mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
* lib/csv.rb: Upgrading output encoding as needed. [ruby-core:33135]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@29808 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
parent
6cba0f0663
commit
40e5b39336
3 changed files with 62 additions and 38 deletions
|
@ -1,3 +1,7 @@
|
||||||
|
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>
|
Tue Nov 16 22:30:39 2010 Yusuke Endoh <mame@tsg.ne.jp>
|
||||||
|
|
||||||
* vm_insnhelper.c (vm_throw): remove fear of undefined behavior :-)
|
* vm_insnhelper.c (vm_throw): remove fear of undefined behavior :-)
|
||||||
|
|
28
lib/csv.rb
28
lib/csv.rb
|
@ -1562,9 +1562,10 @@ class CSV
|
||||||
options = DEFAULT_OPTIONS.merge(options)
|
options = DEFAULT_OPTIONS.merge(options)
|
||||||
|
|
||||||
# create the IO object we will read from
|
# create the IO object we will read from
|
||||||
@io = if data.is_a? String then StringIO.new(data) else data end
|
@io = data.is_a?(String) ? StringIO.new(data) : data
|
||||||
# honor the IO encoding if we can, otherwise default to ASCII-8BIT
|
# honor the IO encoding if we can, otherwise default to ASCII-8BIT
|
||||||
@encoding = raw_encoding || Encoding.default_internal || Encoding.default_external
|
@encoding = raw_encoding || Encoding.default_internal ||
|
||||||
|
Encoding.default_external
|
||||||
#
|
#
|
||||||
# prepare for building safe regular expressions in the target encoding,
|
# prepare for building safe regular expressions in the target encoding,
|
||||||
# if we can transcode the needed characters
|
# if we can transcode the needed characters
|
||||||
|
@ -1711,7 +1712,15 @@ class CSV
|
||||||
@headers = row if header_row?
|
@headers = row if header_row?
|
||||||
@lineno += 1
|
@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.encoding,
|
||||||
|
output.encoding ) )
|
||||||
|
@io = StringIO.new(@io.string.force_encoding(compatible_encoding))
|
||||||
|
@io.seek(0, IO::SEEK_END)
|
||||||
|
end
|
||||||
|
@io << output
|
||||||
|
|
||||||
self # for chaining
|
self # for chaining
|
||||||
end
|
end
|
||||||
|
@ -2043,11 +2052,13 @@ class CSV
|
||||||
@row_sep = @row_sep.to_s.encode(@encoding)
|
@row_sep = @row_sep.to_s.encode(@encoding)
|
||||||
|
|
||||||
# establish quoting rules
|
# establish quoting rules
|
||||||
@force_quotes = options.delete(:force_quotes)
|
@force_quotes = options.delete(:force_quotes)
|
||||||
do_quote = lambda do |field|
|
do_quote = lambda do |field|
|
||||||
@quote_char +
|
field = String(field)
|
||||||
String(field).gsub(@quote_char, @quote_char * 2) +
|
encoded_quote = @quote_char.encode(field.encoding)
|
||||||
@quote_char
|
encoded_quote +
|
||||||
|
field.gsub(encoded_quote, encoded_quote * 2) +
|
||||||
|
encoded_quote
|
||||||
end
|
end
|
||||||
quotable_chars = encode_str("\r\n", @col_sep, @quote_char)
|
quotable_chars = encode_str("\r\n", @col_sep, @quote_char)
|
||||||
@quote = if @force_quotes
|
@quote = if @force_quotes
|
||||||
|
@ -2297,6 +2308,7 @@ class CSV
|
||||||
end
|
end
|
||||||
|
|
||||||
private
|
private
|
||||||
|
|
||||||
def raw_encoding
|
def raw_encoding
|
||||||
if @io.respond_to? :internal_encoding
|
if @io.respond_to? :internal_encoding
|
||||||
@io.internal_encoding || @io.external_encoding
|
@io.internal_encoding || @io.external_encoding
|
||||||
|
|
|
@ -218,6 +218,14 @@ class TestEncodings < Test::Unit::TestCase
|
||||||
end
|
end
|
||||||
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
|
||||||
|
|
||||||
private
|
private
|
||||||
|
|
||||||
def assert_parses(fields, encoding, options = { })
|
def assert_parses(fields, encoding, options = { })
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue