code_zauker 0.0.6 → 0.0.7
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/mczindexer +4 -0
- data/bin/report.rb +40 -0
- data/code_zauker.gemspec +3 -0
- data/lib/code_zauker/cli.rb +42 -0
- data/lib/code_zauker/constants.rb +6 -2
- data/lib/code_zauker/version.rb +1 -1
- data/lib/code_zauker/webgui.rb +2 -1
- data/readme.org +48 -1
- metadata +29 -14
data/bin/mczindexer
ADDED
data/bin/report.rb
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
require 'set'
|
3
|
+
require 'code_zauker'
|
4
|
+
require 'code_zauker/grep'
|
5
|
+
require 'code_zauker/cli'
|
6
|
+
require 'redis/connection/hiredis'
|
7
|
+
require 'redis'
|
8
|
+
require 'tempfile'
|
9
|
+
require 'pdf/reader'
|
10
|
+
|
11
|
+
puts "Redis Code Zauker Report"
|
12
|
+
require 'optparse'
|
13
|
+
options={}
|
14
|
+
optparse= OptionParser.new do |opts|
|
15
|
+
opts.banner="Usage: report [options] "
|
16
|
+
|
17
|
+
options[:redis_host]="127.0.0.1"
|
18
|
+
options[:redis_port]=6379
|
19
|
+
options[:redis_password]=nil
|
20
|
+
|
21
|
+
opts.on('-h','--redis-server pass@SERVER:port', String,
|
22
|
+
'Specify the alternate redis server to use')do |server|
|
23
|
+
myoptions=CodeZauker::CliUtil.new().parse_host_options(server)
|
24
|
+
options[:redis_host]=myoptions[:redis_host]
|
25
|
+
options[:redis_port]=myoptions[:redis_port]
|
26
|
+
options[:redis_password]=myoptions[:redis_password]
|
27
|
+
|
28
|
+
if options[:redis_password]
|
29
|
+
puts "Server: #{options[:redis_host]} Port:#{options[:redis_port]} WithPassword"
|
30
|
+
else
|
31
|
+
puts "Server: #{options[:redis_host]} Port:#{options[:redis_port]}"
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
optparse.parse!
|
36
|
+
|
37
|
+
util=CodeZauker::CliUtil.new()
|
38
|
+
redisConnection=Redis.new(:host => options[:redis_host], :port => options[:redis_port], :password=> options[:redis_password])
|
39
|
+
util.do_report(redisConnection)
|
40
|
+
|
data/code_zauker.gemspec
CHANGED
@@ -27,6 +27,9 @@ Gem::Specification.new do |s|
|
|
27
27
|
s.add_runtime_dependency "redis", "~> 2.2"
|
28
28
|
s.add_runtime_dependency "pdf-reader", "~> 1.0.0"
|
29
29
|
s.add_runtime_dependency "sinatra", "~> 1.3"
|
30
|
+
s.add_runtime_dependency "redis_logger", "~> 0.1"
|
31
|
+
# Eval http://github.com/masonoise/redis_logger-web
|
32
|
+
|
30
33
|
# thin unable to be installed for missing g++ on my dev platform (shame on debian)
|
31
34
|
#s.add_runtime_dependency "thin"
|
32
35
|
## Install and require the hiredis gem before redis-rb for maximum performances.
|
data/lib/code_zauker/cli.rb
CHANGED
@@ -36,5 +36,47 @@ module CodeZauker
|
|
36
36
|
end
|
37
37
|
return options
|
38
38
|
end
|
39
|
+
|
40
|
+
def do_report(redis)
|
41
|
+
puts "Simple Reporting....on #{redis.client.host}"
|
42
|
+
id2filename=redis.keys "fscan:id2filename:*"
|
43
|
+
puts "File Stored:\t\t#{id2filename.length}"
|
44
|
+
processedFiles=redis.scard("fscan:processedFiles")
|
45
|
+
puts "Processed Files:\t#{processedFiles}"
|
46
|
+
# Complex... compute average "fscan:trigramsOnFile:#{fid}"
|
47
|
+
sum=0.0
|
48
|
+
max=0
|
49
|
+
min=90000000000000000
|
50
|
+
fileName2Ids=redis.keys "fscan:id:*"
|
51
|
+
count=fileName2Ids.length+0.0
|
52
|
+
puts "Finding ids..."
|
53
|
+
ids=redis.mget(*(redis.keys("fscan:id:*")))
|
54
|
+
puts "Scanning ids..."
|
55
|
+
ids.each do | fid |
|
56
|
+
# Forma fscan:trigramsOnFile:5503
|
57
|
+
trigramsOnFile=redis.scard("fscan:trigramsOnFile:#{fid}")
|
58
|
+
sum = sum + trigramsOnFile
|
59
|
+
# if trigramsOnFile == 0 or trigramsOnFile >=max
|
60
|
+
# fname=redis.get("fscan:id2filename:#{fid}")
|
61
|
+
# puts "Note fscan:trigramsOnFile:#{fid} -> #{trigramsOnFile} #{fname}"
|
62
|
+
# end
|
63
|
+
max=trigramsOnFile if trigramsOnFile >max
|
64
|
+
min=trigramsOnFile if trigramsOnFile <min and trigramsOnFile>0
|
65
|
+
end
|
66
|
+
av=sum/count
|
67
|
+
puts "Average Trigrams per file:#{av} Min: #{min} Max: #{max}"
|
68
|
+
tagCharSize=max/80
|
69
|
+
#tagCharSize=max/10 if tagCharSize>80
|
70
|
+
puts "Graphic summary... +=#{tagCharSize}"
|
71
|
+
ids.each do | fid |
|
72
|
+
trigramsOnFile=redis.scard("fscan:trigramsOnFile:#{fid}")
|
73
|
+
if trigramsOnFile>= (tagCharSize*3)
|
74
|
+
fname=redis.get("fscan:id2filename:#{fid}")
|
75
|
+
bar="+"*(trigramsOnFile/tagCharSize)
|
76
|
+
puts "#{bar} #{fname}"
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
end
|
39
81
|
end
|
40
82
|
end
|
@@ -10,9 +10,11 @@ module CodeZauker
|
|
10
10
|
DEFAULT_EXCLUDED_EXTENSION=[
|
11
11
|
# Documents
|
12
12
|
".xps",
|
13
|
-
".zip",".7z",
|
13
|
+
".zip",".7z","rar",
|
14
14
|
# MS Office zip-like files...
|
15
15
|
".pptx",".docx",".xlsx",
|
16
|
+
# Avoid slurping text document too...
|
17
|
+
".doc",
|
16
18
|
".ppt",".xls",".rtf",".vsd", ".odf",
|
17
19
|
# Binary bad stuff
|
18
20
|
".dll",".exe",".out",".elf",".lib",".so",
|
@@ -25,7 +27,9 @@ module CodeZauker
|
|
25
27
|
".tar",
|
26
28
|
".gz",".Z",
|
27
29
|
".dropbox",
|
28
|
-
".svn-base",".pdb",".cache",
|
30
|
+
".svn-base",".pdb",".cache",
|
31
|
+
#IDE STUFF
|
32
|
+
".wlwLock",
|
29
33
|
# Music exclusion
|
30
34
|
".mp3",".mp4",".wav",
|
31
35
|
# Image exclusion
|
data/lib/code_zauker/version.rb
CHANGED
data/lib/code_zauker/webgui.rb
CHANGED
@@ -24,7 +24,8 @@ get '/search' do
|
|
24
24
|
pattern=/#{Regexp.escape(askedQuery)}/i
|
25
25
|
lines=grep(f,pattern, pre_context=2, post_context=2);
|
26
26
|
desc=""
|
27
|
-
lines.each do |l |
|
27
|
+
lines.each do | l |
|
28
|
+
# http://stackoverflow.com/questions/1287630/ruby-gsub-and-regex
|
28
29
|
hilighted=l.gsub(/(#{Regexp.escape(askedQuery)})/i){ "<b>#{$1}</b>"}
|
29
30
|
desc=desc+ "#{f}:#{hilighted}\n"
|
30
31
|
end
|
data/readme.org
CHANGED
@@ -14,13 +14,60 @@ 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
16
|
* Try it out
|
17
|
-
|
17
|
+
** To index all your files
|
18
|
+
The following command will index all the code file below /full_path_of_sources/ providing
|
19
|
+
a feedback on standard output
|
20
|
+
#+BEGIN_SRC sh
|
21
|
+
czindexer -v /full_path_of_sources/
|
22
|
+
#+END_SRC
|
23
|
+
If your redis server is on another machine, you can use the following command
|
24
|
+
#+BEGIN_SRC sh
|
25
|
+
czindexer --redis-server myredisserver -v /full_path_of_sources/
|
26
|
+
#+END_SRC
|
27
|
+
Also authentication over redis is supported:
|
28
|
+
#+BEGIN_SRC sh
|
29
|
+
czindexer --redis-server password@rediserverpwp -v /full_path_of_sources/
|
30
|
+
#+END_SRC
|
31
|
+
|
32
|
+
|
33
|
+
To search for the 'my_beautiful_method' try out:
|
34
|
+
#+BEGIN_SRC sh
|
35
|
+
czsearch my_beautiful_method
|
36
|
+
#+END_SRC
|
18
37
|
|
38
|
+
Looking case insensitive can be userful too....
|
39
|
+
#+BEGIN_SRC sh
|
40
|
+
czsearch -i 'Select USER_id'
|
41
|
+
#+END_SRC
|
42
|
+
|
43
|
+
Tip:Take a look to czindex and czsearch commands help for full options list
|
44
|
+
** Web interface
|
45
|
+
There is a new shiny web interface based on sinatra. To try it out, fire
|
46
|
+
#+BEGIN_SRC sh
|
47
|
+
./bin/webgui
|
48
|
+
#+END_SRC
|
49
|
+
It is still beta, but it is *very* fast, thank to redis!
|
50
|
+
|
51
|
+
|
52
|
+
** Parallel execution
|
53
|
+
If you want to speed up indexing, you can use the mczindexer command.
|
54
|
+
For instance:
|
55
|
+
mczindexer eclipse-sources/
|
56
|
+
will fire at most 10 parallel czindexer.
|
57
|
+
|
58
|
+
** Simple stats
|
59
|
+
You can ask code zauker to print a nice stats on standard output.
|
60
|
+
Run
|
61
|
+
#+BEGIN_SRC sh
|
62
|
+
./bin/report.rb
|
63
|
+
#+END_SRC
|
64
|
+
and enjoy!
|
19
65
|
|
20
66
|
|
21
67
|
* Release History
|
22
68
|
| Version | Date | Summary |
|
23
69
|
|---------+-------------+-----------------------------------------------------------------|
|
70
|
+
| 0.0.7 | 13 May 2012 | Better documentation, mczindexer, new report command
|
24
71
|
| 0.0.6 | 04 May 2012 | New redis-server option. Better web search with results hilight |
|
25
72
|
| 0.0.5 | 09 Apr 2012 | Added Sinatra-based web search page, featuring bootrstrap css |
|
26
73
|
| 0.0.4 | 12 Feb 2012 | PDF Searching |
|
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: 0.0.7
|
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: 2012-05-
|
12
|
+
date: 2012-05-13 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: yard
|
16
|
-
requirement: &
|
16
|
+
requirement: &83355880 !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: *83355880
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: rubyzip
|
27
|
-
requirement: &
|
27
|
+
requirement: &83355530 !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: *83355530
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: hiredis
|
38
|
-
requirement: &
|
38
|
+
requirement: &83355130 !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: *83355130
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: redis
|
49
|
-
requirement: &
|
49
|
+
requirement: &83354730 !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: *83354730
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: pdf-reader
|
60
|
-
requirement: &
|
60
|
+
requirement: &83354000 !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: *83354000
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: sinatra
|
71
|
-
requirement: &
|
71
|
+
requirement: &83130590 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ~>
|
@@ -76,7 +76,18 @@ dependencies:
|
|
76
76
|
version: '1.3'
|
77
77
|
type: :runtime
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *83130590
|
80
|
+
- !ruby/object:Gem::Dependency
|
81
|
+
name: redis_logger
|
82
|
+
requirement: &83130330 !ruby/object:Gem::Requirement
|
83
|
+
none: false
|
84
|
+
requirements:
|
85
|
+
- - ~>
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0.1'
|
88
|
+
type: :runtime
|
89
|
+
prerelease: false
|
90
|
+
version_requirements: *83130330
|
80
91
|
description: Code Zauker is based from ideas taken by old Google Code Search and uses
|
81
92
|
Redis as a basic platform
|
82
93
|
email:
|
@@ -84,6 +95,8 @@ email:
|
|
84
95
|
executables:
|
85
96
|
- czindexer
|
86
97
|
- czsearch
|
98
|
+
- mczindexer
|
99
|
+
- report.rb
|
87
100
|
- startRedis
|
88
101
|
- webgui
|
89
102
|
extensions: []
|
@@ -96,6 +109,8 @@ files:
|
|
96
109
|
- Rakefile
|
97
110
|
- bin/czindexer
|
98
111
|
- bin/czsearch
|
112
|
+
- bin/mczindexer
|
113
|
+
- bin/report.rb
|
99
114
|
- bin/startRedis
|
100
115
|
- bin/webgui
|
101
116
|
- code_zauker.gemspec
|