Mercurial > repos > prog > lcmsmatching

annotate NcbiccdsEntry.R @ 5:18254e8d1b72 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit 947b8707b06176a4801de64a71c8771617311ffb-dirty
author prog
date Thu, 16 Mar 2017 08:15:11 -0400
parents 45e985cd8e9e
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
1 #####################
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
2 # CLASS DECLARATION #
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
3 #####################
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
4
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
5 NcbiccdsEntry <- methods::setRefClass("NcbiccdsEntry", contains = "BiodbEntry")
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
6
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
7 ###########
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
8 # FACTORY #
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
9 ###########
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
10
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
11 createNcbiccdsEntryFromHtml <- function(contents, drop = TRUE) {
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
12
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
13 entries <- list()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
14
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
15 for (html in contents) {
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
16
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
17 # Create instance
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
18 entry <- NcbiccdsEntry$new()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
19
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
20 # Parse HTML
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
21 xml <- XML::htmlTreeParse(html, asText = TRUE, useInternalNodes = TRUE)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
22
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
23 if (length(XML::getNodeSet(xml, "//*[starts-with(.,'No results found for CCDS ID ')]")) == 0) {
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
24 entry$setField(BIODB.ACCESSION, XML::xpathSApply(xml, "//input[@id='DATA']", XML::xmlGetAttr, "value"))
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
25 entry$setField(BIODB.SEQUENCE, XML::xpathSApply(xml, "//b[starts-with(.,'Nucleotide Sequence')]/../tt", XML::xmlValue))
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
26 }
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
27
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
28 entries <- c(entries, entry)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
29 }
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
30
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
31 # Replace elements with no accession id by NULL
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
32 entries <- lapply(entries, function(x) if (is.na(x$getField(BIODB.ACCESSION))) NULL else x)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
33
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
34 # If the input was a single element, then output a single object
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
35 if (drop && length(contents) == 1)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
36 entries <- entries[[1]]
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
37
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
38 return(entries)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
39 }