rb_cfg_parser 0.1.0 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4df70690cfafd3255e28fdd3c4954dae237103d97b12eb74f99d8070dd32d0a8
-  data.tar.gz: eed8ed48485581ec18325ca84315b7eefd2350bcb3eeb220f0d1ed503186df98
+  metadata.gz: 67671d34a5ab6b2e94b06ca3152ba1b820fb91bbb44a2cd8c75de155eae3da1b
+  data.tar.gz: c98c2337de6184a209f499d29b569f9836350e22c57d09602378cfe76b215382
 SHA512:
-  metadata.gz: 1d657635a43aa04c046a0f96ad369b0d9e9ce705ff2493120af7f2e31ac041480795f774a79fbd0b96ff3597dd6dab4acb9ac19a6f13c7c1a744bf84ae16d0a4
-  data.tar.gz: e944e9320ba30df3f257e691e2947167d24d5ec7f1bb4cfd70ea6d51ea34a7ca98f95df736da71eb1fc9c6e2eea613c340d27edceea42e87579600b57675615b
+  metadata.gz: 6801e106a59a9df556acb29c253b577befe47014f93f3fb215cec04ad232546b2cd27fcde5031e78ea8cee778c51f3bd2995d3faa2e330595496c959dd83c1ec
+  data.tar.gz: c6120c344a91322f903afb7e9ca4700c997eb09d63e115f90474610332bec605206a30307aa7ed3e221a482bda88dcebab52f1824ad43c9bb5e98625950d01a2

data/LICENSE.txt

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) since 2025: rb-cfg-parser ruby App
+Copyright (c) since 2025: rb-cfg-parser Ruby Gem
 description: ruby gem to parse and load .cfg files
 author:      J. Arrizza   email: cppgent0@gmail.com
 

data/README.md

@@ -6,7 +6,7 @@
 This Ruby gem parses a .cfg file based on how python's ```configparser``` module works.
 
 The need for this came from a "cross-platform utilities" (xplat_utils) repo that I use
-to maintain the many projects for my website. It works on Python, Ruby, C/C++, Android
+to maintain the many projects for my website. It works on Python, Ruby, C/C++, Arduino
 for now.
 
 Having a common .cfg format is ideal in that scenario.
@@ -45,6 +45,20 @@ puts('  >>')
 
 See ut/ut_*.rb for examples of all the possible formats it recognizes.
 
+#### logging
+
+A logging callback is allowed. See ut/ut_tp004_puts_callback.rb for example of how to use it:
+
+```ruby
+@parser.log_cb  = method(:logger)
+@parser.verbose = 1
+# <snip>
+
+def logger(msg)
+# your code to log
+end
+```
+
 #### parsing
 
 A cfg file can be parsed or a string can be parsed:
@@ -57,7 +71,8 @@ cfg = parser.parse_str(lines)
 
 The content returned is a hash.
 The key is the section_name and the variables within that
-section are held as a hash.
+section are held as a hash. Spaces are not allowed in a
+section name.
 
 ```text
 [section_name]  
@@ -133,10 +148,9 @@ vrbl1 = 'val1' 'val2' 'val3'
 vrbl1 = "val1" "val2" "val3"
 ```
 
-Warning: there is currently an issue is inconsistent quoting is done:
+Mixed quote types works:
 
 ```text
-# these will return the incorrect array ['val1', 'val3']
 vrbl1 = 'val1' val2 'val3'  
 vrbl1 = 'val1' "val2" 'val3'
 vrbl1 = "val1" 'val2' "val3"
@@ -151,8 +165,7 @@ vrbl1 = 'val1'
         'val3'
 ```
 
-Note mixed quoted are okay, but recommended since converting them to a single
-line will cause errors
+Mixed quote types works:
 
 ```text
 # this returns an array ['val1', 'val2', 'val3']

data/lib/parser/cfg_lexer.rex.rb

@@ -0,0 +1,111 @@
+#--
+# DO NOT MODIFY!!!!
+# This file is automatically generated by rex 1.0.8
+# from lexical definition file "lib/cfg_lexer.rex".
+#++
+
+class CfgLexer
+      require 'strscan'
+
+      class ScanError < StandardError ; end
+
+      attr_reader   :lineno
+      attr_reader   :filename
+      attr_accessor :state
+
+      def scan_setup(str)
+        @ss = StringScanner.new(str)
+        @lineno =  1
+        @state  = nil
+      end
+
+      def action
+        yield
+      end
+
+      def scan_str(str)
+        scan_setup(str)
+        do_parse
+      end
+      alias :scan :scan_str
+
+      def load_file( filename )
+        @filename = filename
+        File.open(filename, "r") do |f|
+          scan_setup(f.read)
+        end
+      end
+
+      def scan_file( filename )
+        load_file(filename)
+        do_parse
+      end
+
+
+        def next_token
+          return if @ss.eos?
+
+          # skips empty actions
+          until token = _next_token or @ss.eos?; end
+          token
+        end
+
+        def _next_token
+          text = @ss.peek(1)
+          @lineno  +=  1  if text == "\n"
+          token = case @state
+            when nil
+          case
+                  when (text = @ss.scan(/\[\s*VRBL\s*\]/))
+                     action { [:section, text] }
+
+                  when (text = @ss.scan(/\p{Alpha}+(\p{Alnum}|_|-|\.)*/))
+                     action { [:vrbl, text] }
+
+                  when (text = @ss.scan(/'.*?'/))
+                     action { [:value, text] }
+
+                  when (text = @ss.scan(/".*?"/))
+                     action { [:value, text] }
+
+                  when (text = @ss.scan(/=/))
+                     action { [:equal, text] }
+
+                  when (text = @ss.scan(/,/))
+                     action { [:comma, text] }
+
+                  when (text = @ss.scan(/\n/))
+                     action { [:newline, ''] }
+
+                  when (text = @ss.scan(/\[/))
+                     action { [:open_bracket, text] }
+
+                  when (text = @ss.scan(/\]/))
+                     action { [:close_bracket, text] }
+
+                  when (text = @ss.scan(/;.*\n/))
+                     action { [:comment, ''] }
+
+                  when (text = @ss.scan(/\#.*\n/))
+                     action { [:comment, ''] }
+
+                  when (text = @ss.scan(/[ \t]+/))
+                     action { [:wspace, ''] }
+
+                  when (text = @ss.scan(/[^\s]*/))
+                     action { [:value, text] }
+
+          
+          else
+            text = @ss.string[@ss.pos .. -1]
+            raise  ScanError, "can not match: '" + text + "'"
+          end  # if
+
+        else
+          raise  ScanError, "undefined state: '" + state.to_s + "'"
+        end  # case state
+          token
+        end  # def _next_token
+
+end # class
+

data/lib/parser/cfg_parser.rb

@@ -0,0 +1,313 @@
+# frozen_string_literal: true
+require_relative 'cfg_lexer.rex'
+
+###
+# Parse text incoming sections and assignments
+# uses rexical, see https://github.com/sparklemotion/rexical/blob/main/DOCUMENTATION.en.rdoc
+class RbCfgParser
+  attr_writer :verbose
+  attr_writer :log_cb
+
+  ###
+  # constructor
+  def initialize
+    @rex                 = CfgLexer.new
+    @fsm                 = :start
+    @lineno              = 0
+    @token               = nil
+    @tok_posn            = 0
+    @next_token          = nil
+    @next_tok_posn       = 0
+    @curr_values         = nil
+    @curr_section        = nil
+    @curr_section_lineno = 0
+    @log_cb              = method(:_print_raw_line)
+    @verbose             = 0
+    @content             = {}
+  end
+
+  ###
+  # parse the given file
+  # @return the content as a hash
+  def parse_file(path)
+    file_content = File.read(path)
+    parse_str(file_content)
+  end
+
+  ###
+  # parse the given string
+  # @return the content as a hash
+  def parse_str(text)
+    text = text.join("\n") if text.is_a?(Array)
+    @rex.scan_setup(text)
+    get_next_token
+    get_next_token unless @next_token.nil?
+    @fsm    = :start
+    @lineno = 1
+
+    loop do
+      break if @token.nil?
+      # print_dbg(format('fsm:%-17s tok[%d]:%-13s val:%-10s next[%d]=%s', @fsm, @tok_posn, @token[0], @token[1], @next_tok_posn, @next_token))
+
+      if @token[0] == :newline
+        @lineno        += 1
+        @tok_posn      = 0
+        @next_tok_posn = 1
+      end
+
+      if @token[0] == :comment
+        @lineno        += 1
+        @tok_posn      = 0
+        @next_tok_posn = 1
+      elsif @fsm == :start
+        fsm_start
+      elsif @fsm == :read_section
+        fsm_read_section
+      elsif @fsm == :assignments
+        fsm_assignments
+      elsif @fsm == :asgmt_read_values
+        fsm_asgmt_read_values
+      else
+        # :nocov: can't be invoked unless there is an unknown fsm state
+        raise_unexpected_token
+        # :nocov:
+      end
+
+      get_next_token
+    end
+    save_curr_assignment unless @curr_vrbl.nil?
+    raise_err('Incomplete section') if @fsm == :read_section
+
+    @content
+  end
+
+  ###
+  # in the start fsm state:
+  #   read and handle the next value
+  # @return None
+  def fsm_start
+    if @token[0] == :newline
+      @lineno        += 1
+      @tok_posn      = 0
+      @next_tok_posn = 1
+    elsif @token[0] == :open_bracket && @tok_posn == 1
+      @fsm = :read_section
+      reset_section
+    elsif @token[0] == :vrbl && @next_token[0] == :equal
+      @curr_section = :unnamed
+      save_curr_section
+      @curr_vrbl   = @token[1].strip
+      @curr_values = nil
+      @fsm         = :asgmt_read_values
+      # skip the equals
+      get_next_token
+    else
+      raise_unexpected_token
+    end
+  end
+
+  ###
+  # in the read_section fsm state:
+  #   read and handle the next value
+  # @return None
+  def fsm_read_section
+    if @token[0] == :vrbl
+      @curr_section = @token[1]
+    elsif @token[0] == :close_bracket
+      raise_err('missing section name') if @curr_section.nil?
+      @curr_section.strip!
+      save_curr_section
+      print_line(format('%-10s: >>%s<<', 'section', @curr_section))
+      @fsm = :assignments
+    elsif @token[0] == :comma
+      raise_err('invalid section content, did you use square brackets for a value?')
+    elsif @token[0] == :newline
+      raise_err("section must be on one line, see line #{@curr_section_lineno}")
+    else
+      raise_unexpected_token
+    end
+  end
+
+  ###
+  # in the assignments fsm state:
+  #   read and handle the next value
+  # @return None
+  def fsm_assignments
+    if @token[0] == :newline
+      # skip
+    elsif @token[0] == :open_bracket
+      @fsm = :read_section
+      reset_section
+      # elsif @token[0] == :vrbl && @tok_posn == 1
+    elsif @token[0] == :vrbl && @next_token[0] == :equal
+      @curr_vrbl   = @token[1].strip
+      @curr_values = nil
+      @fsm         = :asgmt_read_values
+      # skip the equals
+      get_next_token
+    elsif @token[0] == :value && @next_token[0] == :equal
+      raise_err("missing variable, found :value instead: '#{@token[1]}'")
+    elsif %i[value vrbl].include?(@token[0]) && !@next_token.nil? && @next_token[0] == :newline
+      raise_err('newline not allowed after variable')
+    else
+      raise_unexpected_token
+    end
+  end
+
+  ###
+  # in the asgmt_read_values fsm state:
+  #   read and handle the next value
+  # @return None
+  def fsm_asgmt_read_values
+    if @token[0] == :newline
+      # handle empty value
+      @curr_values = '' if @curr_values.nil?
+      print_line(format('%-10s: %s.%s = >>%s<<', 'assignment', @curr_section, @curr_vrbl, @curr_values))
+      @lineno += 1
+    elsif @token[0] == :comma
+      # skip
+    elsif @token[0] == :open_bracket
+      # it's a new section
+      save_curr_assignment
+
+      # start a new section
+      reset_section
+      @fsm = :read_section
+    elsif @token[0] == :vrbl && !@next_token.nil? && @next_token[0] == :equal
+      # it's a new assigment
+      save_curr_assignment
+
+      # start a new assignment
+      @curr_vrbl   = @token[1].strip
+      @curr_values = nil
+      @fsm         = :asgmt_read_values
+      # skip the equals
+      get_next_token
+    elsif %i[value vrbl].include?(@token[0])
+      # if a vrbl is right next to a value (no wspace), then two tokens should be concatenated
+      if @token[0] == :vrbl && !@next_token.nil? && @next_token[0] == :value && @next_tok_posn == @tok_posn + 1
+        val = @token[1] + @next_token[1]
+        # val = val[1..-2] if (val[0] == "'" && val[-1] == "'") || (val[0] == '"' && val[-1] == '"')
+        get_next_token
+      else
+        val = @token[1]
+      end
+      val = strip_quotes(val)
+
+      # it's a value to save
+      if @curr_values.nil?
+        @curr_values = val
+      elsif @curr_values.is_a?(String)
+        @curr_values = [@curr_values]
+        @curr_values.append(val)
+      else
+        # assume it's an array
+        @curr_values.append(val)
+      end
+    else
+      raise_unexpected_token
+    end
+  end
+
+  ###
+  # strip any quotes (single or double) from the given value
+  # @return the updated value
+  def strip_quotes(val)
+    if (val[0] == "'" && val[-1] == "'") || (val[0] == '"' && val[-1] == '"')
+      val[1..-2]
+    else
+      val
+    end
+  end
+
+  ###
+  # reset the section info
+  # @return None
+  def reset_section
+    @curr_section        = nil
+    @curr_section_lineno = @lineno
+    @curr_vrbl           = nil
+    @curr_values         = nil
+  end
+
+  ###
+  # save the current section that was found
+  # @return None
+  def save_curr_section
+    if @content.include?(@curr_section)
+      raise_err("found duplicate section: \"#{@curr_section}\"")
+    else
+      @content[@curr_section] = {}
+    end
+  end
+
+  ###
+  # save the current assignment that found
+  # @return None
+  def save_curr_assignment
+    if @content[@curr_section].include?(@curr_vrbl)
+      raise_err("found duplicate variable: \"#{@curr_vrbl}\" in section: \"#{@curr_section}\"")
+    else
+      @curr_values                        = '' if @curr_values.nil?
+      @content[@curr_section][@curr_vrbl] = @curr_values
+    end
+  end
+
+  ###
+  # get the next token from the input stream, set token and tok_posn
+  # @return None
+  def get_next_token
+    @token         = @next_token
+    @tok_posn      = @next_tok_posn
+    @next_token    = @rex.next_token
+    @next_tok_posn += 1
+
+    if @token.nil? || @token[0] == :newline
+      @tok_posn      = 0
+      @next_tok_posn = 1
+    end
+
+    return unless !@next_token.nil? && @next_token[0] == :wspace
+    @next_token    = @rex.next_token
+    @next_tok_posn += 1
+  end
+
+  ###
+  # raise an exception indicating an unexpected token was found
+  # @return does not return
+  def raise_unexpected_token
+    raise_err("Unexpected token #{@token}")
+  end
+
+  ###
+  # raise an exception with the given text
+  # @param msg  additional message to print
+  # @return does not return
+  def raise_err(msg)
+    raise("\nline: #{@lineno}] in state: #{@fsm}, #{msg}")
+  end
+
+  ###
+  # print a debug line
+  # @param msg  line to print
+  # @return None
+  def print_dbg(msg)
+    @log_cb.call(format('DBG  line: %3d] %s', @lineno, msg)) if @verbose > 1
+  end
+
+  ###
+  # print a line
+  # @param msg  line to print
+  # @return None
+  def print_line(msg)
+    @log_cb.call(format(' --> line: %3d] %s', @lineno, msg)) if @verbose.positive?
+  end
+
+  ###
+  # default callback to print a simple line to stdout
+  # @param msg  line to print
+  # @return None
+  def _print_raw_line(msg)
+    # skip
+  end
+end

data/lib/rb_cfg_parser.rb

@@ -1,2 +1,2 @@
 # frozen_string_literal: true
-require_relative 'parser/config_parser'
+require_relative 'parser/cfg_parser'

data/lib/version.rb

@@ -1,3 +1,3 @@
 # frozen_string_literal: true
 ## current version
-VERSION = '0.1.0'
+VERSION = '0.1.2'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rb_cfg_parser
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.2
 platform: ruby
 authors:
 - J. Arrizza
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-03-13 00:00:00.000000000 Z
+date: 2025-04-12 00:00:00.000000000 Z
 dependencies: []
 description: ruby gem to parse and load .cfg files
 email: cppgent0@gmail.com
@@ -18,7 +18,9 @@ extra_rdoc_files: []
 files:
 - LICENSE.txt
 - README.md
-- lib/parser/config_parser.rb
+- lib/parser/cfg_lexer.rex.rb
+- lib/parser/cfg_parser.rb
+- lib/parser/pf_config_parser.rb
 - lib/rb_cfg_parser.rb
 - lib/version.rb
 homepage: https://rubygems.org/gems/rb_cfg_parser