Added travis and codecoverage support.

.Rbuildignore

@@ -1,3 +1,5 @@
 ^scythe\.Rproj$
 ^\.Rproj\.user$
 ^LICENSE\.md$
+^\.travis\.yml$
+^codecov\.yml$

.travis.yml

@@ -0,0 +1,7 @@
+# R for travis: see documentation at https://docs.travis-ci.com/user/languages/r
+
+language: R
+cache: packages
+
+after_success:
+    - Rscript -e 'covr::codecov()'

DESCRIPTION

@@ -12,4 +12,6 @@ License: Apache License (>= 2.0)
 Encoding: UTF-8
 LazyData: true
 Suggests: 
-    testthat (>= 2.1.0)
+    testthat (>= 2.1.0),
+    covr
+RoxygenNote: 7.0.2

NAMESPACE

@@ -1,2 +1,9 @@
-# Generated by roxygen2: fake comment so roxygen2 overwrites silently.
-exportPattern("^[^\\.]")
+# Generated by roxygen2: do not edit by hand
+
+import(bib2df)
+import(curl)
+import(dataone)
+import(dplyr)
+import(jsonlite)
+import(rcrossref)
+import(xml2)

R/brute_force_query_master.R

@@ -5,63 +5,76 @@
 # rdatacite package
 # opencitations.net
 
-library(jsonlite)
-library(dplyr)
-library(xml2)
-library(curl)
-
-## bash SCOPUS queries
-# Need to use our API key in links below (saved separately)
-#
-# # multi-page ADC
-# for pg in 0 26; do curl https://api.elsevier.com/content/search/scopus?query=ALL:10.18739\&date=2009-2019\&APIKey=${APIKEY}\&start=${pg} -o results/scopus-10.18739-2009-2019-pg${pg}.json; done
-# 
-# # multi-page KNB
-# for pg in 0 26; do curl https://api.elsevier.com/content/search/scopus?query==ALL:10.5063\&date=2009-2019\&APIKey=${APIKEY}\&start=${pg} -o results/scopus-10.5063-2009-2019-pg${pg}.json; done
-
-# query for ADC DOIs
-cn <- CNode("PROD")
-mn <- getMNode(cn, "urn:node:ARCTIC")
-
-result <- query(mn, list(q = "formatType:METADATA AND (*:* NOT obsoletedBy:*)",
-                                fl = "identifier,rightsHolder,formatId",
-                                start ="0",
-                                rows = "15000"),
-                                as="data.frame")
-
-dois <- grep("doi", result$identifier, value = T) %>% 
-  gsub("doi:", "", .)
-
-# brute force query SCOPUS for each DOI
-t <- list()
-for (i in 1:length(dois)){
-  t[[i]] <- fromJSON(curl(paste0("https://api.elsevier.com/content/search/scopus?query=ALL:",dois[i],"&APIKey=ae55f95a9d2f56c21147d3f9f6c4eef0")))
+#' @import dplyr
+#' @import jsonlite
+#' @import xml2
+#' @import curl
+#' @import dataone
+brute_force_query_master <- function() {
+    ## bash SCOPUS queries
+    # Need to use our API key in links below (saved separately)
+    #
+    # # multi-page ADC
+    # for pg in 0 26; do curl https://api.elsevier.com/content/search/scopus?query=ALL:10.18739\&date=2009-2019\&APIKey=${APIKEY}\&start=${pg} -o results/scopus-10.18739-2009-2019-pg${pg}.json; done
+    #
+    # # multi-page KNB
+    # for pg in 0 26; do curl https://api.elsevier.com/content/search/scopus?query==ALL:10.5063\&date=2009-2019\&APIKey=${APIKEY}\&start=${pg} -o results/scopus-10.5063-2009-2019-pg${pg}.json; done
+
+    # query for ADC DOIs
+    cn <- CNode("PROD")
+    mn <- getMNode(cn, "urn:node:ARCTIC")
+
+    result <-
+        query(mn, list(
+                    q = "formatType:METADATA AND (*:* NOT obsoletedBy:*)",
+                    fl = "identifier,rightsHolder,formatId",
+                    start = "0",
+                    rows = "15000"),
+                as = "data.frame"
+        )
+    dois <- grep("doi", result$identifier, value = T) %>%
+        gsub("doi:", "", .)
+
+    # brute force query SCOPUS for each DOI
+    t <- list()
+    for (i in 1:length(dois)) {
+        t[[i]] <-
+            fromJSON(curl(paste0("https://api.elsevier.com/content/search/scopus?query=ALL:", dois[i], "&APIKey=ae55f95a9d2f56c21147d3f9f6c4eef0")
+            ))
+    }
+
+    # find the number of results per DOI
+    res <-
+        lapply(t, function(x) {
+            x$`search-results`$`opensearch:totalResults`
+        })
+
+    # filter out DOIs with no results
+    t_working <- t[which(res != 0)]
+
+    # pull out information for datasets with results
+    t_results <- lapply(t_working, function(x) {
+        x$`search-results`$entry$search <-
+            x$`search-results`$`opensearch:Query`$`@searchTerms`
+        return(x$`search-results`$entry)
+    })
+
+
+    results <- do.call(bind_rows, t_results)
+
+    # trim out unnecessary information
+    results_slim <- results %>%
+        dplyr::select(`prism:doi`, search) %>%
+        mutate(search = gsub("ALL:", "", search)) %>%
+        rename(
+            journal = `prism:doi`,
+            adc_dataset = search
+        )
+
+    # left col - citer, right col - citee
+    write.csv(
+        results_slim,
+        "~/dataone-citations/results/brute_force_results.csv",
+        row.names = F
+    )
 }
-
-# find the number of results per DOI
-res <- lapply(t, function(x){x$`search-results`$`opensearch:totalResults`})
-
-# filter out DOIs with no results
-t_working <- t[which(res != 0)]
-
-# pull out information for datasets with results
-t_results <- lapply(t_working, function(x){
-  x$`search-results`$entry$search <- x$`search-results`$`opensearch:Query`$`@searchTerms`
-  return(x$`search-results`$entry)
-  })
-
-
-results <- do.call(bind_rows, t_results)
-
-# trim out unnecessary information
-results_slim <- results %>% 
-  dplyr::select(`prism:doi`, search) %>% 
-  mutate(search = gsub("ALL:", "", search)) %>% 
-  rename(journal = `prism:doi`,
-         adc_dataset = search)
-
-# left col - citer, right col - citee
-write.csv(results_slim, "~/dataone-citations/results/brute_force_results.csv", row.names = F)
-
-
-

R/write_citation_pairs.R

@@ -1,34 +1,35 @@
-library(rcrossref)
-library(jsonlite)
-library(bib2df)
+#' @import rcrossref
+#' @import jsonlite
+#' @import bib2df
+write_citation_pairs <- function() {
 
+    # manually generated citations list
+    cit <- read.csv("DBO_citations/citationlist.csv", stringsAsFactors = F)
 
-# manually generated citations list
-cit <- read.csv("DBO_citations/citationlist.csv", stringsAsFactors = F)
+    # write list of citations to bib format
+    bib <- cr_cn(dois = cit$publicationDOI, format = "bibtex")
+    writeLines(unlist(bib), "DBO_citations/all_citations.bib" )
 
-# write list of citations to bib format
-bib <- cr_cn(dois = cit$publicationDOI, format = "bibtex")
-writeLines(unlist(bib), "DBO_citations/all_citations.bib" )
+    # import as a dataframe
+    df <- bib2df("~/dataone-citations/DBO_citations/all_citations.bib")
+    df$datasetID <- cit$datasetID
 
-# import as a dataframe
-df <- bib2df("~/dataone-citations/DBO_citations/all_citations.bib")
-df$datasetID <- cit$datasetID
+    # rename for database ingest
+    cit_full <- df %>%
+        rename(target_id = datasetID,
+               source_id = DOI,
+               source_url = URL,
+               origin = AUTHOR,
+               title = TITLE,
+               publisher = PUBLISHER,
+               journal = JOURNAL,
+               volume = VOLUME,
+               page = PAGES,
+               year_of_publishing = YEAR) %>%
+        select(target_id, source_id, source_url, origin, title, publisher, journal, volume, page, year_of_publishing) %>%
+        mutate(id = NA, report = NA, metadata = NA, link_publication_date = NA) %>%
+        mutate(publisher = ifelse(publisher == "Elsevier {BV", "Elsevier", "Copernicus"))
 
-# rename for database ingest
-cit_full <- df %>% 
-  rename(target_id = datasetID,
-         source_id = DOI,
-         source_url = URL,
-         origin = AUTHOR,
-         title = TITLE,
-         publisher = PUBLISHER,
-         journal = JOURNAL,
-         volume = VOLUME,
-         page = PAGES,
-         year_of_publishing = YEAR) %>% 
-  select(target_id, source_id, source_url, origin, title, publisher, journal, volume, page, year_of_publishing) %>% 
-  mutate(id = NA, report = NA, metadata = NA, link_publication_date = NA) %>% 
-  mutate(publisher = ifelse(publisher == "Elsevier {BV", "Elsevier", "Copernicus"))
-
-write_json(cit_full, "~/dataone-citations/DBO_citations/citations_export.json")
+    write_json(cit_full, "~/dataone-citations/DBO_citations/citations_export.json")
+}
 

README.md

@@ -1,5 +1,6 @@
 [![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/scythe)](https://cran.r-project.org/package=scythe)
 [![Build Status](https://travis-ci.org/DataONEorg/scythe.png?branch=master)](https://travis-ci.org/DataONEorg/scythe)
+[![Codecov test coverage](https://codecov.io/gh/DataONEorg/scythe/branch/master/graph/badge.svg)](https://codecov.io/gh/DataONEorg/scythe?branch=master)
 [![Project Status: WIP – Initial development is in progress, but there has not yet been a stable, usable release suitable for the public.](https://www.repostatus.org/badges/latest/wip.svg)](https://www.repostatus.org/#wip)
 
 - **Authors**: TBD

codecov.yml

@@ -0,0 +1,12 @@
+comment: false
+
+coverage:
+  status:
+    project:
+      default:
+        target: auto
+        threshold: 1%
+    patch:
+      default:
+        target: auto
+        threshold: 1%