Skip to content

fix(parser): support non-standard SCM connection strings (fixes #1645) #1650

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
arnavsharma990 wants to merge 3 commits into
base: main
Choose a base branch
from
Open

fix(parser): support non-standard SCM connection strings (fixes #1645) #1650

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d646fe0
fix(parser): support non-standard SCM connection strings (fixes #1645)
arnavsharma990 Dec 1, 2025
dfc6be3
Remove commented RFC reference and update SCM URL parsing
arnavsharma990 Dec 2, 2025
b267622
Clean up comments in ScmInfoParserTests
arnavsharma990 Dec 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion modules/data/src/main/scala/scaladex/data/cleanup/GithubRepoExtractor.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ class GithubRepoExtractor(paths: DataPaths):
val fromPoms = pom.scm match
case Some(scm) =>
List(scm.connection, scm.developerConnection, scm.url).flatten
.flatMap(ScmInfoParser.parse)
.flatMap(ScmInfoParser.parseRawConnection)
.filter(g => !g.organization.isEmpty() && !g.repository.isEmpty())
case None => List()

Expand Down
3 changes: 1 addition & 2 deletions modules/data/src/main/scala/scaladex/data/cleanup/ScmInfoParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@ import fastparse.*
object ScmInfoParser extends Parsers:
import fastparse.NoWhitespace.*

// More info in Rfc3986
private def Unreserved[A: P] =
P(Alpha | Digit | "-".! | ".".! | "_".! | "~".!).!
private def Segment[A: P] = P(Unreserved | SubDelims | ":" | "@").!
Expand All @@ -26,7 +25,7 @@ object ScmInfoParser extends Parsers:
.! ~ "/" ~ Segment.rep(1).!.map(removeDotGit)
)

def parse(scmInfo: String): Option[Project.Reference] =
def parseRawConnection(scmInfo: String): Option[Project.Reference] =
fastparse.parse(scmInfo, x => ScmUrl(x)) match
case Parsed.Success((organization, repo), _) =>
Some(Project.Reference.from(organization, repo))
Expand Down
26 changes: 12 additions & 14 deletions modules/data/src/test/scala/scaladex/data/cleanup/ScmInfoParserTests.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,38 +7,36 @@ import org.scalatest.matchers.should.Matchers
class ScmInfoParserTests extends AnyFunSpec with Matchers:
describe("ScmInfoParse") {
it("correctly parse valid SCM strings") {
// Implicit protocol
ScmInfoParser
.parse("scm:git:git@github.com:foobarbuz/example.git")
.parseRawConnection("scm:git:git@github.com:foobarbuz/example.git")
.map(_.toString) shouldBe Some("foobarbuz/example")
// HTTPS
ScmInfoParser
.parse("scm:https://github.com/foobarbuz/example.git")
.parseRawConnection("scm:https://github.com/foobarbuz/example.git")
.map(_.toString) shouldBe Some("foobarbuz/example")
ScmInfoParser
.parse("scm:https://github.com/foobarbuz/example")
.parseRawConnection("scm:https://github.com/foobarbuz/example")
.map(_.toString) shouldBe Some("foobarbuz/example")
// Git
ScmInfoParser
.parse("scm:git:git://github.com:foobarbuz/example.git")
.parseRawConnection("scm:git:git://github.com:foobarbuz/example.git")
.map(_.toString) shouldBe Some("foobarbuz/example")
ScmInfoParser
.parse("scm:git://github.com:foobarbuz/example.git")
.parseRawConnection("scm:git://github.com:foobarbuz/example.git")
.map(_.toString) shouldBe Some("foobarbuz/example")
// SSH
ScmInfoParser
.parse("scm:git:ssh://git@github.com:foobarbuz/example.git")
.parseRawConnection("scm:git:ssh://git@github.com:foobarbuz/example.git")
.map(_.toString) shouldBe Some("foobarbuz/example")
ScmInfoParser
.parse("scm:git:ssh://github.com:foobarbuz/example.git")
.parseRawConnection("scm:git:ssh://github.com:foobarbuz/example.git")
.map(_.toString) shouldBe Some("foobarbuz/example")
// Unknown protocol
ScmInfoParser
.parse("scm:git:unknown://git@github.com:foobarbuz/example.git")
.parseRawConnection("scm:git:unknown://git@github.com:foobarbuz/example.git")
.map(_.toString) shouldBe None
ScmInfoParser
.parse("scm:git:unknown://github.com:foobarbuz/example.git")
.parseRawConnection("scm:git:unknown://github.com:foobarbuz/example.git")
.map(_.toString) shouldBe None
ScmInfoParser
.parseRawConnection("scm:git@github.com:mghmay/play-json-shaper.git")
.map(_.toString) shouldBe Some("mghmay/play-json-shaper")
}
}
end ScmInfoParserTests