Mercurial > p > roundup > code
annotate roundup/backends/indexer_common.py @ 4740:fe9568a6cbd6
Untangle template selection logic from template loading functionality.
| author | anatoly techtonik <techtonik@gmail.com> |
|---|---|
| date | Tue, 15 Jan 2013 00:10:01 +0300 |
| parents | 4960a2c21590 |
| children | e74c3611b138 |
| 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 |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
26 |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
27 def is_stopword(self, word): |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
28 return word in self.stopwords |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
29 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
30 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
|
31 return self.find(search_terms) |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
32 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
33 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
|
34 """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
|
35 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
|
36 """ |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
37 # do the index lookup |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
38 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
|
39 if not hits: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
40 return {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
41 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
42 designator_propname = {} |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
43 for nm, propclass in klass.getprops().iteritems(): |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
44 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
|
45 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
|
46 []).append(nm) |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
47 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
48 # 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
|
49 # and files |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
50 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
|
51 propspec = {} # used to do the klass.find |
|
4357
13b3155869e0
Beginnings of a big code cleanup / modernisation to make 2to3 happy
Richard Jones <richard@users.sourceforge.net>
parents:
4281
diff
changeset
|
52 for l in designator_propname.itervalues(): |
|
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
|
53 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
|
54 propspec[propname] = {} # used as a set (value doesn't matter) |
|
3718
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
55 |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
56 # 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
|
57 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
|
58 # 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
|
59 classname = entry[0] |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
60 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
|
61 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
|
62 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
63 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
64 # 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
|
65 # (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
|
66 # 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
|
67 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
|
68 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
|
69 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
|
70 nodeids[nodeid] = {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
71 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
72 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
73 # 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
|
74 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
|
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 # 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
|
78 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
|
79 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
|
80 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
81 # retain only the meaningful entries |
|
4359
b9abbdd15259
another module modernised
Richard Jones <richard@users.sourceforge.net>
parents:
4357
diff
changeset
|
82 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
|
83 if not idset: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
84 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
|
85 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
86 # 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
|
87 propdefs = klass.getprops() |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
88 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
|
89 resid = str(resid) |
|
4017
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
90 if resid in nodeids: |
|
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
91 continue # we ignore duplicate resids |
|
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
92 nodeids[resid] = {} |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
93 node_dict = nodeids[resid] |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
94 # 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
|
95 for linkprop in propspec: |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
96 v = klass.get(resid, linkprop) |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
97 # 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
|
98 if isinstance(propdefs[linkprop], hyperdb.Link): |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
99 if v is None: continue |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
100 v = [v] |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
101 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
|
102 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
|
103 # 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
|
104 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
|
105 node_dict[linkprop] = [nodeid] |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
106 else: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
107 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
|
108 return nodeids |
|
3613
5f4db2650da3
implement close() on all indexers [SF#1242477]
Richard Jones <richard@users.sourceforge.net>
parents:
3544
diff
changeset
|
109 |
