Method: U::String#dump

Defined in:
ext/u/rb_u_string_dump.c

#dump ⇒ U::String

Returns the receiver in a reader-friendly format, inheriting any taint and untrust.

The reader-friendly format looks like “‘“…”.u`”. Inside the “…”, any #print? characters in the ASCII range are output as-is, the following special characters are escaped according to the following table:

<table>

<thead><tr><th>Character</th><th>Dumped Sequence</th></tr></thead>
<tbody>
  <tr><td>U+0022 QUOTATION MARK</td><td><code>\"</code></td></tr>
  <tr><td>U+005C REVERSE SOLIDUS</td><td><code>\\</code></td></tr>
  <tr><td>U+000A LINE FEED (LF)</td><td><code>\n</code></td></tr>
  <tr><td>U+000D CARRIAGE RETURN (CR)</td><td><code>\r</code></td></tr>
  <tr><td>U+0009 CHARACTER TABULATION</td><td><code>\t</code></td></tr>
  <tr><td>U+000C FORM FEED (FF)</td><td><code>\f</code></td></tr>
  <tr><td>U+000B LINE TABULATION</td><td><code>\v</code></td></tr>
  <tr><td>U+0008 BACKSPACE</td><td><code>\b</code></td></tr>
  <tr><td>U+0007 BELL</td><td><code>\a</code></td></tr>
  <tr><td>U+001B ESCAPE</td><td><code>\e</code></td></tr>
</tbody>

</table>

the following special sequences are also escaped:

<table>

<thead><tr><th>Character</th><th>Dumped Sequence</th></tr></thead>
<tbody>
  <tr><td><code>#$</code></td><td><code>\#$</code></td></tr>
  <tr><td><code>#@</code></td><td><code>\#@</code></td></tr>
  <tr><td><code>#{</code></td><td><code>\#{</code></td></tr>
</tbody>

</table>

any valid UTF-8 byte sequences are output as “‘\u{_n_}`”, where n is the lowercase hexadecimal representation of the code point encoded by the UTF-8 sequence, and any other byte is output as “`\x`n”, where n is the two-digit uppercase hexadecimal representation of the byte’s value.

Returns:



125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
 
# File 'ext/u/rb_u_string_dump.c', line 125

VALUE
rb_u_string_dump(VALUE self)
{
        const struct rb_u_string *string = RVAL2USTRING(self);
        const char *p = USTRING_STR(string);
        const char *end = USTRING_END(string);

        VALUE buffer = rb_u_buffer_new_sized(7);

        rb_u_buffer_append(buffer, "\"", 1);
        while (p < end) {
                unsigned char c = *p;

                if (!rb_u_string_dump_escape(buffer, c) &&
                    !rb_u_string_dump_hash(buffer, c, p, end) &&
                    !rb_u_string_dump_ascii_printable(buffer, c) &&
                    !rb_u_string_dump_codepoint(buffer, &p, end))
                        rb_u_string_dump_hex(buffer, c);

                p++;
        }
        rb_u_buffer_append(buffer, "\".u", 3);

        VALUE result = rb_u_buffer_to_u_bang(buffer);

        OBJ_INFECT(result, self);

        return result;
}