summaryrefslogtreecommitdiff
path: root/tests/url
diff options
context:
space:
mode:
authorAndreas Baumann <abaumann@yahoo.com>2012-08-10 17:05:24 +0200
committerAndreas Baumann <abaumann@yahoo.com>2012-08-10 17:05:24 +0200
commit540a8d30ffeac5d6214b2c7bc6354e01d3f403d7 (patch)
tree199e2a1154e5b2ea2e6354db7324eb7d93070a87 /tests/url
parent3763777e7811b7efdae57d747f02f51fe4706fc4 (diff)
downloadcrawler-540a8d30ffeac5d6214b2c7bc6354e01d3f403d7.tar.gz
crawler-540a8d30ffeac5d6214b2c7bc6354e01d3f403d7.tar.bz2
module loader works on Windows, simple URL normalizer test works
Diffstat (limited to 'tests/url')
-rwxr-xr-xtests/url/Makefile.W3216
-rwxr-xr-x[-rw-r--r--]tests/url/test1.cpp113
2 files changed, 68 insertions, 61 deletions
diff --git a/tests/url/Makefile.W32 b/tests/url/Makefile.W32
index c2d74e7..573f636 100755
--- a/tests/url/Makefile.W32
+++ b/tests/url/Makefile.W32
@@ -5,26 +5,28 @@ SUBDIRS =
!INCLUDE $(TOPDIR)\makefiles\nmake\platform.mk
INCLUDE_CXXFLAGS = \
- /D_WIN32_WINNT=0x504
+ /D_WIN32_WINNT=0x504 \
+ /DUSE_MODULELOADER
INCLUDE_DIRS = \
/I. \
- /I$(TOPDIR)\src
+ /I$(TOPDIR)\src \
+ /I$(TOPDIR)\src\modules\urlnormalizer\simpleurl
INCLUDE_LDFLAGS = \
INCLUDE_LIBS = \
+ $(TOPDIR)\src\crawlingwolf.lib \
+ $(TOPDIR)\src\modules\urlnormalizer\simpleurl\simpleurlnormalizer.lib
TEST_CPP_BINS = \
- test1.exe \
- test2.exe
+ test1.exe
OBJS =
!INCLUDE $(TOPDIR)\makefiles\nmake\sub.mk
test1.exe: test1.obj
-test2.exe: test2.obj
local_all:
@@ -34,5 +36,5 @@ local_clean:
local_distclean:
local_test:
- @-exec_test test1 "TypeList and TypeTraits"
- @-exec_test test2 "TypeInfo C++ demangle"
+# @-exec_test test1 "TypeList and TypeTraits"
+# @-exec_test test2 "TypeInfo C++ demangle"
diff --git a/tests/url/test1.cpp b/tests/url/test1.cpp
index b2ee90e..095de24 100644..100755
--- a/tests/url/test1.cpp
+++ b/tests/url/test1.cpp
@@ -4,7 +4,7 @@
#include "ModuleLoader.hpp"
#else
#include "SimpleURLNormalizer.hpp"
-#include "GoogleURLNormalizer.hpp"
+//#include "GoogleURLNormalizer.hpp"
#endif
#include <vector>
@@ -16,71 +16,76 @@ using namespace std;
int main( int argc, char *argv[] )
{
- if( argc < 3 ) {
- cerr << "usage: test1 <method> <action> <baseUrl> [<relativeUrl>]\n" << endl;
- return 1;
- }
-
- char *method = argv[1];
- char *action = argv[2];
- char *baseUrlString = argv[3];
- char *partialUrlString = argv[4];
+ try {
+ if( argc < 3 ) {
+ cerr << "usage: test1 <method> <action> <baseUrl> [<relativeUrl>]\n" << endl;
+ return 1;
+ }
+
+ char *method = argv[1];
+ char *action = argv[2];
+ char *baseUrlString = argv[3];
+ char *partialUrlString = argv[4];
#ifdef USE_MODULELOADER
- vector<string> modules;
- modules.push_back( "../../src/modules/urlnormalizer/simpleurl/mod_urlnormalizer_simple.so" );
- modules.push_back( "../../src/modules/urlnormalizer/googleurl/mod_urlnormalizer_googleurl.so" );
- ModuleLoader<URLNormalizer> urlNormalizers( modules );
+ vector<string> modules;
+ // modules.push_back( "../../src/modules/urlnormalizer/simpleurl/mod_urlnormalizer_simple" MODULE_EXT );
+ modules.push_back( "..\\..\\src\\modules\\urlnormalizer\\simpleurl\\mod_urlnormalizer_simple" MODULE_EXT );
+ // modules.push_back( "../../src/modules/urlnormalizer/googleurl/mod_urlnormalizer_googleurl" MODULE_EXT );
+ ModuleLoader<URLNormalizer> urlNormalizers( modules );
- URLNormalizer *normalizer = urlNormalizers.create( method );
+ URLNormalizer *normalizer = urlNormalizers.create( method );
#else
- URLNormalizer *normalizer;
- if( strcmp( method, "simple" ) == 0 ) {
- normalizer = new SimpleURLNormalizer( );
- } else if( strcmp( method, "google" ) == 0 ) {
- normalizer = new GoogleURLNormalizer( );
- } else {
- cerr << "Unknown normalization method '" << method << "'" << endl;
- return 1;
- }
+ URLNormalizer *normalizer;
+ if( strcmp( method, "simple" ) == 0 ) {
+ normalizer = new SimpleURLNormalizer( );
+ // } else if( strcmp( method, "google" ) == 0 ) {
+ // normalizer = new GoogleURLNormalizer( );
+ } else {
+ cerr << "Unknown normalization method '" << method << "'" << endl;
+ return 1;
+ }
#endif
-
-
- URL url;
-
- if( strcmp( action, "parse" ) == 0 ) {
- url = normalizer->parseUrl( baseUrlString );
- } else if( strcmp( action, "normalize" ) == 0 ) {
- URL baseUrl = normalizer->parseUrl( baseUrlString );
- if( baseUrl == URL::Null ) {
- cerr << "Illegal base URL!" << endl;
+
+ URL url;
+
+ if( strcmp( action, "parse" ) == 0 ) {
+ url = normalizer->parseUrl( baseUrlString );
+ } else if( strcmp( action, "normalize" ) == 0 ) {
+ URL baseUrl = normalizer->parseUrl( baseUrlString );
+ if( baseUrl == URL::Null ) {
+ cerr << "Illegal base URL!" << endl;
+ return 1;
+ }
+ url = normalizer->normalize( baseUrl, partialUrlString );
+ } else {
+ cerr << "Unknown action '" << action << "'" << endl;
return 1;
}
- url = normalizer->normalize( baseUrl, partialUrlString );
- } else {
- cerr << "Unknown action '" << action << "'" << endl;
- return 1;
- }
- if( url == URL::Null ) {
- cerr << "Illegal URL!" << endl;
- return 1;
- }
-
- cout << "protocol: " << url.protocol( ) << endl
- << "host: " << url.host( ) << endl
- << "port: " << url.port( ) << endl
- << "path: " << url.path( ) << endl
- << "query: " << url.query( ) << endl
- << "fragment: " << url.fragment( ) << endl;
+ if( url == URL::Null ) {
+ cerr << "Illegal URL!" << endl;
+ return 1;
+ }
+
+ cout << "protocol: " << url.protocol( ) << endl
+ << "host: " << url.host( ) << endl
+ << "port: " << url.port( ) << endl
+ << "path: " << url.path( ) << endl
+ << "query: " << url.query( ) << endl
+ << "fragment: " << url.fragment( ) << endl;
- cout << "URL: " << url << endl;
+ cout << "URL: " << url << endl;
#ifdef USE_MODULELOADER
- urlNormalizers.destroy( normalizer );
+ urlNormalizers.destroy( normalizer );
#else
- delete normalizer;
+ delete normalizer;
#endif
- return 0;
+ return 0;
+ } catch( exception &e ) {
+ cerr << e.what( ) << endl;
+ return 1;
+ }
}