Assembler: clone-all from link-index registry #1311
+133
−81
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -8,6 +8,7 @@ | |
| using System.IO.Abstractions; | ||
| using Elastic.Documentation.Configuration.Assembler; | ||
| using Elastic.Documentation.Diagnostics; | ||
| using Elastic.Documentation.LinkIndex; | ||
| using Elastic.Markdown.IO; | ||
| using Microsoft.Extensions.Logging; | ||
| using ProcNet; | ||
|
|
@@ -46,129 +47,169 @@ public IReadOnlyCollection<Checkout> GetAll() | |
| return checkouts; | ||
| } | ||
|
|
||
| public async Task<IReadOnlyCollection<Checkout>> CloneAll(bool fetchLatest, Cancel ctx = default) | ||
| { | ||
| _logger.LogInformation("Cloning all repositories for environment {EnvironmentName} using '{ContentSourceStrategy}' content sourcing strategy", | ||
| PublishEnvironment.Name, | ||
| PublishEnvironment.ContentSource.ToStringFast(true) | ||
| ); | ||
| var checkouts = new ConcurrentBag<Checkout>(); | ||
|
|
||
| ILinkIndexReader linkIndexReader = Aws3LinkIndexReader.CreateAnonymous(); | ||
| var linkRegistry = await linkIndexReader.GetRegistry(ctx); | ||
|
|
||
| var repositories = new Dictionary<string, Repository>(Configuration.ReferenceRepositories) | ||
| { | ||
| { NarrativeRepository.RepositoryName, Configuration.Narrative } | ||
| }; | ||
|
|
||
| await Parallel.ForEachAsync(repositories, | ||
| new ParallelOptions | ||
| { | ||
| CancellationToken = ctx, | ||
| MaxDegreeOfParallelism = Environment.ProcessorCount | ||
| }, async (repo, c) => | ||
| { | ||
| await Task.Run(() => | ||
| { | ||
| if (!linkRegistry.Repositories.TryGetValue(repo.Key, out var entry)) | ||
| { | ||
| context.Collector.EmitError("", $"'{repo.Key}' does not exist in link index"); | ||
| return; | ||
| } | ||
| var branch = repo.Value.GetBranch(PublishEnvironment.ContentSource); | ||
| var gitRef = branch; | ||
| if (!fetchLatest) | ||
| { | ||
| if (!entry.TryGetValue(branch, out var entryInfo)) | ||
| { | ||
| context.Collector.EmitError("", $"'{repo.Key}' does not have a '{branch}' entry in link index"); | ||
| return; | ||
| } | ||
| gitRef = entryInfo.GitReference; | ||
| } | ||
| checkouts.Add(RepositorySourcer.CloneRef(repo.Value, gitRef, fetchLatest)); | ||
| }, c); | ||
| }).ConfigureAwait(false); | ||
| return checkouts; | ||
| } | ||
| } | ||
|
|
||
|
|
||
| public class RepositorySourcer(ILoggerFactory logger, IDirectoryInfo checkoutDirectory, IFileSystem readFileSystem, DiagnosticsCollector collector) | ||
| { | ||
| private readonly ILogger<RepositorySourcer> _logger = logger.CreateLogger<RepositorySourcer>(); | ||
|
|
||
| // <summary> | ||
| // Clones the repository to the checkout directory and checks out the specified git reference. | ||
| // </summary> | ||
| // <param name="repository">The repository to clone.</param> | ||
| // <param name="gitRef">The git reference to check out. Branch, commit or tag</param> | ||
| public Checkout CloneRef(Repository repository, string gitRef, bool pull = false, int attempt = 1) | ||
| { | ||
| var checkoutFolder = readFileSystem.DirectoryInfo.New(Path.Combine(checkoutDirectory.FullName, repository.Name)); | ||
| if (attempt > 3) | ||
| { | ||
| collector.EmitError("", $"Failed to clone repository {repository.Name}@{gitRef} after 3 attempts"); | ||
| return new Checkout | ||
| { | ||
| Directory = checkoutFolder, | ||
| HeadReference = "", | ||
| Repository = repository, | ||
| }; | ||
| } | ||
| _logger.LogInformation("{RepositoryName}: Cloning repository {RepositoryName}@{Commit} to {CheckoutFolder}", repository.Name, repository.Name, gitRef, | ||
| checkoutFolder.FullName); | ||
| if (!checkoutFolder.Exists) | ||
| { | ||
| checkoutFolder.Create(); | ||
| checkoutFolder.Refresh(); | ||
| } | ||
| var isGitInitialized = GitInit(repository, checkoutFolder); | ||
| string? head = null; | ||
| if (isGitInitialized) | ||
| { | ||
| try | ||
| { | ||
| head = Capture(checkoutFolder, "git", "rev-parse", "HEAD"); | ||
| } | ||
| catch (Exception e) | ||
| { | ||
| _logger.LogError(e, "{RepositoryName}: Failed to acquire current commit, falling back to recreating from scratch", repository.Name); | ||
| checkoutFolder.Delete(true); | ||
| checkoutFolder.Refresh(); | ||
| return CloneRef(repository, gitRef, pull, attempt + 1); | ||
| } | ||
| } | ||
| // Repository already checked out the same commit | ||
| if (head != null && head == gitRef) | ||
| // nothing to do, already at the right commit | ||
| _logger.LogInformation("{RepositoryName}: HEAD already at {GitRef}", repository.Name, gitRef); | ||
| else | ||
| { | ||
| FetchAndCheckout(repository, gitRef, checkoutFolder); | ||
| if (!pull) | ||
| { | ||
| return new Checkout | ||
| { | ||
| Directory = checkoutFolder, | ||
| HeadReference = gitRef, | ||
| Repository = repository, | ||
| }; | ||
| } | ||
| try | ||
| { | ||
| ExecIn(checkoutFolder, "git", "pull", "--depth", "1", "--allow-unrelated-histories", "--no-ff", "origin", gitRef); | ||
| } | ||
| catch (Exception e) | ||
| { | ||
| _logger.LogError(e, "{RepositoryName}: Failed to update {GitRef} from {RelativePath}, falling back to recreating from scratch", | ||
| repository.Name, gitRef, checkoutFolder.FullName); | ||
| checkoutFolder.Delete(true); | ||
| checkoutFolder.Refresh(); | ||
| return CloneRef(repository, gitRef, pull, attempt + 1); | ||
| } | ||
| } | ||
|
|
||
| return new Checkout | ||
| { | ||
| Directory = checkoutFolder, | ||
| HeadReference = gitRef, | ||
| Repository = repository, | ||
| }; | ||
| } | ||
|
|
||
| /// <summary> | ||
| /// Initializes the git repository if it is not already initialized. | ||
| /// Returns true if the repository was already initialized. | ||
| /// </summary> | ||
| private bool GitInit(Repository repository, IDirectoryInfo checkoutFolder) | ||
| { | ||
| var isGitAlreadyInitialized = Directory.Exists(Path.Combine(checkoutFolder.FullName, ".git")); | ||
| if (isGitAlreadyInitialized) | ||
| return true; | ||
| ExecIn(checkoutFolder, "git", "init"); | ||
| ExecIn(checkoutFolder, "git", "remote", "add", "origin", repository.Origin); | ||
| return false; | ||
| } | ||
|
|
||
| private void FetchAndCheckout(Repository repository, string gitRef, IDirectoryInfo checkoutFolder) | ||
| { | ||
| ExecIn(checkoutFolder, "git", "fetch", "--no-tags", "--prune", "--no-recurse-submodules", "--depth", "1", "origin", gitRef); | ||
| switch (repository.CheckoutStrategy) | ||
| { | ||
| case CheckoutStrategy.Full: | ||
| ExecIn(checkoutFolder, "git", "sparse-checkout", "disable"); | ||
|
There was a problem hiding this comment. Why is this necessary? (not questioning it just looking to learn). There was a problem hiding this comment. It's actually unlikely.. But I was just thinking, if you ever change the checkout strategy and if you run the command, while the repo is still checked out (cached) you want to also disabled it. |
||
| break; | ||
|
Comment on lines
-158
to
-161
There was a problem hiding this comment. Suprised how little effect There was a problem hiding this comment. I think because cone mode is the default according to https://git-scm.com/docs/git-sparse-checkout#_internalscone_mode_handling |
||
| case CheckoutStrategy.Partial: | ||
| ExecIn(checkoutFolder, "git", "sparse-checkout", "set", "docs"); | ||
| break; | ||
| default: | ||
| throw new ArgumentOutOfRangeException(nameof(repository), repository.CheckoutStrategy, null); | ||
| } | ||
| ExecIn(checkoutFolder, "git", "checkout", "--force", gitRef); | ||
| } | ||
|
|
||
| private void ExecIn(IDirectoryInfo? workingDirectory, string binary, params string[] args) | ||
| { | ||
| var arguments = new ExecArguments(binary, args) | ||
|
|
@@ -221,7 +262,6 @@ string CaptureOutput() | |
| return line; | ||
| } | ||
| } | ||
| } | ||
|
|
||
| public class NoopConsoleWriter : IConsoleOutWriter | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Whats our use-case for this? I like the flag but just wondering :)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For local QAing, if you specify a different branch for a repo e.g. feature/new-content, you want to be able to fetch the latest.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In general I wanted to keep the old behaviour. Just in case.