summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--script/unicodify.sed8
1 files changed, 8 insertions, 0 deletions
diff --git a/script/unicodify.sed b/script/unicodify.sed
index 09e70cf..d0df04b 100644
--- a/script/unicodify.sed
+++ b/script/unicodify.sed
@@ -1,9 +1,17 @@
+# Remove spaces on either end of an em-dash.
s,[[:space:]]--[[:space:]],\&\#8212;,g
+
+# Explicitly handle double-quotes before single-quotes.
s,"`,\&\#8220;,g
s,`",\&\#8221;,g
s,'`,\&\#8216;,g
s,`',\&\#8217;,g
+
+# Diacritics.
s,\ï,\&\#239;,g
s,\è,\&\#232;,g
s,\é,\&\#233;,g
+
+# Remove Asciidoc comments now, for the sake of getting more accurate
+# wordcounts.
s,//.*,,g