diff options
Diffstat (limited to 'lib/coderay/scanners')
| -rw-r--r-- | lib/coderay/scanners/css.rb | 8 | ||||
| -rw-r--r-- | lib/coderay/scanners/debug.rb | 26 | ||||
| -rw-r--r-- | lib/coderay/scanners/diff.rb | 4 | ||||
| -rw-r--r-- | lib/coderay/scanners/go.rb | 208 | ||||
| -rw-r--r-- | lib/coderay/scanners/groovy.rb | 21 | ||||
| -rw-r--r-- | lib/coderay/scanners/html.rb | 54 | ||||
| -rw-r--r-- | lib/coderay/scanners/json.rb | 25 | ||||
| -rw-r--r-- | lib/coderay/scanners/lua.rb | 280 | ||||
| -rw-r--r-- | lib/coderay/scanners/php.rb | 26 | ||||
| -rw-r--r-- | lib/coderay/scanners/python.rb | 4 | ||||
| -rw-r--r-- | lib/coderay/scanners/raydebug.rb | 45 | ||||
| -rw-r--r-- | lib/coderay/scanners/ruby.rb | 21 | ||||
| -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 | 47 | ||||
| -rw-r--r-- | lib/coderay/scanners/sql.rb | 51 | ||||
| -rw-r--r-- | lib/coderay/scanners/taskpaper.rb | 36 | ||||
| -rw-r--r-- | lib/coderay/scanners/yaml.rb | 4 |
18 files changed, 753 insertions, 136 deletions
diff --git a/lib/coderay/scanners/css.rb b/lib/coderay/scanners/css.rb index 732f9c5..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? @@ -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 + encoder.text_token match[start.size..-1], :content if match.size > start.size end encoder.end_group :function 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 af0f755..74a6c27 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|$/) @@ -100,7 +100,7 @@ module Scanners next elsif match = scan(/-/) deleted_lines_count += 1 - if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\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/groovy.rb b/lib/coderay/scanners/groovy.rb index cf55daf..c64454f 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 @@ -223,7 +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 @@ -243,7 +246,17 @@ 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] + @state = state + end + + until inline_block_stack.empty? + state, = *inline_block_stack.pop + encoder.end_group :inline + encoder.end_group state == :regexp ? :regexp : :string end encoder diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb index 3ba3b79..ebe7b01 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 = [ @@ -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: @@ -75,9 +76,14 @@ 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, state = [:initial] + if code && !code.empty? + @css_scanner ||= Scanners::CSS.new '', :keep_tokens => true + @css_scanner.tokenize code, :tokens => encoder, :state => state end end @@ -99,7 +105,15 @@ module Scanners case state when :initial - if match = scan(/<!--(?:.*?-->|.*)/m) + if match = scan(/<!\[CDATA\[/) + encoder.text_token match, :inline_delimiter + if match = scan(/.*?\]\]>/m) + encoder.text_token match[0..-4], :plain + encoder.text_token ']]>', :inline_delimiter + elsif match = scan(/.+/) + encoder.text_token match, :error + end + elsif match = scan(/<!--(?:.*?-->|.*)/m) encoder.text_token match, :comment elsif match = scan(/<!(\w+)(?:.*?>|.*)|\]>/m) encoder.text_token match, :doctype @@ -110,7 +124,7 @@ 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] @@ -161,17 +175,21 @@ 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 @@ -206,19 +224,23 @@ 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 diff --git a/lib/coderay/scanners/json.rb b/lib/coderay/scanners/json.rb index 4e0f462..b09970c 100644 --- a/lib/coderay/scanners/json.rb +++ b/lib/coderay/scanners/json.rb @@ -14,15 +14,21 @@ 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 = options[:state] || @state - state = :initial - stack = [] - key_expected = false + if [:string, :key].include? state + encoder.begin_group state + end until eos? @@ -32,18 +38,11 @@ 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 +81,10 @@ module Scanners end end + if options[:keep_state] + @state = state + end + if [:string, :key].include? state encoder.end_group state end diff --git a/lib/coderay/scanners/lua.rb b/lib/coderay/scanners/lua.rb new file mode 100644 index 0000000..fb1e45a --- /dev/null +++ b/lib/coderay/scanners/lua.rb @@ -0,0 +1,280 @@ +# encoding: utf-8 + +module CodeRay +module Scanners + + # 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 Lua < 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 + 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 + 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 + + if options[:keep_state] + @state = state + end + + encoder.end_group :string if [:string].include? state + brace_depth.times { encoder.end_group :map } + + encoder + end + + end + +end +end diff --git a/lib/coderay/scanners/php.rb b/lib/coderay/scanners/php.rb index 6c68834..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 @@ -500,6 +510,14 @@ module Scanners end + 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 end 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 diff --git a/lib/coderay/scanners/raydebug.rb b/lib/coderay/scanners/raydebug.rb index 7a21354..1effdc8 100644 --- a/lib/coderay/scanners/raydebug.rb +++ b/lib/coderay/scanners/raydebug.rb @@ -1,23 +1,30 @@ +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 file_extension 'raydebug' title 'CodeRay Token Dump' protected + def setup + super + @known_token_kinds = TokenKinds.keys.map(&:to_s).to_set + end + def scan_tokens encoder, options - + opened_tokens = [] - + until eos? - + if match = scan(/\s+/) encoder.text_token match, :space @@ -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? + 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 @@ -59,8 +68,8 @@ module Scanners encoder end - + end - + end end diff --git a/lib/coderay/scanners/ruby.rb b/lib/coderay/scanners/ruby.rb index c282f31..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) @@ -269,7 +276,7 @@ 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 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 167051d..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) @@ -176,7 +171,7 @@ 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 @@ -195,7 +190,7 @@ 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 @@ -214,8 +209,18 @@ 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 == :sqstring || state == :dqstring + encoder.end_group :string + end end encoder diff --git a/lib/coderay/scanners/sql.rb b/lib/coderay/scanners/sql.rb index b757278..7d57f77 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( @@ -56,6 +57,12 @@ module CodeRay module Scanners STRING_PREFIXES = /[xnb]|_\w+/i + STRING_CONTENT_PATTERN = { + '"' => / (?: [^\\"] | "" )+ /x, + "'" => / (?: [^\\'] | '' )+ /x, + '`' => / (?: [^\\`] | `` )+ /x, + } + def scan_tokens encoder, options state = :initial @@ -89,7 +96,7 @@ module CodeRay 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 @@ -114,41 +121,28 @@ module CodeRay 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 else raise "else case \" reached; %p not handled." % peek(1), encoder @@ -171,4 +165,5 @@ module CodeRay module Scanners end -end end
\ No newline at end of file +end +end diff --git a/lib/coderay/scanners/taskpaper.rb b/lib/coderay/scanners/taskpaper.rb new file mode 100644 index 0000000..42670bc --- /dev/null +++ b/lib/coderay/scanners/taskpaper.rb @@ -0,0 +1,36 @@ +module CodeRay +module Scanners + + class Taskpaper < Scanner + + register_for :taskpaper + file_extension 'taskpaper' + + protected + + def scan_tokens encoder, options + until eos? + if match = scan(/\S.*:.*$/) # project + encoder.text_token(match, :namespace) + elsif match = scan(/-.+@done.*/) # completed task + encoder.text_token(match, :done) + elsif match = scan(/-(?:[^@\n]+|@(?!due))*/) # task + encoder.text_token(match, :plain) + elsif match = scan(/@due.*/) # comment + encoder.text_token(match, :important) + elsif match = scan(/.+/) # comment + encoder.text_token(match, :comment) + elsif match = scan(/\s+/) # space + encoder.text_token(match, :space) + else # other + encoder.text_token getch, :error + end + end + + encoder + end + + end + +end +end diff --git a/lib/coderay/scanners/yaml.rb b/lib/coderay/scanners/yaml.rb index 96f4e93..32c8e2c 100644 --- a/lib/coderay/scanners/yaml.rb +++ b/lib/coderay/scanners/yaml.rb @@ -47,7 +47,7 @@ module Scanners when !check(/(?:"[^"]*")(?=: |:$)/) && 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 @@ -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 |