Merge pull request #1 from sdelements/feature/enable-whoosh-faceting

Copy of upstream PR#1366
sdelements · Feb 8, 2019 · 1a1dcae · 1a1dcae
2 parents 802b0f6 + ec5fbe0
commit 1a1dcae
Showing 2 changed files with 38 additions and 15 deletions.
diff --git a/docs/backend_support.rst b/docs/backend_support.rst
@@ -63,6 +63,7 @@ Whoosh
 * Term Boosting
 * Stored (non-indexed) fields
 * Highlighting
+* Faceting (no dates or queries)
 * Requires: whoosh (2.0.0+)
 
 Xapian
@@ -83,17 +84,17 @@ Xapian
 Backend Support Matrix
 ======================
 
-+----------------+------------------------+---------------------+----------------+------------+----------+---------------+--------------+---------+
-| Backend        | SearchQuerySet Support | Auto Query Building | More Like This | Term Boost | Faceting | Stored Fields | Highlighting | Spatial |
-+================+========================+=====================+================+============+==========+===============+==============+=========+
-| Solr           | Yes                    | Yes                 | Yes            | Yes        | Yes      | Yes           | Yes          | Yes     |
-+----------------+------------------------+---------------------+----------------+------------+----------+---------------+--------------+---------+
-| ElasticSearch  | Yes                    | Yes                 | Yes            | Yes        | Yes      | Yes           | Yes          | Yes     |
-+----------------+------------------------+---------------------+----------------+------------+----------+---------------+--------------+---------+
-| Whoosh         | Yes                    | Yes                 | Yes            | Yes        | No       | Yes           | Yes          | No      |
-+----------------+------------------------+---------------------+----------------+------------+----------+---------------+--------------+---------+
-| Xapian         | Yes                    | Yes                 | Yes            | Yes        | Yes      | Yes           | Yes (plugin) | No      |
-+----------------+------------------------+---------------------+----------------+------------+----------+---------------+--------------+---------+
++----------------+------------------------+---------------------+----------------+------------+-------------+---------------+--------------+---------+
+| Backend        | SearchQuerySet Support | Auto Query Building | More Like This | Term Boost | Faceting    | Stored Fields | Highlighting | Spatial |
++================+========================+=====================+================+============+=============+===============+==============+=========+
+| Solr           | Yes                    | Yes                 | Yes            | Yes        | Yes         | Yes           | Yes          | Yes     |
++----------------+------------------------+---------------------+----------------+------------+-------------+---------------+--------------+---------+
+| ElasticSearch  | Yes                    | Yes                 | Yes            | Yes        | Yes         | Yes           | Yes          | Yes     |
++----------------+------------------------+---------------------+----------------+------------+-------------+---------------+--------------+---------+
+| Whoosh         | Yes                    | Yes                 | Yes            | Yes        | Yes (basic) | Yes           | Yes          | No      |
++----------------+------------------------+---------------------+----------------+------------+-------------+---------------+--------------+---------+
+| Xapian         | Yes                    | Yes                 | Yes            | Yes        | Yes         | Yes           | Yes (plugin) | No      |
++----------------+------------------------+---------------------+----------------+------------+-------------+---------------+--------------+---------+
 
 
 Unsupported Backends & Alternatives

diff --git a/haystack/backends/whoosh_backend.py b/haystack/backends/whoosh_backend.py
@@ -6,6 +6,7 @@
 import os
 import re
 import shutil
+import operator
 import threading
 import warnings
 
@@ -68,7 +69,7 @@
 from whoosh.qparser import QueryParser, FuzzyTermPlugin
 from whoosh.searching import ResultsPage
 from whoosh.writing import AsyncWriter
-
+from whoosh.sorting import FieldFacet
 
 DATETIME_REGEX = re.compile(
     "^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})T(?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})(\.\d{3,6}Z?)?$"
@@ -469,7 +470,7 @@ def search(
             sort_by = sort_by_list
 
         if facets is not None:
-            warnings.warn("Whoosh does not handle faceting.", Warning, stacklevel=2)
+            facets = [FieldFacet(facet, allow_overlap=True) for facet in facets]
 
         if date_facets is not None:
             warnings.warn(
@@ -520,7 +521,7 @@ def search(
                 if len(recent_narrowed_results) <= 0:
                     return {"results": [], "hits": 0}
 
-                if narrowed_results:
+                if narrowed_results is not None:
                     narrowed_results.filter(recent_narrowed_results)
                 else:
                     narrowed_results = recent_narrowed_results
@@ -541,6 +542,7 @@ def search(
                 "pagelen": page_length,
                 "sortedby": sort_by,
                 "reverse": reverse,
+                'groupedby': facets,
             }
 
             # Handle the case where the results have been narrowed.
@@ -714,10 +716,30 @@ def _process_results(
         if result_class is None:
             result_class = SearchResult
 
-        facets = {}
         spelling_suggestion = None
         unified_index = connections[self.connection_alias].get_unified_index()
         indexed_models = unified_index.get_indexed_models()
+
+        facets = {}
+
+        if len(raw_page.results.facet_names()):
+            facets = {
+                'fields': {},
+                'dates': {},
+                'queries': {},
+            }
+            for facet_fieldname in raw_page.results.facet_names():
+                # split up the list and filter out None-names so we can
+                # sort them in python3 without getting a type error
+                facet_items = []
+                facet_none = []
+                for name, value in raw_page.results.groups(facet_fieldname).items():
+                    if name is not None:
+                        facet_items.append((name, len(value)))
+                    else:
+                        facet_none.append((name, len(value)))
+                facet_items.sort(key=operator.itemgetter(1, 0), reverse=True)
+                facets['fields'][facet_fieldname] = facet_items + facet_none
 
         for doc_offset, raw_result in enumerate(raw_page):
             score = raw_page.score(doc_offset) or 0