From 2aac6f10f65fa2baf37d2dcafc9aebc6098b035a Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Sat, 27 Oct 2007 00:19:45 +0000
Subject: [PATCH] Minor wording improvements per suggestion from Jeff Davis. 
 Also tweak hyphenated-word parser examples per earlier discussion with
 Alvaro.

---
 doc/src/sgml/textsearch.sgml | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/doc/src/sgml/textsearch.sgml b/doc/src/sgml/textsearch.sgml
index a83582a39ca..71e29dbfcbf 100644
--- a/doc/src/sgml/textsearch.sgml
+++ b/doc/src/sgml/textsearch.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.26 2007/10/25 13:06:35 alvherre Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/textsearch.sgml,v 1.27 2007/10/27 00:19:45 tgl Exp $ -->
 
 <chapter id="textsearch">
  <title id="textsearch-title">Full Text Search</title>
@@ -1770,7 +1770,7 @@ LIMIT 10;
      <row>
       <entry><literal>hword</></entry>
       <entry>Hyphenated word, all letters</entry>
-      <entry><literal>pol&iacute;tico-militar</literal></entry>
+      <entry><literal>l&oacute;gico-matem&aacute;tica</literal></entry>
      </row>
      <row>
       <entry><literal>numhword</></entry>
@@ -1780,14 +1780,13 @@ LIMIT 10;
      <row>
       <entry><literal>hword_asciipart</></entry>
       <entry>Hyphenated word part, all ASCII</entry>
-      <entry><literal>militar</literal> in the context
-       <literal>pol&iacute;tico-militar</literal>, or <literal>postgresql</literal> in the context <literal>postgresql-beta1</literal></entry>
+      <entry><literal>postgresql</literal> in the context <literal>postgresql-beta1</literal></entry>
      </row>
      <row>
       <entry><literal>hword_part</></entry>
       <entry>Hyphenated word part, all letters</entry>
-      <entry><literal>f&iacute;sico</literal> or <literal>qu&iacute;mico</literal>
-       in the context <literal>f&iacute;sico-qu&iacute;mico</literal></entry>
+      <entry><literal>l&oacute;gico</literal> or <literal>matem&aacute;tica</literal>
+       in the context <literal>l&oacute;gico-matem&aacute;tica</literal></entry>
      </row>
      <row>
       <entry><literal>hword_numpart</></entry>
@@ -1902,12 +1901,12 @@ SELECT alias, description, token FROM ts_debug('foo-bar-beta1');
    instructive example:
 
 <programlisting>
-SELECT alias, description, token FROM ts_debug('http://foo.com/stuff/index.html');
-  alias   |  description  |          token           
-----------+---------------+--------------------------
+SELECT alias, description, token FROM ts_debug('http://example.com/stuff/index.html');
+  alias   |  description  |            token             
+----------+---------------+------------------------------
  protocol | Protocol head | http://
- url      | URL           | foo.com/stuff/index.html
- host     | Host          | foo.com
+ url      | URL           | example.com/stuff/index.html
+ host     | Host          | example.com
  uri      | URI           | /stuff/index.html
 </programlisting>
   </para>
@@ -3093,8 +3092,9 @@ SELECT plainto_tsquery('supernovae stars');
   </para>
 
   <para>
-   A GiST index is <firstterm>lossy</firstterm>, meaning it is necessary
-   to check the actual table row to eliminate false matches.
+   A GiST index is <firstterm>lossy</firstterm>, meaning that the index
+   may produce false matches, and it is necessary
+   to check the actual table row to eliminate such false matches.
    <productname>PostgreSQL</productname> does this automatically; for
    example, in the query plan below, the <literal>Filter:</literal>
    line indicates the index output will be rechecked:
@@ -3112,14 +3112,15 @@ EXPLAIN SELECT * FROM apod WHERE textsearch @@ to_tsquery('supernovae');
    index by a fixed-length signature. The signature is generated by hashing
    each word into a random bit in an n-bit string, with all these bits OR-ed
    together to produce an n-bit document signature.  When two words hash to
-   the same bit position there will be a false match, and if all words in
+   the same bit position there will be a false match.  If all words in
    the query have matches (real or false) then the table row must be
    retrieved to see if the match is correct.
   </para>
 
   <para>
-   Lossiness causes performance degradation since random access to table
-   records is slow; this limits the usefulness of GiST indexes.  The
+   Lossiness causes performance degradation due to useless fetches of table
+   records that turn out to be false matches.  Since random access to table
+   records is slow, this limits the usefulness of GiST indexes.  The
    likelihood of false matches depends on several factors, in particular the
    number of unique words, so using dictionaries to reduce this number is
    recommended.
-- 
GitLab