git.iko.soy/typeable/pandoc
on master help sign in
Made charWidth in Text.Pandoc.Pretty complete.

Used the unicode spec EastAsianWidth.txt. All characters marked W or F get width 2. Closes #377.

commit5b3c0a10819a317cda5d6acaf2144a017bf55d75 authorJohn MacFarlane <fiddlosopher@gmail.com> dateFri 27 Jan 2012, 13:30 (15 years ago) parent663cfc2
1 file changed+35−29
src/Text/Pandoc/Pretty.hs+35−29
src/Text/Pandoc/Pretty.hs+35−29
@@ -468,36 +468,42 @@ doubleQuotes = inside (char '"') (char '"')
468468charWidth :: Char -> Int
469469charWidth c =
470470 case c of
471− _ | c >= '\x300' && c <= '\x36e' -> 0 -- combining
472− | c == '\x3000' -> 2 -- full
473− | c >= '\xFF01' && c <= '\xFF60' -> 2
474− | c >= '\xFFE0' && c <= '\xFFE6' -> 2
475− | c >= '\x1100' && c <= '\x1159' -> 2 -- wide
476− | c >= '\x115F' && c <= '\x115F' -> 2
471+ _ | c < '\x0300' -> 1
472+ | c >= '\x0300' && c <= '\x036F' -> 0 -- combining
473+ | c >= '\x0370' && c <= '\x10FC' -> 1
474+ | c >= '\x1100' && c <= '\x115F' -> 2
475+ | c >= '\x1160' && c <= '\x11A2' -> 1
476+ | c >= '\x11A3' && c <= '\x11A7' -> 2
477+ | c >= '\x11A8' && c <= '\x11F9' -> 1
478+ | c >= '\x11FA' && c <= '\x11FF' -> 2
479+ | c >= '\x1200' && c <= '\x2328' -> 1
477480 | c >= '\x2329' && c <= '\x232A' -> 2
478− | c >= '\x2E80' && c <= '\x2E99' -> 2
479− | c >= '\x2E9B' && c <= '\x2EF3' -> 2
480− | c >= '\x2F00' && c <= '\x2FD5' -> 2
481− | c >= '\x2FF0' && c <= '\x2FFB' -> 2
482− | c >= '\x3001' && c <= '\x303E' -> 2
483− | c >= '\x3041' && c <= '\x3096' -> 2
484− | c >= '\x3099' && c <= '\x30FF' -> 2
485− | c >= '\x3105' && c <= '\x312C' -> 2
486− | c >= '\x3131' && c <= '\x318E' -> 2
487− | c >= '\x3190' && c <= '\x31B7' -> 2
488− | c >= '\x31F0' && c <= '\x321E' -> 2
489− | c >= '\x3220' && c <= '\x3243' -> 2
490− | c >= '\x3250' && c <= '\x327D' -> 2
491− | c >= '\x327F' && c <= '\x32FE' -> 2
492− | c >= '\x3300' && c <= '\x33FF' -> 2
493− | c >= '\xA000' && c <= '\xA48C' -> 2
494− | c >= '\xA490' && c <= '\xA4C6' -> 2
495− | c >= '\xF900' && c <= '\xFA2D' -> 2
496− | c >= '\xFA30' && c <= '\xFA6A' -> 2
497− | c >= '\xFE30' && c <= '\xFE52' -> 2
498− | c >= '\xFE54' && c <= '\xFE66' -> 2
499− | c >= '\xFE68' && c <= '\xFE6B' -> 2
500− | c >= '\x2F800' && c <= '\x2FA1D' -> 2
481+ | c >= '\x232B' && c <= '\x2E31' -> 1
482+ | c >= '\x2E80' && c <= '\x303E' -> 2
483+ | c == '\x303F' -> 1
484+ | c >= '\x3041' && c <= '\x3247' -> 2
485+ | c >= '\x3248' && c <= '\x324F' -> 1 -- ambiguous
486+ | c >= '\x3250' && c <= '\x4DBF' -> 2
487+ | c >= '\x4DC0' && c <= '\x4DFF' -> 1
488+ | c >= '\x4E00' && c <= '\xA4C6' -> 2
489+ | c >= '\xA4D0' && c <= '\xA95F' -> 1
490+ | c >= '\xA960' && c <= '\xA97C' -> 2
491+ | c >= '\xA980' && c <= '\xABF9' -> 1
492+ | c >= '\xAC00' && c <= '\xD7FB' -> 2
493+ | c >= '\xD800' && c <= '\xDFFF' -> 1
494+ | c >= '\xE000' && c <= '\xF8FF' -> 1 -- ambiguous
495+ | c >= '\xF900' && c <= '\xFAFF' -> 2
496+ | c >= '\xFB00' && c <= '\xFDFD' -> 1
497+ | c >= '\xFE00' && c <= '\xFE0F' -> 1 -- ambiguous
498+ | c >= '\xFE10' && c <= '\xFE19' -> 2
499+ | c >= '\xFE20' && c <= '\xFE26' -> 1
500+ | c >= '\xFE30' && c <= '\xFE6B' -> 2
501+ | c >= '\xFE70' && c <= '\x16A38' -> 1
502+ | c >= '\x1B000' && c <= '\x1B001' -> 2
503+ | c >= '\x1D000' && c <= '\x1F1FF' -> 1
504+ | c >= '\x1F200' && c <= '\x1F251' -> 2
505+ | c >= '\x1F300' && c <= '\x1F773' -> 1
506+ | c >= '\x20000' && c <= '\x3FFFD' -> 2
501507 | otherwise -> 1
502508
503509-- | Get real length of string, taking into account combining and double-wide