Correctly handle multiple chunks from read_in_chunks

read_in_chunks does not clear the intermediate string 'str'
between iterations, so every chunk has every other chunk prepended
to it.

A secondary issue is that it calls str2wcstring() on an intermediate
chunk, which may split multi-byte sequences. This needs to be deferred
to the end.

Test added. Fixes #3756
This commit is contained in:
ridiculousfish 2017-01-21 12:43:20 -08:00
parent f7c133da00
commit 5a5a6a6968
3 changed files with 23 additions and 11 deletions

View file

@ -2024,20 +2024,19 @@ static int read_in_chunks(int fd, wcstring &buff, bool split_null) {
break; break;
} }
long i; const char *end = std::find(inbuf, inbuf + bytes_read, split_null ? L'\0' : L'\n');
for (i = 0; i < bytes_read && !finished; i++) { long bytes_consumed = end - inbuf; // note: must be signed for use in lseek
if ((!split_null && inbuf[i] == L'\n') || (split_null && inbuf[i] == L'\0')) { assert(bytes_consumed <= bytes_read);
finished = true; str.append(inbuf, bytes_consumed);
} else { if (bytes_consumed < bytes_read) {
str.push_back(inbuf[i]); // We found a splitter
} // +1 because we need to treat the splitter as consumed, but not append it to the string
} CHECK(lseek(fd, bytes_consumed - bytes_read + 1, SEEK_CUR) != -1, STATUS_BUILTIN_ERROR)
buff += str2wcstring(str); finished = true;
if (i < bytes_read) {
CHECK(lseek(fd, i - bytes_read, SEEK_CUR) != -1, STATUS_BUILTIN_ERROR)
} }
} }
buff = str2wcstring(str);
if (buff.empty() && eof) { if (buff.empty() && eof) {
exit_res = STATUS_BUILTIN_ERROR; exit_res = STATUS_BUILTIN_ERROR;
} }

View file

@ -117,4 +117,14 @@ echo -ne 'foo\nbar\0baz\nquux' | while read -lza foo
print_vars foo print_vars foo
end end
echo
echo '# chunked read tests'
set -l path /tmp/fish_chunked_read_test.txt
set -l longstr (seq 1024 | string join ',')
echo -n $longstr > $path
read -l longstr2 < $path
test "$longstr" = "$longstr2"
and echo "Chunked reads test pass"
or echo "Chunked reads test failure: long strings don't match!"
true true

View file

@ -55,3 +55,6 @@ newline
1 'foo' 1 'bar' 1 'foo' 1 'bar'
2 'foo' 'bar' 2 'foo' 'bar'
2 'baz' 'quux' 2 'baz' 'quux'
# chunked read tests
Chunked reads test pass