web_grep 0.0.1 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c3227a0d2994fdaf379572fc7dc089fb772b70f6
-  data.tar.gz: 197b8a5aa3088295888e4349a095684f1ca74656
+  metadata.gz: a6cf41b7dc06a31a4e7f297af3c4f31347c2225b
+  data.tar.gz: 30b46cf335dc3c851c2678ca821c31c5195fb084
 SHA512:
-  metadata.gz: ade710caac2058b7d3522c9cb4742d1b9be116513c75e55ff204212abb9d789b80ed1b35f0695aa7471bb4959d85918864b2c354aae94f5889b3bf5de1ca7a9f
-  data.tar.gz: e2700740630b8fcf74dc9136358f2f8c1b61389297430907c31d099026f17c064f5111b152e78133b600798a3af74b7a71f3d77a647733bb480e32f5acd54857
+  metadata.gz: 56ad7babc92330e88045709384dffea4a9ef855e1864b5b040c700925081edbafe8a02df3b797645eb0268aa864a3124bafd5e834763872a0b3186f84fbd05e4
+  data.tar.gz: 5d63c2a62958874d1271feb4a7212c7233f78cec52b0d896fd3c7f1fd9682852defd23382b3c3196f7fa20b470016cb489566561b8fd7146d33c856c26e1eafc

data/.gitignore

@@ -0,0 +1,3 @@
+*.gem
+.bundle
+Gemfile.lock

data/Gemfile

@@ -0,0 +1,9 @@
+source "https://rubygems.org"
+
+gemspec
+
+gem 'rake'
+gem 'bump'
+gem 'minitest'
+gem 'minitest-rg'
+gem 'minitest-around'

data/README.md

@@ -0,0 +1,22 @@
+web_grep
+-------
+
+Web grep is a grep for web pages.
+
+Installation
+============
+
+```
+gem install web_grep
+```
+
+Usage
+=====
+
+
+Copyright
+=========
+
+Copyright (c) 2014 Vladislav Petrov.
+
+See MIT-LICENSE.md for further details.

data/Rakefile

@@ -0,0 +1,7 @@
+require 'rake/testtask'
+require 'bump/tasks'
+
+Rake::TestTask.new :default do |test|
+  test.pattern = 'test/**/*_test.rb'
+  test.verbose = true
+end

data/bin/web_grep

@@ -0,0 +1,44 @@
+#!/usr/bin/env ruby
+$LOAD_PATH << './lib'
+
+require 'optparse'
+require 'web_grep'
+
+options = {}
+OptionParser.new do |opt|
+  opt.banner  = "Usage:\n    web_grep WORD WEB_PAGE [OPTIONS]"
+  opt.separator ''
+  opt.separator 'Options'
+
+  opt.on('-w', '--word [word]', String, 'Searcheble word or RegExp') do |word|
+    options[:word] = word
+  end
+
+  opt.on('-f', '--file [file_path]', String, 'Search in file: "../index.html"') do |file|
+    options[:file] = file
+  end
+
+  opt.on('-u', '--url [url]', String, 'Search in URL: "ya.ru"') do |url|
+    options[:url] = url
+  end
+
+  opt.on_tail('-v', '--version', 'Show version') do
+    puts WebGrep::VERSION
+    exit
+  end
+
+  opt.on_tail('-h', '--help', 'Show this help') { puts opt; exit }
+  
+  if ARGV.empty? && options.empty?
+    opt.on { puts opt; exit }
+  end
+end.parse!
+
+greped = WebGrep::Grep.new(
+  word: options[:word] || ARGV[0],
+  url:  options[:url ] || ARGV[1],
+  file: options[:file]
+).grep!
+
+puts greped
+puts "#{"\033[32;1m"}Found #{greped.count}#{"\033[0m"}"

data/lib/web_grep/grep.rb

@@ -0,0 +1,29 @@
+require 'nokogiri'
+require 'open-uri'
+
+module WebGrep
+  class Grep
+    def initialize(word:,url:,file:)
+      if file && url
+        raise 'Should set one of params, url or file!'
+      end
+      if url && !url.match('http://|https://')
+        url = "http://#{url}"
+      end
+      @word, @url, @file = word, url, file
+    end
+
+    def grep!
+      Nokogiri::XML(open(@url || @file)).search('[text()*=""]').select do |e|
+        e.content
+          .encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
+          .match /#{@word}/
+      end.map do |l|
+        "#{"\033[32;1m"}XPath: #{l.path}#{"\033[0m"}\n" \
+        "\tMatched content: #{l.content}"
+      end
+    rescue SocketError
+      raise 'Bad url or connection!'
+    end
+  end
+end

data/lib/web_grep/version.rb

@@ -1,3 +1,3 @@
 module WebGrep
-  VERSION = '0.0.1'
+  VERSION = '1.0.0'
 end

data/lib/web_grep.rb

@@ -1,3 +1,4 @@
 module WebGrep
   autoload :VERSION, 'web_grep/version'
+  autoload :Grep,    'web_grep/grep'
 end

data/test/test_helper.rb

@@ -0,0 +1,4 @@
+require 'minitest/autorun'
+require 'minitest/rg'
+require 'minitest/around'
+$LOAD_PATH.unshift File.expand_path("../../lib", __FILE__)

data/test/web_grep_test.rb

@@ -0,0 +1,18 @@
+require_relative 'test_helper'
+require 'tmpdir'
+
+describe WebGrep do
+  describe 'CLI' do
+    def web_grep(command='')
+      `#{Bundler.root}/bin/web_grep #{command}`
+    end
+
+    it 'shows --version' do
+      web_grep('--version').must_include WebGrep::VERSION
+    end
+
+    it 'shows --help' do
+      web_grep('--help').must_include 'web_grep'
+    end
+  end
+end

data/web_grep.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new 'web_grep', WebGrep::VERSION do |s|
   s.required_rubygems_version = '>= 2.3.0'
 
   s.files         = `git ls-files`.split
-  s.test_files    = `git ls-files -- {test,spec,features}/*`.split
-  s.executables   = `git ls-files -- bin/*`.split.map{ |f| File.basename(f) }
+  s.test_files    = `git ls-files -- {test,spec,features}`.split
+  s.executables   = `git ls-files -- bin`.split.map{ |f| File.basename(f) }
   s.require_paths = ['lib']
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: web_grep
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Vladislav Petrov
@@ -12,13 +12,22 @@ date: 2014-06-26 00:00:00.000000000 Z
 dependencies: []
 description: Web grep is a grep for web pages
 email: electronicchest@gmail.com
-executables: []
+executables:
+- web_grep
 extensions: []
 extra_rdoc_files: []
 files:
+- ".gitignore"
+- Gemfile
 - MIT-LICENSE.md
+- README.md
+- Rakefile
+- bin/web_grep
 - lib/web_grep.rb
+- lib/web_grep/grep.rb
 - lib/web_grep/version.rb
+- test/test_helper.rb
+- test/web_grep_test.rb
 - web_grep.gemspec
 homepage: http://rubygems.org/gems/web_grep
 licenses:
@@ -44,4 +53,6 @@ rubygems_version: 2.3.0
 signing_key: 
 specification_version: 4
 summary: Web grep is a grep for web pages
-test_files: []
+test_files:
+- test/test_helper.rb
+- test/web_grep_test.rb