Mercurial > repos > prog > lcmsmatching

annotate MirbaseEntry.R @ 2:9a0288561ba3 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 476a081c0da66822f4e77070f5ce59d9f14511f4-dirty
author prog
date Thu, 02 Mar 2017 11:09:37 -0500
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 MirbaseEntry <- methods::setRefClass("MirbaseEntry", 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 createMirbaseEntryFromHtml <- 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 # Define fields regex
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
16 xpath.expr <- character()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
17 xpath.expr[[BIODB.ACCESSION]] <- "//td[text()='Accession number']/../td[2]"
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
18 xpath.expr[[BIODB.NAME]] <- "//td[text()='ID']/../td[2]"
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
19 xpath.expr[[BIODB.SEQUENCE]] <- "//td[text()='Sequence']/..//pre"
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
20
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
21 for (html in contents) {
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 # Create instance
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
24 entry <- MirbaseEntry$new()
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
25
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
26 # Parse HTML
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
27 xml <- XML::htmlTreeParse(html, asText = TRUE, useInternalNodes = TRUE)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
28
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
29 # Test generic xpath expressions
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
30 for (field in names(xpath.expr)) {
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
31 v <- XML::xpathSApply(xml, xpath.expr[[field]], XML::xmlValue)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
32 if (length(v) > 0)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
33 entry$setField(field, v)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
34 }
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
35
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
36 entries <- c(entries, entry)
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
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
39 # 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
40 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
41
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
42 # 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
43 if (drop && length(contents) == 1)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
44 entries <- entries[[1]]
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
45
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
46 return(entries)
45e985cd8e9e planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8-dirty
prog
parents:
diff changeset
47 }