From 1b97846be265588817c74db2ab3d8f8ba82ea82a Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Fri, 1 Apr 2022 10:41:33 -0700
Subject: [PATCH] Fix regression with `ascii_identifiers` and Turkish undotted
i.
Closes #8003.
---
src/Text/Pandoc/Asciify.hs | 6 +++++-
test/command/8003.md | 6 ++++++
2 files changed, 11 insertions(+), 1 deletion(-)
create mode 100644 test/command/8003.md
diff --git a/src/Text/Pandoc/Asciify.hs b/src/Text/Pandoc/Asciify.hs
index 5b84542bf..b7ee6c216 100644
--- a/src/Text/Pandoc/Asciify.hs
+++ b/src/Text/Pandoc/Asciify.hs
@@ -18,11 +18,15 @@ import Data.Text (Text)
import qualified Data.Text as T
toAsciiText :: Text -> Text
-toAsciiText = T.filter isAscii . TN.normalize (TN.NFD)
+toAsciiText = T.filter isAscii . T.map specialCase . TN.normalize (TN.NFD)
+ where
+ specialCase '\x131' = 'i' -- Turkish undotted i
+ specialCase c = c
toAsciiChar :: Char -> Maybe Char
toAsciiChar c = case T.unpack (TN.normalize TN.NFD (T.singleton c)) of
(x:xs) | isAscii x
, all isMark xs
-> Just x
+ ['\x131'] -> Just 'i' -- Turkish undotted i
_ -> Nothing
diff --git a/test/command/8003.md b/test/command/8003.md
new file mode 100644
index 000000000..cff44a03b
--- /dev/null
+++ b/test/command/8003.md
@@ -0,0 +1,6 @@
+```
+% pandoc -f markdown+ascii_identifiers
+# Işık
+^D
+<h1 id="isik">Işık</h1>
+```