Merge remote-tracking branch 'upstream/master' into biblio-place

Author: jdutant

abstract-to-meta/Makefile

@@ -1,10 +1,17 @@
 DIFF ?= diff --strip-trailing-cr -u
 
-test: sample.md abstract-to-meta.lua
-	@pandoc --lua-filter=abstract-to-meta.lua --standalone --to=markdown $< \
-	    | $(DIFF) expected.md -
+test: sample1.md sample2.md abstract-to-meta.lua
+	@pandoc --lua-filter=abstract-to-meta.lua --standalone --to=markdown \
+		sample1.md | $(DIFF) expected1.md -
+	@pandoc --lua-filter=abstract-to-meta.lua --standalone --to=markdown \
+		sample2.md | $(DIFF) expected2.md -
 
-expected.md: sample.md abstract-to-meta.lua
+expected: sample1.md expected1.md sample2.md expected2.md abstract-to-meta.lua
+
+expected1.md: sample1.md abstract-to-meta.lua
+	pandoc --lua-filter=abstract-to-meta.lua --standalone --output $@ $<
+
+expected2.md: sample2.md abstract-to-meta.lua
 	pandoc --lua-filter=abstract-to-meta.lua --standalone --output $@ $<
 
 .PHONY: test

abstract-to-meta/README.md

@@ -35,3 +35,21 @@ satisfy this condition.^[1]
 
 [1]: This requires the `auto_identifier` extension. It is
      enabled by default.
+
+The abstract can be placed anywhere in the document.
+
+The filter assumes that the abstract runs up until the next
+heading or a [horizontal rule], whichever comes first). Thus the
+abstract can be placed at the beginning of a document whose text
+doesn't start with a heading:
+
+    # Abstract
+
+    The abstract text includes this.
+
+    * * * *
+
+    This text is the beginning of the document.
+
+
+[horizontal rule]: https://pandoc.org/MANUAL.html#horizontal-rules

abstract-to-meta/abstract-to-meta.lua

@@ -20,7 +20,11 @@ function abstract_from_blocklist (blocks)
         body_blocks[#body_blocks + 1] = block
       end
     elseif looking_at_abstract then
-      abstract[#abstract + 1] = block
+      if block.t == 'HorizontalRule' then
+        looking_at_abstract = false
+      else
+        abstract[#abstract + 1] = block
+      end
     else
       body_blocks[#body_blocks + 1] = block
     end

abstract-to-meta/expected.md renamed to abstract-to-meta/expected1.md

@@ -0,0 +1,34 @@
+---
+abstract: |
+  Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
+  eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad
+  minim veniam, quis nostrud exercitation ullamco laboris nisi ut
+  aliquip ex ea commodo consequat. Duis aute irure dolor in
+  reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla
+  pariatur.
+
+  -   one
+  -   two
+  -   three
+
+  Excepteur sint occaecat cupidatat non proident, sunt in culpa qui
+  officia deserunt mollit anim id est laborum.
+---
+
+::: {.frontmatter}
+Mauris vel erat tincidunt, venenatis elit ac, luctus augue. Aliquam sed
+hendrerit augue. Donec finibus mi et dolor semper, non malesuada nulla
+ullamcorper. Fusce auctor ullamcorper nunc, sit amet molestie nunc
+ornare ac. Nunc vulputate non ante vitae hendrerit. Pellentesque
+habitant morbi tristique senectus et netus et malesuada fames ac turpis
+egestas. Ut maximus enim molestie ex egestas, a tincidunt quam rhoncus.
+Quisque tincidunt est arcu, quis aliquet justo varius a. Fusce nec massa
+neque.
+:::
+
+# Lorem Ipsum
+
+Quo dolore molestiae et laboriosam occaecati explicabo corrupti. Earum
+expedita ducimus quaerat est quam ut molestiae. Illum deleniti vel
+labore facilis et cum est. Est nemo est vel ad. Assumenda consequatur
+rerum officiis atque officia. Est nihil iste cumque ad qui.

abstract-to-meta/expected2.md

@@ -25,7 +25,8 @@ deserunt mollit anim id est laborum.
 
 # Lorem Ipsum
 
-Quo dolore molestiae et laboriosam occaecati explicabo corrupti. Earum expedita
-ducimus quaerat est quam ut molestiae. Illum deleniti vel labore facilis et cum
-est. Est nemo est vel ad. Assumenda consequatur rerum officiis atque officia.
-Est nihil iste cumque ad qui.
+Quo dolore molestiae et laboriosam occaecati explicabo corrupti.
+Earum expedita ducimus quaerat est quam ut molestiae. Illum
+deleniti vel labore facilis et cum est. Est nemo est vel ad.
+Assumenda consequatur rerum officiis atque officia. Est nihil iste
+cumque ad qui.

abstract-to-meta/sample.md renamed to abstract-to-meta/sample1.md

@@ -0,0 +1,36 @@
+::: {.frontmatter}
+# Abstract
+
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do
+eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut
+enim ad minim veniam, quis nostrud exercitation ullamco laboris
+nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in
+reprehenderit in voluptate velit esse cillum dolore eu fugiat
+nulla pariatur.
+
+- one
+- two
+- three
+
+Excepteur sint occaecat cupidatat non proident, sunt in culpa qui
+officia deserunt mollit anim id est laborum.
+
+---
+
+Mauris vel erat tincidunt, venenatis elit ac, luctus augue.
+Aliquam sed hendrerit augue. Donec finibus mi et dolor semper, non
+malesuada nulla ullamcorper. Fusce auctor ullamcorper nunc, sit
+amet molestie nunc ornare ac. Nunc vulputate non ante vitae
+hendrerit. Pellentesque habitant morbi tristique senectus et netus
+et malesuada fames ac turpis egestas. Ut maximus enim molestie ex
+egestas, a tincidunt quam rhoncus. Quisque tincidunt est arcu,
+quis aliquet justo varius a. Fusce nec massa neque.
+:::
+
+# Lorem Ipsum
+
+Quo dolore molestiae et laboriosam occaecati explicabo corrupti.
+Earum expedita ducimus quaerat est quam ut molestiae. Illum
+deleniti vel labore facilis et cum est. Est nemo est vel ad.
+Assumenda consequatur rerum officiis atque officia. Est nihil iste
+cumque ad qui.

abstract-to-meta/sample2.md

@@ -355,7 +355,7 @@ function CodeBlock(block)
   --
   -- to be referenced as @fig:example outside of the figure when used
   -- with `pandoc-crossref`.
-  local img_attr = pandoc.Attr {
+  local img_attr = {
     id = block.identifier,
     name = block.attributes.name
   }

diagram-generator/diagram-generator.lua

@@ -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/README.md

@@ -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