diff options
Diffstat (limited to 'lib/coderay/scanners')
| -rw-r--r-- | lib/coderay/scanners/css.rb | 4 | ||||
| -rw-r--r-- | lib/coderay/scanners/debug.rb | 26 | ||||
| -rw-r--r-- | lib/coderay/scanners/diff.rb | 2 | ||||
| -rw-r--r-- | lib/coderay/scanners/go.rb | 208 | ||||
| -rw-r--r-- | lib/coderay/scanners/raydebug.rb | 31 | ||||
| -rw-r--r-- | lib/coderay/scanners/ruby.rb | 19 | ||||
| -rw-r--r-- | lib/coderay/scanners/ruby/patterns.rb | 7 | ||||
| -rw-r--r-- | lib/coderay/scanners/ruby/string_state.rb | 22 | ||||
| -rw-r--r-- | lib/coderay/scanners/sass.rb | 37 | ||||
| -rw-r--r-- | lib/coderay/scanners/sql.rb | 42 |
10 files changed, 316 insertions, 82 deletions
diff --git a/lib/coderay/scanners/css.rb b/lib/coderay/scanners/css.rb index 9ed4618..55d5239 100644 --- a/lib/coderay/scanners/css.rb +++ b/lib/coderay/scanners/css.rb @@ -25,7 +25,7 @@ module Scanners HexColor = /#(?:#{Hex}{6}|#{Hex}{3})/ - Num = /-?(?:[0-9]*\.[0-9]+|[0-9]+)/ + Num = /-?(?:[0-9]*\.[0-9]+|[0-9]+)n?/ Name = /#{NMChar}+/ Ident = /-?#{NMStart}#{NMChar}*/ AtKeyword = /@#{Ident}/ @@ -53,7 +53,7 @@ module Scanners end def scan_tokens encoder, options - states = Array(options[:state] || @state) + states = Array(options[:state] || @state).dup value_expected = @value_expected until eos? diff --git a/lib/coderay/scanners/debug.rb b/lib/coderay/scanners/debug.rb index 566bfa7..83ede9a 100644 --- a/lib/coderay/scanners/debug.rb +++ b/lib/coderay/scanners/debug.rb @@ -1,9 +1,11 @@ +require 'set' + module CodeRay module Scanners # = Debug Scanner # - # Interprets the output of the Encoders::Debug encoder. + # Interprets the output of the Encoders::Debug encoder (basically the inverse function). class Debug < Scanner register_for :debug @@ -11,6 +13,11 @@ module Scanners protected + def setup + super + @known_token_kinds = TokenKinds.keys.map(&:to_s).to_set + end + def scan_tokens encoder, options opened_tokens = [] @@ -21,16 +28,19 @@ module Scanners encoder.text_token match, :space elsif match = scan(/ (\w+) \( ( [^\)\\]* ( \\. [^\)\\]* )* ) \)? /x) - kind = self[1].to_sym - match = self[2].gsub(/\\(.)/m, '\1') - unless TokenKinds.has_key? kind - kind = :error - match = matched + if @known_token_kinds.include? self[1] + encoder.text_token self[2].gsub(/\\(.)/m, '\1'), self[1].to_sym + else + encoder.text_token matched, :unknown end - encoder.text_token match, kind elsif match = scan(/ (\w+) ([<\[]) /x) - kind = self[1].to_sym + if @known_token_kinds.include? self[1] + kind = self[1].to_sym + else + kind = :unknown + end + opened_tokens << kind case self[2] when '<' diff --git a/lib/coderay/scanners/diff.rb b/lib/coderay/scanners/diff.rb index fd1aed6..74a6c27 100644 --- a/lib/coderay/scanners/diff.rb +++ b/lib/coderay/scanners/diff.rb @@ -100,7 +100,7 @@ module Scanners next elsif match = scan(/-/) deleted_lines_count += 1 - if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\n\+)/) + if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && changed_lines_count <= 100_000 && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\n\+)/) deleted_lines = Array.new(changed_lines_count) { |i| skip(/\n\-/) if i > 0; scan(/.*/) } inserted_lines = Array.new(changed_lines_count) { |i| skip(/\n\+/) ; scan(/.*/) } diff --git a/lib/coderay/scanners/go.rb b/lib/coderay/scanners/go.rb new file mode 100644 index 0000000..99fdd63 --- /dev/null +++ b/lib/coderay/scanners/go.rb @@ -0,0 +1,208 @@ +module CodeRay +module Scanners + + class Go < Scanner + + register_for :go + file_extension 'go' + + # http://golang.org/ref/spec#Keywords + KEYWORDS = [ + 'break', 'default', 'func', 'interface', 'select', + 'case', 'defer', 'go', 'map', 'struct', + 'chan', 'else', 'goto', 'package', 'switch', + 'const', 'fallthrough', 'if', 'range', 'type', + 'continue', 'for', 'import', 'return', 'var', + ] # :nodoc: + + # http://golang.org/ref/spec#Types + PREDEFINED_TYPES = [ + 'bool', + 'uint8', 'uint16', 'uint32', 'uint64', + 'int8', 'int16', 'int32', 'int64', + 'float32', 'float64', + 'complex64', 'complex128', + 'byte', 'rune', 'string', 'error', + 'uint', 'int', 'uintptr', + ] # :nodoc: + + PREDEFINED_CONSTANTS = [ + 'nil', 'iota', + 'true', 'false', + ] # :nodoc: + + PREDEFINED_FUNCTIONS = %w[ + append cap close complex copy delete imag len + make new panic print println real recover + ] # :nodoc: + + IDENT_KIND = WordList.new(:ident). + add(KEYWORDS, :keyword). + add(PREDEFINED_TYPES, :predefined_type). + add(PREDEFINED_CONSTANTS, :predefined_constant). + add(PREDEFINED_FUNCTIONS, :predefined) # :nodoc: + + ESCAPE = / [rbfntv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x # :nodoc: + UNICODE_ESCAPE = / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x # :nodoc: + + protected + + def scan_tokens encoder, options + + state = :initial + label_expected = true + case_expected = false + label_expected_before_preproc_line = nil + in_preproc_line = false + + until eos? + + case state + + when :initial + + if match = scan(/ \s+ | \\\n /x) + if in_preproc_line && match != "\\\n" && match.index(?\n) + in_preproc_line = false + case_expected = false + label_expected = label_expected_before_preproc_line + end + encoder.text_token match, :space + + elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx) + encoder.text_token match, :comment + + elsif match = scan(/ <?- (?![\d.]) | [+*=<>?:;,!&^|()\[\]{}~%]+ | \/=? | \.(?!\d) /x) + if case_expected + label_expected = true if match == ':' + case_expected = false + end + encoder.text_token match, :operator + + elsif match = scan(/ [A-Za-z_][A-Za-z_0-9]* /x) + kind = IDENT_KIND[match] + if kind == :ident && label_expected && !in_preproc_line && scan(/:(?!:)/) + kind = :label + label_expected = false + match << matched + else + label_expected = false + if kind == :keyword + case match + when 'case', 'default' + case_expected = true + end + end + end + encoder.text_token match, kind + + elsif match = scan(/L?"/) + encoder.begin_group :string + if match[0] == ?L + encoder.text_token 'L', :modifier + match = '"' + end + encoder.text_token match, :delimiter + state = :string + + elsif match = scan(/ ` ([^`]+)? (`)? /x) + encoder.begin_group :shell + encoder.text_token '`', :delimiter + encoder.text_token self[1], :content if self[1] + encoder.text_token self[2], :delimiter if self[2] + encoder.end_group :shell + + elsif match = scan(/ \# \s* if \s* 0 /x) + match << scan_until(/ ^\# (?:elif|else|endif) .*? $ | \z /xm) unless eos? + encoder.text_token match, :comment + + elsif match = scan(/#[ \t]*(\w*)/) + encoder.text_token match, :preprocessor + in_preproc_line = true + label_expected_before_preproc_line = label_expected + state = :include_expected if self[1] == 'include' + + elsif match = scan(/ L?' (?: [^\'\n\\] | \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) )? '? /ox) + label_expected = false + encoder.text_token match, :char + + elsif match = scan(/\$/) + encoder.text_token match, :ident + + elsif match = scan(/-?\d*(\.\d*)?([eE][+-]?\d+)?i/) + label_expected = false + encoder.text_token match, :imaginary + + elsif match = scan(/-?0[xX][0-9A-Fa-f]+/) + label_expected = false + encoder.text_token match, :hex + + elsif match = scan(/-?(?:0[0-7]+)(?![89.eEfF])/) + label_expected = false + encoder.text_token match, :octal + + elsif match = scan(/-?(?:\d*\.\d+|\d+\.)(?:[eE][+-]?\d+)?|\d+[eE][+-]?\d+/) + label_expected = false + encoder.text_token match, :float + + elsif match = scan(/-?(?:\d+)(?![.eEfF])L?L?/) + label_expected = false + encoder.text_token match, :integer + + else + encoder.text_token getch, :error + + end + + when :string + if match = scan(/[^\\\n"]+/) + encoder.text_token match, :content + elsif match = scan(/"/) + encoder.text_token match, :delimiter + encoder.end_group :string + state = :initial + label_expected = false + elsif match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox) + encoder.text_token match, :char + elsif match = scan(/ \\ /x) + encoder.text_token match, :error + elsif match = scan(/$/) + encoder.end_group :string + state = :initial + label_expected = false + else + raise_inspect "else case \" reached; %p not handled." % peek(1), encoder + end + + when :include_expected + if match = scan(/<[^>\n]+>?|"[^"\n\\]*(?:\\.[^"\n\\]*)*"?/) + encoder.text_token match, :include + state = :initial + + elsif match = scan(/\s+/) + encoder.text_token match, :space + state = :initial if match.index ?\n + + else + state = :initial + + end + + else + raise_inspect 'Unknown state', encoder + + end + + end + + if state == :string + encoder.end_group :string + end + + encoder + end + + end + +end +end diff --git a/lib/coderay/scanners/raydebug.rb b/lib/coderay/scanners/raydebug.rb index d39d962..1effdc8 100644 --- a/lib/coderay/scanners/raydebug.rb +++ b/lib/coderay/scanners/raydebug.rb @@ -1,9 +1,11 @@ +require 'set' + module CodeRay module Scanners - # = Debug Scanner + # = Raydebug Scanner # - # Parses the output of the Encoders::Debug encoder. + # Highlights the output of the Encoders::Debug encoder. class Raydebug < Scanner register_for :raydebug @@ -12,6 +14,11 @@ module Scanners protected + def setup + super + @known_token_kinds = TokenKinds.keys.map(&:to_s).to_set + end + def scan_tokens encoder, options opened_tokens = [] @@ -26,20 +33,22 @@ module Scanners encoder.text_token kind, :class encoder.text_token '(', :operator match = self[2] - encoder.text_token match, kind.to_sym unless match.empty? + unless match.empty? + if @known_token_kinds.include? kind + encoder.text_token match, kind.to_sym + else + encoder.text_token match, :plain + end + end encoder.text_token match, :operator if match = scan(/\)/) elsif match = scan(/ (\w+) ([<\[]) /x) - kind = self[1] - case self[2] - when '<' - encoder.text_token kind, :class - when '[' - encoder.text_token kind, :class + encoder.text_token self[1], :class + if @known_token_kinds.include? self[1] + kind = self[1].to_sym else - raise 'CodeRay bug: This case should not be reached.' + kind = :unknown end - kind = kind.to_sym opened_tokens << kind encoder.begin_group kind encoder.text_token self[2], :operator diff --git a/lib/coderay/scanners/ruby.rb b/lib/coderay/scanners/ruby.rb index 80165ca..5b8de42 100644 --- a/lib/coderay/scanners/ruby.rb +++ b/lib/coderay/scanners/ruby.rb @@ -164,15 +164,19 @@ module Scanners end elsif match = scan(/ ' (?:(?>[^'\\]*) ')? | " (?:(?>[^"\\\#]*) ")? /mx) - encoder.begin_group :string if match.size == 1 + kind = check(self.class::StringState.simple_key_pattern(match)) ? :key : :string + encoder.begin_group kind encoder.text_token match, :delimiter - state = self.class::StringState.new :string, match == '"', match # important for streaming + state = self.class::StringState.new kind, match == '"', match # important for streaming else + kind = value_expected == true && scan(/:/) ? :key : :string + encoder.begin_group kind encoder.text_token match[0,1], :delimiter encoder.text_token match[1..-2], :content if match.size > 2 encoder.text_token match[-1,1], :delimiter - encoder.end_group :string + encoder.end_group kind + encoder.text_token ':', :operator if kind == :key value_expected = false end @@ -191,11 +195,14 @@ module Scanners encoder.text_token match, :error method_call_expected = false else - encoder.text_token match, self[1] ? :float : :integer # TODO: send :hex/:octal/:binary + kind = self[1] ? :float : :integer # TODO: send :hex/:octal/:binary + match << 'r' if match !~ /e/i && scan(/r/) + match << 'i' if scan(/i/) + encoder.text_token match, kind end value_expected = false - elsif match = scan(/ [-+!~^\/]=? | [:;] | [*|&]{1,2}=? | >>? /x) + elsif match = scan(/ [-+!~^\/]=? | [:;] | &\. | [*|&]{1,2}=? | >>? /x) value_expected = true encoder.text_token match, :operator @@ -208,7 +215,7 @@ module Scanners encoder.end_group kind heredocs ||= [] # create heredocs if empty heredocs << self.class::StringState.new(kind, quote != "'", delim, - self[1] == '-' ? :indented : :linestart) + self[1] ? :indented : :linestart) value_expected = false elsif value_expected && match = scan(/#{patterns::FANCY_STRING_START}/o) diff --git a/lib/coderay/scanners/ruby/patterns.rb b/lib/coderay/scanners/ruby/patterns.rb index ed071d2..e5a156d 100644 --- a/lib/coderay/scanners/ruby/patterns.rb +++ b/lib/coderay/scanners/ruby/patterns.rb @@ -114,7 +114,7 @@ module Scanners # NOTE: This is not completely correct, but # nobody needs heredoc delimiters ending with \n. HEREDOC_OPEN = / - << (-)? # $1 = float + << ([-~])? # $1 = float (?: ( [A-Za-z_0-9]+ ) # $2 = delim | @@ -157,13 +157,16 @@ module Scanners yield ]) - FANCY_STRING_START = / % ( [QqrsWwx] | (?![a-zA-Z0-9]) ) ([^a-zA-Z0-9]) /x + FANCY_STRING_START = / % ( [iIqQrswWx] | (?![a-zA-Z0-9]) ) ([^a-zA-Z0-9]) /x FANCY_STRING_KIND = Hash.new(:string).merge({ + 'i' => :symbol, + 'I' => :symbol, 'r' => :regexp, 's' => :symbol, 'x' => :shell, }) FANCY_STRING_INTERPRETED = Hash.new(true).merge({ + 'i' => false, 'q' => false, 's' => false, 'w' => false, diff --git a/lib/coderay/scanners/ruby/string_state.rb b/lib/coderay/scanners/ruby/string_state.rb index 2f398d1..95f1e83 100644 --- a/lib/coderay/scanners/ruby/string_state.rb +++ b/lib/coderay/scanners/ruby/string_state.rb @@ -16,7 +16,6 @@ module Scanners STRING_PATTERN = Hash.new do |h, k| delim, interpreted = *k - # delim = delim.dup # workaround for old Ruby delim_pattern = Regexp.escape(delim) if closing_paren = CLOSING_PAREN[delim] delim_pattern << Regexp.escape(closing_paren) @@ -29,12 +28,21 @@ module Scanners # '| [|?*+(){}\[\].^$]' # end - h[k] = - if interpreted && delim != '#' - / (?= [#{delim_pattern}] | \# [{$@] ) /mx - else - / (?= [#{delim_pattern}] ) /mx - end + if interpreted && delim != '#' + / (?= [#{delim_pattern}] | \# [{$@] ) /mx + else + / (?= [#{delim_pattern}] ) /mx + end.tap do |pattern| + h[k] = pattern if (delim.respond_to?(:ord) ? delim.ord : delim[0]) < 256 + end + end + + def self.simple_key_pattern delim + if delim == "'" + / (?> (?: [^\\']+ | \\. )* ) ' : /mx + else + / (?> (?: [^\\"\#]+ | \\. | \#\$[\\"] | \#\{[^\{\}]+\} | \#(?!\{) )* ) " : /mx + end end def initialize kind, interpreted, delim, heredoc = false diff --git a/lib/coderay/scanners/sass.rb b/lib/coderay/scanners/sass.rb index e20bebe..e3296b9 100644 --- a/lib/coderay/scanners/sass.rb +++ b/lib/coderay/scanners/sass.rb @@ -7,11 +7,6 @@ module Scanners register_for :sass file_extension 'sass' - STRING_CONTENT_PATTERN = { - "'" => /(?:[^\n\'\#]+|\\\n|#{RE::Escape}|#(?!\{))+/, - '"' => /(?:[^\n\"\#]+|\\\n|#{RE::Escape}|#(?!\{))+/, - } - protected def setup @@ -19,8 +14,9 @@ module Scanners end def scan_tokens encoder, options - states = Array(options[:state] || @state) - string_delimiter = nil + states = Array(options[:state] || @state).dup + + encoder.begin_group :string if states.last == :sqstring || states.last == :dqstring until eos? @@ -48,7 +44,7 @@ module Scanners elsif case states.last when :initial, :media, :sass_inline if match = scan(/(?>#{RE::Ident})(?!\()/ox) - encoder.text_token match, value_expected ? :value : (check(/.*:/) ? :key : :tag) + encoder.text_token match, value_expected ? :value : (check(/.*:(?![a-z])/) ? :key : :tag) next elsif !value_expected && (match = scan(/\*/)) encoder.text_token match, :tag @@ -91,24 +87,23 @@ module Scanners next end - when :string - if match = scan(STRING_CONTENT_PATTERN[string_delimiter]) + when :sqstring, :dqstring + if match = scan(states.last == :sqstring ? /(?:[^\n\'\#]+|\\\n|#{RE::Escape}|#(?!\{))+/o : /(?:[^\n\"\#]+|\\\n|#{RE::Escape}|#(?!\{))+/o) encoder.text_token match, :content elsif match = scan(/['"]/) encoder.text_token match, :delimiter encoder.end_group :string - string_delimiter = nil states.pop elsif match = scan(/#\{/) encoder.begin_group :inline encoder.text_token match, :inline_delimiter states.push :sass_inline elsif match = scan(/ \\ | $ /x) - encoder.end_group :string + encoder.end_group states.last encoder.text_token match, :error unless match.empty? states.pop else - raise_inspect "else case #{string_delimiter} reached; %p not handled." % peek(1), encoder + raise_inspect "else case #{states.last} reached; %p not handled." % peek(1), encoder end when :include @@ -119,7 +114,7 @@ module Scanners else #:nocov: - raise_inspect 'Unknown state', encoder + raise_inspect 'Unknown state: %p' % [states.last], encoder #:nocov: end @@ -157,15 +152,15 @@ module Scanners elsif match = scan(/['"]/) encoder.begin_group :string - string_delimiter = match encoder.text_token match, :delimiter if states.include? :sass_inline - content = scan_until(/(?=#{string_delimiter}|\}|\z)/) + # no nesting, just scan the string until delimiter + content = scan_until(/(?=#{match}|\}|\z)/) encoder.text_token content, :content unless content.empty? - encoder.text_token string_delimiter, :delimiter if scan(/#{string_delimiter}/) + encoder.text_token match, :delimiter if scan(/#{match}/) encoder.end_group :string else - states.push :string + states.push match == "'" ? :sqstring : :dqstring end elsif match = scan(/#{RE::Function}/o) @@ -214,14 +209,16 @@ module Scanners end + states.pop if states.last == :include + if options[:keep_state] - @state = states + @state = states.dup end while state = states.pop if state == :sass_inline encoder.end_group :inline - elsif state == :string + elsif state == :sqstring || state == :dqstring encoder.end_group :string end end diff --git a/lib/coderay/scanners/sql.rb b/lib/coderay/scanners/sql.rb index 93aeaf3..7d57f77 100644 --- a/lib/coderay/scanners/sql.rb +++ b/lib/coderay/scanners/sql.rb @@ -57,6 +57,12 @@ module Scanners STRING_PREFIXES = /[xnb]|_\w+/i + STRING_CONTENT_PATTERN = { + '"' => / (?: [^\\"] | "" )+ /x, + "'" => / (?: [^\\'] | '' )+ /x, + '`' => / (?: [^\\`] | `` )+ /x, + } + def scan_tokens encoder, options state = :initial @@ -90,7 +96,7 @@ module Scanners state = :string encoder.text_token match, :delimiter - elsif match = scan(/ @? [A-Za-z_][A-Za-z_0-9]* /x) + elsif match = scan(/ @? [A-Za-z_][A-Za-z_0-9\$]* /x) encoder.text_token match, name_expected ? :ident : (match[0] == ?@ ? :variable : IDENT_KIND[match]) name_expected = false @@ -115,40 +121,26 @@ module Scanners end elsif state == :string - if match = scan(/[^\\"'`]+/) - string_content << match - next + if match = scan(STRING_CONTENT_PATTERN[string_type]) + encoder.text_token match, :content elsif match = scan(/["'`]/) if string_type == match if peek(1) == string_type # doubling means escape - string_content << string_type << getch - next - end - unless string_content.empty? - encoder.text_token string_content, :content - string_content = '' + encoder.text_token match + getch, :content + else + encoder.text_token match, :delimiter + encoder.end_group :string + state = :initial + string_type = nil end - encoder.text_token match, :delimiter - encoder.end_group :string - state = :initial - string_type = nil else - string_content << match + encoder.text_token match, :content end elsif match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox) - unless string_content.empty? - encoder.text_token string_content, :content - string_content = '' - end encoder.text_token match, :char elsif match = scan(/ \\ . /mox) - string_content << match - next + encoder.text_token match, :content elsif match = scan(/ \\ | $ /x) - unless string_content.empty? - encoder.text_token string_content, :content - string_content = '' - end encoder.text_token match, :error unless match.empty? encoder.end_group :string state = :initial |