Fast word count function in Vim

Question

I am trying to display a live word count in the vim statusline. I do this by setting my status line in my .vimrc and inserting a function into it. The idea of this function

Answer 1

So I've written:

func CountWords()
    exe "normal g\"
    let words = substitute(v:statusmsg, "^.*Word [^ ]* of ", "", "")
    let words = substitute(words, ";.*", "", "")
    return words
endfunc

But it prints out info to the statusbar, so I don't think it will be suitable for your use-case. It's very fast, though!

Answer 2

My suggestion:

function! UpdateWordCount()
  let b:word_count = eval(join(map(getline("1", "$"), "len(split(v:val, '\\s\\+'))"), "+"))
endfunction

augroup UpdateWordCount
  au!
  autocmd BufRead,BufNewFile,BufEnter,CursorHold,CursorHoldI,InsertEnter,InsertLeave * call UpdateWordCount()
augroup END

let &statusline='wc:%{get(b:, "word_count", 0)}'

I'm not sure how this compares in speed to some of the other solutions, but it's certainly a lot simpler than most.

Answer 3

In case someone else is coming here from Google, I modified Abslom Daak's answer to work with Airline. I saved the following as

~/.vim/bundle/vim-airline/autoload/airline/extensions/pandoc.vim

and added

call airline#extensions#pandoc#init(s:ext)

to extensions.vim

let s:spc = g:airline_symbols.space

function! airline#extensions#pandoc#word_count()
if mode() == "s"
    return 0
else
    let s:old_status = v:statusmsg
    let position = getpos(".")
    let s:word_count = 0
    exe ":silent normal g\<c-g>"
    let stat = v:statusmsg
    let s:word_count = 0
    if stat != '--No lines in buffer--'
        let s:word_count = str2nr(split(v:statusmsg)[11])
        let v:statusmsg = s:old_status
    end
    call setpos('.', position)
    return s:word_count 
end
endfunction

function! airline#extensions#pandoc#apply(...)
if &ft == "pandoc"
    let w:airline_section_x = "%{airline#extensions#pandoc#word_count()} Words"
endif
endfunction

function! airline#extensions#pandoc#init(ext)
call a:ext.add_statusline_func('airline#extensions#pandoc#apply')
endfunction

Answer 4

This is an improvement on Michael Dunn's version, caching the word count so even less processing is needed.

function! WC()
    if &modified || !exists("b:wordcount") 
            let l:old_status = v:statusmsg  
            execute "silent normal g\<c-g>"
            let b:wordcount = str2nr(split(v:statusmsg)[11])
            let v:statusmsg = l:old_status  
            return b:wordcount
    else
            return b:wordcount
    endif
endfunction 

Answer 5

I took the bulk of this from the vim help pages on writing functions.

function! WordCount()
  let lnum = 1
  let n = 0
  while lnum <= line('$')
    let n = n + len(split(getline(lnum)))
    let lnum = lnum + 1
  endwhile
  return n
endfunction

Of course, like the others, you'll need to:

:set statusline=wc:%{WordCount()}

I'm sure this can be cleaned up by somebody to make it more vimmy (s:n instead of just n?), but I believe the basic functionality is there.

Edit:

Looking at this again, I really like Mikael Jansson's solution. I don't like shelling out to wc (not portable and perhaps slow). If we replace his UpdateWordCount function with the code I have above (renaming my function to UpdateWordCount), then I think we have a better solution.

Answer 6

Using the method in the answer provided by Steve Moyer I was able to produce the following solution. It is a rather inelegant hack I'm afraid and I feel that there must be a neater solution, but it works, and is much faster than simply counting all of the words in a buffer every time the status line is updated. I should note also that this solution is platform independent and does not assume a system has 'wc' or something similar.

My solution does not periodically update the buffer, but the answer provided by Mikael Jansson would be able to provide this functionality. I have not, as of yet, found an instance where my solution becomes out of sync. However I have only tested this briefly as an accurate live word count is not essential to my needs. The pattern I use for matching words is also simple and is intended for simple text documents. If anyone has a better idea for a pattern or any other suggestions please feel free to post an answer or edit this post.

My solution:

"returns the count of how many words are in the entire file excluding the current line 
"updates the buffer variable Global_Word_Count to reflect this
fu! OtherLineWordCount() 
    let data = []
    "get lines above and below current line unless current line is first or last
    if line(".") > 1
        let data = getline(1, line(".")-1)
    endif   
    if line(".") < line("$")
        let data = data + getline(line(".")+1, "$") 
    endif   
    let count_words = 0
    let pattern = "\\<\\(\\w\\|-\\|'\\)\\+\\>"
    for str in data
        let count_words = count_words + NumPatternsInString(str, pattern)
    endfor  
    let b:Global_Word_Count = count_words
    return count_words
endf    

"returns the word count for the current line
"updates the buffer variable Current_Line_Number 
"updates the buffer variable Current_Line_Word_Count 
fu! CurrentLineWordCount()
    if b:Current_Line_Number != line(".") "if the line number has changed then add old count
        let b:Global_Word_Count = b:Global_Word_Count + b:Current_Line_Word_Count
    endif   
    "calculate number of words on current line
    let line = getline(".")
    let pattern = "\\<\\(\\w\\|-\\|'\\)\\+\\>"
    let count_words = NumPatternsInString(line, pattern)
    let b:Current_Line_Word_Count = count_words "update buffer variable with current line count
    if b:Current_Line_Number != line(".") "if the line number has changed then subtract current line count
        let b:Global_Word_Count = b:Global_Word_Count - b:Current_Line_Word_Count
    endif   
    let b:Current_Line_Number = line(".") "update buffer variable with current line number
    return count_words
endf    

"returns the word count for the entire file using variables defined in other procedures
"this is the function that is called repeatedly and controls the other word
"count functions.
fu! WordCount()
    if exists("b:Global_Word_Count") == 0 
        let b:Global_Word_Count = 0
        let b:Current_Line_Word_Count = 0
        let b:Current_Line_Number = line(".")
        call OtherLineWordCount()
    endif   
    call CurrentLineWordCount()
    return b:Global_Word_Count + b:Current_Line_Word_Count
endf

"returns the number of patterns found in a string 
fu! NumPatternsInString(str, pat)
    let i = 0
    let num = -1
    while i != -1
        let num = num + 1
        let i = matchend(a:str, a:pat, i)
    endwhile
    return num
endf

This is then added to the status line by:

:set statusline=wc:%{WordCount()}

I hope this helps anyone looking for a live word count in Vim. Albeit one that isn't always exact. Alternatively of course g ctrl-g will provide you with Vim's word count!