Allow tarball URLs to redirect to a lockable immutable URL

Previously, for tarball flakes, we recorded the original URL of the
tarball flake, rather than the URL to which it ultimately
redirects. Thus, a flake URL like
http://example.org/patchelf-latest.tar that redirects to
http://example.org/patchelf-<revision>.tar was not really usable. We
couldn't record the redirected URL, because sites like GitHub redirect
to CDN URLs that we can't rely on to be stable.

So now we use the redirected URL only if the server returns the
`x-nix-is-immutable` or `x-amz-meta-nix-is-immutable` headers in its
response.

4 files changed, 66 insertions, 23 deletions

diff --git a/src/libfetchers/attrs.hh b/src/libfetchers/attrs.hh
index 1a14bb023..9f885a793 100644
--- a/src/libfetchers/attrs.hh
+++ b/src/libfetchers/attrs.hh
@@ -2,6 +2,7 @@
 ///@file
 
 #include "types.hh"
+#include "hash.hh"
 
 #include <variant>
 
diff --git a/src/libfetchers/fetchers.hh b/src/libfetchers/fetchers.hh
index 498ad7e4d..d0738f619 100644
--- a/src/libfetchers/fetchers.hh
+++ b/src/libfetchers/fetchers.hh
@@ -158,6 +158,7 @@ struct DownloadFileResult
     StorePath storePath;
     std::string etag;
     std::string effectiveUrl;
+    std::optional<std::string> immutableUrl;
 };
 
 DownloadFileResult downloadFile(
@@ -167,7 +168,14 @@ DownloadFileResult downloadFile(
     bool locked,
     const Headers & headers = {});
 
-std::pair<Tree, time_t> downloadTarball(
+struct DownloadTarballResult
+{
+    Tree tree;
+    time_t lastModified;
+    std::optional<std::string> immutableUrl;
+};
+
+DownloadTarballResult downloadTarball(
     ref<Store> store,
     const std::string & url,
     const std::string & name,
diff --git a/src/libfetchers/github.cc b/src/libfetchers/github.cc
index 6c1d573ce..80598e7f8 100644
--- a/src/libfetchers/github.cc
+++ b/src/libfetchers/github.cc
@@ -207,21 +207,21 @@ struct GitArchiveInputScheme : InputScheme
 
         auto url = getDownloadUrl(input);
 
-        auto [tree, lastModified] = downloadTarball(store, url.url, input.getName(), true, url.headers);
+        auto result = downloadTarball(store, url.url, input.getName(), true, url.headers);
 
-        input.attrs.insert_or_assign("lastModified", uint64_t(lastModified));
+        input.attrs.insert_or_assign("lastModified", uint64_t(result.lastModified));
 
         getCache()->add(
             store,
             lockedAttrs,
             {
                 {"rev", rev->gitRev()},
-                {"lastModified", uint64_t(lastModified)}
+                {"lastModified", uint64_t(result.lastModified)}
             },
-            tree.storePath,
+            result.tree.storePath,
             true);
 
-        return {std::move(tree.storePath), input};
+        return {result.tree.storePath, input};
     }
 };
 
diff --git a/src/libfetchers/tarball.cc b/src/libfetchers/tarball.cc
index 96fe5faca..e42aca6db 100644
--- a/src/libfetchers/tarball.cc
+++ b/src/libfetchers/tarball.cc
@@ -32,7 +32,8 @@ DownloadFileResult downloadFile(
         return {
             .storePath = std::move(cached->storePath),
             .etag = getStrAttr(cached->infoAttrs, "etag"),
-            .effectiveUrl = getStrAttr(cached->infoAttrs, "url")
+            .effectiveUrl = getStrAttr(cached->infoAttrs, "url"),
+            .immutableUrl = maybeGetStrAttr(cached->infoAttrs, "immutableUrl"),
         };
     };
 
@@ -55,12 +56,14 @@ DownloadFileResult downloadFile(
     }
 
     // FIXME: write to temporary file.
-
     Attrs infoAttrs({
         {"etag", res.etag},
         {"url", res.effectiveUri},
     });
 
+    if (res.immutableUrl)
+        infoAttrs.emplace("immutableUrl", *res.immutableUrl);
+
     std::optional<StorePath> storePath;
 
     if (res.cached) {
@@ -111,10 +114,11 @@ DownloadFileResult downloadFile(
         .storePath = std::move(*storePath),
         .etag = res.etag,
         .effectiveUrl = res.effectiveUri,
+        .immutableUrl = res.immutableUrl,
     };
 }
 
-std::pair<Tree, time_t> downloadTarball(
+DownloadTarballResult downloadTarball(
     ref<Store> store,
     const std::string & url,
     const std::string & name,
@@ -131,8 +135,9 @@ std::pair<Tree, time_t> downloadTarball(
 
     if (cached && !cached->expired)
         return {
-            Tree { .actualPath = store->toRealPath(cached->storePath), .storePath = std::move(cached->storePath) },
-            getIntAttr(cached->infoAttrs, "lastModified")
+            .tree = Tree { .actualPath = store->toRealPath(cached->storePath), .storePath = std::move(cached->storePath) },
+            .lastModified = (time_t) getIntAttr(cached->infoAttrs, "lastModified"),
+            .immutableUrl = maybeGetStrAttr(cached->infoAttrs, "immutableUrl"),
         };
 
     auto res = downloadFile(store, url, name, locked, headers);
@@ -160,6 +165,9 @@ std::pair<Tree, time_t> downloadTarball(
         {"etag", res.etag},
     });
 
+    if (res.immutableUrl)
+        infoAttrs.emplace("immutableUrl", *res.immutableUrl);
+
     getCache()->add(
         store,
         inAttrs,
@@ -168,8 +176,9 @@ std::pair<Tree, time_t> downloadTarball(
         locked);
 
     return {
-        Tree { .actualPath = store->toRealPath(*unpackedStorePath), .storePath = std::move(*unpackedStorePath) },
-        lastModified,
+        .tree = Tree { .actualPath = store->toRealPath(*unpackedStorePath), .storePath = std::move(*unpackedStorePath) },
+        .lastModified = lastModified,
+        .immutableUrl = res.immutableUrl,
     };
 }
 
@@ -189,21 +198,33 @@ struct CurlInputScheme : InputScheme
 
     virtual bool isValidURL(const ParsedURL & url) const = 0;
 
-    std::optional<Input> inputFromURL(const ParsedURL & url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & _url) const override
     {
-        if (!isValidURL(url))
+        if (!isValidURL(_url))
             return std::nullopt;
 
         Input input;
 
-        auto urlWithoutApplicationScheme = url;
-        urlWithoutApplicationScheme.scheme = parseUrlScheme(url.scheme).transport;
+        auto url = _url;
+
+        url.scheme = parseUrlScheme(url.scheme).transport;
 
-        input.attrs.insert_or_assign("type", inputType());
-        input.attrs.insert_or_assign("url", urlWithoutApplicationScheme.to_string());
         auto narHash = url.query.find("narHash");
         if (narHash != url.query.end())
             input.attrs.insert_or_assign("narHash", narHash->second);
+
+        if (auto i = get(url.query, "rev"))
+            input.attrs.insert_or_assign("rev", *i);
+
+        if (auto i = get(url.query, "revCount"))
+            if (auto n = string2Int<uint64_t>(*i))
+                input.attrs.insert_or_assign("revCount", *n);
+
+        url.query.erase("rev");
+        url.query.erase("revCount");
+
+        input.attrs.insert_or_assign("type", inputType());
+        input.attrs.insert_or_assign("url", url.to_string());
         return input;
     }
 
@@ -212,7 +233,8 @@ struct CurlInputScheme : InputScheme
         auto type = maybeGetStrAttr(attrs, "type");
         if (type != inputType()) return {};
 
-        std::set<std::string> allowedNames = {"type", "url", "narHash", "name", "unpack"};
+        // FIXME: some of these only apply to TarballInputScheme.
+        std::set<std::string> allowedNames = {"type", "url", "narHash", "name", "unpack", "rev", "revCount"};
         for (auto & [name, value] : attrs)
             if (!allowedNames.count(name))
                 throw Error("unsupported %s input attribute '%s'", *type, name);
@@ -275,10 +297,22 @@ struct TarballInputScheme : CurlInputScheme
                     : hasTarballExtension(url.path));
     }
 
-    std::pair<StorePath, Input> fetch(ref<Store> store, const Input & input) override
+    std::pair<StorePath, Input> fetch(ref<Store> store, const Input & _input) override
     {
-        auto tree = downloadTarball(store, getStrAttr(input.attrs, "url"), input.getName(), false).first;
-        return {std::move(tree.storePath), input};
+        Input input(_input);
+        auto url = getStrAttr(input.attrs, "url");
+        auto result = downloadTarball(store, url, input.getName(), false);
+
+        if (result.immutableUrl) {
+            auto immutableInput = Input::fromURL(*result.immutableUrl);
+            // FIXME: would be nice to support arbitrary flakerefs
+            // here, e.g. git flakes.
+            if (immutableInput.getType() != "tarball")
+                throw Error("tarball 'Link' headers that redirect to non-tarball URLs are not supported");
+            input = immutableInput;
+        }
+
+        return {result.tree.storePath, std::move(input)};
     }
 };