Mercurial > p > roundup > code
annotate roundup/backends/indexer_common.py @ 4072:d5e2767d4e91
Robustify Date.set.
| author | Stefan Seefeld <stefan@seefeld.name> |
|---|---|
| date | Mon, 23 Feb 2009 19:24:57 +0000 |
| parents | 605f4a7910b4 |
| children | eddb82d0964c |
| rev | line source |
|---|---|
|
4017
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
1 #$Id: indexer_common.py,v 1.11 2008-09-11 19:41:07 schlatterbeck Exp $ |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
2 import re, sets |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
3 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
4 from roundup import hyperdb |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
5 |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
6 STOPWORDS = [ |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
7 "A", "AND", "ARE", "AS", "AT", "BE", "BUT", "BY", |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
8 "FOR", "IF", "IN", "INTO", "IS", "IT", |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
9 "NO", "NOT", "OF", "ON", "OR", "SUCH", |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
10 "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
|
11 "THEY", "THIS", "TO", "WAS", "WILL", "WITH" |
|
3092
a8c2371f45b6
Some cleanup:
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
3088
diff
changeset
|
12 ] |
|
a8c2371f45b6
Some cleanup:
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
3088
diff
changeset
|
13 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
14 def _isLink(propclass): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
15 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
|
16 isinstance(propclass, hyperdb.Multilink)) |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
17 |
|
3613
5f4db2650da3
implement close() on all indexers [SF#1242477]
Richard Jones <richard@users.sourceforge.net>
parents:
3544
diff
changeset
|
18 class Indexer: |
|
3544
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
19 def __init__(self, db): |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
20 self.stopwords = sets.Set(STOPWORDS) |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
21 for word in db.config[('main', 'indexer_stopwords')]: |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
22 self.stopwords.add(word) |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
23 |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
24 def is_stopword(self, word): |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
25 return word in self.stopwords |
|
5cd1c83dea50
Features and fixes.
Richard Jones <richard@users.sourceforge.net>
parents:
3092
diff
changeset
|
26 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
27 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
|
28 return self.find(search_terms) |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
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 search(self, search_terms, klass, ignore={}): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
31 '''Display search results looking for [search, terms] associated |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
32 with the hyperdb Class "klass". Ignore hits on {class: property}. |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
33 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
34 "dre" is a helper, not an argument. |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
35 ''' |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
36 # do the index lookup |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
37 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
|
38 if not hits: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
39 return {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
40 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
41 designator_propname = {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
42 for nm, propclass in klass.getprops().items(): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
43 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
|
44 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
|
45 []).append(nm) |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
46 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
47 # 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
|
48 # and files |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
49 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
|
50 propspec = {} # used 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
|
51 for l in designator_propname.values(): |
|
44603dd791b7
full-text search wasn't coping with multiple multilinks to the same class
Richard Jones <richard@users.sourceforge.net>
parents:
3718
diff
changeset
|
52 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
|
53 propspec[propname] = {} # used as a set (value doesn't matter) |
|
3718
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
54 |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
55 # 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
|
56 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
|
57 # 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
|
58 classname = entry[0] |
|
0d561b24ceff
support sqlite3
Richard Jones <richard@users.sourceforge.net>
parents:
3613
diff
changeset
|
59 property = entry[2] |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
60 if ignore.has_key((classname, property)): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
61 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
62 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
63 # 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
|
64 # (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
|
65 # 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
|
66 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
|
67 if classname == klass.classname: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
68 if not nodeids.has_key(nodeid): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
69 nodeids[nodeid] = {} |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
70 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
71 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
72 # make sure the class is a linked one, otherwise ignore |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
73 if not designator_propname.has_key(classname): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
74 continue |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
75 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
76 # 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
|
77 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
|
78 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
|
79 |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
80 # retain only the meaningful entries |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
81 for propname, idset in propspec.items(): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
82 if not idset: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
83 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
|
84 |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
85 # 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
|
86 propdefs = klass.getprops() |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
87 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
|
88 resid = str(resid) |
|
4017
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
89 if resid in nodeids: |
|
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
90 continue # we ignore duplicate resids |
|
605f4a7910b4
Small performance-improvement and bug-fix for indexer:
Ralf Schlatterbeck <schlatterbeck@users.sourceforge.net>
parents:
3998
diff
changeset
|
91 nodeids[resid] = {} |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
92 node_dict = nodeids[resid] |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
93 # now figure out where it came from |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
94 for linkprop in propspec.keys(): |
|
3997
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
95 v = klass.get(resid, linkprop) |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
96 # 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
|
97 if isinstance(propdefs[linkprop], hyperdb.Link): |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
98 if v is None: continue |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
99 v = [v] |
|
edbb89730dc2
Fix indexer handling of indexed Link properties
Richard Jones <richard@users.sourceforge.net>
parents:
3751
diff
changeset
|
100 for nodeid in v: |
|
3058
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
101 if propspec[linkprop].has_key(nodeid): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
102 # OK, this node[propname] has a winner |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
103 if not node_dict.has_key(linkprop): |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
104 node_dict[linkprop] = [nodeid] |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
105 else: |
|
1c063814d567
Move search method duplicated in indexer_dbm and indexer_tsearch2...
Johannes Gijsbers <jlgijsbers@users.sourceforge.net>
parents:
diff
changeset
|
106 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
|
107 return nodeids |
|
3613
5f4db2650da3
implement close() on all indexers [SF#1242477]
Richard Jones <richard@users.sourceforge.net>
parents:
3544
diff
changeset
|
108 |
