aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Entities.hs
diff options
context:
space:
mode:
Diffstat (limited to 'src/Text/Pandoc/Entities.hs')
-rw-r--r--src/Text/Pandoc/Entities.hs11
1 files changed, 8 insertions, 3 deletions
diff --git a/src/Text/Pandoc/Entities.hs b/src/Text/Pandoc/Entities.hs
index fd3cf9e57..26785b9a8 100644
--- a/src/Text/Pandoc/Entities.hs
+++ b/src/Text/Pandoc/Entities.hs
@@ -32,14 +32,19 @@ module Text.Pandoc.Entities (
entityToChar,
charToEntity,
decodeEntities,
- encodeEntities
+ encodeEntities,
+ characterEntity
) where
import Data.Char ( chr, ord )
-import Text.Regex ( mkRegex, matchRegexAll )
+import Text.Regex ( mkRegex, matchRegexAll, Regex )
import Maybe ( fromMaybe )
--- regexs for entities
+-- | Regular expression for decimal coded entity.
+decimalCodedEntity :: Text.Regex.Regex
decimalCodedEntity = mkRegex "&#([0-9]+);"
+
+-- | Regular expression for character entity.
+characterEntity :: Text.Regex.Regex
characterEntity = mkRegex "&#[0-9]+;|&[A-Za-z0-9]+;"
-- | Return a string with all entity references decoded to unicode characters