Merge pull request #10044 from edolstra/empty-git-repos

Handle empty Git repositories / workdirs

src/libexpr/eval.cc

@@ -467,13 +467,13 @@ EvalState::~EvalState()
 void EvalState::allowPath(const Path & path)
 {
     if (auto rootFS2 = rootFS.dynamic_pointer_cast<AllowListInputAccessor>())
-        rootFS2->allowPath(CanonPath(path));
+        rootFS2->allowPrefix(CanonPath(path));
 }
 
 void EvalState::allowPath(const StorePath & storePath)
 {
     if (auto rootFS2 = rootFS.dynamic_pointer_cast<AllowListInputAccessor>())
-        rootFS2->allowPath(CanonPath(store->toRealPath(storePath)));
+        rootFS2->allowPrefix(CanonPath(store->toRealPath(storePath)));
 }
 
 void EvalState::allowAndSetStorePathString(const StorePath & storePath, Value & v)

src/libfetchers/filtering-input-accessor.cc

@@ -51,33 +51,33 @@ void FilteringInputAccessor::checkAccess(const CanonPath & path)
 
 struct AllowListInputAccessorImpl : AllowListInputAccessor
 {
-    std::set<CanonPath> allowedPaths;
+    std::set<CanonPath> allowedPrefixes;
 
     AllowListInputAccessorImpl(
         ref<InputAccessor> next,
-        std::set<CanonPath> && allowedPaths,
+        std::set<CanonPath> && allowedPrefixes,
         MakeNotAllowedError && makeNotAllowedError)
         : AllowListInputAccessor(SourcePath(next), std::move(makeNotAllowedError))
-        , allowedPaths(std::move(allowedPaths))
+        , allowedPrefixes(std::move(allowedPrefixes))
     { }
 
     bool isAllowed(const CanonPath & path) override
     {
-        return path.isAllowed(allowedPaths);
+        return path.isAllowed(allowedPrefixes);
     }
 
-    void allowPath(CanonPath path) override
+    void allowPrefix(CanonPath prefix) override
     {
-        allowedPaths.insert(std::move(path));
+        allowedPrefixes.insert(std::move(prefix));
     }
 };
 
 ref<AllowListInputAccessor> AllowListInputAccessor::create(
     ref<InputAccessor> next,
-    std::set<CanonPath> && allowedPaths,
+    std::set<CanonPath> && allowedPrefixes,
     MakeNotAllowedError && makeNotAllowedError)
 {
-    return make_ref<AllowListInputAccessorImpl>(next, std::move(allowedPaths), std::move(makeNotAllowedError));
+    return make_ref<AllowListInputAccessorImpl>(next, std::move(allowedPrefixes), std::move(makeNotAllowedError));
 }
 
 bool CachingFilteringInputAccessor::isAllowed(const CanonPath & path)

src/libfetchers/filtering-input-accessor.hh

@@ -54,18 +54,19 @@ struct FilteringInputAccessor : InputAccessor
 };
 
 /**
- * A wrapping `InputAccessor` that checks paths against an allow-list.
+ * A wrapping `InputAccessor` that checks paths against a set of
+ * allowed prefixes.
  */
 struct AllowListInputAccessor : public FilteringInputAccessor
 {
     /**
-     * Grant access to the specified path.
+     * Grant access to the specified prefix.
      */
-    virtual void allowPath(CanonPath path) = 0;
+    virtual void allowPrefix(CanonPath prefix) = 0;
 
     static ref<AllowListInputAccessor> create(
         ref<InputAccessor> next,
-        std::set<CanonPath> && allowedPaths,
+        std::set<CanonPath> && allowedPrefixes,
         MakeNotAllowedError && makeNotAllowedError);
 
     using FilteringInputAccessor::FilteringInputAccessor;

src/libfetchers/git-utils.cc

@@ -2,6 +2,7 @@
 #include "fs-input-accessor.hh"
 #include "input-accessor.hh"
 #include "filtering-input-accessor.hh"
+#include "memory-input-accessor.hh"
 #include "cache.hh"
 #include "finally.hh"
 #include "processes.hh"
@@ -942,17 +943,21 @@ ref<InputAccessor> GitRepoImpl::getAccessor(const Hash & rev, bool exportIgnore)
 ref<InputAccessor> GitRepoImpl::getAccessor(const WorkdirInfo & wd, bool exportIgnore, MakeNotAllowedError makeNotAllowedError)
 {
     auto self = ref<GitRepoImpl>(shared_from_this());
+    /* In case of an empty workdir, return an empty in-memory tree. We
+       cannot use AllowListInputAccessor because it would return an
+       error for the root (and we can't add the root to the allow-list
+       since that would allow access to all its children). */
     ref<InputAccessor> fileAccessor =
-        AllowListInputAccessor::create(
-                makeFSInputAccessor(path),
-                std::set<CanonPath> { wd.files },
-                std::move(makeNotAllowedError));
-    if (exportIgnore) {
+        wd.files.empty()
+        ? makeEmptyInputAccessor()
+        : AllowListInputAccessor::create(
+            makeFSInputAccessor(path),
+            std::set<CanonPath> { wd.files },
+            std::move(makeNotAllowedError)).cast<InputAccessor>();
+    if (exportIgnore)
         return make_ref<GitExportIgnoreInputAccessor>(self, fileAccessor, std::nullopt);
-    }
-    else {
+    else
         return fileAccessor;
-    }
 }
 
 ref<GitFileSystemObjectSink> GitRepoImpl::getFileSystemObjectSink()

src/libfetchers/git.cc

@@ -158,6 +158,8 @@ std::vector<PublicKey> getPublicKeys(const Attrs & attrs)
 
 }  // end namespace
 
+static const Hash nullRev{HashAlgorithm::SHA1};
+
 struct GitInputScheme : InputScheme
 {
     std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const override
@@ -708,10 +710,12 @@ struct GitInputScheme : InputScheme
             if (auto ref = repo->getWorkdirRef())
                 input.attrs.insert_or_assign("ref", *ref);
 
-            auto rev = repoInfo.workdirInfo.headRev.value();
+            /* Return a rev of 000... if there are no commits yet. */
+            auto rev = repoInfo.workdirInfo.headRev.value_or(nullRev);
 
             input.attrs.insert_or_assign("rev", rev.gitRev());
-            input.attrs.insert_or_assign("revCount", getRevCount(repoInfo, repoInfo.url, rev));
+            input.attrs.insert_or_assign("revCount",
+                rev == nullRev ? 0 : getRevCount(repoInfo, repoInfo.url, rev));
 
             verifyCommit(input, repo);
         } else {

src/libfetchers/memory-input-accessor.cc

@@ -20,4 +20,10 @@ ref<MemoryInputAccessor> makeMemoryInputAccessor()
     return make_ref<MemoryInputAccessorImpl>();
 }
 
+ref<InputAccessor> makeEmptyInputAccessor()
+{
+    static auto empty = makeMemoryInputAccessor().cast<InputAccessor>();
+    return empty;
+}
+
 }

src/libfetchers/memory-input-accessor.hh

@@ -13,4 +13,6 @@ struct MemoryInputAccessor : InputAccessor
 
 ref<MemoryInputAccessor> makeMemoryInputAccessor();
 
+ref<InputAccessor> makeEmptyInputAccessor();
+
 }

tests/functional/fetchGit.sh

@@ -271,3 +271,28 @@ git -C "$repo" add hello .gitignore
 git -C "$repo" commit -m 'Bla1'
 cd "$repo"
 path11=$(nix eval --impure --raw --expr "(builtins.fetchGit ./.).outPath")
+
+# Test a workdir with no commits.
+empty="$TEST_ROOT/empty"
+git init "$empty"
+
+emptyAttrs='{ lastModified = 0; lastModifiedDate = "19700101000000"; narHash = "sha256-pQpattmS9VmO3ZIQUFn66az8GSmB4IvYhTTCFn6SUmo="; rev = "0000000000000000000000000000000000000000"; revCount = 0; shortRev = "0000000"; submodules = false; }'
+
+[[ $(nix eval --impure --expr "builtins.removeAttrs (builtins.fetchGit $empty) [\"outPath\"]") = $emptyAttrs ]]
+
+echo foo > "$empty/x"
+
+[[ $(nix eval --impure --expr "builtins.removeAttrs (builtins.fetchGit $empty) [\"outPath\"]") = $emptyAttrs ]]
+
+git -C "$empty" add x
+
+[[ $(nix eval --impure --expr "builtins.removeAttrs (builtins.fetchGit $empty) [\"outPath\"]") = '{ lastModified = 0; lastModifiedDate = "19700101000000"; narHash = "sha256-wzlAGjxKxpaWdqVhlq55q5Gxo4Bf860+kLeEa/v02As="; rev = "0000000000000000000000000000000000000000"; revCount = 0; shortRev = "0000000"; submodules = false; }' ]]
+
+# Test a repo with an empty commit.
+git -C "$empty" rm -f x
+
+git -C "$empty" config user.email "foobar@example.com"
+git -C "$empty" config user.name "Foobar"
+git -C "$empty" commit --allow-empty --allow-empty-message --message ""
+
+nix eval --impure --expr "let attrs = builtins.fetchGit $empty; in assert attrs.lastModified != 0; assert attrs.rev != \"0000000000000000000000000000000000000000\"; assert attrs.revCount == 1; true"