1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

string.c: multiple codepoints

Browse Source 
* string.c (undump_after_backslash): fix multiple codepoints in
  braces.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61290 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2017-12-16 00:30:52 +00:00
parent ae18c8f5b6
commit 7c18db61a1
2 changed files with 31 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
string.c
View File

@ -6160,16 +6160,18 @@ unescape_ascii(unsigned int c)
} }
} }
static int static long
undump_after_backslash(VALUE undumped, const char *s, const char *s_end, rb_encoding **penc) undump_after_backslash(VALUE undumped, const char *s, const char *s_end, rb_encoding **penc)
{ {
unsigned int c, c2; unsigned int c, c2;
int n, codelen; long n;
int codelen;
size_t hexlen; size_t hexlen;
char buf[6]; char buf[6];
static rb_encoding *enc_utf8 = NULL; static rb_encoding *enc_utf8 = NULL;
c = rb_enc_codepoint_len(s, s_end, &n, *penc); c = rb_enc_codepoint_len(s, s_end, &codelen, *penc);
n = codelen;
switch (c) { switch (c) {
case '\\': case '\\':
case '"': case '"':
@ -6203,31 +6205,30 @@ undump_after_backslash(VALUE undumped, const char *s, const char *s_end, rb_enco
if (c2 == '{') { /* handle \u{...} form */ if (c2 == '{') { /* handle \u{...} form */
const char *hexstr = s + 2; const char *hexstr = s + 2;
int hex; int hex;
static const char* const close_brace = "}";
long pos;
if (hexstr >= s_end) { while ((hex = rb_enc_ascget(hexstr, s_end, &codelen, *penc)) != '}') {
rb_raise(rb_eRuntimeError, "unterminated Unicode escape"); if (hex == -1) {
rb_raise(rb_eRuntimeError, "unterminated Unicode escape");
}
if (ISSPACE(hex)) {
hexstr += codelen;
continue;
}
hex = scan_hex(hexstr, s_end-hexstr, &hexlen);
if (hexlen == 0 || hexlen > 6) {
rb_raise(rb_eRuntimeError, "invalid Unicode escape");
}
if (hex > 0x10ffff) {
rb_raise(rb_eRuntimeError, "invalid Unicode codepoint (too large)");
}
if ((hex & 0xfffff800) == 0xd800) {
rb_raise(rb_eRuntimeError, "invalid Unicode codepoint");
}
codelen = rb_enc_mbcput(hex, buf, *penc);
rb_str_cat(undumped, buf, codelen);
hexstr += hexlen;
} }
/* find close brace */ n += hexstr - s + 1;
pos = strseq_core(hexstr, s_end, s_end - hexstr, close_brace, 1, 0, *penc);
if (pos < 0) {
rb_raise(rb_eRuntimeError, "unterminated Unicode escape");
}
hex = scan_hex(hexstr, pos, &hexlen);
if (hexlen == 0 || hexlen > 6) {
rb_raise(rb_eRuntimeError, "invalid Unicode escape");
}
if (hex > 0x10ffff) {
rb_raise(rb_eRuntimeError, "invalid Unicode codepoint (too large)");
}
if ((hex & 0xfffff800) == 0xd800) {
rb_raise(rb_eRuntimeError, "invalid Unicode codepoint");
}
codelen = rb_enc_codelen(hex, *penc);
rb_enc_mbcput(hex, buf, *penc);
rb_str_cat(undumped, buf, codelen);
n += rb_strlen_lit("u{}") + hexlen;
} }
else { /* handle \uXXXX form */ else { /* handle \uXXXX form */
int hex = scan_hex(s+1, 4, &hexlen); int hex = scan_hex(s+1, 4, &hexlen);
@ -6276,9 +6277,8 @@ str_undump(VALUE str)
{ {
const char *s = RSTRING_PTR(str); const char *s = RSTRING_PTR(str);
const char *s_end = RSTRING_END(str); const char *s_end = RSTRING_END(str);
long len = RSTRING_LEN(str); long len = RSTRING_LEN(str), n;
rb_encoding *enc = rb_enc_get(str), *forced_enc = NULL; rb_encoding *enc = rb_enc_get(str), *forced_enc = NULL;
int n;
unsigned int c; unsigned int c;
enum undump_source_format source_format; enum undump_source_format source_format;
VALUE undumped = rb_enc_str_new(s, 0L, enc); VALUE undumped = rb_enc_str_new(s, 0L, enc);
@ -6317,7 +6317,7 @@ str_undump(VALUE str)
} }
for (; s < s_end; s += n) { for (; s < s_end; s += n) {
c = rb_enc_codepoint_len(s, s_end, &n, enc); c = rb_enc_codepoint_len(s, s_end, &w, enc);
if (c == '\\') { if (c == '\\') {
if (s+1 >= s_end) { if (s+1 >= s_end) {
rb_raise(rb_eRuntimeError, "invalid escape"); rb_raise(rb_eRuntimeError, "invalid escape");
@ -6328,6 +6328,7 @@ str_undump(VALUE str)
rb_raise(rb_eRuntimeError, "non-escaped double quote detected"); rb_raise(rb_eRuntimeError, "non-escaped double quote detected");
} }
else { else {
n = w;
rb_str_cat(undumped, s, n); rb_str_cat(undumped, s, n);
} }
} }

1
test/ruby/test_string.rb
View File

@ -762,6 +762,7 @@ CODE
assert_equal(S("\uABCD"), S('"\\uABCD"').undump) assert_equal(S("\uABCD"), S('"\\uABCD"').undump)
assert_equal(S("\u{ABCDE}"), S('"\\u{ABCDE}"').undump) assert_equal(S("\u{ABCDE}"), S('"\\u{ABCDE}"').undump)
assert_equal(S("\u{10ABCD}"), S('"\\u{10ABCD}"').undump) assert_equal(S("\u{10ABCD}"), S('"\\u{10ABCD}"').undump)
assert_equal(S("\u{ABCDE 10ABCD}"), S('"\\u{ABCDE 10ABCD}"').undump)
assert_equal(S("äöü"), S('"\u00E4\u00F6\u00FC"').undump) assert_equal(S("äöü"), S('"\u00E4\u00F6\u00FC"').undump)
assert_equal(S("äöü"), S('"\xC3\xA4\xC3\xB6\xC3\xBC"').undump) assert_equal(S("äöü"), S('"\xC3\xA4\xC3\xB6\xC3\xBC"').undump)