | self.trees.insert(hash, tree?); |
| 106 | } |
| 107 | Ok(()) |
| 108 | } |
| 109 | |
| 110 | /// Reads, level by level and each level at once, the trees on the way |
| 111 | /// to `path` in each of `roots`. |
| 112 | async fn read_paths(&mut self, roots: Vec<String>, path: &str) -> Result<()> { |
| 113 | let parts: Vec<&str> = path.split('/').filter(|part| !part.is_empty()).collect(); |
| 114 | let mut level = roots; |
| 115 | for (index, part) in parts.iter().enumerate() { |
| 116 | self.read_trees(level.clone()).await?; |
| 117 | if index + 1 == parts.len() { |
| 118 | break; |
| 119 | } |
| 120 | level = level |
| 121 | .iter() |
| 122 | .filter_map(|hash| { |
| 123 | let entries = self.trees.get(hash)?.as_ref()?; |
| 124 | entries.iter().find(|entry| entry.name == *part && entry.kind == EntryKind::Tree).map(|entry| entry.hash.clone()) |
| 125 | }) |
| 126 | .collect(); |
| 127 | } |
| 128 | Ok(()) |
| 129 | } |
| 130 | |
| 131 | /// Reads the texts not read yet, all at once. |
| 132 | async fn read_texts(&mut self, blobs: Vec<String>) -> Result<()> { |
| 133 | let wanted: Vec<String> = |
| 134 | blobs.into_iter().filter(|blob| !self.texts.contains_key(blob)).collect::<HashSet<_>>().into_iter().collect(); |
| 135 | self.reads += wanted.len() as u32; |
| 136 | let found = futures_util::future::join_all(wanted.iter().map(|blob| self.repo.read_blob(blob))).await; |
| 137 | for (blob, bytes) in wanted.into_iter().zip(found) { |
| 138 | let text = bytes? |
| 139 | .filter(|bytes| bytes.len() <= MAX_FILE_BYTES && !bytes.contains(&0)) |
| 140 | .and_then(|bytes| String::from_utf8(bytes).ok()) |
| 141 | .map(|text| Rc::new(Text::of(&text))); |
| 142 | self.texts.insert(blob, text); |
| 143 | } |
| 144 | Ok(()) |
| 145 | } |
| 146 | |
| 147 | /// The blob hash of `path` in the tree `root`, if it is a file there. |
| 148 | async fn blob_at(&mut self, root: &str, path: &str) -> Result<Option<String>> { |
| 149 | let mut tree = root.to_owned(); |
| 150 | let parts: Vec<&str> = path.split('/').filter(|part| !part.is_empty()).collect(); |
| 151 | for (index, part) in parts.iter().enumerate() { |
| 152 | if !self.trees.contains_key(&tree) { |
| 153 | self.read_trees(vec![tree.clone()]).await?; |
| 154 | } |
| 155 | let Some(entry) = self.trees[&tree].as_ref().and_then(|entries| entries.iter().find(|entry| entry.name == *part)) else { |
| 156 | return Ok(None); |
| 157 | }; |
| 158 | let last = index == parts.len() - 1; |
| 159 | match (last, entry.kind == EntryKind::Tree) { |
| 160 | (true, false) => return Ok(Some(entry.hash.clone())), |
| 161 | (false, true) => tree = entry.hash.clone(), |
| 162 | _ => return Ok(None), |
| 163 | } |
| 164 | } |
| 165 | Ok(None) |
| 166 | } |
| 167 | |
| 168 | /// A version's text, or `None` if it is binary or too large. |
| 169 | async fn text(&mut self, blob: &str) -> Result<Option<Rc<Text>>> { |
| 170 | if !self.texts.contains_key(blob) { |
| 171 | self.read_texts(vec![blob.to_owned()]).await?; |
| 172 | } |
| 173 | Ok(self.texts[blob].clone()) |
| 174 | } |
| 175 | |
| 176 | /// Reads ahead for `commits`: the trees to `path` in each, then the |
| 177 | /// texts of each version that differs from the next commit's (its |
| 178 | /// parent on the walk), which are the ones the walk compares. |
| 179 | async fn read_ahead(&mut self, commits: &[Commit], path: &str) -> Result<()> { |
| 180 | self.read_paths(commits.iter().map(|commit| commit.tree_hash.clone()).collect(), path).await?; |
| 181 | let mut blobs = Vec::with_capacity(commits.len()); |
| 182 | for commit in commits { |
| 183 | blobs.push(self.blob_at(&commit.tree_hash, path).await?); |
| 184 | } |
| 185 | let mut wanted = Vec::new(); |
| 186 | for pair in blobs.windows(2) { |
| 187 | if let [Some(child), Some(parent)] = pair |
| 188 | && child != parent |
| 189 | { |
| 190 | wanted.push(child.clone()); |
| 191 | wanted.push(parent.clone()); |
| 192 | } |
| 193 | } |
| 194 | self.read_texts(wanted).await |
| 195 | } |
| 196 | } |
| 197 | |
| 198 | /// For each line of `new`, the index of the same, unchanged line in `old`. |
| 199 | fn carried(old: &Text, new: &Text) -> Vec<Option<usize>> { |
| 200 | let diff = TextDiff::from_lines(&old.joined, &new.joined); |
| 201 | let mut map = vec![None; new.lines]; |
| 202 | for change in diff.iter_all_changes() { |
| 203 | if change.tag() == ChangeTag::Equal |
| 204 | && let (Some(o), Some(n)) = (change.old_index(), change.new_index()) |
| 205 | && let Some(slot) = map.get_mut(n) |
| 206 | { |
| 207 | *slot = Some(o); |
| 208 | } |
| 209 | } |
| 210 | map |
| 211 | } |
| 212 | |
| 213 | /// Who last changed each line of `path` as of `head`. `None` if the file is |
| 214 | /// missing or not text. The walk stops before more than `max_reads` reads of |
| 215 | /// the store, or once `out_of_time` says so (asked between read-aheads, |
| 216 | /// after the first). |
| 217 | pub async fn blame<R: GitRepo>( |
| 218 | repo: &R, |
| 219 | head: &str, |
| 220 | path: &str, |
| 221 | out_of_time: &dyn Fn() -> bool, |
| 222 | max_reads: u32, |
| 223 | ) -> Result<Option<Blamed>> { |
| 224 | let history = repo.log(head, MAX_COMMITS).await?; |
| 225 | let Some(first) = history.first() else { |
| 226 | return Ok(None); |
| 227 | }; |
| 228 | let mut reader = Reader { |
| 229 | repo, |
| 230 | trees: HashMap::new(), |
| 231 | texts: HashMap::new(), |
| 232 | reads: 1, |
| 233 | }; |
| 234 | // The first read-ahead also finds the file at the head. |
| 235 | let first_window = &history[..history.len().min(READ_AHEAD + 1)]; |
| 236 | reader.read_ahead(first_window, path).await?; |
| 237 | let mut read_ahead_to = first_window.len(); |
| 238 | let Some(blob) = reader.blob_at(&first.tree_hash, path).await? else { |
| 239 | return Ok(None); |
| 240 | }; |
| 241 | let Some(text) = reader.text(&blob).await? else { |
| 242 | return Ok(None); |
| 243 | }; |
| 244 | let total = text.lines; |
| 245 | let by_hash: HashMap<&str, &Commit> = history.iter().map(|commit| (commit.hash.as_str(), commit)).collect(); |
| 246 | let segments = path.split('/').filter(|part| !part.is_empty()).count(); |
| 247 | // The most one read-ahead reads: every tree on the way, two texts each. |
| 248 | let window_reads = (READ_AHEAD * (segments + 2)) as u32; |
| 249 | |
| 250 | // For each commit still to visit: (line in its version, line in the head's). |
| 251 | let mut pending: HashMap<String, Vec<(usize, usize)>> = HashMap::new(); |
| 252 | pending.insert(first.hash.clone(), (0..total).map(|line| (line, line)).collect()); |
| 253 | let mut owner: Vec<Option<String>> = vec![None; total]; |
| 254 | let mut partial = false; |
| 255 | let mut cut_short = false; |
| 256 | |
| 257 | // The log is newest first, so a commit is reached after its children. |
| 258 | for (index, commit) in history.iter().enumerate() { |
| 259 | if pending.is_empty() { |
| 260 | break; |
| 261 | } |
| 262 | if index + 1 >= read_ahead_to && read_ahead_to < history.len() { |
| 263 | if out_of_time() || reader.reads + window_reads > max_reads { |
| 264 | cut_short = true; |
| 265 | break; |
| 266 | } |
| 267 | let window = &history[index..history.len().min(index + READ_AHEAD + 1)]; |
| 268 | reader.read_ahead(window, path).await?; |
| 269 | read_ahead_to = index + window.len(); |
| 270 | } |
| 271 | let Some(mut lines_here) = pending.remove(&commit.hash) else { |
| 272 | continue; |
| 273 | }; |
| 274 | lines_here.sort_unstable(); |
| 275 | lines_here.dedup_by_key(|(_, final_line)| *final_line); |
| 276 | let Some(blob) = reader.blob_at(&commit.tree_hash, path).await? else { |
| 277 | continue; |
| 278 | }; |
| 279 | // Read only when a parent's version differs. |
| 280 | let mut text: Option<Rc<Text>> = None; |
| 281 | let mut unexplained = lines_here; |
| 282 | for parent_hash in &commit.parents { |
| 283 | if unexplained.is_empty() { |
| 284 | break; |
| 285 | } |
| 286 | let Some(parent) = by_hash.get(parent_hash.as_str()) else { |
| 287 | // Beyond the history read: these lines are at least this old. |
| 288 | partial = true; |
| 289 | continue; |
| 290 | }; |
| 291 | let Some(parent_blob) = reader.blob_at(&parent.tree_hash, path).await? else { |
| 292 | continue; |
| 293 | }; |
| 294 | let handed: Vec<(usize, usize)> = if parent_blob == blob { |
| 295 | std::mem::take(&mut unexplained) |
| 296 | } else { |
| 297 | if text.is_none() { |
| 298 | text = reader.text(&blob).await?; |
| 299 | } |
| 300 | let (Some(here), Some(parent_text)) = (&text, reader.text(&parent_blob).await?) else { |
| 301 | // A version that is not text: its lines are taken as |
| 302 | // this commit's. |
| 303 | continue; |
| 304 | }; |
| 305 | let map = carried(&parent_text, here); |
| 306 | let (moved, kept): (Vec<_>, Vec<_>) = unexplained |
| 307 | .into_iter() |
| 308 | .partition(|(here, _)| map.get(*here).copied().flatten().is_some()); |
| 309 | unexplained = kept; |
| 310 | moved |
| 311 | .into_iter() |
| 312 | .map(|(here, final_line)| (map[here].unwrap_or(here), final_line)) |
| 313 | .collect() |
| 314 | }; |
| 315 | if !handed.is_empty() { |
| 316 | pending.entry(parent_hash.clone()).or_default().extend(handed); |
| 317 | } |
| 318 | } |
| 319 | for (_, final_line) in unexplained { |
| 320 | owner[final_line] = Some(commit.hash.clone()); |
| 321 | } |
| 322 | } |
| 323 | // Lines the walk did not finish with: each goes to the oldest commit it |
| 324 | // was followed to. |
| 325 | if !pending.is_empty() { |
| 326 | partial = true; |
| 327 | for (hash, lines) in pending { |
| 328 | for (_, final_line) in lines { |
| 329 | if owner[final_line].is_none() { |
| 330 | owner[final_line] = Some(hash.clone()); |
| 331 | } |
| 332 | } |
| 333 | } |
| 334 | } |
| 335 | |
| 336 | let mut ranges: Vec<BlameRange> = Vec::new(); |
| 337 | for (index, hash) in owner.into_iter().enumerate() { |
| 338 | let hash = hash.unwrap_or_else(|| first.hash.clone()); |
| 339 | let line = index as u32 + 1; |
| 340 | match ranges.last_mut() { |
| 341 | Some(range) if range.commit == hash => range.end = line, |
| 342 | _ => ranges.push(BlameRange { start: line, end: line, commit: hash }), |
| 343 | } |
| 344 | } |
| 345 | let mut commits: Vec<Commit> = Vec::new(); |
| 346 | for range in &ranges { |
| 347 | if !commits.iter().any(|commit| commit.hash == range.commit) |
| 348 | && let Some(commit) = by_hash.get(range.commit.as_str()) |
| 349 | { |
| 350 | commits.push((*commit).clone()); |
| 351 | } |
| 352 | } |
| 353 | Ok(Some(Blamed { |
| 354 | blame: Blame { |
| 355 | head: first.hash.clone(), |
| 356 | ranges, |
| 357 | commits, |
| 358 | partial, |
| 359 | }, |
| 360 | cut_short, |
| 361 | })) |
| 362 | } |
| 363 | |
| 364 | #[cfg(test)] |
| 365 | mod tests { |
| 366 | use std::cell::{Cell, RefCell}; |
| 367 | use std::future::Future; |
| 368 | use std::pin::pin; |
| 369 | use std::task::{Context, Poll, Waker}; |
| 370 | |
| 371 | use g1t_contracts::repos::{Branch, GitAccess, Signature}; |
| 372 | |
| 373 | use super::*; |
| 374 | use crate::store::Scope; |
| 375 | |
| 376 | fn run<F: Future>(future: F) -> F::Output { |
| 377 | match pin!(future).as_mut().poll(&mut Context::from_waker(Waker::noop())) { |
| 378 | Poll::Ready(output) => output, |
| 379 | Poll::Pending => panic!("the fake store never waits"), |
| 380 | } |
| 381 | } |
| 382 | |
| 383 | fn text(text: &str) -> Text { |
| 384 | Text::of(text) |
| 385 | } |
| 386 | |
| 387 | #[test] |
| 388 | fn unchanged_lines_are_carried_to_the_parent() { |
| 389 | let map = carried(&text("a\nb\nc"), &text("a\nx\nb\nc")); |
| 390 | assert_eq!(map, vec![Some(0), None, Some(1), Some(2)]); |
| 391 | } |
| 392 | |
| 393 | #[test] |
| 394 | fn a_changed_line_is_not_carried() { |
| 395 | let map = carried(&text("a\nb"), &text("a\nB")); |
| 396 | assert_eq!(map, vec![Some(0), None]); |
| 397 | } |
| 398 | |
| 399 | #[test] |
| 400 | fn a_last_line_without_a_newline_matches_one_with() { |
| 401 | let map = carried(&text("a\nb\n"), &text("a\nb")); |
| 402 | assert_eq!(map, vec![Some(0), Some(1)]); |
| 403 | } |
| 404 | |
| 405 | /// A repository whose history is `src/f.txt` growing a line per commit. |
| 406 | #[derive(Default)] |
| 407 | struct Fake { |
| 408 | trees: HashMap<String, Vec<TreeEntry>>, |
| 409 | blobs: HashMap<String, String>, |
| 410 | history: Vec<Commit>, |
| 411 | trees_read: RefCell<Vec<String>>, |
| 412 | blobs_read: RefCell<Vec<String>>, |
| 413 | } |
| 414 | |
| 415 | impl GitRepo for Fake { |
| 416 | async fn access(&self, _scope: Scope) -> Result<GitAccess> { |
| 417 | unimplemented!() |
| 418 | } |
| 419 | async fn branches(&self) -> Result<Vec<Branch>> { |
| 420 | Ok(Vec::new()) |
| 421 | } |
| 422 | async fn log(&self, git_ref: &str, limit: u32) -> Result<Vec<Commit>> { |
| 423 | let start = if git_ref == "main" { Some(0) } else { self.history.iter().position(|commit| commit.hash == git_ref) }; |
| 424 | Ok(start.map(|start| self.history.iter().skip(start).take(limit as usize).cloned().collect()).unwrap_or_default()) |
| 425 | } |
| 426 | async fn parents(&self, _commit_hash: &str) -> Result<Option<Vec<String>>> { |
| 427 | Ok(None) |
| 428 | } |
| 429 | async fn read_tree(&self, tree_hash: &str) -> Result<Option<Vec<TreeEntry>>> { |
| 430 | self.trees_read.borrow_mut().push(tree_hash.to_owned()); |
| 431 | Ok(self.trees.get(tree_hash).cloned()) |
| 432 | } |
| 433 | async fn read_blob(&self, blob_hash: &str) -> Result<Option<Vec<u8>>> { |
| 434 | self.blobs_read.borrow_mut().push(blob_hash.to_owned()); |
| 435 | Ok(self.blobs.get(blob_hash).map(|text| text.as_bytes().to_vec())) |
| 436 | } |
| 437 | async fn read_file(&self, _git_ref: &str, _path: &str) -> Result<Option<Vec<u8>>> { |
| 438 | Ok(None) |
| 439 | } |
| 440 | async fn fork(&self, _target_key: &str, _default_branch_only: bool) -> Result<()> { |
| 441 | Ok(()) |
| 442 | } |
| 443 | } |
| 444 | |
| 445 | fn commit(hash: &str, tree: &str, parent: Option<&str>) -> Commit { |
| 446 | Commit { |
| 447 | hash: hash.into(), |
| 448 | tree_hash: tree.into(), |
| 449 | message: format!("commit {hash}"), |
| 450 | author: Signature { name: "a".into(), email: "a@example.com".into() }, |
| 451 | parents: parent.map(|p| vec![p.to_owned()]).unwrap_or_default(), |
| 452 | authored_at: String::new(), |
| 453 | } |
| 454 | } |
| 455 | |
| 456 | /// `commits` commits, newest first: commit n appends line n to |
| 457 | /// `src/f.txt`. Every tenth commit only touches `README.md` beside it, |
| 458 | /// so `src` stays the same tree there. The repository root changes in |
| 459 | /// every commit. |
| 460 | fn growing(commits: usize) -> Fake { |
| 461 | let mut fake = Fake::default(); |
| 462 | let mut lines: Vec<String> = Vec::new(); |
| 463 | for n in 0..commits { |
| 464 | let changes_file = n == 0 || n % 10 != 0; |
| 465 | if changes_file { |
| 466 | lines.push(format!("line {n}")); |
| 467 | } |
| 468 | let blob = format!("b{}", lines.len()); |
| 469 | fake.blobs.insert(blob.clone(), lines.join("\n")); |
| 470 | let src = format!("s{}", lines.len()); |
| 471 | fake.trees.insert(src.clone(), vec![TreeEntry { name: "f.txt".into(), hash: blob, kind: EntryKind::Blob }]); |
| 472 | let root = format!("r{n}"); |
| 473 | fake.trees.insert( |
| 474 | root.clone(), |
| 475 | vec![ |
| 476 | TreeEntry { name: "README.md".into(), hash: format!("readme{n}"), kind: EntryKind::Blob }, |
| 477 | TreeEntry { name: "src".into(), hash: src, kind: EntryKind::Tree }, |
| 478 | ], |
| 479 | ); |
| 480 | let parent = (n > 0).then(|| format!("c{}", n - 1)); |
| 481 | fake.history.insert(0, commit(&format!("c{n}"), &root, parent.as_deref())); |
| 482 | } |
| 483 | fake |
| 484 | } |
| 485 | |
| 486 | fn owners(blame: &Blame) -> Vec<(u32, u32, String)> { |
| 487 | blame.ranges.iter().map(|range| (range.start, range.end, range.commit.clone())).collect() |
| 488 | } |
| 489 | |
| 490 | #[test] |
| 491 | fn each_line_goes_to_the_commit_that_wrote_it() { |
| 492 | let fake = growing(5); |
| 493 | let blamed = run(blame(&fake, "main", "src/f.txt", &|| false, MAX_READS)).unwrap().unwrap(); |
| 494 | assert!(!blamed.cut_short && !blamed.blame.partial); |
| 495 | assert_eq!(blamed.blame.head, "c4"); |
| 496 | assert_eq!( |
| 497 | owners(&blamed.blame), |
| 498 | (0..5).map(|n| (n + 1, n + 1, format!("c{n}"))).collect::<Vec<_>>() |
| 499 | ); |
| 500 | assert_eq!(blamed.blame.commits.len(), 5); |
| 501 | } |
| 502 | |
| 503 | #[test] |
| 504 | fn a_missing_or_binary_file_has_no_blame() { |
| 505 | let mut fake = growing(3); |
| 506 | assert!(run(blame(&fake, "main", "src/nope.txt", &|| false, MAX_READS)).unwrap().is_none()); |
| 507 | assert!(run(blame(&fake, "unknown", "src/f.txt", &|| false, MAX_READS)).unwrap().is_none()); |
| 508 | fake.blobs.insert("b3".into(), "a\0b".into()); |
| 509 | assert!(run(blame(&fake, "main", "src/f.txt", &|| false, MAX_READS)).unwrap().is_none()); |
| 510 | } |
| 511 | |
| 512 | #[test] |
| 513 | fn each_tree_and_text_is_read_once() { |
| 514 | let fake = growing(60); |
| 515 | let blamed = run(blame(&fake, "main", "src/f.txt", &|| false, MAX_READS)).unwrap().unwrap(); |
| 516 | assert!(!blamed.cut_short); |
| 517 | let trees = fake.trees_read.borrow(); |
| 518 | assert_eq!(trees.len(), trees.iter().collect::<HashSet<_>>().len(), "no tree is read twice"); |
| 519 | let blobs = fake.blobs_read.borrow(); |
| 520 | assert_eq!(blobs.len(), blobs.iter().collect::<HashSet<_>>().len(), "no text is read twice"); |
| 521 | // Each root, and each distinct `src`, once. |
| 522 | assert_eq!(trees.len(), 60 + 55); |
| 523 | } |
| 524 | |
| 525 | #[test] |
| 526 | fn the_walk_stops_once_every_line_has_its_commit() { |
| 527 | // The newest 30 commits rewrite the whole file, so nothing older is needed. |
| 528 | let mut fake = growing(200); |
| 529 | fake.blobs.insert("b181".into(), "only line".into()); |
| 530 | let blamed = run(blame(&fake, "main", "src/f.txt", &|| false, MAX_READS)).unwrap().unwrap(); |
| 531 | assert_eq!(owners(&blamed.blame), vec![(1, 1, "c199".to_owned())]); |
| 532 | assert!(fake.trees_read.borrow().len() < 2 * (READ_AHEAD + 1) * 2, "read only the first read-ahead or two"); |
| 533 | } |
| 534 | |
| 535 | #[test] |
| 536 | fn out_of_time_stops_the_walk_and_credits_the_oldest_commit_reached() { |
| 537 | let fake = growing(100); |
| 538 | let asked = Cell::new(0); |
| 539 | let out_of_time = || { |
| 540 | asked.set(asked.get() + 1); |
| 541 | true |
| 542 | }; |
| 543 | let blamed = run(blame(&fake, "main", "src/f.txt", &out_of_time, MAX_READS)).unwrap().unwrap(); |
| 544 | assert!(blamed.cut_short && blamed.blame.partial); |
| 545 | assert_eq!(asked.get(), 1, "asked once, after the first read-ahead"); |
| 546 | // The newest lines still have their own commits; the rest stop at |
| 547 | // the last commit of the first read-ahead. |
| 548 | let ranges = owners(&blamed.blame); |
| 549 | assert_eq!(ranges.last().unwrap().2, "c99"); |
| 550 | let reached = format!("c{}", 99 - READ_AHEAD); |
| 551 | assert_eq!(ranges[0].2, reached); |
| 552 | assert_eq!(cache_control(&blamed), "max-age=600"); |
| 553 | } |
| 554 | |
| 555 | #[test] |
| 556 | fn reads_are_bounded() { |
| 557 | let fake = growing(300); |
| 558 | let max = 150; |
| 559 | let blamed = run(blame(&fake, "main", "src/f.txt", &|| false, max)).unwrap().unwrap(); |
| 560 | assert!(blamed.cut_short && blamed.blame.partial); |
| 561 | let reads = fake.trees_read.borrow().len() + fake.blobs_read.borrow().len() + 1; |
| 562 | assert!(reads <= max as usize, "{reads} reads, at most {max}"); |
| 563 | } |
| 564 | |
| 565 | #[test] |
| 566 | fn a_history_longer_than_is_read_is_partial_but_kept_for_good() { |
| 567 | let fake = growing(MAX_COMMITS as usize + 20); |
| 568 | let blamed = run(blame(&fake, "main", "src/f.txt", &|| false, 100_000)).unwrap().unwrap(); |
| 569 | assert!(blamed.blame.partial && !blamed.cut_short); |
| 570 | assert_eq!(cache_control(&blamed), "max-age=31536000, immutable"); |
| 571 | } |
| 572 | |
| 573 | #[test] |
| 574 | fn a_blame_is_kept_by_repository_commit_and_path() { |
| 575 | let url = cache_url("repo_1", "abc", "src/f.txt"); |
| 576 | assert!(url.starts_with("https://blame.g1t.internal/v1/repo_1/abc/")); |
| 577 | assert_ne!(url, cache_url("repo_1", "abc", "src/g.txt")); |
| 578 | assert_ne!(url, cache_url("repo_1", "abd", "src/f.txt")); |
| 579 | assert_ne!(url, cache_url("repo_2", "abc", "src/f.txt")); |
| 580 | // A path never reaches the URL as it is. |
| 581 | assert!(!cache_url("r", "h", "a/../b?x#y").contains("..")); |
| 582 | } |
| 583 | } |