From 501df7613c67bcd743eaa00071f0dbb179607394 Mon Sep 17 00:00:00 2001
From: Quintus <sutniuq@gmx.net>
Date: Sun, 22 Apr 2012 22:10:42 +0200
Subject: Lua scanner for CodeRay. Meta-commit. This commit is a super-commit
 containing all the subcommits for implementing the Lua scanner.

---
 lib/coderay/scanners/lua.rb | 267 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 267 insertions(+)
 create mode 100644 lib/coderay/scanners/lua.rb

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
new file mode 100644
index 0000000..e7706fc
--- /dev/null
+++ b/lib/coderay/scanners/lua.rb
@@ -0,0 +1,267 @@
+# -*- coding: utf-8 -*-
+
+# Scanner for the Lua[http://lua.org] programming lanuage.
+#
+# The language’s complete syntax is defined in
+# {the Lua manual}[http://www.lua.org/manual/5.2/manual.html],
+# which is what this scanner tries to conform to.
+class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
+
+  register_for :lua
+  file_extension "lua"
+  title "Lua"
+
+  # Keywords used in Lua.
+  KEYWORDS = %w[and break do else elseif end
+  for function goto if in
+  local not or repeat return
+  then until while
+  ]
+
+  # Constants set by the Lua core.
+  PREDEFINED_CONSTANTS = %w[false true nil]
+
+  # The expressions contained in this array are parts of Lua’s `basic'
+  # library. Although it’s not entirely necessary to load that library,
+  # it is highly recommended and one would have to provide own implementations
+  # of some of these expressions if one does not do so. They however aren’t
+  # keywords, neither are they constants, but nearly predefined, so they
+  # get tagged as `predefined' rather than anything else.
+  #
+  # This list excludes values of form `_UPPERCASE' because the Lua manual
+  # requires such identifiers to be reserved by Lua anyway and they are
+  # highlighted directly accordingly, without the need for specific
+  # identifiers to be listed here.
+  PREDEFINED_EXPRESSIONS = %w[
+  assert collectgarbage dofile error getmetatable
+  ipairs load loadfile next pairs pcall print
+  rawequal rawget rawlen rawset select setmetatable
+  tonumber tostring type xpcall
+  ]
+
+  # Automatic token kind selection for normal words.
+  IDENT_KIND = CodeRay::WordList.new(:ident)
+    .add(KEYWORDS, :keyword)
+    .add(PREDEFINED_CONSTANTS, :predefined_constant)
+    .add(PREDEFINED_EXPRESSIONS, :predefined)
+
+  protected
+
+  # Scanner initialization.
+  def setup
+    @state       = :initial
+    @brace_depth = 0
+  end
+
+  # CodeRay entry hook. Starts parsing.
+  def scan_tokens(encoder, options)
+    @encoder = encoder
+    @options = options
+
+    send(:"handle_state_#@state") until eos?
+
+    @encoder
+  end
+
+  def handle_state_initial
+    if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
+      @num_equals = match.count("=") # Number must match for comment end
+      @encoder.begin_group(:comment)
+      @encoder.text_token(match, :delimiter)
+      @state = :long_comment
+
+    elsif match = scan(/--.*?$/) # --Lua comment
+      @encoder.text_token(match, :comment)
+
+    elsif match = scan(/\[=*\[/)     # [[ long (possibly multiline) string ]]
+      @num_equals = match.count("=") # Number must match for comment end
+      @encoder.begin_group(:string)
+      @encoder.text_token(match, :delimiter)
+      @state = :long_string
+
+    elsif match = scan(/::\s*[a-zA-Z_][a-zA-Z0-9_]+\s*::/) # ::goto_label::
+      @encoder.text_token(match, :label)
+
+    elsif match = scan(/_[A-Z]+/) # _UPPERCASE are names reserved for Lua
+      @encoder.text_token(match, :predefined)
+
+    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # Normal letters (or letters followed by digits)
+      kind = IDENT_KIND[match]
+
+      # Extra highlighting for entities following certain keywords
+      if kind == :keyword and match == "function"
+        @state = :function_expected
+      elsif kind == :keyword and match == "goto"
+        @state = :goto_label_expected
+      elsif kind == :keyword and match == "local"
+        @state = :local_var_expected
+      end
+
+      @encoder.text_token(match, kind)
+
+    elsif match = scan(/{/) # Opening table brace {
+      @encoder.begin_group(:table)
+      @encoder.text_token(match, @brace_depth >= 1 ? :inline_delimiter : :delimiter)
+      @brace_depth += 1
+      @state        = :table
+
+    elsif match = scan(/}/) # Closing table brace }
+      if @brace_depth == 1
+        @brace_depth = 0
+        @encoder.text_token(match, :delimiter)
+      elsif @brace_depth == 0 # Mismatched brace
+        @encoder.text_token(match, :error)
+      else
+        @brace_depth -= 1
+        @encoder.text_token(match, :inline_delimiter)
+        @state = :table
+      end
+      @encoder.end_group(:table)
+
+    elsif match = scan(/["']/) # String delimiters " and '
+      @encoder.begin_group(:string)
+      @encoder.text_token(match, :delimiter)
+      @start_delim = match
+      @state       = :string
+
+                      # ↓Prefix                hex number ←|→ decimal number
+    elsif match = scan(/-? (?:0x\h* \. \h+ (?:p[+\-]?\d+)? | \d*\.\d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
+      @encoder.text_token(match, :float)
+
+                      # ↓Prefix         hex number ←|→ decimal number
+    elsif match = scan(/-? (?:0x\h+ (?:p[+\-]?\d+)? | \d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
+      @encoder.text_token(match, :integer)
+
+    elsif match = scan(/[\+\-\*\/%^\#=~<>\(\)\[\]:;,] | \.(?!\d)/x) # Operators
+      @encoder.text_token(match, :operator)
+
+    elsif match = scan(/\s+/) # Space
+      @encoder.text_token(match, :space)
+
+    else # Invalid stuff. Note that Lua doesn’t accept multibyte chars outside of strings, hence these are also errors.
+      @encoder.text_token(getch, :error)
+    end
+
+    # It may be that we’re scanning a full-blown subexpression of a table
+    # (tables can contain full expressions in parts).
+    # If this is the case, return to :table scanning state.
+    @state = :table if @state == :initial && @brace_depth >= 1
+  end
+
+  def handle_state_function_expected
+    if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
+      @encoder.text_token(match, :operator)
+      @state = :initial
+    elsif match = scan(/[a-zA-Z_] (?:[a-zA-Z0-9_\.] (?!\.\d))* [\.\:]/x) # function tbl.subtbl.foo() | function tbl:foo() # Colon only allowed as last separator
+      @encoder.text_token(match, :ident)
+    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # function foo()
+      @encoder.text_token(match, :function)
+      @state = :initial
+    elsif match = scan(/\s+/) # Between the `function' keyword and the ident may be any amount of whitespace
+      @encoder.text_token(match, :space)
+    else
+      @encoder.text_token(getch, :error)
+      @state = :initial
+    end
+  end
+
+  def handle_state_goto_label_expected
+    if match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
+      @encoder.text_token(match, :label)
+      @state = :initial
+    elsif match = scan(/\s+/) # Between the `goto' keyword and the label may be any amount of whitespace
+      @encoder.text_token(match, :space)
+    else
+      @encoder.text_token(getch, :error)
+    end
+  end
+
+  def handle_state_local_var_expected
+    if match = scan(/function/) # local function ...
+      @encoder.text_token(match, :keyword)
+      @state = :function_expected
+    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
+      @encoder.text_token(match, :local_variable)
+    elsif match = scan(/,/)
+      @encoder.text_token(match, :operator)
+    elsif match = scan(/=/)
+      @encoder.text_token(match, :operator)
+      # After encountering the equal sign, arbitrary expressions are
+      # allowed again, so just return to the main state for further
+      # parsing.
+      @state = :initial
+    elsif match = scan(/\n/)
+      @encoder.text_token(match, :space)
+      @state = :initial
+    elsif match = scan(/\s+/)
+      @encoder.text_token(match, :space)
+    else
+      @encoder.text_token(getch, :error)
+    end
+  end
+
+  def handle_state_long_comment
+    if match = scan(/.*?(?=\]={#@num_equals}\])/m)
+      @encoder.text_token(match, :content)
+
+      delim = scan(/\]={#@num_equals}\]/)
+      @encoder.text_token(delim, :delimiter)
+    else # No terminator found till EOF
+      @encoder.text_token(rest, :error)
+      terminate
+    end
+    @encoder.end_group(:comment)
+    @state = :initial
+  end
+
+  def handle_state_long_string
+    if match = scan(/.*?(?=\]={#@num_equals}\])/m) # Long strings do not interpret any escape sequences
+      @encoder.text_token(match, :content)
+
+      delim = scan(/\]={#@num_equals}\]/)
+      @encoder.text_token(delim, :delimiter)
+    else # No terminator found till EOF
+      @encoder.text_token(rest, :error)
+      terminate
+    end
+    @encoder.end_group(:string)
+    @state = :initial
+  end
+
+  def handle_state_string
+    if match = scan(/[^\\#@start_delim\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
+      @encoder.text_token(match, :content)
+    elsif match = scan(/\\(?:['"abfnrtv\\]|z\s*|x\h\h|\d{1,3}|\n)/m)
+      @encoder.text_token(match, :char)
+    elsif match = scan(Regexp.compile(@start_delim))
+      @encoder.text_token(match, :delimiter)
+      @encoder.end_group(:string)
+      @state = :initial
+    elsif match = scan(/\n/) # Lua forbids unescaped newlines in normal non-long strings
+      @encoder.text_token("\\n\n", :error) # Visually appealing error indicator--otherwise users may wonder whether the highlighter cannot highlight multine strings
+      @encoder.end_group(:string)
+      @state = :initial
+    else
+      @encoder.text_token(getch, :error)
+    end
+  end
+
+  def handle_state_table
+    if match = scan(/[,;]/)
+      @encoder.text_token(match, :operator)
+    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
+      @encoder.text_token(match, :key)
+      @encoder.text_token(scan(/\s+/), :space) if check(/\s+/)
+      @encoder.text_token(scan(/=/), :operator)
+      @state = :initial
+    elsif match = scan(/\s+/m)
+      @encoder.text_token(match, :space)
+    else
+      # Note this clause doesn’t advance the scan pointer, it’s a kind of
+      # "retry with other options" (the :initial state then of course
+      # advances the pointer).
+      @state = :initial
+    end
+  end
+
+end
-- 
cgit v1.2.1


From 8979cc621431248fded86c341e2102a67c5344bb Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Tue, 19 Jun 2012 17:45:49 +0200
Subject: use case+when instead of send and methods

---
 lib/coderay/scanners/lua.rb | 64 ++++++++++++++++++++++-----------------------
 1 file changed, 31 insertions(+), 33 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index e7706fc..e712061 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -40,10 +40,10 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
   ]
 
   # Automatic token kind selection for normal words.
-  IDENT_KIND = CodeRay::WordList.new(:ident)
-    .add(KEYWORDS, :keyword)
-    .add(PREDEFINED_CONSTANTS, :predefined_constant)
-    .add(PREDEFINED_EXPRESSIONS, :predefined)
+  IDENT_KIND = CodeRay::WordList.new(:ident).
+    add(KEYWORDS, :keyword).
+    add(PREDEFINED_CONSTANTS, :predefined_constant).
+    add(PREDEFINED_EXPRESSIONS, :predefined)
 
   protected
 
@@ -57,13 +57,11 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
   def scan_tokens(encoder, options)
     @encoder = encoder
     @options = options
-
-    send(:"handle_state_#@state") until eos?
-
-    @encoder
-  end
-
-  def handle_state_initial
+    
+    until eos?
+  case state
+        
+  when :initial
     if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
       @num_equals = match.count("=") # Number must match for comment end
       @encoder.begin_group(:comment)
@@ -99,13 +97,13 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
 
       @encoder.text_token(match, kind)
 
-    elsif match = scan(/{/) # Opening table brace {
+    elsif match = scan(/\{/) # Opening table brace {
       @encoder.begin_group(:table)
       @encoder.text_token(match, @brace_depth >= 1 ? :inline_delimiter : :delimiter)
       @brace_depth += 1
       @state        = :table
 
-    elsif match = scan(/}/) # Closing table brace }
+    elsif match = scan(/\}/) # Closing table brace }
       if @brace_depth == 1
         @brace_depth = 0
         @encoder.text_token(match, :delimiter)
@@ -146,9 +144,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     # (tables can contain full expressions in parts).
     # If this is the case, return to :table scanning state.
     @state = :table if @state == :initial && @brace_depth >= 1
-  end
-
-  def handle_state_function_expected
+    
+  when :function_expected
     if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
       @encoder.text_token(match, :operator)
       @state = :initial
@@ -163,9 +160,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
       @encoder.text_token(getch, :error)
       @state = :initial
     end
-  end
 
-  def handle_state_goto_label_expected
+  when :goto_label_expected
     if match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
       @encoder.text_token(match, :label)
       @state = :initial
@@ -174,9 +170,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     else
       @encoder.text_token(getch, :error)
     end
-  end
-
-  def handle_state_local_var_expected
+  
+  when :local_var_expected
     if match = scan(/function/) # local function ...
       @encoder.text_token(match, :keyword)
       @state = :function_expected
@@ -198,9 +193,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     else
       @encoder.text_token(getch, :error)
     end
-  end
-
-  def handle_state_long_comment
+    
+  when :long_comment
     if match = scan(/.*?(?=\]={#@num_equals}\])/m)
       @encoder.text_token(match, :content)
 
@@ -212,9 +206,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     end
     @encoder.end_group(:comment)
     @state = :initial
-  end
-
-  def handle_state_long_string
+    
+  when :long_string
     if match = scan(/.*?(?=\]={#@num_equals}\])/m) # Long strings do not interpret any escape sequences
       @encoder.text_token(match, :content)
 
@@ -226,9 +219,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     end
     @encoder.end_group(:string)
     @state = :initial
-  end
-
-  def handle_state_string
+    
+  when :string
     if match = scan(/[^\\#@start_delim\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
       @encoder.text_token(match, :content)
     elsif match = scan(/\\(?:['"abfnrtv\\]|z\s*|x\h\h|\d{1,3}|\n)/m)
@@ -244,9 +236,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     else
       @encoder.text_token(getch, :error)
     end
-  end
-
-  def handle_state_table
+  
+  when :table
     if match = scan(/[,;]/)
       @encoder.text_token(match, :operator)
     elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
@@ -262,6 +253,13 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
       # advances the pointer).
       @state = :initial
     end
+  else
+    raise
+  end
+
+    end
+
+    @encoder
   end
 
 end
-- 
cgit v1.2.1


From b081c1f3ab670301199005c04ecbc11614593285 Mon Sep 17 00:00:00 2001
From: Nathan Youngman <git@nathany.com>
Date: Tue, 11 Sep 2012 15:04:45 -0600
Subject: escape = in regex (my editor gets confused:-)

---
 lib/coderay/scanners/lua.rb | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index e712061..e640397 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -57,10 +57,10 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
   def scan_tokens(encoder, options)
     @encoder = encoder
     @options = options
-    
+
     until eos?
   case state
-        
+
   when :initial
     if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
       @num_equals = match.count("=") # Number must match for comment end
@@ -144,7 +144,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     # (tables can contain full expressions in parts).
     # If this is the case, return to :table scanning state.
     @state = :table if @state == :initial && @brace_depth >= 1
-    
+
   when :function_expected
     if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
       @encoder.text_token(match, :operator)
@@ -170,7 +170,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     else
       @encoder.text_token(getch, :error)
     end
-  
+
   when :local_var_expected
     if match = scan(/function/) # local function ...
       @encoder.text_token(match, :keyword)
@@ -179,7 +179,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
       @encoder.text_token(match, :local_variable)
     elsif match = scan(/,/)
       @encoder.text_token(match, :operator)
-    elsif match = scan(/=/)
+    elsif match = scan(/\=/)
       @encoder.text_token(match, :operator)
       # After encountering the equal sign, arbitrary expressions are
       # allowed again, so just return to the main state for further
@@ -193,7 +193,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     else
       @encoder.text_token(getch, :error)
     end
-    
+
   when :long_comment
     if match = scan(/.*?(?=\]={#@num_equals}\])/m)
       @encoder.text_token(match, :content)
@@ -206,7 +206,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     end
     @encoder.end_group(:comment)
     @state = :initial
-    
+
   when :long_string
     if match = scan(/.*?(?=\]={#@num_equals}\])/m) # Long strings do not interpret any escape sequences
       @encoder.text_token(match, :content)
@@ -219,7 +219,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     end
     @encoder.end_group(:string)
     @state = :initial
-    
+
   when :string
     if match = scan(/[^\\#@start_delim\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
       @encoder.text_token(match, :content)
@@ -236,14 +236,14 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
     else
       @encoder.text_token(getch, :error)
     end
-  
+
   when :table
     if match = scan(/[,;]/)
       @encoder.text_token(match, :operator)
     elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
       @encoder.text_token(match, :key)
       @encoder.text_token(scan(/\s+/), :space) if check(/\s+/)
-      @encoder.text_token(scan(/=/), :operator)
+      @encoder.text_token(scan(/\=/), :operator)
       @state = :initial
     elsif match = scan(/\s+/m)
       @encoder.text_token(match, :space)
-- 
cgit v1.2.1


From 279348d3c2159df4ce6ac5949ada0177aa7c7159 Mon Sep 17 00:00:00 2001
From: Nathan Youngman <git@nathany.com>
Date: Sat, 27 Oct 2012 23:41:52 -0600
Subject: :map token kind

Use :map instead of :table. It's more generic, and won't be confused with the :table rendering style.
---
 lib/coderay/scanners/lua.rb | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index e640397..64763dc 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -98,10 +98,10 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
       @encoder.text_token(match, kind)
 
     elsif match = scan(/\{/) # Opening table brace {
-      @encoder.begin_group(:table)
+      @encoder.begin_group(:map)
       @encoder.text_token(match, @brace_depth >= 1 ? :inline_delimiter : :delimiter)
       @brace_depth += 1
-      @state        = :table
+      @state        = :map
 
     elsif match = scan(/\}/) # Closing table brace }
       if @brace_depth == 1
@@ -112,9 +112,9 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
       else
         @brace_depth -= 1
         @encoder.text_token(match, :inline_delimiter)
-        @state = :table
+        @state = :map
       end
-      @encoder.end_group(:table)
+      @encoder.end_group(:map)
 
     elsif match = scan(/["']/) # String delimiters " and '
       @encoder.begin_group(:string)
@@ -142,8 +142,8 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
 
     # It may be that we’re scanning a full-blown subexpression of a table
     # (tables can contain full expressions in parts).
-    # If this is the case, return to :table scanning state.
-    @state = :table if @state == :initial && @brace_depth >= 1
+    # If this is the case, return to :map scanning state.
+    @state = :map if @state == :initial && @brace_depth >= 1
 
   when :function_expected
     if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
@@ -237,7 +237,7 @@ class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
       @encoder.text_token(getch, :error)
     end
 
-  when :table
+  when :map
     if match = scan(/[,;]/)
       @encoder.text_token(match, :operator)
     elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
-- 
cgit v1.2.1


From d9d6dd5f4a73363ea5d353ecda142f77ed4eba5a Mon Sep 17 00:00:00 2001
From: Gavin Kistner <gkistner@nvidia.com>
Date: Thu, 6 Jun 2013 10:43:19 -0600
Subject: Support CDATA blocks in HTML/XML

---
 lib/coderay/scanners/html.rb | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index 3ba3b79..fcf249a 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -99,7 +99,17 @@ module Scanners
           case state
           
           when :initial
-            if match = scan(/<!--(?:.*?-->|.*)/m)
+            if match = scan(/<!\[CDATA\[/)
+              encoder.begin_group :string
+              encoder.text_token match, :delimiter
+              if match = scan(/.*?\]\]>/m)
+                encoder.text_token match[0..-4], :content
+                encoder.text_token ']]>', :delimiter
+              else
+                encoder.text_token scan(/.*/m), :error
+              end
+              encoder.end_group :string
+            elsif match = scan(/<!--(?:.*?-->|.*)/m)
               encoder.text_token match, :comment
             elsif match = scan(/<!(\w+)(?:.*?>|.*)|\]>/m)
               encoder.text_token match, :doctype
-- 
cgit v1.2.1


From 65eeaca6c18bea379b966559084e47d6fb45c75c Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Wed, 12 Jun 2013 16:19:41 +0200
Subject: add python binary string

---
 lib/coderay/scanners/python.rb | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/python.rb b/lib/coderay/scanners/python.rb
index a9492ab..09c8b6e 100644
--- a/lib/coderay/scanners/python.rb
+++ b/lib/coderay/scanners/python.rb
@@ -157,12 +157,12 @@ module Scanners
             encoder.text_token match, :operator
           
           elsif match = scan(/(u?r?|b)?("""|"|'''|')/i)
+            modifiers = self[1]
             string_delimiter = self[2]
-            string_type = docstring_coming ? :docstring : :string
+            string_type = docstring_coming ? :docstring : (modifiers == 'b' ? :binary : :string)
             docstring_coming = false if docstring_coming
             encoder.begin_group string_type
             string_raw = false
-            modifiers = self[1]
             unless modifiers.empty?
               string_raw = !!modifiers.index(?r)
               encoder.text_token modifiers, :modifier
-- 
cgit v1.2.1


From fc21c91d7a89d98785e494ffd41e9f3adbdfed81 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Wed, 19 Jun 2013 11:50:04 +0200
Subject: use different key/value heuristic in JSON scanner

---
 lib/coderay/scanners/json.rb | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/json.rb b/lib/coderay/scanners/json.rb
index 4e0f462..3754a9b 100644
--- a/lib/coderay/scanners/json.rb
+++ b/lib/coderay/scanners/json.rb
@@ -14,15 +14,17 @@ module Scanners
     
     ESCAPE = / [bfnrt\\"\/] /x  # :nodoc:
     UNICODE_ESCAPE = / u[a-fA-F0-9]{4} /x  # :nodoc:
+    KEY = / (?> (?: [^\\"]+ | \\. )* ) " \s* : /x
     
   protected
     
+    def setup
+      @state = :initial
+    end
+    
     # See http://json.org/ for a definition of the JSON lexic/grammar.
     def scan_tokens encoder, options
-      
-      state = :initial
-      stack = []
-      key_expected = false
+      state = options[:state] || @state
       
       until eos?
         
@@ -32,18 +34,11 @@ module Scanners
           if match = scan(/ \s+ /x)
             encoder.text_token match, :space
           elsif match = scan(/"/)
-            state = key_expected ? :key : :string
+            state = check(/#{KEY}/o) ? :key : :string
             encoder.begin_group state
             encoder.text_token match, :delimiter
           elsif match = scan(/ [:,\[{\]}] /x)
             encoder.text_token match, :operator
-            case match
-            when ':' then key_expected = false
-            when ',' then key_expected = true if stack.last == :object
-            when '{' then stack << :object; key_expected = true
-            when '[' then stack << :array
-            when '}', ']' then stack.pop  # no error recovery, but works for valid JSON
-            end
           elsif match = scan(/ true | false | null /x)
             encoder.text_token match, :value
           elsif match = scan(/ -? (?: 0 | [1-9]\d* ) /x)
@@ -82,6 +77,10 @@ module Scanners
         end
       end
       
+      if options[:keep_state]
+        @state = state
+      end
+      
       if [:string, :key].include? state
         encoder.end_group state
       end
-- 
cgit v1.2.1


From da1425058e9b9e04bd988ddf606331d9cd0c827b Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 01:06:33 +0200
Subject: cleanup Lua scanner, fix end_group(:map) issue - use local instead of
 instance variables

---
 lib/coderay/scanners/lua.rb | 524 ++++++++++++++++++++++----------------------
 1 file changed, 267 insertions(+), 257 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index 64763dc..3bee275 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -1,265 +1,275 @@
-# -*- coding: utf-8 -*-
+# encoding: utf-8
 
-# Scanner for the Lua[http://lua.org] programming lanuage.
-#
-# The language’s complete syntax is defined in
-# {the Lua manual}[http://www.lua.org/manual/5.2/manual.html],
-# which is what this scanner tries to conform to.
-class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
+module CodeRay
+module Scanners
 
-  register_for :lua
-  file_extension "lua"
-  title "Lua"
-
-  # Keywords used in Lua.
-  KEYWORDS = %w[and break do else elseif end
-  for function goto if in
-  local not or repeat return
-  then until while
-  ]
-
-  # Constants set by the Lua core.
-  PREDEFINED_CONSTANTS = %w[false true nil]
-
-  # The expressions contained in this array are parts of Lua’s `basic'
-  # library. Although it’s not entirely necessary to load that library,
-  # it is highly recommended and one would have to provide own implementations
-  # of some of these expressions if one does not do so. They however aren’t
-  # keywords, neither are they constants, but nearly predefined, so they
-  # get tagged as `predefined' rather than anything else.
+  # Scanner for the Lua[http://lua.org] programming lanuage.
   #
-  # This list excludes values of form `_UPPERCASE' because the Lua manual
-  # requires such identifiers to be reserved by Lua anyway and they are
-  # highlighted directly accordingly, without the need for specific
-  # identifiers to be listed here.
-  PREDEFINED_EXPRESSIONS = %w[
-  assert collectgarbage dofile error getmetatable
-  ipairs load loadfile next pairs pcall print
-  rawequal rawget rawlen rawset select setmetatable
-  tonumber tostring type xpcall
-  ]
-
-  # Automatic token kind selection for normal words.
-  IDENT_KIND = CodeRay::WordList.new(:ident).
-    add(KEYWORDS, :keyword).
-    add(PREDEFINED_CONSTANTS, :predefined_constant).
-    add(PREDEFINED_EXPRESSIONS, :predefined)
-
-  protected
-
-  # Scanner initialization.
-  def setup
-    @state       = :initial
-    @brace_depth = 0
-  end
-
-  # CodeRay entry hook. Starts parsing.
-  def scan_tokens(encoder, options)
-    @encoder = encoder
-    @options = options
-
-    until eos?
-  case state
-
-  when :initial
-    if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
-      @num_equals = match.count("=") # Number must match for comment end
-      @encoder.begin_group(:comment)
-      @encoder.text_token(match, :delimiter)
-      @state = :long_comment
-
-    elsif match = scan(/--.*?$/) # --Lua comment
-      @encoder.text_token(match, :comment)
-
-    elsif match = scan(/\[=*\[/)     # [[ long (possibly multiline) string ]]
-      @num_equals = match.count("=") # Number must match for comment end
-      @encoder.begin_group(:string)
-      @encoder.text_token(match, :delimiter)
-      @state = :long_string
-
-    elsif match = scan(/::\s*[a-zA-Z_][a-zA-Z0-9_]+\s*::/) # ::goto_label::
-      @encoder.text_token(match, :label)
-
-    elsif match = scan(/_[A-Z]+/) # _UPPERCASE are names reserved for Lua
-      @encoder.text_token(match, :predefined)
-
-    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # Normal letters (or letters followed by digits)
-      kind = IDENT_KIND[match]
-
-      # Extra highlighting for entities following certain keywords
-      if kind == :keyword and match == "function"
-        @state = :function_expected
-      elsif kind == :keyword and match == "goto"
-        @state = :goto_label_expected
-      elsif kind == :keyword and match == "local"
-        @state = :local_var_expected
+  # The language’s complete syntax is defined in
+  # {the Lua manual}[http://www.lua.org/manual/5.2/manual.html],
+  # which is what this scanner tries to conform to.
+  class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
+    
+    register_for :lua
+    file_extension "lua"
+    title "Lua"
+    
+    # Keywords used in Lua.
+    KEYWORDS = %w[and break do else elseif end
+    for function goto if in
+    local not or repeat return
+    then until while
+    ]
+    
+    # Constants set by the Lua core.
+    PREDEFINED_CONSTANTS = %w[false true nil]
+    
+    # The expressions contained in this array are parts of Lua’s `basic'
+    # library. Although it’s not entirely necessary to load that library,
+    # it is highly recommended and one would have to provide own implementations
+    # of some of these expressions if one does not do so. They however aren’t
+    # keywords, neither are they constants, but nearly predefined, so they
+    # get tagged as `predefined' rather than anything else.
+    #
+    # This list excludes values of form `_UPPERCASE' because the Lua manual
+    # requires such identifiers to be reserved by Lua anyway and they are
+    # highlighted directly accordingly, without the need for specific
+    # identifiers to be listed here.
+    PREDEFINED_EXPRESSIONS = %w[
+    assert collectgarbage dofile error getmetatable
+    ipairs load loadfile next pairs pcall print
+    rawequal rawget rawlen rawset select setmetatable
+    tonumber tostring type xpcall
+    ]
+    
+    # Automatic token kind selection for normal words.
+    IDENT_KIND = CodeRay::WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(PREDEFINED_CONSTANTS, :predefined_constant).
+      add(PREDEFINED_EXPRESSIONS, :predefined)
+    
+    protected
+    
+    # Scanner initialization.
+    def setup
+      @state       = :initial
+      @brace_depth = 0
+    end
+    
+    # CodeRay entry hook. Starts parsing.
+    def scan_tokens(encoder, options)
+      state = options[:state] || @state
+      
+      until eos?
+        case state
+        
+        when :initial
+          if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
+            @num_equals = match.count("=") # Number must match for comment end
+            encoder.begin_group(:comment)
+            encoder.text_token(match, :delimiter)
+            state = :long_comment
+          
+          elsif match = scan(/--.*$/) # --Lua comment
+            encoder.text_token(match, :comment)
+          
+          elsif match = scan(/\[=*\[/)     # [[ long (possibly multiline) string ]]
+            @num_equals = match.count("=") # Number must match for comment end
+            encoder.begin_group(:string)
+            encoder.text_token(match, :delimiter)
+            state = :long_string
+          
+          elsif match = scan(/::\s*[a-zA-Z_][a-zA-Z0-9_]+\s*::/) # ::goto_label::
+            encoder.text_token(match, :label)
+          
+          elsif match = scan(/_[A-Z]+/) # _UPPERCASE are names reserved for Lua
+            encoder.text_token(match, :predefined)
+          
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # Normal letters (or letters followed by digits)
+            kind = IDENT_KIND[match]
+            
+            # Extra highlighting for entities following certain keywords
+            if kind == :keyword and match == "function"
+              state = :function_expected
+            elsif kind == :keyword and match == "goto"
+              state = :goto_label_expected
+            elsif kind == :keyword and match == "local"
+              state = :local_var_expected
+            end
+            
+            encoder.text_token(match, kind)
+          
+          elsif match = scan(/\{/) # Opening table brace {
+            encoder.begin_group(:map)
+            encoder.text_token(match, @brace_depth >= 1 ? :inline_delimiter : :delimiter)
+            @brace_depth += 1
+            state        = :map
+          
+          elsif match = scan(/\}/) # Closing table brace }
+            if @brace_depth == 1
+              @brace_depth = 0
+              encoder.text_token(match, :delimiter)
+              encoder.end_group(:map)
+            elsif @brace_depth == 0 # Mismatched brace
+              encoder.text_token(match, :error)
+            else
+              @brace_depth -= 1
+              encoder.text_token(match, :inline_delimiter)
+              encoder.end_group(:map)
+              state = :map
+            end
+          
+          elsif match = scan(/["']/) # String delimiters " and '
+            encoder.begin_group(:string)
+            encoder.text_token(match, :delimiter)
+            @start_delim = match
+            state       = :string
+          
+                            # ↓Prefix                hex number ←|→ decimal number
+          elsif match = scan(/-? (?:0x\h* \. \h+ (?:p[+\-]?\d+)? | \d*\.\d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
+            encoder.text_token(match, :float)
+          
+                            # ↓Prefix         hex number ←|→ decimal number
+          elsif match = scan(/-? (?:0x\h+ (?:p[+\-]?\d+)? | \d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
+            encoder.text_token(match, :integer)
+          
+          elsif match = scan(/[\+\-\*\/%^\#=~<>\(\)\[\]:;,] | \.(?!\d)/x) # Operators
+            encoder.text_token(match, :operator)
+          
+          elsif match = scan(/\s+/) # Space
+            encoder.text_token(match, :space)
+          
+          else # Invalid stuff. Note that Lua doesn’t accept multibyte chars outside of strings, hence these are also errors.
+            encoder.text_token(getch, :error)
+          end
+          
+          # It may be that we’re scanning a full-blown subexpression of a table
+          # (tables can contain full expressions in parts).
+          # If this is the case, return to :map scanning state.
+          state = :map if state == :initial && @brace_depth >= 1
+        
+        when :function_expected
+          if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
+            encoder.text_token(match, :operator)
+            state = :initial
+          elsif match = scan(/[a-zA-Z_] (?:[a-zA-Z0-9_\.] (?!\.\d))* [\.\:]/x) # function tbl.subtbl.foo() | function tbl:foo() # Colon only allowed as last separator
+            encoder.text_token(match, :ident)
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # function foo()
+            encoder.text_token(match, :function)
+            state = :initial
+          elsif match = scan(/\s+/) # Between the `function' keyword and the ident may be any amount of whitespace
+            encoder.text_token(match, :space)
+          else
+            encoder.text_token(getch, :error)
+            state = :initial
+          end
+        
+        when :goto_label_expected
+          if match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
+            encoder.text_token(match, :label)
+            state = :initial
+          elsif match = scan(/\s+/) # Between the `goto' keyword and the label may be any amount of whitespace
+            encoder.text_token(match, :space)
+          else
+            encoder.text_token(getch, :error)
+          end
+        
+        when :local_var_expected
+          if match = scan(/function/) # local function ...
+            encoder.text_token(match, :keyword)
+            state = :function_expected
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
+            encoder.text_token(match, :local_variable)
+          elsif match = scan(/,/)
+            encoder.text_token(match, :operator)
+          elsif match = scan(/\=/)
+            encoder.text_token(match, :operator)
+            # After encountering the equal sign, arbitrary expressions are
+            # allowed again, so just return to the main state for further
+            # parsing.
+            state = :initial
+          elsif match = scan(/\n/)
+            encoder.text_token(match, :space)
+            state = :initial
+          elsif match = scan(/\s+/)
+            encoder.text_token(match, :space)
+          else
+            encoder.text_token(getch, :error)
+          end
+        
+        when :long_comment
+          if match = scan(/.*?(?=\]={#@num_equals}\])/m)
+            encoder.text_token(match, :content)
+            
+            delim = scan(/\]={#@num_equals}\]/)
+            encoder.text_token(delim, :delimiter)
+          else # No terminator found till EOF
+            encoder.text_token(rest, :error)
+            terminate
+          end
+          encoder.end_group(:comment)
+          state = :initial
+        
+        when :long_string
+          if match = scan(/.*?(?=\]={#@num_equals}\])/m) # Long strings do not interpret any escape sequences
+            encoder.text_token(match, :content)
+            
+            delim = scan(/\]={#@num_equals}\]/)
+            encoder.text_token(delim, :delimiter)
+          else # No terminator found till EOF
+            encoder.text_token(rest, :error)
+            terminate
+          end
+          encoder.end_group(:string)
+          state = :initial
+        
+        when :string
+          if match = scan(/[^\\#@start_delim\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
+            encoder.text_token(match, :content)
+          elsif match = scan(/\\(?:['"abfnrtv\\]|z\s*|x\h\h|\d{1,3}|\n)/m)
+            encoder.text_token(match, :char)
+          elsif match = scan(Regexp.compile(@start_delim))
+            encoder.text_token(match, :delimiter)
+            encoder.end_group(:string)
+            state = :initial
+          elsif match = scan(/\n/) # Lua forbids unescaped newlines in normal non-long strings
+            encoder.text_token("\\n\n", :error) # Visually appealing error indicator--otherwise users may wonder whether the highlighter cannot highlight multine strings
+            encoder.end_group(:string)
+            state = :initial
+          else
+            encoder.text_token(getch, :error)
+          end
+        
+        when :map
+          if match = scan(/[,;]/)
+            encoder.text_token(match, :operator)
+          elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
+            encoder.text_token(match, :key)
+            encoder.text_token(scan(/\s+/), :space) if check(/\s+/)
+            encoder.text_token(scan(/\=/), :operator)
+            state = :initial
+          elsif match = scan(/\s+/m)
+            encoder.text_token(match, :space)
+          else
+            # Note this clause doesn’t advance the scan pointer, it’s a kind of
+            # "retry with other options" (the :initial state then of course
+            # advances the pointer).
+            state = :initial
+          end
+        else
+          raise
+        end
+        
       end
-
-      @encoder.text_token(match, kind)
-
-    elsif match = scan(/\{/) # Opening table brace {
-      @encoder.begin_group(:map)
-      @encoder.text_token(match, @brace_depth >= 1 ? :inline_delimiter : :delimiter)
-      @brace_depth += 1
-      @state        = :map
-
-    elsif match = scan(/\}/) # Closing table brace }
-      if @brace_depth == 1
-        @brace_depth = 0
-        @encoder.text_token(match, :delimiter)
-      elsif @brace_depth == 0 # Mismatched brace
-        @encoder.text_token(match, :error)
-      else
-        @brace_depth -= 1
-        @encoder.text_token(match, :inline_delimiter)
-        @state = :map
+      
+      if options[:keep_state]
+        @state = state
       end
-      @encoder.end_group(:map)
-
-    elsif match = scan(/["']/) # String delimiters " and '
-      @encoder.begin_group(:string)
-      @encoder.text_token(match, :delimiter)
-      @start_delim = match
-      @state       = :string
-
-                      # ↓Prefix                hex number ←|→ decimal number
-    elsif match = scan(/-? (?:0x\h* \. \h+ (?:p[+\-]?\d+)? | \d*\.\d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
-      @encoder.text_token(match, :float)
-
-                      # ↓Prefix         hex number ←|→ decimal number
-    elsif match = scan(/-? (?:0x\h+ (?:p[+\-]?\d+)? | \d+ (?:e[+\-]?\d+)?)/ix) # hexadecimal constants have no E power, decimal ones no P power
-      @encoder.text_token(match, :integer)
-
-    elsif match = scan(/[\+\-\*\/%^\#=~<>\(\)\[\]:;,] | \.(?!\d)/x) # Operators
-      @encoder.text_token(match, :operator)
-
-    elsif match = scan(/\s+/) # Space
-      @encoder.text_token(match, :space)
-
-    else # Invalid stuff. Note that Lua doesn’t accept multibyte chars outside of strings, hence these are also errors.
-      @encoder.text_token(getch, :error)
-    end
-
-    # It may be that we’re scanning a full-blown subexpression of a table
-    # (tables can contain full expressions in parts).
-    # If this is the case, return to :map scanning state.
-    @state = :map if @state == :initial && @brace_depth >= 1
-
-  when :function_expected
-    if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
-      @encoder.text_token(match, :operator)
-      @state = :initial
-    elsif match = scan(/[a-zA-Z_] (?:[a-zA-Z0-9_\.] (?!\.\d))* [\.\:]/x) # function tbl.subtbl.foo() | function tbl:foo() # Colon only allowed as last separator
-      @encoder.text_token(match, :ident)
-    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/) # function foo()
-      @encoder.text_token(match, :function)
-      @state = :initial
-    elsif match = scan(/\s+/) # Between the `function' keyword and the ident may be any amount of whitespace
-      @encoder.text_token(match, :space)
-    else
-      @encoder.text_token(getch, :error)
-      @state = :initial
-    end
-
-  when :goto_label_expected
-    if match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
-      @encoder.text_token(match, :label)
-      @state = :initial
-    elsif match = scan(/\s+/) # Between the `goto' keyword and the label may be any amount of whitespace
-      @encoder.text_token(match, :space)
-    else
-      @encoder.text_token(getch, :error)
-    end
-
-  when :local_var_expected
-    if match = scan(/function/) # local function ...
-      @encoder.text_token(match, :keyword)
-      @state = :function_expected
-    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]*/)
-      @encoder.text_token(match, :local_variable)
-    elsif match = scan(/,/)
-      @encoder.text_token(match, :operator)
-    elsif match = scan(/\=/)
-      @encoder.text_token(match, :operator)
-      # After encountering the equal sign, arbitrary expressions are
-      # allowed again, so just return to the main state for further
-      # parsing.
-      @state = :initial
-    elsif match = scan(/\n/)
-      @encoder.text_token(match, :space)
-      @state = :initial
-    elsif match = scan(/\s+/)
-      @encoder.text_token(match, :space)
-    else
-      @encoder.text_token(getch, :error)
-    end
-
-  when :long_comment
-    if match = scan(/.*?(?=\]={#@num_equals}\])/m)
-      @encoder.text_token(match, :content)
-
-      delim = scan(/\]={#@num_equals}\]/)
-      @encoder.text_token(delim, :delimiter)
-    else # No terminator found till EOF
-      @encoder.text_token(rest, :error)
-      terminate
-    end
-    @encoder.end_group(:comment)
-    @state = :initial
-
-  when :long_string
-    if match = scan(/.*?(?=\]={#@num_equals}\])/m) # Long strings do not interpret any escape sequences
-      @encoder.text_token(match, :content)
-
-      delim = scan(/\]={#@num_equals}\]/)
-      @encoder.text_token(delim, :delimiter)
-    else # No terminator found till EOF
-      @encoder.text_token(rest, :error)
-      terminate
-    end
-    @encoder.end_group(:string)
-    @state = :initial
-
-  when :string
-    if match = scan(/[^\\#@start_delim\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
-      @encoder.text_token(match, :content)
-    elsif match = scan(/\\(?:['"abfnrtv\\]|z\s*|x\h\h|\d{1,3}|\n)/m)
-      @encoder.text_token(match, :char)
-    elsif match = scan(Regexp.compile(@start_delim))
-      @encoder.text_token(match, :delimiter)
-      @encoder.end_group(:string)
-      @state = :initial
-    elsif match = scan(/\n/) # Lua forbids unescaped newlines in normal non-long strings
-      @encoder.text_token("\\n\n", :error) # Visually appealing error indicator--otherwise users may wonder whether the highlighter cannot highlight multine strings
-      @encoder.end_group(:string)
-      @state = :initial
-    else
-      @encoder.text_token(getch, :error)
-    end
-
-  when :map
-    if match = scan(/[,;]/)
-      @encoder.text_token(match, :operator)
-    elsif match = scan(/[a-zA-Z_][a-zA-Z0-9_]* (?=\s*=)/x)
-      @encoder.text_token(match, :key)
-      @encoder.text_token(scan(/\s+/), :space) if check(/\s+/)
-      @encoder.text_token(scan(/\=/), :operator)
-      @state = :initial
-    elsif match = scan(/\s+/m)
-      @encoder.text_token(match, :space)
-    else
-      # Note this clause doesn’t advance the scan pointer, it’s a kind of
-      # "retry with other options" (the :initial state then of course
-      # advances the pointer).
-      @state = :initial
+      
+      encoder
     end
-  else
-    raise
+    
   end
-
-    end
-
-    @encoder
-  end
-
+  
+end
 end
-- 
cgit v1.2.1


From 90c401c9001e0a670360a55d1189e9f814ae7592 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 01:17:49 +0200
Subject: some more code cleanups before merge

---
 lib/coderay/scanners/lua.rb | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index 3bee275..25bebbe 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -8,17 +8,17 @@ module Scanners
   # The language’s complete syntax is defined in
   # {the Lua manual}[http://www.lua.org/manual/5.2/manual.html],
   # which is what this scanner tries to conform to.
-  class CodeRay::Scanners::Lua < CodeRay::Scanners::Scanner
+  class Lua < Scanner
     
     register_for :lua
-    file_extension "lua"
-    title "Lua"
+    file_extension 'lua'
+    title 'Lua'
     
     # Keywords used in Lua.
     KEYWORDS = %w[and break do else elseif end
-    for function goto if in
-    local not or repeat return
-    then until while
+      for function goto if in
+      local not or repeat return
+      then until while
     ]
     
     # Constants set by the Lua core.
@@ -36,10 +36,10 @@ module Scanners
     # highlighted directly accordingly, without the need for specific
     # identifiers to be listed here.
     PREDEFINED_EXPRESSIONS = %w[
-    assert collectgarbage dofile error getmetatable
-    ipairs load loadfile next pairs pcall print
-    rawequal rawget rawlen rawset select setmetatable
-    tonumber tostring type xpcall
+      assert collectgarbage dofile error getmetatable
+      ipairs load loadfile next pairs pcall print
+      rawequal rawget rawlen rawset select setmetatable
+      tonumber tostring type xpcall
     ]
     
     # Automatic token kind selection for normal words.
@@ -52,7 +52,7 @@ module Scanners
     
     # Scanner initialization.
     def setup
-      @state       = :initial
+      @state = :initial
       @brace_depth = 0
     end
     
-- 
cgit v1.2.1


From fa9848b6dbd95a4a97a3e63cb99ad2d4c26516df Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 01:37:06 +0200
Subject: avoid empty tokens in CSS

---
 lib/coderay/scanners/css.rb  | 2 +-
 lib/coderay/scanners/sass.rb | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/css.rb b/lib/coderay/scanners/css.rb
index 732f9c5..6c52c8a 100644
--- a/lib/coderay/scanners/css.rb
+++ b/lib/coderay/scanners/css.rb
@@ -148,7 +148,7 @@ module Scanners
             encoder.text_token match[start.size..-2], :content
             encoder.text_token ')', :delimiter
           else
-            encoder.text_token match[start.size..-1], :content
+            encoder.text_token match[start.size..-1], :content if start.size < match.size
           end
           encoder.end_group :function
           
diff --git a/lib/coderay/scanners/sass.rb b/lib/coderay/scanners/sass.rb
index 167051d..65d40b0 100644
--- a/lib/coderay/scanners/sass.rb
+++ b/lib/coderay/scanners/sass.rb
@@ -176,7 +176,7 @@ module Scanners
             encoder.text_token match[start.size..-2], :content
             encoder.text_token ')', :delimiter
           else
-            encoder.text_token match[start.size..-1], :content
+            encoder.text_token match[start.size..-1], :content if start.size < match.size
           end
           encoder.end_group :function
           
-- 
cgit v1.2.1


From bedd4e4fb5a18270a742e71b65f88fb8e3182050 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 01:40:56 +0200
Subject: avoid empty tokens in Raydebug

---
 lib/coderay/scanners/raydebug.rb | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/raydebug.rb b/lib/coderay/scanners/raydebug.rb
index 7a21354..d39d962 100644
--- a/lib/coderay/scanners/raydebug.rb
+++ b/lib/coderay/scanners/raydebug.rb
@@ -1,11 +1,11 @@
 module CodeRay
 module Scanners
-
+  
   # = Debug Scanner
   # 
   # Parses the output of the Encoders::Debug encoder.
   class Raydebug < Scanner
-
+    
     register_for :raydebug
     file_extension 'raydebug'
     title 'CodeRay Token Dump'
@@ -13,11 +13,11 @@ module Scanners
   protected
     
     def scan_tokens encoder, options
-
+      
       opened_tokens = []
-
+      
       until eos?
-
+        
         if match = scan(/\s+/)
           encoder.text_token match, :space
           
@@ -26,7 +26,7 @@ module Scanners
           encoder.text_token kind, :class
           encoder.text_token '(', :operator
           match = self[2]
-          encoder.text_token match, kind.to_sym
+          encoder.text_token match, kind.to_sym unless match.empty?
           encoder.text_token match, :operator if match = scan(/\)/)
           
         elsif match = scan(/ (\w+) ([<\[]) /x)
@@ -59,8 +59,8 @@ module Scanners
       
       encoder
     end
-
+    
   end
-
+  
 end
 end
-- 
cgit v1.2.1


From 39c074f171eeca1c91aa89757a3f3a12fc78323b Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 01:42:32 +0200
Subject: avoid empty tokens in YAML

---
 lib/coderay/scanners/yaml.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/yaml.rb b/lib/coderay/scanners/yaml.rb
index 96f4e93..358a3f1 100644
--- a/lib/coderay/scanners/yaml.rb
+++ b/lib/coderay/scanners/yaml.rb
@@ -47,7 +47,7 @@ module Scanners
           when !check(/(?:"[^"]*")(?=: |:$)/) && match = scan(/"/)
             encoder.begin_group :string
             encoder.text_token match, :delimiter
-            encoder.text_token match, :content if match = scan(/ [^"\\]* (?: \\. [^"\\]* )* /mx)
+            encoder.text_token match, :content if (match = scan(/ [^"\\]* (?: \\. [^"\\]* )* /mx)) && !match.empty?
             encoder.text_token match, :delimiter if match = scan(/"/)
             encoder.end_group :string
             next
-- 
cgit v1.2.1


From b059a63e7ff3cd7c26dd5664bf048aa42338fbe1 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 05:54:56 +0200
Subject: close open tokens in Groovy scanner

---
 lib/coderay/scanners/groovy.rb | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/groovy.rb b/lib/coderay/scanners/groovy.rb
index cf55daf..d04a535 100644
--- a/lib/coderay/scanners/groovy.rb
+++ b/lib/coderay/scanners/groovy.rb
@@ -36,9 +36,12 @@ module Scanners
     
   protected
     
+    def setup
+      @state = :initial
+    end
+    
     def scan_tokens encoder, options
-      
-      state = :initial
+      state = options[:state] || @state
       inline_block_stack = []
       inline_block_paren_depth = nil
       string_delimiter = nil
@@ -246,6 +249,16 @@ module Scanners
         encoder.end_group state
       end
       
+      if options[:keep_state]
+        @state = state
+      end
+      
+      until inline_block_stack.empty?
+        state, = *inline_block_stack.pop
+        encoder.end_group :inline
+        encoder.end_group state
+      end
+      
       encoder
     end
     
-- 
cgit v1.2.1


From 3c3060acaf2422c23784539b270e365decc9cb2e Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 05:55:23 +0200
Subject: close open tokens in PHP scanner

---
 lib/coderay/scanners/php.rb | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/php.rb b/lib/coderay/scanners/php.rb
index 6c68834..40037f9 100644
--- a/lib/coderay/scanners/php.rb
+++ b/lib/coderay/scanners/php.rb
@@ -500,6 +500,10 @@ module Scanners
         
       end
       
+      while state = states.pop
+        encoder.end_group :string if [:sqstring, :dqstring].include? state
+      end
+      
       encoder
     end
     
-- 
cgit v1.2.1


From 7f45168efd1abe679b261a7a91f3641984091d12 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:06:16 +0200
Subject: remove instance variables from Lua scanner

---
 lib/coderay/scanners/lua.rb | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index 25bebbe..185c133 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -59,13 +59,15 @@ module Scanners
     # CodeRay entry hook. Starts parsing.
     def scan_tokens(encoder, options)
       state = options[:state] || @state
+      brace_depth = @brace_depth
+      num_equals = nil
       
       until eos?
         case state
         
         when :initial
           if match = scan(/\-\-\[\=*\[/)   #--[[ long (possibly multiline) comment ]]
-            @num_equals = match.count("=") # Number must match for comment end
+            num_equals = match.count("=") # Number must match for comment end
             encoder.begin_group(:comment)
             encoder.text_token(match, :delimiter)
             state = :long_comment
@@ -74,7 +76,7 @@ module Scanners
             encoder.text_token(match, :comment)
           
           elsif match = scan(/\[=*\[/)     # [[ long (possibly multiline) string ]]
-            @num_equals = match.count("=") # Number must match for comment end
+            num_equals = match.count("=") # Number must match for comment end
             encoder.begin_group(:string)
             encoder.text_token(match, :delimiter)
             state = :long_string
@@ -101,19 +103,19 @@ module Scanners
           
           elsif match = scan(/\{/) # Opening table brace {
             encoder.begin_group(:map)
-            encoder.text_token(match, @brace_depth >= 1 ? :inline_delimiter : :delimiter)
-            @brace_depth += 1
+            encoder.text_token(match, brace_depth >= 1 ? :inline_delimiter : :delimiter)
+            brace_depth += 1
             state        = :map
           
           elsif match = scan(/\}/) # Closing table brace }
-            if @brace_depth == 1
-              @brace_depth = 0
+            if brace_depth == 1
+              brace_depth = 0
               encoder.text_token(match, :delimiter)
               encoder.end_group(:map)
-            elsif @brace_depth == 0 # Mismatched brace
+            elsif brace_depth == 0 # Mismatched brace
               encoder.text_token(match, :error)
             else
-              @brace_depth -= 1
+              brace_depth -= 1
               encoder.text_token(match, :inline_delimiter)
               encoder.end_group(:map)
               state = :map
@@ -122,7 +124,7 @@ module Scanners
           elsif match = scan(/["']/) # String delimiters " and '
             encoder.begin_group(:string)
             encoder.text_token(match, :delimiter)
-            @start_delim = match
+            start_delim = match
             state       = :string
           
                             # ↓Prefix                hex number ←|→ decimal number
@@ -146,7 +148,7 @@ module Scanners
           # It may be that we’re scanning a full-blown subexpression of a table
           # (tables can contain full expressions in parts).
           # If this is the case, return to :map scanning state.
-          state = :map if state == :initial && @brace_depth >= 1
+          state = :map if state == :initial && brace_depth >= 1
         
         when :function_expected
           if match = scan(/\(.*?\)/m) # x = function() # "Anonymous" function without explicit name
@@ -198,10 +200,10 @@ module Scanners
           end
         
         when :long_comment
-          if match = scan(/.*?(?=\]={#@num_equals}\])/m)
+          if match = scan(/.*?(?=\]={#{num_equals}}\])/m)
             encoder.text_token(match, :content)
             
-            delim = scan(/\]={#@num_equals}\]/)
+            delim = scan(/\]={#{num_equals}}\]/)
             encoder.text_token(delim, :delimiter)
           else # No terminator found till EOF
             encoder.text_token(rest, :error)
@@ -211,10 +213,10 @@ module Scanners
           state = :initial
         
         when :long_string
-          if match = scan(/.*?(?=\]={#@num_equals}\])/m) # Long strings do not interpret any escape sequences
+          if match = scan(/.*?(?=\]={#{num_equals}}\])/m) # Long strings do not interpret any escape sequences
             encoder.text_token(match, :content)
             
-            delim = scan(/\]={#@num_equals}\]/)
+            delim = scan(/\]={#{num_equals}}\]/)
             encoder.text_token(delim, :delimiter)
           else # No terminator found till EOF
             encoder.text_token(rest, :error)
@@ -224,11 +226,11 @@ module Scanners
           state = :initial
         
         when :string
-          if match = scan(/[^\\#@start_delim\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
+          if match = scan(/[^\\#{start_delim}\n]+/) # Everything except \ and the start delimiter character is string content (newlines are only allowed if preceeded by \ or \z)
             encoder.text_token(match, :content)
           elsif match = scan(/\\(?:['"abfnrtv\\]|z\s*|x\h\h|\d{1,3}|\n)/m)
             encoder.text_token(match, :char)
-          elsif match = scan(Regexp.compile(@start_delim))
+          elsif match = scan(Regexp.compile(start_delim))
             encoder.text_token(match, :delimiter)
             encoder.end_group(:string)
             state = :initial
-- 
cgit v1.2.1


From 45bb0c576b67b7a3c0dead02078b3a16b5583154 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:06:52 +0200
Subject: close open token groups in Lua scanner

---
 lib/coderay/scanners/lua.rb | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb
index 185c133..fb1e45a 100644
--- a/lib/coderay/scanners/lua.rb
+++ b/lib/coderay/scanners/lua.rb
@@ -268,6 +268,9 @@ module Scanners
         @state = state
       end
       
+      encoder.end_group :string if [:string].include? state
+      brace_depth.times { encoder.end_group :map }
+      
       encoder
     end
     
-- 
cgit v1.2.1


From dc6071129cdc1bcd15129147bbc4d92ba870f007 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:13:32 +0200
Subject: close open token groups in Sass scanner

---
 lib/coderay/scanners/sass.rb | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/sass.rb b/lib/coderay/scanners/sass.rb
index 65d40b0..0ba383f 100644
--- a/lib/coderay/scanners/sass.rb
+++ b/lib/coderay/scanners/sass.rb
@@ -218,6 +218,14 @@ module Scanners
         @state = states
       end
       
+      while state = states.pop
+        if state == :sass_inline
+          encoder.end_group :inline
+        elsif state == :string
+          encoder.end_group :string
+        end
+      end
+      
       encoder
     end
     
-- 
cgit v1.2.1


From 4327fcbe932ac913f7eb8e92497f97913fb398c5 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:15:55 +0200
Subject: fix Sass regexp modifier

---
 lib/coderay/scanners/sass.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/sass.rb b/lib/coderay/scanners/sass.rb
index 0ba383f..e20bebe 100644
--- a/lib/coderay/scanners/sass.rb
+++ b/lib/coderay/scanners/sass.rb
@@ -195,7 +195,7 @@ module Scanners
         elsif match = scan(/(?:rgb|hsl)a?\([^()\n]*\)?/)
           encoder.text_token match, :color
           
-        elsif match = scan(/@else if\b|#{RE::AtKeyword}/)
+        elsif match = scan(/@else if\b|#{RE::AtKeyword}/o)
           encoder.text_token match, :directive
           value_expected = true
           
-- 
cgit v1.2.1


From 755904f7046d8a8d6208fe8367aaa3b9a19ecd65 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:30:24 +0200
Subject: avoid empty tokens in Diff scanner

---
 lib/coderay/scanners/diff.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/diff.rb b/lib/coderay/scanners/diff.rb
index af0f755..fd1aed6 100644
--- a/lib/coderay/scanners/diff.rb
+++ b/lib/coderay/scanners/diff.rb
@@ -69,7 +69,7 @@ module Scanners
             state = :added
           elsif match = scan(/\\ .*/)
             encoder.text_token match, :comment
-          elsif match = scan(/@@(?>[^@\n]*)@@/)
+          elsif match = scan(/@@(?>[^@\n]+)@@/)
             content_scanner.state = :initial unless match?(/\n\+/)
             content_scanner_entry_state = nil
             if check(/\n|$/)
-- 
cgit v1.2.1


From e1d5e111d968639fa03a6074cf90535ecc90d0dd Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:30:44 +0200
Subject: close correct token groups in Groovy scanner

---
 lib/coderay/scanners/groovy.rb | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/groovy.rb b/lib/coderay/scanners/groovy.rb
index d04a535..c64454f 100644
--- a/lib/coderay/scanners/groovy.rb
+++ b/lib/coderay/scanners/groovy.rb
@@ -226,7 +226,7 @@ module Scanners
             encoder.text_token match, :content  # TODO: Shouldn't this be :error?
             
           elsif match = scan(/ \\ | \n /x)
-            encoder.end_group state
+            encoder.end_group state == :regexp ? :regexp : :string
             encoder.text_token match, :error
             after_def = value_expected = false
             state = :initial
@@ -246,7 +246,7 @@ module Scanners
       end
       
       if [:multiline_string, :string, :regexp].include? state
-        encoder.end_group state
+        encoder.end_group state == :regexp ? :regexp : :string
       end
       
       if options[:keep_state]
@@ -256,7 +256,7 @@ module Scanners
       until inline_block_stack.empty?
         state, = *inline_block_stack.pop
         encoder.end_group :inline
-        encoder.end_group state
+        encoder.end_group state == :regexp ? :regexp : :string
       end
       
       encoder
-- 
cgit v1.2.1


From 603ff7d0b14521cfd0408aa68e2e1cb6ea9086bc Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:36:46 +0200
Subject: avoid empty tokens in YAML scanner

---
 lib/coderay/scanners/yaml.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/yaml.rb b/lib/coderay/scanners/yaml.rb
index 358a3f1..32c8e2c 100644
--- a/lib/coderay/scanners/yaml.rb
+++ b/lib/coderay/scanners/yaml.rb
@@ -84,7 +84,7 @@ module Scanners
           when match = scan(/(?:"[^"\n]*"|'[^'\n]*')(?= *:(?: |$))/)
             encoder.begin_group :key
             encoder.text_token match[0,1], :delimiter
-            encoder.text_token match[1..-2], :content
+            encoder.text_token match[1..-2], :content if match.size > 2
             encoder.text_token match[-1,1], :delimiter
             encoder.end_group :key
             key_indent = column(pos - match.size) - 1
-- 
cgit v1.2.1


From 253a616924000cc5d522a2d4b8030f5693c98e43 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 06:39:30 +0200
Subject: close open string token groups in SQL scanner

---
 lib/coderay/scanners/sql.rb | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/sql.rb b/lib/coderay/scanners/sql.rb
index b757278..93aeaf3 100644
--- a/lib/coderay/scanners/sql.rb
+++ b/lib/coderay/scanners/sql.rb
@@ -1,8 +1,9 @@
-module CodeRay module Scanners
+module CodeRay
+module Scanners
   
   # by Josh Goebel
   class SQL < Scanner
-
+    
     register_for :sql
     
     KEYWORDS = %w(
@@ -149,6 +150,7 @@ module CodeRay module Scanners
               string_content = ''
             end
             encoder.text_token match, :error unless match.empty?
+            encoder.end_group :string
             state = :initial
           else
             raise "else case \" reached; %p not handled." % peek(1), encoder
@@ -171,4 +173,5 @@ module CodeRay module Scanners
     
   end
   
-end end
\ No newline at end of file
+end
+end
-- 
cgit v1.2.1


From c8751fbc09d4a8f43b0b037e3a7dc7ddbfbcacb1 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 13:15:10 +0200
Subject: fix unclosed token group in Ruby scanner

---
 lib/coderay/scanners/ruby.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/ruby.rb b/lib/coderay/scanners/ruby.rb
index c282f31..80165ca 100644
--- a/lib/coderay/scanners/ruby.rb
+++ b/lib/coderay/scanners/ruby.rb
@@ -269,7 +269,7 @@ module Scanners
             end
             
             if last_state
-              state = last_state
+              state = last_state unless state.is_a?(StringState)  # otherwise, a simple 'def"' results in unclosed tokens
               last_state = nil
             end
             
-- 
cgit v1.2.1


From c34ad739bc7342aa40830945a5e19e90e9814e04 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 13:27:43 +0200
Subject: fix token nesting in PHP scanner

---
 lib/coderay/scanners/php.rb | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/php.rb b/lib/coderay/scanners/php.rb
index 40037f9..7a8d75d 100644
--- a/lib/coderay/scanners/php.rb
+++ b/lib/coderay/scanners/php.rb
@@ -265,7 +265,7 @@ module Scanners
             @html_scanner.tokenize match unless match.empty?
           end
         
-        when :php
+        when :php, :php_inline
           if match = scan(/\s+/)
             encoder.text_token match, :space
           
@@ -332,7 +332,7 @@ module Scanners
             if states.size == 1
               encoder.text_token match, :error
             else
-              states.pop
+              state = states.pop
               if states.last.is_a?(::Array)
                 delimiter = states.last[1]
                 states[-1] = states.last[0]
@@ -340,6 +340,7 @@ module Scanners
                 encoder.end_group :inline
               else
                 encoder.text_token match, :operator
+                encoder.end_group :inline if state == :php_inline
                 label_expected = true
               end
             end
@@ -350,7 +351,14 @@ module Scanners
           
           elsif match = scan(RE::PHP_END)
             encoder.text_token match, :inline_delimiter
-            states = [:initial]
+            while state = states.pop
+              encoder.end_group :string if [:sqstring, :dqstring].include? state
+              if state.is_a? Array
+                encoder.end_group :inline
+                encoder.end_group :string if [:sqstring, :dqstring].include? state.first
+              end
+            end
+            states << :initial
           
           elsif match = scan(/<<<(?:(#{RE::IDENTIFIER})|"(#{RE::IDENTIFIER})"|'(#{RE::IDENTIFIER})')/o)
             encoder.begin_group :string
@@ -400,6 +408,7 @@ module Scanners
           elsif match = scan(/\\/)
             encoder.text_token match, :error
           else
+            encoder.end_group :string
             states.pop
           end
         
@@ -459,7 +468,7 @@ module Scanners
               encoder.begin_group :inline
               states[-1] = [states.last, delimiter]
               delimiter = nil
-              states.push :php
+              states.push :php_inline
               encoder.text_token match, :delimiter
             else
               encoder.text_token match, :content
@@ -469,6 +478,7 @@ module Scanners
           elsif match = scan(/\$/)
             encoder.text_token match, :content
           else
+            encoder.end_group :string
             states.pop
           end
         
@@ -502,6 +512,10 @@ module Scanners
       
       while state = states.pop
         encoder.end_group :string if [:sqstring, :dqstring].include? state
+        if state.is_a? Array
+          encoder.end_group :inline
+          encoder.end_group :string if [:sqstring, :dqstring].include? state.first
+        end
       end
       
       encoder
-- 
cgit v1.2.1


From 14f3a4f28341237503a51bfa0764c922bb02bdfa Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 14:13:15 +0200
Subject: tweak HTML CDATA token kinds

---
 lib/coderay/scanners/html.rb | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index fcf249a..530ce44 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -1,13 +1,13 @@
 module CodeRay
 module Scanners
-
+  
   # HTML Scanner
   # 
   # Alias: +xhtml+
   # 
   # See also: Scanners::XML
   class HTML < Scanner
-
+    
     register_for :html
     
     KINDS_NOT_LOC = [
@@ -100,15 +100,13 @@ module Scanners
           
           when :initial
             if match = scan(/<!\[CDATA\[/)
-              encoder.begin_group :string
-              encoder.text_token match, :delimiter
+              encoder.text_token match, :inline_delimiter
               if match = scan(/.*?\]\]>/m)
-                encoder.text_token match[0..-4], :content
-                encoder.text_token ']]>', :delimiter
-              else
-                encoder.text_token scan(/.*/m), :error
+                encoder.text_token match[0..-4], :plain
+                encoder.text_token ']]>', :inline_delimiter
+              elsif match = scan(/.+/)
+                encoder.text_token match, :error
               end
-              encoder.end_group :string
             elsif match = scan(/<!--(?:.*?-->|.*)/m)
               encoder.text_token match, :comment
             elsif match = scan(/<!(\w+)(?:.*?>|.*)|\]>/m)
-- 
cgit v1.2.1


From 5b0dc0f35090949d7512a85dadc8cf2871b91aac Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 14:15:01 +0200
Subject: scan_css in HTML scanner (tags)

---
 lib/coderay/scanners/html.rb | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index 3ba3b79..06728e4 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -75,9 +75,14 @@ module Scanners
     def scan_java_script encoder, code
       if code && !code.empty?
         @java_script_scanner ||= Scanners::JavaScript.new '', :keep_tokens => true
-        # encoder.begin_group :inline
         @java_script_scanner.tokenize code, :tokens => encoder
-        # encoder.end_group :inline
+      end
+    end
+    
+    def scan_css encoder, code
+      if code && !code.empty?
+        @css_scanner ||= Scanners::CSS.new '', :keep_tokens => true
+        @css_scanner.tokenize code, :tokens => encoder
       end
     end
     
@@ -110,7 +115,7 @@ module Scanners
             elsif match = scan(/<\/[-\w.:]*>?/m)
               in_tag = nil
               encoder.text_token match, :tag
-            elsif match = scan(/<(?:(script)|[-\w.:]+)(>)?/m)
+            elsif match = scan(/<(?:(script|style)|[-\w.:]+)(>)?/m)
               encoder.text_token match, :tag
               in_tag = self[1]
               if self[2]
@@ -206,19 +211,23 @@ module Scanners
             
           when :in_special_tag
             case in_tag
-            when 'script'
+            when 'script', 'style'
               encoder.text_token match, :space if match = scan(/[ \t]*\n/)
               if scan(/(\s*<!--)(?:(.*?)(-->)|(.*))/m)
                 code = self[2] || self[4]
                 closing = self[3]
                 encoder.text_token self[1], :comment
               else
-                code = scan_until(/(?=(?:\n\s*)?<\/script>)|\z/)
+                code = scan_until(/(?=(?:\n\s*)?<\/#{in_tag}>)|\z/)
                 closing = false
               end
               unless code.empty?
                 encoder.begin_group :inline
-                scan_java_script encoder, code
+                if in_tag == 'script'
+                  scan_java_script encoder, code
+                else
+                  scan_css encoder, code
+                end
                 encoder.end_group :inline
               end
               encoder.text_token closing, :comment if closing
-- 
cgit v1.2.1


From 7ada74c8f0f77815393e887db83e1d2c36ce7235 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 14:32:14 +0200
Subject: scan_css in HTML scanner (arguments), change token kind from :inline
 to :string

---
 lib/coderay/scanners/html.rb | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index 06728e4..f1dfba0 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -33,7 +33,8 @@ module Scanners
     )
     
     IN_ATTRIBUTE = WordList::CaseIgnoring.new(nil).
-      add(EVENT_ATTRIBUTES, :script)
+      add(EVENT_ATTRIBUTES, :script).
+      add(['style'], :style)
     
     ATTR_NAME = /[\w.:-]+/  # :nodoc:
     TAG_END = /\/?>/  # :nodoc:
@@ -79,10 +80,10 @@ module Scanners
       end
     end
     
-    def scan_css encoder, code
+    def scan_css encoder, code, state = [:initial]
       if code && !code.empty?
         @css_scanner ||= Scanners::CSS.new '', :keep_tokens => true
-        @css_scanner.tokenize code, :tokens => encoder
+        @css_scanner.tokenize code, :tokens => encoder, :state => state
       end
     end
     
@@ -166,17 +167,21 @@ module Scanners
               encoder.text_token match, :attribute_value
               state = :attribute
             elsif match = scan(/["']/)
-              if in_attribute == :script
-                encoder.begin_group :inline
-                encoder.text_token match, :inline_delimiter
+              if in_attribute == :script || in_attribute == :style
+                encoder.begin_group :string
+                encoder.text_token match, :delimiter
                 if scan(/javascript:[ \t]*/)
                   encoder.text_token matched, :comment
                 end
                 code = scan_until(match == '"' ? /(?="|\z)/ : /(?='|\z)/)
-                scan_java_script encoder, code
+                if in_attribute == :script
+                  scan_java_script encoder, code
+                else
+                  scan_css encoder, code, [:block]
+                end
                 match = scan(/["']/)
-                encoder.text_token match, :inline_delimiter if match
-                encoder.end_group :inline
+                encoder.text_token match, :delimiter if match
+                encoder.end_group :string
                 state = :attribute
                 in_attribute = nil
               else
-- 
cgit v1.2.1


From 56f4163e99689912c3797e5d3b2b97244ce65782 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 14:33:22 +0200
Subject: fix another CSS empty token issue

---
 lib/coderay/scanners/css.rb | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/css.rb b/lib/coderay/scanners/css.rb
index 6c52c8a..9ed4618 100644
--- a/lib/coderay/scanners/css.rb
+++ b/lib/coderay/scanners/css.rb
@@ -145,10 +145,10 @@ module Scanners
           start = match[/^\w+\(/]
           encoder.text_token start, :delimiter
           if match[-1] == ?)
-            encoder.text_token match[start.size..-2], :content
+            encoder.text_token match[start.size..-2], :content if match.size > start.size + 1
             encoder.text_token ')', :delimiter
           else
-            encoder.text_token match[start.size..-1], :content if start.size < match.size
+            encoder.text_token match[start.size..-1], :content if match.size > start.size
           end
           encoder.end_group :function
           
-- 
cgit v1.2.1


From b89caf96d1cfc304c2114d8734ebe8b91337c799 Mon Sep 17 00:00:00 2001
From: Kornelius Kalnbach <murphy@rubychan.de>
Date: Sun, 23 Jun 2013 14:53:14 +0200
Subject: fix diff/json token nesting issue

---
 lib/coderay/scanners/json.rb | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'lib/coderay/scanners')

diff --git a/lib/coderay/scanners/json.rb b/lib/coderay/scanners/json.rb
index 3754a9b..b09970c 100644
--- a/lib/coderay/scanners/json.rb
+++ b/lib/coderay/scanners/json.rb
@@ -26,6 +26,10 @@ module Scanners
     def scan_tokens encoder, options
       state = options[:state] || @state
       
+      if [:string, :key].include? state
+        encoder.begin_group state
+      end
+      
       until eos?
         
         case state
-- 
cgit v1.2.1