mirror of
https://github.com/postgres/postgres.git
synced 2025-04-25 21:42:33 +03:00
Doc fixes for commit 1e16af8ab5.
Discussion: https://postgr.es/m/275c47ea-e7f3-e654-c99a-63bc116997d7@enterprisedb.com
This commit is contained in:
Jeff Davis
parent
5abff197cc
commit
f4a9422c0c
@ -386,11 +386,12 @@ initdb --locale-provider=icu --icu-locale=en
|
||||
linkend="icu-language-tag">Language Tag</link>.
|
||||
|
||||
<programlisting>
|
||||
CREATE COLLATION mycollation1 (PROVIDER = icu, LOCALE = 'ja-JP');
|
||||
CREATE COLLATION mycollation2 (PROVIDER = icu, LOCALE = 'fr');
|
||||
CREATE COLLATION mycollation1 (provider = icu, locale = 'ja-JP');
|
||||
CREATE COLLATION mycollation2 (provider = icu, locale = 'fr');
|
||||
</programlisting>
|
||||
</para>
|
||||
</sect3>
|
||||
|
||||
<sect3 id="icu-canonicalization">
|
||||
<title>Locale Canonicalization and Validation</title>
|
||||
<para>
|
||||
@ -399,14 +400,14 @@ CREATE COLLATION mycollation2 (PROVIDER = icu, LOCALE = 'fr');
|
||||
language tag if not already in that form. For instance,
|
||||
|
||||
<screen>
|
||||
CREATE COLLATION mycollation3 (PROVIDER = icu, LOCALE = 'en-US-u-kn-true');
|
||||
CREATE COLLATION mycollation3 (provider = icu, locale = 'en-US-u-kn-true');
|
||||
NOTICE: using standard form "en-US-u-kn" for locale "en-US-u-kn-true"
|
||||
CREATE COLLATION mycollation4 (PROVIDER = icu, LOCALE = 'de_DE.utf8');
|
||||
CREATE COLLATION mycollation4 (provider = icu, locale = 'de_DE.utf8');
|
||||
NOTICE: using standard form "de-DE" for locale "de_DE.utf8"
|
||||
</screen>
|
||||
|
||||
If you see this notice, ensure that the <symbol>PROVIDER</symbol> and
|
||||
<symbol>LOCALE</symbol> are the expected result. For consistent results
|
||||
If you see this notice, ensure that the <symbol>provider</symbol> and
|
||||
<symbol>locale</symbol> are the expected result. For consistent results
|
||||
when using the ICU provider, specify the canonical <link
|
||||
linkend="icu-language-tag">language tag</link> instead of relying on the
|
||||
transformation.
|
||||
@ -427,7 +428,7 @@ NOTICE: using standard form "de-DE" for locale "de_DE.utf8"
|
||||
the following warning:
|
||||
|
||||
<screen>
|
||||
CREATE COLLATION nonsense (PROVIDER = icu, LOCALE = 'nonsense');
|
||||
CREATE COLLATION nonsense (provider = icu, locale = 'nonsense');
|
||||
WARNING: ICU locale "nonsense" has unknown language "nonsense"
|
||||
HINT: To disable ICU locale validation, set parameter icu_validation_level to DISABLED.
|
||||
CREATE COLLATION
|
||||
@ -438,6 +439,7 @@ CREATE COLLATION
|
||||
still be created, but the behavior may not be what the user intended.
|
||||
</para>
|
||||
</sect3>
|
||||
|
||||
<sect3 id="icu-language-tag">
|
||||
<title>Language Tag</title>
|
||||
<para>
|
||||
@ -484,7 +486,7 @@ CREATE COLLATION
|
||||
of digits as a single number:
|
||||
|
||||
<screen>
|
||||
CREATE COLLATION mycollation5 (PROVIDER = icu, DETERMINISTIC = false, LOCALE = 'en-US-u-kn-ks-level2');
|
||||
CREATE COLLATION mycollation5 (provider = icu, deterministic = false, locale = 'en-US-u-kn-ks-level2');
|
||||
SELECT 'aB' = 'Ab' COLLATE mycollation5 as result;
|
||||
result
|
||||
--------
|
||||
@ -1109,16 +1111,16 @@ CREATE COLLATION ignore_accents (provider = icu, locale = 'und-u-ks-level1-kc-tr
|
||||
|
||||
<programlisting>
|
||||
-- ignore differences in accents and case
|
||||
CREATE COLLATION ignore_accent_case (PROVIDER = icu, DETERMINISTIC = false, LOCALE = 'und-u-ks-level1');
|
||||
CREATE COLLATION ignore_accent_case (provider = icu, deterministic = false, locale = 'und-u-ks-level1');
|
||||
SELECT 'Å' = 'A' COLLATE ignore_accent_case; -- true
|
||||
SELECT 'z' = 'Z' COLLATE ignore_accent_case; -- true
|
||||
|
||||
-- upper case letters sort before lower case.
|
||||
CREATE COLLATION upper_first (PROVIDER=icu, LOCALE = 'und-u-kf-upper');
|
||||
CREATE COLLATION upper_first (provider = icu, locale = 'und-u-kf-upper');
|
||||
SELECT 'B' < 'b' COLLATE upper_first; -- true
|
||||
|
||||
-- treat digits numerically and ignore punctuation
|
||||
CREATE COLLATION num_ignore_punct (PROVIDER = icu, DETERMINISTIC = false, LOCALE = 'und-u-ka-shifted-kn');
|
||||
CREATE COLLATION num_ignore_punct (provider = icu, deterministic = false, locale = 'und-u-ka-shifted-kn');
|
||||
SELECT 'id-45' < 'id-123' COLLATE num_ignore_punct; -- true
|
||||
SELECT 'w;x*y-z' = 'wxyz' COLLATE num_ignore_punct; -- true
|
||||
</programlisting>
|
||||
@ -1136,6 +1138,13 @@ SELECT 'w;x*y-z' = 'wxyz' COLLATE num_ignore_punct; -- true
|
||||
linkend="icu-collation-settings-table">collation settings</link>. Higher
|
||||
levels correspond to finer textual features.
|
||||
</para>
|
||||
<para>
|
||||
<xref linkend="icu-collation-levels"/> shows which textual feature
|
||||
differences are considered significant when determining equality at the
|
||||
given level. The unicode character <literal>U+2063</literal> is an
|
||||
invisible separator, and as seen in the table, is ignored for at all
|
||||
levels of comparison less than <literal>identic</literal>.
|
||||
</para>
|
||||
<para>
|
||||
<table id="icu-collation-levels">
|
||||
<title>ICU Collation Levels</title>
|
||||
@ -1215,20 +1224,13 @@ SELECT 'w;x*y-z' = 'wxyz' COLLATE num_ignore_punct; -- true
|
||||
</tgroup>
|
||||
</table>
|
||||
|
||||
The above table shows which textual feature differences are
|
||||
considered significant when determining equality at the given level. The
|
||||
unicode character <literal>U+2063</literal> is an invisible separator,
|
||||
and as seen in the table, is ignored for at all levels of comparison less
|
||||
than <literal>identic</literal>.
|
||||
</para>
|
||||
<para>
|
||||
At every level, even with full normalization off, basic normalization is
|
||||
performed. For example, <literal>'á'</literal> may be composed of the
|
||||
code points <literal>U&'\0061\0301'</literal> or the single code
|
||||
point <literal>U&'\00E1'</literal>, and those sequences will be
|
||||
considered equal even at the <literal>identic</literal> level. To treat
|
||||
any difference in code point representation as distinct, use a collation
|
||||
created with <symbol>DETERMINISTIC</symbol> set to
|
||||
created with <symbol>deterministic</symbol> set to
|
||||
<literal>true</literal>.
|
||||
</para>
|
||||
<sect4 id="icu-collation-level-examples">
|
||||
@ -1236,9 +1238,9 @@ SELECT 'w;x*y-z' = 'wxyz' COLLATE num_ignore_punct; -- true
|
||||
<para>
|
||||
|
||||
<programlisting>
|
||||
CREATE COLLATION level3 (PROVIDER=icu, DETERMINISTIC=false, LOCALE='und-u-ka-shifted-ks-level3');
|
||||
CREATE COLLATION level4 (PROVIDER=icu, DETERMINISTIC=false, LOCALE='und-u-ka-shifted-ks-level4');
|
||||
CREATE COLLATION identic (PROVIDER=icu, DETERMINISTIC=false, LOCALE='und-u-ka-shifted-ks-identic');
|
||||
CREATE COLLATION level3 (provider = icu, deterministic = false, locale = 'und-u-ka-shifted-ks-level3');
|
||||
CREATE COLLATION level4 (provider = icu, deterministic = false, locale = 'und-u-ka-shifted-ks-level4');
|
||||
CREATE COLLATION identic (provider = icu, deterministic = false, locale = 'und-u-ka-shifted-ks-identic');
|
||||
|
||||
-- invisible separator ignored at all levels except identic
|
||||
SELECT 'ab' = U&'a\2063b' COLLATE level4; -- true
|
||||
@ -1252,8 +1254,14 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
</para>
|
||||
</sect4>
|
||||
</sect3>
|
||||
|
||||
<sect3 id="icu-collation-settings">
|
||||
<title>Collation Settings for an ICU Locale</title>
|
||||
<para>
|
||||
<xref linkend="icu-collation-settings-table"/> shows the available
|
||||
collation settings, which can be used as part of a language tag to
|
||||
customize a collation.
|
||||
</para>
|
||||
<para>
|
||||
<table id="icu-collation-settings-table">
|
||||
<title>ICU Collation Settings</title>
|
||||
@ -1272,14 +1280,11 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
</thead>
|
||||
<tbody>
|
||||
<row>
|
||||
<entry><literal>ks</literal></entry>
|
||||
<entry><literal>level1</literal>, <literal>level2</literal>, <literal>level3</literal>, <literal>level4</literal>, <literal>identic</literal></entry>
|
||||
<entry><literal>level3</literal></entry>
|
||||
<entry><literal>co</literal></entry>
|
||||
<entry><literal>emoji</literal>, <literal>phonebk</literal>, <literal>standard</literal>, <replaceable>...</replaceable></entry>
|
||||
<entry><literal>standard</literal></entry>
|
||||
<entry>
|
||||
Sensitivity (or "strength") when determining equality, with
|
||||
<literal>level1</literal> the least sensitive to differences and
|
||||
<literal>identic</literal> the most sensitive to differences. See
|
||||
<xref linkend="icu-collation-levels"/> for details.
|
||||
Collation type. See <xref linkend="icu-external-references"/> for additional options and details.
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
@ -1304,29 +1309,6 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
before <literal>'aé'</literal>.
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>kk</literal></entry>
|
||||
<entry><literal>true</literal>, <literal>false</literal></entry>
|
||||
<entry><literal>false</literal></entry>
|
||||
<entry>
|
||||
<para>
|
||||
Enable full normalization; may affect performance. Basic
|
||||
normalization is performed even when set to
|
||||
<literal>false</literal>. Locales for languages that require full
|
||||
normalization typically enable it by default.
|
||||
</para>
|
||||
<para>
|
||||
Full normalization is important in some cases, such as when
|
||||
multiple accents are applied to a single character. For example,
|
||||
the code point sequences <literal>U&'\0065\0323\0302'</literal>
|
||||
and <literal>U&'\0065\0302\0323'</literal> represent
|
||||
an <literal>e</literal> with circumflex and dot-below accents
|
||||
applied in different orders. With full normalization
|
||||
on, these code point sequences are treated as equal; otherwise they
|
||||
are unequal.
|
||||
</para>
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>kc</literal></entry>
|
||||
<entry><literal>true</literal>, <literal>false</literal></entry>
|
||||
@ -1368,6 +1350,29 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
<literal>'id-123'</literal>.
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>kk</literal></entry>
|
||||
<entry><literal>true</literal>, <literal>false</literal></entry>
|
||||
<entry><literal>false</literal></entry>
|
||||
<entry>
|
||||
<para>
|
||||
Enable full normalization; may affect performance. Basic
|
||||
normalization is performed even when set to
|
||||
<literal>false</literal>. Locales for languages that require full
|
||||
normalization typically enable it by default.
|
||||
</para>
|
||||
<para>
|
||||
Full normalization is important in some cases, such as when
|
||||
multiple accents are applied to a single character. For example,
|
||||
the code point sequences <literal>U&'\0065\0323\0302'</literal>
|
||||
and <literal>U&'\0065\0302\0323'</literal> represent
|
||||
an <literal>e</literal> with circumflex and dot-below accents
|
||||
applied in different orders. With full normalization
|
||||
on, these code point sequences are treated as equal; otherwise they
|
||||
are unequal.
|
||||
</para>
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>kr</literal></entry>
|
||||
<entry>
|
||||
@ -1393,6 +1398,17 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
</para>
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>ks</literal></entry>
|
||||
<entry><literal>level1</literal>, <literal>level2</literal>, <literal>level3</literal>, <literal>level4</literal>, <literal>identic</literal></entry>
|
||||
<entry><literal>level3</literal></entry>
|
||||
<entry>
|
||||
Sensitivity (or "strength") when determining equality, with
|
||||
<literal>level1</literal> the least sensitive to differences and
|
||||
<literal>identic</literal> the most sensitive to differences. See
|
||||
<xref linkend="icu-collation-levels"/> for details.
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>kv</literal></entry>
|
||||
<entry>
|
||||
@ -1410,14 +1426,6 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
to <literal>level3</literal> or lower to take effect.
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry><literal>co</literal></entry>
|
||||
<entry><literal>emoji</literal>, <literal>phonebk</literal>, <literal>standard</literal>, <replaceable>...</replaceable></entry>
|
||||
<entry><literal>standard</literal></entry>
|
||||
<entry>
|
||||
Collation type. See <xref linkend="icu-external-references"/> for additional options and details.
|
||||
</entry>
|
||||
</row>
|
||||
</tbody>
|
||||
</tgroup>
|
||||
</table>
|
||||
@ -1428,7 +1436,7 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
<note>
|
||||
<para>
|
||||
For many collation settings, you must create the collation with
|
||||
<option>DETERMINISTIC</option> set to <literal>false</literal> for the
|
||||
<option>deterministic</option> set to <literal>false</literal> for the
|
||||
setting to have the desired effect (see <xref
|
||||
linkend="collation-nondeterministic"/>). Additionally, some settings
|
||||
only take effect when the key <literal>ka</literal> is set to
|
||||
@ -1437,6 +1445,7 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
</para>
|
||||
</note>
|
||||
</sect3>
|
||||
|
||||
<sect3 id="icu-locale-examples">
|
||||
<title>Examples</title>
|
||||
<para>
|
||||
@ -1487,6 +1496,7 @@ SELECT 'x-y' = 'x_y' COLLATE level4; -- false
|
||||
</variablelist>
|
||||
</para>
|
||||
</sect3>
|
||||
|
||||
<sect3 id="icu-external-references">
|
||||
<title>External References for ICU</title>
|
||||
<para>
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user