feat: get matching PRs from GitHub

cmd/rp/cmd/root.go

@@ -17,11 +17,14 @@ along with this program. If not, see <http://www.gnu.org/licenses/>.
 package cmd
 
 import (
+	"log/slog"
 	"os"
 
 	"github.com/spf13/cobra"
 )
 
+var logger *slog.Logger
+
 // rootCmd represents the base command when called without any subcommands
 var rootCmd = &cobra.Command{
 	Use:   "releaser-pleaser",
@@ -47,6 +50,10 @@ func Execute() {
 }
 
 func init() {
+	logger = slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{
+		Level: slog.LevelDebug,
+	}))
+
 	// Here you will define your flags and configuration settings.
 	// Cobra supports persistent flags, which, if defined here,
 	// will be global for your application.

cmd/rp/cmd/run.go

@@ -5,10 +5,7 @@ package cmd
 
 import (
 	"fmt"
-	"log"
-	"strings"
 
-	"github.com/go-git/go-git/v5"
 	"github.com/spf13/cobra"
 
 	rp "github.com/apricote/releaser-pleaser"
@@ -21,8 +18,10 @@ var runCmd = &cobra.Command{
 }
 
 var (
-	flagForge string
+	flagForge  string
-	flagRepo  string
+	flagBranch string
+	flagOwner  string
+	flagRepo   string
 )
 
 func init() {
@@ -31,51 +30,60 @@ func init() {
 	// Here you will define your flags and configuration settings.
 
 	runCmd.PersistentFlags().StringVar(&flagForge, "forge", "", "")
+	runCmd.PersistentFlags().StringVar(&flagBranch, "branch", "main", "")
+	runCmd.PersistentFlags().StringVar(&flagOwner, "owner", "", "")
 	runCmd.PersistentFlags().StringVar(&flagRepo, "repo", "", "")
 }
 
 func run(cmd *cobra.Command, args []string) error {
+	ctx := cmd.Context()
+
 	var f rp.Forge
 
 	forgeOptions := rp.ForgeOptions{
 		Repository: flagRepo,
+		BaseBranch: flagBranch,
 	}
 
 	switch flagForge {
-	case "gitlab":
+	//case "gitlab":
-		f = rp.NewGitLab(forgeOptions)
+	//f = rp.NewGitLab(forgeOptions)
 	case "github":
-		f = rp.NewGitHub(forgeOptions)
+		f = rp.NewGitHub(logger, &rp.GitHubOptions{
+			ForgeOptions: forgeOptions,
+			Owner:        flagOwner,
+			Repo:         flagRepo,
+		})
 	}
 
-	log.Println("Repo URL: " + f.RepoURL())
+	tag, err := f.LatestTag(ctx)
-
-	//repo, err := git.Clone(memory.NewStorage(), nil, &git.CloneOptions{
-	//	URL:          .RepoURL(),
-	//	SingleBranch: true,
-	//	Depth:        CommitSearchDepth,
-	//})
-	repo, err := git.PlainOpen("~/git/listory")
 	if err != nil {
 		return err
 	}
 
-	commits, previousTag, err := rp.ReleasableCommits(repo)
+	logger.InfoContext(ctx, "Latest Tag", "tag.hash", tag.Hash, "tag.name", tag.Name)
+
+	releaseableCommits, err := f.CommitsSince(ctx, tag)
 	if err != nil {
 		return err
 	}
 
-	analyzedCommits, versionBump, err := rp.AnalyzeCommits(commits)
+	logger.InfoContext(ctx, "Found releasable commits", "length", len(releaseableCommits))
+
+	changesets, err := f.Changesets(ctx, releaseableCommits)
 	if err != nil {
 		return err
 	}
 
-	for _, commit := range analyzedCommits {
+	logger.InfoContext(ctx, "Found changesets", "length", len(changesets))
-		title, _, _ := strings.Cut(commit.Message, "\n")
+
-		fmt.Printf("%s %s\n", commit.Hash, title)
+	for _, changeset := range changesets {
+		fmt.Printf("%s %s\n", changeset.Identifier, changeset.URL)
+		for _, entry := range changeset.ChangelogEntries {
+			fmt.Printf("  - %s %s\n", entry.Hash, entry.Description)
+		}
 	}
-	fmt.Printf("Previous Tag: %s\n", previousTag.Name)
+	fmt.Printf("Previous Tag: %s\n", tag.Name)
-	fmt.Printf("Recommended Bump: %v\n", versionBump)
 
 	return nil
 }

forge.go

@@ -1,38 +1,231 @@
 package rp
 
 import (
+	"context"
 	"fmt"
+	"log/slog"
+
+	"github.com/google/go-github/v63/github"
 )
 
+type Changeset struct {
+	URL              string
+	Identifier       string
+	ChangelogEntries []AnalyzedCommit
+}
+
 type Forge interface {
 	RepoURL() string
+
+	// LatestTag returns the last tag created on the main branch. If no tag is found, it returns nil.
+	LatestTag(context.Context) (*Tag, error)
+
+	// CommitsSince returns all commits to main branch after the Tag. The tag can be `nil`, in which case this
+	// function should return all commits.
+	CommitsSince(context.Context, *Tag) ([]Commit, error)
+
+	// Changesets looks up the Pull/Merge Requests for each commit, returning its parsed metadata.
+	Changesets(context.Context, []Commit) ([]Changeset, error)
 }
 
 type ForgeOptions struct {
 	Repository string
+	BaseBranch string
 }
 
 var _ Forge = &GitHub{}
-var _ Forge = &GitLab{}
+
+// var _ Forge = &GitLab{}
 
 type GitHub struct {
-	options ForgeOptions
+	options *GitHubOptions
+
+	client *github.Client
+	log    *slog.Logger
 }
 
 func (g *GitHub) RepoURL() string {
 	return fmt.Sprintf("https://github.com/%s", g.options.Repository)
 }
 
-func (g *GitHub) autodiscover() {
+func (g *GitHub) LatestTag(ctx context.Context) (*Tag, error) {
-	// Read settings from GitHub Actions env vars
+	g.log.Debug("listing all tags in github repository")
-}
+	// We only get the first page because the latest tag is returned as the first item
-
+	tags, _, err := g.client.Repositories.ListTags(ctx, g.options.Owner, g.options.Repo, nil)
-func NewGitHub(options ForgeOptions) *GitHub {
+	if err != nil {
-	gh := &GitHub{
+		return nil, err
-		options: options,
 	}
 
-	gh.autodiscover()
+	if len(tags) > 0 {
+		// TODO: Is tags sorted?
+		tag := tags[0]
+		return &Tag{
+			Hash: tag.GetCommit().GetSHA(),
+			Name: tag.GetName(),
+		}, nil
+	}
+
+	return nil, nil
+}
+
+func (g *GitHub) CommitsSince(ctx context.Context, tag *Tag) ([]Commit, error) {
+	var repositoryCommits []*github.RepositoryCommit
+	var err error
+	if tag != nil {
+		repositoryCommits, err = g.commitsSinceTag(ctx, tag)
+	} else {
+		return nil, fmt.Errorf("not implemented")
+	}
+
+	if err != nil {
+		return nil, err
+	}
+
+	var commits = make([]Commit, 0, len(repositoryCommits))
+	for _, ghCommit := range repositoryCommits {
+		commits = append(commits, Commit{
+			Hash:    ghCommit.GetSHA(),
+			Message: ghCommit.GetCommit().GetMessage(),
+		})
+	}
+
+	return commits, nil
+}
+
+func (g *GitHub) commitsSinceTag(ctx context.Context, tag *Tag) ([]*github.RepositoryCommit, error) {
+	head := g.options.BaseBranch
+	log := g.log.With("base", tag.Hash, "head", head)
+	log.Debug("comparing commits", "base", tag.Hash, "head", head)
+
+	page := 1
+
+	var repositoryCommits []*github.RepositoryCommit
+	for {
+		log.Debug("fetching page", "page", page)
+		comparison, resp, err := g.client.Repositories.CompareCommits(
+			ctx, g.options.Owner, g.options.Repo,
+			tag.Hash, head, &github.ListOptions{
+				Page:    page,
+				PerPage: 100,
+			})
+		if err != nil {
+			return nil, err
+		}
+
+		if repositoryCommits == nil {
+			// Pre-initialize slice on first request
+			log.Debug("found commits", "length", comparison.GetTotalCommits())
+			repositoryCommits = make([]*github.RepositoryCommit, 0, comparison.GetTotalCommits())
+		}
+
+		repositoryCommits = append(repositoryCommits, comparison.Commits...)
+
+		if page == resp.LastPage || resp.LastPage == 0 {
+			break
+		}
+
+		page = resp.NextPage
+	}
+
+	return repositoryCommits, nil
+}
+
+func (g *GitHub) Changesets(ctx context.Context, commits []Commit) ([]Changeset, error) {
+	// We naively look up the associated PR for each commit through the "List pull requests associated with a commit"
+	// endpoint. This requires len(commits) requests.
+	// Using the "List pull requests" endpoint might be faster, as it allows us to fetch 100 arbitrary PRs per request,
+	// but worst case we need to look up all PRs made in the repository ever.
+
+	changesets := make([]Changeset, 0, len(commits))
+
+	for _, commit := range commits {
+		log := g.log.With("commit.hash", commit.Hash)
+		page := 1
+		var associatedPRs []*github.PullRequest
+
+		for {
+			log.Debug("fetching pull requests associated with commit", "page", page)
+			prs, resp, err := g.client.PullRequests.ListPullRequestsWithCommit(
+				ctx, g.options.Owner, g.options.Repo,
+				commit.Hash, &github.ListOptions{
+					Page:    page,
+					PerPage: 100,
+				})
+			if err != nil {
+				return nil, err
+			}
+
+			associatedPRs = append(associatedPRs, prs...)
+
+			if page == resp.LastPage || resp.LastPage == 0 {
+				break
+			}
+			page = resp.NextPage
+		}
+
+		var pullrequest *github.PullRequest
+		for _, pr := range associatedPRs {
+			// We only look for the PR that has this commit set as the "merge commit" => The result of squashing this branch onto main
+			if pr.GetMergeCommitSHA() == commit.Hash {
+				pullrequest = pr
+				break
+			}
+		}
+		if pullrequest == nil {
+			log.Warn("did not find associated pull request, not considering it for changesets")
+			// No pull request was found for this commit, nothing to do here
+			// TODO: We could also return the minimal changeset for this commit, so at least it would come up in the changelog.
+			continue
+		}
+
+		log = log.With("pullrequest.id", pullrequest.GetID())
+
+		// TODO: Parse PR description for overrides
+		changelogEntries, _, err := AnalyzeCommits([]Commit{commit})
+		if err != nil {
+			log.Warn("unable to parse changelog entries", "error", err)
+			continue
+		}
+
+		if len(changelogEntries) > 0 {
+			changesets = append(changesets, Changeset{
+				URL:              pullrequest.GetHTMLURL(),
+				Identifier:       fmt.Sprintf("#%d", pullrequest.GetNumber()),
+				ChangelogEntries: changelogEntries,
+			})
+		}
+	}
+
+	return changesets, nil
+}
+
+func (g *GitHubOptions) autodiscover() {
+	// TODO: Read settings from GitHub Actions env vars
+}
+
+type GitHubOptions struct {
+	ForgeOptions
+
+	Owner string
+	Repo  string
+
+	APIToken string
+}
+
+func NewGitHub(log *slog.Logger, options *GitHubOptions) *GitHub {
+	options.autodiscover()
+
+	client := github.NewClient(nil)
+	if options.APIToken != "" {
+		client = client.WithAuthToken(options.APIToken)
+	}
+
+	gh := &GitHub{
+		options: options,
+
+		client: client,
+		log:    log.With("forge", "github"),
+	}
 
 	return gh
 }

go.mod

@@ -5,6 +5,7 @@ go 1.22.4
 require (
 	github.com/go-git/go-billy/v5 v5.5.0
 	github.com/go-git/go-git/v5 v5.12.0
+	github.com/leodido/go-conventionalcommits v0.12.0
 	github.com/spf13/cobra v1.8.1
 	github.com/stretchr/testify v1.9.0
 )
@@ -19,12 +20,14 @@ require (
 	github.com/emirpasic/gods v1.18.1 // indirect
 	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
+	github.com/google/go-github/v63 v63.0.0 // indirect
+	github.com/google/go-querystring v1.1.0 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
 	github.com/kevinburke/ssh_config v1.2.0 // indirect
-	github.com/leodido/go-conventionalcommits v0.12.0 // indirect
 	github.com/pjbgf/sha1cd v0.3.0 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/rwtodd/Go.Sed v0.0.0-20230610052213-ba3e9c186f0a // indirect
 	github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect
 	github.com/sirupsen/logrus v1.9.3 // indirect
 	github.com/skeema/knownhosts v1.2.2 // indirect

go.sum

@@ -35,8 +35,13 @@ github.com/go-git/go-git/v5 v5.12.0 h1:7Md+ndsjrzZxbddRDZjF14qK+NN56sy6wkqaVrjZt
 github.com/go-git/go-git/v5 v5.12.0/go.mod h1:FTM9VKtnI2m65hNI/TenDDDnUf2Q9FHnXYjuz9i5OEY=
 github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
 github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/go-github/v63 v63.0.0 h1:13xwK/wk9alSokujB9lJkuzdmQuVn2QCPeck76wR3nE=
+github.com/google/go-github/v63 v63.0.0/go.mod h1:IqbcrgUmIcEaioWrGYei/09o+ge5vhffGOcxrO0AfmA=
+github.com/google/go-querystring v1.1.0 h1:AnCroh3fv4ZBgVIf1Iwtovgjaw/GiKJo8M8yD/fhyJ8=
+github.com/google/go-querystring v1.1.0/go.mod h1:Kcdr2DB4koayq7X8pmAG4sNG59So17icRSOU623lUBU=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
@@ -63,6 +68,8 @@ github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZN
 github.com/rogpeppe/go-internal v1.11.0 h1:cWPaGQEPrBb5/AsnsZesgZZ9yb1OQ+GOISoDNXVBh4M=
 github.com/rogpeppe/go-internal v1.11.0/go.mod h1:ddIwULY96R17DhadqLgMfk9H9tvdUzkipdSkR5nkCZA=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/rwtodd/Go.Sed v0.0.0-20230610052213-ba3e9c186f0a h1:URwYffGNuBQkfwkcn+1CZhb8IE/mKSXxPXp/zzQsn80=
+github.com/rwtodd/Go.Sed v0.0.0-20230610052213-ba3e9c186f0a/go.mod h1:c6qgHcSUeSISur4+Kcf3WYTvpL07S8eAsoP40hDiQ1I=
 github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 h1:n661drycOFuPLCN3Uc8sB6B/s6Z4t2xvBgU1htSHuq8=
 github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3/go.mod h1:A0bzQcvG0E7Rwjx0REVgAGH58e96+X0MeOfepqsbeW4=
 github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
@@ -146,6 +153,7 @@ golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
 golang.org/x/tools v0.13.0 h1:Iey4qkscZuv0VvIt8E0neZjtPVQFSc870HQ448QgEmQ=
 golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=