statsailr 0.7.2 → 0.7.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 428f469213d12c0613eb7eeab1690cad296ac94cff448bea96f140b55f2d8a24
-  data.tar.gz: 684382167f17c762e22c752ac3303ec6a5666cbf83f02ef672f515167e43d2b6
+  metadata.gz: 3404e4a53509861318d70a8309cf54fb82326f98d3715893ac3a1fe447eb94f5
+  data.tar.gz: cd48566b46c5ea5bdfd9fb38beb2381095f857b58ad1d0cbf2998ad5de4dded9
 SHA512:
-  metadata.gz: 64352807559d052da5415f75f0917f629146cf5b9671bdce7b294720795404b954f16569930d5ad6d68c40465a46efc2ab2a2d9e4d5d9f18b2673926d98045e5
-  data.tar.gz: 4bf58f63503187e3e8a33aae1485ef226123c03e8741593c2f6cf434e90d24b055d119b921edf8ccc69f43e5d93398ec46fcb6067eb2f1be4c9cd9f4c192361f
+  metadata.gz: f4ec746898a33f909803d6dbc4fc284818e3a65ba89c1e93199b0582c061e85ca6be472f77abdde9b9c9937bb43315e3ac8e9f4caa8e9d947b062c7c098c048d
+  data.tar.gz: ba926958960340cbd9ad2e278ef78841509ca2db771a1cab93def58b6b8eb305e7b40b29adb8410d8d48662c2e3568868183f739f89ce02937928f0f7d9a6010

data/README.md

@@ -254,7 +254,7 @@ END
             + How main argument part is parsed varies on each instruction. This is defined in main_arg_and_how_to_treat variable in setting.
         + opt_args
             + Optional arguments. Values specified in opt_args are also passed to R function's argument.
-            + opt_args part consists of (a) key-value(s) or key(s).
+            + opt_args part consists of (a) key-value(s).
             + Internally, this argument parsing is conducted by methods in STSBlockParseProcOpts.
 
 

data/lib/statsailr/block_builder/sts_block.rb

@@ -1,8 +1,82 @@
 require "r_bridge"
 require_relative "./sts_block_parse_proc_opts.rb"
 
+module QuotedStringSupport
+  def interpret_escape_sequences(str)
+    # This deals with escape sequences in double quoted string literals
+    # The behavior should be same as libsailr (or datasailr)
+    new_str = ""
+    str_array = str.split(//)
+    idx = 0
+    while( idx < str_array.size) do
+      c = str_array[idx]
+      if(c == "\\")
+        idx = idx + 1
+        c = str_array[idx]
+        raise "Tokenizer error: double quoted string literal should never end with \\" if idx >= str_array.size
+        case c
+        when 't'
+          new_str << "\t"
+        when 'n'
+          new_str << "\n"
+        when 'r'
+          new_str << "\r"
+        when "\\"
+          new_str << "\\"
+        when "\'"
+          new_str << "\'"
+        when "\""
+          new_str << "\""
+        when '?'
+          new_str << '?'
+        else
+          new_str << c
+        end
+      else
+        new_str << c
+      end
+      idx = idx + 1
+    end
+    return new_str
+  end
+
+  def escape_backslashes(str)
+    str.gsub("\\", "\\\\")
+  end
+end
+
 module BlockSupport
-  def type_adjust(obj , type)
+  include QuotedStringSupport
+  class QuotedStringR
+    include QuotedStringSupport
+    def initialize(str, quote_type)
+      raise ":dq or :sq should be specified for quote_type" unless [:dq, :sq].include? quote_type
+      @ori_str = str
+      @quote_type = quote_type
+    end
+
+    def to_s
+      to_s_for_r_bridge
+    end
+
+    def to_s_for_r_bridge
+      if @quote_type == :dq
+        interpret_escape_sequences( @ori_str )
+      elsif
+        @ori_str
+      end
+    end
+
+    def to_s_for_r_parsing
+      if @quote_type == :dq
+        %q{"} + @ori_str + %q{"}
+      elsif @quote_type == :sq
+        %q{'} + escape_backslashes( @ori_str ) + %q{'}
+      end
+    end
+  end
+
+  def type_adjust(obj , type , *opts)
     case type
     when :ident
       if obj.is_a?(String)
@@ -22,6 +96,28 @@ module BlockSupport
       else
         raise "GramNode with inconsistent type(#{type.to_s}) and object(#{obj.class})"
       end
+    when :sq_string
+      if obj.is_a?(String)
+        unless opts.include?( :retain_input_string )
+          # default behavior
+          result = obj
+        else
+          result = QuotedStringR.new( obj, :sq )
+        end
+      else
+        raise "GramNode with inconsistent type(#{type.to_s}) and object(#{obj.class})"
+      end
+    when :dq_string
+      if obj.is_a?(String)
+        unless opts.include?( :retain_input_string )
+          # default behavior
+          result = interpret_escape_sequences( obj )
+        else
+          result = QuotedStringR.new( obj, :dq )
+        end
+      else
+        raise "GramNode with inconsistent type(#{type.to_s}) and object(#{obj.class})"
+      end
     when :sign
       if obj.is_a?(String)
         result = RBridge::SignR.new(obj)
@@ -137,10 +233,16 @@ class ProcBlock
           idx = 0
           while idx < proc_stmt_arg_ori.size() do
             elem = proc_stmt_arg_ori[idx]
-            if( elem.type == :sign && elem.e1 == "/" )
-              break
+            next_elem = proc_stmt_arg_ori[idx + 1]
+            next_next_elem = proc_stmt_arg_ori[idx + 2]
+            if(elem.type == :sign && elem.e1 == "/" ) then
+               if( ! next_elem.nil? && next_elem.type == :ident &&   # After /, optional arguments start
+                   ! next_next_elem.nil? && next_next_elem.type == :sign && next_next_elem.e1 == "=") ||
+                   next_elem.nil? then  # After /, there is nothing
+                 break
+               end
             else
-              x = type_adjust( elem.e1, elem.type )
+              x = type_adjust( elem.e1, elem.type, :retain_input_string )
               proc_stmt_arg << x
               idx = idx + 1
             end

data/lib/statsailr/block_builder/sts_block_parse_proc_opts.rb

@@ -50,7 +50,6 @@ class STSBlockParseProcOpts
 # arg_opt  : IDENT = primary
 #          | IDENT = array
 #          | IDENT = func 
-#          | IDENT
 #
 # parimary : STRING
 #          | NUM
@@ -87,15 +86,15 @@ class STSBlockParseProcOpts
         else
           opt_value = ident() # According to BNF, this should be parimary(). However, ident() is more direct and makes sense here.
         end
-      elsif [:string, :num].include? peek.type
+      elsif [:dq_string, :sq_string, :num].include? peek.type
          next_token()
          opt_value = primary()
       else
         p current_token()
-        raise "the token should be :ident or primaries such as :ident, :num and :string after = . Current token: " + current_token().type.to_s
+        raise "the token should be :ident or primaries such as :ident, :num and :string after = . Next token: " + peek.type.to_s
       end
     else
-      opt_value = true
+      raise "proc instruction optional argumeents should be in the form of a sequence of 'key = value'"
     end
     @result_hash[opt_key.to_s] = opt_value
   end
@@ -127,12 +126,14 @@ class STSBlockParseProcOpts
     case current_token.type
     when :ident
       return ident()
-    when :string
+    when :dq_string
+      return string()
+    when :sq_string
       return string()
     when :num
       return num()
     else
-      raise "the current token should be :ident, :string or :num."
+      raise "the current token should be :ident, :dq_string, :sq_string or :num."
     end
   end
 
@@ -155,8 +156,13 @@ class STSBlockParseProcOpts
   end
 
   def string()
-    raise "the current token should be string" if current_token.type != :string 
-    return type_adjust( current_token.e1, :string)
+    if (current_token.type != :dq_string)
+      return type_adjust( current_token.e1, :dq_string)
+    elsif (current_token.type != :sq_string)
+      return type_adjust( current_token.e1, :sq_string)
+    else
+      raise "the current token should be string (:dq_string or :sq_string)"
+    end
   end
 
   def num()

data/lib/statsailr/block_to_r/proc_setting_support/proc_block_finalizer.rb

@@ -0,0 +1,10 @@
+class ProcBlockFinalizer
+  attr :enabled, true
+  def initialize
+    @enabled = false
+  end
+
+  def enabled?
+    return @enabled
+  end
+end

data/lib/statsailr/block_to_r/proc_setting_support/proc_opt_validator.rb

@@ -18,7 +18,7 @@ class ProcOptValidator
             raise "#{opt_name} is required for this PROC option"
           end
         end
-        if ! validator["is_a"].nil?
+        if ! param_manager.param_hash[opt_name].nil? && ! validator["is_a"].nil?
           if validator["is_a"].is_a?(Array)
             if ! validator["is_a"].include? class_name_in_param_manager
               raise "#{opt_name} needs to be one of #{validator["is_a"].join("|")}, but #{class_name_in_param_manager} is assigned"
@@ -30,7 +30,7 @@ class ProcOptValidator
           end
 
         end
-        if ! validator["as"].nil?
+        if ! param_manager.param_hash[opt_name].nil? && ! validator["as"].nil?
           if validator["as"] != class_name_in_param_manager
             case validator["as"]
             when "SymbolR"

data/lib/statsailr/block_to_r/proc_setting_support/proc_setting_module.rb

@@ -1,10 +1,12 @@
 require "pathname"
 require_relative("./proc_opt_validator.rb")
+require_relative("./proc_block_finalizer.rb")
 
 module ProcSettingModule
   def self.included base
     base.extend ClassMethods
     base.instance_variable_set(:@validator, ProcOptValidator.new())
+    base.instance_variable_set(:@finalizer, ProcBlockFinalizer.new())
     base.send :include, InstanceMethods
   end
 
@@ -12,6 +14,8 @@ module ProcSettingModule
     def extend_object( extender )
       extender.instance_variable_set(:@validator, @validator)
       extender.singleton_class.__send__( :attr_accessor, :validator)
+      extender.instance_variable_set(:@finalizer, @finalizer)
+      extender.singleton_class.__send__( :attr_accessor, :finalizer)
       super
     end
 
@@ -36,6 +40,14 @@ module ProcSettingModule
     def validator
       @validator
     end
+
+    def finalizer_enabled
+      @finalizer.enabled = true
+    end
+
+    def finalizer
+      @finalizer
+    end
   end
 
   module InstanceMethods

data/lib/statsailr/block_to_r/sts_block_to_r.rb

@@ -69,6 +69,8 @@ require_relative("proc_setting_support/proc_setting_module.rb")
 
 module ProcBlockToR
   include BlockToRSupport
+  FINALIZER_NAME = "finalizer"
+
   def self.create_lazy_funcs( blk , proc_setting_manager )
     proc_command = blk.command
     param_manager = RBridge::RParamManager.new( blk.opts )
@@ -90,6 +92,13 @@ module ProcBlockToR
     proc_lazy_funcs_with_print_result_opts = proc_stmts.map(){|proc_stmt|
       lzf_gen.gen_lazy_func( proc_command, proc_stmt, param_manager )
     }
+
+    finalizer = lzf_gen.finalizer
+    if finalizer.enabled?
+      finalizer_func = lzf_gen.gen_lazy_func( proc_command , [ FINALIZER_NAME, "", nil] , param_manager )
+      proc_lazy_funcs_with_print_result_opts.push( finalizer_func )
+    end
+
     return proc_lazy_funcs_with_print_result_opts
   end
 end

data/lib/statsailr/block_to_r/sts_lazy_func_gen.rb

@@ -40,6 +40,132 @@ module LazyFuncGeneratorSettingUtility
     return RBridge.create_strvec( ary.map(){|elem| elem.to_s } )
   end
 
+  def read_symbols_or_functions_as_strvec(ary)
+    deapth_ary = Array.new( ary.size )
+    idx = 0
+    last_idx = ary.size - 1
+    deapth = 0
+    while( idx <= last_idx )
+      if( ary[idx].is_a?(RBridge::SymbolR) && (ary[idx + 1].is_a?(RBridge::SignR) && ary[idx + 1].to_s == "("))
+        # function starts
+        deapth_ary[idx] = deapth
+        deapth = deapth + 1
+        idx = idx + 1
+        deapth_ary[idx] = deapth
+      elsif( ary[idx].is_a?(RBridge::SignR) && ary[idx].to_s == "(")
+        # parenthesis starts
+        deapth = deapth + 1
+        deapth_ary[idx] = deapth
+      elsif( ary[idx].is_a?(RBridge::SignR) && ary[idx].to_s == ")")
+        # parenthesis ends or function ends
+        deapth_ary[idx] = deapth
+        deapth = deapth - 1
+      else
+        deapth_ary[idx] = deapth
+      end
+      idx = idx + 1
+    end
+
+    result_ary = []
+    ary.zip( deapth_ary).each(){|elem, deapth|
+      if elem.respond_to? :to_s_for_r_parsing
+        elem_str = elem.to_s_for_r_parsing
+      else
+        elem_str = elem.to_s
+      end
+
+      if( deapth == 0)
+        result_ary.push( elem_str )
+      else
+        result_ary.last << " " << elem_str
+      end
+    }
+
+    return RBridge.create_strvec( result_ary )
+  end
+
+  def read_named_args_as_named_strvec(ary)
+    arg_num_ary = Array.new( ary.size )
+    deapth_ary = Array.new( ary.size )
+    idx = 0
+    last_idx = ary.size - 1
+    arg_num = nil
+    deapth = nil
+
+    while( idx <= last_idx )
+      if( idx == 0 )
+        # name starts
+        unless ( deapth.nil? && ary[idx].is_a?(RBridge::SymbolR) && (ary[idx + 1].is_a?(RBridge::SignR) && ary[idx + 1].to_s == "="))
+          raise "read_named_args_as_named_strvec requires an argument to start with name=expr"
+        end
+        arg_num = 0
+        deapth = 0
+      elsif( deapth == 0 && ary[idx].is_a?(RBridge::SymbolR) && (ary[idx + 1].is_a?(RBridge::SignR) && ary[idx + 1].to_s == "="))
+        # name starts
+        arg_num = arg_num + 1
+      elsif( ary[idx].is_a?(RBridge::SymbolR) && (ary[idx + 1].is_a?(RBridge::SignR) && ary[idx + 1].to_s == "("))
+        # function starts
+        deapth_ary[idx] = deapth
+        arg_num_ary[idx] = arg_num
+        deapth = deapth + 1
+        idx = idx + 1
+        deapth_ary[idx] = deapth
+      elsif( ary[idx].is_a?(RBridge::SignR) && ary[idx].to_s == "(")
+        # parenthesis starts
+        deapth = deapth + 1
+        deapth_ary[idx] = deapth
+      elsif( ary[idx].is_a?(RBridge::SignR) && ary[idx].to_s == ")")
+        # parenthesis ends or function ends
+        deapth_ary[idx] = deapth
+        deapth = deapth - 1
+      else
+        deapth_ary[idx] = deapth
+      end
+      arg_num_ary[idx] = arg_num
+      idx = idx + 1
+    end
+
+    result_ary = []
+    name_ary = []
+    prev_arg_num = -1
+    idx = 0
+    elem_arg_num_ary = ary.zip( arg_num_ary )
+    while( idx < elem_arg_num_ary.size )
+      elem = ary[idx]
+      arg_num = arg_num_ary[idx]
+      if elem.respond_to? :to_s_for_r_parsing
+        elem_str = elem.to_s_for_r_parsing
+      else
+        elem_str = elem.to_s
+      end
+
+      if( arg_num != prev_arg_num ) # starts new 'name=expr'
+        name_ary.push elem_str
+        idx = idx + 1
+        if( ary[idx].to_s != "=" )
+          raise "An argument should be in the form of 'name=expr'"
+        end
+      else
+        if( result_ary[arg_num].nil? )
+          unless result_ary.size == arg_num
+            raise "arg_num is not an appropriate number."
+          end
+          result_ary[arg_num] = [elem_str]
+        else
+          result_ary[arg_num].push( elem_str )
+        end
+      end
+      idx = idx + 1
+      prev_arg_num = arg_num
+    end
+
+    result_vec = RBridge.create_strvec( result_ary.map(){|ary| ary.join(" ") } )
+    name_vec = RBridge.create_strvec( name_ary )
+    add_name_func = RBridge.create_ns_function_call("stats", "setNames", {"object" => result_vec, "nm" => name_vec })
+    result_name_vec = RBridge.exec_function( add_name_func )
+    return result_name_vec
+  end
+
   def result( name , *addl )
     if addl.empty?
       return RBridge::RResultName.new(name)
@@ -59,6 +185,10 @@ module LazyFuncGeneratorSettingUtility
     return RBridge::RResultPrevious.new( default_obj )
   end
 
+  def previous_inst_name()
+    return RBridge::RInstPrevious.new()
+  end
+
   def r_obj( val )
     return RBridge.convert_to_r_object( val )
   end