samiandClaude Sonnet 5
201ebc55d4
net/content_disposition — total parser for the mojibake-prone header: RFC 6266 filename (quoted/token), RFC 5987 filename* ext-values (charset'lang'pct-encoded, incl. RFC 2231 continuations), legacy RFC 2047 encoded-words (=?UTF-8?B?..?= / ?Q?), and raw Latin-1 bytes; prefers filename* over filename; strips path components AFTER decoding (a base64 payload can hold '/'). 22-case test table. net/text_codec (internal) — percent-decode, UTF-8 validation, Latin-1-> UTF-8, base64, RFC 2047 — shared by the CD parser and the URL splitter. net/url — a small total URL splitter (scheme/userinfo/host/port/path/ query/fragment, http(s) validity) and url_filename() for the last path segment; used for the filename fallback. net/probe — HEAD then a ranged GET bytes=0-0 that PROVES resumability (206 + matching Content-Range + a validator), rather than trusting Accept-Ranges which servers lie about; the ranged GET is also the HEAD- refused (403/405/501) fallback. 401/407 -> success result with requires_auth, not an error. Runs on its own pool (max_concurrent, default 4) outside the segment budget per ADR 0011 §5. suggest_filename() does the resolution order (explicit -> disposition -> URL -> download.bin) with a light strip; rules/ (stage 9) owns the authoritative sanitize. tools/fuzz — libFuzzer targets for the CD parser and the URL splitter, compiling the parser sources directly so they're fully instrumented; self-guards on VELOX_BUILD_FUZZ + Clang (the top-level CMake adds every tools/* unconditionally). Seed corpora included. Fixed on the way: a p -> Transfer -> State -> cbs -> p reference cycle in Prober that leaked every probe (drop the stored Transfer; the worker keeps State alive). Tests green under ASan/UBSan and TSan. Co-Authored-By: Claude Sonnet 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01HPPSGhiArbvQgwC2DNiURS
72 lines
2.3 KiB
C++
72 lines
2.3 KiB
C++
#include "vdm/net/url.hpp"
|
|
|
|
#include <string>
|
|
|
|
#include "vtest.hpp"
|
|
|
|
using vdm::net::split_url;
|
|
using vdm::net::SplitUrl;
|
|
using vdm::net::url_filename;
|
|
|
|
VT_TEST(url_basic_https) {
|
|
auto u = split_url("https://example.com/path/to/file.iso?x=1#frag");
|
|
VT_CHECK(u.valid);
|
|
VT_CHECK_EQ(u.scheme, std::string("https"));
|
|
VT_CHECK_EQ(u.host, std::string("example.com"));
|
|
VT_CHECK(!u.port.has_value());
|
|
VT_CHECK_EQ(u.path, std::string("/path/to/file.iso"));
|
|
VT_CHECK_EQ(u.query, std::string("x=1"));
|
|
VT_CHECK_EQ(u.fragment, std::string("frag"));
|
|
}
|
|
|
|
VT_TEST(url_port_userinfo_lowercasing) {
|
|
auto u = split_url("HTTP://User:[email protected]:8080/a");
|
|
VT_CHECK_EQ(u.scheme, std::string("http"));
|
|
VT_CHECK_EQ(u.userinfo, std::string("User:pw"));
|
|
VT_CHECK_EQ(u.host, std::string("host.example.com"));
|
|
VT_REQUIRE(u.port.has_value());
|
|
VT_CHECK_EQ(*u.port, 8080);
|
|
}
|
|
|
|
VT_TEST(url_ipv6_host) {
|
|
auto u = split_url("http://[2001:db8::1]:9000/file");
|
|
VT_CHECK_EQ(u.host, std::string("2001:db8::1"));
|
|
VT_REQUIRE(u.port.has_value());
|
|
VT_CHECK_EQ(*u.port, 9000);
|
|
}
|
|
|
|
VT_TEST(url_no_path) {
|
|
auto u = split_url("https://example.com");
|
|
VT_CHECK(u.valid);
|
|
VT_CHECK_EQ(u.path, std::string(""));
|
|
}
|
|
|
|
VT_TEST(url_non_http_is_invalid_but_parsed) {
|
|
auto u = split_url("ftp://host/file");
|
|
VT_CHECK(!u.valid); // not http/https
|
|
VT_CHECK_EQ(u.scheme, std::string("ftp"));
|
|
VT_CHECK(!u.is_http());
|
|
}
|
|
|
|
VT_TEST(url_garbage_does_not_crash) {
|
|
VT_CHECK(!split_url("").valid);
|
|
VT_CHECK(!split_url("not a url").valid);
|
|
VT_CHECK(!split_url("://noscheme/x").valid);
|
|
VT_CHECK(!split_url("http://").valid);
|
|
auto a = split_url("http://////");
|
|
auto b = split_url("https://h/%%%/%");
|
|
(void)a;
|
|
(void)b;
|
|
}
|
|
|
|
VT_TEST(url_filename_extraction) {
|
|
VT_CHECK_EQ(url_filename("https://x.com/a/b/report%20final.pdf"),
|
|
std::string("report final.pdf"));
|
|
VT_CHECK_EQ(url_filename("https://x.com/a/b/file.iso?sig=abc"), std::string("file.iso"));
|
|
VT_CHECK_EQ(url_filename("https://x.com/dir/"), std::string(""));
|
|
VT_CHECK_EQ(url_filename("https://x.com"), std::string(""));
|
|
VT_CHECK_EQ(url_filename("https://x.com/%2e%2e"), std::string("")); // ".." rejected
|
|
VT_CHECK_EQ(url_filename("https://x.com/a%2Fb"),
|
|
std::string("a_b")); // decoded '/' neutralised
|
|
}
|