Mercurial > p > roundup > code
annotate roundup/indexer.py @ 1669:17ec0bd6ecc5 maint-0.5
*** empty log message ***
| author | Richard Jones <richard@users.sourceforge.net> |
|---|---|
| date | Wed, 18 Jun 2003 23:52:54 +0000 |
| parents | 728a0809183e |
| children | 4884fb0860f9 |
| rev | line source |
|---|---|
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
1 # |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
2 # This module is derived from the module described at: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
3 # http://gnosis.cx/publish/programming/charming_python_15.txt |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
4 # |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
5 # Author: David Mertz (mertz@gnosis.cx) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
6 # Thanks to: Pat Knight (p.knight@ktgroup.co.uk) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
7 # Gregory Popovitch (greg@gpy.com) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
8 # |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
9 # The original module was released under this license, and remains under |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
10 # it: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
11 # |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
12 # This file is released to the public domain. I (dqm) would |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
13 # appreciate it if you choose to keep derived works under terms |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
14 # that promote freedom, but obviously am giving up any rights |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
15 # to compel such. |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
16 # |
|
1206
728a0809183e
handle multiple unrelated indexed classes
Richard Jones <richard@users.sourceforge.net>
parents:
1090
diff
changeset
|
17 #$Id: indexer.py,v 1.14 2002-09-25 05:06:14 richard Exp $ |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
18 ''' |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
19 This module provides an indexer class, RoundupIndexer, that stores text |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
20 indices in a roundup instance. This class makes searching the content of |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
21 messages, string properties and text files possible. |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
22 ''' |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
23 import os, shutil, re, mimetypes, marshal, zlib, errno |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
24 from hyperdb import Link, Multilink |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
25 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
26 class Indexer: |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
27 ''' Indexes information from roundup's hyperdb to allow efficient |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
28 searching. |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
29 |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
30 Three structures are created by the indexer: |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
31 files {identifier: (fileid, wordcount)} |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
32 words {word: {fileid: count}} |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
33 fileids {fileid: identifier} |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
34 where identifier is (classname, nodeid, propertyname) |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
35 ''' |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
36 def __init__(self, db_path): |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
37 self.indexdb_path = os.path.join(db_path, 'indexes') |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
38 self.indexdb = os.path.join(self.indexdb_path, 'index.db') |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
39 self.reindex = 0 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
40 self.quiet = 9 |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
41 self.changed = 0 |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
42 |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
43 # see if we need to reindex because of a change in code |
| 863 | 44 version = os.path.join(self.indexdb_path, 'version') |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
45 if (not os.path.exists(self.indexdb_path) or |
| 863 | 46 not os.path.exists(version)): |
| 47 # for now the file itself is a flag | |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
48 self.force_reindex() |
| 863 | 49 elif os.path.exists(version): |
| 50 version = open(version).read() | |
| 51 # check the value and reindex if it's not the latest | |
|
880
de3da99a7c02
Add Number and Boolean types to hyperdb.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
867
diff
changeset
|
52 if version.strip() != '1': |
| 863 | 53 self.force_reindex() |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
54 |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
55 def force_reindex(self): |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
56 '''Force a reindex condition |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
57 ''' |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
58 if os.path.exists(self.indexdb_path): |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
59 shutil.rmtree(self.indexdb_path) |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
60 os.makedirs(self.indexdb_path) |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
61 os.chmod(self.indexdb_path, 0775) |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
62 open(os.path.join(self.indexdb_path, 'version'), 'w').write('1\n') |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
63 self.reindex = 1 |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
64 self.changed = 1 |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
65 |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
66 def should_reindex(self): |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
67 '''Should we reindex? |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
68 ''' |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
69 return self.reindex |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
70 |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
71 def add_text(self, identifier, text, mime_type='text/plain'): |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
72 ''' Add some text associated with the (classname, nodeid, property) |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
73 identifier. |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
74 ''' |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
75 # make sure the index is loaded |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
76 self.load_index() |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
77 |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
78 # remove old entries for this identifier |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
79 if self.files.has_key(identifier): |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
80 self.purge_entry(identifier) |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
81 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
82 # split into words |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
83 words = self.splitter(text, mime_type) |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
84 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
85 # Find new file index, and assign it to identifier |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
86 # (_TOP uses trick of negative to avoid conflict with file index) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
87 self.files['_TOP'] = (self.files['_TOP'][0]-1, None) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
88 file_index = abs(self.files['_TOP'][0]) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
89 self.files[identifier] = (file_index, len(words)) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
90 self.fileids[file_index] = identifier |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
91 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
92 # find the unique words |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
93 filedict = {} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
94 for word in words: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
95 if filedict.has_key(word): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
96 filedict[word] = filedict[word]+1 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
97 else: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
98 filedict[word] = 1 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
99 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
100 # now add to the totals |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
101 for word in filedict.keys(): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
102 # each word has a dict of {identifier: count} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
103 if self.words.has_key(word): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
104 entry = self.words[word] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
105 else: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
106 # new word |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
107 entry = {} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
108 self.words[word] = entry |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
109 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
110 # make a reference to the file for this word |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
111 entry[file_index] = filedict[word] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
112 |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
113 # save needed |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
114 self.changed = 1 |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
115 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
116 def splitter(self, text, ftype): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
117 ''' Split the contents of a text string into a list of 'words' |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
118 ''' |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
119 if ftype == 'text/plain': |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
120 words = self.text_splitter(text) |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
121 else: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
122 return [] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
123 return words |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
124 |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
125 def text_splitter(self, text): |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
126 """Split text/plain string into a list of words |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
127 """ |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
128 # case insensitive |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
129 text = text.upper() |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
130 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
131 # Split the raw text, losing anything longer than 25 characters |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
132 # since that'll be gibberish (encoded text or somesuch) or shorter |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
133 # than 3 characters since those short words appear all over the |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
134 # place |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
135 return re.findall(r'\b\w{2,25}\b', text) |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
136 |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
137 def search(self, search_terms, klass, ignore={}, |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
138 dre=re.compile(r'([^\d]+)(\d+)')): |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
139 ''' Display search results looking for [search, terms] associated |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
140 with the hyperdb Class "klass". Ignore hits on {class: property}. |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
141 |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
142 "dre" is a helper, not an argument. |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
143 ''' |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
144 # do the index lookup |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
145 hits = self.find(search_terms) |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
146 if not hits: |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
147 return {} |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
148 |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
149 #designator_propname = {'msg': 'messages', 'file': 'files'} |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
150 designator_propname = {} |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
151 for nm, propclass in klass.getprops().items(): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
152 if isinstance(propclass, Link) or isinstance(propclass, Multilink): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
153 designator_propname[propclass.classname] = nm |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
154 |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
155 # build a dictionary of nodes and their associated messages |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
156 # and files |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
157 nodeids = {} # this is the answer |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
158 propspec = {} # used to do the klass.find |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
159 for propname in designator_propname.values(): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
160 propspec[propname] = {} # used as a set (value doesn't matter) |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
161 for classname, nodeid, property in hits.values(): |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
162 # skip this result if we don't care about this class/property |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
163 if ignore.has_key((classname, property)): |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
164 continue |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
165 |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
166 # if it's a property on klass, it's easy |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
167 if classname == klass.classname: |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
168 if not nodeids.has_key(nodeid): |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
169 nodeids[nodeid] = {} |
|
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
170 continue |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
171 |
|
1206
728a0809183e
handle multiple unrelated indexed classes
Richard Jones <richard@users.sourceforge.net>
parents:
1090
diff
changeset
|
172 # make sure the class is a linked one, otherwise ignore |
|
728a0809183e
handle multiple unrelated indexed classes
Richard Jones <richard@users.sourceforge.net>
parents:
1090
diff
changeset
|
173 if not designator_propname.has_key(classname): |
|
728a0809183e
handle multiple unrelated indexed classes
Richard Jones <richard@users.sourceforge.net>
parents:
1090
diff
changeset
|
174 continue |
|
728a0809183e
handle multiple unrelated indexed classes
Richard Jones <richard@users.sourceforge.net>
parents:
1090
diff
changeset
|
175 |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
176 # it's a linked class - set up to do the klass.find |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
177 linkprop = designator_propname[classname] # eg, msg -> messages |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
178 propspec[linkprop][nodeid] = 1 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
179 |
|
834
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
180 # retain only the meaningful entries |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
181 for propname, idset in propspec.items(): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
182 if not idset: |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
183 del propspec[propname] |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
184 |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
185 # klass.find tells me the klass nodeids the linked nodes relate to |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
186 for resid in klass.find(**propspec): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
187 resid = str(resid) |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
188 if not nodeids.has_key(id): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
189 nodeids[resid] = {} |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
190 node_dict = nodeids[resid] |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
191 # now figure out where it came from |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
192 for linkprop in propspec.keys(): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
193 for nodeid in klass.get(resid, linkprop): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
194 if propspec[linkprop].has_key(nodeid): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
195 # OK, this node[propname] has a winner |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
196 if not node_dict.has_key(linkprop): |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
197 node_dict[linkprop] = [nodeid] |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
198 else: |
|
568eed5fb4fd
Optimize Class.find so that the propspec can contain a set of ids to match.
Gordon B. McMillan <gmcm@users.sourceforge.net>
parents:
833
diff
changeset
|
199 node_dict[linkprop].append(nodeid) |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
200 return nodeids |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
201 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
202 # we override this to ignore not 2 < word < 25 and also to fix a bug - |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
203 # the (fail) case. |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
204 def find(self, wordlist): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
205 ''' Locate files that match ALL the words in wordlist |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
206 ''' |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
207 if not hasattr(self, 'words'): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
208 self.load_index() |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
209 self.load_index(wordlist=wordlist) |
|
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
210 entries = {} |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
211 hits = None |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
212 for word in wordlist: |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
213 if not 2 < len(word) < 25: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
214 # word outside the bounds of what we index - ignore |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
215 continue |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
216 word = word.upper() |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
217 entry = self.words.get(word) # For each word, get index |
|
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
218 entries[word] = entry # of matching files |
|
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
219 if not entry: # Nothing for this one word (fail) |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
220 return {} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
221 if hits is None: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
222 hits = {} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
223 for k in entry.keys(): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
224 hits[k] = self.fileids[k] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
225 else: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
226 # Eliminate hits for every non-match |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
227 for fileid in hits.keys(): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
228 if not entry.has_key(fileid): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
229 del hits[fileid] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
230 if hits is None: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
231 return {} |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
232 return hits |
|
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
233 |
|
827
0a2c1f5e0e5a
We're indexing numbers now, and _underscore words
Richard Jones <richard@users.sourceforge.net>
parents:
826
diff
changeset
|
234 segments = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ#_-!" |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
235 def load_index(self, reload=0, wordlist=None): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
236 # Unless reload is indicated, do not load twice |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
237 if self.index_loaded() and not reload: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
238 return 0 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
239 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
240 # Ok, now let's actually load it |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
241 db = {'WORDS': {}, 'FILES': {'_TOP':(0,None)}, 'FILEIDS': {}} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
242 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
243 # Identify the relevant word-dictionary segments |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
244 if not wordlist: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
245 segments = self.segments |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
246 else: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
247 segments = ['-','#'] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
248 for word in wordlist: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
249 segments.append(word[0].upper()) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
250 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
251 # Load the segments |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
252 for segment in segments: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
253 try: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
254 f = open(self.indexdb + segment, 'rb') |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
255 except IOError, error: |
| 863 | 256 # probably just nonexistent segment index file |
| 257 if error.errno != errno.ENOENT: raise | |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
258 else: |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
259 pickle_str = zlib.decompress(f.read()) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
260 f.close() |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
261 dbslice = marshal.loads(pickle_str) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
262 if dbslice.get('WORDS'): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
263 # if it has some words, add them |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
264 for word, entry in dbslice['WORDS'].items(): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
265 db['WORDS'][word] = entry |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
266 if dbslice.get('FILES'): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
267 # if it has some files, add them |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
268 db['FILES'] = dbslice['FILES'] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
269 if dbslice.get('FILEIDS'): |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
270 # if it has fileids, add them |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
271 db['FILEIDS'] = dbslice['FILEIDS'] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
272 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
273 self.words = db['WORDS'] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
274 self.files = db['FILES'] |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
275 self.fileids = db['FILEIDS'] |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
276 self.changed = 0 |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
277 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
278 def save_index(self): |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
279 # only save if the index is loaded and changed |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
280 if not self.index_loaded() or not self.changed: |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
281 return |
|
825
0779ea9f1f18
More indexer work:
Richard Jones <richard@users.sourceforge.net>
parents:
818
diff
changeset
|
282 |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
283 # brutal space saver... delete all the small segments |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
284 for segment in self.segments: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
285 try: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
286 os.remove(self.indexdb + segment) |
| 863 | 287 except OSError, error: |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
288 # probably just nonexistent segment index file |
| 867 | 289 if error.errno != errno.ENOENT: raise |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
290 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
291 # First write the much simpler filename/fileid dictionaries |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
292 dbfil = {'WORDS':None, 'FILES':self.files, 'FILEIDS':self.fileids} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
293 open(self.indexdb+'-','wb').write(zlib.compress(marshal.dumps(dbfil))) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
294 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
295 # The hard part is splitting the word dictionary up, of course |
|
827
0a2c1f5e0e5a
We're indexing numbers now, and _underscore words
Richard Jones <richard@users.sourceforge.net>
parents:
826
diff
changeset
|
296 letters = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ#_" |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
297 segdicts = {} # Need batch of empty dicts |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
298 for segment in letters: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
299 segdicts[segment] = {} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
300 for word, entry in self.words.items(): # Split into segment dicts |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
301 initchar = word[0].upper() |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
302 segdicts[initchar][word] = entry |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
303 |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
304 # save |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
305 for initchar in letters: |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
306 db = {'WORDS':segdicts[initchar], 'FILES':None, 'FILEIDS':None} |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
307 pickle_str = marshal.dumps(db) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
308 filename = self.indexdb + initchar |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
309 pickle_fh = open(filename, 'wb') |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
310 pickle_fh.write(zlib.compress(pickle_str)) |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
311 os.chmod(filename, 0664) |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
312 |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
313 # save done |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
314 self.changed = 0 |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
315 |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
316 def purge_entry(self, identifier): |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
317 ''' Remove a file from file index and word index |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
318 ''' |
|
891
974a4b94c5e3
Implemented the destroy() method needed by the session database...
Richard Jones <richard@users.sourceforge.net>
parents:
880
diff
changeset
|
319 self.load_index() |
|
974a4b94c5e3
Implemented the destroy() method needed by the session database...
Richard Jones <richard@users.sourceforge.net>
parents:
880
diff
changeset
|
320 |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
321 if not self.files.has_key(identifier): |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
322 return |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
323 |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
324 file_index = self.files[identifier][0] |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
325 del self.files[identifier] |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
326 del self.fileids[file_index] |
|
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
327 |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
328 # The much harder part, cleanup the word index |
|
826
6d7a45c8464a
Added reindex command to roundup-admin.
Richard Jones <richard@users.sourceforge.net>
parents:
825
diff
changeset
|
329 for key, occurs in self.words.items(): |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
330 if occurs.has_key(file_index): |
|
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
331 del occurs[file_index] |
|
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
332 |
|
833
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
333 # save needed |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
334 self.changed = 1 |
|
b80aaedba3db
Only save the index if the thing is loaded and changed.
Richard Jones <richard@users.sourceforge.net>
parents:
827
diff
changeset
|
335 |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
336 def index_loaded(self): |
|
818
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
337 return (hasattr(self,'fileids') and hasattr(self,'files') and |
|
254b8d112eec
cleaned up the indexer code:
Richard Jones <richard@users.sourceforge.net>
parents:
749
diff
changeset
|
338 hasattr(self,'words')) |
|
749
51c425129b35
Merged search_indexing-branch with HEAD
Roche Compaan <rochecompaan@users.sourceforge.net>
parents:
diff
changeset
|
339 |
| 1090 | 340 # vim: set filetype=python ts=4 sw=4 et si |
