summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorCharlotte Koch <charlotte@magentastripe.com>2023-12-31 15:03:49 -0800
committerCharlotte Koch <charlotte@magentastripe.com>2023-12-31 15:03:49 -0800
commita28da6ed9a385c8624d45510ad96928b2585cf70 (patch)
treed484f40a81446a3bed2f4f0dcf247e91deb81252
parentff5eaede74d81e978584ba9c732fc27346c773de (diff)
Comments in the unicodify script.
-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,\&iuml;,\&\#239;,g
s,\&egrave;,\&\#232;,g
s,\&eacute;,\&\#233;,g
+
+# Remove Asciidoc comments now, for the sake of getting more accurate
+# wordcounts.
s,//.*,,g