diff NcbiccdsEntry.R @ 2:20d69a062da3 draft

planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/NcbiccdsEntry.R	Thu Mar 02 08:55:00 2017 -0500
@@ -0,0 +1,39 @@
+#####################
+# CLASS DECLARATION #
+#####################
+
+NcbiccdsEntry <- methods::setRefClass("NcbiccdsEntry", contains = "BiodbEntry")
+
+###########
+# FACTORY #
+###########
+
+createNcbiccdsEntryFromHtml <- function(contents, drop = TRUE) {
+
+	entries <- list()
+
+	for (html in contents) {
+
+		# Create instance
+		entry <- NcbiccdsEntry$new()
+	
+		# Parse HTML
+		xml <-  XML::htmlTreeParse(html, asText = TRUE, useInternalNodes = TRUE)
+
+		if (length(XML::getNodeSet(xml, "//*[starts-with(.,'No results found for CCDS ID ')]")) == 0) {
+			entry$setField(BIODB.ACCESSION, XML::xpathSApply(xml, "//input[@id='DATA']", XML::xmlGetAttr, "value"))
+			entry$setField(BIODB.SEQUENCE, XML::xpathSApply(xml, "//b[starts-with(.,'Nucleotide Sequence')]/../tt", XML::xmlValue))
+		}
+
+		entries <- c(entries, entry)
+	}
+
+	# Replace elements with no accession id by NULL
+	entries <- lapply(entries, function(x) if (is.na(x$getField(BIODB.ACCESSION))) NULL else x)
+
+	# If the input was a single element, then output a single object
+	if (drop && length(contents) == 1)
+		entries <- entries[[1]]
+
+	return(entries)
+}