Allow empty replacement strings in contrib/unaccent.

tglsfdc · tglsfdc · commit 97c40ce61465 · 2014-06-30T20:51:30.000-04:00
This is useful in languages where diacritic signs are represented as
separate characters; it's also one step towards letting unaccent be used
for arbitrary substring substitutions.

In passing, improve the user documentation for unaccent, which was sadly
vague about some important details.

Mohammad Alhashash, reviewed by Abhijit Menon-Sen
diff --git a/contrib/unaccent/unaccent.c b/contrib/unaccent/unaccent.c
@@ -104,11 +104,21 @@ initTrie(char *filename)
 
 			while ((line = tsearch_readline(&trst)) != NULL)
 			{
-				/*
-				 * The format of each line must be "src trg" where src and trg
-				 * are sequences of one or more non-whitespace characters,
-				 * separated by whitespace.  Whitespace at start or end of
-				 * line is ignored.
+				/*----------
+				 * The format of each line must be "src" or "src trg", where
+				 * src and trg are sequences of one or more non-whitespace
+				 * characters, separated by whitespace.  Whitespace at start
+				 * or end of line is ignored.  If trg is omitted, an empty
+				 * string is used as the replacement.
+				 *
+				 * We use a simple state machine, with states
+				 *	0	initial (before src)
+				 *	1	in src
+				 *	2	in whitespace after src
+				 *	3	in trg
+				 *	4	in whitespace after trg
+				 *	-1	syntax error detected (line will be ignored)
+				 *----------
 				 */
 				int			state;
 				char	   *ptr;
@@ -160,7 +170,14 @@ initTrie(char *filename)
 					}
 				}
 
-				if (state >= 3)
+				if (state == 1 || state == 2)
+				{
+					/* trg was omitted, so use "" */
+					trg = "";
+					trglen = 0;
+				}
+
+				if (state > 0)
 					rootTrie = placeChar(rootTrie,
 										 (unsigned char *) src, srclen,
 										 trg, trglen);
diff --git a/doc/src/sgml/unaccent.sgml b/doc/src/sgml/unaccent.sgml
@@ -45,9 +45,9 @@
   <itemizedlist>
    <listitem>
     <para>
-     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,
+     Each line represents one translation rule, 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
@@ -57,6 +57,27 @@
 &Aring;        A
 &AElig;        A
 </programlisting>
+     The two characters must be separated by whitespace, and any leading or
+     trailing whitespace on a line is ignored.
+    </para>
+   </listitem>
+
+   <listitem>
+    <para>
+     Alternatively, if only one character is given on a line, instances of
+     that character are deleted; this is useful in languages where accents
+     are represented by separate characters.
+    </para>
+   </listitem>
+
+   <listitem>
+    <para>
+     As with other <productname>PostgreSQL</> text search configuration files,
+     the rules file must be stored in UTF-8 encoding.  The data is
+     automatically translated into the current database's encoding when
+     loaded.  Any lines containing untranslatable characters are silently
+     ignored, so that rules files can contain rules that are not applicable in
+     the current encoding.
     </para>
    </listitem>
   </itemizedlist>
@@ -132,8 +153,8 @@ mydb=# select ts_headline('fr','H&ocirc;tel de la Mer',to_tsquery('fr','Hotels')
 
  <para>
   The <function>unaccent()</> function removes accents (diacritic signs) from
-  a given string.  Basically, it's a wrapper around the
-  <filename>unaccent</> dictionary, but it can be used outside normal
+  a given string.  Basically, it's a wrapper around
+  <filename>unaccent</>-type dictionaries, but it can be used outside normal
   text search contexts.
  </para>
 
@@ -145,6 +166,11 @@ mydb=# select ts_headline('fr','H&ocirc;tel de la Mer',to_tsquery('fr','Hotels')
 unaccent(<optional><replaceable class="PARAMETER">dictionary</replaceable>, </optional> <replaceable class="PARAMETER">string</replaceable>) returns <type>text</type>
 </synopsis>
 
+ <para>
+  If the <replaceable class="PARAMETER">dictionary</replaceable> argument is
+  omitted, <literal>unaccent</> is assumed.
+ </para>
+
  <para>
   For example:
 <programlisting>
