wordcount: adds process-anyway option (#162)

In standalone mode, setting a `wordcount` variable to `process-anyway`
allows the pandoc process to continue in addition to counting words.

Author: jdutant

wordcount/README.md

@@ -1,11 +1,29 @@
 # wordcount
 
-This filter counts the words and characters in the body of a document (omitting
-metadata like titles and abstracts), including words in code.
-It should be more accurate than `wc -w` or `wc -m` run directly on a
-Markdown document, since `wc` will also count markup
-characters, like the `#` in front of an ATX header, or
-tags in HTML documents.
+This filter counts the words and characters in the body of a document
+(omitting metadata like titles and abstracts), including words in
+code. It should be more accurate than `wc -w` or `wc -m` run directly
+on a Markdown document, since `wc` will also count markup characters,
+like the `#` in front of an ATX header, or tags in HTML documents.
 
 To run it, `pandoc --lua-filter wordcount.lua myfile.md`.
 The word count will be printed to stdout.
+
+If you want to process the document as well as printing the word count
+set the variable `wordcount` to `process` (or `process-anyway` or `convert`).
+This works only in conjunction with the standalone document option (`-s`).
+This can be done through the command line:
+
+```
+pandoc -s -L wordcount.lua -M wordcount=process sample.md -o output.html
+```
+
+Or the document's metadata block:
+
+```
+---
+title: My Long Book
+wordcount: process-anyway
+---
+```
+

wordcount/wordcount.lua

@@ -1,45 +1,56 @@
--- counts words in a document 
+-- counts words in a document
 
-words = 0 
+words = 0
 characters = 0
 characters_and_spaces = 0
+process_anyway = false
 
-wordcount = { 
-  Str = function(el) 
-    -- we don't count a word if it's entirely punctuation: 
-    if el.text:match("%P") then 
-        words = words + 1 
-    end 
+wordcount = {
+  Str = function(el)
+    -- we don't count a word if it's entirely punctuation:
+    if el.text:match("%P") then
+        words = words + 1
+    end
     characters = characters + utf8.len(el.text)
     characters_and_spaces = characters_and_spaces + utf8.len(el.text)
-  end, 
+  end,
 
   Space = function(el)
     characters_and_spaces = characters_and_spaces + 1
   end,
 
-  Code = function(el) 
-    _,n = el.text:gsub("%S+","") 
-    words = words + n 
+  Code = function(el)
+    _,n = el.text:gsub("%S+","")
+    words = words + n
     text_nospace = el.text:gsub("%s", "")
     characters = characters + utf8.len(text_nospace)
     characters_and_spaces = characters_and_spaces + utf8.len(el.text)
-  end, 
+  end,
 
-  CodeBlock = function(el) 
-    _,n = el.text:gsub("%S+","") 
-    words = words + n 
+  CodeBlock = function(el)
+    _,n = el.text:gsub("%S+","")
+    words = words + n
     text_nospace = el.text:gsub("%s", "")
     characters = characters + utf8.len(text_nospace)
     characters_and_spaces = characters_and_spaces + utf8.len(el.text)
-  end 
-} 
+  end
+}
+
+-- check if the `wordcount` variable is set to `process-anyway`
+function Meta(meta)
+  if meta.wordcount and (meta.wordcount=="process-anyway"
+    or meta.wordcount=="process" or meta.wordcount=="convert") then
+      process_anyway = true
+  end
+end
 
-function Pandoc(el) 
-    -- skip metadata, just count body: 
-    pandoc.walk_block(pandoc.Div(el.blocks), wordcount) 
-    print(words .. " words in body") 
+function Pandoc(el)
+    -- skip metadata, just count body:
+    pandoc.walk_block(pandoc.Div(el.blocks), wordcount)
+    print(words .. " words in body")
     print(characters .. " characters in body")
     print(characters_and_spaces .. " characters in body (including spaces)")
-    os.exit(0) 
+    if not process_anyway then
+      os.exit(0)
+    end
 end