Pick any line to see why it is the way it is: the commit, the pull request and issue it came from, and what the agent was thinking.
| Merge branch 'worktree-agent-a6a121745e81f639f' | 1 | //! What the RubyGems registry needs that does not touch the network: gem |
| 2 | //! names and versions, the registry's paths, the `Gem::Specification` read | |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 3 | //! from a `.gem` (a tar holding `metadata.gz`), the compact index |
| 4 | //! Bundler reads (`versions`, `info/<gem>` and `names`), and the full | |
| 5 | //! index `gem install --source` reads: `specs.4.8.gz` and its latest and | |
| 6 | //! pre-release kin, and each version's `quick/Marshal.4.8` specification. | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 7 | //! |
| 8 | //! A version is keyed by its number and platform as the compact index | |
| 9 | //! writes it (`1.0.0`, `1.0.0-x86_64-linux`), and keeps what its index | |
| 10 | //! line needs as its metadata, made once when it is pushed. | |
| 11 | ||
| 12 | use serde_json::{Value, json}; | |
| 13 | ||
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 14 | use std::cmp::Ordering; |
| 15 | ||
| Merge branch 'worktree-agent-a6a121745e81f639f' | 16 | use crate::archive; |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 17 | use crate::marshal::{self, Value as Ruby}; |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 18 | use crate::yaml; |
| 19 | ||
| 20 | /// The longest gem name taken. | |
| 21 | pub const MAX_NAME: usize = 128; | |
| 22 | /// The largest `metadata.gz`, unpacked, read from a gem. | |
| 23 | const MAX_METADATA_BYTES: usize = 4 * 1024 * 1024; | |
| 24 | ||
| 25 | /// A gem's name: letters, digits, `.`, `-` and `_`, with a letter in it. | |
| 26 | pub fn valid_name(name: &str) -> bool { | |
| 27 | !name.is_empty() | |
| 28 | && name.len() <= MAX_NAME | |
| 29 | && name.bytes().all(|b| b.is_ascii_alphanumeric() || matches!(b, b'.' | b'-' | b'_')) | |
| 30 | && name.bytes().any(|b| b.is_ascii_alphabetic()) | |
| 31 | && name.as_bytes()[0].is_ascii_alphanumeric() | |
| 32 | } | |
| 33 | ||
| 34 | /// A version as `Gem::Version` takes it: numbers and words joined by dots, | |
| 35 | /// starting with a number (`1.0.0`, `2.0.0.rc1`, `1.0.0-beta.1`). | |
| 36 | pub fn valid_version(version: &str) -> bool { | |
| 37 | let (core, suffix) = version.split_once('-').map_or((version, None), |(c, s)| (c, Some(s))); | |
| 38 | let mut parts = core.split('.'); | |
| 39 | let first_ok = parts.next().is_some_and(|p| !p.is_empty() && p.bytes().all(|b| b.is_ascii_digit())); | |
| 40 | first_ok | |
| 41 | && version.len() <= 128 | |
| 42 | && parts.all(|p| !p.is_empty() && p.bytes().all(|b| b.is_ascii_alphanumeric())) | |
| 43 | && suffix.is_none_or(|s| s.split('.').all(|p| !p.is_empty() && p.bytes().all(|b| b.is_ascii_alphanumeric() || b == b'-'))) | |
| 44 | } | |
| 45 | ||
| 46 | /// A version with a letter in it is a pre-release, as RubyGems decides. | |
| 47 | pub fn is_prerelease(version: &str) -> bool { | |
| 48 | version.bytes().any(|b| b.is_ascii_alphabetic()) | |
| 49 | } | |
| 50 | ||
| 51 | /// The version as the index keys it: `1.0.0`, or `1.0.0-java` for a gem | |
| 52 | /// built for a platform. | |
| 53 | pub fn key(version: &str, platform: &str) -> String { | |
| 54 | if platform.is_empty() || platform == "ruby" { version.to_owned() } else { format!("{version}-{platform}") } | |
| 55 | } | |
| 56 | ||
| 57 | /// One of the registry's endpoints, under `/-/rubygems/<workspace>/`. | |
| 58 | #[derive(Clone, Debug, PartialEq, Eq)] | |
| 59 | pub enum GemRoute { | |
| 60 | /// `versions`: every gem and its versions, for Bundler. | |
| 61 | Versions, | |
| 62 | /// `info/<gem>`: a gem's versions, dependencies and checksums. | |
| 63 | Info { name: String }, | |
| 64 | /// `names`: every gem's name. | |
| 65 | Names, | |
| 66 | /// `gems/<name>-<version>[-<platform>].gem`; the name and version are | |
| 67 | /// told apart by the handler, as names may hold `-`. | |
| 68 | Gem { stem: String }, | |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 69 | /// `specs.4.8.gz`, `latest_specs.4.8.gz` or `prerelease_specs.4.8.gz`. |
| 70 | Specs(Specs), | |
| 71 | /// `quick/Marshal.4.8/<name>-<version>[-<platform>].gemspec.rz`: one | |
| 72 | /// version's specification. | |
| 73 | QuickSpec { stem: String }, | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 74 | /// `api/v1/gems`: `gem push`. |
| 75 | Push, | |
| 76 | /// `api/v1/gems/yank`: `gem yank`. | |
| 77 | Yank, | |
| 78 | } | |
| 79 | ||
| 80 | pub fn route(path: &str) -> Option<(String, GemRoute)> { | |
| 81 | let rest = path.strip_prefix("/-/rubygems/")?; | |
| 82 | let (workspace, rest) = rest.split_once('/')?; | |
| 83 | let workspace = workspace.to_ascii_lowercase(); | |
| 84 | if workspace.is_empty() { | |
| 85 | return None; | |
| 86 | } | |
| 87 | let route = match rest.trim_end_matches('/') { | |
| 88 | "versions" => GemRoute::Versions, | |
| 89 | "names" => GemRoute::Names, | |
| 90 | "api/v1/gems" => GemRoute::Push, | |
| 91 | "api/v1/gems/yank" => GemRoute::Yank, | |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 92 | "specs.4.8.gz" => GemRoute::Specs(Specs::Released), |
| 93 | "latest_specs.4.8.gz" => GemRoute::Specs(Specs::Latest), | |
| 94 | "prerelease_specs.4.8.gz" => GemRoute::Specs(Specs::Prerelease), | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 95 | other => { |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 96 | if let Some(file) = other.strip_prefix("quick/Marshal.4.8/") { |
| 97 | let stem = file.strip_suffix(".gemspec.rz")?; | |
| 98 | if stem.contains('/') || candidates(stem).is_empty() { | |
| 99 | return None; | |
| 100 | } | |
| 101 | return Some((workspace, GemRoute::QuickSpec { stem: stem.to_owned() })); | |
| 102 | } | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 103 | if let Some(name) = other.strip_prefix("info/") { |
| 104 | if !valid_name(name) { | |
| 105 | return None; | |
| 106 | } | |
| 107 | GemRoute::Info { name: name.to_owned() } | |
| 108 | } else { | |
| 109 | let file = other.strip_prefix("gems/")?; | |
| 110 | let stem = file.strip_suffix(".gem")?; | |
| 111 | if stem.contains('/') || candidates(stem).is_empty() { | |
| 112 | return None; | |
| 113 | } | |
| 114 | GemRoute::Gem { stem: stem.to_owned() } | |
| 115 | } | |
| 116 | } | |
| 117 | }; | |
| 118 | Some((workspace, route)) | |
| 119 | } | |
| 120 | ||
| 121 | /// The ways a file's stem splits into a name and a version key: at each | |
| 122 | /// `-` followed by a digit, longest name last (`a-b-1.0` is `a-b` `1.0`). | |
| 123 | pub fn candidates(stem: &str) -> Vec<(String, String)> { | |
| 124 | stem.char_indices() | |
| 125 | .filter(|&(i, c)| c == '-' && stem[i + 1..].starts_with(|n: char| n.is_ascii_digit())) | |
| 126 | .map(|(i, _)| (stem[..i].to_owned(), stem[i + 1..].to_owned())) | |
| 127 | .filter(|(name, _)| valid_name(name)) | |
| 128 | .collect() | |
| 129 | } | |
| 130 | ||
| 131 | /// What is read from a gem's specification. | |
| 132 | #[derive(Clone, Debug, Default, PartialEq, Eq)] | |
| 133 | pub struct Gemspec { | |
| 134 | pub name: String, | |
| 135 | pub version: String, | |
| 136 | pub platform: String, | |
| 137 | pub summary: Option<String>, | |
| 138 | pub description: Option<String>, | |
| 139 | pub homepage: Option<String>, | |
| 140 | pub source_code_uri: Option<String>, | |
| 141 | pub licenses: Vec<String>, | |
| 142 | pub authors: Vec<String>, | |
| 143 | /// Runtime dependencies: name and requirement (`>= 2.0&< 4`). | |
| 144 | pub dependencies: Vec<(String, String)>, | |
| 145 | pub ruby: Option<String>, | |
| 146 | pub rubygems: Option<String>, | |
| 147 | } | |
| 148 | ||
| 149 | /// A `Gem::Requirement` as the compact index writes it: `>= 2.0&< 4`. | |
| 150 | pub fn requirement(value: &Value) -> String { | |
| 151 | value["requirements"] | |
| 152 | .as_array() | |
| 153 | .map(|list| { | |
| 154 | list.iter() | |
| 155 | .filter_map(|pair| { | |
| 156 | let op = pair.get(0)?.as_str()?; | |
| 157 | let version = pair.get(1).map(|v| v.get("version").unwrap_or(v)).and_then(Value::as_str)?; | |
| 158 | Some(format!("{op} {version}")) | |
| 159 | }) | |
| 160 | .collect::<Vec<_>>() | |
| 161 | .join("&") | |
| 162 | }) | |
| 163 | .unwrap_or_default() | |
| 164 | } | |
| 165 | ||
| 166 | /// A requirement that says nothing (`>= 0`), as left out of the index. | |
| 167 | fn anything(requirement: &str) -> bool { | |
| 168 | requirement.is_empty() || requirement == ">= 0" | |
| 169 | } | |
| 170 | ||
| 171 | fn text(value: &Value) -> Option<String> { | |
| 172 | value.as_str().map(str::trim).filter(|s| !s.is_empty()).map(str::to_owned) | |
| 173 | } | |
| 174 | ||
| 175 | fn texts(value: &Value) -> Vec<String> { | |
| 176 | match value { | |
| 177 | Value::Array(list) => list.iter().filter_map(text).collect(), | |
| 178 | Value::String(_) => text(value).into_iter().collect(), | |
| 179 | _ => Vec::new(), | |
| 180 | } | |
| 181 | } | |
| 182 | ||
| 183 | /// Reads a specification RubyGems wrote as YAML. | |
| 184 | pub fn read_spec(text_yaml: &str) -> Result<Gemspec, String> { | |
| 185 | let spec = yaml::parse(text_yaml).map_err(|problem| format!("The gem's metadata is not YAML: {problem}"))?; | |
| 186 | if !spec.is_object() { | |
| 187 | return Err("The gem's metadata is not a specification.".to_owned()); | |
| 188 | } | |
| 189 | let version = &spec["version"]; | |
| 190 | let version = text(version.get("version").unwrap_or(version)).ok_or("The gem's metadata names no version.")?; | |
| 191 | let platform = match &spec["platform"] { | |
| 192 | Value::Object(map) => ["cpu", "os", "version"].iter().filter_map(|k| map.get(*k).and_then(text)).collect::<Vec<_>>().join("-"), | |
| 193 | other => text(other).unwrap_or_else(|| "ruby".to_owned()), | |
| 194 | }; | |
| 195 | let dependencies = spec["dependencies"] | |
| 196 | .as_array() | |
| 197 | .map(|deps| { | |
| 198 | deps.iter() | |
| 199 | .filter(|d| d["type"].as_str().is_none_or(|t| t.trim_start_matches(':') == "runtime")) | |
| 200 | .filter_map(|d| { | |
| 201 | let name = text(&d["name"])?; | |
| 202 | let req = d.get("requirement").filter(|r| r.is_object()).or_else(|| d.get("version_requirements")).map(requirement).unwrap_or_default(); | |
| 203 | Some((name, if req.is_empty() { ">= 0".to_owned() } else { req })) | |
| 204 | }) | |
| 205 | .collect() | |
| 206 | }) | |
| 207 | .unwrap_or_default(); | |
| 208 | let required = |key: &str| Some(requirement(&spec[key])).filter(|r| !anything(r)); | |
| 209 | Ok(Gemspec { | |
| 210 | name: text(&spec["name"]).ok_or("The gem's metadata names no gem.")?, | |
| 211 | version, | |
| 212 | platform: if platform.is_empty() { "ruby".to_owned() } else { platform }, | |
| 213 | summary: text(&spec["summary"]), | |
| 214 | description: text(&spec["description"]), | |
| 215 | homepage: text(&spec["homepage"]), | |
| 216 | source_code_uri: text(&spec["metadata"]["source_code_uri"]), | |
| 217 | licenses: texts(&spec["licenses"]), | |
| 218 | authors: texts(&spec["authors"]), | |
| 219 | dependencies, | |
| 220 | ruby: required("required_ruby_version"), | |
| 221 | rubygems: required("required_rubygems_version"), | |
| 222 | }) | |
| 223 | } | |
| 224 | ||
| 225 | /// Reads a `.gem`: the specification in its `metadata.gz`. | |
| 226 | pub fn read_gem(gem: &[u8]) -> Result<Gemspec, String> { | |
| 227 | let files = archive::tar_files(gem).map_err(|_| "The file is not a .gem: it is not a tar archive.".to_owned())?; | |
| 228 | let (_, metadata) = files.iter().find(|(name, _)| name == "metadata.gz").ok_or("The gem has no metadata.gz.")?; | |
| 229 | let yaml = archive::gunzip(metadata, MAX_METADATA_BYTES)?; | |
| 230 | read_spec(&String::from_utf8(yaml).map_err(|_| "The gem's metadata is not UTF-8.".to_owned())?) | |
| 231 | } | |
| 232 | ||
| 233 | /// What a version keeps for its index line and the gem's page. | |
| 234 | pub fn stored(spec: &Gemspec) -> Value { | |
| 235 | json!({ | |
| 236 | "name": spec.name, | |
| 237 | "number": spec.version, | |
| 238 | "platform": spec.platform, | |
| 239 | "summary": spec.summary, | |
| 240 | "description": spec.description, | |
| 241 | "homepage": spec.homepage, | |
| 242 | "source_code_uri": spec.source_code_uri, | |
| 243 | "licenses": spec.licenses, | |
| 244 | "authors": spec.authors, | |
| 245 | "dependencies": spec.dependencies.iter().map(|(name, req)| json!({ "name": name, "requirement": req })).collect::<Vec<_>>(), | |
| 246 | "ruby": spec.ruby, | |
| 247 | "rubygems": spec.rubygems, | |
| 248 | }) | |
| 249 | } | |
| 250 | ||
| 251 | /// One line of a gem's info file: `1.0.0 rack:>= 2.0&< 4|checksum:<sha256>,ruby:>= 3.0`. | |
| 252 | pub fn info_line(key: &str, stored: &Value, checksum: &str) -> String { | |
| 253 | let deps: Vec<String> = stored["dependencies"] | |
| 254 | .as_array() | |
| 255 | .map(|deps| { | |
| 256 | deps.iter() | |
| 257 | .filter_map(|d| Some(format!("{}:{}", d["name"].as_str()?, d["requirement"].as_str().unwrap_or(">= 0")))) | |
| 258 | .collect() | |
| 259 | }) | |
| 260 | .unwrap_or_default(); | |
| 261 | let mut requirements = vec![format!("checksum:{checksum}")]; | |
| 262 | if let Some(ruby) = stored["ruby"].as_str() { | |
| 263 | requirements.push(format!("ruby:{ruby}")); | |
| 264 | } | |
| 265 | if let Some(rubygems) = stored["rubygems"].as_str() { | |
| 266 | requirements.push(format!("rubygems:{rubygems}")); | |
| 267 | } | |
| 268 | format!("{key} {}|{}", deps.join(","), requirements.join(",")) | |
| 269 | } | |
| 270 | ||
| 271 | /// A gem's info file, from its versions' lines, oldest first. | |
| 272 | pub fn info(lines: &[String]) -> String { | |
| 273 | let mut out = String::from("---\n"); | |
| 274 | for line in lines { | |
| 275 | out.push_str(line); | |
| 276 | out.push('\n'); | |
| 277 | } | |
| 278 | out | |
| 279 | } | |
| 280 | ||
| 281 | /// The `versions` file: each gem's versions and its info file's MD5. | |
| 282 | pub fn versions_file(created_at: &str, gems: &[(String, Vec<String>, String)]) -> String { | |
| 283 | let mut out = format!("created_at: {created_at}\n---\n"); | |
| 284 | for (name, versions, md5) in gems { | |
| 285 | out.push_str(&format!("{name} {} {md5}\n", versions.join(","))); | |
| 286 | } | |
| 287 | out | |
| 288 | } | |
| 289 | ||
| 290 | pub fn names_file(names: &[String]) -> String { | |
| 291 | let mut out = String::from("---\n"); | |
| 292 | for name in names { | |
| 293 | out.push_str(name); | |
| 294 | out.push('\n'); | |
| 295 | } | |
| 296 | out | |
| 297 | } | |
| 298 | ||
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 299 | /// Which of the full index's files: every released version, the highest |
| 300 | /// released version of each gem and platform, or every pre-release. | |
| 301 | #[derive(Clone, Copy, Debug, PartialEq, Eq)] | |
| 302 | pub enum Specs { | |
| 303 | Released, | |
| 304 | Latest, | |
| 305 | Prerelease, | |
| 306 | } | |
| 307 | ||
| 308 | /// A version's parts as `Gem::Version` compares them: `1.0.0.rc1` is | |
| 309 | /// `1 0 0 rc 1`, and `1.0.0-beta` is `1.0.0.pre.beta`. | |
| 310 | #[derive(Clone, Debug, PartialEq, Eq)] | |
| 311 | enum Part { | |
| 312 | Number(u64), | |
| 313 | Word(String), | |
| 314 | } | |
| 315 | ||
| 316 | fn parts(version: &str) -> Vec<Part> { | |
| 317 | let version = version.trim().replace('-', ".pre."); | |
| 318 | let mut out = Vec::new(); | |
| 319 | for piece in version.split('.') { | |
| 320 | let mut rest = piece; | |
| 321 | while !rest.is_empty() { | |
| 322 | let digits = rest.bytes().next().is_some_and(|b| b.is_ascii_digit()); | |
| 323 | let len = rest.bytes().take_while(|b| b.is_ascii_digit() == digits).count(); | |
| 324 | let (run, after) = rest.split_at(len); | |
| 325 | out.push(if digits { Part::Number(run.parse().unwrap_or(u64::MAX)) } else { Part::Word(run.to_owned()) }); | |
| 326 | rest = after; | |
| 327 | } | |
| 328 | } | |
| 329 | out | |
| 330 | } | |
| 331 | ||
| 332 | /// `Gem::Version`'s order: by part, a missing part is 0, and a word (a | |
| 333 | /// pre-release) is lower than any number. | |
| 334 | pub fn compare(a: &str, b: &str) -> Ordering { | |
| 335 | let (a, b) = (parts(a), parts(b)); | |
| 336 | for i in 0..a.len().max(b.len()) { | |
| 337 | let zero = Part::Number(0); | |
| 338 | let (x, y) = (a.get(i).unwrap_or(&zero), b.get(i).unwrap_or(&zero)); | |
| 339 | let order = match (x, y) { | |
| 340 | (Part::Number(x), Part::Number(y)) => x.cmp(y), | |
| 341 | (Part::Word(x), Part::Word(y)) => x.cmp(y), | |
| 342 | (Part::Word(_), Part::Number(_)) => Ordering::Less, | |
| 343 | (Part::Number(_), Part::Word(_)) => Ordering::Greater, | |
| 344 | }; | |
| 345 | if order != Ordering::Equal { | |
| 346 | return order; | |
| 347 | } | |
| 348 | } | |
| 349 | Ordering::Equal | |
| 350 | } | |
| 351 | ||
| 352 | /// One version in the full index: its gem, number and platform. | |
| 353 | #[derive(Clone, Debug, PartialEq, Eq)] | |
| 354 | pub struct Tuple { | |
| 355 | pub name: String, | |
| 356 | pub number: String, | |
| 357 | pub platform: String, | |
| 358 | } | |
| 359 | ||
| 360 | impl Tuple { | |
| 361 | /// What a version keeps says its number and platform. | |
| 362 | pub fn of(name: &str, key: &str, stored: &Value) -> Tuple { | |
| 363 | let platform = stored["platform"].as_str().filter(|p| !p.is_empty()).unwrap_or("ruby").to_owned(); | |
| 364 | let number = stored["number"].as_str().map(str::to_owned).unwrap_or_else(|| { | |
| 365 | key.strip_suffix(&format!("-{platform}")).unwrap_or(key).to_owned() | |
| 366 | }); | |
| 367 | Tuple { name: name.to_owned(), number, platform } | |
| 368 | } | |
| 369 | } | |
| 370 | ||
| 371 | /// A `Gem::Version`, marshalled as its `marshal_dump`: `[version]`. | |
| 372 | fn gem_version(number: &str) -> Ruby { | |
| 373 | Ruby::UserMarshal { class: "Gem::Version".into(), data: Box::new(Ruby::Array(vec![Ruby::str(number)])) } | |
| 374 | } | |
| 375 | ||
| 376 | /// A full index file: each version of `tuples` that `which` lists, as | |
| 377 | /// `[name, Gem::Version, platform]`, marshalled and gzipped. | |
| 378 | pub fn specs_file(which: Specs, tuples: &[Tuple]) -> Vec<u8> { | |
| 379 | let mut chosen: Vec<&Tuple> = match which { | |
| 380 | Specs::Released => tuples.iter().filter(|t| !is_prerelease(&t.number)).collect(), | |
| 381 | Specs::Prerelease => tuples.iter().filter(|t| is_prerelease(&t.number)).collect(), | |
| 382 | Specs::Latest => { | |
| 383 | let mut highest: Vec<&Tuple> = Vec::new(); | |
| 384 | for tuple in tuples.iter().filter(|t| !is_prerelease(&t.number)) { | |
| 385 | match highest.iter_mut().find(|h| h.name == tuple.name && h.platform == tuple.platform) { | |
| 386 | Some(kept) if compare(&tuple.number, &kept.number) == Ordering::Greater => *kept = tuple, | |
| 387 | Some(_) => {} | |
| 388 | None => highest.push(tuple), | |
| 389 | } | |
| 390 | } | |
| 391 | highest | |
| 392 | } | |
| 393 | }; | |
| 394 | chosen.sort_by(|a, b| a.name.cmp(&b.name).then_with(|| compare(&a.number, &b.number)).then_with(|| a.platform.cmp(&b.platform))); | |
| 395 | let list = chosen | |
| 396 | .into_iter() | |
| 397 | .map(|t| Ruby::Array(vec![Ruby::str(&t.name), gem_version(&t.number), Ruby::str(&t.platform)])) | |
| 398 | .collect(); | |
| 399 | archive::gzip(&marshal::dump(&Ruby::Array(list))) | |
| 400 | } | |
| 401 | ||
| 402 | /// A `Gem::Requirement` from the index's form (`< 4&>= 2.0`), marshalled | |
| 403 | /// as its `marshal_dump`: `[[[op, Gem::Version], ...]]`. | |
| 404 | fn gem_requirement(text: Option<&str>) -> Ruby { | |
| 405 | let mut pairs: Vec<Ruby> = text | |
| 406 | .unwrap_or("") | |
| 407 | .split('&') | |
| 408 | .map(str::trim) | |
| 409 | .filter(|r| !r.is_empty()) | |
| 410 | .map(|r| { | |
| 411 | let (op, number) = match r.split_once(' ') { | |
| 412 | Some((op, number)) => (op.trim(), number.trim()), | |
| 413 | None => ("=", r), | |
| 414 | }; | |
| 415 | Ruby::Array(vec![Ruby::str(op), gem_version(number)]) | |
| 416 | }) | |
| 417 | .collect(); | |
| 418 | if pairs.is_empty() { | |
| 419 | pairs.push(Ruby::Array(vec![Ruby::str(">="), gem_version("0")])); | |
| 420 | } | |
| 421 | Ruby::UserMarshal { class: "Gem::Requirement".into(), data: Box::new(Ruby::Array(vec![Ruby::Array(pairs)])) } | |
| 422 | } | |
| 423 | ||
| 424 | /// A `Gem::Platform` (`x86_64-linux` is cpu `x86_64`, os `linux`), or the | |
| 425 | /// string `ruby` for a pure-Ruby gem, as RubyGems marshals it. | |
| 426 | fn gem_platform(platform: &str) -> Ruby { | |
| 427 | if platform == "ruby" { | |
| 428 | return Ruby::str("ruby"); | |
| 429 | } | |
| 430 | let parts: Vec<&str> = platform.splitn(3, '-').collect(); | |
| 431 | let (cpu, os, version) = match parts.as_slice() { | |
| 432 | [os] => (None, *os, None), | |
| 433 | [cpu, os] => (Some(*cpu), *os, None), | |
| 434 | [cpu, os, version, ..] => (Some(*cpu), *os, Some(*version)), | |
| 435 | [] => (None, platform, None), | |
| 436 | }; | |
| 437 | Ruby::Object { | |
| 438 | class: "Gem::Platform".into(), | |
| 439 | ivars: vec![("@cpu".into(), Ruby::opt(cpu)), ("@os".into(), Ruby::str(os)), ("@version".into(), Ruby::opt(version))], | |
| 440 | } | |
| 441 | } | |
| 442 | ||
| 443 | /// A version's `Gem::Specification`, from what it keeps, marshalled as | |
| 444 | /// RubyGems' `_dump` writes it and deflated: the `.gemspec.rz` that | |
| 445 | /// `gem install` reads before it downloads the gem. | |
| 446 | pub fn quick_spec(name: &str, key: &str, stored: &Value, published_at: &str) -> Vec<u8> { | |
| 447 | let tuple = Tuple::of(name, key, stored); | |
| 448 | let text = |key: &str| stored[key].as_str().map(str::trim).filter(|t| !t.is_empty()); | |
| 449 | let strings = |key: &str| Ruby::Array(texts(&stored[key]).into_iter().map(Ruby::Str).collect()); | |
| 450 | let dependencies = stored["dependencies"] | |
| 451 | .as_array() | |
| 452 | .map(|deps| { | |
| 453 | deps.iter() | |
| 454 | .filter_map(|d| { | |
| 455 | let name = d["name"].as_str()?; | |
| 456 | let requirement = gem_requirement(d["requirement"].as_str()); | |
| 457 | Some(Ruby::Object { | |
| 458 | class: "Gem::Dependency".into(), | |
| 459 | ivars: vec![ | |
| 460 | ("@name".into(), Ruby::str(name)), | |
| 461 | ("@requirement".into(), requirement.clone()), | |
| 462 | ("@type".into(), Ruby::Symbol("runtime".into())), | |
| 463 | ("@prerelease".into(), Ruby::Bool(false)), | |
| 464 | ("@version_requirements".into(), requirement), | |
| 465 | ], | |
| 466 | }) | |
| 467 | }) | |
| 468 | .collect() | |
| 469 | }) | |
| 470 | .unwrap_or_default(); | |
| 471 | let mut metadata = Vec::new(); | |
| 472 | if let Some(uri) = text("source_code_uri") { | |
| 473 | metadata.push((Ruby::str("source_code_uri"), Ruby::str(uri))); | |
| 474 | } | |
| 475 | let date = published_at.get(..10).filter(|d| d.len() == 10).unwrap_or("1980-01-02"); | |
| 476 | // The fields of `Gem::Specification#_dump`, in its order. | |
| 477 | let fields = Ruby::Array(vec![ | |
| 478 | Ruby::str(text("rubygems_version").unwrap_or("3.5.0")), | |
| 479 | Ruby::Int(4), | |
| 480 | Ruby::str(&tuple.name), | |
| 481 | gem_version(&tuple.number), | |
| 482 | Ruby::str(date), | |
| 483 | Ruby::str(text("summary").unwrap_or("")), | |
| 484 | gem_requirement(text("ruby")), | |
| 485 | gem_requirement(text("rubygems")), | |
| 486 | Ruby::str(&tuple.platform), | |
| 487 | Ruby::Array(dependencies), | |
| 488 | Ruby::str(""), | |
| 489 | Ruby::Nil, | |
| 490 | strings("authors"), | |
| 491 | Ruby::opt(text("description")), | |
| 492 | Ruby::opt(text("homepage")), | |
| 493 | Ruby::Bool(true), | |
| 494 | gem_platform(&tuple.platform), | |
| 495 | strings("licenses"), | |
| 496 | Ruby::Hash(metadata), | |
| 497 | ]); | |
| 498 | let spec = Ruby::UserDef { class: "Gem::Specification".into(), data: marshal::dump(&fields) }; | |
| 499 | miniz_oxide::deflate::compress_to_vec_zlib(&marshal::dump(&spec), 6) | |
| 500 | } | |
| 501 | ||
| Merge branch 'worktree-agent-a6a121745e81f639f' | 502 | /// A value from a form body or query string (`gem_name=hello&version=1.0`). |
| 503 | pub fn form_value(form: &str, key: &str) -> Option<String> { | |
| 504 | let url = worker::Url::parse(&format!("http://form.invalid/?{form}")).ok()?; | |
| 505 | url.query_pairs().find(|(k, _)| k == key).map(|(_, v)| v.into_owned()).filter(|v| !v.is_empty()) | |
| 506 | } | |
| 507 | ||
| 508 | #[cfg(test)] | |
| 509 | mod tests { | |
| 510 | use super::*; | |
| 511 | ||
| 512 | #[test] | |
| 513 | fn names_and_versions_follow_rubygems_rules() { | |
| 514 | for good in ["rails", "hello-world", "net_http2", "a1", "Hello.rb"] { | |
| 515 | assert!(valid_name(good), "{good}"); | |
| 516 | } | |
| 517 | for bad in ["", "123", "-a", ".a", "a b", "a/b", &"a".repeat(129)] { | |
| 518 | assert!(!valid_name(bad), "{bad}"); | |
| 519 | } | |
| 520 | for good in ["1.0.0", "0.1", "2.0.0.rc1", "1.0.0-beta.1", "3"] { | |
| 521 | assert!(valid_version(good), "{good}"); | |
| 522 | } | |
| 523 | for bad in ["", "a.1", "1..0", "1.0 0", "1.0-"] { | |
| 524 | assert!(!valid_version(bad), "{bad}"); | |
| 525 | } | |
| 526 | assert!(is_prerelease("2.0.0.rc1") && !is_prerelease("2.0.0")); | |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 527 | let mut sorted = vec!["1.10.0", "1.0.0", "1.0.0.rc1", "1.0", "1.2.0-beta.1", "1.2.0", "0.9"]; |
| 528 | sorted.sort_by(|a, b| compare(a, b)); | |
| 529 | assert_eq!(sorted, ["0.9", "1.0.0.rc1", "1.0.0", "1.0", "1.2.0-beta.1", "1.2.0", "1.10.0"]); | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 530 | assert_eq!(key("1.0.0", "ruby"), "1.0.0"); |
| 531 | assert_eq!(key("1.0.0", "x86_64-linux"), "1.0.0-x86_64-linux"); | |
| 532 | } | |
| 533 | ||
| 534 | #[test] | |
| 535 | fn every_endpoint_is_routed() { | |
| 536 | let at = |route: GemRoute| Some(("acme".to_owned(), route)); | |
| 537 | assert_eq!(route("/-/rubygems/Acme/versions"), at(GemRoute::Versions)); | |
| 538 | assert_eq!(route("/-/rubygems/acme/names"), at(GemRoute::Names)); | |
| 539 | assert_eq!(route("/-/rubygems/acme/info/hello-world"), at(GemRoute::Info { name: "hello-world".into() })); | |
| 540 | assert_eq!(route("/-/rubygems/acme/gems/hello-world-0.1.0.gem"), at(GemRoute::Gem { stem: "hello-world-0.1.0".into() })); | |
| 541 | assert_eq!(route("/-/rubygems/acme/api/v1/gems"), at(GemRoute::Push)); | |
| 542 | assert_eq!(route("/-/rubygems/acme/api/v1/gems/yank"), at(GemRoute::Yank)); | |
| 543 | assert_eq!(route("/-/rubygems/acme/gems/hello.gem"), None, "no version"); | |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 544 | assert_eq!(route("/-/rubygems/acme/specs.4.8.gz"), at(GemRoute::Specs(Specs::Released))); |
| 545 | assert_eq!(route("/-/rubygems/acme/latest_specs.4.8.gz"), at(GemRoute::Specs(Specs::Latest))); | |
| 546 | assert_eq!(route("/-/rubygems/acme/prerelease_specs.4.8.gz"), at(GemRoute::Specs(Specs::Prerelease))); | |
| 547 | assert_eq!( | |
| 548 | route("/-/rubygems/acme/quick/Marshal.4.8/hello-world-0.1.0.gemspec.rz"), | |
| 549 | at(GemRoute::QuickSpec { stem: "hello-world-0.1.0".into() }) | |
| 550 | ); | |
| 551 | assert_eq!(route("/-/rubygems/acme/quick/Marshal.4.8/hello.gemspec.rz"), None, "no version"); | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 552 | assert_eq!(route("/-/rubygems/acme/info/a b"), None); |
| 553 | assert_eq!(route("/-/rubygems/acme/other"), None); | |
| 554 | assert_eq!(route("/-/rubygems/acme"), None); | |
| 555 | assert_eq!( | |
| 556 | candidates("hello-world-0.1.0-x86_64-linux"), | |
| 557 | [("hello-world".to_owned(), "0.1.0-x86_64-linux".to_owned())], | |
| 558 | "x86_64 starts with a letter" | |
| 559 | ); | |
| 560 | assert_eq!(candidates("a-2-1.0"), [("a".to_owned(), "2-1.0".to_owned()), ("a-2".to_owned(), "1.0".to_owned())]); | |
| 561 | } | |
| 562 | ||
| 563 | const SPEC: &str = r#"--- !ruby/object:Gem::Specification | |
| 564 | name: hello-world | |
| 565 | version: !ruby/object:Gem::Version | |
| 566 | version: 0.2.0 | |
| 567 | platform: ruby | |
| 568 | authors: | |
| 569 | - Ada | |
| 570 | dependencies: | |
| 571 | - !ruby/object:Gem::Dependency | |
| 572 | name: rack | |
| 573 | requirement: !ruby/object:Gem::Requirement | |
| 574 | requirements: | |
| 575 | - - "<" | |
| 576 | - !ruby/object:Gem::Version | |
| 577 | version: '4' | |
| 578 | - - ">=" | |
| 579 | - !ruby/object:Gem::Version | |
| 580 | version: '2.0' | |
| 581 | type: :runtime | |
| 582 | prerelease: false | |
| 583 | version_requirements: !ruby/object:Gem::Requirement | |
| 584 | requirements: | |
| 585 | - - "<" | |
| 586 | - !ruby/object:Gem::Version | |
| 587 | version: '4' | |
| 588 | - !ruby/object:Gem::Dependency | |
| 589 | name: json | |
| 590 | requirement: !ruby/object:Gem::Requirement | |
| 591 | requirements: | |
| 592 | - - ">=" | |
| 593 | - !ruby/object:Gem::Version | |
| 594 | version: '0' | |
| 595 | type: :runtime | |
| 596 | - !ruby/object:Gem::Dependency | |
| 597 | name: rspec | |
| 598 | requirement: !ruby/object:Gem::Requirement | |
| 599 | requirements: | |
| 600 | - - "~>" | |
| 601 | - !ruby/object:Gem::Version | |
| 602 | version: '3.0' | |
| 603 | type: :development | |
| 604 | description: Says hello. | |
| 605 | homepage: https://g1t.sh/acme/hello-world | |
| 606 | licenses: | |
| 607 | - MIT | |
| 608 | metadata: | |
| 609 | source_code_uri: https://g1t.sh/acme/hello-world | |
| 610 | required_ruby_version: !ruby/object:Gem::Requirement | |
| 611 | requirements: | |
| 612 | - - ">=" | |
| 613 | - !ruby/object:Gem::Version | |
| 614 | version: 3.0.0 | |
| 615 | required_rubygems_version: !ruby/object:Gem::Requirement | |
| 616 | requirements: | |
| 617 | - - ">=" | |
| 618 | - !ruby/object:Gem::Version | |
| 619 | version: '0' | |
| 620 | summary: Says hello | |
| 621 | "#; | |
| 622 | ||
| 623 | #[test] | |
| 624 | fn a_gem_is_read_from_its_metadata() { | |
| 625 | let mut gz = vec![0x1f, 0x8b, 8, 0, 0, 0, 0, 0, 0, 3]; | |
| 626 | gz.extend_from_slice(&miniz_oxide::deflate::compress_to_vec(SPEC.as_bytes(), 6)); | |
| 627 | gz.extend_from_slice(&crate::composer::crc32(SPEC.as_bytes()).to_le_bytes()); | |
| 628 | gz.extend_from_slice(&(SPEC.len() as u32).to_le_bytes()); | |
| 629 | let mut gem = Vec::new(); | |
| 630 | for (name, data) in [("metadata.gz", gz.as_slice()), ("data.tar.gz", b"x".as_slice())] { | |
| 631 | let mut header = [0u8; 512]; | |
| 632 | header[..name.len()].copy_from_slice(name.as_bytes()); | |
| 633 | header[124..136].copy_from_slice(format!("{:011o}\0", data.len()).as_bytes()); | |
| 634 | header[156] = b'0'; | |
| 635 | gem.extend_from_slice(&header); | |
| 636 | gem.extend_from_slice(data); | |
| 637 | gem.resize(gem.len().div_ceil(512) * 512, 0); | |
| 638 | } | |
| 639 | gem.extend_from_slice(&[0; 1024]); | |
| 640 | let spec = read_gem(&gem).unwrap(); | |
| 641 | assert_eq!((spec.name.as_str(), spec.version.as_str(), spec.platform.as_str()), ("hello-world", "0.2.0", "ruby")); | |
| 642 | assert_eq!(spec.dependencies, [("rack".to_owned(), "< 4&>= 2.0".to_owned()), ("json".to_owned(), ">= 0".to_owned())], "runtime only"); | |
| 643 | assert_eq!(spec.ruby.as_deref(), Some(">= 3.0.0")); | |
| 644 | assert_eq!(spec.rubygems, None, ">= 0 says nothing"); | |
| 645 | assert_eq!(spec.source_code_uri.as_deref(), Some("https://g1t.sh/acme/hello-world")); | |
| 646 | assert_eq!(spec.licenses, ["MIT"]); | |
| 647 | assert!(read_gem(b"not a gem").is_err()); | |
| 648 | ||
| 649 | let line = info_line(&key(&spec.version, &spec.platform), &stored(&spec), "abc123"); | |
| 650 | assert_eq!(line, "0.2.0 rack:< 4&>= 2.0,json:>= 0|checksum:abc123,ruby:>= 3.0.0"); | |
| 651 | let bare = info_line("1.0.0", &json!({ "dependencies": [] }), "ff"); | |
| 652 | assert_eq!(bare, "1.0.0 |checksum:ff"); | |
| 653 | } | |
| 654 | ||
| 655 | #[test] | |
| 656 | fn a_platform_mapping_reads_as_its_name() { | |
| 657 | let spec = read_spec("name: native\nversion: !ruby/object:Gem::Version\n version: 1.0.0\nplatform: !ruby/object:Gem::Platform\n cpu: x86_64\n os: linux\n version:\n").unwrap(); | |
| 658 | assert_eq!(spec.platform, "x86_64-linux"); | |
| 659 | assert!(read_spec("name: x\n").is_err(), "no version"); | |
| 660 | } | |
| 661 | ||
| 662 | #[test] | |
| 663 | fn the_compact_index_is_bundlers_shape() { | |
| 664 | let info = info(&["0.1.0 |checksum:aa".to_owned(), "0.2.0 rack:>= 2|checksum:bb".to_owned()]); | |
| 665 | assert_eq!(info, "---\n0.1.0 |checksum:aa\n0.2.0 rack:>= 2|checksum:bb\n"); | |
| 666 | let versions = versions_file("2026-10-06T00:00:00Z", &[("hello".into(), vec!["0.1.0".into(), "0.2.0".into()], "d41d8".into())]); | |
| 667 | assert_eq!(versions, "created_at: 2026-10-06T00:00:00Z\n---\nhello 0.1.0,0.2.0 d41d8\n"); | |
| 668 | assert_eq!(names_file(&["a".into(), "b".into()]), "---\na\nb\n"); | |
| 669 | assert_eq!(form_value("gem_name=hello-world&version=0.1.0&platform=", "gem_name").as_deref(), Some("hello-world")); | |
| 670 | assert_eq!(form_value("gem_name=a%2Bb", "gem_name").as_deref(), Some("a+b")); | |
| 671 | assert_eq!(form_value("version=1", "platform"), None); | |
| 672 | } | |
| Merge branch 'worktree-agent-ac1de8a731938ed81' | 673 | |
| 674 | fn tuples() -> Vec<Tuple> { | |
| 675 | let tuple = |name: &str, number: &str, platform: &str| Tuple { name: name.into(), number: number.into(), platform: platform.into() }; | |
| 676 | vec![ | |
| 677 | tuple("hello", "0.2.0", "ruby"), | |
| 678 | tuple("hello", "0.10.0", "ruby"), | |
| 679 | tuple("hello", "1.0.0.rc1", "ruby"), | |
| 680 | tuple("hello", "0.10.0", "java"), | |
| 681 | tuple("abc", "1.0.0", "ruby"), | |
| 682 | ] | |
| 683 | } | |
| 684 | ||
| 685 | #[test] | |
| 686 | fn the_full_index_lists_versions_as_tuples() { | |
| 687 | let file = specs_file(Specs::Latest, &tuples()); | |
| 688 | let bytes = archive::gunzip(&file, 1 << 20).unwrap(); | |
| 689 | // By name, then version and platform: hello's highest of each. | |
| 690 | let dumped = marshal::dump(&Ruby::Array(vec![ | |
| 691 | Ruby::Array(vec![Ruby::str("abc"), gem_version("1.0.0"), Ruby::str("ruby")]), | |
| 692 | Ruby::Array(vec![Ruby::str("hello"), gem_version("0.10.0"), Ruby::str("java")]), | |
| 693 | Ruby::Array(vec![Ruby::str("hello"), gem_version("0.10.0"), Ruby::str("ruby")]), | |
| 694 | ])); | |
| 695 | assert_eq!(bytes, dumped); | |
| 696 | let released = archive::gunzip(&specs_file(Specs::Released, &tuples()), 1 << 20).unwrap(); | |
| 697 | assert_eq!(released.windows(5).filter(|w| *w == b"hello").count(), 3, "every released version"); | |
| 698 | let pre = archive::gunzip(&specs_file(Specs::Prerelease, &tuples()), 1 << 20).unwrap(); | |
| 699 | assert!(pre.windows(9).any(|w| w == b"1.0.0.rc1")); | |
| 700 | assert!(!pre.windows(6).any(|w| w == b"0.10.0")); | |
| 701 | } | |
| 702 | ||
| 703 | #[test] | |
| 704 | fn a_quick_spec_is_a_deflated_specification() { | |
| 705 | let stored = json!({ | |
| 706 | "name": "hello-world", "number": "0.2.0", "platform": "ruby", "summary": "Says hello", | |
| 707 | "authors": ["Ada"], "licenses": ["MIT"], "homepage": "https://g1t.sh/acme/hello-world", | |
| 708 | "dependencies": [{ "name": "rack", "requirement": "< 4&>= 2.0" }], "ruby": ">= 3.0.0", "rubygems": null, | |
| 709 | }); | |
| 710 | let rz = quick_spec("hello-world", "0.2.0", &stored, "2026-10-07T01:02:03.000Z"); | |
| 711 | let bytes = miniz_oxide::inflate::decompress_to_vec_zlib(&rz).unwrap(); | |
| 712 | assert_eq!(&bytes[..3], b"\x04\x08u"); | |
| 713 | assert!(bytes.windows(18).any(|w| w == b"Gem::Specification")); | |
| 714 | assert!(bytes.windows(10).any(|w| w == b"2026-10-07")); | |
| 715 | assert!(bytes.windows(15).any(|w| w == b"Gem::Dependency")); | |
| 716 | // A gem built for a platform names it as a Gem::Platform too. | |
| 717 | let native = quick_spec("native", "1.0.0-x86_64-linux", &json!({ "number": "1.0.0", "platform": "x86_64-linux" }), ""); | |
| 718 | let bytes = miniz_oxide::inflate::decompress_to_vec_zlib(&native).unwrap(); | |
| 719 | assert!(bytes.windows(13).any(|w| w == b"Gem::Platform")); | |
| 720 | assert_eq!(Tuple::of("native", "1.0.0-x86_64-linux", &json!({})).number, "1.0.0-x86_64-linux", "no platform kept: the key"); | |
| 721 | assert_eq!(Tuple::of("native", "1.0.0-java", &json!({ "platform": "java" })).number, "1.0.0"); | |
| 722 | } | |
| 723 | ||
| 724 | /// Writes the full index for `tuples()` and a quick spec where a real | |
| 725 | /// Ruby can read them: `G1T_MARSHAL_OUT=<dir> cargo test marshal_files`, | |
| 726 | /// then `ruby -e` over the files (see the RubyGems guide's notes). | |
| 727 | #[test] | |
| 728 | fn marshal_files_for_ruby() { | |
| 729 | let Ok(dir) = std::env::var("G1T_MARSHAL_OUT") else { return }; | |
| 730 | let dir = std::path::Path::new(&dir); | |
| 731 | std::fs::write(dir.join("specs.4.8.gz"), specs_file(Specs::Released, &tuples())).unwrap(); | |
| 732 | std::fs::write(dir.join("latest_specs.4.8.gz"), specs_file(Specs::Latest, &tuples())).unwrap(); | |
| 733 | let stored = json!({ | |
| 734 | "name": "hello-world", "number": "0.2.0", "platform": "ruby", "summary": "Says hello", "description": "Says hello.", | |
| 735 | "authors": ["Ada"], "licenses": ["MIT"], "homepage": "https://g1t.sh/acme/hello-world", "source_code_uri": "https://g1t.sh/acme/hello-world", | |
| 736 | "dependencies": [{ "name": "rack", "requirement": "< 4&>= 2.0" }, { "name": "json", "requirement": ">= 0" }], "ruby": ">= 3.0.0", | |
| 737 | }); | |
| 738 | std::fs::write(dir.join("hello-world-0.2.0.gemspec.rz"), quick_spec("hello-world", "0.2.0", &stored, "2026-10-07T00:00:00.000Z")).unwrap(); | |
| 739 | let native = json!({ "name": "native", "number": "1.0.0", "platform": "x86_64-linux", "dependencies": [] }); | |
| 740 | std::fs::write(dir.join("native-1.0.0-x86_64-linux.gemspec.rz"), quick_spec("native", "1.0.0-x86_64-linux", &native, "2026-10-07T00:00:00.000Z")).unwrap(); | |
| 741 | } | |
| Merge branch 'worktree-agent-a6a121745e81f639f' | 742 | } |
This file's history is long; its oldest lines are credited to the oldest commit read.