Mirrors/privacore-open-source-search-engine
1
0
Fork 1
mirror of https://github.com/privacore/open-source-search-engine.git synced 2025-07-15 02:36:08 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add block by file for UrlMatch

Browse Source
This commit is contained in:
Ai Lin Chia
2017-09-06 12:03:25 +02:00
parent 1f7b82c384
commit 17f843c273
5 changed files with 54 additions and 11 deletions

18
UrlMatch.cpp

@ -17,6 +17,12 @@ urlmatchdomain_t::urlmatchdomain_t(const std::string &domain, const std::string
, m_pathcriteria(pathcriteria) {
}
urlmatchfile_t::urlmatchfile_t(const std::string &file)
: m_file(file) {
}
urlmatchhost_t::urlmatchhost_t(const std::string &host, const std::string &path)
: m_host(host)
, m_path(path) {
@ -42,6 +48,11 @@ UrlMatch::UrlMatch(const std::shared_ptr<urlmatchdomain_t> &urlmatchdomain)
, m_domain(urlmatchdomain) {
}
UrlMatch::UrlMatch(const std::shared_ptr<urlmatchfile_t> &urlmatchfile)
: m_type(url_match_file)
, m_file(urlmatchfile) {
}
UrlMatch::UrlMatch(const std::shared_ptr<urlmatchhost_t> &urlmatchhost)
: m_type(url_match_host)
, m_host(urlmatchhost) {
@ -84,6 +95,9 @@ bool UrlMatch::match(const Url &url) const {
return true;
}
break;
case url_match_file:
return (m_file->m_file.length() == static_cast<size_t>(url.getFilenameLen()) &&
memcmp(m_file->m_file.c_str(), url.getFilename(), url.getFilenameLen()) == 0);
case url_match_host:
if (m_host->m_host.length() == static_cast<size_t>(url.getHostLen()) &&
memcmp(m_host->m_host.c_str(), url.getHost(), url.getHostLen()) == 0) {
@ -132,6 +146,10 @@ void UrlMatch::logMatch(const Url &url) const {
type = "domain";
value = m_domain->m_domain.c_str();
break;
case url_match_file:
type = "file";
value = m_file->m_file.c_str();
break;
case url_match_host:
type = "host";
value = m_host->m_host.c_str();

9
UrlMatch.h

@ -20,6 +20,12 @@ struct urlmatchdomain_t {
pathcriteria_t m_pathcriteria;
};
struct urlmatchfile_t {
urlmatchfile_t(const std::string &file);
std::string m_file;
};
struct urlmatchhost_t {
urlmatchhost_t(const std::string &host, const std::string &path);
@ -53,6 +59,7 @@ class Url;
class UrlMatch {
public:
UrlMatch(const std::shared_ptr<urlmatchdomain_t> &urlmatchdomain);
UrlMatch(const std::shared_ptr<urlmatchfile_t> &urlmatchfile);
UrlMatch(const std::shared_ptr<urlmatchhost_t> &urlmatchhost);
UrlMatch(const std::shared_ptr<urlmatchpath_t> &urlmatchpath);
UrlMatch(const std::shared_ptr<urlmatchregex_t> &urlmatchregex);
@ -64,6 +71,7 @@ public:
private:
enum urlmatchtype_t {
url_match_domain,
url_match_file,
url_match_host,
url_match_path,
url_match_regex,
@ -73,6 +81,7 @@ private:
urlmatchtype_t m_type;
std::shared_ptr<urlmatchdomain_t> m_domain;
std::shared_ptr<urlmatchfile_t> m_file;
std::shared_ptr<urlmatchhost_t> m_host;
std::shared_ptr<urlmatchpath_t> m_path;
std::shared_ptr<urlmatchregex_t> m_regex;

29
UrlMatchList.cpp

@ -117,17 +117,26 @@ bool UrlMatchList::load() {
switch (line[0]) {
case 'd':
// domain
if (firstColEnd==5 && memcmp(line.data(), "domain", 5) != 0) {
logTrace(g_conf.m_logTraceUrlMatchList, "");
if (firstColEnd == 5 && memcmp(line.data(), "domain", 5) != 0) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
parseDomain(&tmpUrlMatchList, col2, col3, col4);
break;
case 'f':
// file
if (firstColEnd == 4 && memcmp(line.data(), "file", 4) != 0) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
tmpUrlMatchList->emplace_back(std::shared_ptr<urlmatchfile_t>(new urlmatchfile_t(col2)));
break;
case 'h':
// host
if (firstColEnd==4 && memcmp(line.data(), "host", 4) != 0) {
logTrace(g_conf.m_logTraceUrlMatchList, "");
if (firstColEnd == 4 && memcmp(line.data(), "host", 4) != 0) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
@ -135,8 +144,8 @@ bool UrlMatchList::load() {
break;
case 'p':
// path
if (firstColEnd==4 && memcmp(line.data(), "path", 4) != 0) {
logTrace(g_conf.m_logTraceUrlMatchList, "");
if (firstColEnd == 4 && memcmp(line.data(), "path", 4) != 0) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
@ -144,8 +153,8 @@ bool UrlMatchList::load() {
break;
case 'r':
// regex
if (firstColEnd==5 && memcmp(line.data(), "regex", 5) != 0) {
logTrace(g_conf.m_logTraceUrlMatchList, "");
if (firstColEnd == 5 && memcmp(line.data(), "regex", 5) != 0) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
@ -162,8 +171,8 @@ bool UrlMatchList::load() {
tmpUrlMatchList->emplace_back(std::shared_ptr<urlmatchregex_t>(new urlmatchregex_t(col3, GbRegex(col3.c_str(), PCRE_NO_AUTO_CAPTURE, PCRE_STUDY_JIT_COMPILE), col2)));
break;
case 't':
if (firstColEnd==3 && memcmp(line.data(), "tld", 3) != 0) {
logTrace(g_conf.m_logTraceUrlMatchList, "");
if (firstColEnd == 3 && memcmp(line.data(), "tld", 3) != 0) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}

6
test/unit/UrlMatchListTest.cpp

@ -140,6 +140,12 @@ TEST(UrlMatchListTest, Path) {
EXPECT_TRUE(urlMatchList.isUrlMatched("http://www.example.com/wp-admin/"));
EXPECT_FALSE(urlMatchList.isUrlMatched("http://www.example.com/tag/wp-admin/"));
EXPECT_TRUE(urlMatchList.isUrlMatched("http://www.example.com/blog/wp-login.php"));
EXPECT_TRUE(urlMatchList.isUrlMatched("http://www.example.com/wp-login.php"));
EXPECT_FALSE(urlMatchList.isUrlMatched("http://www.example.com/awp-login.php"));
EXPECT_FALSE(urlMatchList.isUrlMatched("http://www.example.com/wp-login.php5"));
EXPECT_TRUE(urlMatchList.isUrlMatched("http://www.example.com/blog/wp-login.php?param=value&param2=value2"));
EXPECT_TRUE(urlMatchList.isUrlMatched("https://www.host.com/file1.html"));
EXPECT_TRUE(urlMatchList.isUrlMatched("https://www.example.com/file1.html"));
}

3
test/unit/blocklist/path.txt

@ -1,2 +1,3 @@
path /wp-admin/
regex * https?://[^/]+/file1.html
file wp-login.php
regex * https?://[^/]+/file1.html