From a56c92f938f81df6b9d59b5bb7edc44008f0e06c Mon Sep 17 00:00:00 2001 From: Andrew Dunstan Date: Sat, 8 Jun 2013 10:21:06 -0400 Subject: [PATCH] Don't downcase non-ascii identifier chars in multi-byte encodings. MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Long-standing code has called tolower() on identifier character bytes with the high bit set. This is clearly an error and produces junk output when the encoding is multi-byte. This patch therefore restricts this activity to cases where there is a character with the high bit set AND the encoding is single-byte. There have been numerous gripes about this, most recently from Martin Schäfer. Backpatch to all live releases. --- src/backend/parser/scansup.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/src/backend/parser/scansup.c b/src/backend/parser/scansup.c index 6101457a10..1c39fd3a3f 100644 --- a/src/backend/parser/scansup.c +++ b/src/backend/parser/scansup.c @@ -130,8 +130,10 @@ downcase_truncate_identifier(const char *ident, int len, bool warn) { char *result; int i; + bool enc_is_single_byte; result = palloc(len + 1); + enc_is_single_byte = pg_database_encoding_max_length() == 1; /* * SQL99 specifies Unicode-aware case normalization, which we don't yet @@ -139,8 +141,8 @@ downcase_truncate_identifier(const char *ident, int len, bool warn) * locale-aware translation. However, there are some locales where this * is not right either (eg, Turkish may do strange things with 'i' and * 'I'). Our current compromise is to use tolower() for characters with - * the high bit set, and use an ASCII-only downcasing for 7-bit - * characters. + * the high bit set, as long as they aren't part of a multi-byte character, + * and use an ASCII-only downcasing for 7-bit characters. */ for (i = 0; i < len; i++) { @@ -148,7 +150,7 @@ downcase_truncate_identifier(const char *ident, int len, bool warn) if (ch >= 'A' && ch <= 'Z') ch += 'a' - 'A'; - else if (IS_HIGHBIT_SET(ch) && isupper(ch)) + else if (enc_is_single_byte && IS_HIGHBIT_SET(ch) && isupper(ch)) ch = tolower(ch); result[i] = (char) ch; } -- 2.40.0