You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by gu...@apache.org on 2020/05/03 03:44:12 UTC
[spark] branch branch-3.0 updated: [SPARK-31571][R] Overhaul
stop/message/warning calls to be more canonical
This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch branch-3.0
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.0 by this push:
new 9c101e9 [SPARK-31571][R] Overhaul stop/message/warning calls to be more canonical
9c101e9 is described below
commit 9c101e982bb990a4b9297460f42f4f48a9be6f50
Author: Michael Chirico <mi...@grabtaxi.com>
AuthorDate: Sun May 3 12:40:20 2020 +0900
[SPARK-31571][R] Overhaul stop/message/warning calls to be more canonical
### What changes were proposed in this pull request?
Internal usages like `{stop,warning,message}({paste,paste0,sprintf}` and `{stop,warning,message}(some_literal_string_as_variable` have been removed and replaced as appropriate.
### Why are the changes needed?
CRAN policy recommends against using such constructions to build error messages, in particular because it makes the process of creating portable error messages for the package more onerous.
### Does this PR introduce any user-facing change?
There may be some small grammatical changes visible in error messaging.
### How was this patch tested?
Not done
Closes #28365 from MichaelChirico/r-stop-paste.
Authored-by: Michael Chirico <mi...@grabtaxi.com>
Signed-off-by: HyukjinKwon <gu...@apache.org>
(cherry picked from commit f53d8c63e80172295e2fbc805c0c391bdececcaa)
Signed-off-by: HyukjinKwon <gu...@apache.org>
---
R/pkg/R/DataFrame.R | 40 +++++++++++-----------
R/pkg/R/RDD.R | 2 +-
R/pkg/R/SQLContext.R | 17 +++++-----
R/pkg/R/client.R | 7 ++--
R/pkg/R/context.R | 8 ++---
R/pkg/R/deserialize.R | 2 +-
R/pkg/R/group.R | 4 +--
R/pkg/R/install.R | 62 +++++++++++++++--------------------
R/pkg/R/mllib_classification.R | 4 +--
R/pkg/R/mllib_stat.R | 3 +-
R/pkg/R/pairRDD.R | 2 +-
R/pkg/R/schema.R | 2 +-
R/pkg/R/serialize.R | 4 +--
R/pkg/R/sparkR.R | 9 ++---
R/pkg/R/utils.R | 53 +++++++++++++++---------------
R/pkg/tests/fulltests/test_sparkSQL.R | 2 +-
16 files changed, 103 insertions(+), 118 deletions(-)
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index 09e8318..15b3ce2 100644
--- a/R/pkg/R/DataFrame.R
+++ b/R/pkg/R/DataFrame.R
@@ -431,7 +431,7 @@ setMethod("coltypes",
if (is.null(type)) {
specialtype <- specialtypeshandle(x)
if (is.null(specialtype)) {
- stop(paste("Unsupported data type: ", x))
+ stop("Unsupported data type: ", x)
}
type <- PRIMITIVE_TYPES[[specialtype]]
}
@@ -829,8 +829,8 @@ setMethod("repartitionByRange",
jcol <- lapply(cols, function(c) { c@jc })
sdf <- callJMethod(x@sdf, "repartitionByRange", numToInt(numPartitions), jcol)
} else {
- stop(paste("numPartitions and col must be numeric and Column; however, got",
- class(numPartitions), "and", class(col)))
+ stop("numPartitions and col must be numeric and Column; however, got ",
+ class(numPartitions), " and ", class(col))
}
} else if (!is.null(col)) {
# only columns are specified
@@ -839,7 +839,7 @@ setMethod("repartitionByRange",
jcol <- lapply(cols, function(c) { c@jc })
sdf <- callJMethod(x@sdf, "repartitionByRange", jcol)
} else {
- stop(paste("col must be Column; however, got", class(col)))
+ stop("col must be Column; however, got ", class(col))
}
} else if (!is.null(numPartitions)) {
# only numPartitions is specified
@@ -1068,10 +1068,10 @@ setMethod("sample",
signature(x = "SparkDataFrame"),
function(x, withReplacement = FALSE, fraction, seed) {
if (!is.numeric(fraction)) {
- stop(paste("fraction must be numeric; however, got", class(fraction)))
+ stop("fraction must be numeric; however, got ", class(fraction))
}
if (!is.logical(withReplacement)) {
- stop(paste("withReplacement must be logical; however, got", class(withReplacement)))
+ stop("withReplacement must be logical; however, got ", class(withReplacement))
}
if (!missing(seed)) {
@@ -1211,11 +1211,10 @@ setMethod("collect",
checkSchemaInArrow(schema(x))
TRUE
}, error = function(e) {
- warning(paste0("The conversion from Spark DataFrame to R DataFrame was attempted ",
- "with Arrow optimization because ",
- "'spark.sql.execution.arrow.sparkr.enabled' is set to true; ",
- "however, failed, attempting non-optimization. Reason: ",
- e))
+ warning("The conversion from Spark DataFrame to R DataFrame was attempted ",
+ "with Arrow optimization because ",
+ "'spark.sql.execution.arrow.sparkr.enabled' is set to true; ",
+ "however, failed, attempting non-optimization. Reason: ", e)
FALSE
})
}
@@ -1508,8 +1507,8 @@ dapplyInternal <- function(x, func, schema) {
if (inherits(schema, "structType")) {
checkSchemaInArrow(schema)
} else if (is.null(schema)) {
- stop(paste0("Arrow optimization does not support 'dapplyCollect' yet. Please disable ",
- "Arrow optimization or use 'collect' and 'dapply' APIs instead."))
+ stop("Arrow optimization does not support 'dapplyCollect' yet. Please disable ",
+ "Arrow optimization or use 'collect' and 'dapply' APIs instead.")
} else {
stop("'schema' should be DDL-formatted string or structType.")
}
@@ -2012,8 +2011,8 @@ setMethod("[", signature(x = "SparkDataFrame"),
x
} else {
if (class(i) != "Column") {
- stop(paste0("Expressions other than filtering predicates are not supported ",
- "in the first parameter of extract operator [ or subset() method."))
+ stop("Expressions other than filtering predicates are not supported ",
+ "in the first parameter of extract operator [ or subset() method.")
}
filter(x, i)
}
@@ -2604,18 +2603,17 @@ setMethod("join",
if (is.null(joinType)) {
sdf <- callJMethod(x@sdf, "join", y@sdf, joinExpr@jc)
} else {
- if (joinType %in% c("inner", "cross",
+ validJoinTypes <- c("inner", "cross",
"outer", "full", "fullouter", "full_outer",
"left", "leftouter", "left_outer",
"right", "rightouter", "right_outer",
- "semi", "left_semi", "leftsemi", "anti", "left_anti", "leftanti")) {
+ "semi", "leftsemi", "left_semi", "anti", "leftanti", "left_anti")
+ if (joinType %in% validJoinTypes) {
joinType <- gsub("_", "", joinType, fixed = TRUE)
sdf <- callJMethod(x@sdf, "join", y@sdf, joinExpr@jc, joinType)
} else {
- stop(paste("joinType must be one of the following types:",
- "'inner', 'cross', 'outer', 'full', 'fullouter', 'full_outer',",
- "'left', 'leftouter', 'left_outer', 'right', 'rightouter', 'right_outer',",
- "'semi', 'leftsemi', 'left_semi', 'anti', 'leftanti' or 'left_anti'."))
+ stop("joinType must be one of the following types: ",
+ "'", paste(validJoinTypes, collapse = "', '"), "'")
}
}
}
diff --git a/R/pkg/R/RDD.R b/R/pkg/R/RDD.R
index 7ee725d..7a1d157 100644
--- a/R/pkg/R/RDD.R
+++ b/R/pkg/R/RDD.R
@@ -947,7 +947,7 @@ setMethod("takeSample", signature(x = "RDD", withReplacement = "logical",
MAXINT <- .Machine$integer.max
if (num < 0)
- stop(paste("Negative number of elements requested"))
+ stop("Negative number of elements requested")
if (initialCount > MAXINT - 1) {
maxSelected <- MAXINT - 1
diff --git a/R/pkg/R/SQLContext.R b/R/pkg/R/SQLContext.R
index 1ef2641..c0ac683 100644
--- a/R/pkg/R/SQLContext.R
+++ b/R/pkg/R/SQLContext.R
@@ -34,7 +34,7 @@ getInternalType <- function(x) {
Date = "date",
POSIXlt = "timestamp",
POSIXct = "timestamp",
- stop(paste("Unsupported type for SparkDataFrame:", class(x))))
+ stop("Unsupported type for SparkDataFrame: ", class(x)))
}
#' return the SparkSession
@@ -112,9 +112,9 @@ sparkR.conf <- function(key, defaultValue) {
error = function(e) {
estr <- as.character(e)
if (any(grepl("java.util.NoSuchElementException", estr, fixed = TRUE))) {
- stop(paste0("Config '", key, "' is not set"))
+ stop("Config '", key, "' is not set")
} else {
- stop(paste0("Unknown error: ", estr))
+ stop("Unknown error: ", estr)
}
})
} else {
@@ -208,7 +208,7 @@ getSchema <- function(schema, firstRow = NULL, rdd = NULL) {
names <- lapply(names, function(n) {
nn <- gsub(".", "_", n, fixed = TRUE)
if (nn != n) {
- warning(paste("Use", nn, "instead of", n, "as column name"))
+ warning("Use ", nn, " instead of ", n, " as column name")
}
nn
})
@@ -290,10 +290,9 @@ createDataFrame <- function(data, schema = NULL, samplingRatio = 1.0,
TRUE
},
error = function(e) {
- warning(paste0("createDataFrame attempted Arrow optimization because ",
- "'spark.sql.execution.arrow.sparkr.enabled' is set to true; however, ",
- "failed, attempting non-optimization. Reason: ",
- e))
+ warning("createDataFrame attempted Arrow optimization because ",
+ "'spark.sql.execution.arrow.sparkr.enabled' is set to true; however, ",
+ "failed, attempting non-optimization. Reason: ", e)
FALSE
})
}
@@ -326,7 +325,7 @@ createDataFrame <- function(data, schema = NULL, samplingRatio = 1.0,
} else if (inherits(data, "RDD")) {
rdd <- data
} else {
- stop(paste("unexpected type:", class(data)))
+ stop("unexpected type: ", class(data))
}
schema <- getSchema(schema, firstRow, rdd)
diff --git a/R/pkg/R/client.R b/R/pkg/R/client.R
index 872b214..797a5c7 100644
--- a/R/pkg/R/client.R
+++ b/R/pkg/R/client.R
@@ -102,10 +102,9 @@ checkJavaVersion <- function() {
javaVersionNum <- as.integer(versions[1])
}
if (javaVersionNum < minJavaVersion || javaVersionNum >= maxJavaVersion) {
- stop(paste0("Java version, greater than or equal to ", minJavaVersion,
- " and less than ", maxJavaVersion,
- ", is required for this package; found version: ",
- javaVersionStr))
+ stop("Java version, greater than or equal to ", minJavaVersion,
+ " and less than ", maxJavaVersion, ", is required for this ",
+ "package; found version: ", javaVersionStr)
}
return(javaVersionNum)
}
diff --git a/R/pkg/R/context.R b/R/pkg/R/context.R
index d96a287..e3c9d9f 100644
--- a/R/pkg/R/context.R
+++ b/R/pkg/R/context.R
@@ -144,13 +144,13 @@ parallelize <- function(sc, coll, numSlices = 1) {
if ((!is.list(coll) && !is.vector(coll)) || is.data.frame(coll)) {
# nolint end
if (is.data.frame(coll)) {
- message(paste("context.R: A data frame is parallelized by columns."))
+ message("context.R: A data frame is parallelized by columns.")
} else {
if (is.matrix(coll)) {
- message(paste("context.R: A matrix is parallelized by elements."))
+ message("context.R: A matrix is parallelized by elements.")
} else {
- message(paste("context.R: parallelize() currently only supports lists and vectors.",
- "Calling as.list() to coerce coll into a list."))
+ message("context.R: parallelize() currently only supports lists and vectors. ",
+ "Calling as.list() to coerce coll into a list.")
}
}
coll <- as.list(coll)
diff --git a/R/pkg/R/deserialize.R b/R/pkg/R/deserialize.R
index ca4a6e3..3e7c456 100644
--- a/R/pkg/R/deserialize.R
+++ b/R/pkg/R/deserialize.R
@@ -57,7 +57,7 @@ readTypedObject <- function(con, type) {
"s" = readStruct(con),
"n" = NULL,
"j" = getJobj(readString(con)),
- stop(paste("Unsupported type for deserialization", type)))
+ stop("Unsupported type for deserialization ", type))
}
readStringData <- function(con, len) {
diff --git a/R/pkg/R/group.R b/R/pkg/R/group.R
index 2b7995e..99d6224 100644
--- a/R/pkg/R/group.R
+++ b/R/pkg/R/group.R
@@ -234,8 +234,8 @@ gapplyInternal <- function(x, func, schema) {
if (inherits(schema, "structType")) {
checkSchemaInArrow(schema)
} else if (is.null(schema)) {
- stop(paste0("Arrow optimization does not support 'gapplyCollect' yet. Please disable ",
- "Arrow optimization or use 'collect' and 'gapply' APIs instead."))
+ stop("Arrow optimization does not support 'gapplyCollect' yet. Please disable ",
+ "Arrow optimization or use 'collect' and 'gapply' APIs instead.")
} else {
stop("'schema' should be DDL-formatted string or structType.")
}
diff --git a/R/pkg/R/install.R b/R/pkg/R/install.R
index 8c5355a..ea2c0b4 100644
--- a/R/pkg/R/install.R
+++ b/R/pkg/R/install.R
@@ -89,8 +89,8 @@ install.spark <- function(hadoopVersion = "2.7", mirrorUrl = NULL,
}
if (overwrite) {
- message(paste0("Overwrite = TRUE: download and overwrite the tar file",
- "and Spark package directory if they exist."))
+ message("Overwrite = TRUE: download and overwrite the tar file",
+ "and Spark package directory if they exist.")
}
releaseUrl <- Sys.getenv("SPARKR_RELEASE_DOWNLOAD_URL")
@@ -103,12 +103,11 @@ install.spark <- function(hadoopVersion = "2.7", mirrorUrl = NULL,
# can use dir.exists(packageLocalDir) under R 3.2.0 or later
if (!is.na(file.info(packageLocalDir)$isdir) && !overwrite) {
if (releaseUrl != "") {
- message(paste(packageName, "found, setting SPARK_HOME to", packageLocalDir))
+ message(packageName, " found, setting SPARK_HOME to ", packageLocalDir)
} else {
- fmt <- "%s for Hadoop %s found, setting SPARK_HOME to %s"
- msg <- sprintf(fmt, version, ifelse(hadoopVersion == "without", "Free build", hadoopVersion),
- packageLocalDir)
- message(msg)
+ message(version, " for Hadoop ",
+ if (hadoopVersion == "without") "Free build" else hadoopVersion,
+ " found, setting SPARK_HOME to ", packageLocalDir)
}
Sys.setenv(SPARK_HOME = packageLocalDir)
return(invisible(packageLocalDir))
@@ -127,26 +126,23 @@ install.spark <- function(hadoopVersion = "2.7", mirrorUrl = NULL,
success <- downloadUrl(releaseUrl, packageLocalPath)
if (!success) {
unlink(packageLocalPath)
- stop(paste0("Fetch failed from ", releaseUrl))
+ stop("Fetch failed from ", releaseUrl)
}
} else {
robustDownloadTar(mirrorUrl, version, hadoopVersion, packageName, packageLocalPath)
}
}
- message(sprintf("Installing to %s", localDir))
+ message("Installing to ", localDir)
# There are two ways untar can fail - untar could stop() on errors like incomplete block on file
# or, tar command can return failure code
success <- tryCatch(untar(tarfile = packageLocalPath, exdir = localDir) == 0,
error = function(e) {
- message(e)
- message()
+ message(e, "\n")
FALSE
},
warning = function(w) {
- # Treat warning as error, add an empty line with message()
- message(w)
- message()
+ message(w, "\n")
FALSE
})
if (!tarExists || overwrite || !success) {
@@ -160,7 +156,7 @@ install.spark <- function(hadoopVersion = "2.7", mirrorUrl = NULL,
if (!success) stop("Extract archive failed.")
message("DONE.")
Sys.setenv(SPARK_HOME = packageLocalDir)
- message(paste("SPARK_HOME set to", packageLocalDir))
+ message("SPARK_HOME set to ", packageLocalDir)
invisible(packageLocalDir)
}
@@ -173,7 +169,7 @@ robustDownloadTar <- function(mirrorUrl, version, hadoopVersion, packageName, pa
if (success) {
return()
} else {
- message(paste0("Unable to download from mirrorUrl: ", mirrorUrl))
+ message("Unable to download from mirrorUrl: ", mirrorUrl)
}
} else {
message("MirrorUrl not provided.")
@@ -201,11 +197,9 @@ robustDownloadTar <- function(mirrorUrl, version, hadoopVersion, packageName, pa
# remove any partially downloaded file
unlink(packageLocalPath)
message("Unable to download from default mirror site: ", mirrorUrl)
- msg <- sprintf(paste("Unable to download Spark %s for Hadoop %s.",
- "Please check network connection, Hadoop version,",
- "or provide other mirror sites."),
- version, ifelse(hadoopVersion == "without", "Free build", hadoopVersion))
- stop(msg)
+ stop("Unable to download Spark ", version,
+ " for Hadoop ", if (hadoopVersion == "without") "Free build" else hadoopVersion,
+ ". Please check network connection, Hadoop version, or provide other mirror sites.")
}
}
@@ -222,7 +216,7 @@ getPreferredMirror <- function(version, packageName) {
endPos <- matchInfo + attr(matchInfo, "match.length") - 2
mirrorPreferred <- base::substr(linePreferred, startPos, endPos)
mirrorPreferred <- paste0(mirrorPreferred, "spark")
- message(sprintf("Preferred mirror site found: %s", mirrorPreferred))
+ message("Preferred mirror site found: ", mirrorPreferred)
} else {
mirrorPreferred <- NULL
}
@@ -231,24 +225,20 @@ getPreferredMirror <- function(version, packageName) {
directDownloadTar <- function(mirrorUrl, version, hadoopVersion, packageName, packageLocalPath) {
packageRemotePath <- paste0(file.path(mirrorUrl, version, packageName), ".tgz")
- fmt <- "Downloading %s for Hadoop %s from:\n- %s"
- msg <- sprintf(fmt, version, ifelse(hadoopVersion == "without", "Free build", hadoopVersion),
- packageRemotePath)
- message(msg)
+ message("Downloading ", version, " for Hadoop ",
+ if (hadoopVersion == "without") "Free build" else hadoopVersion,
+ " from:\n- ", packageRemotePath)
downloadUrl(packageRemotePath, packageLocalPath)
}
downloadUrl <- function(remotePath, localPath) {
isFail <- tryCatch(download.file(remotePath, localPath),
error = function(e) {
- message(e)
- message()
+ message(e, "\n")
TRUE
},
warning = function(w) {
- # Treat warning as error, add an empty line with message()
- message(w)
- message()
+ message(w, "\n")
TRUE
})
!isFail
@@ -279,9 +269,9 @@ sparkCachePath <- function() {
winAppPath <- Sys.getenv("USERPROFILE", unset = NA)
}
if (is.na(winAppPath)) {
- stop(paste("%LOCALAPPDATA% and %USERPROFILE% not found.",
- "Please define the environment variable",
- "or restart and enter an installation path in localDir."))
+ stop("%LOCALAPPDATA% and %USERPROFILE% not found. ",
+ "Please define the environment variable ",
+ "or restart and enter an installation path in localDir.")
} else {
path <- file.path(winAppPath, "Apache", "Spark", "Cache")
}
@@ -293,7 +283,7 @@ sparkCachePath <- function() {
Sys.getenv("XDG_CACHE_HOME", file.path(Sys.getenv("HOME"), ".cache")), "spark")
}
} else {
- stop(sprintf("Unknown OS: %s", .Platform$OS.type))
+ stop("Unknown OS: ", .Platform$OS.type)
}
normalizePath(path, mustWork = FALSE)
}
@@ -322,7 +312,7 @@ installInstruction <- function(mode) {
"If you need further help, ",
"contact the administrators of the cluster.")
} else {
- stop(paste0("No instruction found for ", mode, " mode."))
+ stop("No instruction found for mode ", mode)
}
}
diff --git a/R/pkg/R/mllib_classification.R b/R/pkg/R/mllib_classification.R
index 1af81f8..53c9775 100644
--- a/R/pkg/R/mllib_classification.R
+++ b/R/pkg/R/mllib_classification.R
@@ -331,8 +331,8 @@ setMethod("spark.logit", signature(data = "SparkDataFrame", formula = "formula")
if (!is.null(lowerBoundsOnCoefficients) && (row != nrow(upperBoundsOnCoefficients)
|| col != ncol(upperBoundsOnCoefficients))) {
- stop(paste0("dimension of upperBoundsOnCoefficients ",
- "is not the same as lowerBoundsOnCoefficients"))
+ stop("dimension of upperBoundsOnCoefficients ",
+ "is not the same as lowerBoundsOnCoefficients")
}
if (is.null(lowerBoundsOnCoefficients)) {
diff --git a/R/pkg/R/mllib_stat.R b/R/pkg/R/mllib_stat.R
index f8c3329..6db4d5d 100644
--- a/R/pkg/R/mllib_stat.R
+++ b/R/pkg/R/mllib_stat.R
@@ -69,8 +69,7 @@ setMethod("spark.kstest", signature(data = "SparkDataFrame"),
function(data, testCol = "test", nullHypothesis = c("norm"), distParams = c(0, 1)) {
tryCatch(match.arg(nullHypothesis),
error = function(e) {
- msg <- paste("Distribution", nullHypothesis, "is not supported.")
- stop(msg)
+ stop("Distribution ", nullHypothesis, " is not supported.")
})
if (nullHypothesis == "norm") {
distParams <- as.numeric(distParams)
diff --git a/R/pkg/R/pairRDD.R b/R/pkg/R/pairRDD.R
index 9c2e57d..b29381b 100644
--- a/R/pkg/R/pairRDD.R
+++ b/R/pkg/R/pairRDD.R
@@ -906,7 +906,7 @@ setMethod("sampleByKey",
for (elem in fractions) {
if (elem < 0.0) {
- stop(paste("Negative fraction value ", fractions[which(fractions == elem)]))
+ stop("Negative fraction value ", fractions[which(fractions == elem)])
}
}
diff --git a/R/pkg/R/schema.R b/R/pkg/R/schema.R
index 89d5c2c..7044ede 100644
--- a/R/pkg/R/schema.R
+++ b/R/pkg/R/schema.R
@@ -199,7 +199,7 @@ checkType <- function(type) {
})
}
- stop(paste("Unsupported type for SparkDataframe:", type))
+ stop("Unsupported type for SparkDataframe: ", type)
}
#' @param type The data type of the field
diff --git a/R/pkg/R/serialize.R b/R/pkg/R/serialize.R
index cb3c1c5..7760d9b 100644
--- a/R/pkg/R/serialize.R
+++ b/R/pkg/R/serialize.R
@@ -84,7 +84,7 @@ writeObject <- function(con, object, writeType = TRUE) {
Date = writeDate(con, object),
POSIXlt = writeTime(con, object),
POSIXct = writeTime(con, object),
- stop(paste("Unsupported type for serialization", type)))
+ stop("Unsupported type for serialization ", type))
}
writeVoid <- function(con) {
@@ -158,7 +158,7 @@ writeType <- function(con, class) {
Date = "D",
POSIXlt = "t",
POSIXct = "t",
- stop(paste("Unsupported type for serialization", class)))
+ stop("Unsupported type for serialization ", class))
writeBin(charToRaw(type), con)
}
diff --git a/R/pkg/R/sparkR.R b/R/pkg/R/sparkR.R
index 9ba36ad..e4a11a5 100644
--- a/R/pkg/R/sparkR.R
+++ b/R/pkg/R/sparkR.R
@@ -154,8 +154,8 @@ sparkR.sparkContext <- function(
connectionTimeout <- as.numeric(Sys.getenv("SPARKR_BACKEND_CONNECTION_TIMEOUT", "6000"))
if (existingPort != "") {
if (length(packages) != 0) {
- warning(paste("sparkPackages has no effect when using spark-submit or sparkR shell",
- " please use the --packages commandline instead", sep = ","))
+ warning("sparkPackages has no effect when using spark-submit or sparkR shell, ",
+ "please use the --packages commandline instead")
}
backendPort <- existingPort
authSecret <- Sys.getenv("SPARKR_BACKEND_AUTH_SECRET")
@@ -439,8 +439,9 @@ sparkR.session <- function(
rPackageVersion <- paste0(packageVersion("SparkR"))
if (jvmVersionStrip != rPackageVersion) {
- warning(paste("Version mismatch between Spark JVM and SparkR package. JVM version was",
- jvmVersion, ", while R package version was", rPackageVersion))
+ warning("Version mismatch between Spark JVM and SparkR package. ",
+ "JVM version was ", jvmVersion,
+ ", while R package version was ", rPackageVersion)
}
sparkSession
diff --git a/R/pkg/R/utils.R b/R/pkg/R/utils.R
index c60e4db..65db9c2 100644
--- a/R/pkg/R/utils.R
+++ b/R/pkg/R/utils.R
@@ -46,9 +46,9 @@ convertJListToRList <- function(jList, flatten, logicalUpperBound = NULL,
res <- list(unserialize(keyBytes),
unserialize(valBytes))
} else {
- stop(paste("utils.R: convertJListToRList only supports",
- "RDD[Array[Byte]] and",
- "JavaPairRDD[Array[Byte], Array[Byte]] for now"))
+ stop("utils.R: convertJListToRList only supports ",
+ "RDD[Array[Byte]] and ",
+ "JavaPairRDD[Array[Byte], Array[Byte]] for now")
}
} else {
if (inherits(obj, "raw")) {
@@ -354,8 +354,8 @@ varargsToStrEnv <- function(...) {
} else {
value <- pairs[[name]]
if (!(is.logical(value) || is.numeric(value) || is.character(value) || is.null(value))) {
- stop(paste0("Unsupported type for ", name, " : ", class(value),
- ". Supported types are logical, numeric, character and NULL."), call. = FALSE)
+ stop("Unsupported type for ", name, " : ", toString(class(value)), ". ",
+ "Supported types are logical, numeric, character and NULL.", call. = FALSE)
}
if (is.logical(value)) {
env[[name]] <- tolower(as.character(value))
@@ -369,8 +369,7 @@ varargsToStrEnv <- function(...) {
}
if (length(ignoredNames) != 0) {
- warning(paste0("Unnamed arguments ignored: ", paste(ignoredNames, collapse = ", "), "."),
- call. = FALSE)
+ warning("Unnamed arguments ignored: ", toString(ignoredNames), ".", call. = FALSE)
}
env
}
@@ -449,7 +448,7 @@ storageLevelToString <- function(levelObj) {
# the user to type (for example) `5` instead of `5L` to avoid a confusing error message.
numToInt <- function(num) {
if (as.integer(num) != num) {
- warning(paste("Coercing", as.list(sys.call())[[2]], "to integer."))
+ warning("Coercing ", as.list(sys.call())[[2L]], " to integer.")
}
as.integer(num)
}
@@ -650,8 +649,8 @@ mergePartitions <- function(rdd, zip) {
# For zip operation, check if corresponding partitions
# of both RDDs have the same number of elements.
if (zip && lengthOfKeys != lengthOfValues) {
- stop(paste("Can only zip RDDs with same number of elements",
- "in each pair of corresponding partitions."))
+ stop("Can only zip RDDs with same number of elements ",
+ "in each pair of corresponding partitions.")
}
if (lengthOfKeys > 1) {
@@ -804,7 +803,7 @@ handledCallJMethod <- function(obj, method, ...) {
captureJVMException <- function(e, method) {
rawmsg <- as.character(e)
- if (any(grep("^Error in .*?: ", rawmsg))) {
+ if (any(grepl("^Error in .*?: ", rawmsg))) {
# If the exception message starts with "Error in ...", this is possibly
# "Error in invokeJava(...)". Here, it replaces the characters to
# `paste("Error in", method, ":")` in order to identify which function
@@ -818,58 +817,58 @@ captureJVMException <- function(e, method) {
}
# StreamingQueryException could wrap an IllegalArgumentException, so look for that first
- if (any(grep("org.apache.spark.sql.streaming.StreamingQueryException: ",
- stacktrace, fixed = TRUE))) {
+ if (any(grepl("org.apache.spark.sql.streaming.StreamingQueryException: ",
+ stacktrace, fixed = TRUE))) {
msg <- strsplit(stacktrace, "org.apache.spark.sql.streaming.StreamingQueryException: ",
fixed = TRUE)[[1]]
# Extract "Error in ..." message.
rmsg <- msg[1]
# Extract the first message of JVM exception.
first <- strsplit(msg[2], "\r?\n\tat")[[1]][1]
- stop(paste0(rmsg, "streaming query error - ", first), call. = FALSE)
- } else if (any(grep("java.lang.IllegalArgumentException: ", stacktrace, fixed = TRUE))) {
+ stop(rmsg, "streaming query error - ", first, call. = FALSE)
+ } else if (any(grepl("java.lang.IllegalArgumentException: ", stacktrace, fixed = TRUE))) {
msg <- strsplit(stacktrace, "java.lang.IllegalArgumentException: ", fixed = TRUE)[[1]]
# Extract "Error in ..." message.
rmsg <- msg[1]
# Extract the first message of JVM exception.
first <- strsplit(msg[2], "\r?\n\tat")[[1]][1]
- stop(paste0(rmsg, "illegal argument - ", first), call. = FALSE)
- } else if (any(grep("org.apache.spark.sql.AnalysisException: ", stacktrace, fixed = TRUE))) {
+ stop(rmsg, "illegal argument - ", first, call. = FALSE)
+ } else if (any(grepl("org.apache.spark.sql.AnalysisException: ", stacktrace, fixed = TRUE))) {
msg <- strsplit(stacktrace, "org.apache.spark.sql.AnalysisException: ", fixed = TRUE)[[1]]
# Extract "Error in ..." message.
rmsg <- msg[1]
# Extract the first message of JVM exception.
first <- strsplit(msg[2], "\r?\n\tat")[[1]][1]
- stop(paste0(rmsg, "analysis error - ", first), call. = FALSE)
+ stop(rmsg, "analysis error - ", first, call. = FALSE)
} else
- if (any(grep("org.apache.spark.sql.catalyst.analysis.NoSuchDatabaseException: ",
- stacktrace, fixed = TRUE))) {
+ if (any(grepl("org.apache.spark.sql.catalyst.analysis.NoSuchDatabaseException: ",
+ stacktrace, fixed = TRUE))) {
msg <- strsplit(stacktrace, "org.apache.spark.sql.catalyst.analysis.NoSuchDatabaseException: ",
fixed = TRUE)[[1]]
# Extract "Error in ..." message.
rmsg <- msg[1]
# Extract the first message of JVM exception.
first <- strsplit(msg[2], "\r?\n\tat")[[1]][1]
- stop(paste0(rmsg, "no such database - ", first), call. = FALSE)
+ stop(rmsg, "no such database - ", first, call. = FALSE)
} else
- if (any(grep("org.apache.spark.sql.catalyst.analysis.NoSuchTableException: ",
- stacktrace, fixed = TRUE))) {
+ if (any(grepl("org.apache.spark.sql.catalyst.analysis.NoSuchTableException: ",
+ stacktrace, fixed = TRUE))) {
msg <- strsplit(stacktrace, "org.apache.spark.sql.catalyst.analysis.NoSuchTableException: ",
fixed = TRUE)[[1]]
# Extract "Error in ..." message.
rmsg <- msg[1]
# Extract the first message of JVM exception.
first <- strsplit(msg[2], "\r?\n\tat")[[1]][1]
- stop(paste0(rmsg, "no such table - ", first), call. = FALSE)
- } else if (any(grep("org.apache.spark.sql.catalyst.parser.ParseException: ",
- stacktrace, fixed = TRUE))) {
+ stop(rmsg, "no such table - ", first, call. = FALSE)
+ } else if (any(grepl("org.apache.spark.sql.catalyst.parser.ParseException: ",
+ stacktrace, fixed = TRUE))) {
msg <- strsplit(stacktrace, "org.apache.spark.sql.catalyst.parser.ParseException: ",
fixed = TRUE)[[1]]
# Extract "Error in ..." message.
rmsg <- msg[1]
# Extract the first message of JVM exception.
first <- strsplit(msg[2], "\r?\n\tat")[[1]][1]
- stop(paste0(rmsg, "parse error - ", first), call. = FALSE)
+ stop(rmsg, "parse error - ", first, call. = FALSE)
} else {
stop(stacktrace, call. = FALSE)
}
diff --git a/R/pkg/tests/fulltests/test_sparkSQL.R b/R/pkg/tests/fulltests/test_sparkSQL.R
index 0b55271..fb0ed74 100644
--- a/R/pkg/tests/fulltests/test_sparkSQL.R
+++ b/R/pkg/tests/fulltests/test_sparkSQL.R
@@ -2472,7 +2472,7 @@ test_that("join(), crossJoin() and merge() on a DataFrame", {
error_msg <- paste("joinType must be one of the following types:",
"'inner', 'cross', 'outer', 'full', 'fullouter', 'full_outer',",
"'left', 'leftouter', 'left_outer', 'right', 'rightouter', 'right_outer',",
- "'semi', 'leftsemi', 'left_semi', 'anti', 'leftanti' or 'left_anti'.")
+ "'semi', 'leftsemi', 'left_semi', 'anti', 'leftanti', 'left_anti'")
expect_error(join(df2, df, df2$name == df$name, "invalid"), error_msg)
merged <- merge(df, df2, by.x = "name", by.y = "name", all.x = TRUE, all.y = TRUE)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org