concordia-server

Former-commit-id: d6738a8d8b0c9482ef5a7416af5b732422e37dbe

concordia-server-starter/CMakeLists.txt

@@ -0,0 +1,21 @@
+
+add_executable(concordia-server-starter concordia_server_starter.cpp)
+
+target_link_libraries(concordia-server-starter concordia-server concordia ${Boost_LIBRARIES} ${FCGIPP_LIB} ${FCGI_LIB} ${LIBCONFIG_LIB})
+
+if (WITH_RE2)
+  target_link_libraries(concordia-server-starter re2)
+  if (WITH_PCRE)
+    target_link_libraries(concordia-server-starter pcrecpp)
+  endif(WITH_PCRE)
+else(WITH_RE2)
+  if (WITH_PCRE)
+    target_link_libraries(concordia-server-starter pcrecpp)
+  endif(WITH_PCRE)
+endif(WITH_RE2)
+
+# =====================================
+
+install(TARGETS concordia-server-starter DESTINATION bin/)
+
+  

concordia-server-starter/concordia_server_starter.cpp

@@ -0,0 +1,99 @@
+#include <iostream>
+#include <sstream>
+#include <string>
+#include <boost/algorithm/string/replace.hpp>
+#include <fcgio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "concordia-server/concordia_server.hpp"
+
+using namespace std;
+
+static const unsigned long STDIN_MAX = 1000000;
+
+static long gstdin(FCGX_Request * request, char ** content)
+{
+    char * clenstr = FCGX_GetParam("CONTENT_LENGTH", request->envp);
+    unsigned long clen = STDIN_MAX;
+
+    if (clenstr)
+    {
+        clen = strtol(clenstr, &clenstr, 10);
+        if (*clenstr)
+        {
+            cerr << "can't parse \"CONTENT_LENGTH="
+                 << FCGX_GetParam("CONTENT_LENGTH", request->envp)
+                 << "\"\n";
+            clen = STDIN_MAX;
+        }
+
+        // *always* put a cap on the amount of data that will be read
+        if (clen > STDIN_MAX) clen = STDIN_MAX;
+
+        *content = new char[clen];
+
+        cin.read(*content, clen);
+        clen = cin.gcount();
+    }
+    else
+    {
+        // *never* read stdin when CONTENT_LENGTH is missing or unparsable
+        *content = 0;
+        clen = 0;
+    }
+
+    // Chew up any remaining stdin - this shouldn't be necessary
+    // but is because mod_fastcgi doesn't handle it correctly.
+
+    // ignore() doesn't set the eof bit in some versions of glibc++
+    // so use gcount() instead of eof()...
+    do cin.ignore(1024); while (cin.gcount() == 1024);
+
+    return clen;
+}
+
+int main(int argc, char** argv) {
+
+    // Backup the stdio streambufs
+    streambuf * cin_streambuf  = cin.rdbuf();
+    streambuf * cout_streambuf = cout.rdbuf();
+    streambuf * cerr_streambuf = cerr.rdbuf();
+
+    ConcordiaServer concordiaServer("concordia.cfg");
+
+    FCGX_Request request;
+
+    FCGX_Init();
+    FCGX_InitRequest(&request, 0, 0);
+
+    while (FCGX_Accept_r(&request) == 0) {
+        fcgi_streambuf cin_fcgi_streambuf(request.in);
+        fcgi_streambuf cout_fcgi_streambuf(request.out);
+        fcgi_streambuf cerr_fcgi_streambuf(request.err);
+
+        cin.rdbuf(&cin_fcgi_streambuf);
+        cout.rdbuf(&cout_fcgi_streambuf);
+        cerr.rdbuf(&cerr_fcgi_streambuf);
+
+
+        char * content;
+        unsigned long clen = gstdin(&request, &content);
+        
+        string requestString(content);
+        
+        //TODO passing unicode strings
+        //boost::replace_all(requestString, "+", " ");
+        
+        cout << concordiaServer.handleRequest(requestString);
+        
+        // Note: the fcgi_streambuf destructor will auto flush
+    }
+
+    // restore stdio streambufs
+    cin.rdbuf(cin_streambuf);
+    cout.rdbuf(cout_streambuf);
+    cerr.rdbuf(cerr_streambuf);
+
+    return 0;
+}

concordia-server/CMakeLists.txt

@@ -0,0 +1,25 @@
+add_library(concordia-server SHARED
+  concordia_server.cpp
+  )
+
+add_subdirectory(t)
+# =====================================
+
+install(TARGETS concordia-server DESTINATION lib/)
+install(FILES concordia_server.hpp DESTINATION include/concordia-server/)
+
+target_link_libraries(concordia-server log4cpp)
+target_link_libraries(concordia-server ${LIBSTEMMER_LIB})
+target_link_libraries(concordia-server ${Boost_LIBRARIES})
+
+if (WITH_RE2)
+  target_link_libraries(concordia-server re2)
+  if (WITH_PCRE)
+    target_link_libraries(concordia-server pcrecpp)
+  endif(WITH_PCRE)
+else(WITH_RE2)
+  if (WITH_PCRE)
+    target_link_libraries(concordia-server pcrecpp)
+  endif(WITH_PCRE)
+endif(WITH_RE2)
+

concordia-server/TODO.txt

@@ -0,0 +1 @@
+use the echo.cpp source as an example for concordia-server-starter. It works with the up-to-date version of test.html (the one that specifies UTF-8 as character encoding in the <form>)

concordia-server/compilation.dox

@@ -0,0 +1,61 @@
+/** \page compilation Concordia Installation & Build Manual
+
+This file describes how to compile, build
+and install Concordia library.
+
+\section compilation1 Requirements
+
+- cmake
+- Boost library
+- Log4cpp
+- libstemmer (Snowball stemming library)
+- (optional) Doxygen
+
+\subsection compilation1_1 Boost Ubuntu installation
+
+sudo apt-get install libboost-dev libboost-serialization-dev libboost-test-dev libboost-filesystem-dev libboost-system-de libboost-program-options-dev libboost-iostreams-dev
+
+\subsection compilation1_2 Log4cpp Ubuntu installation
+
+sudo apt-get install liblog4cpp5-dev
+
+\subsection compilation1_3 Libconfig Ubuntu installation
+
+sudo apt-get install libconfig++-dev
+sudo apt-get install libconfig-dev
+
+\subsection compilation1_4 Libstemmer Ubuntu installation
+
+sudo apt-get install libstemmer-dev
+
+\subsection compilation1_5 Perl-compatible regular expressions (PCRE) Ubuntu installation
+
+sudo apt-get install libpcre3-dev
+
+\subsection compilation1_6 Doxygen Ubuntu installation
+
+sudo apt-get install doxygen
+
+\section compilation2 Build & installation procedure
+
+mkdir build<br/>
+cd build<br/>
+../cmake.sh<br/>
+make<br/>
+make test<br/>
+make install
+
+\section compilation3 Documentation
+
+If Doxygen is available, a successful compilation generates documentation data in three
+formats in the build/doc directory.
+
+The man files in doc/man will be installed during installation. Open doc/html/index.html for
+a HTML version of the same documentation. The latex directory contains uncompiled latex
+files. To generate a single pdf file run
+
+cd doc/latex
+make
+
+This should generate a single file called refman.pdf in the same directory.
+*/

concordia-server/concordia_server.cpp

@@ -0,0 +1,62 @@
+#include "concordia-server/concordia_server.hpp"
+
+#include <sstream>
+#include <concordia/example.hpp>
+#include <concordia/substring_occurence.hpp>
+#include <boost/ptr_container/ptr_vector.hpp>
+#include <boost/foreach.hpp>
+
+
+ConcordiaServer::ConcordiaServer(const std::string & configFilePath)
+                                         throw(ConcordiaException) {
+    _concordia = boost::shared_ptr<Concordia> (
+                            new Concordia(configFilePath));
+
+}
+
+ConcordiaServer::~ConcordiaServer() {
+}
+
+string ConcordiaServer::handleRequest(string & requestString) {
+    stringstream ss;
+    try {
+        ss << "Content-type: text/html\r\n"
+             << "\r\n"
+             << "<html>\n"
+             << "  <head>\n"
+             << "    <title>Hello, World!</title>\n"
+             << "  </head>\n"
+             << "  <body>\n"
+             << "    <h1>Hello, World!</h1>\n"
+             << "    The concordia version is: "<< _concordia->getVersion() << "\n"
+             << "    <h1>Input data:</h1>\n"
+             << requestString;
+
+        ss << "    <h1>Adding content as example:</h1>\n";
+
+        Example example1(requestString, 0);
+        Example example2("Ala ma kota", 1);
+        Example example3("Marysia nie ma kota chyba", 2);
+        _concordia->addExample(example1);
+        _concordia->addExample(example2);
+        _concordia->addExample(example3);
+
+        _concordia->refreshSAfromRAM();
+
+        ss << "    <h1>Searching ma kota:</h1>\n";
+        boost::ptr_vector<SubstringOccurence> result =
+                                 _concordia->simpleSearch("ma kota");
+        BOOST_FOREACH(SubstringOccurence occurence, result) {
+            ss << "\t\tfound match in sentence number: "
+                      << occurence.getId() << "<br/><br/>";
+        }                                 
+        ss << "  </body>\n"
+             << "</html>\n";
+             
+    } catch (ConcordiaException & e) {
+        ss << "<h1> Concordia error:" << e.what() << "</h1>";
+        
+    }
+    return ss.str();
+
+}

concordia-server/concordia_server.hpp

@@ -0,0 +1,30 @@
+#ifndef CONCORDIA_SERVER_HDR
+#define CONCORDIA_SERVER_HDR
+
+#include <string>
+#include <concordia/concordia_exception.hpp>
+#include <boost/shared_ptr.hpp>
+#include <concordia/concordia.hpp>
+
+
+using namespace std;
+
+class ConcordiaServer {
+public:
+    /*! Constructor.
+      \param configFilePath path to the Concordia configuration file
+      \throws ConcordiaException
+    */
+    explicit ConcordiaServer(const std::string & configFilePath)
+                                         throw(ConcordiaException);
+    /*! Destructor.
+    */
+    virtual ~ConcordiaServer();
+
+    string handleRequest(string & requestString);
+
+private:
+    boost::shared_ptr<Concordia> _concordia;
+};
+
+#endif

concordia-server/main.dox

@@ -0,0 +1,12 @@
+/** \mainpage Introduction
+
+\section main_1 Concordia - Tool for concordance search in CAT
+
+
+\section main_2 Overview
+
+- \subpage compilation This chapter contains instructions to compile, install and run Concordia.
+- \subpage running The methods of making use of the Concordia library are described in this chapter.
+- \subpage technical In this chapter technical information about unit tests, project resources and code style is provided.
+
+*/

concordia-server/running.dox

@@ -0,0 +1,32 @@
+/** \page running Running the Concordia library
+
+\section running1 Programmatical use of the library
+
+The main access point to the functionalities of the library is the Concordia class. An example programmatical use of the class is shown below:
+
+\verbatim
+snippet
+\endverbatim
+
+\section running2 The concordia-console program
+
+
+After successful build of the project (see \ref compilation2) the concordia-console program is available in the folder build/concordia-console.
+
+\subsection running2_1 concordia-console options
+
+The full list of program options is given below:
+
+\verbatim
+  -h [ --help ]         Display this message
+  -c [ --config ] arg   Concordia configuration file (required)
+\endverbatim
+
+\subsection running2_2 concordia-console example run
+
+\subsection running2_3 concordia-console output format
+
+
+\section running3 The Concordia configuration
+
+Concordia is configured by the means of a configuration file in the libconfig format (http://www.hyperrealm.com/libconfig/). 

concordia-server/t/CMakeLists.txt

@@ -0,0 +1,6 @@
+add_library(concordia-server-tests
+  test_concordia.cpp
+  test_concordia_config.cpp
+  )
+
+target_link_libraries(concordia-server-tests concordia ${LIBCONFIG_LIB} concordia-tests-common)

concordia-server/t/test_concordia.cpp

@@ -0,0 +1,19 @@
+#include "tests/unit-tests/unit_tests_globals.hpp"
+#include "concordia/concordia.hpp"
+#include "tests/common/test_resources_manager.hpp"
+
+
+#include <string>
+
+using namespace std;
+
+BOOST_AUTO_TEST_SUITE(concordia_main)
+
+BOOST_AUTO_TEST_CASE( ConcordiaVersion )
+{
+    Concordia concordia = Concordia(TestResourcesManager::getTestConcordiaConfigFilePath("concordia.cfg"));
+    string version = concordia.getVersion();
+    BOOST_CHECK_EQUAL( version , "0.1");
+}
+
+BOOST_AUTO_TEST_SUITE_END()

concordia-server/t/test_concordia_config.cpp

@@ -0,0 +1,52 @@
+#include "tests/unit-tests/unit_tests_globals.hpp"
+
+#include "concordia/concordia_config.hpp"
+#include "tests/common/test_resources_manager.hpp"
+
+#include <string>
+#include <list>
+#include <boost/algorithm/string/predicate.hpp>
+
+using namespace std;
+
+BOOST_AUTO_TEST_SUITE(concordia_config)
+
+BOOST_AUTO_TEST_CASE( ConfigParameters )
+{
+    ConcordiaConfig config(TestResourcesManager::getTestConcordiaConfigFilePath("concordia-test.cfg"));
+    BOOST_CHECK_EQUAL( config.getPuddleTagsetFilePath() , "puddle/tagset.txt" );
+}
+
+BOOST_AUTO_TEST_CASE( NonexistentConfigTest )
+{
+    bool exceptionThrown = false;
+    string message = "";
+    try {
+        ConcordiaConfig config(TestResourcesManager::getTestConcordiaConfigFilePath("foo.cfg")); 
+    } catch (ConcordiaException & e) {
+        exceptionThrown = true;
+        message = e.what();
+    }    
+    BOOST_CHECK_EQUAL(exceptionThrown, true);    
+    BOOST_CHECK_EQUAL(boost::starts_with(message, "I/O error reading config file"), true);    
+}
+
+
+BOOST_AUTO_TEST_CASE( InvalidConfigTest )
+{
+    bool exceptionThrown = false;
+    string message = "";
+    try {
+        ConcordiaConfig config(TestResourcesManager::getTestConcordiaConfigFilePath("invalid.cfg")); 
+    } catch (ConcordiaException & e) {
+        exceptionThrown = true;
+        message = e.what();
+    }    
+    BOOST_CHECK_EQUAL(exceptionThrown, true);    
+    BOOST_CHECK_EQUAL(boost::starts_with(message, "Error parsing config file"), true);    
+}
+
+
+
+
+BOOST_AUTO_TEST_SUITE_END()

concordia-server/technical.dox

@@ -0,0 +1,28 @@
+/** \page technical Project technical information
+
+\section technical1 Development
+
+\subsection technical1_1 Code style
+
+Use: ./run-checkers.sh script to find the most
+C++ coding errors. The script uses the following
+external tools:
+
+- cpplint.py (http://google-styleguide.googlecode.com/svn/trunk/cppguide.xml?showone=cpplint)
+- cppcheck
+
+The reports are stored in the XXX-result.txt files (where XXX is the name of the tool)
+in the current directory.
+
+\subsection technical1_2 Unit tests
+
+Unit tests are integrated into makefiles. Unit tests codes are
+put in the t/ subdirectory for each library.
+
+In order to run all unit tests just type:
+
+make test
+
+You can get detailed test report by running:
+
+./tests/unit-tests/test_runner

concordia-server/test.html

@@ -0,0 +1,7 @@
+<html>
+<body>
+<form enctype="multipart/form-data" action="http://localhost:8081" accept-charset="UTF-8" method="POST">
+    <input type="text" name="input_field" />
+</form>
+</body>
+</html>