ID | date | POS tagged text | pattern | ...

123 | 2009-03-27 | gross_JJ domestic_JJ product_NN | the_DT most_NN | ...

step1 <- function(df){
    df %>%
    partition(variable, cluster=cl) %>%
    dplyr::filter(str_detect(phrases, paste(patternList, collapse = '|'))) %>%
    collect()
}

preprocess <- function(p) {
    lapply(p, function(x) {
    x = gsub("\/\/", "_", x)
  })
}

df$variable <- unlist(preprocess(df$variable))

## Again using multidplyr and skipping some lines of code
partition(source_code, cluster=cl) %>%
    mutate(match=str_detect(POStagged, pattern)) %>%
    filter(!(match==FALSE)) %>%
    filter(!is.na(match))

preprocess <- function(df) {
    lapply(df, function(POStagged, pattern) {
    mutate(p = str_detect(POStagged, pattern))
    filter(!(p==FALSE))
    filter(!is.na(p))
})
}

data_sample$match <- unlist(preprocess(data_sample))

Error in type(pattern) : argument "pattern" is missing, with no default

R version 3.4.4 (2018-03-15)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 16.04.5 LTS