From 32df5ad916626b0ddd6f0d980f350c6485f23867 Mon Sep 17 00:00:00 2001
From: Waylan Limberg <waylan.limberg@icloud.com>
Date: Sat, 7 Feb 2015 14:28:42 -0500
Subject: Add Docs spellchecking Test.

Not sure this is the best way to go, but it works. I'm not crazy about
running the spellcheck against the built docs, but aspell has a builtin
option to easily ignore everything in `<code>` tags which greatly simplfies
things.

I looked at Doug Hellmans' sphinxcontrib-spelling package which does
something similar for Sphinx. However, as Sphinx uses rST and the rST
parser outputs a parse tree, Doug is essentially taking that parse tree
and running the spellcheck on the appropriate parts (skipping code, etc.).
He did a nice [writeup][5] of his development process if you are interested.

As Python-Markdown's parse tree is represented as HTML (through ElementTree)
I would have to use HTML anyway. And [PyEnchant][2] doesn't currently have
good support for HTML. So I used [aspell][3], with inspiration from the
[git-spell-check][4] hook.

[1]: http://sphinxcontrib-spelling.readthedocs.org/en/latest/index.html
[2]: https://pythonhosted.org/pyenchant/
[3]: http://aspell.net/
[4]: https://github.com/mprpic/git-spell-check
[5]: http://doughellmann.com/2011/05/26/creating-a-spelling-checker-for-restructuredtext-documents.html
---
 checkspelling.sh | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100755 checkspelling.sh

(limited to 'checkspelling.sh')

diff --git a/checkspelling.sh b/checkspelling.sh
new file mode 100755
index 0000000..4ae20cc
--- /dev/null
+++ b/checkspelling.sh
@@ -0,0 +1,32 @@
+#!/bin/bash
+
+echo "Building docs..."
+python setup.py --quiet build_docs --force
+echo "Compiling Dictionary..."
+aspell --lang=en create master ./tmp <.spell-dict
+echo "Checking spelling...\n"
+
+let "fails=0"
+
+for file in $(find build/docs/ -type f -name "*.html"); do
+    words=$(aspell list --lang=en --mode=html --add-html-skip=code --extra-dicts=./tmp  <$file)
+    if [ "$words" ]; then
+        uniquewords=$(tr ' ' '\n' <<< "${words[@]}" | sort -u | tr '\n' ' ')
+        let "fails++"
+        echo "Misspelled words in '$file':"
+        echo "-----------------------------------------------------------------"
+        for word in ${uniquewords[@]}; do
+            echo $word
+        done
+        echo "-----------------------------------------------------------------"
+    fi
+done
+rm -f ./tmp
+rm -rf build
+
+if [ $fails -gt 0 ]; then
+    echo "$fails files with misspelled words."
+    exit 1
+else
+    exit 0
+fi
-- 
cgit v1.2.3