0

我有两个哈希数组，格式为：

哈希1

[{:root => root_value, :child1 => child1_value, :subchild1 => subchild1_value, bases => hit1,hit2,hit3}...]

哈希2

[{:path => root_value/child1_value/subchild1_value, :hit1_exist => t ,hit2_exist => t,hit3_exist => f}...]

如果我这样做

Def sample
  results = nil
  project = Project.find(params[:project_id])
  testrun_query = "SELECT root_name, suite_name, case_name, ic_name, executed_platforms FROM testrun_caches WHERE start_date >= '#{params[:start_date]}' AND start_date < '#{params[:end_date]}' AND project_id = #{params[:project_id]} AND result <> 'SKIP' AND result <> 'N/A'"
  if !params[:platform].nil? && params[:platform] != [""]
    #yell_and_log "platform not nil"
    platform_query = nil
    params[:platform].each do |platform|
      if platform_query.nil?
        platform_query = " AND (executed_platforms LIKE '%#{platform.to_s},%'"
      else
        platform_query += " OR executed_platforms LIKE '%#{platform.to_s},%'"
      end
    end
    testrun_query += ")" + platform_query
  end
  if !params[:location].nil? &&!params[:location].empty?
    #yell_and_log "location not nil"
    testrun_query += "AND location LIKE '#{params[:location].to_s}%'"    
  end
  testrun_query += " GROUP BY root_name, suite_name, case_name, ic_name,   executed_platforms ORDER BY root_name, suite_name, case_name, ic_name"
  ic_query = "SELECT ics.path, memberships.pts8210, memberships.sv6, memberships.sv7,   memberships.pts14k, memberships.pts22k, memberships.pts24k, memberships.spb32, memberships.spb64, memberships.sde, projects.name FROM ics INNER JOIN memberships on memberships.ic_id = ics.id INNER JOIN test_groups ON test_groups.id = memberships.test_group_id INNER JOIN projects ON test_groups.project_id = projects.id WHERE deleted = 'false' AND (memberships.pts8210 = true OR memberships.sv6 = true OR memberships.sv7 = true OR memberships.pts14k = true OR memberships.pts22k = true OR memberships.pts24k = true OR memberships.spb32 = true OR memberships.spb64 = true OR memberships.sde = true) AND projects.name = '#{project.name}' GROUP BY path, memberships.pts8210, memberships.sv6, memberships.sv7, memberships.pts14k, memberships.pts22k, memberships.pts24k, memberships.spb32, memberships.spb64, memberships.sde, projects.name ORDER BY ics.path"
  if params[:ic_type] == "never_run"
    runtest = TestrunCache.connection.select_all(testrun_query)
    alltest = TrsIc.connection.select_all(ic_query) 
    (alltest.length).times do |i|
      #exec_pltfrm = test['executed_platforms'].split(",")
      unfinishedtest = comparison(runtest[i],alltest[i])
      yell_and_log("test = #{unfinishedtest}")
      yell_and_log("#{runtest[i]}")
      yell_and_log("#{alltest[i]}")
    end
  end
end

我进入我的日志：

test = true
array of hash 1 = {"root_name"=>"BSDPLATFORM", "suite_name"=>"cli",  "case_name"=>"functional", "ic_name"=>"cli_sanity_test", "executed_platforms"=>"pts22k,pts24k,sv7,"}
array of hash 2 = {"path"=>"BSDPLATFORM/cli/functional/cli_sanity_test", "pts8210"=>"f", "sv6"=>"f", "sv7"=>"t", "pts14k"=>nil, "pts22k"=>"t", "pts24k"=>"t", "spb32"=>nil, "spb64"=>nil, "sde"=>nil, "name"=>"pts_6_20"}
test = false
array of hash 1 = {"root_name"=>"BSDPLATFORM", "suite_name"=>"infrastructure", "case_name"=>"bypass_pts14k_copper", "ic_name"=>"ic_packet_9", "executed_platforms"=>"sv6,"}
array of hash 2 = {"path"=>"BSDPLATFORM/infrastructure/build/copyrights", "pts8210"=>"f", "sv6"=>"t", "sv7"=>"t", "pts14k"=>"f", "pts22k"=>"t", "pts24k"=>"t", "spb32"=>"f", "spb64"=>nil, "sde"=>nil, "name"=>"pts_6_20"}
test = false
array of hash 1 = {"root_name"=>"BSDPLATFORM", "suite_name"=>"infrastructure", "case_name"=>"bypass_pts14k_copper", "ic_name"=>"ic_status_1", "executed_platforms"=>"sv6,"}
array of hash 2 = {"path"=>"BSDPLATFORM/infrastructure/build/ic_1", "pts8210"=>"f", "sv6"=>"t", "sv7"=>"t", "pts14k"=>"f", "pts22k"=>"t", "pts24k"=>"t", "spb32"=>"f", "spb64"=>nil, "sde"=>nil, "name"=>"pts_6_20"}
test = false
array of hash 1 = {"root_name"=>"BSDPLATFORM", "suite_name"=>"infrastructure", "case_name"=>"bypass_pts14k_copper", "ic_name"=>"ic_status_2", "executed_platforms"=>"sv6,"}
array of hash 2 = {"path"=>"BSDPLATFORM/infrastructure/build/ic_files", "pts8210"=>"f", "sv6"=>"t", "sv7"=>"f", "pts14k"=>"f", "pts22k"=>"t", "pts24k"=>"t", "spb32"=>"f", "spb64"=>nil, "sde"=>nil, "name"=>"pts_6_20"}

所以我只得到第一个匹配但休息变得不同，我得到一个而不是 4230

我想通过路径和 root/suite/case/ic 进行匹配，然后比较在哈希 1 数组中传递的执行平台与在哈希 2 数组中设置为 true 的平台

4

2 回答 2

1

不确定这是否最快，我是根据您未提供示例代码的原始问题编写的，但是：

def compare(h1, h2)
  (h2[:path] == "#{h1[:root]}/#{h1[:child1]}/#{h1[:subchild1]}") && \
  (h2[:hit1_exist] == ((h1[:bases][0] == nil) ? 'f' : 't')) && \
  (h2[:hit2_exist] == ((h1[:bases][1] == nil) ? 'f' : 't')) && \
  (h2[:hit3_exist] == ((h1[:bases][2] == nil) ? 'f' : 't'))
end

def compare_arr(h1a, h2a)
  (h1a.length).times do |i|
    compare(h1a[i],h2a[i])
  end
end

测试：

require "benchmark"

h1a = []
h2a = []

def rstr
  # from http://stackoverflow.com/a/88341/178651
  (0...2).map{65.+(rand(26)).chr}.join
end

def rnil
  rand(2) > 0 ? '' : nil
end

10000.times do
  h1a << {:root => rstr(), :child1 => rstr(), :subchild1 => rstr(), :bases => [rnil,rnil,rnil]}
  h2a << {:path => '#{rstr()}/#{rstr()}/#{rstr()}', :hit1_exist => 't', :hit2_exist => 't', :hit3_exist => 'f'}
end

Benchmark.measure do
  compare_arr(h1a,h2a)
end

结果：

=>   0.020000   0.000000   0.020000 (  0.024039)

现在我正在查看您的代码，我认为可以通过删除数组创建以及创建需要垃圾收集的数组和字符串的拆分和连接来优化它，这也会减慢速度，但不会减慢你提到。

您的数据库查询可能很慢。对它们运行解释/分析或类似操作，以查看为什么每个都慢，优化/减少查询，在需要的地方添加索引等。此外，检查 cpu 和内存利用率等。它可能不仅仅是代码。

但是，有一些明确的事情需要解决。您还面临一些 SQL 注入攻击的风险，例如：

... start_date >= '#{params[:start_date]}' AND start_date < '#{params[:end_date]}' AND project_id = #{params[:project_id]} ...

将参数和变量直接放入 SQL 的任何地方都可能存在危险。您需要确保使用准备好的语句或至少 SQL 转义值。一直阅读： http: //guides.rubyonrails.org/active_record_querying.html

于 2013-02-05T15:24:10.847 回答
0 
([element_being_tested].each do |el|
  [hash_array_1, hash_array_2].reject do |x, y|
    x[el] == y[el]
  end
end).each {|x, y| puts (x[bases] | y[bases])}

枚举要测试的哈希元素。[element_being_tested].each 做 |el|

然后遍历散列数组本身，将给定的散列与由外部循环定义的给定比较的元素进行比较，拒绝那些不适当相等的散列。（==实际上可能需要，!=但你可以弄清楚那么多）

  [hash_array_1, hash_array_2].reject do |x, y|
    x[el] == y[el]
  end

最后，您再次比较采用其元素的集合并集的哈希值。

.each {|x, y| puts (x[bases] | y[bases])}

您可能需要测试代码。与其说是用于演示不如说是用于生产，因为我不确定我是否正确阅读了您的代码。如果此答案不令人满意，请发布更大的源样本，包括有问题的数据结构。

关于速度：如果您正在迭代一个大型数据集并比较多个数据集，那么您可能无能为力。也许您可以反转我提出的循环，并使散列数组成为外循环。如果数据结构很大，你不会在 Ruby（实际上是任何语言）中获得闪电般的速度。

于 2013-02-05T01:14:22.017 回答