From 625f721bc43d8b50b76c425ceb5663a154e09393 Mon Sep 17 00:00:00 2001
From: Koichi ITO <koic.ito@gmail.com>
Date: Mon, 1 Jun 2020 22:50:42 +0900
Subject: [PATCH] Add `undef: :replace` for `CSV.open`

This PR adds `undef: :replace` option for `CSV.open`.

`File.open` has `undef: :replace` option, but `CSV.open` does not.
It would be convenient if `CSV.open` could have a shortcut by having
`undef: :replace` option.
---
 lib/csv.rb                      |  7 +++++++
 test/csv/interface/test_read.rb | 22 ++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/lib/csv.rb b/lib/csv.rb
index 4ffffe40..a06c92a1 100644
--- a/lib/csv.rb
+++ b/lib/csv.rb
@@ -960,6 +960,11 @@ def generate_line(row, **options)
     #   open( filename, mode = "rb", **options )
     #   open( filename, **options )
     #
+    # possible options elements:
+    #   hash form:
+    #     :undef => :replace # replace undefined conversion
+    #     :replace => string # replacement string ("?" or "\uFFFD" if not specified)
+    #
     # This method opens an IO object, and wraps that with CSV. This is intended
     # as the primary interface for writing a CSV file.
     #
@@ -1021,6 +1026,8 @@ def open(filename, mode="r", **options)
       # wrap a File opened with the remaining +args+ with no newline
       # decorator
       file_opts = {universal_newline: false}.merge(options)
+      options.delete(:undef)
+      options.delete(:replace)
 
       begin
         f = File.open(filename, mode, **file_opts)
diff --git a/test/csv/interface/test_read.rb b/test/csv/interface/test_read.rb
index 58ec188f..4b0f5e7e 100644
--- a/test/csv/interface/test_read.rb
+++ b/test/csv/interface/test_read.rb
@@ -125,6 +125,28 @@ def test_open_encoding_utf_8_with_bom
     end
   end
 
+  def test_open_with_undef_replace
+    # U+00B7 Middle Dot
+    CSV.open(@input.path, "w", encoding: Encoding::CP932, undef: :replace) do |rows|
+      rows << ["\u00B7"]
+    end
+    CSV.open(@input.path, encoding: Encoding::CP932) do |csv|
+      assert_equal([["?"]],
+                   csv.to_a)
+    end
+  end
+
+  def test_open_with_undef_replace_and_replace_string
+    # U+00B7 Middle Dot
+    CSV.open(@input.path, "w", encoding: Encoding::CP932, undef: :replace, replace: "X") do |rows|
+      rows << ["\u00B7"]
+    end
+    CSV.open(@input.path, encoding: Encoding::CP932) do |csv|
+      assert_equal([["X"]],
+                   csv.to_a)
+    end
+  end
+
   def test_parse
     assert_equal(@rows,
                  CSV.parse(@data, col_sep: "\t", row_sep: "\r\n"))