## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  eval = any(dir.exists(c("working_example_data", "benchmark_data", "new_benchmark_data", "topic_data", "valid_data", "new_stage_data"))),
  comment = "#>",
  warning = FALSE,
  fig.width = 6,
  fig.height = 6
)

## ----results = FALSE, message=FALSE, warning=FALSE----------------------------
#install.packages("CiteSource")
library(CiteSource)

## -----------------------------------------------------------------------------
file_path <- "../vignettes/new_benchmark_data/"
citation_files <- list.files(path = file_path, pattern = "\\.ris", full.names = TRUE)
citation_files

## -----------------------------------------------------------------------------
imported_tbl <- tibble::tribble(
  ~files,              ~cite_sources,  ~cite_labels,
  "benchmark_15.ris",  "benchmark",    "benchmark",
  "search1_166.ris",   "search 1",     "search",
  "search2_278.ris",   "search 2",     "search",
  "search3_302.ris",   "search 3",     "search",
  "search4_460.ris",   "search 4",     "search",
  "search5_495.ris",   "search 5",     "search"
) |>
  dplyr::mutate(files = paste0(file_path, files))

raw_citations <- read_citations(metadata = imported_tbl, verbose = FALSE)

## -----------------------------------------------------------------------------
unique_citations  <- dedup_citations(raw_citations)
n_unique          <- count_unique(unique_citations)
source_comparison <- compare_sources(unique_citations, comp_type = "sources")

## -----------------------------------------------------------------------------
initial_records <- calculate_initial_records(unique_citations)
create_initial_record_table(initial_records)

## ----fig.alt="An upset plot visualizing the overlap of benchmarking articles found across five search strategies. Nine articles were identified by all five searches; four benchmarking articles were missed entirely."----
plot_source_overlap_upset(source_comparison, decreasing = c(TRUE, TRUE))

## -----------------------------------------------------------------------------
unique_citations |>
  dplyr::filter(stringr::str_detect(cite_source, "benchmark")) |>
  record_level_table(return = "DT")

## -----------------------------------------------------------------------------
detailed_records <- calculate_detailed_records(unique_citations, n_unique)
create_detailed_record_table(detailed_records)

## -----------------------------------------------------------------------------
# Export deduplicated results as CSV, RIS, or BibTeX
#export_csv(unique_citations, filename = "citesource_benchmark_export.csv")
#export_ris(unique_citations, filename = "citesource_benchmark_export.ris", source_field = "DB", label_field = "C5")
#export_bib(unique_citations, filename = "citesource_benchmark_export.bib", include = c("sources", "labels", "strings"))

# Reimport a previously exported file
#unique_citations <- reimport_csv("citesource_benchmark_export.csv")
#n_unique <- count_unique(unique_citations)
#source_comparison <- compare_sources(unique_citations, comp_type = "sources")