47 # include <winsock2.h>
56 const std::string S_ToolName =
"urldbsample";
57 const std::string S_ToolVersion =
"1.3";
64 "<dca-redist-folder> <ticket> <product> <url-list-file>\n"
65 " dca-redist-folder - the folder where the DCA is installed to\n"
66 " ticket - a valid ticket\n"
67 " product - the product associated with your ticket\n"
68 " url-list-file - file that includes the URLs to classify\n\n"
76 # define DCA_BINDIR "bin/Win32"
78 # define DCA_BINDIR "bin/linux"
85 #define DCA_INITDIR "init"
90 #define DCA_LOGDIR "./logs"
118 static bool StartupLibraries()
123 WORD wVersionRequested = MAKEWORD( 2, 2 );
125 int err = WSAStartup( wVersionRequested, &wsaData );
127 std::cout <<
"Error on WSAStartup (" << err <<
") occured, aborting" <<
145 static void ShutdownLibraries()
164 static void SetupLicense(
const std::string& ticket,
const std::string& product,
167 licenseData.
ticket = ticket;
192 struct tm *expirationTime = localtime( &expirationDate );
194 std::cout <<
"License Info:" << std::endl;
195 std::cout <<
" DCA is " << ( aLicense.
isLicensed() ?
"licensed." :
196 "not licensed." ) << std::endl;
197 std::cout <<
" MaxUsers:" << aLicense.
getMaxUsers() <<
201 std::cout <<
" Ticket:" << aLicense.
getTicket() <<
203 std::cout <<
" Session:" << aLicense.
getSession() <<
207 std::cout <<
" Expiration Date:" << asctime( expirationTime ) <<
217 static void PrintDbConnectionInfo(
const DbConnection& aDbConnection )
222 std::cout <<
"URL Database Version: " << databaseInformation.
versionString
238 if( numOfCats == 0 ) {
239 std::cout <<
"No categories found." << std::endl;
247 const Category myCategory = myCategories.
byId( result );
248 const std::string catname = myCategory.
name(
"en_US" );
251 std::cout << (i+1) <<
".\t Category '" << catname <<
252 "' (id=" << myCategory.
id() <<
253 ", groupid=" << myCategory.
groupId() <<
265 std::cout <<
"IBM DCA Sample: " << S_ToolName <<
" (" << S_ToolVersion <<
")" << std::endl;
275 std::cout << name <<
" usage:" << std::endl;
285 static void LoadUrlFile(
const std::string& fileName, std::vector<std::string>& urlList )
287 std::ifstream fstream( fileName.c_str(), std::ios::in );
288 if (!fstream.is_open())
return;
292 while ( std::getline(fstream, line) )
294 if( !line.empty() && line[line.length()-1] ==
'\r')
295 line.erase( line.length() - 1 );
298 urlList.push_back( line );
320 void TestUrlClassification(
const std::string& aUrlListFile,
const DcaInstance& myDca,
323 std::cout <<
"Starting URL db classification routine..." << std::endl;
327 std::vector<std::string> myUrlList;
328 LoadUrlFile( aUrlListFile, myUrlList );
330 for( std::vector<std::string>::const_iterator U = myUrlList.begin(),
331 UEnd = myUrlList.end(); U != UEnd; ++U ) {
333 const std::string& myUrlString = *U;
335 std::cout <<
" Starting URL db classification for URL '" <<
336 myUrlString <<
"'" << std::endl;
347 std::cerr <<
"Invalid URL. ";
350 std::cerr <<
"Unsupported URL protocol. ";
353 std::cerr <<
"Error from URL db classification. Details: " << myFR.
getDescription() <<
356 std::cerr <<
"Continuing with next URL." << std::endl;
362 std::cout <<
"Results: URL '" << myUrlString <<
"' is not known in the database. " <<
363 "Continuing with next URL." << std::endl;
370 std::cout <<
"Results: URL '" << myUrlString <<
"' is not categorized (but known in the database). "
371 <<
"Continuing with next URL" << std::endl;
376 std::cout <<
"Classification Results for URL '" << myUrlString <<
"'" << std::endl;
377 PrintResults( myCategoriesInfo, myUrlClassificationResults );
379 std::cout <<
"Leaving URL db classification routine." << std::endl;
389 int main(
int argc,
char *argv[] )
401 std::string myRedistFolder = argv[ 1 ];
402 const std::string myTicket = argv[ 2 ];
403 const std::string myProduct = argv[ 3 ];
404 const std::string myUrlList = argv[ 4 ];
406 if( myRedistFolder.empty() || myTicket.empty() ||
407 myProduct.empty() || myUrlList.empty() ) {
413 const char c = myRedistFolder[ myRedistFolder.length() - 1 ];
414 if( c !=
'/' && c !=
'\\' )
415 myRedistFolder +=
"/";
418 if( !StartupLibraries() )
440 SetupConnectionData( myDbConnectionData );
442 PrintDbConnectionInfo( myDbConnection );
459 TestUrlClassification( myUrlList, myDca, myUrlDbClassifier, myCategoriesInfo );
465 catch(
const ExDca& ex ) {
466 std::cerr <<
"DCA Exception occured. Details: " << ex.
getDescription() <<
470 catch(
const std::exception& s ) {
471 std::cerr <<
"std::exception occured. Details: " << s.what() <<
"." << std::endl;
475 std::cerr <<
"Unknown exception caught." << std::endl;
static DCA_MODULE_ID_TYPE ID
The unique ID of the URL classification module.
Is used to create a License object. A license first must be created with DcaInstance::createLicense t...
Exception class used in the DCA.
bool isCategorized() const
Returns whether or not the URL matched one or more categories.
static Url create(const DcaInstance &aDcaInstance, const std::string &urlString)
Standard Url creation function.
const DCA_CATEGORIES_INFO_TYPE DCA_CAT_INFO_TYPE_URL
Refers to the internal categories info for URL classification.
void InitCUrl()
Initializes libcurl. Do not use any DCA function before initializing libcurl.
std::string initDir
the directory in which the DCA init files are stored
int getMaxSessions() const
Returns the maximum allowed sessions associated with your ticket/license.
time_t getExpirationDate() const
Returns the expiration date of the license in UTC.
std::string getDescription() const
Returns a description of the error.
Definition of a container class for Category objects.
CategoriesInfo getCategoriesInfo(DCA_CATEGORIES_INFO_TYPE categoryType) const
Returns the DCA internal categories, groups and locales.
DatabaseInformation getDatabaseInformation() const
Returns information about the underlying database.
DCA_RESULT_TYPE getReturnCode() const
Returns the last error code (if any).
FunctionResult classify(const Url &aUrl, UrlClassificationResults &urlResults) const
Performs the URL classification and returns the results.
static void SetupInitData(const std::string &redist_folder, InitData &initData)
Sets up the given initData by substituting the given redist_folder with DCA subdirectories.
std::string binDir
the directory in which the DCA binary (*.dca) files are stored
This header includes initialization/deinitialization support functions for the 3rd party libraries us...
A container class that allows access to the contained Categories, Groups and Locales.
Sets up options for embedded URL detection and provided Feedback mechanism.
void SetOpenSslCallbacks()
Initializes the required callbacks for OpenSSL when using HTTPS or SSL connections in a multi-threade...
Stores the connection data for a database.
void UnsetOpenSslCallbacks()
Unsets the openssl callbacks. Do not call any DCA function after you have called this function.
DCA_CATEGORY_ID_TYPE id() const
The category id.
int getMaxUsers() const
Returns the maximum allowed users associated with your ticket/license.
void DeinitCUrl()
Deinitializes libcurl. Do not call any DCA function after you have called this function.
bool isUnknownUrl() const
Returns whether a URL is known or unknown. A URL is unknown if it is not contained in the database.
Database connection class for a local or remote database.
This header includes all header files of the URL Classification Package.
#define DCA_LOGDIR
Relative directory for logfile(s).
Main class for the URL classification.
#define DCA_INITDIR
DCA subdirectory of the DCA initialization data.
bool enable_Feedback
This switches the Feedback feature on or off. This is switched off by default.
DCA_RESULT_TYPE getReturnCode() const
Gets the code of the error.
DCA_CATEGORY_ID_TYPE UrlClassificationResult
The item of an URL classification result is typedef'd as DCA_CATEGORY_ID_TYPE.
const int ERR_URL_INVALID
Error code: The URL is invalid.
Results of an URL classification.
bool detect_EmbeddedUrlsInUrlPath
If set to true, you can specify that embedded URL detection is additionally performed in the path par...
URL database classifier class.
static void PrintToolHeader()
Prints out the name and the version of this sample.
Use a License to initialize a classification package or a toolbox package.
Category byId(DCA_CATEGORY_ID_TYPE id) const
Returns the category with the given category id.
bool isLicensed(DCA_MODULE_ID_TYPE id=0, bool force=false) const
Checks whether the given License is valid for the given module id.
static void PrintLicenseInfo(const License &aLicense)
Prints out the information about the provided License.
std::string ticket
The ticket as provided in the license.
This header includes all header files of the DCA Base Package.
bool useLocalDatabase
Set to true to connect to a local or custom database, set to false to use a remote database.
Encapsulates the init and deinit of the DCA API.
Category NullCategory
Defines a constant unassigned Category you can use for checks. if( myCat == NullCategory ) --> myCat ...
std::string product
The product code used with the license.
const DbType DBT_Url
Used for DbConnection classes for URL classification.
static UrlClassification create(const DcaInstance &aDcaInstance, const License &aLicense)
Creates the URL classification module by using the given DcaInstance and License.
std::string logDir
the directory in which the DCA log file should be created
const int ERR_URL_UNSUPPORTED_PROTOCOL
Error code: The protocol of the URL is unsupported.
static void PrintUsage(const char *name)
Prints out the syntax of the sample.
std::string getLastMessage() const
Returns the last message received from our license server or if none available the last available mes...
size_t DCA_INDEX_TYPE
Type for index access (used for arrays and collections).
DbType dbType
The type of the database.
Categories getCategories() const
Returns the contained Categories.
std::string getDescription() const
Returns the description for the error or warning.
size_t DCA_SIZE_TYPE
Type for size (used for size of array and collections).
std::string name(const std::string &localeString=std::string()) const
Returns the localized (display) name of the category.
std::string getTicket() const
Returns the ticket of the license as string.
DCA_GROUP_ID_TYPE groupId() const
If the category is associated with a group, this is the group id.
bool enable_EmbeddedUrlDetection
If set to true embedded URL detection will be used in URL classification. This is switched on by defa...
#define DCA_BINDIR
DCA subdirectory of the DCA binaries.
Standard function result.
std::string getSession() const
Returns the session of the license as string.
Encapsulates a URL object.
UrlDbClassifier createDbClassifier(const DbConnection &aDbConnection, const UrlDbClassifierOptions &options=UrlDbClassifierOptions()) const
Create a URL database classifier. The classifier is created by using the provided database connection...
const std::string S_UsageString
Usage string, displayed if a parameter is missing.
DbConnection createDbConnection(const License &aLicense, const DbConnectionData &dbcData, const ProxySettings &proxySettings=ProxySettings(), LogLevel aLogLevel=LOG_Initial) const
Creates a DbConnection object using the given DbConnectionData.
This structure is used to initialize the DcaInstance.
Encapsulates a category as defined in the categories XML schema (see Categories XML: Categories).
static DcaInstance create(const InitData &initData)
Creates a DcaInstance, starts up the DCA API and initializes the required main module.
static void SetupLicense(const std::string &ticket, const std::string &product, LicenseData &licenseData)
Sets up the given licenseData by copying the given ticket and product strings.
License createLicense(const LicenseData &licData, const ProxySettings &proxySettings=ProxySettings(), LogLevel aLogLevel=LOG_Initial) const
Creates a License object using the given LicenseData.
DCA_SIZE_TYPE size() const
Returns the number of results in the container.
int main(int argc, char *argv[])
The main routine.