email.tidyr.R

library(tidyverse)

# Load our emails
emails <- read_csv("C:/temp/all_emails.csv")

# Set our email regular expression
email.re <- "^[a-zA-Z0-9.!#$%&'*+\\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$"
email.re.potential <- "[a-zA-Z0-9.!#$%&'*+\\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*"


emails$OriginalEmail <- emails$Value
emails$ModifiedEmail <- gsub(" ", "", emails$OriginalEmail, fixed=TRUE) #Remove erroneous spaces
emails$ModifiedEmail <- gsub( "\"", "", emails$ModifiedEmail, fixed=TRUE) #Remove erroneous quote marks


# Extract our actual emails
emails$CorrectEmail <- str_extract(emails$ModifiedEmail, email.re.potential)

tmp<-emails %>% filter(is.na(CorrectEmail))


emails.final <- emails %>%
  mutate(Action = case_when(
    is.na(CorrectEmail) ~ "DELETE",
    ModifiedEmail != OriginalEmail ~ "CHANGE",
    TRUE ~ "NO ACTION"
  )) %>%
  filter(Action != "NO ACTION")