diff options
| author | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-07-22 08:13:38 +0000 |
|---|---|---|
| committer | duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2016-07-22 08:13:38 +0000 |
| commit | c6692d9410ab5b20ed3fa84db72d51d9a37a6179 (patch) | |
| tree | 95e02bdf839098fed2ea6765f4f24be09ff36915 /string.c | |
| parent | 21269d37a110f78d84e875af8efa2f511e101717 (diff) | |
* string.c (String#dump): Change escaping of non-ASCII characters in
UTF-8 to use upper-case four-digit hexadecimal escapes without braces
where possible [Feature #12419].
* test/ruby/test_string.rb (test_dump): Add tests for above.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55728 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'string.c')
| -rw-r--r-- | string.c | 15 |
1 files changed, 11 insertions, 4 deletions
@@ -5656,12 +5656,16 @@ rb_str_dump(VALUE str) len++; } else { - if (u8 && c > 0x7F) { /* \u{NN} */ + if (u8 && c > 0x7F) { /* \u notation */ int n = rb_enc_precise_mbclen(p-1, pend, enc); if (MBCLEN_CHARFOUND_P(n)) { unsigned int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc); - while (cc >>= 4) len++; - len += 5; + if (cc <= 0xFFFF) + len += 6; /* \uXXXX */ + else if (cc <= 0xFFFFF) + len += 9; /* \u{XXXXX} */ + else + len += 10; /* \u{XXXXXX} */ p += MBCLEN_CHARFOUND_LEN(n)-1; break; } @@ -5734,7 +5738,10 @@ rb_str_dump(VALUE str) if (MBCLEN_CHARFOUND_P(n)) { int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc); p += n; - snprintf(q, qend-q, "u{%x}", cc); + if (cc <= 0xFFFF) + snprintf(q, qend-q, "u%04X", cc); /* \uXXXX */ + else + snprintf(q, qend-q, "u{%X}", cc); /* \u{XXXXX} or \u{XXXXXX} */ q += strlen(q); continue; } |