instance method
String#undump
() -> ::String
undump → new_string
string.c
View on GitHub ↗
static VALUE
str_undump(VALUE str)
{
const char *s = RSTRING_PTR(str);
const char *s_end = RSTRING_END(str);
rb_encoding *enc = rb_enc_get(str);
VALUE undumped = rb_enc_str_new(s, 0L, enc);
bool utf8 = false;
bool binary = false;
int w;
rb_must_asciicompat(str);
if (rb_str_is_ascii_only_p(str) == Qfalse) {
rb_raise(rb_eRuntimeError, "non-ASCII character detected");
}
if (!str_null_check(str, &w)) {
rb_raise(rb_eRuntimeError, "string contains null byte");
}
if (RSTRING_LEN(str) < 2) goto invalid_format;
if (*s != '"') goto invalid_format;
/* strip '"' at the start */
s++;
for (;;) {
if (s >= s_end) {
rb_raise(rb_eRuntimeError, "unterminated dumped string");
}
if (*s == '"') {
/* epilogue */
s++;
if (s == s_end) {
/* ascii compatible dumped string */
break;
}
else {
static const char force_encoding_suffix[] = ".force_encoding(\""; /* "\")" */
static const char dup_suffix[] = ".dup";
const char *encname;
int encidx;
ptrdiff_t size;
/* check separately for strings dumped by older versions */
size = sizeof(dup_suffix) - 1;
if (s_end - s > size && memcmp(s, dup_suffix, size) == 0) s += size;
size = sizeof(force_encoding_suffix) - 1;
if (s_end - s <= size) goto invalid_format;
if (memcmp(s, force_encoding_suffix, size) != 0) goto invalid_format;
s += size;
if (utf8) {
rb_raise(rb_eRuntimeError, "dumped string contained Unicode escape but used force_encoding");
}
encname = s;
s = memchr(s, '"', s_end-s);
size = s - encname;
if (!s) goto invalid_format;
if (s_end - s != 2) goto invalid_format;
if (s[0] != '"' || s[1] != ')') goto invalid_format;
encidx = rb_enc_find_index2(encname, (long)size);
if (encidx < 0) {
rb_raise(rb_eRuntimeError, "dumped string has unknown encoding name");
}
rb_enc_associate_index(undumped, encidx);
}
break;
}
if (*s == '\\') {
s++;
if (s >= s_end) {
rb_raise(rb_eRuntimeError, "invalid escape");
}
undump_after_backslash(undumped, &s, s_end, &enc, &utf8, &binary);
}
else {
rb_str_cat(undumped, s++, 1);
}
}
RB_GC_GUARD(str);
return undumped;
invalid_format:
rb_raise(rb_eRuntimeError, "invalid dumped string; not wrapped with '\"' nor '\"...\".force_encoding(\"...\")' form");
}
Inverse of String#dump; returns a copy of self with changes of the kinds made by String#dump “undone.”
Related: see Converting to New String.
See also
#tr_s!
#unicode_normalize
#tr_s
#unicode_normalize!
also in
4.1 · 3.4 · 3.3 · 3.2 · 3.1 · 3.0