skinny_jeans 0.2.3 → 0.3.0

data/README.rdoc

@@ -10,7 +10,7 @@ http://img696.imageshack.us/img696/75/skinnys3.jpg
   0.0.0.0 - - [01/Oct/2010:00:00:03 -0700] "GET /posts/my-first-post HTTP/1.1" 200 1337 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)" "-"
   0.0.0.0 - - [02/Oct/2010:00:00:03 -0700] "GET /posts/my-first-post HTTP/1.1" 200 1337 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)" "-"
 
-*  then you get 2 SQL rows that looks like:
+*  then you get 2 SQL rows that look like:
   2010-10-01, my-first-post, 3
   2010-10-02, my-first-post, 1
 *  note the date columns truncate timestamp, so the days are in whatever timezone your log file reports in
@@ -25,7 +25,7 @@ http://img696.imageshack.us/img696/75/skinnys3.jpg
   sj = SkinnyJeans::execute(logfile_path = "access.log", sqlite_skinny_jeans = "sqlite_skinny_jeans.db", path_regexp = /\s\/posts\/(.*)\sHTTP/, date_regexp = /\[(\d.*\d)\]/)
   sj.pageview.where("date = '2010-10-01' and path = 'my-first-post'")
   => #<SkinnyJeans::Pageview id: 1, date: "2010-10-01", path: "my-first-post", pageview_count: 3>
-1.  NOTE: for now *you have to monkey patch the SkinnyJeans#parse_string_as_date*
+1.  NOTE: for now **you have to monkey patch the SkinnyJeans#parse_string_as_date**
 2.  Parse oldest logs first, then run regularly against your main log, let logrotate handle the rest (skinny_jeans remembers where it left off)
 3.  ASSUMES reading log files in ascending order, keeps track of last line read so you could put it on a scheduler or cron job
 4.  access the 2 activerecord classes, sj.pageview (returns Pageview class), and sj.update
@@ -34,4 +34,9 @@ http://img696.imageshack.us/img696/75/skinnys3.jpg
 
 == PERFORMANCE
 *  it parses 100,000 lines in < 2.5 seconds
-*  persists 1,000 requests with 2 compound indexes in 15 seconds, or 10 seconds with home_run c extension
+*  persists 1,000 requests with 2 compound indexes in 15 seconds, or 10 seconds with home_run c extension
+*  25,000 rows == 4 megabyte sqlite database
+
+== NOTES
+*  supports gzipped files
+*  creates a temp copy of the log file before parsing

data/VERSION

@@ -1 +1 @@
-0.2.3
+0.3.0

data/lib/skinny_jeans.rb

@@ -4,6 +4,7 @@ require 'rubygems'
 require 'sqlite3'
 require 'active_record'
 require 'zlib'
+require 'fileutils'
 # require 'home_run'
 
 class SkinnyJeans
@@ -113,14 +114,21 @@ class SkinnyJeans
 
   end
 
+  # copies the log file, reads it, then removes it
   def file_reader
+
+    temp_file_path = "#{@logfile_path}.copy"
+    temp_file = FileUtils.cp(@logfile_path, temp_file_path)
+
     if @is_gzipped
       lineno = 0
-      Zlib::GzipReader.new(File.new(@logfile_path, "r")).each_line{|line|yield([line,lineno]);lineno+=1}
+      Zlib::GzipReader.new(File.new(temp_file_path, "r")).each_line{|line|yield([line,lineno]);lineno+=1}
       # Zlib::GzipReader.open(@logfile_path).each_line{|line|yield([line,lineno]);lineno+=1}
     else
-      File.new(@logfile_path, "r").each_with_index{|line, lineno| yield([line,lineno])}
+      File.new(temp_file_path, "r").each_with_index{|line, lineno| yield([line,lineno])}
     end
+
+    FileUtils.rm_f(temp_file_path)
   end
 
   def pageview;get_ar_class(Pageview);end

data/skinny_jeans.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{skinny_jeans}
-  s.version = "0.2.3"
+  s.version = "0.3.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Jonathan Otto"]
-  s.date = %q{2010-10-04}
+  s.date = %q{2010-10-05}
   s.email = %q{jonathan.otto@gmail.com}
   s.extra_rdoc_files = [
     "README.rdoc"

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: skinny_jeans
 version: !ruby/object:Gem::Version 
-  hash: 17
+  hash: 19
   prerelease: false
   segments: 
   - 0
-  - 2
   - 3
-  version: 0.2.3
+  - 0
+  version: 0.3.0
 platform: ruby
 authors: 
 - Jonathan Otto
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-10-04 00:00:00 -05:00
+date: 2010-10-05 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency