mhs-xapian 1.0.18a

data/python/docs/examples/simpleindex.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python
+#
+# Index each paragraph of a text file as a Xapian document.
+#
+# Copyright (C) 2003 James Aylett
+# Copyright (C) 2004,2007 Olly Betts
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation; either version 2 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301
+# USA
+
+import sys
+import xapian
+import string
+
+
+if len(sys.argv) != 2:
+    print >> sys.stderr, "Usage: %s PATH_TO_DATABASE" % sys.argv[0]
+    sys.exit(1)
+
+try:
+    # Open the database for update, creating a new database if necessary.
+    database = xapian.WritableDatabase(sys.argv[1], xapian.DB_CREATE_OR_OPEN)
+
+    indexer = xapian.TermGenerator()
+    stemmer = xapian.Stem("english")
+    indexer.set_stemmer(stemmer)
+
+    para = ''
+    try:
+        for line in sys.stdin:
+            line = string.strip(line)
+            if line == '':
+                if para != '':
+                    # We've reached the end of a paragraph, so index it.
+                    doc = xapian.Document()
+                    doc.set_data(para)
+
+                    indexer.set_document(doc)
+                    indexer.index_text(para)
+
+                    # Add the document to the database.
+                    database.add_document(doc)
+                    para = ''
+            else:
+                if para != '':
+                    para += ' '
+                para += line
+    except StopIteration:
+        pass
+
+except Exception, e:
+    print >> sys.stderr, "Exception: %s" % str(e)
+    sys.exit(1)

data/python/docs/examples/simplematchdecider.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+#
+# Simple command-line match decider example
+#
+# Copyright (C) 2003 James Aylett
+# Copyright (C) 2004,2007,2009 Olly Betts
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation; either version 2 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
+# USA
+
+import sys
+import xapian
+
+# This example runs a query like simplesearch does, but uses a MatchDecider
+# (mymatchdecider) to discard any document for which value 0 is equal to
+# the string passed as the second command line argument.
+
+if len(sys.argv) < 4:
+    print >> sys.stderr, "Usage: %s PATH_TO_DATABASE AVOID_VALUE QUERY" % sys.argv[0]
+    sys.exit(1)
+
+class mymatchdecider(xapian.MatchDecider):
+    def __init__(self, avoidvalue):
+        xapian.MatchDecider.__init__(self)
+        self.avoidvalue = avoidvalue
+        
+    def __call__(self, doc):
+        return doc.get_value(0) != self.avoidvalue
+
+try:
+    # Open the database for searching.
+    database = xapian.Database(sys.argv[1])
+
+    # Start an enquire session.
+    enquire = xapian.Enquire(database)
+
+    # Combine the rest of the command line arguments with spaces between
+    # them, so that simple queries don't have to be quoted at the shell
+    # level.
+    avoid_value = sys.argv[2]
+    query_string = str.join(' ', sys.argv[3:])
+
+    # Parse the query string to produce a Xapian::Query object.
+    qp = xapian.QueryParser()
+    stemmer = xapian.Stem("english")
+    qp.set_stemmer(stemmer)
+    qp.set_database(database)
+    qp.set_stemming_strategy(xapian.QueryParser.STEM_SOME)
+    query = qp.parse_query(query_string)
+    print "Parsed query is: %s" % str(query)
+
+    # Find the top 10 results for the query.
+    enquire.set_query(query)
+    mdecider = mymatchdecider(avoid_value)
+    matches = enquire.get_mset(0, 10, None, mdecider)
+
+    # Display the results.
+    print "%i results found." % matches.get_matches_estimated()
+    print "Results 1-%i:" % matches.size()
+
+    for m in matches:
+        print "%i: %i%% docid=%i [%s]" % (m.rank + 1, m.percent, m.docid, m.document.get_data())
+
+except Exception, e:
+    print >> sys.stderr, "Exception: %s" % str(e)
+    sys.exit(1)

data/python/docs/examples/simplesearch.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python
+#
+# Simple command-line search script.
+#
+# Copyright (C) 2003 James Aylett
+# Copyright (C) 2004,2007,2009 Olly Betts
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation; either version 2 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
+# USA
+
+import sys
+import xapian
+
+# We require at least two command line arguments.
+if len(sys.argv) < 3:
+    print >> sys.stderr, "Usage: %s PATH_TO_DATABASE QUERY" % sys.argv[0]
+    sys.exit(1)
+
+try:
+    # Open the database for searching.
+    database = xapian.Database(sys.argv[1])
+
+    # Start an enquire session.
+    enquire = xapian.Enquire(database)
+
+    # Combine the rest of the command line arguments with spaces between
+    # them, so that simple queries don't have to be quoted at the shell
+    # level.
+    query_string = str.join(' ', sys.argv[2:])
+
+    # Parse the query string to produce a Xapian::Query object.
+    qp = xapian.QueryParser()
+    stemmer = xapian.Stem("english")
+    qp.set_stemmer(stemmer)
+    qp.set_database(database)
+    qp.set_stemming_strategy(xapian.QueryParser.STEM_SOME)
+    query = qp.parse_query(query_string)
+    print "Parsed query is: %s" % str(query)
+
+    # Find the top 10 results for the query.
+    enquire.set_query(query)
+    matches = enquire.get_mset(0, 10)
+
+    # Display the results.
+    print "%i results found." % matches.get_matches_estimated()
+    print "Results 1-%i:" % matches.size()
+
+    for m in matches:
+        print "%i: %i%% docid=%i [%s]" % (m.rank + 1, m.percent, m.docid, m.document.get_data())
+
+except Exception, e:
+    print >> sys.stderr, "Exception: %s" % str(e)
+    sys.exit(1)

data/python/docs/index.html

@@ -0,0 +1,420 @@
+<html><head><title>Python bindings for Xapian</title></head>
+<body>
+<h1>Python bindings for Xapian</h1>
+
+<p>
+The Python bindings for Xapian are packaged in the <code>xapian</code> module,
+and largely follow the C++ API, with the following differences and
+additions. Python strings and lists, etc., are converted automatically
+in the bindings, so generally it should just work as expected.
+</p>
+
+<p>
+The <code>examples</code> subdirectory contains examples showing how to use the
+Python bindings based on the simple examples from <code>xapian-examples</code>:
+<a href="examples/simpleindex.py">simpleindex.py</a>,
+<a href="examples/simplesearch.py">simplesearch.py</a>,
+<a href="examples/simpleexpand.py">simpleexpand.py</a>.
+There's also 
+<a href="examples/simplematchdecider.py">simplematchdecider.py</a>
+which shows how to define a MatchDecider in Python.
+</p>
+
+<p>
+The Python bindings come with a test suite, consisting of two test files:
+<code>smoketest.py</code> and <code>pythontest.py</code>. These are run by the
+"<code>make check</code>" command, or may be run manually.  By default, they
+will display the names of any tests which failed, and then display a count of
+tests which run and which failed.  The verbosity may be increased by setting
+the "<code>VERBOSE</code>" environment variable: a value of 1 will display
+detailed information about failures, and a value of 2 will display further
+information about the progress of tests.
+</p>
+
+<h2>Exceptions</h2>
+
+<p>
+   Xapian exceptions are translated into Python exceptions with the same names
+   and inheritance hierarchy as the C++ exception classes.  The base class of
+   all Xapian exceptions is the <code>xapian.Error</code> class, and this in
+   turn is a child of the standard python <code>exceptions.Exception</code>
+   class.
+</p>
+<p>
+   This means that programs can trap all xapian exceptions using "<code>except
+   xapian.Error</code>", and can trap all exceptions which don't indicate that
+   the program should terminate using "<code>except Exception</code>".
+</p>
+
+<h2>Unicode</h2>
+
+<p>
+   The xapian Python bindings accept unicode strings as well as simple strings
+   (ie, "str" type strings) at all places in the API which accept string data.
+   Any unicode strings supplied will automatically be translated into UTF-8
+   simple strings before being passed to the Xapian core.  The Xapian core is
+   largely agnostic about character encoding, but in those places where it does
+   process data in a character encoding dependent way it assumes that the data
+   is in UTF-8.  The Xapian Python bindings always return string data as simple
+   strings.
+</p>
+<p>
+   Therefore, in order to avoid issues with character encodings, you should
+   always pass text data to Xapian as unicode strings, or UTF-8 encoded simple
+   strings.  There is, however, no requirement for simple strings passed into
+   Xapian to be valid UTF-8 encoded strings, unless they are being passed to a
+   text processing routine (such as the query parser, or the stemming
+   algorithms).  For example, it is perfectly valid to pass arbitrary binary
+   data in a simple string to the <code>xapian.Document.set_data()</code>
+   method.
+</p>
+<p>
+   It is often useful to normalise unicode data before passing it to Xapian -
+   Xapian currently has no built-in support for normalising unicode
+   representations of data.  The standard python module
+   "<code>unicodedata</code>" provides support for normalising unicode: you
+   probably want the "<code>NFKC</code>" normalisation scheme: in other words,
+   use something like
+</p>
+<pre>
+   unicodedata.normalize('NFKC', u'foo')
+</pre>
+<p>
+   to normalise the string "foo" before passing it to Xapian.
+</p>
+
+<h2>Iterators</h2>
+
+<p>
+The iterator classes in the Xapian C++ API are wrapped in a "Pythonic" style.
+The following are supported (where marked as default iterator, it means
+<code>__iter__()</code> does the right
+thing so you can for instance use <code>for term in document</code> to
+iterate over terms in a Document object):
+</p>
+
+<table title="Python iterators">
+<thead><td>Class</td><td>Method</td><td>Equivalent to</td><td>Iterator type</td></thead>
+<tr><td><code>MSet</code></td><td>default iterator</td><td><code>begin()</code></td><td><code>MSetIter</code></td></tr>
+<tr><td><code>ESet</code></td><td>default iterator</td><td><code>begin()</code></td><td><code>ESetIter</code></td></tr>
+<tr><td><code>Enquire</code></td><td><code>matching_terms()</code></td><td><code>get_matching_terms_begin()</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Query</code></td><td>default iterator</td><td><code>get_terms_begin()</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>allterms()</code> (also as default iterator)</td><td><code>allterms_begin()</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>postlist(tname)</code></td><td><code>postlist_begin(tname)</code></td><td><code>PostingIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>termlist(docid)</code></td><td><code>termlist_begin(docid)</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>positionlist(docid, tname)</code></td><td><code>positionlist_begin(docid, tname)</code></td><td><code>PositionIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>metadata_keys(prefix)</code></td><td><code>metadata_keys_begin(prefix)</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>spellings()</code></td><td><code>spellings_begin(term)</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>synonyms(term)</code></td><td><code>synonyms_begin(term)</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Database</code></td><td><code>synonym_keys(prefix)</code></td><td><code>synonym_keys_begin(prefix)</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>Document</code></td><td><code>values()</code></td><td><code>values_begin()</code></td><td><code>ValueIter</code></td></tr>
+<tr><td><code>Document</code></td><td><code>termlist()</code> (also as default iterator)</td><td><code>termlist_begin()</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>QueryParser</code></td><td><code>stoplist()</code></td><td><code>stoplist_begin()</code></td><td><code>TermIter</code></td></tr>
+<tr><td><code>QueryParser</code></td><td><code>unstemlist(tname)</code></td><td><code>unstem_begin(tname)</code></td><td><code>TermIter</code></td></tr>
+</table>
+
+<p>
+The pythonic iterators return Python objects, with properties available as
+available as attribute values, with lazy evaluation where appropriate.  An
+exception is the <code>PositionIter</code> object returned by
+<code>Database.positionlist</code>, which returns an integer.
+</p>
+
+<p>
+The lazy evaluation is mainly transparent, but does become visible in one situation: if you keep an object returned by an iterator, without evaluating its properties to force the lazy evaluation to happen, and then move the iterator forward, the object may no longer be able to efficiently perform the lazy evaluation.  In this situation, an exception will be raised indicating that the information requested wasn't available.  This will only happen for a few of the properties - most are either not evaluated lazily (because the underlying Xapian implementation doesn't evaluate them lazily, so there's no advantage in lazy evaluation), or can be accessed even after the iterator has moved.  The simplest work around is simply to evaluate any properties you wish to use which are affected by this before moving the iterator.  The complete set of iterator properties affected by this is:
+</p>
+
+<ul>
+<li>
+Database.allterms (also accessible as Database.__iter__): <b>termfreq</b>
+</li><li>
+Database.termlist: <b>termfreq</b> and <b>positer</b>
+</li><li>
+Document.termlist (also accessible as Document.__iter__): <b>termfreq</b> and <b>positer</b>
+</li><li>
+Database.postlist: <b>positer</b>
+</li>
+</ul>
+
+<p>
+In older releases, the pythonic iterators returned lists representing the
+appropriate item when their <code>next()</code> method was called, except
+PositionIter which just returned a single value.  For backward compatibility,
+this sequence API is still supported so existing code should continue to work,
+but its use is now deprecated and it will be removed in Xapian 1.1.0, so we
+recommend users migrate to the new API.
+</p>
+
+<table title="Sequence API equivalents">
+<thead><td>Class</td><td>Returns</td></thead>
+<tr><td><code>MSetIter</code></td><td>[docid, weight, rank, percentage, document]</td></tr>
+<tr><td><code>ESetIter</code></td><td>[term, weight]</td></tr>
+<tr><td><code>TermIter</code></td><td>[term, wdf, termfreq, position iterator]</td></tr>
+<tr><td><code>PostingIter</code></td><td>[docid, doclength, wdf, position iterator]</td></tr>
+<tr><td><code>PositionIter</code></td><td>termpos</td></tr>
+<tr><td><code>ValueIter</code></td><td>[valueno, value]</td></tr>
+</table>
+   
+<h2>Non-Pythonic Iterators</h2>
+
+<p>
+Before the pythonic iterator wrappers were added, the python bindings provided
+thin wrappers around the C++ iterators.  However, these iterators don't behave
+like most iterators do in Python, so the pythonic iterators were implemented to
+replace them.  The non-pythonic iterators are still available to allow existing
+code to continue to work, but they're now deprecated and we plan to remove them
+in Xapian 1.3.0.  The documentation below is provided to aid migration away from
+them.
+</p>
+
+<p>
+   All non-pythonic iterators support <code>next()</code> and
+   <code>equals()</code> methods
+   to move through and test iterators (as for all language bindings).
+   MSetIterator and ESetIterator also support <code>prev()</code>.
+   Python-wrapped iterators also support direct comparison, so something like:
+</p>
+
+<pre>
+   m=mset.begin()
+   while m!=mset.end():
+     # do something
+     m.next()
+</pre>
+
+<p>
+   C++ iterators are often dereferenced to get information, eg
+   <code>(*it)</code>. With Python these are all mapped to named methods, as
+   follows:
+</p>
+
+<table title="Iterator deferencing methods">
+<thead><td>Iterator</td><td>Dereferencing method</td></thead>
+<tr><td>PositionIterator</td>	<td><code>get_termpos()</code></td></tr>
+<tr><td>PostingIterator</td>	<td><code>get_docid()</code></td></tr>
+<tr><td>TermIterator</td>	<td><code>get_term()</code></td></tr>
+<tr><td>ValueIterator</td>	<td><code>get_value()</code></td></tr>
+<tr><td>MSetIterator</td>	<td><code>get_docid()</code></td></tr>
+<tr><td>ESetIterator</td>	<td><code>get_term()</code></td></tr>
+</table>
+
+<p>
+   Other methods, such as <code>MSetIterator.get_document()</code>, are
+   available unchanged.
+</p>
+
+<h2>MSet</h2>
+
+<p>
+   MSet objects have some additional methods to simplify access (these
+   work using the C++ array dereferencing):
+</p>
+
+<table title="MSet additional methods">
+<thead><td>Method name</td><td>Explanation</td></thead>
+<tr><td><code>get_hit(index)</code></td><td>returns MSetItem at index</td></tr>
+<tr><td><code>get_document_percentage(index)</code></td><td><code>convert_to_percent(get_hit(index))</code></td></tr>
+<tr><td><code>get_document(index)</code></td><td><code>get_hit(index).get_document()</code></td></tr>
+<tr><td><code>get_docid(index)</code></td><td><code>get_hit(index).get_docid()</code></td></tr>
+</table>
+
+<p>
+Additionally, the MSet has a property, <code>mset.items</code>, which returns a
+list of tuples representing the MSet; this may be more convenient than using
+an MSetIter. The members of the tuple are as follows.
+</p>
+
+<table title="MSet.items member members">
+<thead><td>Index</td><td>Contents</td></thead>
+<tr><td><code>xapian.MSET_DID</code></td><td>Document id</td></tr>
+<tr><td><code>xapian.MSET_WT</code></td><td>Weight</td></tr>
+<tr><td><code>xapian.MSET_RANK</code></td><td>Rank</td></tr>
+<tr><td><code>xapian.MSET_PERCENT</code></td><td>Percentage weight</td></tr>
+<tr><td><code>xapian.MSET_DOCUMENT</code></td><td>Document object</td></tr>
+</table>
+
+<p>
+Two MSet objects are equal if they have the same number and maximum possible
+number of members, and if every document member of the first MSet exists at the
+same index in the second MSet, with the same weight.
+</p>
+
+<h2>ESet</h2>
+
+<p>
+The ESet has a property, <code>eset.items</code>, which returns a list of
+tuples representing the ESet; this may be more convenient than using the
+ESetIterator. The members of the tuple are as follows.
+</p>
+
+<table title="ESet.items member members">
+<thead><td>Index</td><td>Contents</td></thead>
+<tr><td><code>xapian.ESET_TNAME</code></td><td>Term name</td></tr>
+<tr><td><code>xapian.ESET_WT</code></td><td>Weight</td></tr>
+</table>
+
+<h2>Non-Class Functions</h2>
+
+<p>The C++ API contains a few non-class functions (the Database factory
+functions, and some functions reporting version information), which are
+wrapped like so for Python:
+<ul>
+<ul>
+<li> <code>Xapian::version_string()</code> is wrapped as <code>xapian.version_string()</code>
+<li> <code>Xapian::major_version()</code> is wrapped as <code>xapian.major_version()</code>
+<li> <code>Xapian::minor_version()</code> is wrapped as <code>xapian.minor_version()</code>
+<li> <code>Xapian::revision()</code> is wrapped as <code>xapian.revision()</code>
+</ul>
+<ul>
+<li> <code>Xapian::Auto::open_stub()</code> is wrapped as <code>xapian.open_stub()</code>
+<li> <code>Xapian::Flint::open()</code> is wrapped as <code>xapian.flint_open()</code>
+<li> <code>Xapian::InMemory::open()</code> is wrapped as <code>xapian.inmemory_open()</code>
+<li> <code>Xapian::Quartz::open()</code> is wrapped as <code>xapian.quartz_open()</code>
+<li> <code>Xapian::Remote::open()</code> is wrapped as <code>xapian.remote_open()</code> (both
+the TCP and "program" versions are wrapped - the SWIG wrapper checks the parameter list to
+decide which to call).
+<li> <code>Xapian::Remote::open_writable()</code> is wrapped as <code>xapian.remote_open_writable()</code> (both
+the TCP and "program" versions are wrapped - the SWIG wrapper checks the parameter list to
+decide which to call).
+</ul>
+</ul>
+
+<h2>Query</h2>
+
+<p>
+   In C++ there's a Xapian::Query constructor which takes a query operator and
+   start/end iterators specifying a number of terms or queries, plus an optional
+   parameter.  In Python, this is wrapped to accept any Python sequence (for
+   example a list or tuple) to give the terms/queries, and you can specify
+   a mixture of terms and queries if you wish.  For example:
+</p>
+
+<pre>
+   subq = xapian.Query(xapian.Query.OP_AND, "hello", "world")
+   q = xapian.Query(xapian.Query.OP_AND, [subq, "foo", xapian.Query("bar", 2)])
+</pre>
+
+<h2>Enquire</h2>
+
+<p>
+   There is an additional method <code>get_matching_terms()</code> which takes
+   an MSetIterator and returns a list of terms in the current query which
+   match the document given by that iterator.  You may find this
+   more convenient than using the TermIterator directly.
+</p>
+
+<h2>MatchDecider</h2>
+
+<p>
+Custom MatchDeciders can be created in Python; simply subclass
+xapian.MatchDecider, ensure you call the super-constructor, and define a
+__call__ method that will do the work. The simplest example (which does nothing
+useful) would be as follows:
+</p>
+
+<pre>
+class mymatchdecider(xapian.MatchDecider):
+  def __init__(self):
+    xapian.MatchDecider.__init__(self)
+
+  def __call__(self, doc):
+    return 1
+</pre>
+
+<h2>ValueRangeProcessors</h2>
+
+<p>
+The ValueRangeProcessor class (and its subclasses) provide an operator() method
+(which is exposed in python as a __call__() method, making the class instances
+into callables).  This method checks whether a beginning and end of a range are
+in a format understood by the ValueRangeProcessor, and if so, converts the
+beginning and end into strings which sort appropriately.  ValueRangeProcessors
+can be defined in python (and then passed to the QueryParser), or there are
+several default built-in ones which can be used.
+</p>
+
+<p>
+Unfortunately, in C++ the operator() method takes two std::string arguments by
+reference, and returns values by modifying these arguments.  This is not
+possible in Python, since strings are immutable objects.  Instead, in the
+Python implementation, when the __call__ method is called, the resulting values
+of these arguments are returned as part of a tuple.  The operator() method in
+C++ returns a value number; the return value of __call__ in python consists of
+a 3-tuple starting with this value number, followed by the returned "begin"
+value, followed by the returned "end" value.  For example:
+</p>
+
+<pre>
+    vrp = xapian.NumberValueRangeProcessor(0, '$', True)
+    a = '$10'
+    b = '20'
+    slot, a, b = vrp(a, b)
+</pre>
+
+<p>
+Additionally, a ValueRangeProcessor may be implemented in Python.  The Python
+implementation should override the __call__() method with its own
+implementation, and, again, since it cannot return values by reference, it
+should return a tuple of (value number, begin, end).  For example:
+</p>
+
+<pre>
+    class MyVRP(xapian.ValueRangeProcessor):
+        def __init__(self):
+            xapian.ValueRangeProcessor.__init__(self)
+        def __call__(self, begin, end):
+            return (7, "A"+begin, "B"+end)
+</pre>
+
+
+<h2>Apache and mod_python/mod_wsgi</h2>
+
+<p>
+By default, both mod_python and mod_wsgi use a separate sub-interpreter for
+each application.  However, Python's sub-interpreter support is incompatible
+with the simplified GIL state API which SWIG-generated Python bindings use
+by default.  So to avoid deadlocks, you need to tell mod_python and mod_wsgi
+to run applications which use Xapian in the main interpreter as detailed below.
+</p>
+
+<p>
+This restriction could be removed - the details are in Xapian's bugtracker - see
+<a href="http://trac.xapian.org/ticket/364">ticket #364</a> for details of
+what needs doing.
+</p>
+
+<h3 id="mod_python">mod_python</h3>
+
+<p>
+You need to set this option in the Apache configuration section for all
+mod_python scripts which use Xapian:
+</p>
+<pre>PythonInterpreter main_interpreter
+</pre>
+
+<p>
+You may also need to use Python &gt;= 2.4 (due to <a
+href="http://issues.apache.org/jira/browse/MODPYTHON-217">problems in Python
+2.3 with the APIs the code uses</a>).
+</p>
+
+<h3 id="mod_wsgi">mod_wsgi</h3>
+
+<p>
+You need to set the
+<a href="http://code.google.com/p/modwsgi/wiki/ConfigurationDirectives#WSGIApplicationGroup">WSGIApplicationGroup option</a> like so:
+</p>
+
+<pre>WSGIApplicationGroup %{GLOBAL}
+</pre>
+
+<p>
+The mod_wsgi documentation 
+<a href="http://code.google.com/p/modwsgi/wiki/ApplicationIssues#Python_Simplified_GIL_State_API">also discusses this issue</a>.
+</p>
+
+<address>
+Last updated $Date: 2009-05-23 08:20:54 +0100 (Sat, 23 May 2009) $
+</address>
+</body>
+</html>