@@ -98,10 +98,10 @@ Collate:

     'aggregate-class.R'

     'authOp.R'

     'browseOp.R'

-    'condition-class.R'

     'cover_param-class.R'

     'datasetOp.R'

     'distal-class.R'

+    'evaluation_functions.R'

     'onLoad.R'

     'operator-class.R'

     'ordering-class.R'

@@ -8,13 +8,14 @@ export(BAG)

 export(BAGD)

 export(COUNT)

 export(DESC)

+export(DF)

 export(DG)

 export(DGE)

 export(DL)

 export(DLE)

 export(DOWN)

-export(EXACT)

-export(FULL)

+export(EX)

+export(FN)

 export(MAX)

 export(MD)

 export(MEDIAN)

@@ -50,6 +51,7 @@ export(sample_metadata)

 export(sample_region)

 export(save_query)

 export(save_query_fromfile)

+export(semijoin)

 export(show_datasets_list)

 export(show_job_log)

 export(show_jobs_list)

@@ -70,6 +72,7 @@ exportMethods(materialize)

 exportMethods(setdiff)

 exportMethods(sort)

 exportMethods(subset)

+exportMethods(take)

 exportMethods(union)

 import(GenomicRanges)

 import(httr)

@@ -51,24 +51,20 @@

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

 #' ALL() / K }

 #' }

-#' @param groupBy list of CONDITION objects where every object contains 

-#' the name of metadata to be used in semijoin, or simple string concatenation 

-#' of name of metadata, e.g. c("cell_type", "attribute_tag", "size") 

-#' without declaring condition.

-#' The CONDITION's available are:

+#' @param groupBy list of evalation function to define condition 

+#' evaluation on metadata:

 #' \itemize{

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

+#' \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{EXACT}}: Exact evaluation, only attributes exactly 

+#' \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.}

 #' }

-#' Every condition accepts only one string value. (e.g. FULL("cell_type") )

-#' In case of single concatenation with no CONDITION or list with some value 

-#' without conditon, the metadata are considered having default 

-#' evaluation: the two attributes match if both end with value.

+#' @param ... Additional arguments for use in specific methods.

 #' 

-#' @param aggregates list of element in the form \emph{key} = \emph{aggregate}.

+#' In this case a series of element in the form \emph{key} = \emph{aggregate}.

 #' The \emph{aggregate} is an object of class AGGREGATES

 #' The aggregate functions available are: \code{\link{SUM}}, 

 #' \code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

@@ -100,7 +96,6 @@

 #' the AccIndex region attribute.}

 #' \item{cover: default value.}

 #' }

-#' @param ... Additional arguments for use in specific methods.

 #' 

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

 #' for the subsequent GMQL function

@@ -128,26 +123,28 @@

 #' 

 #' test_path <- system.file("example", "DATASET", package = "RGMQL")

 #' exp = read_dataset(test_path)

-#' res = cover(exp, 2, 3, c("cell"), list(min_pValue = MIN("pvalue")))

+#' res = cover(exp, 2, 3, groupBy = list(DF("cell")), 

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

 #' }

 #' 

 #' @aliases cover, cover-method

 #' @export

 setMethod("cover", "GMQLDataset",

-            function(data, min_acc, max_acc, groupBy = NULL, aggregates = NULL, 

-                        variation = "cover")

+            function(data, min_acc, max_acc, groupBy = NULL, 

+                    variation = "cover", ...)

             {

                 val <- data@value

                 q_max <- .check_cover_param(max_acc,FALSE)

                 q_min <- .check_cover_param(min_acc,FALSE)

                 flag = toupper(variation)

+                aggregates = list(...)

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

             })

 gmql_cover <- function(data, min_acc, max_acc, groupBy = NULL, 

-                        aggregates = NULL, flag)

+                            aggregates = NULL, flag)

 {

     if(!is.null(groupBy))

@@ -156,7 +153,7 @@ gmql_cover <- function(data, min_acc, max_acc, groupBy = NULL,

     else

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

-    if(!is.null(aggregates))

+    if(!is.null(aggregates) && !length(aggregates) == 0)

         metadata_matrix <- .jarray(.aggregates(aggregates,"AGGREGATES"),

                                     dispatch = TRUE)

     else

@@ -1,5 +1,7 @@

-#' GMQL Operation: DIFFERENCE

-#'

+#' Method setdiff

+#' 

+#' Wrapper to GMQL difference function

+#' 

 #' It produces one sample in the result for each sample of the left operand,

 #' by keeping the same metadata of the left input sample and only those 

 #' regions (with their schema and values) of the left input sample which 

@@ -17,22 +19,18 @@

 #' 

 #' @param x GMQLDataset class object

 #' @param y GMQLDataset class object

-#' @param joinBy vector of CONDITION objects where every object contains 

-#' the name of metadata to be used in semijoin, or string concatenation 

-#' of name of metadata, e.g. c("cell_type", "attribute_tag", "size") 

-#' without declaring condition.

-#' The CONDITION's available are:

+#' @param ... Additional arguments for use in specific methods.

+#' 

+#' This method accept a function to define condition evaluation on metadata.

 #' \itemize{

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

+#' \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{EXACT}}: Exact evaluation, only attributes exactly 

+#' \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.}

 #' }

-#' Every condition accepts only one string value. (e.g. FULL("cell_type") )

-#' In case of single concatenation with no CONDITION the metadata are 

-#' considered having default evaluation: 

-#' the two attributes match if both end with value.

 #' 

 #' @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 

@@ -40,7 +38,7 @@

 #' if is_exact = FALSE, the difference is executed on all regions in 

 #' left_input_data that overlap with at least one region in right_input_data 

 #' (even just one base).

-#'

+#' 

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

 #' for the subsequent GMQL function

 #' 

@@ -69,25 +67,29 @@

 #' test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 #' exp1 = read_dataset(test_path)

 #' exp2 = read_dataset(test_path2)

-#' out = setdiff(exp1, exp2, joinBy = c("antibody_target"))

+#' out = setdiff(exp1, exp2, DF("antibody_target"))

 #'

 #' }

-#' 

-#' @aliases setdiff, setdiff-method

+#' @name setdiff

+#' @aliases setdiff,GMQLDataset,GMQLDataset-method

+#' @aliases setdiff-method

 #' @export

 setMethod("setdiff", c("GMQLDataset","GMQLDataset"),

-            function(x, y, is_exact = FALSE, joinBy = NULL)

+            function(x, y, ..., is_exact = FALSE)

             {

-                val_x = x@value

-                val_y = y@value

-                gmql_difference(val_x, val_y, is_exact, joinBy)

+                ptr_data_x = x@value

+                ptr_data_y = y@value

+                joinBy = list(...)

+                gmql_difference(ptr_data_x, ptr_data_y, is_exact, joinBy)

             })

 gmql_difference <- function(left_data, right_data, is_exact, joinBy)

 {

-    if(!is.null(joinBy))

-        join_condition_matrix <- .jarray(.join_condition(joinBy),

-                                            dispatch = TRUE)

+    if(!is.null(joinBy) && !length(joinBy) == 0)

+    {

+        cond <- .join_condition(joinBy)

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

+    }

     else

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

@@ -1,11 +1,3 @@

-#' @name extend

-#' @rdname extend-GMQLDataset-method

-#' @aliases extend, GMQLDataset-method

-#' @exportMethod extend

-setGeneric("extend", function(.data, ...) 

-    standardGeneric("extend"))

-

-

 #' GMQL Operation: EXTEND

 #'

 #' It generates new metadata attributes as result of aggregate functions 

@@ -20,7 +12,8 @@ setGeneric("extend", function(.data, ...)

 #' @param .data GMQLDataset class object 

 #' @param ... Additional arguments for use in specific methods.

 #' 

-#' In this case a series of element in the form \emph{key} = \emph{aggregate}.

+#' This method accept a series of aggregate function on region attribute.

+#' All the element in the form \emph{key} = \emph{aggregate}.

 #' The \emph{aggregate} is an object of class AGGREGATES

 #' The aggregate functions available are: \code{\link{SUM}}, 

 #' \code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

@@ -60,31 +53,32 @@ setGeneric("extend", function(.data, ...)

 #' init_gmql()

 #' test_path <- system.file("example", "DATASET", package = "RGMQL")

 #' exp = read_dataset(test_path)

-#' res = extend(exp, RegionCount = COUNT(), MinP = MIN("pvalue")))

+#' res = extend(exp, RegionCount = COUNT(), MinP = MIN("pvalue"))

 #' 

 #' }

 #' @aliases extend-method

 #' @export

-setMethod("extend", "GMQLDataset",

-            function(.data, ...)

+setMethod("extend", "GMQLDataset", function(.data, ...)

             {

-                val_x = .data@value

+                ptr_data = .data@value

                 meta <- list(...)

-                gmql_extend(val_x, meta)

+                gmql_extend(ptr_data, meta)

             })

 gmql_extend <-function(input_data, meta)

 {

-    if(!is.null(meta) && !length(meta)==0)

-        metadata_matrix <- .jarray(.aggregates(meta,"META_AGGREGATES"),

-                                    dispatch = TRUE)

+    if(!is.null(meta) && !length(meta) == 0)

+    {

+        aggr <- .aggregates(meta, "META_AGGREGATES")

+        metadata_matrix <- .jarray(aggr, dispatch = TRUE)

+    }

     else

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

     WrappeR <- J("it/polimi/genomics/r/Wrapper")

-    response <- WrappeR$extend(metadata_matrix,input_data)

+    response <- WrappeR$extend(metadata_matrix, input_data)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -39,7 +39,7 @@ setMethod("show", "GMQLDataset",

 # num_fetch = 0, reg_fetch_opt = NULL, 

 # reg_num_fetch = 0) standardGeneric("sort"))

-#' Method mutate

+#' Method aggregate

 #' 

 #' Wrapper to GMQL merge function

 #' 

@@ -47,7 +47,7 @@ setMethod("show", "GMQLDataset",

 #' @rdname aggregate-GMQLDataset-method

 #' @aliases aggregate

 #'  

-setGeneric("aggregate", function(data, groupBy = NULL) 

+setGeneric("aggregate", function(data, ...) 

                                     standardGeneric("aggregate"))

@@ -59,7 +59,7 @@ setGeneric("aggregate", function(data, groupBy = NULL)

 #' @rdname join-GMQLDataset-method

 #' @aliases join

 #' 

-setGeneric("join", function(x, y, by = NULL,...) standardGeneric("join"))

+setGeneric("join", function(x, y, ...) standardGeneric("join"))

 #' Method filter

@@ -70,7 +70,7 @@ setGeneric("join", function(x, y, by = NULL,...) standardGeneric("join"))

 #' @rdname filter-GMQLDataset-method

 #' @aliases filter

 #' 

-setGeneric("filter", function(.data,...) standardGeneric("filter"))

+setGeneric("filter", function(.data, ...) standardGeneric("filter"))

 #' Method cover

 #' 

@@ -80,7 +80,8 @@ setGeneric("filter", function(.data,...) standardGeneric("filter"))

 #' @rdname cover-GMQLDataset-method

 #' @aliases cover

 #' 

-setGeneric("cover", function(data, ...) standardGeneric("cover"))

+setGeneric("cover", function(data, min_acc, max_acc, ...)

+                        standardGeneric("cover"))

 #' Method map

 #' 

@@ -93,5 +94,35 @@ setGeneric("cover", function(data, ...) standardGeneric("cover"))

 setGeneric("map", function(x, y, ...) standardGeneric("map"))

+#' Method materialize

+#' 

+#' Wrapper to GMQL materialize function

+#' 

+#' @name materialize

+#' @rdname materialize-GMQLDataset-method

+#' @export

+setGeneric("materialize", function(data, ...) standardGeneric("materialize"))

+

+

+#' Method take

+#' 

+#' GMQL Operation: TAKE

+#' 

+#' @name take

+#' @rdname take-GMQLDataset-method

+#' @export

+setGeneric("take", function(data, ...) standardGeneric("take"))

+

+

+#' Method extend

+#' 

+#' Wrapper to GMQL extend function

+#' 

+#' @name extend

+#' @rdname extend-GMQLDataset-method

+#' @aliases extend, GMQLDataset-method

+#' @exportMethod extend

+setGeneric("extend", function(.data, ...) standardGeneric("extend"))

+

@@ -35,7 +35,8 @@

 #'

 #'

 #' @examples

-#'

+#' 

+#' \dontrun{

 #' library(GenomicRanges)

 #' gr1 <- GRanges(seqnames = "chr2", ranges = IRanges(3, 6), strand = "+", 

 #' score = 5L, GC = 0.45)

@@ -45,7 +46,7 @@

 #' grl = GRangesList(gr1, gr2)

 #' test_out_path <- system.file("example", package = "RGMQL")

 #' export_gmql(grl, test_out_path,TRUE)

-#'

+#' }

 #' @export

 #'

 export_gmql <- function(samples, dir_out, is_gtf)

@@ -69,7 +70,7 @@ export_gmql <- function(samples, dir_out, is_gtf)

 }

-.exportGMQL <- function(samples, dir_out,to_GTF)

+.exportGMQL <- function(samples, dir_out, to_GTF)

 {

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

         stop("samples must be a GrangesList")

@@ -18,28 +18,24 @@

 #' 

 #' @param x GMQLDataset class object

 #' @param y GMQLDataset class object

+

 #' @param genometric_predicate is a list of lists of DISTAL object

 #' For details of DISTAL objects see:

 #' \code{\link{DLE}}, \code{\link{DGE}}, \code{\link{DL}}, \code{\link{DG}},

 #' \code{\link{MD}}, \code{\link{UP}}, \code{\link{DOWN}}

+#' 

 #' @param ... Additional arguments for use in specific methods.

-#' @param by list of CONDITION objects where every object contains 

-#' the name of metadata to be used in semijoin, or simple string concatenation 

-#' of name of metadata, e.g. c("cell_type", "attribute_tag", "size") 

-#' without declaring condition.

-#' The CONDITION's available are:

+#' 

+#' This method accept a function to define condition evaluation on metadata.

 #' \itemize{

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

+#' \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{EXACT}}: Exact evaluation, only attributes exactly 

+#' \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.}

 #' }

-#' Every condition accepts only one string value. (e.g. FULL("cell_type") )

-#' In case of single concatenation with no CONDITION, or list with some value 

-#' without conditon, the metadata are considered having default 

-#' evaluation: the two attributes match if both end with value.

-#' 

 #' 

 #' @param region_output single string that declare which region is given in 

 #' output for each input pair of left dataset right dataset regions 

@@ -63,8 +59,7 @@

 #'

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

 #' for the subsequent GMQL function

-#'

-#'

+#' 

 #' @examples

 #' 

 #' # Given a dataset 'hm' and one called 'tss' with a sample including 

@@ -80,20 +75,21 @@

 #' TSS = read_dataset(test_path)

 #' HM = read_dataset(test_path2)

 #' join_data = join(TSS, HM, 

-#' genometric_predicate = list(list(MD(1), DLE(120000))), by = c("provider"), 

-#' region_output="RIGHT")

+#' genometric_predicate = list(list(MD(1), DLE(120000))), DF("provider"), 

+#' region_output = "RIGHT")

 #' 

 #' @aliases join-method

 #' @export

 setMethod("join", "GMQLDataset",

-                function(x, y, by = NULL, genometric_predicate = NULL, 

-                    region_output="contig")

+                function(x, y, genometric_predicate = NULL, 

+                    region_output = "contig", ...)

                 {

-                    r_data <- x@value

-                    l_data <- y@value

-                    gmql_join(r_data, l_data, genometric_predicate, by, 

-                            region_output="contig")

+                    ptr_data_x <- x@value

+                    ptr_data_y <- y@value

+                    joinBy = list(...)

+                    gmql_join(ptr_data_x, ptr_data_y, genometric_predicate, 

+                                joinBy, region_output="contig")

                 })

@@ -40,27 +40,21 @@

 #' }

 #' "mixed style" is not allowed

 #'

-#' @param joinBy list of CONDITION objects where every object contains 

-#' the name of metadata to be used in semijoin, or simple string concatenation 

-#' of name of metadata, e.g. c("cell_type", "attribute_tag", "size") 

-#' without declaring condition.

-#' The CONDITION's available are:

+#' @param joinBy list of evalation function to define condition 

+#' evaluation on metadata:

 #' \itemize{

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

+#' \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{EXACT}}: Exact evaluation, only attributes exactly 

+#' \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.}

 #' }

-#' Every condition accepts only one string value. (e.g. FULL("cell_type") )

-#' In case of single concatenation with no CONDITION, or list with some value 

-#' without conditon, the metadata are considered having default 

-#' evaluation: the two attributes match if both end with value.

 #' 

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

 #' for the subsequent GMQL function

 #' 

-#'

 #' @examples

 #'

 #' # It counts the number of regions in each sample from exp that overlap with 

@@ -77,7 +71,8 @@

 #' test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 #' exp = read_dataset(test_path)

 #' ref = read_dataset(test_path2)

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

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

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

 #' 

 #' @aliases map-method

 #' @export

@@ -11,10 +11,10 @@

 #'

 #' init_gmql()

 #' test_path <- system.file("example","DATASET",package = "RGMQL")

-#' r = read_dataset(test_path)

-#' s = filter(r)

-#' m = aggregate(s, groupBy = c("antibody_targer","cell_karyotype"))

-#' materialize(m, dir_out = test_path)

+#' rd = read_dataset(test_path)

+#' filtered = filter(rd)

+#' aggr = aggregate(filtered, DF("antibody_targer","cell_karyotype"))

+#' materialize(aggr, dir_out = test_path)

 #' 

 #' \dontrun{

 #' execute()

@@ -65,9 +65,6 @@ execute <- function()

     }

 }

-#' @rdname materialize-GMQLDataset-method

-#' @export

-setGeneric("materialize", function(data, ...) standardGeneric("materialize"))

 #' GMQL Operation: MATERIALIZE

@@ -84,7 +81,9 @@ setGeneric("materialize", function(data, ...) standardGeneric("materialize"))

 #' @param data GMQLDataset class object

 #' @param dir_out destination folder path.

 #' by default is current working directory of the R process

-#' @param ... Additional arguments for use in specific methods.

+#' 

+#' @param ... Additional arguments for use in specific methods

+#' 

 #' @return None

 #'

 #' @examples

@@ -93,7 +92,7 @@ setGeneric("materialize", function(data, ...) standardGeneric("materialize"))

 #' test_path <- system.file("example","DATASET",package = "RGMQL")

 #' r = read_dataset(test_path)

 #' s = filter(r)

-#' m = aggregate(s, groupBy = c("antibody_targer","cell_karyotype"))

+#' m = aggregate(s, DF("antibody_targer","cell_karyotype"))

 #' materialize(m, dir_out = test_path)

 #' 

 #' @aliases materialize-method

@@ -101,14 +100,14 @@ setGeneric("materialize", function(data, ...) standardGeneric("materialize"))

 setMethod("materialize", "GMQLDataset",

             function(data, dir_out = getwd())

             {

-                gmql_materialize(data, dir_out)

+                ptr_data <- data@value

+                gmql_materialize(ptr_data, dir_out)

             })

-

-gmql_materialize <- function(data, dir_out)

+gmql_materialize <- function(input_data, dir_out)

 {

     WrappeR <- J("it/polimi/genomics/r/Wrapper")

-    response <- WrappeR$materialize(data@value,dir_out)

+    response <- WrappeR$materialize(input_data, dir_out)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -132,31 +131,41 @@ gmql_materialize <- function(data, dir_out)

 #' @importFrom rJava J

 #' @importFrom rJava .jevalArray

 #' 

-#' @param input_data returned object from any GMQL function

+#' @param data returned object from any GMQL function

 #' @param rows number of rows for each sample regions that you want to 

 #' retrieve and stored in memory.

 #' by default is 0 that means take all rows for each sample

-#'

+#' 

+#' @param ... Additional arguments for use in specific methods

+#' 

 #' @return GrangesList with associated metadata

 #'

 #' @examples

 #'

 #' init_gmql()

 #' test_path <- system.file("example", "DATASET", package = "RGMQL")

-#' r = read_dataset(test_path)

-#' m = aggregate(r, groupBy = c("antibody_target", "cell_karyotype"))

-#' g <- take(m, rows = 45)

+#' rd = read_dataset(test_path)

+#' aggr = aggregate(rd, DF("antibody_target", "cell_karyotype"))

+#' taken <- take(aggr, rows = 45)

 #' 

+#' @aliases take-method

 #' @export

-#'

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

+setMethod("take", "GMQLDataset",

+            function(data, rows = 0L)

+            {

+                ptr_data <- data@value

+                gmql_take(ptr_data, rows)

+            })

+

+

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

 {

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

     if(rows<0)

         stop("rows cannot be negative")

     WrappeR <- J("it/polimi/genomics/r/Wrapper")

-    response <- WrappeR$take(input_data@value,rows)

+    response <- WrappeR$take(input_data, rows)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -16,22 +16,19 @@

 #' @importFrom rJava .jarray

 #'  

 #' @param data GMQLDataset class object 

-#' @param groupBy list of CONDITION objects where every object contains 

-#' the name of metadata to be used in semijoin, or simple string concatenation 

-#' of name of metadata, e.g. c("cell_type", "attribute_tag", "size") 

-#' without declaring condition.

-#' The CONDITION's available are:

+#' @param ... Additional arguments for use in specific methods.

+#' 

+#' 

+#' This method accept a function to define condition evaluation on metadata.

 #' \itemize{

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

+#' \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{EXACT}}: Exact evaluation, only attributes exactly 

+#' \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.}

 #' }

-#' Every condition accepts only one string value. (e.g. FULL("cell_type") )

-#' In case of single concatenation with no CONDITION, or list with some value 

-#' without conditon, the metadata are considered having default 

-#' evaluation: the two attributes match if both end with value.

 #' 

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

 #' for the subsequent GMQL function

@@ -41,33 +38,37 @@

 #' # It creates a dataset called merged which contains one sample for each 

 #' # antibody_target value found within the metadata of the exp dataset sample; 

 #' # each created sample contains all regions from all 'exp' samples 

-#' # with a specific value for their antibody_target metadata attribute.

+#' # with a specific value for their antibody_target and cell metadata 

+#' # attributes.

 #' 

 #' init_gmql()

 #' test_path <- system.file("example","DATASET",package = "RGMQL")

 #' exp = read_dataset(test_path)

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

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

 #' 

 #' @aliases aggregate-method

 #' @export

 #' 

 setMethod("aggregate", "GMQLDataset",

-            function(data, groupBy = NULL)

+            function(data, ...)

             {

-                val = data@value

-                gmql_merge(val, groupBy)

+                ptr_data = data@value

+                groupBy = list(...)

+                gmql_merge(ptr_data, groupBy)

             })

-gmql_merge <- function(data, groupBy = NULL)

+gmql_merge <- function(input_data, groupBy)

 {

-    if(!is.null(groupBy))

-        join_condition_matrix <- .jarray(.join_condition(groupBy), 

-                                            dispatch = TRUE)

+    if(!is.null(groupBy) && !length(groupBy) == 0)

+    {

+        cond <- .join_condition(groupBy)

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

+    }

     else

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

     WrappeR <- J("it/polimi/genomics/r/Wrapper")

-    response <- WrappeR$merge(join_condition_matrix,data)

+    response <- WrappeR$merge(join_condition_matrix, input_data)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -42,7 +42,7 @@

 #' \itemize{

 #' \item{All aggregation functions already defined by AGGREGATES object}

 #' \item{All basic mathematical operations (+, -, *, /), including parenthesis}

-#' \item{SQRT, META, NULLABLE constructor object defined by OPERATOR object}

+#' \item{SQRT, META, NIL constructor object defined by OPERATOR object}

 #' }

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

 #' for the subsequent GMQL function

@@ -73,7 +73,7 @@

 #' ## the four basic coordinates (chr, left, right, strand) and the specified 

 #' ## region attributes 'variant_classification' and 'variant_type', 

 #' ## and as metadata attributes only the specified ones, 

-#' ## i.e. manually_curated__tissue_status and manually_curated__tumor_tag.

+#' ## i.e. manually_curated_tissue_status and manually_curated_tumor_tag.

 #' 

 #' init_gmql()

 #' test_path <- system.file("example", "DATASET", package = "RGMQL")

@@ -118,7 +118,8 @@ init_gmql <- function(output_format = "gtf", remote_processing = FALSE,

 #' r2 = read_dataset("public.HG19_TCGA_dnaseq",is_local = FALSE)

 #' 

 #' }

-#' 

+#' @name read

+#' @rdname read-function

 #' @export

 #'

 read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE, 

@@ -137,6 +138,11 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

         if(basename(dataset) !="files")

             dataset <- paste0(dataset,"/files")

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

+                                    full.names = TRUE)

+        if(length(schema_XML) == 0)

+            stop("schema must be present")

+        

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

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

     }

@@ -159,11 +165,12 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

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

         else

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

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

     }

     parser_name <- .check_parser(parser)

     response <- WrappeR$readDataset(dataset,parser_name, is_local, is_GMQL, 

-                                        schema_matrix)

+                                        schema_matrix,schema_XML)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -182,21 +189,9 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

 #' 

 #' @param samples GrangesList

 #' 

-#' @return DataSet class object. It contains the value to use as input 

-#' for the subsequent GMQL function

 #' 

-#' @examples

-#' 

-#' library("GenomicRanges")

-#' gr1 <- GRanges(seqnames = "chr2", ranges = IRanges(103, 106),

-#' strand = "+", score = 5L, GC = 0.45)

-#' gr2 <- GRanges(seqnames = c("chr1", "chr1"), ranges = IRanges(c(107, 113), 

-#' width = 3), strand = c("+", "-"), score = 3:4, GC = c(0.3, 0.5))

-#' 

-#' grl <- GRangesList("txA" = gr1, "txB" = gr2)

-#' 

-#' data_out <- read(grl)

-#'

+#' @name read

+#' @rdname read-function

 #' @export

 #'

 read <- function(samples)

@@ -22,29 +22,11 @@

 #' @param r_predicate logical predicate made up by R logical operation 

 #' on chema region values. 

 #' Only !, |, ||, &, && are admitted.

-#' @param semi_join vector of CONDITION objects where every object contains 

-#' the name of metadata to be used in semijoin, or simple string concatenation 

-#' of name of metadata, e.g. c("cell_type", "attribute_tag", "size") 

-#' without declaring condition.

-#' The CONDITION's available are:

-#' \itemize{

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

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

-#' }

-#' Every condition accepts only one string value. (e.g. FULL("cell_type") )

-#' In case of single concatenation with no CONDITION the metadata are 

-#' considered having default evaluation: 

-#' the two attributes match if both end with value.

+#' @param ... Additional arguments for use in specific methods.

 #' 

-#' @param not_in logical value: T => semijoin is perfomed 

-#' considering semi_join NOT IN semi_join_dataset, F => semijoin is performed 

-#' considering semi_join IN semi_join_dataset

+#' @param semijoin \code{\link{semijoin}} function 

+#' to define filter method with semijoin condition (see examples).

 #' 

-#' @param semi_join_dataset GMQLDataset class object

-#' @param ... Additional arguments for use in specific methods.

 #' 

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

 #' for the subsequent GMQL function

@@ -59,7 +41,6 @@

 #' input <- read_dataset(test_path)

 #' s <- filter(input, Patient_age < 70)

 #' 

-#' 

 #' \dontrun{

 #' 

 #' It creates a new dataset called 'jun_tf' by selecting those samples and 

@@ -80,8 +61,8 @@

 #' test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 #' data <- read_dataset(test_path)

 #' join_data <-  read_dataset(test_path2)

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

-#' TRUE, semi_join_dataset = join_data )

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

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

 #' 

 #' }

 #' 

@@ -89,8 +70,7 @@

 #' @export

 setMethod("filter", "GMQLDataset",

             function(.data, m_predicate = NULL, r_predicate = NULL, 

-                    semi_join = NULL, not_in = FALSE, 

-                    semi_join_dataset = NULL)

+                        semijoin = NULL, ...)

             {

                 val <- .data@value

                 meta_pred <- substitute(m_predicate)

@@ -110,44 +90,20 @@ setMethod("filter", "GMQLDataset",

                 }

                 else

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

-            

-                gmql_select(val, predicate, region_predicate, 

-                        semi_join, not_in, semi_join_dataset)