From bfd5c6b172b7b4cc471b1ed80673bac545604f62 Mon Sep 17 00:00:00 2001
From: Herwig Stuetz <herwig@herwigstuetz.com>
Date: Tue, 23 May 2017 21:30:31 +0200
Subject: Org reader: Fix cite parsing behaviour

Until now, org-ref cite keys included special characters also at the
end. This caused problems when citations occur right before colons or
at the end of a sentence.

With this change, all non alphanumeric characters at the end of a cite
key are ignored.

This also adds `,` to the list of special characters that are legal
in cite keys to better mirror the behaviour of org-export.
---
 src/Text/Pandoc/Readers/Org/Inlines.hs | 12 ++++++++++--
 test/Tests/Readers/Org.hs              | 36 ++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/src/Text/Pandoc/Readers/Org/Inlines.hs b/src/Text/Pandoc/Readers/Org/Inlines.hs
index 6946e8379..dcea61222 100644
--- a/src/Text/Pandoc/Readers/Org/Inlines.hs
+++ b/src/Text/Pandoc/Readers/Org/Inlines.hs
@@ -339,8 +339,16 @@ linkLikeOrgRefCite = try $ do
 -- | Read a citation key.  The characters allowed in citation keys are taken
 -- from the `org-ref-cite-re` variable in `org-ref.el`.
 orgRefCiteKey :: PandocMonad m => OrgParser m String
-orgRefCiteKey = try . many1 . satisfy $ \c ->
-                  isAlphaNum c || c `elem` ("-_:\\./"::String)
+orgRefCiteKey =
+  let citeKeySpecialChars = "-_:\\./," :: String
+      isCiteKeySpecialChar c = c `elem` citeKeySpecialChars
+      isCiteKeyChar c = isAlphaNum c || isCiteKeySpecialChar c
+
+  in try $ many1Till (satisfy $ isCiteKeyChar)
+           $ try . lookAhead $ do
+               many . satisfy $ isCiteKeySpecialChar
+               satisfy $ not . isCiteKeyChar
+
 
 -- | Supported citation types.  Only a small subset of org-ref types is
 -- supported for now.  TODO: rewrite this, use LaTeX reader as template.
diff --git a/test/Tests/Readers/Org.hs b/test/Tests/Readers/Org.hs
index 37ad2462b..3302e0c3e 100644
--- a/test/Tests/Readers/Org.hs
+++ b/test/Tests/Readers/Org.hs
@@ -334,6 +334,18 @@ tests =
                        }
         in (para $ cite [citation] "cite:pandoc")
 
+      , "Org-ref simple citation with underscores" =:
+        "cite:pandoc_org_ref" =?>
+        let citation = Citation
+                       { citationId = "pandoc_org_ref"
+                       , citationPrefix = mempty
+                       , citationSuffix = mempty
+                       , citationMode = AuthorInText
+                       , citationNoteNum = 0
+                       , citationHash = 0
+                       }
+        in (para $ cite [citation] "cite:pandoc_org_ref")
+
       , "Org-ref simple citation succeeded by comma" =:
         "cite:pandoc," =?>
         let citation = Citation
@@ -346,6 +358,30 @@ tests =
                        }
         in (para $ cite [citation] "cite:pandoc" <> str ",")
 
+      , "Org-ref simple citation succeeded by dot" =:
+        "cite:pandoc." =?>
+        let citation = Citation
+                       { citationId = "pandoc"
+                       , citationPrefix = mempty
+                       , citationSuffix = mempty
+                       , citationMode = AuthorInText
+                       , citationNoteNum = 0
+                       , citationHash = 0
+                       }
+        in (para $ cite [citation] "cite:pandoc" <> str ".")
+
+      , "Org-ref simple citation succeeded by colon" =:
+        "cite:pandoc:" =?>
+        let citation = Citation
+                       { citationId = "pandoc"
+                       , citationPrefix = mempty
+                       , citationSuffix = mempty
+                       , citationMode = AuthorInText
+                       , citationNoteNum = 0
+                       , citationHash = 0
+                       }
+        in (para $ cite [citation] "cite:pandoc" <> str ":")
+
       , "Org-ref simple citep citation" =:
         "citep:pandoc" =?>
         let citation = Citation
-- 
cgit v1.2.3