Skip to content

fix: anonymous vertex suppot for variable length pattern #783

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

Merged
SemyonSinchenko merged 1 commit into from
Jan 27, 2026
Merged

fix: anonymous vertex suppot for variable length pattern #783

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 5 additions & 3 deletions core/src/main/scala/org/graphframes/GraphFrame.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -469,8 +469,8 @@ class GraphFrame private (
* @group motif
*/
def find(pattern: String): DataFrame = {
val VarLengthPattern = """\((\w+)\)-\[(\w*)\*(\d*)\.\.(\d*)\]-(>?)\((\w+)\)""".r
val FixedLengthUndirectedPattern = """\((\w+)\)-\[(\w*)\*(\d*)\]-\((\w+)\)""".r
val VarLengthPattern = """\((\w*)\)-\[(\w*)\*(\d*)\.\.(\d*)\]-(>?)\((\w*)\)""".r
val FixedLengthUndirectedPattern = """\((\w*)\)-\[(\w*)\*(\d*)\]-\((\w*)\)""".r

pattern match {
case VarLengthPattern(src, name, min, max, direction, dst) =>
Expand Down Expand Up @@ -537,7 +537,9 @@ class GraphFrame private (
val augmentedPatterns = extraPositivePatterns ++ patterns
val df = findSimple(augmentedPatterns)

val names = Pattern.findNamedElementsInOrder(patterns, includeEdges = true)
val names = Pattern
.findNamedElementsInOrder(patterns, includeEdges = true)
.filter(x => !x.startsWith("__tmpv"))
if (names.isEmpty) df else df.select(quote(names.head), names.tail.map(quote): _*)
}

Expand Down
4 changes: 3 additions & 1 deletion core/src/main/scala/org/graphframes/pattern/patterns.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,9 @@ private[graphframes] object Pattern {
case fixedLengthPattern(negation, src, name, num, dst) =>
val hop: Int = num.toInt
if (hop > 0) {
val midVertices = (1 until hop).map(i => s"_${src}${dst}${i}")
val midVertices =
if (src.isEmpty && dst.isEmpty) (1 until hop).map(i => s"__tmpv${i}")
else (1 until hop).map(i => s"_${src}${dst}${i}")
val vertices = src +: midVertices :+ dst
vertices
.sliding(2)
Expand Down
15 changes: 15 additions & 0 deletions core/src/test/scala/org/graphframes/PatternMatchSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -798,6 +798,21 @@ class PatternMatchSuite extends SparkFunSuite with GraphFrameTestSparkContext {
assert(res.except(expected).isEmpty && expected.except(res).isEmpty)
}

test("undirected edge without vertex name") {
val res = g.find("()-[e*3]-()").drop("_pattern").collect().toSet
val expected =
g.find("(u)-[e*3]-(v)").select("_e1", "_e2", "_e3", "_hop", "_direction").collect().toSet

compareResultToExpected(res, expected)
}

test("directed edge name without vertex name") {
val res = g.find("()-[e*3]->()").collect().toSet
val expected = g.find("(u)-[e*3]->(v)").select("_e1", "_e2", "_e3").collect().toSet

compareResultToExpected(res, expected)
}

test("stateful predicates via UDFs") {
val chain4 = g
.find("(a)-[ab]->(b); (b)-[bc]->(c); (c)-[cd]->(d)")
Expand Down