diff NcbiCcdsCompound.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/NcbiCcdsCompound.R	Tue Jul 12 12:02:37 2016 -0400
@@ -0,0 +1,46 @@
+if ( ! exists('NcbiccdsCompound')) { # Do not load again if already loaded
+
+	source('BiodbEntry.R')
+
+	#####################
+	# CLASS DECLARATION #
+	#####################
+
+	NcbiccdsCompound <- setRefClass("NcbiccdsCompound", contains = "BiodbEntry")
+
+	###########
+	# FACTORY #
+	###########
+
+	createNcbiccdsCompoundFromHtml <- function(contents, drop = TRUE) {
+
+		library(XML)
+
+		compounds <- list()
+
+		for (html in contents) {
+
+			# Create instance
+			compound <- NcbiccdsCompound$new()
+		
+			# Parse HTML
+			xml <-  htmlTreeParse(html, asText = TRUE, useInternalNodes = TRUE)
+
+			if (length(getNodeSet(xml, "//*[starts-with(.,'No results found for CCDS ID ')]")) == 0) {
+				compound$setField(RBIODB.ACCESSION, xpathSApply(xml, "//input[@id='DATA']", xmlGetAttr, "value"))
+				compound$setField(RBIODB.SEQUENCE, xpathSApply(xml, "//b[starts-with(.,'Nucleotide Sequence')]/../tt", xmlValue))
+			}
+
+			compounds <- c(compounds, compound)
+		}
+
+		# Replace elements with no accession id by NULL
+		compounds <- lapply(compounds, function(x) if (is.na(x$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)
+	}
+}