for #167, moving contacts suggestions search logic to a separate module

2 files changed, 57 insertions, 22 deletions

diff --git a/service/pixelated/adapter/search/__init__.py b/service/pixelated/adapter/search/__init__.py
index 12829c65..eedeaa45 100644
--- a/service/pixelated/adapter/search/__init__.py
+++ b/service/pixelated/adapter/search/__init__.py
@@ -18,13 +18,11 @@ from pixelated.support.encrypted_file_storage import EncryptedFileStorage
 
 import os
 from pixelated.adapter.model.status import Status
-from pixelated.adapter.contacts import address_duplication_filter
-from pixelated.support.functional import flatten
+from pixelated.adapter.search.contacts import contacts_suggestions
 from whoosh.index import FileIndex
 from whoosh.fields import *
 from whoosh.qparser import QueryParser
 from whoosh.qparser import MultifieldParser
-from whoosh.query import Term
 from whoosh import sorting
 from pixelated.support.functional import unique
 from pixelated.support.date import milliseconds
@@ -196,22 +194,5 @@ class SearchEngine(object):
                 writer.commit()
 
     def contacts(self, query):
-        restrict_q = Term("tag", "drafts") | Term("tag", "trash")
-
-        if query:
-            to = QueryParser('to', self._index.schema)
-            cc = QueryParser('cc', self._index.schema)
-            bcc = QueryParser('bcc', self._index.schema)
-            sender = QueryParser('sender', self._index.schema)
-            with self._index.searcher() as searcher:
-                to = searcher.search(to.parse("*%s*" % query), limit=None, mask=restrict_q,
-                                     groupedby=sorting.FieldFacet('to', allow_overlap=True)).groups()
-                cc = searcher.search(cc.parse("*%s*" % query), limit=None, mask=restrict_q,
-                                     groupedby=sorting.FieldFacet('cc', allow_overlap=True)).groups()
-                bcc = searcher.search(bcc.parse("*%s*" % query), limit=None, mask=restrict_q,
-                                      groupedby=sorting.FieldFacet('bcc', allow_overlap=True)).groups()
-                sender = searcher.search(sender.parse("*%s*" % query), limit=None, mask=restrict_q,
-                                         groupedby=sorting.FieldFacet('sender', allow_overlap=True)).groups()
-                return address_duplication_filter(flatten([to, cc, bcc, sender]))
-
-        return []
+        with self._index.searcher() as searcher:
+            return contacts_suggestions(query, searcher)
diff --git a/service/pixelated/adapter/search/contacts.py b/service/pixelated/adapter/search/contacts.py
new file mode 100644
index 00000000..afef6ad0
--- /dev/null
+++ b/service/pixelated/adapter/search/contacts.py
@@ -0,0 +1,54 @@
+#
+# Copyright (c) 2014 ThoughtWorks, Inc.
+#
+# Pixelated is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Pixelated 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Pixelated. If not, see <http://www.gnu.org/licenses/>.
+from email.utils import parseaddr
+from pixelated.support.functional import flatten
+from whoosh.qparser import QueryParser
+from whoosh import sorting
+from whoosh.query import Term
+
+
+def address_duplication_filter(contacts):
+    contacts_by_mail = dict()
+
+    for contact in contacts:
+        mail_address = extract_mail_address(contact)
+        current = contacts_by_mail.get(mail_address, '')
+        current = contact if len(contact) > len(current) else current
+        contacts_by_mail[mail_address] = current
+    return contacts_by_mail.values()
+
+
+def extract_mail_address(text):
+    return parseaddr(text)[1]
+
+
+def contacts_suggestions(query, searcher):
+    if query:
+        return address_duplication_filter(search_addresses(searcher, query))
+    return []
+
+
+def search_addresses(searcher, query):
+    restrict_q = Term("tag", "drafts") | Term("tag", "trash")
+    results = []
+    for field in ['to', 'cc', 'bcc', 'sender']:
+        query_parser = QueryParser(field, searcher.schema)
+        results.append(searcher.search(query_parser.parse("*%s*" % query),
+                                       limit=None,
+                                       mask=restrict_q,
+                                       groupedby=sorting.FieldFacet(field,
+                                                                    allow_overlap=True)).groups())
+    return flatten(results)