fix: accept \r in unquoted fields when row_sep excludes \r

Fixes #60

Author: jsxs0

lib/csv/parser.rb

@@ -675,7 +675,10 @@ def prepare_quoted
     def prepare_unquoted
       return if @quote_character.nil?
 
-      no_unquoted_values = "\r\n".encode(@encoding)
+      # Only exclude characters that are actually part of the row separator
+      # instead of hardcoding "\r\n"
+      row_separator_chars = @row_separator.chars.map { |c| Regexp.escape(c) }.join
+      no_unquoted_values = row_separator_chars.encode(@encoding)
       no_unquoted_values << @escaped_first_column_separator
       unless @liberal_parsing
         no_unquoted_values << @escaped_quote_character

test/csv/parse/test_general.rb

@@ -139,27 +139,24 @@ def test_non_regex_edge_cases
   end
 
   def test_malformed_csv_cr_first_line
-    error = assert_raise(CSV::MalformedCSVError) do
-      CSV.parse_line("1,2\r,3", row_sep: "\n")
-    end
-    assert_equal("Unquoted fields do not allow new line <\"\\r\"> in line 1.",
-                 error.message)
+    # With the fix for accepting \r without quote when row separator doesn't include \r,
+    # this should now parse successfully when row_sep is "\n"
+    result = CSV.parse_line("1,2\r,3", row_sep: "\n")
+    assert_equal(["1", "2\r", "3"], result)
   end
 
   def test_malformed_csv_cr_middle_line
-    csv = <<-CSV
-line,1,abc
-line,2,"def\nghi"
-
-line,4,some\rjunk
-line,5,jkl
-    CSV
-
-    error = assert_raise(CSV::MalformedCSVError) do
-      CSV.parse(csv)
-    end
-    assert_equal("Unquoted fields do not allow new line <\"\\r\"> in line 4.",
-                 error.message)
+    # With the fix for accepting \r without quote when row separator doesn't include \r,
+    # this should now parse successfully (default row_sep is "\n")
+    csv = "line,1,abc\nline,2,\"def\nghi\"\nline,4,some\rjunk\nline,5,jkl\n"
+    result = CSV.parse(csv)
+    expected = [
+      ["line", "1", "abc"],
+      ["line", "2", "def\nghi"],
+      ["line", "4", "some\rjunk"],
+      ["line", "5", "jkl"]
+    ]
+    assert_equal(expected, result)
   end
 
   def test_malformed_csv_unclosed_quote

test/csv/parse/test_invalid.rb

@@ -5,12 +5,11 @@
 
 class TestCSVParseInvalid < Test::Unit::TestCase
   def test_no_column_mixed_new_lines
-    error = assert_raise(CSV::MalformedCSVError) do
-      CSV.parse("\n" +
-                "\r")
-    end
-    assert_equal("New line must be <\"\\n\"> not <\"\\r\"> in line 2.",
-                 error.message)
+    # With the fix for accepting \r without quote when row separator doesn't include \r,
+    # this should now parse successfully (default row_sep is "\n")
+    result = CSV.parse("\n" + "\r")
+    # This should parse as an empty first row and a second row with just "\r"
+    assert_equal([[], ["\r"]], result)
   end
 
   def test_ignore_invalid_line

test/csv/parse/test_unquoted_cr.rb

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+# frozen_string_literal: false
+
+require_relative "../helper"
+
+class TestCSVParseUnquotedCR < Test::Unit::TestCase
+  extend DifferentOFS
+
+  def test_accept_cr_in_unquoted_field_when_row_separator_is_lf_only
+    # When row separator is just \n, \r should be allowed in unquoted fields
+    data = "field1,field\rwith\rcr,field3\nrow2,data,here\n"
+    expected = [
+      ["field1", "field\rwith\rcr", "field3"],
+      ["row2", "data", "here"]
+    ]
+    assert_equal(expected, CSV.parse(data, row_sep: "\n"))
+  end
+
+  def test_accept_cr_in_unquoted_field_when_row_separator_is_custom
+    # When row separator is custom (like "|"), \r should be allowed in unquoted fields
+    data = "field1,field\rwith\rcr,field3|row2,data,here|"
+    expected = [
+      ["field1", "field\rwith\rcr", "field3"],
+      ["row2", "data", "here"]
+    ]
+    assert_equal(expected, CSV.parse(data, row_sep: "|"))
+  end
+
+  def test_reject_cr_when_row_separator_includes_cr
+    # When row separator includes \r (like \r\n), \r should still be rejected in unquoted fields
+    data = "field1,field2,field3\r\nrow2,data,here\r\n"
+    expected = [
+      ["field1", "field2", "field3"],
+      ["row2", "data", "here"]
+    ]
+    assert_equal(expected, CSV.parse(data, row_sep: "\r\n"))
+  end
+
+  def test_reject_cr_when_row_separator_is_cr_only
+    # When row separator is just \r, \r should be rejected in unquoted fields
+    data = "field1,field2,field3\rrow2,data,here\r"
+    expected = [
+      ["field1", "field2", "field3"],
+      ["row2", "data", "here"]
+    ]
+    assert_equal(expected, CSV.parse(data, row_sep: "\r"))
+  end
+
+  def test_liberal_parsing_with_custom_row_separator
+    # Test liberal parsing mode with custom row separator
+    data = "field1,field\rwith\rcr,field3|row2,data,here|"
+    expected = [
+      ["field1", "field\rwith\rcr", "field3"],
+      ["row2", "data", "here"]
+    ]
+    assert_equal(expected, CSV.parse(data, row_sep: "|", liberal_parsing: true))
+  end
+
+  def test_quoted_fields_with_cr_and_custom_row_separator
+    # Quoted fields should always allow \r regardless of row separator
+    data = "field1,\"field\rwith\rcr\",field3|row2,data,here|"
+    expected = [
+      ["field1", "field\rwith\rcr", "field3"],
+      ["row2", "data", "here"]
+    ]
+    assert_equal(expected, CSV.parse(data, row_sep: "|"))
+  end
+end