method
each_codepoint

v2_4_6 - Show latest stable - 0 notes - Class: IO
each_codepoint() public
Passes the Integer ordinal of each character in ios, passing the codepoint as an argument. The stream must be opened for reading or an IOError will be raised.
If no block is given, an enumerator is returned instead.
Show source
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);
    if (NEED_READCONV(fptr)) {
        SET_BINARY_MODE(fptr);
        r = 1;         /* no invalid char yet */
        for (;;) {
            make_readconv(fptr, 0);
            for (;;) {
                if (fptr->cbuf.len) {
                    if (fptr->encs.enc)
                        r = rb_enc_precise_mbclen(fptr->cbuf.ptr+fptr->cbuf.off,
                                                  fptr->cbuf.ptr+fptr->cbuf.off+fptr->cbuf.len,
                                                  fptr->encs.enc);
                    else
                        r = ONIGENC_CONSTRUCT_MBCLEN_CHARFOUND(1);
                    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)) {
                        enc = fptr->encs.enc;
                        goto invalid;
                    }
                    return io;
                }
            }
            if (MBCLEN_INVALID_P(r)) {
                enc = fptr->encs.enc;
                goto invalid;
            }
            n = MBCLEN_CHARFOUND_LEN(r);
            if (fptr->encs.enc) {
                c = rb_enc_codepoint(fptr->cbuf.ptr+fptr->cbuf.off,
                                     fptr->cbuf.ptr+fptr->cbuf.off+fptr->cbuf.len,
                                     fptr->encs.enc);
            }
            else {
                c = (unsigned char)fptr->cbuf.ptr[fptr->cbuf.off];
            }
            fptr->cbuf.off += n;
            fptr->cbuf.len -= n;
            rb_yield(UINT2NUM(c));
        }
    }
    NEED_NEWLINE_DECORATOR_ON_READ_CHECK(fptr);
    enc = io_input_encoding(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)) {
          invalid:
            rb_raise(rb_eArgError, "invalid byte sequence in %s", rb_enc_name(enc));
        }
        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;
        }
    }
    return io;
}
each_codepoint

Related methods
