Mercurial > p > roundup > code
annotate roundup/backends/indexer_common.py @ 6591:feab8c878d08
Fix code formatting, add link for Configuring Compression.
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Mon, 24 Jan 2022 21:29:44 -0500 |
| parents | 91ab3e0ffcd0 |
| children | 39189dd94f2c |
| rev | line source |
|---|---|
|
4089
eddb82d0964c
Add compatibility package to allow us to deal with Python versions 2.3..2.6.
Richard Jones <richard@users.sourceforge.net>
parents:
4017
diff
changeset
|
1 import re |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
2 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
3 from roundup import hyperdb |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
4 |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
5 STOPWORDS = [ |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
6 "A", "AND", "ARE", "AS", "AT", "BE", "BUT", "BY", |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
7 "FOR", "IF", "IN", "INTO", "IS", "IT", |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
8 "NO", "NOT", "OF", "ON", "OR", "SUCH", |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
9 "THAT", "THE", "THEIR", "THEN", "THERE", "THESE", |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
10 "THEY", "THIS", "TO", "WAS", "WILL", "WITH" |
|
3092
a8c2371f45b6
Some cleanup:
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
3088
diff
changeset
|
11 ] |
|
a8c2371f45b6
Some cleanup:
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
3088
diff
changeset
|
12 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
13 def _isLink(propclass): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
14 return (isinstance(propclass, hyperdb.Link) or |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
15 isinstance(propclass, hyperdb.Multilink)) |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
16 |
|
3613
5f4db2650da3
implement close() on all indexers [SF#1242477]
Richard Jones <richard@users.sourceforge.net>
parents:
3544
diff
changeset
|
17 class Indexer: |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
18 def __init__(self, db): |
|
4089
eddb82d0964c
Add compatibility package to allow us to deal with Python versions 2.3..2.6.
Richard Jones <richard@users.sourceforge.net>
parents:
4017
diff
changeset
|
19 self.stopwords = set(STOPWORDS) |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
20 for word in db.config[('main', 'indexer_stopwords')]: |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
21 self.stopwords.add(word) |
|
4252
2ff6f39aa391
Indexers behaviour made more consistent regarding length of indexed words...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4089
diff
changeset
|
22 # Do not index anything longer than 25 characters since that'll be |
|
2ff6f39aa391
Indexers behaviour made more consistent regarding length of indexed words...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4089
diff
changeset
|
23 # gibberish (encoded text or somesuch) or shorter than 2 characters |
|
2ff6f39aa391
Indexers behaviour made more consistent regarding length of indexed words...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4089
diff
changeset
|
24 self.minlength = 2 |
|
2ff6f39aa391
Indexers behaviour made more consistent regarding length of indexed words...
Bernhard Reiter <Bernhard.Reiter@intevation.de>
parents:
4089
diff
changeset
|
25 self.maxlength = 25 |
|
6353
9d209d2b34ae
Add indexer_language to change stemmer for xapian FTS indexer
John Rouillard <rouilj@ieee.org>
parents:
5395
diff
changeset
|
26 self.language = db.config[('main','indexer_language')] |
|
6588
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
27 # Some indexers have a query language. If that is the case, |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
28 # we don't parse the user supplied query into a wordlist. |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
29 self.query_language = False |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
30 |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
31 def is_stopword(self, word): |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
32 return word in self.stopwords |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
33 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
34 def getHits(self, search_terms, klass): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
35 return self.find(search_terms) |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
36 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
37 def search(self, search_terms, klass, ignore={}): |
|
4089
eddb82d0964c
Add compatibility package to allow us to deal with Python versions 2.3..2.6.
Richard Jones <richard@users.sourceforge.net>
parents:
4017
diff
changeset
|
38 """Display search results looking for [search, terms] associated |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
39 with the hyperdb Class "klass". Ignore hits on {class: property}. |
|
4089
eddb82d0964c
Add compatibility package to allow us to deal with Python versions 2.3..2.6.
Richard Jones <richard@users.sourceforge.net>
parents:
4017
diff
changeset
|
40 """ |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
41 # do the index lookup |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
42 hits = self.getHits(search_terms, klass) |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
43 if not hits: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
44 return {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
45 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
46 designator_propname = {} |
|
5395
23b8e6067f7c
Python 3 preparation: update calls to dict methods.
Joseph Myers <jsm@polyomino.org.uk>
parents:
5388
diff
changeset
|
47 for nm, propclass in klass.getprops().items(): |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
48 if _isLink(propclass): |
|
3751
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
49 designator_propname.setdefault(propclass.classname, |
|
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
50 []).append(nm) |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
51 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
52 # build a dictionary of nodes and their associated messages |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
53 # and files |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
54 nodeids = {} # this is the answer |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
55 propspec = {} # used to do the klass.find |
|
5395
23b8e6067f7c
Python 3 preparation: update calls to dict methods.
Joseph Myers <jsm@polyomino.org.uk>
parents:
5388
diff
changeset
|
56 for l in designator_propname.values(): |
|
3751
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
57 for propname in l: |
|
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
58 propspec[propname] = {} # used as a set (value doesn't matter) |
|
3718
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
59 |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
60 # don't unpack hits entries as sqlite3's Row can't be unpacked :( |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
61 for entry in hits: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
62 # skip this result if we don't care about this class/property |
|
3718
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
63 classname = entry[0] |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
64 property = entry[2] |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
65 if (classname, property) in ignore: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
66 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
67 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
68 # if it's a property on klass, it's easy |
|
3998
20c9a1cefb39
make sure item ids are str()
Richard Jones <richard@users.sourceforge.net>
parents:
3997
diff
changeset
|
69 # (make sure the nodeid is str() not unicode() as returned by some |
|
20c9a1cefb39
make sure item ids are str()
Richard Jones <richard@users.sourceforge.net>
parents:
3997
diff
changeset
|
70 # backends as that can cause problems down the track) |
|
20c9a1cefb39
make sure item ids are str()
Richard Jones <richard@users.sourceforge.net>
parents:
3997
diff
changeset
|
71 nodeid = str(entry[1]) |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
72 if classname == klass.classname: |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
73 if nodeid not in nodeids: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
74 nodeids[nodeid] = {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
75 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
76 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
77 # make sure the class is a linked one, otherwise ignore |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
78 if classname not in designator_propname: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
79 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
80 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
81 # it's a linked class - set up to do the klass.find |
|
3751
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
82 for linkprop in designator_propname[classname]: |
|
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
83 propspec[linkprop][nodeid] = 1 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
84 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
85 # retain only the meaningful entries |
|
4359
b9abbdd15259
another module modernised
Richard Jones <richard@users.sourceforge.net>
parents:
4357
diff
changeset
|
86 for propname, idset in list(propspec.items()): |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
87 if not idset: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
88 del propspec[propname] |
|
3751
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
89 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
90 # klass.find tells me the klass nodeids the linked nodes relate to |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
91 propdefs = klass.getprops() |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
92 for resid in klass.find(**propspec): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
93 resid = str(resid) |
|
4017
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
94 if resid in nodeids: |
|
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
95 continue # we ignore duplicate resids |
|
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
96 nodeids[resid] = {} |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
97 node_dict = nodeids[resid] |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
98 # now figure out where it came from |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
99 for linkprop in propspec: |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
100 v = klass.get(resid, linkprop) |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
101 # the link might be a Link so deal with a single result or None |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
102 if isinstance(propdefs[linkprop], hyperdb.Link): |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
103 if v is None: continue |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
104 v = [v] |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
105 for nodeid in v: |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
106 if nodeid in propspec[linkprop]: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
107 # OK, this node[propname] has a winner |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
108 if linkprop not in node_dict: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
109 node_dict[linkprop] = [nodeid] |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
110 else: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
111 node_dict[linkprop].append(nodeid) |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
112 return nodeids |
|
3613
5f4db2650da3
implement close() on all indexers [SF#1242477]
Richard Jones <richard@users.sourceforge.net>
parents:
3544
diff
changeset
|
113 |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
114 def get_indexer(config, db): |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
115 indexer_name = getattr(config, "INDEXER", "") |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
116 if not indexer_name: |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
117 # Try everything |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
118 try: |
|
5388
d26921b851c3
Python 3 preparation: make relative imports explicit.
Joseph Myers <jsm@polyomino.org.uk>
parents:
5096
diff
changeset
|
119 from .indexer_xapian import Indexer |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
120 return Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
121 except ImportError: |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
122 pass |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
123 |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
124 try: |
|
5388
d26921b851c3
Python 3 preparation: make relative imports explicit.
Joseph Myers <jsm@polyomino.org.uk>
parents:
5096
diff
changeset
|
125 from .indexer_whoosh import Indexer |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
126 return Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
127 except ImportError: |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
128 pass |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
129 |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
130 indexer_name = "native" # fallback to native full text search |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
131 |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
132 if indexer_name == "xapian": |
|
5388
d26921b851c3
Python 3 preparation: make relative imports explicit.
Joseph Myers <jsm@polyomino.org.uk>
parents:
5096
diff
changeset
|
133 from .indexer_xapian import Indexer |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
134 return Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
135 |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
136 if indexer_name == "whoosh": |
|
5388
d26921b851c3
Python 3 preparation: make relative imports explicit.
Joseph Myers <jsm@polyomino.org.uk>
parents:
5096
diff
changeset
|
137 from .indexer_whoosh import Indexer |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
138 return Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
139 |
|
6588
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
140 if indexer_name == "native-fts": |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
141 if db.dbtype not in ("sqlite", "postgres"): |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
142 raise AssertionError("Indexer native-fts is configured, but only sqlite and postgres support it. Database is: %r" % db.dbtype) |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
143 |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
144 if db.dbtype == "sqlite": |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
145 from roundup.backends.indexer_sqlite_fts import Indexer |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
146 return Indexer(db) |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
147 |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
148 if db.dbtype == "postgres": |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
149 raise NotImplementedError("Postgres FTS not available") |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
150 from roundup.backends.indexer_postgres_fts import Indexer |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
151 return Indexer(db) |
|
91ab3e0ffcd0
Summary: Add test cases for sqlite fts
John Rouillard <rouilj@ieee.org>
parents:
6353
diff
changeset
|
152 |
|
5096
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
153 if indexer_name == "native": |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
154 # load proper native indexing based on database type |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
155 if db.dbtype == "anydbm": |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
156 from roundup.backends.indexer_dbm import Indexer |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
157 return Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
158 |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
159 if db.dbtype in ("sqlite", "postgres", "mysql"): |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
160 from roundup.backends.indexer_rdbms import Indexer |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
161 return Indexer(db) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
162 |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
163 raise AssertionError("Invalid indexer: %r" %(indexer_name)) |
|
e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
John Rouillard <rouilj@ieee.org>
parents:
4687
diff
changeset
|
164 |
