From c6692d9410ab5b20ed3fa84db72d51d9a37a6179 Mon Sep 17 00:00:00 2001 From: duerst Date: Fri, 22 Jul 2016 08:13:38 +0000 Subject: * 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 --- ChangeLog | 8 ++++++++ string.c | 15 +++++++++++---- test/ruby/test_string.rb | 12 ++++++++++++ 3 files changed, 31 insertions(+), 4 deletions(-) diff --git a/ChangeLog b/ChangeLog index eeb792cf42..792c5865df 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,11 @@ +Fri Jul 22 17:13:37 2016 Martin Duerst + + * 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. + Fri Jul 22 10:35:35 2016 Kouhei Sutou * lib/rexml/attribute.rb (REXML::Attribute#to_string): Fix wrong diff --git a/string.c b/string.c index ec26a589f1..5b5f69a60a 100644 --- a/string.c +++ b/string.c @@ -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; } diff --git a/test/ruby/test_string.rb b/test/ruby/test_string.rb index 4df5f4f841..790fa21536 100644 --- a/test/ruby/test_string.rb +++ b/test/ruby/test_string.rb @@ -614,6 +614,18 @@ CODE def test_dump a= S("Test") << 1 << 2 << 3 << 9 << 13 << 10 assert_equal(S('"Test\\x01\\x02\\x03\\t\\r\\n"'), a.dump) + b= S("\u{7F}") + assert_equal(S('"\\x7F"'), b.dump) + b= S("\u{AB}") + assert_equal(S('"\\u00AB"'), b.dump) + b= S("\u{ABC}") + assert_equal(S('"\\u0ABC"'), b.dump) + b= S("\uABCD") + assert_equal(S('"\\uABCD"'), b.dump) + b= S("\u{ABCDE}") + assert_equal(S('"\\u{ABCDE}"'), b.dump) + b= S("\u{10ABCD}") + assert_equal(S('"\\u{10ABCD}"'), b.dump) end def test_dup -- cgit v1.2.3