libstore: Reallow unbracketed IPv6 addresses in store references

This implements a special back-compat shim to specifically allow
unbracketed IPv6 addresses in store references. This is something
that is relied upon in the wild and the old parsing logic accepted
both ways (brackets were optional). This patch restores this behavior.
As always, we didn't have any tests for this.

Addresses #13937.

(cherry picked from commit 7cc654afa9)

src/libstore-tests/data/store-reference/ssh_unbracketed_ipv6_1.txt

@@ -0,0 +1 @@
+ssh://::1

src/libstore-tests/data/store-reference/ssh_unbracketed_ipv6_2.txt

@@ -0,0 +1 @@
+ssh://userinfo@fea5:23e1:3916:fc24:cb52:2837:2ecb:ea8e

src/libstore-tests/data/store-reference/ssh_unbracketed_ipv6_3.txt

@@ -0,0 +1 @@
+ssh://userinfo@fea5:23e1:3916:fc24:cb52:2837:2ecb:ea8e?a=b&c=d

src/libstore-tests/store-reference.cc

@@ -148,4 +148,39 @@ URI_TEST(
         .params = {},
     }))
 
+static StoreReference sshLoopbackIPv6{
+    .variant =
+        StoreReference::Specified{
+            .scheme = "ssh",
+            .authority = "[::1]",
+        },
+};
+
+URI_TEST_READ(ssh_unbracketed_ipv6_1, sshLoopbackIPv6)
+
+static StoreReference sshIPv6AuthorityWithUserinfo{
+    .variant =
+        StoreReference::Specified{
+            .scheme = "ssh",
+            .authority = "userinfo@[fea5:23e1:3916:fc24:cb52:2837:2ecb:ea8e]",
+        },
+};
+
+URI_TEST_READ(ssh_unbracketed_ipv6_2, sshIPv6AuthorityWithUserinfo)
+
+static StoreReference sshIPv6AuthorityWithUserinfoAndParams{
+    .variant =
+        StoreReference::Specified{
+            .scheme = "ssh",
+            .authority = "userinfo@[fea5:23e1:3916:fc24:cb52:2837:2ecb:ea8e]",
+        },
+    .params =
+        {
+            {"a", "b"},
+            {"c", "d"},
+        },
+};
+
+URI_TEST_READ(ssh_unbracketed_ipv6_3, sshIPv6AuthorityWithUserinfoAndParams)
+
 } // namespace nix

src/libstore/meson.build

@@ -105,6 +105,7 @@ boost = dependency(
     'container',
     # Shouldn't list, because can header-only, and Meson currently looks for libs
     #'regex',
+    'url',
   ],
   include_type : 'system',
 )

src/libstore/store-reference.cc

@@ -1,11 +1,12 @@
-#include <regex>
-
 #include "nix/util/error.hh"
+#include "nix/util/split.hh"
 #include "nix/util/url.hh"
 #include "nix/store/store-reference.hh"
 #include "nix/util/file-system.hh"
 #include "nix/util/util.hh"
 
+#include <boost/url/ipv6_address.hpp>
+
 namespace nix {
 
 static bool isNonUriPath(const std::string & spec)
@@ -43,6 +44,29 @@ std::string StoreReference::render(bool withParams) const
     return res;
 }
 
+namespace {
+
+struct SchemeAndAuthorityWithPath
+{
+    std::string_view scheme;
+    std::string_view authority;
+};
+
+} // namespace
+
+/**
+ * Return the 'scheme' and remove the '://' or ':' separator.
+ */
+static std::optional<SchemeAndAuthorityWithPath> splitSchemePrefixTo(std::string_view string)
+{
+    auto scheme = splitPrefixTo(string, ':');
+    if (!scheme)
+        return std::nullopt;
+
+    splitPrefix(string, "//");
+    return SchemeAndAuthorityWithPath{.scheme = *scheme, .authority = string};
+}
+
 StoreReference StoreReference::parse(const std::string & uri, const StoreReference::Params & extraParams)
 {
     auto params = extraParams;
@@ -92,6 +116,32 @@ StoreReference StoreReference::parse(const std::string & uri, const StoreReferen
                     },
                 .params = std::move(params),
             };
+        } else if (auto schemeAndAuthority = splitSchemePrefixTo(baseURI)) {
+            /* Back-compatibility shim to accept unbracketed IPv6 addresses after the scheme.
+             * Old versions of nix allowed that. Note that this is ambiguous and does not allow
+             * specifying the port number. For that the address must be bracketed, otherwise it's
+             * greedily assumed to be the part of the host address. */
+            auto authorityString = schemeAndAuthority->authority;
+            auto userinfo = splitPrefixTo(authorityString, '@');
+            auto maybeIpv6 = boost::urls::parse_ipv6_address(authorityString);
+            if (maybeIpv6) {
+                std::string fixedAuthority;
+                if (userinfo) {
+                    fixedAuthority += *userinfo;
+                    fixedAuthority += '@';
+                }
+                fixedAuthority += '[';
+                fixedAuthority += authorityString;
+                fixedAuthority += ']';
+                return {
+                    .variant =
+                        Specified{
+                            .scheme = std::string(schemeAndAuthority->scheme),
+                            .authority = fixedAuthority,
+                        },
+                    .params = std::move(params),
+                };
+            }
         }
     }