Skip to content
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

fix simple url to download #61

Merged
merged 2 commits into from
Jun 19, 2023
Merged

fix simple url to download #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
568a1d1
fix simple url to download
ofilangi Jun 19, 2023
98ef609
update libs
ofilangi Jun 19, 2023
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
10 changes: 5 additions & 5 deletions build.sbt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,17 +51,17 @@ publishLocalConfiguration := publishLocalConfiguration.value.withOverwrite(true)
pomIncludeRepository := { _ => false }
publishMavenStyle := true

lazy val rdf4jVersion = "4.0.2"
lazy val slf4jVersion = "1.7.36"
lazy val uTestVersion = "0.7.11"
val sparkVersion = "3.1.3"
lazy val rdf4jVersion = "4.2.3"
lazy val slf4jVersion = "2.0.5"
lazy val uTestVersion = "0.8.1"
val sparkVersion = "3.3.2"

crossScalaVersions := supportedScalaVersions


libraryDependencies ++= Seq(
"org.apache.spark" %% "spark-sql" % sparkVersion % "provided,test",
"com.github.scopt" %% "scopt" % "4.0.1",
"com.github.scopt" %% "scopt" % "4.1.0",
"org.eclipse.rdf4j" % "rdf4j-storage" % rdf4jVersion,
"com.github.jsonld-java" % "jsonld-java" % "0.13.4",
"org.slf4j" % "slf4j-api" % slf4jVersion,
Expand Down
48 changes: 28 additions & 20 deletions src/main/scala/fr/inrae/metabolomics/services/ServiceRdfDatabaseDeployment.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,7 @@ case object ServiceRdfDatabaseDeployment extends App {
}

def buildScript(
files: Seq[String],
filesIn: Seq[String],
output: File,
category: String,
databaseName: String,
Expand All @@ -150,6 +150,7 @@ case object ServiceRdfDatabaseDeployment extends App {
startDate : String
): Unit = {

val files = filesIn.map(_.trim()).filter(_.nonEmpty).filter(_!="\\")
new File(output.getPath).delete()

val bw = new BufferedWriter(new FileWriter(new File(output.getPath)))
Expand All @@ -159,6 +160,7 @@ case object ServiceRdfDatabaseDeployment extends App {
val dirProvData = s"${rootPathDatabasesHdfsCluster}/prov/"
val wgetOpt = "--spider -nv -r -nd --no-parent -e robots=off"
bw.write("#!/bin/bash\n")
bw.write("set -e\n")

bw.write(s"$hdfs dfs -mkdir -p ${dirData}\n")
bw.write(s"$hdfs dfs -mkdir -p ${dirAskOmicsAbstraction}\n")
Expand All @@ -171,9 +173,16 @@ case object ServiceRdfDatabaseDeployment extends App {
).foreach(
x => {
/* get files names */
bw.write("FILES=$(wget "+s"$wgetOpt -A "+ "\"$(basename "+x+")\"" +
" $(dirname "+x+")/ 2>&1 | egrep \"200[[:blank:]]+OK$\" | awk '{print $4}')\n")

// only if joker "*." on the base name
if (x.split("/").lastOption.exists(_.contains("*"))) {
bw.write("## USING JOKER METHOD : " + x + "\n")
bw.write("FILES=$(wget " + s"$wgetOpt -A " + "\"$(basename " + x + ")\"" +
" $(dirname " + x + ")/ 2>&1 | egrep \"200[[:blank:]]+OK$\" | awk '{print $4}')\n")
bw.write("[ -z \"$FILES\" ] && echo \"Can not find FILES with the special character '*' " +
"and this url=" + x + "\" && exit 1\n")
} else {
bw.write("FILES=\""+x+"\"\n")
}
bw.write("for file in $FILES\n")
bw.write("do\n")
bw.write("if [ \"${file: -3}\" == \".gz\" ]; then\n")
Expand All @@ -188,27 +197,26 @@ case object ServiceRdfDatabaseDeployment extends App {
)

files.filter(
x => ! x.matches("^(http|https|ftp)://.*$")
).foreach(
x => x match {
case file if file.endsWith(".gz") => {
bw.write("file_expr=$(basename "+file+")\n")
bw.write("for file in $(ls $file_expr 2>/dev/null)\n")
bw.write("do\n")
bw.write("gunzip -c $file "+s"| $hdfs dfs -put - " +
s"${dirData}"+"/$(basename ${file%.gz})\n")
bw.write("done\n")
}
case _ => {
bw.write(s"$hdfs"+" dfs -put -f $(basename "+x+") "+s"${dirData}\n")
}
x => !x.matches("^(http|https|ftp)://.*$")
).foreach {
case file if file.endsWith(".gz") => {
bw.write("file_expr=$(basename " + file + ")\n")
bw.write("for file in $(ls $file_expr 2>/dev/null)\n")
bw.write("do\n")
bw.write("gunzip -c $file " + s"| $hdfs dfs -put - " +
s"${dirData}" + "/$(basename ${file%.gz})\n")
bw.write("done\n")
}
case x =>
bw.write(s"$hdfs" + " dfs -put -f $(basename " + x + ") " + s"${dirData}\n")

})
}

abstraction_askomics match {
abstraction_askomics.map(_.trim()).filter(_.nonEmpty) match {
case Some(file) if file.endsWith(".ttl") =>
if ( file.matches("^(http|https|ftp)://.*$"))
bw.write(s"wget $file\n")

bw.write(s"$hdfs dfs -put -f "+"$("+s"basename $file) " +
s"${dirAskOmicsAbstraction}/"+"$("+s"basename $file)\n")
case Some( f ) => System.err.println(s"Can not manage this Askomics extension file ${f}")
Expand Down