debugging the `tm::stemCompletion` function

stemCompletion.R

## Identifying the differences between using a Corpus dictionary, and a vector of strings. 

## ---------
## Using a Corpus dictionary
## and type == "prevalent"

tm::stemCompletion(x = stemDocument(w), 
		dictionary = Corpus(x = VectorSource(x = w)), 
		type = "prevalent")
# intersect      intersect      intersect      intersect 
# "intersecting" "intersecting" "intersecting" "intersecting"

## ---------
## Using a vector dictionary
## and type == "prevalent"
w <- c("intersection", "intersecting", "intersection", "intersects")

tm::stemCompletion(x = stemDocument(w), 
		dictionary = w, 
		type = "prevalent")
# intersect      intersect      intersect      intersect 
# "intersection" "intersection" "intersection" "intersection"


## ----------
## Extracting the specific code from tm::stemCompletion to debug


## ---------
## Using a Corpus dictionary
## and type == "prevalent"

w <- c("intersection", "intersecting", "intersection", "intersects")
dictionary <- Corpus(x = VectorSource(x = w))
x <- stemDocument(x = w, language = "english")

## the following lines are taken from the `tm::stemCompletion` function
dictionary <- unique(unlist(lapply(dictionary, words)))

possibleCompletions <- lapply(x, function(w) grep(sprintf("^%s", w), dictionary, value = TRUE))

possibleCompletions <- lapply(possibleCompletions, function(x) { 
	sort(table(x), decreasing = TRUE)
	})
possibleCompletions
			      
n <- names(sapply(possibleCompletions, "[", 1))
setNames(if (length(n)) n else rep_len(NA, length(x)),x)
# intersect      intersect      intersect      intersect 
# "intersecting" "intersecting" "intersecting" "intersecting"



## ---------
## Using a vector dictionary
## and type == "prevalent"

w <- c("intersection", "intersecting", "intersection", "intersects")
dictionary <- w
x <- stemDocument(x = w, language = "english")

## the following lines are taken from the `tm::stemCompletion` function
possibleCompletions <- lapply(x, function(w) grep(sprintf("^%s", w), dictionary, value = TRUE))

possibleCompletions <- lapply(possibleCompletions, function(x) { 
	sort(table(x), decreasing = TRUE)
})
possibleCompletions

n <- names(sapply(possibleCompletions, "[", 1))
setNames(if (length(n)) n else rep_len(NA, length(x)),x)
# intersect      intersect      intersect      intersect 
# "intersection" "intersection" "intersection" "intersection"