@@ -8,21 +8,18 @@ Description: This package brings the GenoMetric Query Language (GMQL)

     functionalities into the R environment. GMQL is a high-level, declarative

     language to query and compare multiple and heterogeneous genomic datasets

     for biomedical knowledge discovery. It allows expressing easily queries and

-    processing over genomic regions and their metadata, in a way similar to what

-    can be done with the Structured Query Language (SQL) over a relational database,

-    to extract genomic regions of interest and compute their properties. GMQL

-    adopts algorithms designed for big data and their efficient implementation

-    using cloud-computing technologies, including Apache Hadoop framework and

-    Spark engine; these make GMQL able to run on modern high performance computing

+    processing over genomic regions and their metadata, to extract genomic regions 

+    of interest and compute their properties. GMQL adopts algorithms designed 

+    for big data and their efficient implementation using cloud-computing 

+    technologies, including Apache Hadoop framework and Spark engine; 

+    these make GMQL able to run on modern high performance computing

     infrastructures, CPU clusters and network infrastructures, in order to achieve

-    scalability and performance on big data. With GMQL very complex genomic

-    operations can be written as simple queries, with implicit iteration over

-    thousands of heterogeneous samples, and computed efficiently in few minutes over

-    servers or clouds. This RGMQL package is built over a scalable data management

-    engine written in Scala programming language, released as Scala API; it provides

-    a set of functions to create, manipulate and extract genomic data from different

-    data sources both from local and remote datasets. These RGMQL functions allow

-    performing complex queries and processing without knowing the GMQL syntax,

+    scalability and performance on big data. This RGMQL package is built over 

+    a scalable data management engine written in Scala programming language, 

+    released as Scala API; it provides a set of functions to create, 

+    manipulate and extract genomic data from different data sources both 

+    from local and remote datasets. These RGMQL functions allow performing 

+    complex queries and processing without knowing the GMQL syntax,

     but leveraging on R idiomatic paradigm and logic. RGMQL provides two different

     approaches in writing GMQL queries and processing scripts: a) REST calls b)

     standard R APIs The REST approach let users to log into a remote infrastructure

@@ -67,7 +64,7 @@ Imports:

     glue,

     BiocGenerics

 Depends:

-    R(>= 3.4.2)

+    R(<= 3.4.2), RGMQLScalaLibs

 VignetteBuilder: knitr

 Suggests: 

     BiocStyle,

@@ -45,11 +45,11 @@ import_gmql <- function(dataset_path, is_gtf)

     if(!dir.exists(datasetName))

         stop("Directory does not exists")

-    if(length(list.files(datasetName))==0)

+    if(!length(list.files(datasetName)))

         stop("no samples present in this dataset")

     regions <- list.files(datasetName, pattern = "*.gtf$",full.names = TRUE)

-    if(length(regions) != 0)

+    if(length(regions))

     {

         name_samples <- lapply(regions, function(x){

             gsub("*.gtf", "", basename(x))})

@@ -62,7 +62,7 @@ import_gmql <- function(dataset_path, is_gtf)

         stop("No GTF files present")

     meta <- list.files(datasetName, pattern = "*.gtf.meta$",full.names = TRUE)

-    if(length(meta) != 0)

+    if(length(meta))

     {

         meta_list <- lapply(meta, .add_metadata)

         names(meta_list) <- name_samples

@@ -83,17 +83,17 @@ import_gmql <- function(dataset_path, is_gtf)

     if(!dir.exists(datasetName))

         stop("Directory does not exists")

-    if(length(list.files(datasetName))==0)

+    if(!length(list.files(datasetName)))

         stop("no samples present in this dataset")

     regions <- list.files(datasetName, pattern = "*.gdm$",full.names = TRUE)

-    if(length(regions) != 0)

+    if(length(regions))

     {

         name_samples <- lapply(regions, function(x){

             gsub("*.gdm", "",basename(x))})

         vector_field <- .schema_header(datasetName)

-        names(vector_field)=NULL

+        names(vector_field) <- NULL

         sampleList <- lapply(regions,function(x){

             df <- read.delim(x,col.names = vector_field,header = FALSE)

             g <- GenomicRanges::makeGRangesFromDataFrame(df,

@@ -108,7 +108,7 @@ import_gmql <- function(dataset_path, is_gtf)

         stop("No GDM files present")

     meta <- list.files(datasetName, pattern = "*.gdm.meta$",full.names = TRUE)

-    if(length(meta) != 0)

+    if(length(meta))

     {

         meta_list <- lapply(meta, .add_metadata)

         names(meta_list) <- name_samples

@@ -134,7 +134,7 @@ export_gmql <- function(samples, dir_out, is_gtf)

         },files_sub_dir)

     }

     # first regions to get column names

-    col_names <- sapply(elementMetadata(samples[[1]]),class) 

+    col_names <- vapply(elementMetadata(samples[[1]]),class,character(1)) 

     # write schema XML

     .write_schema(col_names,files_sub_dir,to_GTF)

     c = .counter(0)

@@ -145,9 +145,9 @@ export_gmql <- function(samples, dir_out, is_gtf)

 .write_metadata <- function(meta_list,sample_name)

 {

     #create my own list if metadata empty

-    if(length(meta_list)==0){

+    if(!length(meta_list))

         meta_list <- list(Provider = "Polimi", Application = "R-GMQL")

-    }

+    

     names_list <- names(meta_list)

     value_list <- unlist(meta_list)

     file_meta_name = paste0(sample_name,".meta")

@@ -72,6 +72,8 @@ take_value.META_AGGREGATES <- function(obj){

 #' function sum, performing all the type conversions needed  }

 #' \item{COUNT: It prepares input parameter to be passed to the library 

 #' function count, performing all the type conversions needed }

+#' \item{COUNTSAMP: It prepares input parameter to be passed to the library 

+#' function third quartile, performing all the type conversions needed }

 #' \item{MIN: It prepares input parameter to be passed to the library 

 #' function minimum, performing all the type conversions needed  }

 #' \item{MAX: It prepares input parameter to be passed to the library 

@@ -197,6 +199,25 @@ as.character.COUNT <- function(obj) {

 check.COUNT <- function(obj){}

+#' @name AGGREGATES-Object

+#' @aliases COUNTSAMP

+#' @rdname aggr-class

+#' @export

+#'

+COUNTSAMP <- function()

+{

+    list <- list()

+    ## Set the name for the class

+    class(list) <- c("COUNTSAMP","AGGREGATES","META_AGGREGATES")

+    return(list)

+}

+as.character.COUNTSAMP <- function(obj) {

+    class <- class(obj)[1]

+    c(class,"")

+}

+check.COUNTSAMP <- function(obj){}

+

+

 #' @name AGGREGATES-Object

 #' @aliases MIN

 #' @rdname aggr-class

@@ -12,7 +12,7 @@

 {

     x <- scan(files, what="", sep="\n")

     y <- strsplit(x, "\t")

-    names(y) <- sapply(y, `[[`, 1)

+    names(y) <- vapply(y, `[[`,character(1), 1)

     listMeta <- lapply(y, `[`, -1)

 }

@@ -23,7 +23,7 @@

     schema_name_xml <- list.files(datasetName, pattern = "*.xml$",

                                 full.names = TRUE)

-    if(length(schema_name)==0 && length(schema_name_xml) == 0)

+    if(!length(schema_name) && !length(schema_name_xml))

         stop("schema not present")

     xml_schema <- xml2::read_xml(schema_name)

@@ -37,24 +37,24 @@

     if(!is.list(meta_data))

         stop("meta_data: invalid input")

-    if(!all(sapply(meta_data, function(x) is(x,class))))

+    if(!all(vapply(meta_data, function(x) is(x,class), logical(1))))

         stop("All elements must be META_AGGREGATES object")

     names <- names(meta_data)

     if(is.null(names))

     {

         warning("You did not assign a names to a list.\nWe build it for you")

-        names <- sapply(meta_data, take_value.META_AGGREGATES)

+        names <- vapply(meta_data, take_value.META_AGGREGATES,character(1))

     }

     else

     {

         if("" %in% names)

             stop("No partial names assignment is allowed")

     }

-    aggregate_matrix <- t(sapply(meta_data, function(x) {

+    aggregate_matrix <- t(vapply(meta_data, function(x) {

         new_value = as.character(x)

         matrix <- matrix(new_value)

-    }))

+    },character(2)))

     m_names <- matrix(names)

     metadata_matrix <- cbind(m_names,aggregate_matrix)

@@ -28,7 +28,7 @@

 #' 

 #' @examples

 #' 

-#' "where is my example?"

+#' "Where is my example?"

 #' 

 #' @name Evaluation-Function

 #' @aliases condition_evaluation

@@ -51,10 +51,10 @@ conds <- function(default = c(""), full = c(""), exact = c(""))

         join_condition_matrix <- NULL

     else

     {

-        join_condition_matrix <- t(sapply(array, function(x) {

+        join_condition_matrix <- t(vapply(array, function(x) {

             new_value = c(cond, x)

             matrix <- matrix(new_value)

-        }))

+        },character(2)))

     }

     join_condition_matrix

 }

@@ -86,25 +86,25 @@ filter_and_extract <- function(data, metadata = NULL,

     gtf_meta_files <- list.files(datasetName, pattern = "*.gtf.meta$",

                                     full.names = TRUE)

-    if(length(gdm_meta_files)==0 && length(gtf_meta_files)==0)

+    if(!length(gdm_meta_files) && !length(gtf_meta_files))

         stop("no samples present or no files format supported")

-    if(length(gdm_meta_files)>=1 && length(gtf_meta_files)>=1)

+    if(length(gdm_meta_files) && length(gtf_meta_files))

         stop("GMQL dataset cannot be mixed dataset: no GTF and GDM together")

     vector_field <- .schema_header(datasetName)

-    if(length(gdm_meta_files)>0)

+    if(length(gdm_meta_files))

     {

         samples_with_suffix <- .check_metadata_files(metadata,metadata_prefix,

                                                 gdm_meta_files, suffix)

-        samples_file <- sapply(samples_with_suffix, function(x) x$sample)

-        suffix_vec <- sapply(samples_with_suffix, function(x) x$suffix)

+        samples_file <- lapply(samples_with_suffix, function(x) x$sample)

+        suffix_vec <- lapply(samples_with_suffix, function(x) x$suffix)

         suffixes <- unlist(suffix_vec)

         samples_to_read <- unlist(samples_file)

-        if(length(samples_to_read)>0)

+        if(length(samples_to_read))

             samples_to_read <- gsub(".meta$", "", samples_to_read)

         else

             samples_to_read <- gsub(".meta$", "", gdm_meta_files)

@@ -117,12 +117,12 @@ filter_and_extract <- function(data, metadata = NULL,

         samples_with_suffix <- .check_metadata_files(metadata,metadata_prefix,

                                                     gtf_meta_files, suffix)

-        samples_file <- sapply(samples_with_suffix, function(x) x$sample)

-        suffix_vec <- sapply(samples_with_suffix, function(x) x$suffix)

+        samples_file <- lapply(samples_with_suffix, function(x) x$sample)

+        suffix_vec <- lapply(samples_with_suffix, function(x) x$suffix)

         suffixes <- unlist(suffix_vec)

         samples_to_read <- unlist(samples_file)

-        if(length(samples_to_read)>0)

+        if(length(samples_to_read))

             samples_to_read <- gsub(".meta$", "", samples_to_read)

         else

             samples_to_read <- gsub(".meta$", "", gtf_meta_files)

@@ -137,13 +137,13 @@ filter_and_extract <- function(data, metadata = NULL,

     if(!is(rangesList,"GRangesList"))

         stop("only GrangesList admitted")

-    if(length(rangesList)<=0)

+    if(!length(rangesList))

         stop("rangesList empty")

     meta_list <- metadata(rangesList)

     samples <- .check_metadata_list(metadata, metadata_prefix, meta_list, 

                                         suffix)

-    if(length(unlist(samples))<=0)

+    if(!length(unlist(samples)))

         samples <- rangesList

     else

     {

@@ -174,8 +174,8 @@ filter_and_extract <- function(data, metadata = NULL,

     vec_meta <- paste0(metadata_prefix,metadata)

     list <- mapply(function(x,index){

         vec_names <- names(x)

-        a <- sapply(vec_meta, function(y) {

-            which(y==vec_names)

+        a <- lapply(vec_meta, function(y) {

+            which(y == vec_names)

         })

         ## we would like that manage more index from grep

         found <- as.logical(length(unlist(a)))

@@ -191,9 +191,7 @@ filter_and_extract <- function(data, metadata = NULL,

     meta_list <- lapply(meta_files, function(x){

         list <- .add_metadata(x)

         vec_names <- names(list)

-        a <- sapply(vec_meta, function(y) {

-            grep(y,vec_names)

-        })

+        a <- lapply(vec_meta, function(y)grep(y,vec_names))

         ## we would like that manage more index from grep

         found <- as.logical(length(unlist(a)))

         index <- grep(suffix,vec_names)

@@ -249,7 +247,7 @@ filter_and_extract <- function(data, metadata = NULL,

             if(!is.null(regions))

                 col_names <- col_names[col_names %in% regions]

-            if(length(col_names)!=0)

+            if(length(col_names))

                 r <- subset(region_frame,TRUE,col_names)

         },regions,vector_field)

@@ -48,8 +48,8 @@

 #' \item{an expression built using PARAMETER object: (ALL() + N) / K or

 #' ALL() / K, with N and K integer values  }

 #' }

-#' @param groupBy \code{\link{condition_evaluation}} function to support 

-#' methods with groupBy or JoinBy input paramter

+#' @param groupBy \code{\link{conds}} function to support methods with 

+#' groupBy or JoinBy input parameter

 #' 

 #' @param ... a series of expressions separated by comma in the form 

 #' \emph{key} = \emph{aggregate}. The \emph{aggregate} is an object of 

@@ -115,8 +115,7 @@

 #' ## regions the minimum pvalue of the overlapping regions (min_pvalue) 

 #' ## and their Jaccard indexes (JaccardIntersect and JaccardResult).

 #' 

-#' res = cover(exp, 2, 3, groupBy = condition_evaluation(c("cell")), 

-#' min_pValue = MIN("pvalue"))

+#' res = cover(exp, 2, 3, groupBy = conds("cell"), min_pValue = MIN("pvalue"))

 #' 

 #' @name cover

 #' @rdname cover

@@ -141,9 +140,7 @@ setMethod("cover", "GMQLDataset",

                 gmql_cover(val, q_min, q_max, groupBy, aggregates, flag)

             })

-

-

-gmql_cover <- function(input_data, min_acc, max_acc, groupBy, aggregates, flag)

+gmql_cover <- function(input_data, min_acc, max_acc, groupBy,aggregates,flag)

 {

     if(!is.null(groupBy))

     {

@@ -156,7 +153,7 @@ gmql_cover <- function(input_data, min_acc, max_acc, groupBy, aggregates, flag)

                 join_matrix <- .jarray(cond, dispatch = TRUE)

         }

         else

-            stop("use function condition_evaluation()")

+            stop("use function conds()")

     }

     else

         join_matrix <- .jnull("java/lang/String")

@@ -184,7 +181,7 @@ gmql_cover <- function(input_data, min_acc, max_acc, groupBy, aggregates, flag)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -195,14 +192,7 @@ gmql_cover <- function(input_data, min_acc, max_acc, groupBy, aggregates, flag)

     if(length(param) > 1)

         stop("length > 1")

-    if(is.numeric(param))

-    {

-        if(param <= 0)

-            stop("No negative value")

-        else

-            return(as.character(param))

-    }

-    else if(is.character(param))

+    if(is.character(param))

     {

         if(is_min && identical(param,"ANY"))

             stop("min cannot assume ANY as value")

@@ -214,7 +204,7 @@ gmql_cover <- function(input_data, min_acc, max_acc, groupBy, aggregates, flag)

 }

-.trasform_cover <- function(predicate=NULL)

+.trasform_cover <- function(predicate)

 {

     predicate <- gsub("\\(\\)","",predicate)

 }

@@ -17,8 +17,8 @@

 #' 

 #' @param x GMQLDataset class object

 #' @param y GMQLDataset class object

-#' @param joinBy \code{\link{condition_evaluation}} function to support 

-#' methods with groupBy or JoinBy input paramter

+#' @param joinBy \code{\link{conds}} function to support methods with 

+#' groupBy or JoinBy input paramter

 #' 

 #' @param is_exact single logical value: TRUE means that the region difference 

 #' is executed only on regions in left_input_data with exactly the same 

@@ -30,7 +30,6 @@

 #' @return GMQLDataset object. It contains the value to use as input 

 #' for the subsequent GMQLDataset method

 #' 

-#'

 #' @examples

 #' ## This statement initializes and runs the GMQL server for local execution 

 #' ## and creation of results on disk. Then, with system.file() it defines 

@@ -55,7 +54,7 @@

 #' ## do not overlap any region in s2; 

 #' ## metadata of the result are the same as the metadata of s1.

 #' 

-#' out_t = setdiff(data1, data2, condition_evaluation(c("cell")))

+#' out_t = setdiff(data1, data2, conds("cell"))

 #'

 #' @name setdiff

 #' @aliases setdiff,GMQLDataset,GMQLDataset-method

@@ -87,7 +86,7 @@ gmql_difference <- function(left_data, right_data, is_exact, joinBy)

                                         is_exact)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -79,7 +79,7 @@ gmql_extend <-function(input_data, meta)

     response <- WrappeR$extend(metadata_matrix, input_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -1,7 +1,7 @@

 group_by.GMQLDateset <- function(.data, groupBy_meta = NULL, 

     groupBy_regions = NULL, region_aggregates = NULL, meta_aggregates = NULL)

 {

-    ptr_data = .data@value

+    ptr_data = value(.data)

     gmql_group(ptr_data, groupBy_meta, groupBy_regions, region_aggregates, 

                 meta_aggregates)

 }

@@ -14,16 +14,9 @@ group_by.GMQLDateset <- function(.data, groupBy_meta = NULL,

 #' @importFrom dplyr group_by

 #' 

 #' @param .data GMQLDataset object

-#' @param groupBy_meta it define condition evaluation on metadata.

-#' \itemize{

-#' \item{\code{\link{FN}}: Fullname evaluation, two attributes match 

-#' if they both end with value and, if they have a further prefixes,

-#' the two prefix sequence are identical}

-#' \item{\code{\link{EX}}: Exact evaluation, only attributes exactly 

-#' as value will match; no further prefixes are allowed. }

-#' \item{\code{\link{DF}}: Default evaluation, the two attributes match 

-#' if both end with value.}

-#' }

+#' @param groupBy_meta \code{\link{conds}} function to support methods with 

+#' groupBy or JoinBy input parameter

+#' 

 #' @param groupBy_regions vector of string made up by schema field attribute

 #' @param region_aggregates It accept a series of aggregate function on 

 #' region attribute. 

@@ -89,7 +82,7 @@ gmql_group <- function(input_data, group_meta, group_reg, region_aggregates,

                 join_matrix <- .jarray(cond, dispatch = TRUE)

         }

         else

-            stop("use function condition_evaluation()")

+            stop("use function conds()")

     }

     else

         join_matrix <- .jnull("java/lang/String")

@@ -132,7 +125,7 @@ gmql_group <- function(input_data, group_meta, group_reg, region_aggregates,

                                 region_matrix, input_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -43,12 +43,12 @@

 #' having left (right) coordinates equal to the minimum (maximum) of the 

 #' corresponding coordinate values in the 'x' and 'y' regions satisfying 

 #' the genometric predicate)}

-#' \item{LEFT_DISTINCT: It outputs the duplicate elimination of "x" output 

+#' \item{LEFT_DIST: It outputs the duplicate elimination of "x" output 

 #' regions with the same values, regardless the "y" paired region and its 

 #' values. In this case, the output regions attributes and their values are 

 #' all those of "x", and the output metadata are equal to the "x" metadata, 

 #' without additional prefixes}

-#' \item{RIGHT_DISTINCT: It outputs the duplicate elimination of "y" output 

+#' \item{RIGHT_DIST: It outputs the duplicate elimination of "y" output 

 #' regions with the same values, regardless the "x" paired region and its 

 #' values. In this case, the output regions attributes and their values are 

 #' all those of "y", and the output metadata are equal to the "y" metadata, 

@@ -109,19 +109,20 @@ gmql_join <- function(left_data, right_data, genometric_predicate, joinBy,

 {

     if(!is.null(genometric_predicate))

     {

-        if(length(genometric_predicate) >4)

+        if(length(genometric_predicate) > 4)

             stop("genometric_predicate: only 4 DISTAL condition")

         if(!is.list(genometric_predicate))

             stop("genometric_predicate must be a list")

-        if(!all(sapply(genometric_predicate, function(x) {is(x,"DISTAL")} )))

+        if(!all(vapply(genometric_predicate, function(x) {is(x,"DISTAL")},

+                        logical(1))))

             stop("All elements should be DISTAL object")

-        genomatrix <- t(sapply(genometric_predicate, function(x) {

+        genomatrix <- t(vapply(genometric_predicate, function(x) {

                 new_value = as.character(x)

                 array <- c(new_value)

-        }))

+        },character(2)))

         genomatrix <- .jarray(genomatrix, dispatch = TRUE)

     }

@@ -166,7 +167,7 @@ gmql_join <- function(left_data, right_data, genometric_predicate, joinBy,

                                 left_data, right_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -39,16 +39,8 @@

 #' }

 #' "mixed style" is not allowed

 #'

-#' @param joinBy list of evalation functions to define evaluation on metadata:

-#' \itemize{

-#' \item{ \code{\link{FN}}(value): Fullname evaluation, two attributes match 

-#' if they both end with \emph{value} and, if they have further prefixes,

-#' the two prefix sequence are identical.}

-#' \item{ \code{\link{EX}}(value): Exact evaluation, only attributes exactly 

-#' as \emph{value} match; no further prefixes are allowed.}

-#' \item{ \code{\link{DF}}(value): Default evaluation, the two attributes match 

-#' if both end with \emph{value}.}

-#' }

+#' @param joinBy \code{\link{conds}} function to support methods with 

+#' groupBy or JoinBy input parameter

 #' @param count_name string defining the metadata count name; if it is 

 #' not specifying the name is "count_left_right" 

 #' 

@@ -78,15 +70,14 @@

 #' # but with a different value from the one(s) of ref sample(s), 

 #' # are disregarded.

 #' 

-#' out = map(ref, exp, minScore = MIN("score"), 

-#' joinBy = list(DF("cell_tissue")))

+#' out = map(ref, exp, minScore = MIN("score"), joinBy = conds("cell_tissue"))

 #' 

 #' @name map

 #' @rdname map

 #' @aliases map-method

 #' @export

 setMethod("map", "GMQLDataset",

-            function(x, y, ..., joinBy = NULL, count_name = NULL)

+            function(x, y, ..., joinBy = NULL, count_name = "")

             {

                 left_data <- value(x)

                 right_data <- value(y)

@@ -120,6 +111,9 @@ gmql_map <- function(left_data, right_data, aggregates, joinBy, count_name)

     {

         if(!is.character(count_name))

             stop("count_name: must be string")

+        

+        if(identical(count_name,""))

+            count_name <- .jnull("java/lang/String")

     }

     else

         count_name <- .jnull("java/lang/String")

@@ -129,7 +123,7 @@ gmql_map <- function(left_data, right_data, aggregates, joinBy, count_name)

                             right_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -40,7 +40,7 @@ execute <- function()

     response <- WrappeR$execute()

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

     {

@@ -62,13 +62,13 @@ execute <- function()

     remote <- WrappeR$is_remote_processing()

     if(remote)

     {

-        sapply(data_list,function(x){

+        lapply(data_list,function(x){

             if(!is.null(x[[1]]) && !is.na(x[[1]]))

                 upload_dataset(url,x[[2]],x[[1]],x[[3]],FALSE)})

     }

     else

     {

-        sapply(data_list,function(x){

+        lapply(data_list,function(x){

             if(!is.null(x[[2]]) && !is.na(x[[2]]))

                 download_dataset(url,x[[2]],x[[1]])})

     }

@@ -147,7 +147,7 @@ gmql_materialize <- function(input_data, dir_out, name)

     response <- WrappeR$materialize(input_data, res_dir_out)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         invisible(NULL)

@@ -204,7 +204,7 @@ setMethod("take", "GMQLDataset",

                 gmql_take(ptr_data, rows)

             })

-gmql_take <- function(input_data, rows = 0L)

+gmql_take <- function(input_data, rows)

 {

     rows <- as.integer(rows[1])

     if(rows<0)

@@ -214,7 +214,7 @@ gmql_take <- function(input_data, rows = 0L)

     response <- WrappeR$take(input_data, rows)

     error <- strtoi(response[1])

     data <- response[2]

-    if(error!=0)

+    if(error)

         stop(data)

     reg <- .jevalArray(WrappeR$get_reg(),simplify = TRUE)

@@ -40,7 +40,7 @@

 #' ## antibody_target and cell metadata

 #' ## attributes.

 #'

-#' merged = aggregate(exp, condition_evaluation(c("antibody_target","cell")))

+#' merged = aggregate(exp, conds(c("antibody_target","cell")))

 #'

 #' @name aggregate

 #' @rdname aggregate

@@ -72,7 +72,7 @@ gmql_merge <- function(input_data, groupBy)

     response <- WrappeR$merge(join_matrix, input_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

@@ -130,13 +130,12 @@ gmql_order <- function(input_data, metadata_ordering, regions_ordering,

                         region_matrix, input_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

 }

-

 .ordering_meta <- function(ordering)

 {

     order_matrix <- do.call(rbind, ordering)

@@ -2,7 +2,7 @@ select.GMQLDataset <- function(.data, metadata = NULL, metadata_update = NULL,

                             all_but_meta = FALSE, regions = NULL, 

                             regions_update = NULL, all_but_reg = FALSE) 

 {

-    data = .data@value

+    data = value(.data)

     r_update <- substitute(regions_update)

     if(!is.null(r_update))

     {

@@ -132,7 +132,7 @@ gmql_project <-function(input_data, metadata, metadata_update, all_but_meta,

         metadata <- metadata[!metadata %in% ""]

         metadata <- metadata[!duplicated(metadata)]

-        if(length(metadata)==0)

+        if(!length(metadata))

             metadata <- .jnull("java/lang/String")

         metadata <- .jarray(metadata)

@@ -148,7 +148,7 @@ gmql_project <-function(input_data, metadata, metadata_update, all_but_meta,

         regions = regions[!regions %in% ""]

         regions = regions[!duplicated(regions)]

-        if(length(regions)==0)

+        if(!length(regions))

             regions <- .jnull("java/lang/String")

         regions <- .jarray(regions)

@@ -171,13 +171,13 @@ gmql_project <-function(input_data, metadata, metadata_update, all_but_meta,

                     regions, regions_update, all_but_reg, input_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)

 }

-.trasform_update <- function(predicate=NULL)

+.trasform_update <- function(predicate)

 {

     predicate <- gsub("list\\(","",predicate)

     predicate <- gsub("\\)$","",predicate)

@@ -83,7 +83,7 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

         schema_XML <- list.files(dataset, pattern = "*.schema$",

                                     full.names = TRUE)

-        if(length(schema_XML) == 0)

+        if(!length(schema_XML))

             stop("schema must be present")

         schema_matrix <- .jnull("java/lang/String")

@@ -99,12 +99,12 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

             stop("You have to log on using login function")

         list <- show_schema(url,dataset)

-        schema_names <- sapply(list$fields, function(x){x$name})

-        schema_type <- sapply(list$fields, function(x){x$type})

+        schema_names <- vapply(list$fields, function(x){x$name},character(1))

+        schema_type <- vapply(list$fields, function(x){x$type},character(1))

         schema_matrix <- cbind(schema_type,schema_names)

         #schema_type <- list$type

-        if(is.null(schema_matrix) || length(schema_matrix)==0)

+        if(is.null(schema_matrix) || !length(schema_matrix))

             schema_matrix <- .jnull("java/lang/String")

         else

             schema_matrix <- .jarray(schema_matrix, dispatch = TRUE)

@@ -116,7 +116,7 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

                                         schema_matrix, schema_XML)

     error <- strtoi(response[1])

     data <- response[2]

-    if(error!=0)

+    if(error)

         stop(data)

     else

         GMQLDataset(data)

@@ -138,11 +138,12 @@ read <- function(samples)

         stop("only GrangesList")

     meta <- S4Vectors::metadata(samples)

-    if(is.null(meta) || length(meta)==0) 

+    if(is.null(meta) || !length(meta)) 

     {

         #repeat meta for each sample in samples list

         len <- length(samples)

-        warning("No metadata.\nWe provide two metadata for you")

+        warning("No metadata.\nWe provide two metadata for you:

+                \n1.provider = PoliMi\n2.application = RGMQL\n")

         index_meta <- rep(seq_len(len),each = len)

         rep_meta <- rep(c("provider","PoliMi", "application", "RGMQL"),

                             times = len)

@@ -160,10 +161,11 @@ read <- function(samples)

     df <- data.frame(samples)

     df <- df[-2] #delete group_name

-    region_matrix <- as.matrix(sapply(df, as.character))

+    len_df <- dim(df)[1] # number of rows

+    region_matrix <- as.matrix(vapply(df, as.character,character(len_df)))

     region_matrix[is.na(region_matrix)] <- "NA"

     region_matrix <- region_matrix[,setdiff(colnames(region_matrix),"width")]

-    col_types <- sapply(df,class)

+    col_types <- vapply(df,class,character(1))

     col_names <- names(col_types)

     #re order the schema?

     if("phase" %in% col_names) # if GTF, change

@@ -98,7 +98,7 @@ filter.GMQLDateset <- function(.data, m_predicate = NULL, r_predicate = NULL,

 #' ## less than 0.01 are conserved in output

 #' 

 #' jun_tf <- filter(data, antibody_target == "JUN", pValue < 0.01, 

-#' semijoin(join_data, TRUE, list(DF("cell"))))

+#' semijoin(join_data, TRUE, conds("cell")))

 #' 

 #' 

 #' @name filter

@@ -125,7 +125,7 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

                                     input_data)

     error <- strtoi(response[1])

     data <- response[2]

-    if(error!=0)

+    if(error)

         stop(data)

     else

         GMQLDataset(data)

@@ -137,6 +137,7 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

 #' This function is used as support to the filter method to define 

 #' semijoin conditions on metadata  

 #' 

+#' 

 #' @param .data GMQLDataset class object

 #' 

 #' @param not_in logical value: TRUE => for a given sample of input dataset

@@ -184,39 +185,44 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

 #' # less than 0.01 are conserved in output

 #' 

 #' jun_tf <- filter(data, antibody_target == "JUN", pValue < 0.01, 

-#' semijoin(join_data, TRUE, list(DF("cell"))))

+#' semijoin(join_data, TRUE, conds("cell")))

 #' 

 #' @return semijoin condition as list

 #' @export

 #' 

-semijoin <- function(.data, not_in = FALSE, groupBy = NULL)

+semijoin <- function(.data, not_in = FALSE, groupBy)

 {

-    if(!is.list(groupBy))

-        stop("groupBy: must be a list")

-    

-    semij_cond = groupBy

+    if(!is.null(groupBy))

+    {

+        if("condition" %in% names(groupBy))

+        {

+            cond <- .join_condition(groupBy)

+            if(is.null(cond))

+                stop("groupBy cannot be NULL")

+        }

+        else

+            stop("use function conds()")

+    }

+    else

+        stop("groupBy cannot be NULL")

-    if(is.null(data))

-        stop("data cannot be NULL")

+    if(is.null(.data))

+        stop(".data cannot be NULL")

-    if(!isClass("GMQLDataset", data))

+    if(!isClass("GMQLDataset", .data))

         stop("data: Must be a GMQLDataset object") 

     .check_logical(not_in)

     ptr_data <- value(.data)

-    

     data_cond <- cbind(ptr_data,not_in)

-    cond <- .join_condition(semij_cond)

-    cond <- rbind(data_cond,cond)

-    join_condition_matrix <- .jarray(cond, dispatch = TRUE)

+    all_conds <- rbind(data_cond,cond)

+    join_condition_matrix <- .jarray(all_conds, dispatch = TRUE)

     semijoin <- list("semijoin" = join_condition_matrix)

 }

-

-

-.trasform <- function(predicate=NULL)

+.trasform <- function(predicate)

 {

     predicate <- gsub("&|&&","AND",predicate)

     predicate <- gsub("\\||\\|\\|","OR",predicate)

@@ -64,7 +64,7 @@ gmql_union <- function(left_data, right_data)

     response <- WrappeR$union(left_data, right_data)

     error <- strtoi(response[1])

     val <- response[2]

-    if(error!=0)

+    if(error)

         stop(val)

     else

         GMQLDataset(val)