Add , perl = TRUE to grepl() calls per #51

R/check_text_logicals.R

@@ -326,7 +326,7 @@ contraction <- function(x){
             "([a-z]'(nt|t|ve|d|ll|m|re))|('(cause|tis|twas))|(\\b(he|how|it|",
             "let|she|that|there|what|when|where|who|why)'s)"
         ),
-        x, ignore.case = TRUE
+        x, ignore.case = TRUE, perl = TRUE
     )
 }
 #contraction(c('jon\'s a good man', "'cause I want to", '4was\'nt', 'the dog', 
@@ -337,7 +337,7 @@ date <- qr2fun('rm_date')
 
 ## digits
 digit <- function(x) {
-    grepl('\\d', x)    
+    grepl('\\d', x, perl = TRUE)    
 }
 
 ## email addresses
@@ -350,12 +350,12 @@ emoticon <- qr2fun('rm_emoticon')
 ## just white space
 empty <- function(x) {
     #any(grepl("^\\s*$", stats::na.omit(x)))
-    grepl("^\\s*$", x)
+    grepl("^\\s*$", x, perl = TRUE)
 }
 
 ## are there escaped backslashes
 escaped <- function(x) {
-    grepl("[\\\\]", x) & !grepl("\\\"|\\\'|\\\`", x)
+    grepl("[\\\\]", x) & !grepl("\\\"|\\\'|\\\`", x, perl = TRUE)
 }
 
 
@@ -366,7 +366,7 @@ hash <- qr2fun('rm_hash')
 ## contains html
 html <- function(x) {
     pat <- paste0("<[^>]+>|", paste(html_symbols[['html']], collapse ="|"))
-    grepl(pat, x)
+    grepl(pat, x, perl = TRUE)
 }
 
 ## incomplete sentences usually indicated by 2-4 enmarks that are 
@@ -376,12 +376,12 @@ incomplete <- function(x) {
         "\\?*\\?[.]+|[.?!]*\\? [.][.?!]+|[.?!]*\\. [.?!]+|[.?!]+\\. [.?!]*|",
         "[.?!]+\\.[.?!]*|[.?!]*\\.[.?!]+"
     )
-    grepl(pat, x)
+    grepl(pat, x, perl = TRUE)
 }
 
 ## contains kerning
 kern <- function(x) {
-   grepl('(([A-Z]\\s+){2,}[A-Z])', x)
+   grepl('(([A-Z]\\s+){2,}[A-Z])', x, perl = TRUE)
 } 
 
 ## check if something is a list of vectors
@@ -419,7 +419,7 @@ misspelled <- function(x){
 
 ## Does it have no letters
 no_alpha <- function(x) {
-    !is.na(x) & !grepl("[a-zA-Z]", x)
+    !is.na(x) & !grepl("[a-zA-Z]", x, perl = TRUE)
 }
 
 
@@ -430,14 +430,14 @@ no_endmark <- function(x) {
 
 ## is comma with no space
 no_space_after_comma <- function(x) {
-    grepl("(,)([^ ])", x)
+    grepl("(,)([^ ])", x, perl = TRUE)
 }
 
 
 
 ## are there any non ascii characters
 non_ascii <- function(x) {
-    grepl("[^ -~]", x) & !is.na(x) & !grepl("^\\s*$", x)
+    grepl("[^ -~]", x, perl = TRUE) & !is.na(x) & !grepl("^\\s*$", x, perl = TRUE)
 }
 
 ## not character

R/drop_row.R

@@ -79,7 +79,7 @@ drop_empty_row <- function(dataframe) {
     x <- apply(dataframe, 1, function(x) {
         paste(stats::na.omit(x), collapse = "")
     })
-    return(dataframe[!grepl("^\\s*$", x),  ,drop = FALSE] )
+    return(dataframe[!grepl("^\\s*$", x, perl = TRUE),  ,drop = FALSE] )
 }
 
 

R/has_endmark.R

@@ -21,7 +21,7 @@
 has_endmark <- function(x, endmarks = c('?', '.', '!'), ...){
     !is.na(x) & grepl(
         sprintf('[%s]\\s*$', paste(endmarks, collapse = "")), 
-        x, 
+        x, perl = TRUE, 
         ...
     )
 }

R/make_plural.R

@@ -22,7 +22,7 @@ make_plural <- function (x, keep.original = FALSE,
     hits <- match(tolower(x), tolower(irregular[[1]]))
 
     ends <- "(sh?|x|z|ch)$"
-    pluralify <- ifelse(grepl(ends, x), "es", "s")
+    pluralify <- ifelse(grepl(ends, x, perl = TRUE), "es", "s")
     out <- gsub("ys$", "ies", paste0(x, pluralify))
     out[which(!is.na(hits))] <- irregular[[2]][hits[which(!is.na(hits))]]
 

R/match_tokens.R

@@ -23,7 +23,7 @@ match_tokens <- function(x, pattern, ignore.case = TRUE, ...){
     y <- rm_na(unique(unlist(textshape::split_token(x, lower = ignore.case))))
     if (isTRUE(ignore.case)) pattern <- tolower(pattern)
 
-    y[grepl(paste(paste0('(', pattern, ')'), collapse = '|'), y)]
+    y[grepl(paste(paste0('(', pattern, ')'), collapse = '|'), y, perl = TRUE)]
 
 }
 

R/replace_money.R

@@ -37,8 +37,8 @@ replace_money <- function(x, pattern = '(-?)([$])([0-9,]+)(\\.\\d{2})?',
 
 replace_money_fun <- function(x, decimal = ' and '){
 
-    sign <- ifelse(grepl('^-', x), 'negative ', '')
-    if (grepl('\\.', x)) {
+    sign <- ifelse(grepl('^-', x, perl = TRUE), 'negative ', '')
+    if (grepl('\\.', x, perl = TRUE)) {
         number <- replace_number(
             gsub(
                 '\\.', 

R/replace_number.R

@@ -110,8 +110,8 @@ replace_number  <- function(x, num.paste = FALSE, remove = FALSE, ...) {
     num_df[['den']][is.na(num_df[['den']])] <- ""
     num_df[['int']] <- eng(num_df[['integer']], ...)
 
-    is_decimal <- grepl("\\.", num_df[[1]])  
-    not_integer_decimal <- !grepl('\\d\\.', num_df[[1]])
+    is_decimal <- grepl("\\.", num_df[[1]], perl = TRUE)  
+    not_integer_decimal <- !grepl('\\d\\.', num_df[[1]], perl = TRUE)
 
     num_df[['int']][is_decimal & not_integer_decimal] <- ""
 

R/replace_word_elongation.R

@@ -28,7 +28,7 @@
 #' 2011 Conference on Empirical Methods in Natural Language Processing (pp. 
 #' 562-570). Edinburgh, Scotland. Retrieved from 
 #' http://www.aclweb.org/anthology/D11-1052 \cr \cr
-#' \url{http://storage.googleapis.com/books/ngrams/books/datasetsv2.html} \cr \cr
+#' \url{https://storage.googleapis.com/books/ngrams/books/datasetsv2.html} \cr \cr
 #' \url{https://www.theatlantic.com/magazine/archive/2013/03/dragging-it-out/309220} \cr \cr
 #' \url{https://english.stackexchange.com/questions/189517/is-there-a-name-term-for-multiplied-vowels}
 #' @export

R/utils.R

@@ -236,7 +236,7 @@ drop_sci_note <- function(x, ...){
 
     x <- as.character(as.numeric(x))
 
-    locs <- grepl('e\\+', x)
+    locs <- grepl('e\\+', x, perl = TRUE)
 
     x[locs] <- unlist(Map(function(b, e) {