icd (version 2.2)

rtf_fix_unicode: Fix Unicode characters in RTF

Description

fix ASCII, Code Page 1252 and Unicode horror: some character definitions are split over lines... This needs care in Windows, or course. Maybe Mac, too?

Usage

rtf_fix_unicode(filtered, ...)

Details

First: c cedilla, e grave, e acute Then: n tilde, o umlaut

Examples

# NOT RUN {
# rtf_fix_unicode is a slow step, useBytes and perl together is faster
f_info_rtf <- rtf_fetch_year("2011", offline = FALSE)
rtf_lines <- readLines(f_info_rtf$file_path, warn = FALSE, encoding = "ASCII")
microbenchmark::microbenchmark(
  res_both <- rtf_fix_unicode(rtf_lines, perl = TRUE, useBytes = TRUE),
  res_none <- rtf_fix_unicode(rtf_lines, perl = FALSE, useBytes = FALSE),
  res_bytes <- rtf_fix_unicode(rtf_lines, perl = FALSE, useBytes = TRUE),
  res_perl <- rtf_fix_unicode(rtf_lines, perl = TRUE, useBytes = FALSE),
  times = 5
)
stopifnot(identical(res_both, res_none))
# }