Docs review for unaccent: fix grammar, markup, etc.

doc/src/sgml/unaccent.sgml

@@ -1,3 +1,5 @@
+<!-- $PostgreSQL: pgsql/doc/src/sgml/unaccent.sgml,v 1.6 2010/08/25 02:12:00 tgl Exp $ -->
+
 <sect1 id="unaccent">
  <title>unaccent</title>
 
@@ -6,24 +8,24 @@
  </indexterm>
 
  <para>
-  <filename>unaccent</> removes accents (diacritic signs) from a lexeme.
+  <filename>unaccent</> is a text search dictionary that removes accents
-  It's a filtering dictionary, that means its output is 
+  (diacritic signs) from lexemes.
-  always passed to the next dictionary (if any), contrary to the standard 
+  It's a filtering dictionary, which means its output is
-  behavior. Currently, it supports most important accents from European 
+  always passed to the next dictionary (if any), unlike the normal
-  languages. 
+  behavior of dictionaries.  This allows accent-insensitive processing
+  for full text search.
  </para>
 
  <para>
-  Limitation: Current implementation of <filename>unaccent</> 
+  The current implementation of <filename>unaccent</> cannot be used as a
-  dictionary cannot be used as a normalizing dictionary for 
+  normalizing dictionary for the <filename>thesaurus</filename> dictionary.
-  <filename>thesaurus</filename> dictionary.
  </para>
 
  <sect2>
   <title>Configuration</title>
 
   <para>
-   A <literal>unaccent</> dictionary accepts the following options:
+   An <literal>unaccent</> dictionary accepts the following options:
   </para>
   <itemizedlist>
    <listitem>
@@ -43,23 +45,27 @@
   <itemizedlist>
    <listitem>
     <para>
-     Each line represents pair: character_with_accent  character_without_accent
+     Each line represents a pair, consisting of a character with accent
+     followed by a character without accent.  The first is translated into
+     the second.  For example,
 <programlisting>
 &Agrave;        A
 &Aacute;        A
-&Acirc;         A
+&Acirc;        A
 &Atilde;        A
-&Auml;          A
+&Auml;        A
-&Aring;         A
+&Aring;        A
-&AElig;         A
+&AElig;        A
 </programlisting>
     </para>
    </listitem>
   </itemizedlist>
 
   <para>
-   Look at <filename>unaccent.rules</>, which is installed in
+   A more complete example, which is directly useful for most European
-   <filename>$SHAREDIR/tsearch_data/</>, for an example.
+   languages, can be found in <filename>unaccent.rules</>, which is installed
+   in <filename>$SHAREDIR/tsearch_data/</> when the <filename>unaccent</>
+   module is installed.
   </para>
  </sect2>
 
@@ -67,23 +73,22 @@
   <title>Usage</title>
 
   <para>
-   Running the installation script creates a text search template
+   Running the installation script <filename>unaccent.sql</> creates a text
-   <literal>unaccent</> and a dictionary <literal>unaccent</>
+   search template <literal>unaccent</> and a dictionary <literal>unaccent</>
    based on it, with default parameters.  You can alter the
    parameters, for example
 
 <programlisting>
-=# ALTER TEXT SEARCH DICTIONARY unaccent (RULES='my_rules');
+mydb=# ALTER TEXT SEARCH DICTIONARY unaccent (RULES='my_rules');
 </programlisting>
 
    or create new dictionaries based on the template.
   </para>
 
   <para>
-   To test the dictionary, you can try
+   To test the dictionary, you can try:
-
 <programlisting>
-=# select ts_lexize('unaccent','Hôtel');
+mydb=# select ts_lexize('unaccent','H&ocirc;tel');
  ts_lexize
 -----------
  {Hotel}
@@ -92,41 +97,42 @@
   </para>
 
   <para>
-  Filtering dictionary are useful for correct work of 
+   Here is an example showing how to insert the
-  <function>ts_headline</function> function.
+   <filename>unaccent</> dictionary into a text search configuration:
 <programlisting>
-=# CREATE TEXT SEARCH CONFIGURATION fr ( COPY = french );
+mydb=# CREATE TEXT SEARCH CONFIGURATION fr ( COPY = french );
-=# ALTER TEXT SEARCH CONFIGURATION fr
+mydb=# ALTER TEXT SEARCH CONFIGURATION fr
         ALTER MAPPING FOR hword, hword_part, word
         WITH unaccent, french_stem;
-=# select to_tsvector('fr','Hôtels de la Mer');
+mydb=# select to_tsvector('fr','H&ocirc;tels de la Mer');
     to_tsvector
 -------------------
  'hotel':1 'mer':4
 (1 row)
 
-=# select to_tsvector('fr','Hôtel de la Mer') @@ to_tsquery('fr','Hotels');
+mydb=# select to_tsvector('fr','H&ocirc;tel de la Mer') @@ to_tsquery('fr','Hotels');
  ?column?
 ----------
  t
 (1 row)
-=# select ts_headline('fr','Hôtel de la Mer',to_tsquery('fr','Hotels'));
+
+mydb=# select ts_headline('fr','H&ocirc;tel de la Mer',to_tsquery('fr','Hotels'));
       ts_headline
 ------------------------
-  &lt;b&gt;Hôtel&lt;/b&gt;de la Mer
+ &lt;b&gt;H&ocirc;tel&lt;/b&gt; de la Mer
 (1 row)
-
 </programlisting>
   </para>
  </sect2>
 
  <sect2>
- <title>Function</title>
+ <title>Functions</title>
 
  <para>
-  <function>unaccent</> function removes accents (diacritic signs) from
+  The <function>unaccent()</> function removes accents (diacritic signs) from
-  argument string. Basically, it's a wrapper around 
+  a given string.  Basically, it's a wrapper around the
-  <filename>unaccent</> dictionary.
+  <filename>unaccent</> dictionary, but it can be used outside normal
+  text search contexts.
  </para>
 
  <indexterm>
@@ -134,14 +140,14 @@
  </indexterm>
 
 <synopsis>
-unaccent(<optional><replaceable class="PARAMETER">dictionary</replaceable>, </optional> <replaceable class="PARAMETER">string</replaceable>)
+unaccent(<optional><replaceable class="PARAMETER">dictionary</replaceable>, </optional> <replaceable class="PARAMETER">string</replaceable>) returns <type>text</type>
-returns <type>text</type>
 </synopsis>
 
  <para>
+  For example:
 <programlisting>
-SELECT unaccent('unaccent', 'Hôtel');
+SELECT unaccent('unaccent', 'H&ocirc;tel');
-SELECT unaccent('Hôtel');
+SELECT unaccent('H&ocirc;tel');
 </programlisting>
  </para>
  </sect2>