csv 3.0.0 → 3.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 878c0fd11ecaed5d4fb2ac420068c42b707a721144062ba7fe623002a13478be
-  data.tar.gz: 007c48a609bcef16dba46b8f7aca667dbdcd3cb24f05a6b7f2470726dcfeea17
+  metadata.gz: f6ad673a6db13541d439c4798f677ae19e118fb031411b8434ec4534bafc47a9
+  data.tar.gz: 427070352e63b901d410a70eba6f7073103bc6cbe8e57f7e161e01003ae1598c
 SHA512:
-  metadata.gz: 4daffd50dd28082465a243e17f77eeb8ccd1c6727c9094eeb3f0fcaaa05426949f7e3103fa84fdad87e27e1e493365f13d4491000d8ac61a006094ff2be2602a
-  data.tar.gz: adc33341e6dd75c8d8ab343343fd8d455b7e048e081a2e22992f54397c42b3a70a4c78561fc871324b4424ed562a1fc9e59da4a12a56ff7ade2d3161195c3deb
+  metadata.gz: 3d2c69c8b784d79149dfd5999d2c937e037f83ccc806bd4fe5a674b913518ab4be4a13911e2ec3f5590c45dc6ebdd346eed6f85be253fad6dae40cd9eb0cb704
+  data.tar.gz: 25a0fee13c07fb870831c0b59ea88c9df6844ccf63810925d7ed437000c220b83a212781d5d615529ef487bd3ffdbd90a13b293475e8a4074a2feb249258b156

data/README.md

@@ -1,6 +1,7 @@
 # CSV
 
 [![Build Status](https://travis-ci.org/ruby/csv.svg?branch=master)](https://travis-ci.org/ruby/csv)
+[![Test Coverage](https://api.codeclimate.com/v1/badges/321fa39e510a0abd0369/test_coverage)](https://codeclimate.com/github/ruby/csv/test_coverage)
 
 This library provides a complete interface to CSV files and data. It offers tools to enable you to read and write to and from Strings or IO objects, as needed.
 

data/lib/csv.rb

@@ -141,7 +141,7 @@ end
 # There are several specialized class methods for one-statement reading or writing,
 # described in the Specialized Methods section.
 #
-# If a String passed into ::new, it is internally wrapped into a StringIO object.
+# If a String is passed into ::new, it is internally wrapped into a StringIO object.
 #
 # +options+ can be used for specifying the particular CSV flavor (column
 # separators, row separators, value quoting and so on), and for data conversion,
@@ -890,8 +890,12 @@ class CSV
   #                                       attempt to parse input not conformant
   #                                       with RFC 4180, such as double quotes
   #                                       in unquoted fields.
-  # <b><tt>:nil_value</tt></b>::          TODO: WRITE ME.
-  # <b><tt>:empty_value</tt></b>::        TODO: WRITE ME.
+  # <b><tt>:nil_value</tt></b>::          When set an object, any values of an
+  #                                       empty field are replaced by the set
+  #                                       object, not nil.
+  # <b><tt>:empty_value</tt></b>::        When set an object, any values of a
+  #                                       blank string field is replaced by
+  #                                       the set object.
   #
   # See CSV::DEFAULT_OPTIONS for the default settings.
   #
@@ -908,6 +912,7 @@ class CSV
 
     # create the IO object we will read from
     @io = data.is_a?(String) ? StringIO.new(data) : data
+    @prefix_io = nil  # cache for input data possibly read by init_separators
     @encoding = determine_encoding(encoding, internal_encoding)
     #
     # prepare for building safe regular expressions in the target encoding,
@@ -1156,7 +1161,7 @@ class CSV
   def read
     rows = to_a
     if @use_headers
-      Table.new(rows)
+      Table.new(rows, headers: @headers)
     else
       rows
     end
@@ -1200,8 +1205,14 @@ class CSV
 
     loop do
       # add another read to the line
-      unless parse = @io.gets(@row_sep)
-        return nil
+      if @prefix_io
+        parse = @prefix_io.gets(@row_sep)
+        if @prefix_io.eof?
+          parse << (@io.gets(@row_sep) || "") unless parse.end_with?(@row_sep)
+          @prefix_io = nil  # avoid having to test @prefix_io.eof? in main code path
+        end
+      else
+        return nil unless parse = @io.gets(@row_sep)
       end
 
       if in_extended_col
@@ -1311,7 +1322,7 @@ class CSV
 
       if in_extended_col
         # if we're at eof?(), a quoted field wasn't closed...
-        if @io.eof?
+        if @io.eof? and !@prefix_io
           raise MalformedCSVError.new("Unclosed quoted field",
                                       lineno + 1)
         elsif @field_size_limit and csv.last.size >= @field_size_limit
@@ -1433,68 +1444,62 @@ class CSV
     # (not fully encoding safe)
     #
     if @row_sep == :auto
-      if [ARGF, STDIN, STDOUT, STDERR].include?(@io) or
-         (defined?(Zlib) and @io.class == Zlib::GzipWriter)
-        @row_sep = $INPUT_RECORD_SEPARATOR
-      else
-        begin
+      saved_prefix = []  # sample chunks to be reprocessed later
+      begin
+        while @row_sep == :auto && @io.respond_to?(:gets)
           #
-          # remember where we were (pos() will raise an exception if @io is pipe
-          # or not opened for reading)
+          # if we run out of data, it's probably a single line
+          # (ensure will set default value)
           #
-          saved_pos = @io.pos
-          while @row_sep == :auto
-            #
-            # if we run out of data, it's probably a single line
-            # (ensure will set default value)
-            #
-            break unless sample = @io.gets(nil, 1024)
-
-            cr = encode_str("\r")
-            lf = encode_str("\n")
-            # extend sample if we're unsure of the line ending
-            if sample.end_with?(cr)
-              sample << (@io.gets(nil, 1) || "")
-            end
+          break unless sample = @io.gets(nil, 1024)
+
+          cr = encode_str("\r")
+          lf = encode_str("\n")
+          # extend sample if we're unsure of the line ending
+          if sample.end_with?(cr)
+            sample << (@io.gets(nil, 1) || "")
+          end
 
-            # try to find a standard separator
-            sample.each_char.each_cons(2) do |char, next_char|
-              case char
-              when cr
-                if next_char == lf
-                  @row_sep = encode_str("\r\n")
-                else
-                  @row_sep = cr
-                end
-                break
-              when lf
-                @row_sep = lf
-                break
+          saved_prefix << sample
+
+          # try to find a standard separator
+          last_char = nil
+          sample.each_char.each_cons(2) do |char, next_char|
+            last_char = next_char
+            case char
+            when cr
+              if next_char == lf
+                @row_sep = encode_str("\r\n")
+              else
+                @row_sep = cr
               end
+              break
+            when lf
+              @row_sep = lf
+              break
             end
           end
-
-          # tricky seek() clone to work around GzipReader's lack of seek()
-          @io.rewind
-          # reset back to the remembered position
-          while saved_pos > 1024  # avoid loading a lot of data into memory
-            @io.read(1024)
-            saved_pos -= 1024
+          if @row_sep == :auto
+            case last_char
+            when cr
+              @row_sep = cr
+            when lf
+              @row_sep = lf
+            end
           end
-          @io.read(saved_pos) if saved_pos.nonzero?
-        rescue IOError         # not opened for reading
-          # do nothing:  ensure will set default
-        rescue NoMethodError   # Zlib::GzipWriter doesn't have some IO methods
-          # do nothing:  ensure will set default
-        rescue SystemCallError # pipe
-          # do nothing:  ensure will set default
-        ensure
-          #
-          # set default if we failed to detect
-          # (stream not opened for reading, a pipe, or a single line of data)
-          #
-          @row_sep = $INPUT_RECORD_SEPARATOR if @row_sep == :auto
         end
+      rescue IOError
+        # do nothing:  ensure will set default
+      ensure
+        #
+        # set default if we failed to detect
+        # (stream not opened for reading or a single line of data)
+        #
+        @row_sep = $INPUT_RECORD_SEPARATOR if @row_sep == :auto
+
+        # save sampled input for later parsing (but only if there is some!)
+        saved_prefix = saved_prefix.join('')
+        @prefix_io = StringIO.new(saved_prefix) unless saved_prefix.empty?
       end
     end
     @row_sep = @row_sep.to_s.encode(@encoding)
@@ -1743,8 +1748,6 @@ class CSV
   def raw_encoding(default = Encoding::ASCII_8BIT)
     if @io.respond_to? :internal_encoding
       @io.internal_encoding || @io.external_encoding
-    elsif @io.is_a? StringIO
-      @io.string.encoding
     elsif @io.respond_to? :encoding
       @io.encoding
     else

data/lib/csv/row.rb

@@ -48,6 +48,11 @@ class CSV
     extend Forwardable
     def_delegators :@row, :empty?, :length, :size
 
+    def initialize_copy(other)
+      super
+      @row = @row.dup
+    end
+
     # Returns +true+ if this is a header row.
     def header_row?
       @header_row

data/lib/csv/table.rb

@@ -16,6 +16,11 @@ class CSV
     # Construct a new CSV::Table from +array_of_rows+, which are expected
     # to be CSV::Row objects.  All rows are assumed to have the same headers.
     #
+    # The optional +headers+ parameter can be set to Array of headers.
+    # If headers aren't set, headers are fetched from CSV::Row objects.
+    # Otherwise, headers() method will return headers being set in
+    # headers arugument.
+    #
     # A CSV::Table object supports the following Array methods through
     # delegation:
     #
@@ -23,8 +28,17 @@ class CSV
     # * length()
     # * size()
     #
-    def initialize(array_of_rows)
+    def initialize(array_of_rows, headers: nil)
       @table = array_of_rows
+      @headers = headers
+      unless @headers
+        if @table.empty?
+          @headers = []
+        else
+          @headers = @table.first.headers
+        end
+      end
+
       @mode  = :col_or_row
     end
 
@@ -122,11 +136,7 @@ class CSV
     # other rows).  An empty Array is returned for empty tables.
     #
     def headers
-      if @table.empty?
-        Array.new
-      else
-        @table.first.headers
-      end
+      @headers.dup
     end
 
     #
@@ -171,6 +181,10 @@ class CSV
           @table[index_or_header] = value
         end
       else                 # set column
+        unless index_or_header.is_a? Integer
+          index = @headers.index(index_or_header) || @headers.size
+          @headers[index] = index_or_header
+        end
         if value.is_a? Array  # multiple values
           @table.each_with_index do |row, i|
             if row.header_row?
@@ -258,6 +272,11 @@ class CSV
             (@mode == :col_or_row and index_or_header.is_a? Integer)
           @table.delete_at(index_or_header)
         else                 # by header
+          if index_or_header.is_a? Integer
+            @headers.delete_at(index_or_header)
+          else
+            @headers.delete(index_or_header)
+          end
           @table.map { |row| row.delete(index_or_header).last }
         end
       end
@@ -375,4 +394,4 @@ class CSV
       "#<#{self.class} mode:#{@mode} row_count:#{to_a.size}>".encode("US-ASCII")
     end
   end
-end
+end

data/lib/csv/version.rb

@@ -2,5 +2,5 @@
 
 class CSV
   # The version of the installed library.
-  VERSION = "3.0.0"
+  VERSION = "3.0.1"
 end

data/news.md

@@ -1,5 +1,56 @@
 # News
 
+## 3.0.1 - 2018-12-07
+
+### Improvements
+
+  * Added a test.
+    [GitHub#38][Patch by 284km]
+
+  * `CSV::Row#dup`: Changed to duplicate internal data.
+    [GitHub#39][Reported by André Guimarães Sakata]
+
+  * Documented `:nil_value` and `:empty_value` options.
+    [GitHub#41][Patch by OwlWorks]
+
+  * Added support for separator detection for non-seekable inputs.
+    [GitHub#45][Patch by Ilmari Karonen]
+
+  * Removed needless code.
+    [GitHub#48][Patch by Espartaco Palma]
+
+  * Added support for parsing header only CSV with `headers: true`.
+    [GitHub#47][Patch by Kazuma Shibasaka]
+
+  * Added support for coverage report in CI.
+    [GitHub#48][Patch by Espartaco Palma]
+
+  * Improved auto CR row separator detection.
+    [GitHub#51][Reported by Yuki Kurihara]
+
+### Fixes
+
+  * Fixed a typo in document.
+    [GitHub#40][Patch by Marcus Stollsteimer]
+
+### Thanks
+
+  * 284km
+
+  * André Guimarães Sakata
+
+  * Marcus Stollsteimer
+
+  * OwlWorks
+
+  * Ilmari Karonen
+
+  * Espartaco Palma
+
+  * Kazuma Shibasaka
+
+  * Yuki Kurihara
+
 ## 3.0.0 - 2018-06-06
 
 ### Fixes

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: csv
 version: !ruby/object:Gem::Version
-  version: 3.0.0
+  version: 3.0.1
 platform: ruby
 authors:
 - James Edward Gray II
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-06-06 00:00:00.000000000 Z
+date: 2018-12-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -53,6 +53,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: The CSV library provides a complete interface to CSV files and data.
   It offers tools to enable you to read and write to and from Strings or IO objects,
   as needed.
@@ -92,7 +106,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 3.0.0.beta1
+rubygems_version: 3.0.0.beta3
 signing_key: 
 specification_version: 4
 summary: CSV Reading and Writing