Close previously open holes for invalidly encoded data to enter the

database via builtin functions, as recently discussed on -hackers.

chr() now returns a character in the database encoding. For UTF8 encoded databases
the argument is treated as a Unicode code point. For other multi-byte encodings
the argument must designate a strict ascii character, or an error is raised,
as is also the case if the argument is 0.

ascii() is adjusted so that it remains the inverse of chr().

The two argument form of convert() is gone, and the three argument form now
takes a bytea first argument and returns a bytea. To cover this loss three new
functions are introduced:
. convert_from(bytea, name) returns text - converts the first argument from the
  named encoding to the database encoding
. convert_to(text, name) returns bytea - converts the first argument from the
  database encoding to the named encoding
. length(bytea, name) returns int - gives the length of the first argument in
  characters in the named encoding

1 files changed, 68 insertions, 11 deletions

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 393c1e31766..b3dae7dcead 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.395 2007/09/14 15:53:48 momjian Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.396 2007/09/18 17:41:16 adunstan Exp $ -->
 
  <chapter id="functions">
   <title>Functions and Operators</title>
@@ -1122,13 +1122,14 @@
       <row>
        <entry><literal><function>convert</function>(<parameter>string</parameter>
        using <parameter>conversion_name</parameter>)</literal></entry>
-       <entry><type>text</type></entry>
+       <entry><type>bytea</type></entry>
        <entry>
         Change encoding using specified conversion name.  Conversions
         can be defined by <command>CREATE CONVERSION</command>.  Also
         there are some pre-defined conversion names. See <xref
         linkend="conversion-names"> for available conversion
-        names.
+        names. The <parameter>string</parameter> must be valid in the
+		source encoding.
        </entry>
        <entry><literal>convert('PostgreSQL' using iso_8859_1_to_utf8)</literal></entry>
        <entry><literal>'PostgreSQL'</literal> in UTF8 (Unicode, 8-bit) encoding</entry>
@@ -1245,6 +1246,12 @@
     <primary>chr</primary>
    </indexterm>
    <indexterm>
+    <primary>convert_from</primary>
+   </indexterm>
+   <indexterm>
+    <primary>convert_to</primary>
+   </indexterm>
+   <indexterm>
     <primary>decode</primary>
    </indexterm>
    <indexterm>
@@ -1319,7 +1326,12 @@
       <row>
        <entry><literal><function>ascii</function>(<parameter>string</parameter>)</literal></entry>
        <entry><type>int</type></entry>
-       <entry><acronym>ASCII</acronym> code of the first byte of the argument</entry>
+       <entry>
+	     <acronym>ASCII</acronym> code of the first character of the argument. 
+		 For <acronym>UTF8</acronym> returns the Unicode code point of the character. 
+		 For other multi-byte encodings. the argument must be a strictly 
+		 <acronym>ASCII</acronym> character.
+	   </entry>
        <entry><literal>ascii('x')</literal></entry>
        <entry><literal>120</literal></entry>
       </row>
@@ -1340,24 +1352,27 @@
       <row>
        <entry><literal><function>chr</function>(<type>int</type>)</literal></entry>
        <entry><type>text</type></entry>
-       <entry>Character with the given <acronym>ASCII</acronym> code</entry>
+       <entry>
+	     Character with the given code. For <acronym>UTF8</acronym> the argument is
+		 treated as a Unicode code point. For other multi-byte encodings the argument
+		 must designate a strictly <acronym>ASCII</acronym> character.
+	   </entry>
        <entry><literal>chr(65)</literal></entry>
        <entry><literal>A</literal></entry>
       </row>
 
       <row>
        <entry>
-        <literal><function>convert</function>(<parameter>string</parameter> <type>text</type>,
-        <optional><parameter>src_encoding</parameter> <type>name</type>,</optional>
+        <literal><function>convert</function>(<parameter>string</parameter> <type>bytea</type>,
+        <parameter>src_encoding</parameter> <type>name</type>,
         <parameter>dest_encoding</parameter> <type>name</type>)</literal>
        </entry>
-       <entry><type>text</type></entry>
+       <entry><type>bytea</type></entry>
        <entry>
         Convert string to <parameter>dest_encoding</parameter>.
         The original encoding is specified by
-        <parameter>src_encoding</parameter>.  If
-        <parameter>src_encoding</parameter> is omitted, database
-        encoding is assumed.
+		<parameter>src_encoding</parameter>. The <parameter>string</parameter>
+		must be valid in this encoding.
        </entry>
        <entry><literal>convert( 'text_in_utf8', 'UTF8', 'LATIN1')</literal></entry>
        <entry><literal>text_in_utf8</literal> represented in ISO 8859-1 encoding</entry>
@@ -1365,6 +1380,35 @@
 
       <row>
        <entry>
+        <literal><function>convert_from</function>(<parameter>string</parameter> <type>bytea</type>,
+        <parameter>src_encoding</parameter> <type>name</type>)</literal>
+       </entry>
+       <entry><type>text</type></entry>
+       <entry>
+        Convert string to the database encoding.
+        The original encoding is specified by
+		<parameter>src_encoding</parameter>. The <parameter>string</parameter>
+		must be valid in this encoding.
+       </entry>
+       <entry><literal>convert_from( 'text_in_utf8', 'UTF8')</literal></entry>
+       <entry><literal>text_in_utf8</literal> represented in the current database encoding</entry>
+      </row>
+
+      <row>
+       <entry>
+        <literal><function>convert_to</function>(<parameter>string</parameter> <type>text</type>,
+        <parameter>dest_encoding</parameter> <type>name</type>)</literal>
+       </entry>
+       <entry><type>text</type></entry>
+       <entry>
+        Convert string to <parameter>dest_encoding</parameter>.
+       </entry>
+       <entry><literal>convert_to( 'some text', 'UTF8')</literal></entry>
+       <entry><literal>some text</literal> represented in the UTF8 encoding</entry>
+      </row>
+
+      <row>
+       <entry>
         <literal><function>decode</function>(<parameter>string</parameter> <type>text</type>,
         <parameter>type</parameter> <type>text</type>)</literal>
        </entry>
@@ -1416,6 +1460,19 @@
       </row>
 
       <row>
+       <entry><literal><function>length</function>(<parameter>string</parameter><type>bytea</type>,
+        <parameter>encoding</parameter> <type>name</type> )</literal></entry>
+       <entry><type>int</type></entry>
+       <entry>
+        Number of characters in <parameter>string</parameter> in the 
+		given <parameter>encoding</parameter>. The 
+		<parameter>string</parameter> must be valid in this encoding.
+       </entry>
+       <entry><literal>length('jose', 'UTF8')</literal></entry>
+       <entry><literal>4</literal></entry>
+      </row>
+
+      <row>
        <entry>
         <literal><function>lpad</function>(<parameter>string</parameter> <type>text</type>,
         <parameter>length</parameter> <type>int</type>