ahocorasick: improve matching with subdomains (#2331)

The basic idea is to have the following logic:
* pattern "DOMAIN" matches the domain itself (i.e exact match) *and* any
subdomains (i.e. "ANYTHING.DOMAIN")
* pattern "DOMAIN." matches *also* any strings for which is a prefix
[please, note that this kind of match is handy but it is quite
dangerous...]
* pattern "-DOMAIN" matches *also* any strings for which is a postfix

Examples:
* pattern "wikipedia.it":
  * "wikipiedia.it" -> OK
  * "foo.wikipedia.it -> OK
  * "foowikipedia.it -> NO MATCH
  * "wikipedia.it.com -> NO MATCH
* pattern "wikipedia.":
  * "wikipedia.it" -> OK
  * "foo.wikipedia.it -> OK
  * "foowikipedia.it -> NO MATCH
  * "wikipedia.it.com -> OK
* pattern "-wikipedia.it":
  * "wikipedia.it" -> NO MATCH
  * "foo.wikipedia.it -> NO MATCH
  * "0001-wikipedia.it -> OK
  * "foo.0001-wikipedia.it -> OK

Bottom line:
* exact match
* prefix with "." (always, implicit)
* prefix with "-" (only if esplicitly set)
* postfix with "." (only if esplicitly set)

That means that the patterns cannot start with '.' anymore.

Close #2330

1 files changed, 43 insertions, 0 deletions

diff --git a/example/ndpiReader.c b/example/ndpiReader.c
index 361cc36a7..ef5307934 100644
--- a/example/ndpiReader.c
+++ b/example/ndpiReader.c
@@ -5005,6 +5005,48 @@ void automataUnitTest() {
   ndpi_free_automa(automa);
 }
 
+/* *********************************************** */
+
+void automataDomainsUnitTest() {
+  void *automa = ndpi_init_automa_domain();
+
+  assert(automa);
+  assert(ndpi_add_string_to_automa(automa, ndpi_strdup("wikipedia.it")) == 0);
+  ndpi_finalize_automa(automa);
+  assert(ndpi_match_string(automa, "wikipedia.it") == 1);
+  assert(ndpi_match_string(automa, "foo.wikipedia.it") == 1);
+  assert(ndpi_match_string(automa, "foowikipedia.it") == 0);
+  assert(ndpi_match_string(automa, "foowikipedia") == 0);
+  assert(ndpi_match_string(automa, "-wikipedia.it") == 0);
+  assert(ndpi_match_string(automa, "foo-wikipedia.it") == 0);
+  assert(ndpi_match_string(automa, "wikipedia.it.com") == 0);
+  ndpi_free_automa(automa);
+
+  automa = ndpi_init_automa_domain();
+  assert(automa);
+  assert(ndpi_add_string_to_automa(automa, ndpi_strdup("wikipedia.")) == 0);
+  ndpi_finalize_automa(automa);
+  assert(ndpi_match_string(automa, "wikipedia.it") == 1);
+  assert(ndpi_match_string(automa, "foo.wikipedia.it") == 1);
+  assert(ndpi_match_string(automa, "foowikipedia.it") == 0);
+  assert(ndpi_match_string(automa, "foowikipedia") == 0);
+  assert(ndpi_match_string(automa, "-wikipedia.it") == 0);
+  assert(ndpi_match_string(automa, "foo-wikipedia.it") == 0);
+  assert(ndpi_match_string(automa, "wikipediafoo") == 0);
+  assert(ndpi_match_string(automa, "wikipedia.it.com") == 1);
+  ndpi_free_automa(automa);
+
+  automa = ndpi_init_automa_domain();
+  assert(automa);
+  assert(ndpi_add_string_to_automa(automa, ndpi_strdup("-buy.itunes.apple.com")) == 0);
+  ndpi_finalize_automa(automa);
+  assert(ndpi_match_string(automa, "buy.itunes.apple.com") == 0);
+  assert(ndpi_match_string(automa, "p53-buy.itunes.apple.com") == 1);
+  assert(ndpi_match_string(automa, "p53buy.itunes.apple.com") == 0);
+  assert(ndpi_match_string(automa, "foo.p53-buy.itunes.apple.com") == 1);
+  ndpi_free_automa(automa);
+}
+
 #endif
 
 /* *********************************************** */
@@ -5927,6 +5969,7 @@ int main(int argc, char **argv) {
     bitmapUnitTest();
     filterUnitTest();
     automataUnitTest();
+    automataDomainsUnitTest();
     analyzeUnitTest();
     ndpi_self_check_host_match(stderr);
     analysisUnitTest();