From d0f18cde7e40f1f6412bb35e8645888cd620682f Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Wed, 16 Sep 2015 14:50:12 -0400
Subject: [PATCH] Fix documentation of regular expression character-entry
escapes.
The docs claimed that \uhhhh would be interpreted as a Unicode value
regardless of the database encoding, but it's never been implemented
that way: \uhhhh and \xhhhh actually mean exactly the same thing, namely
the character that pg_mb2wchar translates to 0xhhhh. Moreover we were
falsely dismissive of the usefulness of Unicode code points above FFFF.
Fix that.
It's been like this for ages, so back-patch to all supported branches.
---
doc/src/sgml/func.sgml | 21 +++++++++++++++++----
1 file changed, 17 insertions(+), 4 deletions(-)
diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 22d4f615259..91a9379ae77 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -4669,7 +4669,7 @@ SELECT foo FROM regexp_split_to_table('the quick brown fox', E'\\s*') AS foo;
<entry> <literal>\e</> </entry>
<entry> the character whose collating-sequence name
is <literal>ESC</>,
- or failing that, the character with octal value 033 </entry>
+ or failing that, the character with octal value <literal>033</> </entry>
</row>
<row>
@@ -4695,15 +4695,17 @@ SELECT foo FROM regexp_split_to_table('the quick brown fox', E'\\s*') AS foo;
<row>
<entry> <literal>\u</><replaceable>wxyz</> </entry>
<entry> (where <replaceable>wxyz</> is exactly four hexadecimal digits)
- the UTF16 (Unicode, 16-bit) character <literal>U+</><replaceable>wxyz</>
- in the local byte ordering </entry>
+ the character whose hexadecimal value is
+ <literal>0x</><replaceable>wxyz</>
+ </entry>
</row>
<row>
<entry> <literal>\U</><replaceable>stuvwxyz</> </entry>
<entry> (where <replaceable>stuvwxyz</> is exactly eight hexadecimal
digits)
- reserved for a hypothetical Unicode extension to 32 bits
+ the character whose hexadecimal value is
+ <literal>0x</><replaceable>stuvwxyz</>
</entry>
</row>
@@ -4752,6 +4754,17 @@ SELECT foo FROM regexp_split_to_table('the quick brown fox', E'\\s*') AS foo;
Octal digits are <literal>0</>-<literal>7</>.
</para>
+ <para>
+ Numeric character-entry escapes specifying values outside the ASCII range
+ (0-127) have meanings dependent on the database encoding. When the
+ encoding is UTF-8, escape values are equivalent to Unicode code points,
+ for example <literal>\u1234</> means the character <literal>U+1234</>.
+ For other multibyte encodings, character-entry escapes usually just
+ specify the concatenation of the byte values for the character. If the
+ escape value does not correspond to any legal character in the database
+ encoding, no error will be raised, but it will never match any data.
+ </para>
+
<para>
The character-entry escapes are always taken as ordinary characters.
For example, <literal>\135</> is <literal>]</> in ASCII, but
--
GitLab