Preview Ruby 4.1 is a preview. It can change before the final release. Switch to Ruby 4.0 →
instance method
IO#each_codepoint
() { (::Integer c) -> void } -> self
() -> ::Enumerator[::Integer, self]
each_codepoint {|c| ... } → self
each_codepoint → enumerator
io.c
View on GitHub ↗
static VALUE
rb_io_each_codepoint(VALUE io)
{
rb_io_t *fptr;
rb_encoding *enc;
unsigned int c;
int r, n;
RETURN_ENUMERATOR(io, 0, 0);
GetOpenFile(io, fptr);
rb_io_check_char_readable(fptr);
READ_CHECK(fptr);
enc = io_read_encoding(fptr);
if (NEED_READCONV(fptr)) {
SET_BINARY_MODE(fptr);
r = 1; /* no invalid char yet */
for (;;) {
make_readconv(fptr, 0);
for (;;) {
if (fptr->cbuf.len) {
r = rb_enc_precise_mbclen(fptr->cbuf.ptr+fptr->cbuf.off,
fptr->cbuf.ptr+fptr->cbuf.off+fptr->cbuf.len,
enc);
if (!MBCLEN_NEEDMORE_P(r))
break;
if (fptr->cbuf.len == fptr->cbuf.capa) {
rb_raise(rb_eIOError, "too long character");
}
}
if (more_char(fptr) == MORE_CHAR_FINISHED) {
clear_readconv(fptr);
if (!MBCLEN_CHARFOUND_P(r)) {
goto invalid;
}
return io;
}
}
if (MBCLEN_INVALID_P(r)) {
goto invalid;
}
n = MBCLEN_CHARFOUND_LEN(r);
c = rb_enc_codepoint(fptr->cbuf.ptr+fptr->cbuf.off,
fptr->cbuf.ptr+fptr->cbuf.off+fptr->cbuf.len,
enc);
fptr->cbuf.off += n;
fptr->cbuf.len -= n;
rb_yield(UINT2NUM(c));
rb_io_check_char_readable(fptr);
}
}
NEED_NEWLINE_DECORATOR_ON_READ_CHECK(fptr);
while (io_fillbuf(fptr) >= 0) {
r = rb_enc_precise_mbclen(fptr->rbuf.ptr+fptr->rbuf.off,
fptr->rbuf.ptr+fptr->rbuf.off+fptr->rbuf.len, enc);
if (MBCLEN_CHARFOUND_P(r) &&
(n = MBCLEN_CHARFOUND_LEN(r)) <= fptr->rbuf.len) {
c = rb_enc_codepoint(fptr->rbuf.ptr+fptr->rbuf.off,
fptr->rbuf.ptr+fptr->rbuf.off+fptr->rbuf.len, enc);
fptr->rbuf.off += n;
fptr->rbuf.len -= n;
rb_yield(UINT2NUM(c));
}
else if (MBCLEN_INVALID_P(r)) {
goto invalid;
}
else if (MBCLEN_NEEDMORE_P(r)) {
char cbuf[8], *p = cbuf;
int more = MBCLEN_NEEDMORE_LEN(r);
if (more > numberof(cbuf)) goto invalid;
more += n = fptr->rbuf.len;
if (more > numberof(cbuf)) goto invalid;
while ((n = (int)read_buffered_data(p, more, fptr)) > 0 &&
(p += n, (more -= n) > 0)) {
if (io_fillbuf(fptr) < 0) goto invalid;
if ((n = fptr->rbuf.len) > more) n = more;
}
r = rb_enc_precise_mbclen(cbuf, p, enc);
if (!MBCLEN_CHARFOUND_P(r)) goto invalid;
c = rb_enc_codepoint(cbuf, p, enc);
rb_yield(UINT2NUM(c));
}
else {
continue;
}
rb_io_check_byte_readable(fptr);
}
return io;
invalid:
rb_raise(rb_eArgError, "invalid byte sequence in %s", rb_enc_name(enc));
UNREACHABLE_RETURN(Qundef);
}
Calls the given block with each codepoint in the stream; returns self:
Example
File.read('t.ja') # => "こんにちは" f = File.new('t.ja') a = [] f.each_codepoint {|c| a << c } a # => [12371, 12435, 12395, 12385, 12399] f.close
Returns an Enumerator if no block is given.
Related: IO#each_byte, IO#each_char.