diff options
author | yugui <yugui@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2010-12-20 13:22:40 +0000 |
---|---|---|
committer | yugui <yugui@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2010-12-20 13:22:40 +0000 |
commit | 35c70b2137fed0ac3c399bb4466190b869687962 (patch) | |
tree | f693cbe2876f70a6d476e887384348ecbf66d838 | |
parent | 0e1cd3e37c07e65053fafc61df5eb34bf3bf9003 (diff) |
merges r29808 and r29822 from trunk into ruby_1_9_2.; workaround for StringIO.
--
* lib/csv.rb: Upgrading output encoding as needed. [ruby-core:33135]
--
* lib/csv.rb: Upgrading output encoding with ASCII content
as needed. [ruby-core:33229]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_1_9_2@30259 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r-- | ChangeLog | 13 | ||||
-rw-r--r-- | lib/csv.rb | 21 | ||||
-rw-r--r-- | test/csv/test_encodings.rb | 16 | ||||
-rw-r--r-- | version.h | 2 |
4 files changed, 45 insertions, 7 deletions
@@ -1,3 +1,16 @@ +Thu Nov 18 00:02:17 2010 James Edward Gray II <jeg2@ruby-lang.org> + + * lib/csv.rb: Upgrading output encoding with ASCII content + as needed. [ruby-core:33229] + +Tue Nov 17 08:54:04 2010 James Edward Gray II <jeg2@ruby-lang.org> + + * lib/csv.rb: Upgrading output encoding as needed. [ruby-core:33135] + +Tue Nov 17 08:54:04 2010 James Edward Gray II <jeg2@ruby-lang.org> + + * lib/csv.rb: Upgrading output encoding as needed. [ruby-core:33135] + Tue Nov 16 22:30:39 2010 Yusuke Endoh <mame@tsg.ne.jp> * vm_insnhelper.c (vm_throw): remove fear of undefined behavior :-) diff --git a/lib/csv.rb b/lib/csv.rb index 86209eb19b..9942802c3e 100644 --- a/lib/csv.rb +++ b/lib/csv.rb @@ -1703,7 +1703,14 @@ class CSV @headers = row if header_row? @lineno += 1 - @io << row.map(&@quote).join(@col_sep) + @row_sep # quote and separate + output = row.map(&@quote).join(@col_sep) + @row_sep # quote and separate + if @io.is_a?(StringIO) and + output.encoding != raw_encoding and + (compatible_encoding = Encoding.compatible?(@io.string, output)) + @io = StringIO.new(@io.string.force_encoding(compatible_encoding)) + @io.seek(0, IO::SEEK_END) + end + @io << output self # for chaining end @@ -2038,11 +2045,13 @@ class CSV @row_sep = @row_sep.to_s.encode(@encoding) # establish quoting rules - @force_quotes = options.delete(:force_quotes) - do_quote = lambda do |field| - @quote_char + - String(field).gsub(@quote_char, @quote_char * 2) + - @quote_char + @force_quotes = options.delete(:force_quotes) + do_quote = lambda do |field| + field = String(field) + encoded_quote = @quote_char.encode(field.encoding) + encoded_quote + + field.gsub(encoded_quote, encoded_quote * 2) + + encoded_quote end quotable_chars = encode_str("\r\n", @col_sep, @quote_char) @quote = if @force_quotes diff --git a/test/csv/test_encodings.rb b/test/csv/test_encodings.rb index 5d29ac1fa9..3dc80ccdb1 100644 --- a/test/csv/test_encodings.rb +++ b/test/csv/test_encodings.rb @@ -217,6 +217,22 @@ class TestEncodings < Test::Unit::TestCase assert_equal(data, CSV.read(@temp_csv_path, encoding: encoding.name)) end end + + def test_encoding_is_upgraded_during_writing_as_needed + data = ["foo".force_encoding("US-ASCII"), "\u3042"] + assert_equal("US-ASCII", data.first.encoding.name) + assert_equal("UTF-8", data.last.encoding.name) + assert_equal("UTF-8", data.join.encoding.name) + assert_equal("UTF-8", data.to_csv.encoding.name) + end + + def test_encoding_is_upgraded_for_ascii_content_during_writing_as_needed + data = ["foo".force_encoding("ISO-8859-1"), "\u3042"] + assert_equal("ISO-8859-1", data.first.encoding.name) + assert_equal("UTF-8", data.last.encoding.name) + assert_equal("UTF-8", data.join.encoding.name) + assert_equal("UTF-8", data.to_csv.encoding.name) + end private @@ -1,5 +1,5 @@ #define RUBY_VERSION "1.9.2" -#define RUBY_PATCHLEVEL 99 +#define RUBY_PATCHLEVEL 100 #define RUBY_VERSION_MAJOR 1 #define RUBY_VERSION_MINOR 9 #define RUBY_VERSION_TEENY 1 |