Module for accessing apt-xapian-index.

debexpo/lib/axi.py

+# -*- coding: utf-8 -*-
+#
+#   axi.py — Access to apt-xapian-index
+#
+#   This file is part of debexpo - https://alioth.debian.org/projects/debexpo/
+#
+#   Copyright © 2012 Clément Schreiner <clement@mux.me>
+#
+#
+#   Permission is hereby granted, free of charge, to any person
+#   obtaining a copy of this software and associated documentation
+#   files (the "Software"), to deal in the Software without
+#   restriction, including without limitation the rights to use,
+#   copy, modify, merge, publish, distribute, sublicense, and/or sell
+#   copies of the Software, and to permit persons to whom the
+#   Software is furnished to do so, subject to the following
+#   conditions:
+#
+#   The above copyright notice and this permission notice shall be
+#   included in all copies or substantial portions of the Software.
+#
+#   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+#   EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+#   OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+#   NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+#   HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+#   WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+#   FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+#   OTHER DEALINGS IN THE SOFTWARE.
+
+import xapian
+
+"""
+Classes for accessing apt-xapian-index
+"""
+
+
+class XapianQuery(object):
+    """
+    Search packages in apt-xapian-index.
+    """
+
+    def __init__(self):
+        self.db = xapian.Database('/var/lib/apt-xapian-index/index')
+        self.stemmer = xapian.Stem("english")
+
+        self.terms = []
+
+    @classmethod
+    def _clean_word(cls, word):
+        """
+        Remove unwanted characters from a word and make it lowercase.
+        """
+        return word.strip(':;,-.*\n').replace('<br />', '').lower()
+
+    @classmethod
+    def tokenize(cls, text):
+        """
+        Takes a string and returns a list of words ready for a xapian
+        query.
+        """
+        return [cls._clean_word(word) for word in text.split(' ')]
+
+    def add_words(self, word_list):
+        """
+        Add words and their stemmed version to the query terms.
+        """
+        for word in word_list:
+            self.terms.append(word)
+            stem = self.stemmer(word)
+            if stem != word:
+                self.terms.append('Z'+stem)
+
+    def add_text(self, description):
+        """
+        Process a text and add its words to the query terms.
+        """
+        self.add_words(self.tokenize(description))
+
+    def add_tags(self, tags):
+        """
+        Add tags from an iterable to the query terms.
+        """
+        for tag in tags:
+            self.terms.append('XT'+tag)
+
+    def query(self):
+        """
+        Actually performs the query and return the results as a
+        generator.
+        """
+        query = xapian.Query(xapian.Query.OP_OR, self.terms)
+        enquire = xapian.Enquire(self.db)
+        enquire.set_query(query)
+
+        matches = enquire.get_mset(0, 20)
+        for m in matches:
+            yield m.document.get_data(), m.percent