diff EnzymeCompound.R @ 0:3afe41d3e9e7 draft

planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit bb4d3e23d99828bfee16d31d794c49a17313ec2f

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/EnzymeCompound.R	Mon Jul 11 09:12:03 2016 -0400
@@ -0,0 +1,61 @@
+if ( ! exists('EnzymeCompound')) { # Do not load again if already loaded
+
+	source('BiodbEntry.R')
+
+	#####################
+	# CLASS DECLARATION #
+	#####################
+
+	EnzymeCompound <- setRefClass("EnzymeCompound", contains = 'BiodbEntry')
+
+	###########
+	# FACTORY #
+	###########
+
+	createEnzymeCompoundFromTxt <- function(contents, drop = TRUE) {
+
+		library(stringr)
+
+		compounds <- list()
+	
+		# Define fields regex
+		regex <- character()
+		regex[[RBIODB.ACCESSION]] <- "^ID\\s+([0-9.]+)$"
+		regex[[RBIODB.DESCRIPTION]] <- "^DE\\s+(.+)$"
+
+		for (text in contents) {
+
+			# Create instance
+			compound <- EnzymeCompound$new()
+
+			lines <- strsplit(text, "\n")
+			for (s in lines[[1]]) {
+
+				# Test generic regex
+				parsed <- FALSE
+				for (field in names(regex)) {
+					g <- str_match(s, regex[[field]])
+					if ( ! is.na(g[1,1])) {
+						compound$setField(field, g[1,2])
+						parsed <- TRUE
+						break
+					}
+				}
+				if (parsed)
+					next
+			}
+
+			compounds <- c(compounds, compound)
+		}
+
+		# Replace elements with no accession id by NULL
+		compounds <- lapply(compounds, function(x) if (is.na(x$getField(RBIODB.ACCESSION))) NULL else x)
+
+		# If the input was a single element, then output a single object
+		if (drop && length(contents) == 1)
+			compounds <- compounds[[1]]
+	
+		return(compounds)
+
+	}
+}