In jeksterslabds/jeksterslabRlib: Utility Functions to Organize my Personal Library

Data Source

data_source <- "https://adminportal.springernature.com/metadata/books"

Data is sourced from r paste0("[Springer Nature Metadata]", "(", data_source, ")").

Languages and eBook Collections

• English/International
  • Computer Science without Lecture Notes (starting 1960)
  • Lecture Notes in Computer Science
  • Mathematics and Statistics without Lecture Notes (starting 1929)
  • Lecture Notes in Mathematics

Subject Classification

all

• Computer Science
• Education
• Mathematics
• Philosophy
• Popular Science
• Psychology
• Social Sciences
• Statistics

parts

• Architecture / Design
  • Design, general
  • Graphic Design
• Business and Management
  • Management
  • Project Management
  • Knowledge Management
  • Operations Research/Decision Theory
  • IT in Business
  • Business Mathematics
• Criminology and Criminal Justice
  • Research Methods in Criminology
• Cultural and Media Studies
  • Photography
  • Printing and Publishing
  • Library Science
• Economics
  • History of Economic Thought/Methodology
  • Economic Theory/Quantitative Economics/Mathematical Methods
  • Behavioral/Experimental Economics
• Life Sciences
  • Bioinformatics
  • Behavioral Sciences
  • Computer Appl. in Life Science
• Linguistics
  • Research Methods in Language and Linguistics
• Medicine & Public Health
  • Health Informatics
  • Epidemiology

Set parameters

• If production = TRUE, use production data (SpringerNature_Books*).
• If production = FALSE, use test data (Tests_Springer*).

Library

source("https://raw.githubusercontent.com/jeksterslabds/jeksterslabRutils/master/R/util_txt2file.R")
source("https://raw.githubusercontent.com/jeksterslabds/jeksterslabRterm/master/R/term_user_lib.R")
term_user_lib()

repos <- "https://cran.rstudio.org"
if (!require("remotes")) {
  install.packages(
    "remotes",
    repos = repos
  )
}
pkg <- c(
  "jeksterslabRpkg",
  "jeksterslabRutils",
  "jeksterslabRlib"
)
foo <- function(pkg) {
  if (!require(pkg, character.only = TRUE)) {
    remotes::install_github(
      paste0(
        "jeksterslabds/",
        pkg
      )
    )
  }
}
invisible(
  lapply(
    X = pkg,
    FUN = foo
  )
)

Set parameters

tmp_dir <- tempdir()
root <- pkg_find_root(pkg_name = "jeksterslabRlib")
dir <- "/media/jeksterslib/books/springer"
production <- TRUE
chkfiles <- FALSE
par <- TRUE
ncores <- parallel::detectCores() - 1
if (production) {
  pattern <- "^SpringerNature_Books*"
} else {
  pattern <- "^Test_Springer*"
}
cat(
  paste0(
    "Parameters:\n",
    "\t", "dir = ", "\"", dir, "\"", "\n",
    "\t", "production = ", production, "\n",
    "\t", "chkfiles = ", chkfiles, "\n",
    "\t", "par = ", par, "\n",
    "\t", "ncores = ", ncores, "\n"
  )
)

Build Springer Books data

cat(
  "Binding Springer Books data from SpringerNature...\n"
)
files <- list.files(
  pattern = glob2rx(
    paste0(
      pattern,
      ".zip"
    )
  )
)
for (i in seq_along(files)) {
  unzip(
    zipfile = files[i],
    exdir = tmp_dir
  )
}
springer_books <- util_bind(
  dir = tmp_dir,
  format = "xlsx",
  pattern = pattern,
  fn_column = FALSE,
  save = FALSE
)
springer_books_doi <- unique(
  springer_books[["DOI URL"]]
)
springer_books <- springer_books[!duplicated(springer_books[["DOI URL"]]), ]

Get available files

cat(
  paste0(
    "Checking downloaded files in ",
    dir,
    "...",
    "\n"
  )
)
springer_books_available <- lib_springer_files(dir = dir)
doi_pdf <- lib_remove_doi_http(
  springer_books_available[["available_pdf"]][["DOI URL"]]
)
doi_epub <- lib_remove_doi_http(
  springer_books_available[["available_epub"]][["DOI URL"]]
)
doi_root_pdf <- lib_remove_doi_prefix(doi = doi_pdf)
doi_root_epub <- lib_remove_doi_prefix(doi = doi_epub)

Check PDF files and delete invalid files

if (chkfiles) {
  cat(
    "Checking and deleting invalid PDF documents...\n"
  )
  util_check_file_type(
    dir = dir,
    fn = paste0(
      doi_root_pdf,
      ".pdf"
    ),
    file_type = "PDF document",
    remove_files = TRUE,
    par = par,
    ncores = ncores
  )
}

Check EPUB files and delete invalid files

if (chkfiles) {
  cat(
    "Checking and deleting invalid EPUB documents...\n"
  )
  util_check_file_type(
    dir = dir,
    fn = paste0(
      doi_root_epub,
      ".epub"
    ),
    file_type = "EPUB document",
    remove_files = TRUE,
    par = par,
    ncores = ncores
  )
}

Rerun lib_springer_files to get available files after deleting invalid files

if (chkfiles) {
  springer_books_available <- lib_springer_files(
    dir = dir
  )
  doi_pdf <- lib_remove_doi_http(
    springer_books_available[["available_pdf"]][["DOI URL"]]
  )
  doi_epub <- lib_remove_doi_http(
    springer_books_available[["available_epub"]][["DOI URL"]]
  )
}
cat(
  paste0(
    length(doi_pdf),
    " ",
    "available PDF files.\n",
    length(doi_epub),
    " ",
    "available EPUB files.\n"
  )
)

Save data

extdata

springer_books_fn <- file.path(
  root,
  "inst",
  "extdata",
  "springer_books.Rds"
)
cat(
  paste0(
    "Saving ",
    springer_books_fn,
    "...\n"
  )
)
saveRDS(
  object = springer_books,
  file = springer_books_fn,
  compress = "xz"
)

springer_books_available_fn <- file.path(
  root,
  "inst",
  "extdata",
  "springer_books_available.Rds"
)
cat(
  paste0(
    "Saving ",
    springer_books_available_fn,
    "...\n"
  )
)
saveRDS(
  object = springer_books_available,
  file = springer_books_available_fn,
  compress = "xz"
)

data

springer_books_doi_fn <- file.path(
  root,
  "data",
  "springer_books_doi.rda"
)
cat(
  paste0(
    "Saving ",
    springer_books_doi_fn,
    "...\n"
  )
)
save(
  springer_books_doi,
  file = springer_books_doi_fn,
  compress = "xz"
)

Clean tempdir

util_clean_tempdir()

jeksterslabds/jeksterslabRlib documentation built on Jan. 19, 2021, 11:04 a.m.