Mercurial > kallithea
annotate rhodecode/lib/indexers/__init__.py @ 683:341beaa9edba beta
Implemented whoosh index building as paster command.
docs update
fixed manifest.in for missing yui file.
Fixed setup to beta
added base for paster upgrade-db command
author | Marcin Kuzminski <marcin@python-works.com> |
---|---|
date | Sat, 13 Nov 2010 02:29:46 +0100 |
parents | 05528ad948c4 |
children | b9442a8b5e02 |
rev | line source |
---|---|
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
1 import os |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
2 import sys |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
3 from os.path import dirname as dn, join as jn |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
4 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
5 #to get the rhodecode import |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
6 sys.path.append(dn(dn(dn(os.path.realpath(__file__))))) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
7 |
547
1e757ac98988
renamed project to rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
497
diff
changeset
|
8 from rhodecode.config.environment import load_environment |
629
7e536d1af60d
Code refactoring,models renames
Marcin Kuzminski <marcin@python-works.com>
parents:
604
diff
changeset
|
9 from rhodecode.model.hg import HgModel |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
10 from shutil import rmtree |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
11 from webhelpers.html.builder import escape |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
12 from vcs.utils.lazy import LazyProperty |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
13 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
14 from whoosh.analysis import RegexTokenizer, LowercaseFilter, StopFilter |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
15 from whoosh.fields import TEXT, ID, STORED, Schema, FieldType |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
16 from whoosh.index import create_in, open_dir |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
17 from whoosh.formats import Characters |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
18 from whoosh.highlight import highlight, SimpleFragmenter, HtmlFormatter |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
19 |
406
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
20 import traceback |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
21 |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
22 |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
23 #LOCATION WE KEEP THE INDEX |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
24 IDX_LOCATION = jn(dn(dn(dn(dn(os.path.abspath(__file__))))), 'data', 'index') |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
25 |
436
28f19fa562df
updated config files,
Marcin Kuzminski <marcin@python-works.com>
parents:
406
diff
changeset
|
26 #EXTENSIONS WE WANT TO INDEX CONTENT OFF |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
27 INDEX_EXTENSIONS = ['action', 'adp', 'ashx', 'asmx', 'aspx', 'asx', 'axd', 'c', |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
28 'cfg', 'cfm', 'cpp', 'cs', 'css', 'diff', 'do', 'el', 'erl', |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
29 'h', 'htm', 'html', 'ini', 'java', 'js', 'jsp', 'jspx', 'lisp', |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
30 'lua', 'm', 'mako', 'ml', 'pas', 'patch', 'php', 'php3', |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
31 'php4', 'phtml', 'pm', 'py', 'rb', 'rst', 's', 'sh', 'sql', |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
32 'tpl', 'txt', 'vim', 'wss', 'xhtml', 'xml', 'xsl', 'xslt', |
436
28f19fa562df
updated config files,
Marcin Kuzminski <marcin@python-works.com>
parents:
406
diff
changeset
|
33 'yaws'] |
406
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
34 |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
35 #CUSTOM ANALYZER wordsplit + lowercase filter |
436
28f19fa562df
updated config files,
Marcin Kuzminski <marcin@python-works.com>
parents:
406
diff
changeset
|
36 ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter() |
406
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
37 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
38 |
406
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
39 #INDEX SCHEMA DEFINITION |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
40 SCHEMA = Schema(owner=TEXT(), |
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
41 repository=TEXT(stored=True), |
556
65b2f150beb7
Added searching for file names within the repository in rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
547
diff
changeset
|
42 path=TEXT(stored=True), |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
43 content=FieldType(format=Characters(ANALYZER), |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
44 scorable=True, stored=True), |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
45 modtime=STORED(), extension=TEXT(stored=True)) |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
46 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
47 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
48 IDX_NAME = 'HG_INDEX' |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
49 FORMATTER = HtmlFormatter('span', between='\n<span class="break">...</span>\n') |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
50 FRAGMENTER = SimpleFragmenter(200) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
51 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
52 from paste.script import command |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
53 import ConfigParser |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
54 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
55 class MakeIndex(command.Command): |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
56 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
57 max_args = 1 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
58 min_args = 1 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
59 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
60 usage = "CONFIG_FILE" |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
61 summary = "Creates index for full text search given configuration file" |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
62 group_name = "RhodeCode" |
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
63 takes_config_file = -1 |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
64 parser = command.Command.standard_parser(verbose=True) |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
65 parser.add_option('--repo-location', |
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
66 action='store', |
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
67 dest='repo_location', |
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
68 help="Specifies repositories location to index REQUIRED", |
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
69 ) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
70 parser.add_option('-f', |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
71 action='store_true', |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
72 dest='full_index', |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
73 help="Specifies that index should be made full i.e" |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
74 " destroy old and build from scratch", |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
75 default=False) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
76 def command(self): |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
77 config_name = self.args[0] |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
78 p = config_name.split('/') |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
79 root = '.' if len(p) == 1 else '/'.join(p[:-1]) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
80 config = ConfigParser.ConfigParser({'here':root}) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
81 config.read(config_name) |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
82 |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
83 index_location = dict(config.items('app:main'))['index_dir'] |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
84 repo_location = self.options.repo_location |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
85 |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
86 #====================================================================== |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
87 # WHOOSH DAEMON |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
88 #====================================================================== |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
89 from rhodecode.lib.pidlock import LockHeld, DaemonLock |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
90 from rhodecode.lib.indexers.daemon import WhooshIndexingDaemon |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
91 try: |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
92 l = DaemonLock() |
683
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
93 WhooshIndexingDaemon(index_location=index_location, |
341beaa9edba
Implemented whoosh index building as paster command.
Marcin Kuzminski <marcin@python-works.com>
parents:
631
diff
changeset
|
94 repo_location=repo_location)\ |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
95 .run(full_index=self.options.full_index) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
96 l.release() |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
97 except LockHeld: |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
98 sys.exit(1) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
99 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
100 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
101 class ResultWrapper(object): |
556
65b2f150beb7
Added searching for file names within the repository in rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
547
diff
changeset
|
102 def __init__(self, search_type, searcher, matcher, highlight_items): |
65b2f150beb7
Added searching for file names within the repository in rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
547
diff
changeset
|
103 self.search_type = search_type |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
104 self.searcher = searcher |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
105 self.matcher = matcher |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
106 self.highlight_items = highlight_items |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
107 self.fragment_size = 200 / 2 |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
108 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
109 @LazyProperty |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
110 def doc_ids(self): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
111 docs_id = [] |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
112 while self.matcher.is_active(): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
113 docnum = self.matcher.id() |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
114 chunks = [offsets for offsets in self.get_chunks()] |
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
115 docs_id.append([docnum, chunks]) |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
116 self.matcher.next() |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
117 return docs_id |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
118 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
119 def __str__(self): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
120 return '<%s at %s>' % (self.__class__.__name__, len(self.doc_ids)) |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
121 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
122 def __repr__(self): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
123 return self.__str__() |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
124 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
125 def __len__(self): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
126 return len(self.doc_ids) |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
127 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
128 def __iter__(self): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
129 """ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
130 Allows Iteration over results,and lazy generate content |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
131 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
132 *Requires* implementation of ``__getitem__`` method. |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
133 """ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
134 for docid in self.doc_ids: |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
135 yield self.get_full_content(docid) |
406
b153a51b1d3b
Implemented search using whoosh. Still as experimental option.
Marcin Kuzminski <marcin@python-works.com>
parents:
diff
changeset
|
136 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
137 def __getslice__(self, i, j): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
138 """ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
139 Slicing of resultWrapper |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
140 """ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
141 slice = [] |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
142 for docid in self.doc_ids[i:j]: |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
143 slice.append(self.get_full_content(docid)) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
144 return slice |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
145 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
146 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
147 def get_full_content(self, docid): |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
148 res = self.searcher.stored_fields(docid[0]) |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
149 f_path = res['path'][res['path'].find(res['repository']) \ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
150 + len(res['repository']):].lstrip('/') |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
151 |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
152 content_short = self.get_short_content(res, docid[1]) |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
153 res.update({'content_short':content_short, |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
154 'content_short_hl':self.highlight(content_short), |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
155 'f_path':f_path}) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
156 |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
157 return res |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
158 |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
159 def get_short_content(self, res, chunks): |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
160 |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
161 return ''.join([res['content'][chunk[0]:chunk[1]] for chunk in chunks]) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
162 |
479
149940ba96d9
fixed search chunking bug and optimized chunk size
Marcin Kuzminski <marcin@python-works.com>
parents:
478
diff
changeset
|
163 def get_chunks(self): |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
164 """ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
165 Smart function that implements chunking the content |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
166 but not overlap chunks so it doesn't highlight the same |
556
65b2f150beb7
Added searching for file names within the repository in rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
547
diff
changeset
|
167 close occurrences twice. |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
168 @param matcher: |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
169 @param size: |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
170 """ |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
171 memory = [(0, 0)] |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
172 for span in self.matcher.spans(): |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
173 start = span.startchar or 0 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
174 end = span.endchar or 0 |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
175 start_offseted = max(0, start - self.fragment_size) |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
176 end_offseted = end + self.fragment_size |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
177 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
178 if start_offseted < memory[-1][1]: |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
179 start_offseted = memory[-1][1] |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
180 memory.append((start_offseted, end_offseted,)) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
181 yield (start_offseted, end_offseted,) |
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
182 |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
183 def highlight(self, content, top=5): |
556
65b2f150beb7
Added searching for file names within the repository in rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
547
diff
changeset
|
184 if self.search_type != 'content': |
65b2f150beb7
Added searching for file names within the repository in rhodecode
Marcin Kuzminski <marcin@python-works.com>
parents:
547
diff
changeset
|
185 return '' |
478
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
186 hl = highlight(escape(content), |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
187 self.highlight_items, |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
188 analyzer=ANALYZER, |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
189 fragmenter=FRAGMENTER, |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
190 formatter=FORMATTER, |
7010af6efde5
Reimplemented searching for speed on large files and added paging for search results
Marcin Kuzminski <marcin@python-works.com>
parents:
436
diff
changeset
|
191 top=top) |
631
05528ad948c4
Hacking for git support,and new faster repo scan
Marcin Kuzminski <marcin@python-works.com>
parents:
629
diff
changeset
|
192 return hl |