In smart mode, use nonbreaking spaces after abbreviations in markdown parser.

Thus, for example, "Mr. Brown" comes out as "Mr.~Brown" in LaTeX, and does
not produce a sentence-separating space.  Resolves Issue #75.


git-svn-id: https://pandoc.googlecode.com/svn/trunk@1298 788f1e2b-df1e-0410-8736-df70ead52e1b

README

@@ -316,10 +316,11 @@ For further documentation, see the `pandoc(1)` man page.
 `-S` or `--smart`
 :   causes `pandoc` to produce typographically correct output, along the
     lines of John Gruber's [Smartypants]. Straight quotes are converted
-    to curly quotes, `---` to dashes, and `...` to ellipses. (Note: This
-    option is only significant when the input format is `markdown`.
-    It is selected automatically when the output format is `latex` or
-    `context`.)
+    to curly quotes, `---` to dashes, and `...` to ellipses. Nonbreaking
+    spaces are inserted after certain abbreviations, such as "Mr."
+    (Note: This option is only significant when the input format is
+    `markdown`. It is selected automatically when the output format is
+    `latex` or `context`.)
 
 `-m`*[url]* or `--asciimathml`*[=url]*
 :   causes `pandoc` to use Peter Jipsen's [ASCIIMathML] script to display

Text/Pandoc/Readers/Markdown.hs

@@ -33,7 +33,7 @@ module Text.Pandoc.Readers.Markdown (
 
 import Data.List ( transpose, isPrefixOf, isSuffixOf, lookup, sortBy, findIndex )
 import Data.Ord ( comparing )
-import Data.Char ( isAlphaNum )
+import Data.Char ( isAlphaNum, isAlpha, isLower, isDigit )
 import Data.Maybe ( fromMaybe )
 import Text.Pandoc.Definition
 import Text.Pandoc.Shared 
@@ -697,7 +697,8 @@ table = simpleTable <|> multilineTable <?> "table"
 
 inline = choice inlineParsers <?> "inline"
 
-inlineParsers = [ str
+inlineParsers = [ abbrev
+                , str
                 , smartPunctuation
                 , whitespace
                 , endline
@@ -792,6 +793,26 @@ subscript = failIfStrict >> enclosed (char '~') (char '~')
             (notFollowedBy' whitespace >> inline) >>=  -- may not contain Space
             return . Subscript 
 
+abbrev = failUnlessSmart >>
+         (assumedAbbrev <|> knownAbbrev) >>= return . Str . (++ ".\160")
+
+-- an string of letters followed by a period that does not end a sentence
+-- is assumed to be an abbreviation.  It is assumed that sentences don't
+-- start with lowercase letters or numerals.
+assumedAbbrev = try $ do
+  result <- many1 $ satisfy isAlpha
+  string ". "
+  lookAhead $ satisfy (\x -> isLower x || isDigit x)
+  return result
+
+-- these strings are treated as abbreviations even if they are followed
+-- by a capital letter (such as a name).
+knownAbbrev = try $ do
+  result <- oneOfStrings [ "Mr", "Mrs", "Ms", "Capt", "Dr", "Prof", "Gen",
+                           "Gov", "e.g", "i.e", "Sgt", "St", "vol", "vs" ]
+  string ". "
+  return result
+  
 smartPunctuation = failUnlessSmart >> 
                    choice [ quoted, apostrophe, dash, ellipses ]
 

tests/testsuite.native

@@ -165,7 +165,7 @@ Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite"] ["John MacFarlane
       [ [ Plain [Str "Nested",Str "."] ]
      ] ] ]
 , Para [Str "Should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "list",Space,Str "item:"]
-, Para [Str "M",Str ".",Str "A",Str ".",Space,Str "2007"]
+, Para [Str "M",Str ".",Str "A.\160",Str "2007"]
 , Para [Str "B",Str ".",Space,Str "Williams"]
 , HorizontalRule
 , Header 1 [Str "Definition",Space,Str "Lists"]

tests/writer.context

@@ -444,7 +444,7 @@ Autonumbering:
 
 Should not be a list item:
 
-M.A. 2007
+M.A.~2007
 
 B. Williams
 

tests/writer.docbook

@@ -606,7 +606,7 @@ These should not be escaped:  \$ \\ \> \[ \{
         Should not be a list item:
       </para>
       <para>
-        M.A. 2007
+        M.A.&nbsp;2007
       </para>
       <para>
         B. Williams

tests/writer.html

@@ -412,7 +412,7 @@ These should not be escaped:  \$ \\ \> \[ \{
     ><p
     >Should not be a list item:</p
     ><p
-    >M.A. 2007</p
+    >M.A.&#160;2007</p
     ><p
     >B. Williams</p
     ><hr

tests/writer.latex

@@ -394,7 +394,7 @@ Autonumbering:
 \end{enumerate}
 Should not be a list item:
 
-M.A. 2007
+M.A.~2007
 
 B. Williams
 

tests/writer.man

@@ -296,7 +296,7 @@ Nested\.
 .PP
 Should not be a list item:
 .PP
-M\.A\. 2007
+M\.A\.\ 2007
 .PP
 B\. Williams
 .PP

tests/writer.markdown

@@ -269,7 +269,7 @@ Autonumbering:
 
 Should not be a list item:
 
-M.A. 2007
+M.A. 2007
 
 B. Williams
 

tests/writer.native

@@ -165,7 +165,7 @@ Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite"] ["John MacFarlane
       [ [ Plain [Str "Nested",Str "."] ]
      ] ] ]
 , Para [Str "Should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "list",Space,Str "item:"]
-, Para [Str "M",Str ".",Str "A",Str ".",Space,Str "2007"]
+, Para [Str "M",Str ".",Str "A.\160",Str "2007"]
 , Para [Str "B",Str ".",Space,Str "Williams"]
 , HorizontalRule
 , Header 1 [Str "Definition",Space,Str "Lists"]

tests/writer.rst

@@ -329,7 +329,7 @@ Autonumbering:
 
 Should not be a list item:
 
-M.A. 2007
+M.A. 2007
 
 B. Williams
 

tests/writer.rtf

@@ -148,7 +148,7 @@ These should not be escaped:  \\$ \\\\ \\> \\[ \\\{\par}
 {\pard \ql \f0 \sa0 \li360 \fi-360 2.\tx360\tab More.\par}
 {\pard \ql \f0 \sa0 \li720 \fi-360 a.\tx360\tab Nested.\sa180\sa180\par}
 {\pard \ql \f0 \sa180 \li0 \fi0 Should not be a list item:\par}
-{\pard \ql \f0 \sa180 \li0 \fi0 M.A. 2007\par}
+{\pard \ql \f0 \sa180 \li0 \fi0 M.A.\u160?2007\par}
 {\pard \ql \f0 \sa180 \li0 \fi0 B. Williams\par}
 {\pard \qc \f0 \sa180 \li0 \fi0 \emdash\emdash\emdash\emdash\emdash\par}
 {\pard \ql \f0 \sa180 \li0 \fi0 \b \fs36 Definition Lists\par}

tests/writer.texinfo

@@ -506,7 +506,7 @@ Nested.
 
 Should not be a list item:
 
-M.A. 2007
+M.A.@ 2007
 
 B. Williams