csv 3.2.3 → 3.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 915b3ed5a51bf4836f08f7bb06efc3b07bdc90e09209a5253092130e2cad2ab6
-  data.tar.gz: 6bce2e39329afcf200691b4b2f422b6a48d45da66368f5d5e136e0c761cd6217
+  metadata.gz: 3ef88fc9b205f8f64c5e817b22f121d5d03534c155cb8d27dc9d87aa62e6b7e0
+  data.tar.gz: e12b86cee946837a96ae609314a50246e2135fab855dca58e800de1ddc50e524
 SHA512:
-  metadata.gz: 5c1434c8e91c16de40d19d4d1200f193248e786720b67f2bbecf26a481859fe814b8cbaa02d22027668ff02588541266c8ff5d00b9fc1cfc2163b358b8e9ece9
-  data.tar.gz: 1978e933549049129f0ec99e80a10f2838b3c75a282103aa177d8421fe7589d428308e2786b29a961a4a7a5565ede77e3b1ef44ba8f4bc91b593a5a884ded7aa
+  metadata.gz: d663d0917d63315e4fc5802f9538727731f39ea06997adea485f5f137f37639f0791db1f9697476e7d0c4a8048a0339b9e4fb7aecd79f3ec8ee8eb24a4cb676e
+  data.tar.gz: f9d22fe50d227b8f8ca0d075ed0fbf1f39a10bf59a1adb68835fede727f3d1dfd1d2f88754caa1098fe9c24df738c71b29ae5fc3080a25d80df484f76530344e

data/NEWS.md

@@ -1,5 +1,46 @@
 # News
 
+## 3.2.4 - 2022-08-22
+
+### Improvements
+
+  * Cleaned up internal implementations.
+    [[GitHub#249](https://github.com/ruby/csv/pull/249)]
+    [[GitHub#250](https://github.com/ruby/csv/pull/250)]
+    [[GitHub#251](https://github.com/ruby/csv/pull/251)]
+    [Patch by Mau Magnaguagno]
+
+  * Added support for RFC 3339 style time.
+    [[GitHub#248](https://github.com/ruby/csv/pull/248)]
+    [Patch by Thierry Lambert]
+
+  * Added support for transcoding String CSV. Syntax is
+    `from-encoding:to-encoding`.
+    [[GitHub#254](https://github.com/ruby/csv/issues/254)]
+    [Reported by Richard Stueven]
+
+  * Added quoted information to `CSV::FieldInfo`.
+    [[GitHub#254](https://github.com/ruby/csv/pull/253)]
+    [Reported by Hirokazu SUZUKI]
+
+### Fixes
+
+  * Fixed a link in documents.
+    [[GitHub#244](https://github.com/ruby/csv/pull/244)]
+    [Patch by Peter Zhu]
+
+### Thanks
+
+  * Peter Zhu
+
+  * Mau Magnaguagno
+
+  * Thierry Lambert
+
+  * Richard Stueven
+
+  * Hirokazu SUZUKI
+
 ## 3.2.3 - 2022-04-09
 
 ### Improvements

data/lib/csv/fields_converter.rb

@@ -44,7 +44,7 @@ class CSV
       @converters.empty?
     end
 
-    def convert(fields, headers, lineno)
+    def convert(fields, headers, lineno, quoted_fields)
       return fields unless need_convert?
 
       fields.collect.with_index do |field, index|
@@ -63,7 +63,8 @@ class CSV
             else
               header = nil
             end
-            field = converter[field, FieldInfo.new(index, lineno, header)]
+            quoted = quoted_fields[index]
+            field = converter[field, FieldInfo.new(index, lineno, header, quoted)]
           end
           break unless field.is_a?(String)  # short-circuit pipeline for speed
         end

data/lib/csv/parser.rb

@@ -2,15 +2,10 @@
 
 require "strscan"
 
-require_relative "delete_suffix"
 require_relative "input_record_separator"
-require_relative "match_p"
 require_relative "row"
 require_relative "table"
 
-using CSV::DeleteSuffix if CSV.const_defined?(:DeleteSuffix)
-using CSV::MatchP if CSV.const_defined?(:MatchP)
-
 class CSV
   # Note: Don't use this class directly. This is an internal class.
   class Parser
@@ -763,9 +758,10 @@ class CSV
       case headers
       when Array
         @raw_headers = headers
+        quoted_fields = [false] * @raw_headers.size
         @use_headers = true
       when String
-        @raw_headers = parse_headers(headers)
+        @raw_headers, quoted_fields = parse_headers(headers)
         @use_headers = true
       when nil, false
         @raw_headers = nil
@@ -775,21 +771,28 @@ class CSV
         @use_headers = true
       end
       if @raw_headers
-        @headers = adjust_headers(@raw_headers)
+        @headers = adjust_headers(@raw_headers, quoted_fields)
       else
         @headers = nil
       end
     end
 
     def parse_headers(row)
-      CSV.parse_line(row,
-                     col_sep:    @column_separator,
-                     row_sep:    @row_separator,
-                     quote_char: @quote_character)
+      quoted_fields = []
+      converter = lambda do |field, info|
+        quoted_fields << info.quoted?
+        field
+      end
+      headers = CSV.parse_line(row,
+                               col_sep:    @column_separator,
+                               row_sep:    @row_separator,
+                               quote_char: @quote_character,
+                               converters: [converter])
+      [headers, quoted_fields]
     end
 
-    def adjust_headers(headers)
-      adjusted_headers = @header_fields_converter.convert(headers, nil, @lineno)
+    def adjust_headers(headers, quoted_fields)
+      adjusted_headers = @header_fields_converter.convert(headers, nil, @lineno, quoted_fields)
       adjusted_headers.each {|h| h.freeze if h.is_a? String}
       adjusted_headers
     end
@@ -933,9 +936,11 @@ class CSV
         if line.empty?
           next if @skip_blanks
           row = []
+          quoted_fields = []
         else
           line = strip_value(line)
           row = line.split(@split_column_separator, -1)
+          quoted_fields = [false] * row.size
           if @max_field_size
             row.each do |column|
               validate_field_size(column)
@@ -949,7 +954,7 @@ class CSV
           end
         end
         @last_line = original_line
-        emit_row(row, &block)
+        emit_row(row, quoted_fields, &block)
       end
     end
 
@@ -971,25 +976,30 @@ class CSV
             next
           end
           row = []
+          quoted_fields = []
         elsif line.include?(@cr) or line.include?(@lf)
           @scanner.keep_back
           @need_robust_parsing = true
           return parse_quotable_robust(&block)
         else
           row = line.split(@split_column_separator, -1)
+          quoted_fields = []
           n_columns = row.size
           i = 0
           while i < n_columns
             column = row[i]
             if column.empty?
+              quoted_fields << false
               row[i] = nil
             else
               n_quotes = column.count(@quote_character)
               if n_quotes.zero?
+                quoted_fields << false
                 # no quote
               elsif n_quotes == 2 and
                    column.start_with?(@quote_character) and
                    column.end_with?(@quote_character)
+                quoted_fields << true
                 row[i] = column[1..-2]
               else
                 @scanner.keep_back
@@ -1004,13 +1014,14 @@ class CSV
         @scanner.keep_drop
         @scanner.keep_start
         @last_line = original_line
-        emit_row(row, &block)
+        emit_row(row, quoted_fields, &block)
       end
       @scanner.keep_drop
     end
 
     def parse_quotable_robust(&block)
       row = []
+      quoted_fields = []
       skip_needless_lines
       start_row
       while true
@@ -1024,20 +1035,24 @@ class CSV
         end
         if parse_column_end
           row << value
+          quoted_fields << @quoted_column_value
         elsif parse_row_end
           if row.empty? and value.nil?
-            emit_row([], &block) unless @skip_blanks
+            emit_row([], [], &block) unless @skip_blanks
           else
             row << value
-            emit_row(row, &block)
+            quoted_fields << @quoted_column_value
+            emit_row(row, quoted_fields, &block)
             row = []
+            quoted_fields = []
           end
           skip_needless_lines
           start_row
         elsif @scanner.eos?
           break if row.empty? and value.nil?
           row << value
-          emit_row(row, &block)
+          quoted_fields << @quoted_column_value
+          emit_row(row, quoted_fields, &block)
           break
         else
           if @quoted_column_value
@@ -1141,7 +1156,7 @@ class CSV
       if (n_quotes % 2).zero?
         quotes[0, (n_quotes - 2) / 2]
       else
-        value = quotes[0, (n_quotes - 1) / 2]
+        value = quotes[0, n_quotes / 2]
         while true
           quoted_value = @scanner.scan_all(@quoted_value)
           value << quoted_value if quoted_value
@@ -1165,11 +1180,9 @@ class CSV
           n_quotes = quotes.size
           if n_quotes == 1
             break
-          elsif (n_quotes % 2) == 1
-            value << quotes[0, (n_quotes - 1) / 2]
-            break
           else
             value << quotes[0, n_quotes / 2]
+            break if (n_quotes % 2) == 1
           end
         end
         value
@@ -1205,18 +1218,15 @@ class CSV
 
     def strip_value(value)
       return value unless @strip
-      return nil if value.nil?
+      return value if value.nil?
 
       case @strip
       when String
-        size = value.size
-        while value.start_with?(@strip)
-          size -= 1
-          value = value[1, size]
+        while value.delete_prefix!(@strip)
+          # do nothing
         end
-        while value.end_with?(@strip)
-          size -= 1
-          value = value[0, size]
+        while value.delete_suffix!(@strip)
+          # do nothing
         end
       else
         value.strip!
@@ -1239,22 +1249,22 @@ class CSV
       @scanner.keep_start
     end
 
-    def emit_row(row, &block)
+    def emit_row(row, quoted_fields, &block)
       @lineno += 1
 
       raw_row = row
       if @use_headers
         if @headers.nil?
-          @headers = adjust_headers(row)
+          @headers = adjust_headers(row, quoted_fields)
           return unless @return_headers
           row = Row.new(@headers, row, true)
         else
           row = Row.new(@headers,
-                        @fields_converter.convert(raw_row, @headers, @lineno))
+                        @fields_converter.convert(raw_row, @headers, @lineno, quoted_fields))
         end
       else
         # convert fields, if needed...
-        row = @fields_converter.convert(raw_row, nil, @lineno)
+        row = @fields_converter.convert(raw_row, nil, @lineno, quoted_fields)
       end
 
       # inject unconverted fields and accessor, if requested...

data/lib/csv/row.rb

@@ -703,7 +703,7 @@ class CSV
     # by +index_or_header+ and +specifiers+.
     #
     # The nested objects may be instances of various classes.
-    # See {Dig Methods}[https://docs.ruby-lang.org/en/master/doc/dig_methods_rdoc.html].
+    # See {Dig Methods}[https://docs.ruby-lang.org/en/master/dig_methods_rdoc.html].
     #
     # Examples:
     #   source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"

data/lib/csv/version.rb

@@ -2,5 +2,5 @@
 
 class CSV
   # The version of the installed library.
-  VERSION = "3.2.3"
+  VERSION = "3.2.4"
 end

data/lib/csv/writer.rb

@@ -1,11 +1,8 @@
 # frozen_string_literal: true
 
 require_relative "input_record_separator"
-require_relative "match_p"
 require_relative "row"
 
-using CSV::MatchP if CSV.const_defined?(:MatchP)
-
 class CSV
   # Note: Don't use this class directly. This is an internal class.
   class Writer
@@ -42,7 +39,10 @@ class CSV
       @headers ||= row if @use_headers
       @lineno += 1
 
-      row = @fields_converter.convert(row, nil, lineno) if @fields_converter
+      if @fields_converter
+        quoted_fields = [false] * row.size
+        row = @fields_converter.convert(row, nil, lineno, quoted_fields)
+      end
 
       i = -1
       converted_row = row.collect do |field|
@@ -97,7 +97,7 @@ class CSV
       return unless @headers
 
       converter = @options[:header_fields_converter]
-      @headers = converter.convert(@headers, nil, 0)
+      @headers = converter.convert(@headers, nil, 0, [])
       @headers.each do |header|
         header.freeze if header.is_a?(String)
       end

data/lib/csv.rb

@@ -95,14 +95,11 @@ require "stringio"
 
 require_relative "csv/fields_converter"
 require_relative "csv/input_record_separator"
-require_relative "csv/match_p"
 require_relative "csv/parser"
 require_relative "csv/row"
 require_relative "csv/table"
 require_relative "csv/writer"
 
-using CSV::MatchP if CSV.const_defined?(:MatchP)
-
 # == \CSV
 #
 # === In a Hurry?
@@ -866,8 +863,9 @@ class CSV
   # <b><tt>index</tt></b>::  The zero-based index of the field in its row.
   # <b><tt>line</tt></b>::   The line of the data source this row is from.
   # <b><tt>header</tt></b>:: The header for the column, when available.
+  # <b><tt>quoted?</tt></b>:: True or false, whether the original value is quoted or not.
   #
-  FieldInfo = Struct.new(:index, :line, :header)
+  FieldInfo = Struct.new(:index, :line, :header, :quoted?)
 
   # A Regexp used to find and convert some common Date formats.
   DateMatcher     = / \A(?: (\w+,?\s+)?\w+\s+\d{1,2},?\s+\d{2,4} |
@@ -875,10 +873,9 @@ class CSV
   # A Regexp used to find and convert some common DateTime formats.
   DateTimeMatcher =
     / \A(?: (\w+,?\s+)?\w+\s+\d{1,2}\s+\d{1,2}:\d{1,2}:\d{1,2},?\s+\d{2,4} |
-            \d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2} |
-            # ISO-8601
+            # ISO-8601 and RFC-3339 (space instead of T) recognized by DateTime.parse
             \d{4}-\d{2}-\d{2}
-              (?:T\d{2}:\d{2}(?::\d{2}(?:\.\d+)?(?:[+-]\d{2}(?::\d{2})|Z)?)?)?
+              (?:[T\s]\d{2}:\d{2}(?::\d{2}(?:\.\d+)?(?:[+-]\d{2}(?::\d{2})|Z)?)?)?
         )\z /x
 
   # The encoding used by all converters.
@@ -1893,8 +1890,19 @@ class CSV
     raise ArgumentError.new("Cannot parse nil as CSV") if data.nil?
 
     if data.is_a?(String)
+      if encoding
+        if encoding.is_a?(String)
+          data_external_encoding, data_internal_encoding = encoding.split(":", 2)
+          if data_internal_encoding
+            data = data.encode(data_internal_encoding, data_external_encoding)
+          else
+            data = data.dup.force_encoding(data_external_encoding)
+          end
+        else
+          data = data.dup.force_encoding(encoding)
+        end
+      end
       @io = StringIO.new(data)
-      @io.set_encoding(encoding || data.encoding)
     else
       @io = data
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: csv
 version: !ruby/object:Gem::Version
-  version: 3.2.3
+  version: 3.2.4
 platform: ruby
 authors:
 - James Edward Gray II
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-04-08 00:00:00.000000000 Z
+date: 2022-08-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -116,10 +116,8 @@ files:
 - lib/csv.rb
 - lib/csv/core_ext/array.rb
 - lib/csv/core_ext/string.rb
-- lib/csv/delete_suffix.rb
 - lib/csv/fields_converter.rb
 - lib/csv/input_record_separator.rb
-- lib/csv/match_p.rb
 - lib/csv/parser.rb
 - lib/csv/row.rb
 - lib/csv/table.rb

data/lib/csv/delete_suffix.rb

@@ -1,18 +0,0 @@
-# frozen_string_literal: true
-
-# This provides String#delete_suffix? for Ruby 2.4.
-unless String.method_defined?(:delete_suffix)
-  class CSV
-    module DeleteSuffix
-      refine String do
-        def delete_suffix(suffix)
-          if end_with?(suffix)
-            self[0...-suffix.size]
-          else
-            self
-          end
-        end
-      end
-    end
-  end
-end

data/lib/csv/match_p.rb

@@ -1,20 +0,0 @@
-# frozen_string_literal: true
-
-# This provides String#match? and Regexp#match? for Ruby 2.3.
-unless String.method_defined?(:match?)
-  class CSV
-    module MatchP
-      refine String do
-        def match?(pattern)
-          self =~ pattern
-        end
-      end
-
-      refine Regexp do
-        def match?(string)
-          self =~ string
-        end
-      end
-    end
-  end
-end