Skip to content

refactor: remove the fill_dois function #865

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
andreishket wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

refactor: remove the fill_dois function #865

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 0 additions & 33 deletions server/preprocessing/other-scripts/openaire.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,11 +52,6 @@ get_papers <- function(query, params) {
funder = funder,
format = 'xml')
pubs_metadata <- parse_response(response)
# FYI: The deactivation of the fill_dois() function is a hotfix
# to enable creation of OpenAIRE project maps
# TODO: root cause analysis of failure mode
# TODO: refactor/replace/remove the function, decision pending
#pubs_metadata <- fill_dois(pubs_metadata)
},
error = function(err){
olog$warn(paste0("vis_id:", .GlobalEnv$VIS_ID, "publications: ", err))
Expand Down Expand Up @@ -193,34 +188,6 @@ parse_response <- function(response) {
}
}

fill_dois <- function(df) {
missing_doi_indices <- which(is.na(df$doi))
titles <- df[missing_doi_indices,]$title
if (exists("DEBUG") && DEBUG) {
olog$debug(paste("Missing DOIs:", length(titles)))
olog$debug("Time for filling missing DOIs")
olog$debug(system.time(cr_works(query=queries(titles), async=TRUE)))
}
tryCatch({
if (length(titles) > 1) {
response <- cr_works(query=queries(titles))
candidates <- lapply(response, get_doi_candidates)
dois <- mapply(check_distance, titles, candidates, USE.NAMES=FALSE)
} else if (length(titles) == 1) {
response <- cr_works(flq=c('query.title'=titles))$data
candidate_response = response[1,]
dois <- check_distance(titles, candidate_response)
} else {
dois <- ""
}
df$doi[c(missing_doi_indices)] <- dois
}, error=function(err){
olog$error(paste("vis_id:", .GlobalEnv$VIS_ID, "DOI enrichment failed:", paste(err)))
}
)
return (df)
}

get_doi_candidates <- function(response){
if (nrow(response) >= 1) {
candidate = response[1,c('doi', 'title')]
Expand Down
Loading