diff MassbankCompound.R @ 0:e66bb061af06 draft

planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit 3529b25417f8e1a5836474c9adec4b696d35099d-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/MassbankCompound.R	Tue Jul 12 12:02:37 2016 -0400
@@ -0,0 +1,66 @@
+if ( ! exists('MassbankCompound')) { # Do not load again if already loaded
+
+	source('BiodbEntry.R')
+	
+	#####################
+	# CLASS DECLARATION #
+	#####################
+	
+	MassbankCompound <- setRefClass("MassbankCompound", contains = "BiodbEntry")
+
+	###########
+	# FACTORY #
+	###########
+	
+	createMassbankCompoundFromTxt <- function(contents) {
+
+		library(stringr)
+
+		compounds <- list()
+
+		for (text in contents) {
+
+			# Create instance
+			compound <- MassbankCompound$new()
+
+			# Read text
+			lines <- strsplit(text, "\n")
+			for (s in lines[[1]]) {
+
+				# NAME
+				if (is.na(compound$getField(RBIODB.NAME))) {
+					g <- str_match(s, "^CH\\$NAME:\\s+(.+)$")
+					if ( ! is.na(g[1,1]))
+						compound$setField(RBIODB.NAME, g[1,2])
+				}
+		
+				# CHEBI ID
+				g <- str_match(s, "^CH\\$LINK: CHEBI\\s+(.+)$")
+				if ( ! is.na(g[1,1]))
+					compound$setField(RBIODB.CHEBI.ID, g[1,2])
+		
+				# KEGG ID
+				g <- str_match(s, "^CH\\$LINK: KEGG\\s+(.+)$")
+				if ( ! is.na(g[1,1]))
+					compound$setField(RBIODB.KEGG.ID, g[1,2])
+		
+				# PUBCHEM ID
+				g <- str_match(s, "^CH\\$LINK: PUBCHEM\\s+(.+)$")
+				if ( ! is.na(g[1,1]))
+					compound$setField(RBIODB.PUBCHEM.ID, g[1,2])
+		
+				# INCHI
+				g <- str_match(s, "^CH\\$IUPAC:\\s+(.+)$")
+				if ( ! is.na(g[1,1]))
+					compound$setField(RBIODB.INCHI, g[1,2])
+			}
+
+			compounds <- c(compounds, compound)
+		}
+
+		# Replace elements with no accession id by NULL
+		compounds <- lapply(compounds, function(x) if (is.na(x$getField(RBIODB.NAME))) NULL else x)
+
+		return(compounds)
+	}
+}