Skip to content

Filters by file size #201

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
merged 4 commits into from
Feb 19, 2019
Merged

Filters by file size #201

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8c02daa
Remove empty files from hashing
smacker Feb 15, 2019
bdffa62
Exclude very small files from similarity hashing
smacker Feb 15, 2019
f1131f5
apply file limit only in file-similarity mode
smacker Feb 19, 2019
62566ea
update test due to changed output of similarity
smacker Feb 19, 2019
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
21 changes: 18 additions & 3 deletions src/main/scala/tech/sourced/gemini/Hash.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@ import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.cassandra._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.functions.{udf => sparkUdf} // udf name conflicts with engine
import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession}
import org.apache.spark.storage.StorageLevel
import org.bblfsh.client.BblfshClient
Expand Down Expand Up @@ -42,6 +43,9 @@ class Hash(session: SparkSession,
mode: String = Gemini.fileSimilarityMode,
docFreqPath: String = "") {

// very small files produce too much false positives
val fileSizeThresholdBytes = 500

import session.implicits._

def report(header: String, countProcessed: Long, skipped: MapAccumulator): Unit = {
Expand Down Expand Up @@ -120,20 +124,31 @@ class Hash(session: SparkSession,
protected def filesForRepos(repos: DataFrame): DataFrame = {
log.warn("Listing files")

val fileSizeUdf = sparkUdf { (content: Array[Byte]) => content.size }

repos
.getHEAD
.getCommits
.getTreeEntries
.getBlobs
.filter(r => !Enry.isVendor(r.getAs[String]("path")))
.filter('is_binary === false)
.filter(r => !Enry.isVendor(r.getAs[String]("path")))
.withColumn("content_size", fileSizeUdf('content))
.filter('content_size !== 0) // empty files only pollute results
}

protected def extractUast(files: DataFrame): DataFrame = {
log.warn("Extracting UASTs")

files
.dropDuplicates("blob_id")
val blobs = files.dropDuplicates("blob_id")

val filteredBlobs = if (mode == Gemini.fileSimilarityMode) {
blobs.filter('content_size > fileSizeThresholdBytes)
} else {
blobs
}

filteredBlobs
.classifyLanguages
.filter('lang.isNotNull)
.extractUASTs
Expand Down
6 changes: 3 additions & 3 deletions src/test/scala/tech/sourced/gemini/ReportSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,12 +104,12 @@ class ReportSpec extends FlatSpec
val similarGroups = report.findSimilarItems("/tmp/report-files-test", Gemini.fileSimilarityMode)
println("Done")

similarGroups should have size 6
similarGroups should have size 7

val files = similarGroups.head.map(_.toString)
files.toSeq should contain theSameElementsAs Seq(
"https://github.com/erizocosmico/borges/blob/b1fcd3bf0ba810c05cb418babc09cc7f7783cc03/fixtures_test.go",
"https://github.com/src-d/borges/blob/e784f9d5f59d5c081c5f8f71b6c517918b899df0/fixtures_test.go"
"https://github.com/erizocosmico/borges/blob/b1fcd3bf0ba810c05cb418babc09cc7f7783cc03/consumer_test.go",
"https://github.com/src-d/borges/blob/e784f9d5f59d5c081c5f8f71b6c517918b899df0/consumer_test.go"
)
}

Expand Down