From ed5353d422bdf0916b40486c4043d54845b6a1b4 Mon Sep 17 00:00:00 2001
From: marco-lancini <info@marcolancini.it>
Date: Thu, 21 Sep 2023 10:12:49 +0100
Subject: [PATCH] wip

---
 docker/pandoc/Dockerfile            |  4 ++++
 docker/pandoc/filters/wordcount.lua | 29 +++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)
 create mode 100644 docker/pandoc/filters/wordcount.lua

diff --git a/docker/pandoc/Dockerfile b/docker/pandoc/Dockerfile
index cebfeb3..45b2494 100644
--- a/docker/pandoc/Dockerfile
+++ b/docker/pandoc/Dockerfile
@@ -13,6 +13,10 @@ COPY docker/pandoc/requirements.txt /requirements.txt
 RUN pip3 install --no-cache-dir -r /requirements.txt    \
     && rm -f /requirements.txt
 
+# Install custom filters
+COPY docker/pandoc/filters/* /root/.pandoc/filters/
+
+# Set working directory
 WORKDIR /data
 
 # Command
diff --git a/docker/pandoc/filters/wordcount.lua b/docker/pandoc/filters/wordcount.lua
new file mode 100644
index 0000000..bcaf9ac
--- /dev/null
+++ b/docker/pandoc/filters/wordcount.lua
@@ -0,0 +1,29 @@
+-- counts words in a document
+
+words = 0
+
+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
+  end,
+
+  Code = function(el)
+    _,n = el.text:gsub("%S+","")
+    words = words + n
+  end,
+
+  CodeBlock = function(el)
+    _,n = el.text:gsub("%S+","")
+    words = words + n
+  end
+}
+
+function Pandoc(el)
+    -- skip metadata, just count body:
+    el.blocks:walk(wordcount)
+    print(words .. " words in body")
+    os.exit(0)
+end