From cbf2ed37bf41cd6469fda02ef1c7a38d8086fcfb Mon Sep 17 00:00:00 2001
From: Michael Camilleri <mike@inqk.net>
Date: Thu, 4 Jun 2020 05:40:00 +0900
Subject: [PATCH] Improve support for single quotes in Haskell lexer (#1524)

Haskell uses matching single quotes to express character literals (e.g.
`'A'`). However, the unmatched single quote character, `'`, is also
used for various purposes (e.g. as part of a variable name like `x'` or
in the name of a promoted type like `'Bar`). Currently, Rouge's Haskell
lexer permits the use of an unmatched single quote by having separate
rules for naming and then a general rule of lower precedence for when
the lexer encounters `'`.

A better approach would be to only treat `'` as being part of a
character literal if the lexer detects that there is a matching `'`
within an appropriate number of characters. This commit does that and
then creates a more general rule for matching names.
---
 lib/rouge/lexers/haskell.rb | 46 ++++++++++++++++++++++---------------
 spec/visual/samples/haskell |  2 ++
 2 files changed, 29 insertions(+), 19 deletions(-)

diff --git a/lib/rouge/lexers/haskell.rb b/lib/rouge/lexers/haskell.rb
index 594cd927f1..6891847d15 100644
--- a/lib/rouge/lexers/haskell.rb
+++ b/lib/rouge/lexers/haskell.rb
@@ -17,8 +17,8 @@ def self.detect?(text)
       end
 
       reserved = %w(
-        _ case class data default deriving do else if in
-        infix[lr]? instance let newtype of then type where
+        _ case class data default deriving do else if in infix infixl infixr
+        instance let newtype of then type where
       )
 
       ascii = %w(
@@ -54,14 +54,31 @@ def self.detect?(text)
       state :root do
         mixin :basic
 
-        rule %r/\bimport\b/, Keyword::Reserved, :import
-        rule %r/\bmodule\b/, Keyword::Reserved, :module
-        rule %r/\b(?:#{reserved.join('|')})\b/, Keyword::Reserved
-        # not sure why, but ^ doesn't work here
-        # rule %r/^[_a-z][\w']*/, Name::Function
-        rule %r/[_a-z][\w']*/, Name
-        rule %r/[A-Z][\w']*/, Keyword::Type
-        rule %r/'[A-Z]\w+'?/, Keyword::Type  # promoted data constructor
+        rule %r/'(?=(?:.|\\\S+)')/, Str::Char, :character
+        rule %r/"/, Str, :string
+
+        rule %r/\d+e[+-]?\d+/i, Num::Float
+        rule %r/\d+\.\d+(e[+-]?\d+)?/i, Num::Float
+        rule %r/0o[0-7]+/i, Num::Oct
+        rule %r/0x[\da-f]+/i, Num::Hex
+        rule %r/\d+/, Num::Integer
+
+        rule %r/[\w']+/ do |m|
+          match = m[0]
+          if match == "import"
+            token Keyword::Reserved
+            push :import
+          elsif match == "module"
+            token Keyword::Reserved
+            push :module
+          elsif reserved.include?(match)
+            token Keyword::Reserved
+          elsif match =~ /\A'?[A-Z]/
+            token Keyword::Type
+          else
+            token Name
+          end
+        end
 
         # lambda operator
         rule %r(\\(?![:!#\$\%&*+.\\/<=>?@^\|~-]+)), Name::Function
@@ -72,15 +89,6 @@ def self.detect?(text)
         # other operators
         rule %r([:!#\$\%&*+.\\/<=>?@^\|~-]+), Operator
 
-        rule %r/\d+e[+-]?\d+/i, Num::Float
-        rule %r/\d+\.\d+(e[+-]?\d+)?/i, Num::Float
-        rule %r/0o[0-7]+/i, Num::Oct
-        rule %r/0x[\da-f]+/i, Num::Hex
-        rule %r/\d+/, Num::Integer
-
-        rule %r/'/, Str::Char, :character
-        rule %r/"/, Str, :string
-
         rule %r/\[\s*\]/, Keyword::Type
         rule %r/\(\s*\)/, Name::Builtin
 
diff --git a/spec/visual/samples/haskell b/spec/visual/samples/haskell
index a0ac7d1ce0..6d7a9e1f3e 100644
--- a/spec/visual/samples/haskell
+++ b/spec/visual/samples/haskell
@@ -399,3 +399,5 @@ quasi3 = [here|Newlines
 are part of
 the quotation
 |]
+
+[ H.label [ H.for' hName, H.class' "col-sm-2 col-form-label" ] [ text msg ]