我为自定义文本文件格式创建了一个 Qi 解析器。有数以万计的条目要处理，每个条目通常有 1-10 个子条目。我放了一个精简的解析器工作示例 here .
#include <boost/config/warning_disable.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <boost/spirit/include/phoenix_fusion.hpp>
#include <boost/spirit/include/phoenix_stl.hpp>
#include <boost/spirit/include/phoenix_object.hpp>
#include <boost/spirit/include/support_istream_iterator.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/fusion/include/io.hpp>
#include <fstream>
#include <iostream>
#include <string>
using std::string;
using std::vector;
using std::cout;
using std::endl;
namespace model
{
namespace qi = boost::spirit::qi;
struct spectrum
{
string comment;
string file;
string nativeId;
double precursorMz;
int precursorCharge;
double precursorIntensity;
};
struct cluster
{
string id;
vector<spectrum> spectra;
};
struct clustering
{
string name;
vector<cluster> clusters;
};
}
// Tell fusion about the data structures to make them first-class fusion citizens.
// Must be at global scope.
BOOST_FUSION_ADAPT_STRUCT(
model::spectrum,
(string, comment)
(string, file)
(string, nativeId)
(double, precursorMz)
(int, precursorCharge)
(double, precursorIntensity)
)
BOOST_FUSION_ADAPT_STRUCT(
model::cluster,
(string, id)
(std::vector<model::spectrum>, spectra)
)
BOOST_FUSION_ADAPT_STRUCT(
model::clustering,
(string, name)
(std::vector<model::cluster>, clusters)
)
namespace {
struct ReportError
{
template<typename, typename, typename, typename> struct result { typedef void type; };
// contract the string to the surrounding new-line characters
template<typename Iter>
void operator()(Iter first_iter, Iter last_iter,
Iter error_iter, const boost::spirit::qi::info& what) const
{
std::string first(first_iter, error_iter);
std::string last(error_iter, last_iter);
auto first_pos = first.rfind('\n');
auto last_pos = last.find('\n');
auto error_line = ((first_pos == std::string::npos) ? first
: std::string(first, first_pos + 1))
+ std::string(last, 0, last_pos);
//auto error_pos = (error_iter - first_iter) + 1;
/*auto error_pos = error
if (first_pos != std::string::npos)
error_pos -= (first_pos + 1);*/
std::cerr << "Error parsing in " << what << std::endl
<< error_line << std::endl
//<< std::setw(error_pos) << '^'
<< std::endl;
}
};
const boost::phoenix::function<ReportError> report_error = ReportError();
}
namespace model
{
template <typename Iterator>
struct cluster_parser : qi::grammar<Iterator, clustering(), qi::blank_type>
{
cluster_parser() : cluster_parser::base_type(clusters)
{
using qi::int_;
using qi::lit;
using qi::double_;
using qi::bool_;
using qi::lexeme;
using qi::eol;
using qi::ascii::char_;
using qi::on_error;
using qi::fail;
using namespace qi::labels;
using boost::phoenix::construct;
using boost::phoenix::val;
quoted_string %= lexeme['"' > +(char_ - '"') > '"'];
spectrum_start %=
lit("SPEC") >
"#" > +(char_ - "File:") >
"File:" > quoted_string > lit(",") >
"NativeID:" > quoted_string >
bool_ > double_ > int_ > double_;
cluster_start %=
"=Cluster=" > eol >
"id=" > +(char_ - eol) > eol >
spectrum_start % eol;
clusters %=
"name=" > +(char_ - eol) > eol >
eol >
cluster_start % eol;
BOOST_SPIRIT_DEBUG_NODES((clusters)(cluster_start)(quoted_string)(spectrum_start))
//on_error<fail>(clusters, report_error(_1, _2, _3, _4));
//on_error<fail>(cluster_start, report_error(_1, _2, _3, _4));
//on_error<fail>(spectrum_start, report_error(_1, _2, _3, _4));
//on_error<fail>(quoted_string, report_error(_1, _2, _3, _4));
// on_success(cluster_start, quantify_cluster(_1, _2, _3, _4)); ??
}
qi::rule<Iterator, std::string(), qi::blank_type> quoted_string;
qi::rule<Iterator, cluster(), qi::blank_type> cluster_start;
qi::rule<Iterator, spectrum(), qi::blank_type> spectrum_start;
qi::rule<Iterator, clustering(), qi::blank_type> clusters;
};
}
int main()
{
using namespace model;
cluster_parser<boost::spirit::istream_iterator> g; // Our grammar
string str;
//std::ifstream input("c:/test/Mo_tai.clustering");
std::istringstream input("name=GreedyClustering_0.99\n"
"\n"
"=Cluster=\n"
"id=9c8c5830-5841-4f77-b819-64180509615b\n"
"SPEC\t#file=w:\\test\\Mo_Tai_iTRAQ_f4.mgf#id=index=219#title=Mo_Tai_iTRAQ_f4.1254.1254.2 File:\"Mo_Tai_iTRAQ_f4.raw\", NativeID:\"controllerType=0 controllerNumber=1 scan=1254\"\ttrue\t\t300.1374\t2\t\t\t0.0\n"
"=Cluster=\n"
"id=f8f384a1-3d5f-4af1-9581-4d03a5aa3342\n"
"SPEC\t#file=w:\\test\\Mo_Tai_iTRAQ_f9.mgf#id=index=560#title=Mo_Tai_iTRAQ_f9.1666.1666.3 File:\"Mo_Tai_iTRAQ_f9.raw\", NativeID:\"controllerType=0 controllerNumber=1 scan=1666\"\ttrue\t\t300.14413\t3\t\t\t0.0\n"
"SPEC\t#file=w:\\test\\Mo_Tai_iTRAQ_f9.mgf#id=index=520#title=Mo_Tai_iTRAQ_f9.1621.1621.3 File:\"Mo_Tai_iTRAQ_f9.raw\", NativeID:\"controllerType=0 controllerNumber=1 scan=1621\"\ttrue\t\t300.14197\t3\t\t\t0.0\n"
"=Cluster=\n"
"id=b84b79e1-44bc-44c0-a9af-5391ca02582d\n"
"SPEC\t#file=w:\\test\\Mo_Tai_iTRAQ_f2.mgf#id=index=7171#title=Mo_Tai_iTRAQ_f2.12729.12729.2 File:\"Mo_Tai_iTRAQ_f2.raw\", NativeID:\"controllerType=0 controllerNumber=1 scan=12729\"\ttrue\t\t300.15695\t2\t\t\t0.0");
input.unsetf(std::ios::skipws);
boost::spirit::istream_iterator begin(input);
boost::spirit::istream_iterator end;
clustering clusteringResults;
bool r = phrase_parse(begin, end, g, qi::blank, clusteringResults);
if (r && begin == end)
{
cout << "Parsing succeeded (" << clusteringResults.clusters.size() << " clusters)\n";
/*for (size_t i = 0; i < std::min((size_t)10, clusteringResults.clusters.size()); ++i)
{
cluster& c = clusteringResults.clusters[i];
cout << "Cluster " << c.id << " - avg. precursor m/z: " << c.avgPrecursorMz << ", num. spectra: " << c.spectra.size() << endl;
}*/
return 1;
}
else
{
std::cout << "Parsing failed (" << clusteringResults.clusters.size() << " clusters)\n";
if (!clusteringResults.clusters.empty())
{
cluster& c = clusteringResults.clusters.back();
cout << "Last cluster parsed " << c.id << ", num. spectra: " << c.spectra.size() << endl;
}
return 1;
}
}
我不想在处理之前将整个文件解析到内存中。如何让它在每个簇解析完后排队一个条目(簇)进行处理，处理完删除簇，然后继续解析？更好的方法是让另一个线程异步处理处理。
最佳答案
只需使用流式迭代器。
或者对内存映射文件进行操作。
在处理端，将 Action 从语义 Action 内部推送到队列。
Note: you could run into a supposed bug that doesn't clear the backtrack buffers properly; You might want to check this and take preventative measures as described in this answer: Boost spirit memory leak using
flush_multi_pass
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/fusion/include/io.hpp>
namespace model
{
namespace qi = boost::spirit::qi;
namespace px = boost::phoenix;
struct spectrum {
std::string comment;
std::string file;
std::string nativeId;
double precursorMz;
int precursorCharge;
double precursorIntensity;
};
struct cluster {
std::string id;
std::vector<spectrum> spectra;
};
}
BOOST_FUSION_ADAPT_STRUCT(model::spectrum, comment, file, nativeId, precursorMz, precursorCharge, precursorIntensity)
BOOST_FUSION_ADAPT_STRUCT(model::cluster, id, spectra)
namespace model
{
template <typename Iterator>
struct cluster_parser : qi::grammar<Iterator>
{
cluster_parser(std::function<void(std::string const&, model::cluster const&)> handler)
: cluster_parser::base_type(start),
submit_(handler)
{
using namespace qi;
quoted_string %= lexeme['"' > +(char_ - '"') > '"'];
spectrum_start %=
lit("SPEC") >
"#" > +(char_ - "File:") >
"File:" > quoted_string > lit(",") >
"NativeID:" > quoted_string >
bool_ > double_ > int_ > double_;
cluster_start %=
"=Cluster=" > eol >
"id=" > +(char_ - eol) > eol >
spectrum_start % eol;
clusters %=
"name=" > qi::as_string[ +(char_ - eol) ][ name_ = _1 ] > eol > eol >
cluster_start [ submit_(name_, _1) ] % eol;
start = skip(blank) [clusters];
BOOST_SPIRIT_DEBUG_NODES((start)(clusters)(cluster_start)(quoted_string)(spectrum_start))
}
private:
qi::_a_type name_;
px::function<std::function<void(std::string const&, model::cluster const&)> > submit_;
qi::rule<Iterator, std::string(), qi::blank_type> quoted_string;
qi::rule<Iterator, cluster(), qi::blank_type> cluster_start;
qi::rule<Iterator, spectrum(), qi::blank_type> spectrum_start;
qi::rule<Iterator, qi::locals<std::string>, qi::blank_type> clusters;
qi::rule<Iterator> start;
};
}
int main()
{
using namespace model;
cluster_parser<boost::spirit::istream_iterator> g([&](auto const&...){std::cout << "handled\n";}); // Our grammar
std::string str;
//std::ifstream input("c:/test/Mo_tai.clustering");
std::istringstream input(R"(name=GreedyClustering_0.99
=Cluster=
id=9c8c5830-5841-4f77-b819-64180509615b
SPEC #file=w:\test\Mo_Tai_iTRAQ_f4.mgf#id=index=219#title=Mo_Tai_iTRAQ_f4.1254.1254.2 File:"Mo_Tai_iTRAQ_f4.raw", NativeID:"controllerType=0 controllerNumber=1 scan=1254" true 300.1374 2 0.0
=Cluster=
id=f8f384a1-3d5f-4af1-9581-4d03a5aa3342
SPEC #file=w:\test\Mo_Tai_iTRAQ_f9.mgf#id=index=560#title=Mo_Tai_iTRAQ_f9.1666.1666.3 File:"Mo_Tai_iTRAQ_f9.raw", NativeID:"controllerType=0 controllerNumber=1 scan=1666" true 300.14413 3 0.0
SPEC #file=w:\test\Mo_Tai_iTRAQ_f9.mgf#id=index=520#title=Mo_Tai_iTRAQ_f9.1621.1621.3 File:"Mo_Tai_iTRAQ_f9.raw", NativeID:"controllerType=0 controllerNumber=1 scan=1621" true 300.14197 3 0.0
=Cluster=
id=b84b79e1-44bc-44c0-a9af-5391ca02582d
SPEC #file=w:\test\Mo_Tai_iTRAQ_f2.mgf#id=index=7171#title=Mo_Tai_iTRAQ_f2.12729.12729.2 File:"Mo_Tai_iTRAQ_f2.raw", NativeID:"controllerType=0 controllerNumber=1 scan=12729" true 300.15695 2 0.0)");
input.unsetf(std::ios::skipws);
boost::spirit::istream_iterator begin(input);
boost::spirit::istream_iterator end;
bool r = phrase_parse(begin, end, g, qi::blank);
if (r && begin == end) {
std::cout << "Parsing succeeded\n";
}
else {
std::cout << "Parsing failed\n";
}
if (begin!=end) {
std::cout << "Unparsed remaining input: '" << std::string(begin, end) << "\n";
}
return (r && begin==end)? 0 : 1;
}
打印
handled
handled
handled
Parsing succeeded
这是一个在线程池上调度集群以进行异步处理的版本。
Note that the submit method posts a lambda to the service. The lambda captures by value because the lifetime of the parameters should extend during the processing.
#include <boost/asio.hpp>
#include <boost/thread.hpp>
namespace ba = boost::asio;
struct Processing {
Processing() {
for (unsigned i=0; i < boost::thread::hardware_concurrency(); ++i)
_threads.create_thread([this] { _svc.run(); });
}
~Processing() {
_work.reset();
_threads.join_all();
}
void submit(std::string const& name, model::cluster const& cluster) {
_svc.post([=] { do_processing(name, cluster); });
}
private:
void do_processing(std::string const& name, model::cluster const& cluster) {
std::cout << "Thread " << boost::this_thread::get_id() << ": " << name << " cluster of " << cluster.spectra.size() << " spectra\n";
boost::this_thread::sleep_for(boost::chrono::milliseconds(950));
}
ba::io_service _svc;
boost::optional<ba::io_service::work> _work = ba::io_service::work(_svc);
boost::thread_group _threads;
};
[...snip...] 和主要内容:
Processing processing;
auto handler = [&processing](auto&... args) { processing.submit(args...); };
cluster_parser<boost::spirit::istream_iterator> g(handler); // Our grammar
其余未修改，现在打印(例如):
Thread 7f0144a5b700: GreedyClustering_0.99 cluster of 1 spectra
Thread 7f014425a700: GreedyClustering_0.99 cluster of 2 spectra
Parsing succeeded
Thread 7f0143a59700: GreedyClustering_0.99 cluster of 1 spectra
关于c++ - 如何使用 Boost.Spirit.Qi 增量解析(并作用于)大文件？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/41748596/
我正在学习如何使用Nokogiri，根据这段代码我遇到了一些问题:require'rubygems'require'mechanize'post_agent=WWW::Mechanize.newpost_page=post_agent.get('http://www.vbulletin.org/forum/showthread.php?t=230708')puts"\nabsolutepathwithtbodygivesnil"putspost_page.parser.xpath('/html/body/div/div/div/div/div/table/tbody/tr/td/div
总的来说，我对ruby还比较陌生，我正在为我正在创建的对象编写一些rspec测试用例。许多测试用例都非常基础，我只是想确保正确填充和返回值。我想知道是否有办法使用循环结构来执行此操作。不必为我要测试的每个方法都设置一个assertEquals。例如:describeitem,"TestingtheItem"doit"willhaveanullvaluetostart"doitem=Item.new#HereIcoulddotheitem.name.shouldbe_nil#thenIcoulddoitem.category.shouldbe_nilendend但我想要一些方法来使用
我有一个Ruby程序，它使用rubyzip压缩XML文件的目录树。gem。我的问题是文件开始变得很重，我想提高压缩级别，因为压缩时间不是问题。我在rubyzipdocumentation中找不到一种为创建的ZIP文件指定压缩级别的方法。有人知道如何更改此设置吗？是否有另一个允许指定压缩级别的Ruby库？ 最佳答案 这是我通过查看rubyzip内部创建的代码。level=Zlib::BEST_COMPRESSIONZip::ZipOutputStream.open(zip_file)do|zip|Dir.glob("**/*")d
类classAprivatedeffooputs:fooendpublicdefbarputs:barendprivatedefzimputs:zimendprotecteddefdibputs:dibendendA的实例a=A.new测试a.foorescueputs:faila.barrescueputs:faila.zimrescueputs:faila.dibrescueputs:faila.gazrescueputs:fail测试输出failbarfailfailfail.发送测试[:foo,:bar,:zim,:dib,:gaz].each{|m|a.send(m)resc
很好奇，就使用rubyonrails自动化单元测试而言，你们正在做什么？您是否创建了一个脚本来在cron中运行rake作业并将结果邮寄给您？git中的预提交Hook？只是手动调用？我完全理解测试，但想知道在错误发生之前捕获错误的最佳实践是什么。让我们理所当然地认为测试本身是完美无缺的，并且可以正常工作。下一步是什么以确保他们在正确的时间将可能有害的结果传达给您？ 最佳答案 不确定您到底想听什么，但是有几个级别的自动代码库控制:在处理某项功能时，您可以使用类似autotest的内容获得关于哪些有效，哪些无效的即时反馈。要确保您的提
假设我做了一个模块如下:m=Module.newdoclassCendend三个问题:除了对m的引用之外，还有什么方法可以访问C和m中的其他内容？我可以在创建匿名模块后为其命名吗(就像我输入“module...”一样)？如何在使用完匿名模块后将其删除，使其定义的常量不再存在？ 最佳答案 三个答案:是的，使用ObjectSpace.此代码使c引用你的类(class)C不引用m:c=nilObjectSpace.each_object{|obj|c=objif(Class===objandobj.name=~/::C$/)}当然这取决于
我试图在一个项目中使用rake，如果我把所有东西都放到Rakefile中，它会很大并且很难读取/找到东西，所以我试着将每个命名空间放在lib/rake中它自己的文件中，我添加了这个到我的rake文件的顶部:Dir['#{File.dirname(__FILE__)}/lib/rake/*.rake'].map{|f|requiref}它加载文件没问题，但没有任务。我现在只有一个.rake文件作为测试，名为“servers.rake”，它看起来像这样:namespace:serverdotask:testdoputs"test"endend所以当我运行rakeserver:testid时
我的目标是转换表单输入，例如“100兆字节”或“1GB”，并将其转换为我可以存储在数据库中的文件大小(以千字节为单位)。目前，我有这个:defquota_convert@regex=/([0-9]+)(.*)s/@sizes=%w{kilobytemegabytegigabyte}m=self.quota.match(@regex)if@sizes.include?m[2]eval("self.quota=#{m[1]}.#{m[2]}")endend这有效，但前提是输入是倍数(“gigabytes”，而不是“gigabyte”)并且由于使用了eval看起来疯狂不安全。所以，功能正常，
我正在尝试使用ruby和Savon来使用网络服务。测试服务为http://www.webservicex.net/WS/WSDetails.aspx?WSID=9&CATID=2require'rubygems'require'savon'client=Savon::Client.new"http://www.webservicex.net/stockquote.asmx?WSDL"client.get_quotedo|soap|soap.body={:symbol=>"AAPL"}end返回SOAP异常。检查soap信封，在我看来soap请求没有正确的命名空间。任何人都可以建议我
关闭。这个问题是opinion-based.它目前不接受答案。想要改进这个问题？更新问题，以便editingthispost可以用事实和引用来回答它.关闭4年前。Improvethisquestion我想在固定时间创建一系列低音和高音调的哔哔声。例如:在150毫秒时发出高音调的蜂鸣声在151毫秒时发出低音调的蜂鸣声200毫秒时发出低音调的蜂鸣声250毫秒的高音调蜂鸣声有没有办法在Ruby或Python中做到这一点？我真的不在乎输出编码是什么(.wav、.mp3、.ogg等等)，但我确实想创建一个输出文件。