llm-shell 0.9.2 → 0.10.0

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/diff.rb

@@ -0,0 +1,221 @@
+module CodeRay
+module Scanners
+  
+  # Scanner for output of the diff command.
+  # 
+  # Alias: +patch+
+  class Diff < Scanner
+    
+    register_for :diff
+    title 'diff output'
+    
+    DEFAULT_OPTIONS = {
+      :highlight_code => true,
+      :inline_diff    => true,
+    }
+    
+  protected
+    
+    def scan_tokens encoder, options
+      
+      line_kind = nil
+      state = :initial
+      deleted_lines_count = 0
+      scanners = Hash.new do |h, lang|
+        h[lang] = Scanners[lang].new '', :keep_tokens => true, :keep_state => true
+      end
+      content_scanner = scanners[:plain]
+      content_scanner_entry_state = nil
+      
+      until eos?
+        
+        if match = scan(/\n/)
+          deleted_lines_count = 0 unless line_kind == :delete
+          if line_kind
+            encoder.end_line line_kind
+            line_kind = nil
+          end
+          encoder.text_token match, :space
+          next
+        end
+        
+        case state
+        
+        when :initial
+          if match = scan(/--- |\+\+\+ |=+|_+/)
+            encoder.begin_line line_kind = :head
+            encoder.text_token match, :head
+            if match = scan(/[^\x00\n]+?(?=$|[\t\n]|  \(revision)/)
+              encoder.text_token match, :filename
+              if options[:highlight_code] && match != '/dev/null'
+                file_type = CodeRay::FileType.fetch(match, :text)
+                file_type = :text if file_type == :diff
+                content_scanner = scanners[file_type]
+                content_scanner_entry_state = nil
+              end
+            end
+            next unless match = scan(/.+/)
+            encoder.text_token match, :plain
+          elsif match = scan(/Index: |Property changes on: /)
+            encoder.begin_line line_kind = :head
+            encoder.text_token match, :head
+            next unless match = scan(/.+/)
+            encoder.text_token match, :plain
+          elsif match = scan(/Added: /)
+            encoder.begin_line line_kind = :head
+            encoder.text_token match, :head
+            next unless match = scan(/.+/)
+            encoder.text_token match, :plain
+            state = :added
+          elsif match = scan(/\\ .*/)
+            encoder.text_token match, :comment
+          elsif match = scan(/@@(?>[^@\n]+)@@/)
+            content_scanner.state = :initial unless match?(/\n\+/)
+            content_scanner_entry_state = nil
+            if check(/\n|$/)
+              encoder.begin_line line_kind = :change
+            else
+              encoder.begin_group :change
+            end
+            encoder.text_token match[0,2], :change
+            encoder.text_token match[2...-2], :plain
+            encoder.text_token match[-2,2], :change
+            encoder.end_group :change unless line_kind
+            next unless match = scan(/.+/)
+            if options[:highlight_code]
+              content_scanner.tokenize match, :tokens => encoder
+            else
+              encoder.text_token match, :plain
+            end
+            next
+          elsif match = scan(/\+/)
+            encoder.begin_line line_kind = :insert
+            encoder.text_token match, :insert
+            next unless match = scan(/.+/)
+            if options[:highlight_code]
+              content_scanner.tokenize match, :tokens => encoder
+            else
+              encoder.text_token match, :plain
+            end
+            next
+          elsif match = scan(/-/)
+            deleted_lines_count += 1
+            if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && changed_lines_count <= 100_000 && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\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(/.*/) }
+              
+              deleted_lines_tokenized  = []
+              inserted_lines_tokenized = []
+              for deleted_line, inserted_line in deleted_lines.zip(inserted_lines)
+                pre, deleted_part, inserted_part, post = diff deleted_line, inserted_line
+                content_scanner_entry_state = content_scanner.state
+                deleted_lines_tokenized << content_scanner.tokenize([pre, deleted_part, post], :tokens => Tokens.new)
+                content_scanner.state = content_scanner_entry_state || :initial
+                inserted_lines_tokenized << content_scanner.tokenize([pre, inserted_part, post], :tokens => Tokens.new)
+              end
+              
+              for pre, deleted_part, post in deleted_lines_tokenized
+                encoder.begin_line :delete
+                encoder.text_token '-', :delete
+                encoder.tokens pre
+                unless deleted_part.empty?
+                  encoder.begin_group :eyecatcher
+                  encoder.tokens deleted_part
+                  encoder.end_group :eyecatcher
+                end
+                encoder.tokens post
+                encoder.end_line :delete
+                encoder.text_token "\n", :space
+              end
+              
+              for pre, inserted_part, post in inserted_lines_tokenized
+                encoder.begin_line :insert
+                encoder.text_token '+', :insert
+                encoder.tokens pre
+                unless inserted_part.empty?
+                  encoder.begin_group :eyecatcher
+                  encoder.tokens inserted_part
+                  encoder.end_group :eyecatcher
+                end
+                encoder.tokens post
+                changed_lines_count -= 1
+                if changed_lines_count > 0
+                  encoder.end_line :insert
+                  encoder.text_token "\n", :space
+                end
+              end
+              
+              line_kind = :insert
+              
+            elsif match = scan(/.*/)
+              encoder.begin_line line_kind = :delete
+              encoder.text_token '-', :delete
+              if options[:highlight_code]
+                if deleted_lines_count == 1
+                  content_scanner_entry_state = content_scanner.state
+                end
+                content_scanner.tokenize match, :tokens => encoder unless match.empty?
+                if !match?(/\n-/)
+                  if match?(/\n\+/)
+                    content_scanner.state = content_scanner_entry_state || :initial
+                  end
+                  content_scanner_entry_state = nil
+                end
+              else
+                encoder.text_token match, :plain
+              end
+            end
+            next
+          elsif match = scan(/ .*/)
+            if options[:highlight_code]
+              content_scanner.tokenize match, :tokens => encoder
+            else
+              encoder.text_token match, :plain
+            end
+            next
+          elsif match = scan(/.+/)
+            encoder.begin_line line_kind = :comment
+            encoder.text_token match, :plain
+          else
+            raise_inspect 'else case rached'
+          end
+        
+        when :added
+          if match = scan(/   \+/)
+            encoder.begin_line line_kind = :insert
+            encoder.text_token match, :insert
+            next unless match = scan(/.+/)
+            encoder.text_token match, :plain
+          else
+            state = :initial
+            next
+          end
+        end
+        
+      end
+      
+      encoder.end_line line_kind if line_kind
+      
+      encoder
+    end
+    
+  private
+    
+    def diff a, b
+      # i will be the index of the leftmost difference from the left.
+      i_max = [a.size, b.size].min
+      i = 0
+      i += 1 while i < i_max && a[i] == b[i]
+      # j_min will be the index of the leftmost difference from the right.
+      j_min = i - i_max
+      # j will be the index of the rightmost difference from the right which
+      # does not precede the leftmost one from the left.
+      j = -1
+      j -= 1 while j >= j_min && a[j] == b[j]
+      return a[0...i], a[i..j], b[i..j], (j < -1) ? a[j + 1..-1] : ''
+    end
+    
+  end
+  
+end
+end

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/erb.rb

@@ -0,0 +1,81 @@
+module CodeRay
+module Scanners
+  
+  load :html
+  load :ruby
+  
+  # Scanner for HTML ERB templates.
+  class ERB < Scanner
+    
+    register_for :erb
+    title 'HTML ERB Template'
+    
+    KINDS_NOT_LOC = HTML::KINDS_NOT_LOC
+    
+    ERB_RUBY_BLOCK = /
+      (<%(?!%)[-=\#]?)
+      ((?>
+        [^\-%]*    # normal*
+        (?>        # special
+          (?: %(?!>) | -(?!%>) )
+          [^\-%]*  # normal*
+        )*
+      ))
+      ((?: -?%> )?)
+    /x  # :nodoc:
+    
+    START_OF_ERB = /
+      <%(?!%)
+    /x  # :nodoc:
+    
+  protected
+    
+    def setup
+      @ruby_scanner = CodeRay.scanner :ruby, :tokens => @tokens, :keep_tokens => true
+      @html_scanner = CodeRay.scanner :html, :tokens => @tokens, :keep_tokens => true, :keep_state => true
+    end
+    
+    def reset_instance
+      super
+      @html_scanner.reset
+    end
+    
+    def scan_tokens encoder, options
+      
+      until eos?
+        
+        if (match = scan_until(/(?=#{START_OF_ERB})/o) || scan_rest) and not match.empty?
+          @html_scanner.tokenize match, :tokens => encoder
+          
+        elsif match = scan(/#{ERB_RUBY_BLOCK}/o)
+          start_tag = self[1]
+          code = self[2]
+          end_tag = self[3]
+          
+          encoder.begin_group :inline
+          encoder.text_token start_tag, :inline_delimiter
+          
+          if start_tag == '<%#'
+            encoder.text_token code, :comment
+          else
+            @ruby_scanner.tokenize code, :tokens => encoder
+          end unless code.empty?
+          
+          encoder.text_token end_tag, :inline_delimiter unless end_tag.empty?
+          encoder.end_group :inline
+          
+        else
+          raise_inspect 'else-case reached!', encoder
+          
+        end
+        
+      end
+      
+      encoder
+      
+    end
+    
+  end
+  
+end
+end

data/lib/llm/shell/internal/coderay/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