Pre-process a bib file for clean use in documentation

prepare_bib.R

# To prepare it for use in documentation, import a .bib file, strip Bibdesk's extra fields and additions, and enclose each entry with code compatible with Latex's {listings} package.

library(dplyr)
library(stringr)
library(readr)

# 0. Set relative file path for the bibfile
# setwd()

# 1. read the bib file as a vector of lines
bibdata <- scan("handbook9.bib", what="character", sep = "\n") %>% .[-c(1:4)]

# 2. Drop the smart list from the end
bibdata <- bibdata[-c(grep("@comment\\{BibDesk Smart Groups",bibdata):length(bibdata))]

# 3. Find all the lines that include undesirable fields created by Bibdesk and add these line numbers to a vector. Make sure to exclude any line numbers that are at the end of a source entry.
badlines <- grep("\tBdsk-Url-1|\tdate-added|\tdate-modified",bibdata) %>%
  .[!c(. %in% grep("}}",bibdata))]

# 4. Drop these bad lines
bibdata <- bibdata[-badlines]

# 5. Index the start and end of each entry
startlines <- grep("^@",bibdata)
endlines <-
  (startlines[2:length(startlines)]-1) %>%
  c(length(bibdata))

# 6. Tidy up any remaining undesirable fields that were left behind (because they were the last line in a source entry) by reducing them to just the closing bracket.
bibdata[grep("\tBdsk-Url-1|\tdate-added|\tdate-modified",bibdata)] <- "}"

# 7. Get a list of cite keys in order.
citekeys <- bibdata[startlines] %>%
  str_remove("^@[a-z]*\\{") %>%
  str_remove(",")

# 8. Start each entry with a {listings}-compatible opening that references its cite key.
bibdata[startlines] <-
  paste("%[[", citekeys, "]]")%>%
  paste(bibdata[startlines], sep="\n")

# 9. End each entry with a {listings}-compatible close.
bibdata[endlines] <-
  paste("%[[", "end", "]]")%>%
  paste(bibdata[endlines], ., sep="\n")

# 10. Convert the vector to a single block of text.
bibtext <- bibdata %>%
  paste(collapse = "\n")

# 11. Clean up any dangling brackets.
bibtext <- gsub("\n}","}", bibtext) %>%
  gsub(",}","}",.)

# 12. Save it to a new file.
write_file(bibtext, "handbook9_clean.bib")