tomlrb 1.3.0 → 2.0.4

data/lib/tomlrb/scanner.rb

@@ -1,58 +1,92 @@
+# frozen-string-literal: true
+
 require 'strscan'
 
 module Tomlrb
   class Scanner
-    COMMENT = /#.*/
-    IDENTIFIER = /[A-Za-z0-9_-]+/
-    SPACE = /[ \t\r\n]/
-    STRING_BASIC = /(["])(?:\\?.)*?\1/
-    STRING_MULTI = /"{3}([\s\S]*?"{3,4})/m
-    STRING_LITERAL = /(['])(?:\\?.)*?\1/
-    STRING_LITERAL_MULTI = /'{3}([\s\S]*?'{3})/m
-    DATETIME = /(-?\d{4})-(\d{2})-(\d{2})(?:(?:t|\s)(\d{2}):(\d{2}):(\d{2}(?:\.\d+)?))?(z|[-+]\d{2}:\d{2})?/i
-    FLOAT = /[+-]?(?:[0-9_]+\.[0-9_]*|\d+(?=[eE]))(?:[eE][+-]?[0-9_]+)?/
-    FLOAT_INF = /[+-]?inf/
-    FLOAT_NAN = /[+-]?nan/
-    INTEGER = /[+-]?([1-9](_?\d)*|0)(?![A-Za-z0-9_-]+)/
-    TRUE   = /true/
-    FALSE  = /false/
+    COMMENT =
+      /#[^\u0000-\u0008\u000A-\u001F\u007F]*/.freeze
+    IDENTIFIER =
+      /[A-Za-z0-9_-]+/.freeze
+    SPACE =
+      /[ \t]/.freeze
+    NEWLINE =
+      /(?:[ \t]*(?:\r?\n)[ \t]*)+/.freeze
+    STRING_BASIC =
+      /(")(?:\\?[^\u0000-\u0008\u000A-\u001F\u007F\\]|(?:\\[^\u0000-\u0008\u000A-\u001F\u007F]))*?\1/.freeze
+    STRING_MULTI =
+      /"{3}([^\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F]*?(?<!\\)"{3,5})/m.freeze
+    STRING_LITERAL =
+      /(')(?:\\?[^\u0000-\u0008\u000A-\u001F\u007F])*?\1/.freeze
+    STRING_LITERAL_MULTI =
+      /'{3}([^\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F]*?'{3,5})/m.freeze
+    DATETIME =
+      /(-?\d{4})-([01]\d)-([0-3]\d)(?:(?:t|\s)([0-2]\d):([0-5]\d):([0-6]\d(?:\.\d+)?))?(z|[-+][01]\d:\d{2})?/i.freeze
+    LOCAL_TIME =
+      /([0-2]\d):([0-5]\d):([0-6]\d(?:\.\d+)?)/.freeze
+    FLOAT =
+      /[+-]?(?:(?:\d|[1-9](?:_?\d)*)\.\d(?:_?\d)*|\d+(?=[eE]))(?:[eE][+-]?[0-9]+(_[0-9])*[0-9]*)?(?!\w)/.freeze
+    FLOAT_KEYWORD =
+      /[+-]?(?:inf|nan)\b/.freeze
+    INTEGER =
+      /[+-]?([1-9](_?\d)*|0)(?![A-Za-z0-9_-]+)/.freeze
+    NON_DEC_INTEGER =
+      /0(?:x[0-9A-Fa-f](_?[0-9A-Fa-f])*|o[0-7](_?[0-7])*|b[01](_?[01])*)/.freeze
+    BOOLEAN =
+      /true|false/.freeze
+    SPACED_ARRAY_OF_TABLES_START =
+      /^\[[ \t]+\[(#{IDENTIFIER}|#{STRING_BASIC}|#{STRING_LITERAL}|#{INTEGER}|#{NON_DEC_INTEGER}|#{FLOAT_KEYWORD}|#{BOOLEAN})\]\]$/.freeze
+    SPACED_ARRAY_OF_TABLES_END =
+      /^\[\[(#{IDENTIFIER}|#{STRING_BASIC}|#{STRING_LITERAL}|#{INTEGER}|#{NON_DEC_INTEGER}|#{FLOAT_KEYWORD}|#{BOOLEAN})\][ \t]+\]$/.freeze
+    SPACED_ARRAY_OF_TABLES_BOTH =
+      /^\[[ \t]+\[(#{IDENTIFIER}|#{STRING_BASIC}|#{STRING_LITERAL}|#{INTEGER}|#{NON_DEC_INTEGER}|#{FLOAT_KEYWORD}|#{BOOLEAN})\][ \t]+\]$/.freeze
 
     def initialize(io)
       @ss = StringScanner.new(io.read)
+      @eos = false
     end
 
     def next_token
-      return if @ss.eos?
-
       case
+      when @ss.scan(NEWLINE) then [:NEWLINE, nil]
+      when @ss.scan(SPACED_ARRAY_OF_TABLES_START) then raise ParseError.new('Array of tables has spaces in starting brackets')
+      when @ss.scan(SPACED_ARRAY_OF_TABLES_END) then raise ParseError.new('Array of tables has spaces in ending brackets')
+      when @ss.scan(SPACED_ARRAY_OF_TABLES_BOTH) then raise ParseError.new('Array of tables has spaces in starting and ending brackets')
       when @ss.scan(SPACE) then next_token
       when @ss.scan(COMMENT) then next_token
       when @ss.scan(DATETIME) then process_datetime
+      when @ss.scan(LOCAL_TIME) then process_local_time
       when text = @ss.scan(STRING_MULTI) then [:STRING_MULTI, text[3..-4]]
       when text = @ss.scan(STRING_BASIC) then [:STRING_BASIC, text[1..-2]]
       when text = @ss.scan(STRING_LITERAL_MULTI) then [:STRING_LITERAL_MULTI, text[3..-4]]
       when text = @ss.scan(STRING_LITERAL) then [:STRING_LITERAL, text[1..-2]]
       when text = @ss.scan(FLOAT) then [:FLOAT, text]
-      when text = @ss.scan(FLOAT_INF) then [:FLOAT_INF, text]
-      when text = @ss.scan(FLOAT_NAN) then [:FLOAT_NAN, text]
+      when text = @ss.scan(FLOAT_KEYWORD) then [:FLOAT_KEYWORD, text]
       when text = @ss.scan(INTEGER) then [:INTEGER, text]
-      when text = @ss.scan(TRUE)   then [:TRUE, text]
-      when text = @ss.scan(FALSE)  then [:FALSE, text]
+      when text = @ss.scan(NON_DEC_INTEGER) then [:NON_DEC_INTEGER, text]
+      when text = @ss.scan(BOOLEAN) then [:BOOLEAN, text]
       when text = @ss.scan(IDENTIFIER) then [:IDENTIFIER, text]
-      else
-        x = @ss.getch
-        [x, x]
+      when @ss.eos? then process_eos
+      else x = @ss.getch; [x, x]
       end
     end
 
     def process_datetime
-      if @ss[7].nil?
-        offset = '+00:00'
-      else
-        offset = @ss[7].gsub('Z', '+00:00')
-      end
-      args = [@ss[1], @ss[2], @ss[3], @ss[4] || 0, @ss[5] || 0, @ss[6].to_f, offset]
+      offset = @ss[7].gsub(/[zZ]/, '+00:00') if @ss[7]
+      args = [@ss[0], @ss[1], @ss[2], @ss[3], @ss[4], @ss[5], @ss[6], offset]
       [:DATETIME, args]
     end
+
+    def process_local_time
+      args = [@ss[0], @ss[1], @ss[2], @ss[3].to_f]
+      [:LOCAL_TIME, args]
+    end
+
+    def process_eos
+      return if @eos
+
+      @eos = true
+      [:EOS, nil]
+    end
   end
 end

data/lib/tomlrb/string_utils.rb

@@ -1,6 +1,7 @@
+# frozen-string-literal: true
+
 module Tomlrb
   class StringUtils
-
     SPECIAL_CHARS = {
       '\\t'  => "\t",
       '\\b'  => "\b",
@@ -12,7 +13,13 @@ module Tomlrb
     }.freeze
 
     def self.multiline_replacements(str)
-      strip_spaces(str).gsub(/\\\n\s+/, '')
+      strip_spaces(str).gsub(/\\+\s*\n\s*/) do |matched|
+        if matched.match(/\\+/)[0].length.odd?
+          matched.gsub(/\\\s*\n\s*/, '')
+        else
+          matched
+        end
+      end
     end
 
     def self.replace_escaped_chars(str)

data/lib/tomlrb/version.rb

@@ -1,3 +1,5 @@
+# frozen-string-literal: true
+
 module Tomlrb
-  VERSION = '1.3.0'.freeze
+  VERSION = '2.0.4'
 end

data/lib/tomlrb.rb

@@ -1,10 +1,15 @@
+# frozen-string-literal: true
+
 require 'time'
 require 'stringio'
-require "tomlrb/version"
+require 'tomlrb/version'
+require 'tomlrb/local_date_time'
+require 'tomlrb/local_date'
+require 'tomlrb/local_time'
 require 'tomlrb/string_utils'
-require "tomlrb/scanner"
-require "tomlrb/parser"
-require "tomlrb/handler"
+require 'tomlrb/scanner'
+require 'tomlrb/parser'
+require 'tomlrb/handler'
 
 module Tomlrb
   class ParseError < StandardError; end
@@ -38,7 +43,7 @@ module Tomlrb
     # By default Ruby sets the external encoding of an IO object to the
     # default external encoding. The default external encoding is set by
     # locale encoding or the interpreter -E option.
-    tmp = File.read(path, :encoding=>'utf-8')
+    tmp = File.read(path, encoding: 'utf-8')
     Tomlrb.parse(tmp, **options)
   end
 end

metadata

@@ -1,15 +1,28 @@
 --- !ruby/object:Gem::Specification
 name: tomlrb
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 2.0.4
 platform: ruby
 authors:
 - Francois Bernier
-autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-03-19 00:00:00.000000000 Z
-dependencies: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: psych
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4'
 description: A racc based toml parser
 email:
 - frankbernier@gmail.com
@@ -21,6 +34,9 @@ files:
 - lib/tomlrb.rb
 - lib/tomlrb/generated_parser.rb
 - lib/tomlrb/handler.rb
+- lib/tomlrb/local_date.rb
+- lib/tomlrb/local_date_time.rb
+- lib/tomlrb/local_time.rb
 - lib/tomlrb/parser.rb
 - lib/tomlrb/parser.y
 - lib/tomlrb/scanner.rb
@@ -30,7 +46,6 @@ homepage: https://github.com/fbernier/tomlrb
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -45,8 +60,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.6
-signing_key: 
+rubygems_version: 3.6.9
 specification_version: 4
 summary: A racc based toml parser
 test_files: []