csvreader 1.1.4 → 1.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: dd541a30e12622b666a01bc18b5ba80d93cbd1aa
-  data.tar.gz: 773aa117ae2b41bfce6a8cde5df1ed1df4eadeab
+  metadata.gz: 5a26d07e0e618e2cfb6803c8f059e76cf0541a47
+  data.tar.gz: 71ed3dba6b2d0df06e733832b35a709bd427aabc
 SHA512:
-  metadata.gz: b4720613f00b591b3d419f03c06aef8d5e8bb274e4d35e7b1f12f6d14aadb64d1611c7822e3fdc0d2a63c60b653b79a64339aabfd107fb73b14a47bf646c7153
-  data.tar.gz: 3ce20e6925e81e80c6a61e03fd208d852741b7c8d3dd32d045f56b748844782a47810ce041eaa1a8d30f63f282c1655fc6939f7f0ff10294e25ec0be48ede043
+  metadata.gz: 10a4ef973d7c573243fd02c224ee16951a7403ad8472ad5a7b0806c252ec718be3ef404c90e3c32ff41dc2388e441e6a3931226330ce870da54dcff979ced024
+  data.tar.gz: '09030d9645657ef71643c1703209806613b29d6da34aa9c01eb88f3c9a7530c6b2b4953931e5f3789d5fc4a3a2daac9e65317544305dee00347f84cd5e41d22d'

data/lib/csvreader/builder.rb

@@ -1,7 +1,7 @@
 # encoding: utf-8
 
 class CsvReader
-class Builder  ## rename to CsvReaderBuilder - why? why not?
+class Builder
 
 
   def initialize( parser )
@@ -11,53 +11,35 @@ class Builder  ## rename to CsvReaderBuilder - why? why not?
 
   ## (auto-)forward to wrapped parser
   ##   note/fix: not all parser use/have config e.g. ParserTab, ParserFixed, etc.
-  def config() @parser.config; end
-
-
+  ##
   ## todo/fix:
   ##   add parser config (attribute) setter e.g.
   ##   - sep=(value)
   ##   - comment=(value)
   ##   - and so on!!!
+  def config() @parser.config; end
+
 
-  def open( path, mode=nil,
-                 sep: nil,
-                 converters: nil,
-                 width: nil,
-                 parser: @parser, &block )
-      CsvReader.open( path, mode,
-                      sep: sep, converters: converters, width: width,
-                      parser: @parser, &block )
-  end
 
-  def read( path, sep: nil,
-                  converters: nil,
-                  width: nil )
-    CsvReader.read( path,
-                  sep: sep, converters: converters, width: width,
-                  parser: @parser )
+  def open( path, mode=nil, **kwargs, &block )
+    CsvReader.open( path, mode, parser: @parser, **kwargs, &block )
   end
 
-  def header( path, sep: nil, width: nil )
-    CsvReader.header( path,
-                    sep: sep, width: width,
-                    parser: @parser )
+  def read( path, **kwargs )
+    CsvReader.read( path, parser: @parser, **kwargs )
   end
 
-  def foreach( path, sep: nil,
-                     converters: nil, width: nil, &block )
-    CsvReader.foreach( path,
-                     sep: sep, converters: converters, width: width,
-                     parser: @parser, &block )
+  def header( path, **kwargs )
+    CsvReader.header( path, parser: @parser, **kwargs )
   end
 
+  def foreach( path, **kwargs, &block )
+    CsvReader.foreach( path, parser: @parser, **kwargs, &block )
+  end
 
 
-  def parse( data, sep: nil,
-                   converters: nil, width: nil, &block )
-    CsvReader.parse( data,
-                   sep: sep, converters: converters, width: width,
-                   parser: @parser, &block )
+  def parse( str_or_readable, **kwargs, &block )
+    CsvReader.parse( str_or_readable, parser: @parser, **kwargs, &block )
   end
 end # class Builder
 end # class CsvReader
@@ -65,72 +47,38 @@ end # class CsvReader
 
 
 class CsvHashReader
-class Builder  ## rename to CsvHashReaderBuilder - why? why not?
+class Builder
   def initialize( parser )
     @parser = parser
   end
 
   ## (auto-)forward to wrapped parser
   ##   note/fix: not all parser use/have config e.g. ParserTab, ParserFixed, etc.
-  def config() @parser.config; end
-
+  ##
   ## todo/fix:
   ##   add parser config (attribute) setter e.g.
   ##   - sep=(value)
   ##   - comment=(value)
   ##   - and so on!!!
+  def config() @parser.config; end
+
 
 
-  def open( path, mode=nil,
-                 headers: nil,
-                 sep: nil,
-                 converters: nil,
-                 header_converters: nil,
-                 width: nil,
-                 parser: @parser, &block )
-      CsvHashReader.open( path, mode,
-                      headers: headers, sep: sep, converters: converters,
-                      header_converters: header_converters,
-                      width: width,
-                      parser: @parser, &block )
+  def open( path, mode=nil, **kwargs, &block )
+    CsvHashReader.open( path, mode, parser: @parser, **kwargs, &block )
   end
 
-  def read( path, headers: nil,
-                  sep: nil,
-                  converters: nil,
-                  header_converters: nil,
-                  width: nil )
-    CsvHashReader.read( path,
-                  headers: headers,
-                  sep: sep, converters: converters,
-                  header_converters: header_converters,
-                  width: width,
-                  parser: @parser )
+  def read( path, **kwargs )
+    CsvHashReader.read( path, parser: @parser, **kwargs )
   end
 
-  def foreach( path, headers: nil,
-                     sep: nil,
-                     converters: nil,
-                     header_converters: nil, width: nil, &block )
-    CsvHashReader.foreach( path,
-                     headers: headers,
-                     sep: sep, converters: converters,
-                     header_converters: header_converters,
-                     width: width,
-                     parser: @parser, &block )
+  def foreach( path, **kwargs, &block )
+    CsvHashReader.foreach( path, parser: @parser, **kwargs, &block )
   end
 
 
-  def parse( data, headers: nil,
-                   sep: nil,
-                   converters: nil,
-                   header_converters: nil, width: nil, &block )
-    CsvHashReader.parse( data,
-                   headers: headers,
-                   sep: sep, converters: converters,
-                   header_converters: header_converters,
-                   width: width,
-                   parser: @parser, &block )
+  def parse( str_or_readable, **kwargs, &block )
+    CsvHashReader.parse( str_or_readable, parser: @parser, **kwargs, &block )
   end
 end # class Builder
 end # class CsvHashReader

data/lib/csvreader/converter.rb

@@ -110,7 +110,8 @@ def initialize( converters, registry=CONVERTERS )
            add_converter( converter, registry )
         end
      end
-   end
+end
+
 
    def to_a() @converters; end    ## todo: rename to/use converters attribute name - why? why not?
    def empty?() @converters.empty?; end

data/lib/csvreader/parser_tab.rb

@@ -44,7 +44,12 @@ def parse_lines( input, &block )
     ## pp line
 
     # note: trailing empty fields get (auto-)trimmed by split !!!!!!!
-    values = line.split( "\t" )
+    #  Solution!!  change split( "\t" ) to split( "\t", -1 ) 
+    #    If the limit parameter is omitted, trailing null fields are suppressed. 
+    #     If limit is a positive number, at most that number of fields will be returned 
+    #     (if limit is 1, the entire string is returned as the only entry in an array). 
+    #     If negative, there is no limit to the number of fields returned, and trailing null fields are not suppressed.    
+    values = line.split( "\t", -1 )
     ## pp values
 
     ## note: requires block - enforce? how? why? why not?

data/lib/csvreader/reader.rb

@@ -5,15 +5,13 @@ class CsvReader
     def self.open( path, mode=nil,
                    sep: nil,
                    converters: nil,
-                   width: nil,
-                   parser: nil, &block )   ## rename path to filename or name - why? why not?
+                   parser: nil, **kwargs, &block )   ## rename path to filename or name - why? why not?
 
         ## note: default mode (if nil/not passed in) to 'r:bom|utf-8'
         f = File.open( path, mode ? mode : 'r:bom|utf-8' )
-        csv = new(f, sep: sep,
+        csv = new(f, sep:        sep,
                      converters: converters,
-                     width: width,
-                     parser: parser )
+                     parser:     parser,  **kwargs )
 
         # handle blocks like Ruby's open(), not like the (old old) CSV library
         if block_given?
@@ -30,22 +28,21 @@ class CsvReader
 
     def self.read( path, sep: nil,
                          converters: nil,
-                         width: nil,
-                         parser: nil )
+                         parser: nil, **kwargs )
+
         open( path,
               sep: sep,
               converters: converters,
-              width: width,
-              parser: parser ) { |csv| csv.read }
+              parser: parser, **kwargs ) { |csv| csv.read }
     end
 
 
-    def self.header( path, sep: nil, width: nil, parser: nil )   ## use header or headers - or use both (with alias)?
+    def self.header( path, sep: nil, parser: nil, **kwargs )   ## use header or headers - or use both (with alias)?
        # read first lines (only)
        #  and parse with csv to get header from csv library itself
 
        records = []
-       open( path, sep: sep, width: width, parser: parser ) do |csv|
+       open( path, sep: sep, parser: parser, **kwargs ) do |csv|
           csv.each do |record|
             records << record
             break   ## only parse/read first record
@@ -60,8 +57,8 @@ class CsvReader
 
 
     def self.foreach( path, sep: nil,
-                            converters: nil, width: nil, parser: nil, &block )
-      csv = open( path, sep: sep, converters: converters, width: width, parser: parser )
+                            converters: nil, parser: nil, **kwargs, &block )
+      csv = open( path, sep: sep, converters: converters, parser: parser, **kwargs )
 
       if block_given?
         begin
@@ -78,11 +75,10 @@ class CsvReader
     end # method self.foreach
 
 
-    def self.parse( data, sep: nil,
+    def self.parse( str_or_readable, sep: nil,
                           converters: nil,
-                          width: nil,
-                          parser: nil, &block )
-      csv = new( data, sep: sep, converters: converters, width: width, parser: parser )
+                          parser: nil, **kwargs, &block )
+      csv = new( str_or_readable, sep: sep, converters: converters, parser: parser, **kwargs )
 
       if block_given?
         csv.each( &block )  ## note: caller (responsible) must close file!!! - add autoclose - why? why not?
@@ -93,14 +89,15 @@ class CsvReader
 
 
 
+
     ############################
     ## note: only add parse_line convenience helper for default
     ##   always use parse (do NOT/NOT/NOT use parse_line)  - why? why not?
     ##   todo/fix: remove parse_line!!!
-    def self.parse_line( data, sep: nil,
-                               converters: nil, width: nil )
+    def self.parse_line( str_or_readable, sep: nil,
+                               converters: nil, **kwargs )
        records = []
-       parse( data, sep: sep, converters: converters, width: width ) do |record|
+       parse( str_or_readable, sep: sep, converters: converters, **kwargs ) do |record|
          records << record
          break   # only parse first record
        end
@@ -110,15 +107,15 @@ class CsvReader
 
 
 
-    def initialize( data, sep: nil, converters: nil, width: nil, parser: nil )
-          raise ArgumentError.new( "Cannot parse nil as CSV" )  if data.nil?
+    def initialize( str_or_readable, sep: nil, converters: nil, parser: nil, **kwargs )
+          raise ArgumentError.new( "Cannot parse nil as CSV" )  if str_or_readable.nil?
           ## todo: use (why? why not) - raise ArgumentError, "Cannot parse nil as CSV"     if data.nil?
 
           # create the IO object we will read from
-          @io = data.is_a?(String) ? StringIO.new(data) : data
+          @io = str_or_readable.is_a?(String) ? StringIO.new(str_or_readable) : str_or_readable
 
-          @sep   = sep     # (optional) for ParserStd, ParserStrict
-          @width = width   # (optional) for ParserFixed
+          @sep    = sep           # (optional) for ParserStd, ParserStrict
+          @kwargs = kwargs        # e.g.  (optional) :width for ParserFixed
 
           @converters  = Converter.create_converters( converters )
 
@@ -150,7 +147,11 @@ class CsvReader
          ##  todo/fix: change sep keyword to "known" classes!!!!
          kwargs[:sep]   = @sep    if @sep && @parser.respond_to?( :'sep=' )
 
-         kwargs[:width] = @width  if @parser.is_a?( ParserFixed )
+
+         kwargs[:width] = @kwargs[:width]    if @parser.is_a?( ParserFixed )
+
+         ##  todo/fix: print warning about unused / unknown kwargs!!!!!
+
 
          ## check array / pipeline of converters is empty (size=0 e.g. is [])
          if @converters.empty?

data/lib/csvreader/reader_hash.rb

@@ -15,8 +15,7 @@ def self.open( path, mode=nil,
                sep: nil,
                converters: nil,
                header_converters: nil,
-               width: nil,
-               parser: nil, &block )   ## rename path to filename or name - why? why not?
+               parser: nil, **kwargs, &block )   ## rename path to filename or name - why? why not?
 
     ## note: default mode (if nil/not passed in) to 'r:bom|utf-8'
     f = File.open( path, mode ? mode : 'r:bom|utf-8' )
@@ -24,8 +23,7 @@ def self.open( path, mode=nil,
                  sep: sep,
                  converters: converters,
                  header_converters: header_converters,
-                 width: width,
-                 parser: parser )
+                 parser: parser, **kwargs )
 
     # handle blocks like Ruby's open(), not like the (old old) CSV library
     if block_given?
@@ -44,15 +42,14 @@ def self.read( path, headers: nil,
                      sep: nil,
                      converters: nil,
                      header_converters: nil,
-                     width: nil,
-                     parser: nil )
+                     parser: nil,
+                     **kwargs )
     open( path,
           headers: headers,
           sep: sep,
           converters: converters,
           header_converters: header_converters,
-          width: width,
-          parser: parser ) { |csv| csv.read }
+          parser: parser, **kwargs ) { |csv| csv.read }
 end
 
 
@@ -61,15 +58,14 @@ def self.foreach( path, headers: nil,
                         sep: nil,
                         converters: nil,
                         header_converters: nil,
-                        width: nil,
-                        parser: nil, &block )
+                        parser: nil, **kwargs, &block )
   csv = open( path,
               headers: headers,
               sep: sep,
               converters: converters,
               header_converters: header_converters,
-              width: width,
-              parser: parser )
+              parser: parser,
+              **kwargs )
 
   if block_given?
     begin
@@ -86,19 +82,17 @@ def self.foreach( path, headers: nil,
 end # method self.foreach
 
 
-def self.parse( data, headers: nil,
+def self.parse( str_or_readable, headers: nil,
                       sep: nil,
                       converters: nil,
                       header_converters: nil,
-                      width: nil,
-                      parser: nil, &block )
-  csv = new( data,
+                      parser: nil, **kwargs, &block )
+  csv = new( str_or_readable,
              headers: headers,
              sep: sep,
              converters: converters,
              header_converters: header_converters,
-             width: width,
-             parser: parser )
+             parser: parser, **kwargs )
 
   if block_given?
     csv.each( &block )  ## note: caller (responsible) must close file!!! - add autoclose - why? why not?
@@ -111,24 +105,24 @@ end # method self.parse
 
 
 
-def initialize( data, headers: nil, sep: nil,
+def initialize( str_or_readable, headers: nil, sep: nil,
                       converters: nil,
                       header_converters: nil,
-                      width: nil,
-                      parser: nil )
-      raise ArgumentError.new( "Cannot parse nil as CSV" )  if data.nil?
+                      parser: nil,
+                      **kwargs )
+      raise ArgumentError.new( "Cannot parse nil as CSV" )  if str_or_readable.nil?
       ## todo: use (why? why not) - raise ArgumentError, "Cannot parse nil as CSV"     if data.nil?
 
       # create the IO object we will read from
-      @io = data.is_a?(String) ? StringIO.new(data) : data
+      @io = str_or_readable.is_a?(String) ? StringIO.new(str_or_readable) : str_or_readable
 
       ## pass in headers as array e.g. ['A', 'B', 'C']
       ##  double check: run header_converters on passed in headers?
       ##    for now - do NOT auto-convert passed in headers - keep them as-is (1:1)
       @names = headers ? headers : nil
 
-      @sep   = sep
-      @width = width
+      @sep    = sep
+      @kwargs = kwargs
 
       @converters        = Converter.create_converters( converters )
       @header_converters = Converter.create_header_converters( header_converters )
@@ -170,7 +164,7 @@ def_delegators :@io,
      ##  todo/fix: change sep keyword to "known" classes!!!!
      kwargs[:sep] = @sep    if @sep && @parser.respond_to?( :'sep=' )
 
-     kwargs[:width] = @width  if @parser.is_a?( ParserFixed )
+     kwargs[:width] = @kwargs[:width]    if @parser.is_a?( ParserFixed )
 
 
      @parser.parse( @io, kwargs ) do |raw_values|     # sep: sep

data/lib/csvreader/version.rb

@@ -6,7 +6,7 @@ class CsvReader   ## note: uses a class for now - change to module - why? why no
   module Version
     MAJOR = 1    ## todo: namespace inside version or something - why? why not??
     MINOR = 1
-    PATCH = 4
+    PATCH = 5
 
     ## self.to_s  - why? why not?
   end

data/test/test_parser.rb

@@ -11,7 +11,7 @@ class TestParser < MiniTest::Test
 
 
 def parser
-  parser = CsvReader::Parser::DEFAULT
+  CsvReader::Parser::DEFAULT
 end
 
 

data/test/test_parser_directive.rb

@@ -11,7 +11,7 @@ class TestParserDirective < MiniTest::Test
 
 
 def parser
-  parser = CsvReader::Parser::DEFAULT
+  CsvReader::Parser::DEFAULT
 end
 
 

data/test/test_parser_meta.rb

@@ -11,7 +11,7 @@ class TestParserMeta < MiniTest::Test
 
 
 def parser
-  parser = CsvReader::Parser::DEFAULT
+  CsvReader::Parser::DEFAULT
 end
 
 

data/test/test_parser_tab.rb

@@ -11,7 +11,7 @@ class TestParserTab < MiniTest::Test
 
 
 def parser
-  parser = CsvReader::Parser::TAB
+  CsvReader::Parser::TAB
 end
 
 
@@ -33,11 +33,12 @@ def test_parse
 end
 
 def test_parse_empties
-  # note: trailing empty fields get (auto-)trimmed !!!!!!!
-  assert_equal [[]],                parser.parse( "\t\t" )
-  assert_equal [[]],                parser.parse( "\t\t\t\t" )
-  assert_equal [["1"]],             parser.parse( "1\t\t" )
-  assert_equal [["1"]],             parser.parse( "1\t\t\t\t" )
+  # note: trailing empty fields got (auto-)trimmed !!!!!!!;
+  #        add missing -1 limit option :-) now works
+  assert_equal [["","",""]],        parser.parse( "\t\t" )
+  assert_equal [["","","","",""]],  parser.parse( "\t\t\t\t" )
+  assert_equal [["1","",""]],       parser.parse( "1\t\t" )
+  assert_equal [["1","","","",""]], parser.parse( "1\t\t\t\t" )
   assert_equal [["","","3"]],       parser.parse( "\t\t3" )
   assert_equal [["","","","","5"]], parser.parse( "\t\t\t\t5" )
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csvreader
 version: !ruby/object:Gem::Version
-  version: 1.1.4
+  version: 1.1.5
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-10-27 00:00:00.000000000 Z
+date: 2018-11-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc