[ruby/csv] Revert "parser: fix a keep bug that some texts may be dropped unexpectedly"

This reverts commit https://github.com/ruby/csv/commit/5c6523da0a61.

This introduces another pbolem. We should try again later.

https://github.com/ruby/csv/commit/43a1d6fff1
This commit is contained in:
Sutou Kouhei 2021-12-24 10:44:11 +09:00 коммит произвёл Sutou Kouhei
Родитель 002ce9f515
Коммит 22ef4f6445
2 изменённых файлов: 37 добавлений и 91 удалений

Просмотреть файл

@ -167,7 +167,6 @@ class CSV
end
def keep_start
adjust_last_keep
@keeps.push([@scanner.pos, nil])
end
@ -198,17 +197,7 @@ class CSV
end
def keep_drop
_, buffer = @keeps.pop
return unless buffer
last_keep = @keeps.last
return unless last_keep
if last_keep[1]
last_keep[1] << buffer
else
last_keep[1] = buffer
end
@keeps.pop
end
def rest
@ -216,13 +205,12 @@ class CSV
end
private
def adjust_last_keep
def read_chunk
return false if @last_scanner
unless @keeps.empty?
keep = @keeps.last
return if keep.nil?
keep_start = keep[0]
return if @scanner.pos == keep_start
string = @scanner.string
keep_data = string.byteslice(keep_start, @scanner.pos - keep_start)
if keep_data
@ -236,11 +224,6 @@ class CSV
keep[0] = 0
end
def read_chunk
return false if @last_scanner
adjust_last_keep
input = @inputs.first
case input
when StringIO
@ -746,7 +729,9 @@ class CSV
sample[0, 128].index(@quote_character)
end
class UnoptimizedStringIO # :nodoc:
SCANNER_TEST = (ENV["CSV_PARSER_SCANNER_TEST"] == "yes")
if SCANNER_TEST
class UnoptimizedStringIO
def initialize(string)
@io = StringIO.new(string, "rb:#{string.encoding}")
end
@ -764,8 +749,8 @@ class CSV
end
end
SCANNER_TEST = (ENV["CSV_PARSER_SCANNER_TEST"] == "yes")
if SCANNER_TEST
SCANNER_TEST_CHUNK_SIZE =
Integer((ENV["CSV_PARSER_SCANNER_TEST_CHUNK_SIZE"] || "1"), 10)
def build_scanner
inputs = @samples.collect do |sample|
UnoptimizedStringIO.new(sample)
@ -775,12 +760,10 @@ class CSV
else
inputs << @input
end
chunk_size =
Integer((ENV["CSV_PARSER_SCANNER_TEST_CHUNK_SIZE"] || "1"), 10)
InputsScanner.new(inputs,
@encoding,
@row_separator,
chunk_size: chunk_size)
chunk_size: SCANNER_TEST_CHUNK_SIZE)
end
else
def build_scanner

Просмотреть файл

@ -1,37 +0,0 @@
require_relative "../helper"
class TestCSVParseInputsScanner < Test::Unit::TestCase
include Helper
def test_keep_over_chunks_nested_back
input = CSV::Parser::UnoptimizedStringIO.new("abcdefghijklmnl")
scanner = CSV::Parser::InputsScanner.new([input],
Encoding::UTF_8,
nil,
chunk_size: 2)
scanner.keep_start
assert_equal("abc", scanner.scan_all(/[a-c]+/))
scanner.keep_start
assert_equal("def", scanner.scan_all(/[d-f]+/))
scanner.keep_back
scanner.keep_back
assert_equal("abcdefg", scanner.scan_all(/[a-g]+/))
end
def test_keep_over_chunks_nested_drop_back
input = CSV::Parser::UnoptimizedStringIO.new("abcdefghijklmnl")
scanner = CSV::Parser::InputsScanner.new([input],
Encoding::UTF_8,
nil,
chunk_size: 3)
scanner.keep_start
assert_equal("ab", scanner.scan(/../))
scanner.keep_start
assert_equal("c", scanner.scan(/./))
assert_equal("d", scanner.scan(/./))
scanner.keep_drop
scanner.keep_back
assert_equal("abcdefg", scanner.scan_all(/[a-g]+/))
end
end