Started to ignore Word lock files

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: LexisNexisTools
 Title: Working with Files from 'LexisNexis'
 Version: 0.3.3.9000
-Date: 2021-03-06
+Date: 2021-03-30
 Authors@R: person("Johannes", "Gruber", email = "[email protected]", 
   role = c("aut", "cre"))
 Description: My PhD supervisor once told me that everyone doing newspaper

NEWS.md

@@ -1,3 +1,9 @@
+# LexisNexisTools 0.3.4
+
+* Fixes for compliance with quanteda v3 (thank you @kbenoit)
+* All images for building the vignette now live inside the package
+* `lnt_read_lines` and `lnt_read` now ignore Word lock files
+
 # LexisNexisTools 0.3.3
 
 * Updated namespacing for planned v3 modularisation of quanteda (thank you @kbenoit)

R/LexisNexisTools.R

@@ -1610,8 +1610,9 @@ lnt_lookup.character <- function(x,
 #'   LNToutput = lnt_read(lnt_sample(copy = FALSE)),
 #'   threshold = 0.97
 #' )
-#'
+#' \dontrun{
 #' lnt_diff(duplicates.df, min = 0.18, max = 0.30)
+#' }
 #' @author Johannes Gruber
 #' @export
 #' @importFrom quanteda tokens
@@ -2439,6 +2440,8 @@ lnt_read_lines <- function(files,
   if (length(files$.doc) > 0) {
     check_install("striprtf")
     if (length(files$.doc) > 1) {
+      # ignore lock files
+      files$.doc <- files$.doc[!grepl("^~\\$", basename(files$.doc))]
       lines_doc <- unlist(lapply(files$.doc, function(f) {
         out <- striprtf::read_rtf(f)
         names(out) <- rep(f, times = length(out))
@@ -2499,6 +2502,8 @@ lnt_read_lines <- function(files,
   if (length(files$docx) > 0) {
     check_install("xml2")
     if (length(files$docx) > 1) {
+      # ignore lock files
+      files$docx <- files$docx[!grepl("^~\\$", basename(files$docx))]
       lines_docx <- unlist(lapply(files$docx, function(f) {
         con <- unz(description = f, filename = "word/document.xml")
         out <- xml2::read_xml(con, encoding = "utf-8")

Update package.R

@@ -37,16 +37,16 @@ spelling::spell_check_files("README.Rmd", ignore = readLines("./inst/WORDLIST"),
 ## Update Citation
 update_citation <- function() {
   cit <- readLines("./inst/CITATION")
-  note <- grep("note =", cit)
+  version <- grep("note = ", cit)
+  year <- grep("year = ", cit)
+
   desc <- readLines("DESCRIPTION")
-  date <- desc[grepl("^Date:", desc)]
-  date2 <- gsub("[^[:digit:]-]", "", date)
-  desc[grepl("^Date:", desc)] <- gsub(date2, Sys.Date(), desc[grepl("^Date:", desc)])
-  vers <- desc[grepl("^Version:", desc)]
-  vers2 <- gsub("[^[:digit:].]", "", vers)
-  vers3 <- gsub("\\d+{3}", "", vers2)
-  vers3 <- gsub("[[:punct:]]$", "", vers3)
-  cit[note] <- gsub("\\d+.\\d+.\\d+", vers3, cit[note]) 
+  vers <- gsub("[^[:digit:].]", "", grep("^Version:", desc, value = TRUE))
+  cit[version] <- gsub("R package version (.*)", paste0("R package version ", vers), cit[version])
+
+  y <- gsub(".*(\\d{4}).*", "\\1", grep("^Date:", desc, value = TRUE))
+  cit[year] <- paste0("         year = ", y, ",")
+
   writeLines(cit, "./inst/CITATION")
 }
 update_citation()

inst/CITATION

@@ -1,7 +1,7 @@
 bibentry(bibtype = "Manual",
          title = "{L}exis{N}exis{T}ools. {A}n {R} package for working with newspaper data from '{LexisNexis}'",
          author = as.person("Johannes Gruber"),
-         year = format(Sys.Date(), "%Y"),
+         year = 2021,
          url = "https://github.com/JBGruber/LexisNexisTools",
-         note = "R package version 0.3.3"
+         note = "R package version 0.3.3.9000
 )