Made charWidth in Text.Pandoc.Pretty complete.

Used the unicode spec EastAsianWidth.txt.
All characters marked W or F get width 2.

Closes #377.

1 files changed, 35 insertions, 29 deletions

diff --git a/src/Text/Pandoc/Pretty.hs b/src/Text/Pandoc/Pretty.hs
index c3979348e..b06f2f384 100644
--- a/src/Text/Pandoc/Pretty.hs
+++ b/src/Text/Pandoc/Pretty.hs
@@ -468,36 +468,42 @@ doubleQuotes = inside (char '"') (char '"')
 charWidth :: Char -> Int
 charWidth c =
   case c of
-      _ | c >= '\x300' && c <= '\x36e'     -> 0  -- combining
-        | c == '\x3000'                    -> 2  -- full
-        | c >= '\xFF01' && c <= '\xFF60'   -> 2
-        | c >= '\xFFE0' && c <= '\xFFE6'   -> 2
-        | c >= '\x1100' && c <= '\x1159'   -> 2  -- wide
-        | c >= '\x115F' && c <= '\x115F'   -> 2
+      _ | c <  '\x0300'                    -> 1
+        | c >= '\x0300' && c <= '\x036F'   -> 0  -- combining
+        | c >= '\x0370' && c <= '\x10FC'   -> 1
+        | c >= '\x1100' && c <= '\x115F'   -> 2
+        | c >= '\x1160' && c <= '\x11A2'   -> 1
+        | c >= '\x11A3' && c <= '\x11A7'   -> 2
+        | c >= '\x11A8' && c <= '\x11F9'   -> 1
+        | c >= '\x11FA' && c <= '\x11FF'   -> 2
+        | c >= '\x1200' && c <= '\x2328'   -> 1
         | c >= '\x2329' && c <= '\x232A'   -> 2
-        | c >= '\x2E80' && c <= '\x2E99'   -> 2
-        | c >= '\x2E9B' && c <= '\x2EF3'   -> 2
-        | c >= '\x2F00' && c <= '\x2FD5'   -> 2
-        | c >= '\x2FF0' && c <= '\x2FFB'   -> 2
-        | c >= '\x3001' && c <= '\x303E'   -> 2
-        | c >= '\x3041' && c <= '\x3096'   -> 2
-        | c >= '\x3099' && c <= '\x30FF'   -> 2
-        | c >= '\x3105' && c <= '\x312C'   -> 2
-        | c >= '\x3131' && c <= '\x318E'   -> 2
-        | c >= '\x3190' && c <= '\x31B7'   -> 2
-        | c >= '\x31F0' && c <= '\x321E'   -> 2
-        | c >= '\x3220' && c <= '\x3243'   -> 2
-        | c >= '\x3250' && c <= '\x327D'   -> 2
-        | c >= '\x327F' && c <= '\x32FE'   -> 2
-        | c >= '\x3300' && c <= '\x33FF'   -> 2
-        | c >= '\xA000' && c <= '\xA48C'   -> 2
-        | c >= '\xA490' && c <= '\xA4C6'   -> 2
-        | c >= '\xF900' && c <= '\xFA2D'   -> 2
-        | c >= '\xFA30' && c <= '\xFA6A'   -> 2
-        | c >= '\xFE30' && c <= '\xFE52'   -> 2
-        | c >= '\xFE54' && c <= '\xFE66'   -> 2
-        | c >= '\xFE68' && c <= '\xFE6B'   -> 2
-        | c >= '\x2F800' && c <= '\x2FA1D' -> 2
+        | c >= '\x232B' && c <= '\x2E31'   -> 1
+        | c >= '\x2E80' && c <= '\x303E'   -> 2
+        | c == '\x303F'                    -> 1
+        | c >= '\x3041' && c <= '\x3247'   -> 2
+        | c >= '\x3248' && c <= '\x324F'   -> 1 -- ambiguous
+        | c >= '\x3250' && c <= '\x4DBF'   -> 2
+        | c >= '\x4DC0' && c <= '\x4DFF'   -> 1
+        | c >= '\x4E00' && c <= '\xA4C6'   -> 2
+        | c >= '\xA4D0' && c <= '\xA95F'   -> 1
+        | c >= '\xA960' && c <= '\xA97C'   -> 2
+        | c >= '\xA980' && c <= '\xABF9'   -> 1
+        | c >= '\xAC00' && c <= '\xD7FB'   -> 2
+        | c >= '\xD800' && c <= '\xDFFF'   -> 1
+        | c >= '\xE000' && c <= '\xF8FF'   -> 1 -- ambiguous
+        | c >= '\xF900' && c <= '\xFAFF'   -> 2
+        | c >= '\xFB00' && c <= '\xFDFD'   -> 1
+        | c >= '\xFE00' && c <= '\xFE0F'   -> 1 -- ambiguous
+        | c >= '\xFE10' && c <= '\xFE19'   -> 2
+        | c >= '\xFE20' && c <= '\xFE26'   -> 1
+        | c >= '\xFE30' && c <= '\xFE6B'   -> 2
+        | c >= '\xFE70' && c <= '\x16A38'  -> 1
+        | c >= '\x1B000' && c <= '\x1B001' -> 2
+        | c >= '\x1D000' && c <= '\x1F1FF' -> 1
+        | c >= '\x1F200' && c <= '\x1F251' -> 2
+        | c >= '\x1F300' && c <= '\x1F773' -> 1
+        | c >= '\x20000' && c <= '\x3FFFD' -> 2
         | otherwise                        -> 1
 
 -- | Get real length of string, taking into account combining and double-wide