code_zauker 0.0.5 → 0.0.6
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +1 -0
- data/bin/czindexer +23 -1
- data/bin/czsearch +19 -3
- data/lib/code_zauker/cli.rb +40 -0
- data/lib/code_zauker/constants.rb +3 -1
- data/lib/code_zauker/version.rb +1 -1
- data/lib/code_zauker/webgui.rb +18 -1
- data/readme.org +26 -10
- data/templates/show_results.erb +8 -3
- metadata +16 -15
data/.gitignore
CHANGED
data/bin/czindexer
CHANGED
@@ -2,11 +2,18 @@
|
|
2
2
|
# Suggested execution is mixing find / xargs with the parallel (P) parameters:
|
3
3
|
# find test/fixture/ -type f | xargs -P 5 -n 10 ./bin/czindexer
|
4
4
|
# will fire 5 czindexer each with 10 files to process...
|
5
|
+
require 'code_zauker/cli'
|
6
|
+
require 'redis/connection/hiredis'
|
7
|
+
require 'redis'
|
5
8
|
require 'optparse'
|
6
9
|
options={}
|
7
10
|
optparse= OptionParser.new do |opts|
|
8
11
|
opts.banner="Usage: czindexer [options] [file1] [file2]..."
|
9
12
|
options[:verbose] = false
|
13
|
+
options[:redis_host]="127.0.0.1"
|
14
|
+
options[:redis_port]=6379
|
15
|
+
options[:redis_password]=nil
|
16
|
+
|
10
17
|
|
11
18
|
opts.on( '-v', '--verbose', 'Output more information' ) do
|
12
19
|
options[:verbose] = true
|
@@ -17,6 +24,20 @@ optparse= OptionParser.new do |opts|
|
|
17
24
|
options[:reindex]=true
|
18
25
|
end
|
19
26
|
|
27
|
+
opts.on('-h','--redis-server pass@SERVER:port', String,
|
28
|
+
'Specify the alternate redis server to use')do |server|
|
29
|
+
myoptions=CodeZauker::CliUtil.new().parse_host_options(server)
|
30
|
+
options[:redis_host]=myoptions[:redis_host]
|
31
|
+
options[:redis_port]=myoptions[:redis_port]
|
32
|
+
options[:redis_password]=myoptions[:redis_password]
|
33
|
+
|
34
|
+
if options[:redis_password]
|
35
|
+
puts "Server: #{options[:redis_host]} Port:#{options[:redis_port]} WithPassword"
|
36
|
+
else
|
37
|
+
puts "Server: #{options[:redis_host]} Port:#{options[:redis_port]}"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
20
41
|
opts.on( '-h', '--help', 'Display this screen' ) do
|
21
42
|
puts opts
|
22
43
|
exit
|
@@ -82,7 +103,8 @@ end
|
|
82
103
|
begin
|
83
104
|
$CUMULATED_TIME=0
|
84
105
|
# Allocated here to recycle connection
|
85
|
-
|
106
|
+
redisConnection=Redis.new(:host => options[:redis_host], :port => options[:redis_port], :password=> options[:redis_password])
|
107
|
+
fs=CodeZauker::FileScanner.new(redisConnection)
|
86
108
|
$PROCESSED_FILES=0
|
87
109
|
puts "Code Zauker v#{CodeZauker::VERSION}" if options[:verbose]
|
88
110
|
puts "Reindexing..." if options[:verbose]==true and options[:reindex]==true
|
data/bin/czsearch
CHANGED
@@ -4,6 +4,9 @@
|
|
4
4
|
$VERBOSE=nil
|
5
5
|
require 'code_zauker'
|
6
6
|
require 'code_zauker/grep'
|
7
|
+
require 'code_zauker/cli'
|
8
|
+
require 'redis/connection/hiredis'
|
9
|
+
require 'redis'
|
7
10
|
require 'tempfile'
|
8
11
|
require 'pdf/reader'
|
9
12
|
include Grep
|
@@ -17,6 +20,9 @@ optparse= OptionParser.new do |opts|
|
|
17
20
|
options[:postcontext]=0
|
18
21
|
options[:extensions_to_ignore]=[]
|
19
22
|
options[:file_to_exclude]=[]
|
23
|
+
options[:redis_host]="127.0.0.1"
|
24
|
+
options[:redis_port]=6379
|
25
|
+
options[:redis_password]=nil
|
20
26
|
|
21
27
|
opts.on('-i', '--ignore-case','ignore case distinctions') do
|
22
28
|
options[:ignorecase]=true
|
@@ -44,9 +50,18 @@ optparse= OptionParser.new do |opts|
|
|
44
50
|
end
|
45
51
|
|
46
52
|
|
47
|
-
opts.on('-h','--redis-server SERVER', String,
|
53
|
+
opts.on('-h','--redis-server pass@SERVER:port', String,
|
48
54
|
'Specify the alternate redis server to use')do |server|
|
49
|
-
|
55
|
+
myoptions=CodeZauker::CliUtil.new().parse_host_options(server)
|
56
|
+
options[:redis_host]=myoptions[:redis_host]
|
57
|
+
options[:redis_port]=myoptions[:redis_port]
|
58
|
+
options[:redis_password]=myoptions[:redis_password]
|
59
|
+
|
60
|
+
if options[:redis_password]
|
61
|
+
puts "Server: #{options[:redis_host]} Port:#{options[:redis_port]} WithPassword"
|
62
|
+
else
|
63
|
+
puts "Server: #{options[:redis_host]} Port:#{options[:redis_port]}"
|
64
|
+
end
|
50
65
|
end
|
51
66
|
|
52
67
|
|
@@ -69,7 +84,8 @@ optparse.parse!
|
|
69
84
|
ARGV.each do | s |
|
70
85
|
#puts "Code Zauker Searching for #{s}"
|
71
86
|
util=CodeZauker::Util.new()
|
72
|
-
|
87
|
+
redisConnection=Redis.new(:host => options[:redis_host], :port => options[:redis_port], :password=> options[:redis_password])
|
88
|
+
fs=CodeZauker::FileScanner.new(redisConnection)
|
73
89
|
if options[:ignorecase]==false
|
74
90
|
files=fs.search(s)
|
75
91
|
pattern=/#{Regexp.escape(s)}/
|
@@ -0,0 +1,40 @@
|
|
1
|
+
module CodeZauker
|
2
|
+
|
3
|
+
class CliUtil
|
4
|
+
|
5
|
+
def parse_host_options(connection_string)
|
6
|
+
#puts "Parsing... #{connection_string}"
|
7
|
+
options={}
|
8
|
+
options[:redis_host]="127.0.0.1"
|
9
|
+
options[:redis_port]=6379
|
10
|
+
options[:redis_password]=nil
|
11
|
+
r=/(\w+)@([a-zA-Z0-9.]+):([0-9]+)?/
|
12
|
+
rNoPass=/([a-zA-Z0-9.]+):([0-9]+)?/
|
13
|
+
rHostAndPass=/(\w+)@([a-zA-Z0-9.]+)/
|
14
|
+
m=r.match(connection_string)
|
15
|
+
if m
|
16
|
+
options[:redis_password]=m.captures[0]
|
17
|
+
options[:redis_host]=m.captures[1]
|
18
|
+
options[:redis_port]=m.captures[2]
|
19
|
+
|
20
|
+
else
|
21
|
+
m=rNoPass.match(connection_string)
|
22
|
+
if m
|
23
|
+
options[:redis_host]=m.captures[0]
|
24
|
+
options[:redis_port]=m.captures[1]
|
25
|
+
else
|
26
|
+
# Check the auth@host case right here
|
27
|
+
m2=rHostAndPass.match(connection_string)
|
28
|
+
if m2
|
29
|
+
options[:redis_password]=m2.captures[0]
|
30
|
+
options[:redis_host]=m2.captures[1]
|
31
|
+
else
|
32
|
+
#puts "SERVER ONLY"
|
33
|
+
options[:redis_host]=connection_string
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
return options
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
@@ -1,5 +1,7 @@
|
|
1
1
|
module CodeZauker
|
2
|
-
|
2
|
+
# Under Amazon AWS, a lot of timeout can happen.
|
3
|
+
# We put a higer retry here
|
4
|
+
MAX_PUSH_TRIGRAM_RETRIES=15
|
3
5
|
# Stats
|
4
6
|
# It is difficult to decide what is the best trigram push size.
|
5
7
|
# a larger one ensure a best in memory processing but can lead to longer transactions
|
data/lib/code_zauker/version.rb
CHANGED
data/lib/code_zauker/webgui.rb
CHANGED
@@ -3,6 +3,8 @@ require 'sinatra'
|
|
3
3
|
require "code_zauker/version"
|
4
4
|
require "code_zauker"
|
5
5
|
require "erb"
|
6
|
+
require 'code_zauker/grep'
|
7
|
+
include Grep
|
6
8
|
|
7
9
|
# See http://www.sinatrarb.com/intro
|
8
10
|
get '/' do
|
@@ -14,7 +16,22 @@ get '/search' do
|
|
14
16
|
# Process the search and show the results...
|
15
17
|
fs=CodeZauker::FileScanner.new()
|
16
18
|
files=fs.isearch(params[:q])
|
17
|
-
|
19
|
+
util=CodeZauker::Util.new()
|
20
|
+
abstracts=[]
|
21
|
+
files.each do |f|
|
22
|
+
if util.is_pdf?(f)==false
|
23
|
+
askedQuery=params[:q]
|
24
|
+
pattern=/#{Regexp.escape(askedQuery)}/i
|
25
|
+
lines=grep(f,pattern, pre_context=2, post_context=2);
|
26
|
+
desc=""
|
27
|
+
lines.each do |l |
|
28
|
+
hilighted=l.gsub(/(#{Regexp.escape(askedQuery)})/i){ "<b>#{$1}</b>"}
|
29
|
+
desc=desc+ "#{f}:#{hilighted}\n"
|
30
|
+
end
|
31
|
+
abstracts.push(desc)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
erb :show_results, :locals => {:files => abstracts, :q => params[:q] }
|
18
35
|
end
|
19
36
|
|
20
37
|
configure do
|
data/readme.org
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
* Code Zauker: your code, indexed
|
2
2
|
Code Zauker is a search engine for programming languages.
|
3
|
-
Code Zauker is based from ideas taken by old Google Code Search and uses Redis as
|
3
|
+
Code Zauker is based from ideas taken by old Google Code Search and uses Redis as storage engine.
|
4
4
|
|
5
5
|
For news and discussion: http://gioorgi.com/tag/code-zauker/
|
6
6
|
|
@@ -13,17 +13,33 @@ To install Code Zauker,simply issue
|
|
13
13
|
You need also [[http://redis.io/][redis-2.4.6]] or better.
|
14
14
|
For a sample redis configuration see the etc/ directory of the project
|
15
15
|
|
16
|
+
* Try it out
|
17
|
+
Take a look to czindex and czsearch commands help for usage patterns.
|
18
|
+
|
19
|
+
|
16
20
|
|
17
21
|
* Release History
|
18
|
-
| Version | Date | Summary
|
19
|
-
|
20
|
-
| 0.0.
|
21
|
-
| 0.0.
|
22
|
-
| 0.0.
|
23
|
-
| 0.0.
|
24
|
-
| 0.0.
|
25
|
-
|
|
26
|
-
| | |
|
22
|
+
| Version | Date | Summary |
|
23
|
+
|---------+-------------+-----------------------------------------------------------------|
|
24
|
+
| 0.0.6 | 04 May 2012 | New redis-server option. Better web search with results hilight |
|
25
|
+
| 0.0.5 | 09 Apr 2012 | Added Sinatra-based web search page, featuring bootrstrap css |
|
26
|
+
| 0.0.4 | 12 Feb 2012 | PDF Searching |
|
27
|
+
| 0.0.3 | 03 Feb 2012 | Added Case insensitive search.UTF-8 trigram database |
|
28
|
+
| 0.0.2 | 29 Jan 2012 | Removed dependency on unix find for czindexer. |
|
29
|
+
| 0.0.1 | 26 Jan 2012 | First RubyGems Release (for testing purpose only) |
|
30
|
+
| | | |
|
31
|
+
| | | |
|
32
|
+
|
33
|
+
* Aws tests
|
34
|
+
** Micro instance
|
35
|
+
Without multiplexing you get
|
36
|
+
real 4m39.599s
|
37
|
+
for indexing code_zauker
|
38
|
+
|
39
|
+
With
|
40
|
+
time find . -type f -print0 | xargs -0 -P 10 -n 20 ./bin/czindexer -v --redis-server awsserver
|
41
|
+
You get about
|
42
|
+
real 0m31.284s
|
27
43
|
|
28
44
|
|
29
45
|
* DEVELOPING
|
data/templates/show_results.erb
CHANGED
@@ -32,15 +32,20 @@
|
|
32
32
|
|
33
33
|
</form>
|
34
34
|
</p>
|
35
|
+
<style>
|
36
|
+
b{
|
37
|
+
color: #A1A100;
|
38
|
+
}
|
39
|
+
</style>
|
35
40
|
<span class="badge badge-success"> <%=files.length%> Results</span>
|
36
41
|
<ol>
|
37
42
|
<%
|
38
43
|
files.each do |f|
|
39
|
-
|
44
|
+
%>
|
40
45
|
<li><%=f%>
|
41
|
-
|
46
|
+
<%
|
42
47
|
end
|
43
|
-
|
48
|
+
%>
|
44
49
|
</ol>
|
45
50
|
</div>
|
46
51
|
</div>
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: code_zauker
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.6
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-04
|
12
|
+
date: 2012-05-04 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: yard
|
16
|
-
requirement: &
|
16
|
+
requirement: &74198570 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ~>
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0.7'
|
22
22
|
type: :development
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *74198570
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: rubyzip
|
27
|
-
requirement: &
|
27
|
+
requirement: &74197690 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ~>
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: '0.9'
|
33
33
|
type: :development
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *74197690
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: hiredis
|
38
|
-
requirement: &
|
38
|
+
requirement: &74196880 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ~>
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0.3'
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *74196880
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: redis
|
49
|
-
requirement: &
|
49
|
+
requirement: &74196090 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ~>
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '2.2'
|
55
55
|
type: :runtime
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *74196090
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: pdf-reader
|
60
|
-
requirement: &
|
60
|
+
requirement: &74187710 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: 1.0.0
|
66
66
|
type: :runtime
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *74187710
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: sinatra
|
71
|
-
requirement: &
|
71
|
+
requirement: &74186780 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ~>
|
@@ -76,7 +76,7 @@ dependencies:
|
|
76
76
|
version: '1.3'
|
77
77
|
type: :runtime
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *74186780
|
80
80
|
description: Code Zauker is based from ideas taken by old Google Code Search and uses
|
81
81
|
Redis as a basic platform
|
82
82
|
email:
|
@@ -129,6 +129,7 @@ files:
|
|
129
129
|
- htdocs/js/bootstrap.js
|
130
130
|
- htdocs/js/bootstrap.min.js
|
131
131
|
- lib/code_zauker.rb
|
132
|
+
- lib/code_zauker/cli.rb
|
132
133
|
- lib/code_zauker/constants.rb
|
133
134
|
- lib/code_zauker/grep.rb
|
134
135
|
- lib/code_zauker/version.rb
|
@@ -163,7 +164,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
163
164
|
version: '0'
|
164
165
|
requirements: []
|
165
166
|
rubyforge_project: code_zauker
|
166
|
-
rubygems_version: 1.8.
|
167
|
+
rubygems_version: 1.8.11
|
167
168
|
signing_key:
|
168
169
|
specification_version: 3
|
169
170
|
summary: A search engine for programming languages
|