From 9e762454cf62d0d7a6259b560cc3e340f6f5ec6e Mon Sep 17 00:00:00 2001
From: Eelco Dolstra <edolstra@gmail.com>
Date: Tue, 20 Feb 2024 11:40:02 +0100
Subject: [PATCH] Support empty Git repositories / workdirs

Fixes #10039.
---
 src/libfetchers/git-utils.cc             | 21 ++++++++++++--------
 src/libfetchers/git.cc                   |  8 ++++++--
 src/libfetchers/memory-input-accessor.cc |  6 ++++++
 src/libfetchers/memory-input-accessor.hh |  2 ++
 tests/functional/fetchGit.sh             | 25 ++++++++++++++++++++++++
 5 files changed, 52 insertions(+), 10 deletions(-)

diff --git a/src/libfetchers/git-utils.cc b/src/libfetchers/git-utils.cc
index 4f034e9d4..037fcc365 100644
--- a/src/libfetchers/git-utils.cc
+++ b/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()
diff --git a/src/libfetchers/git.cc b/src/libfetchers/git.cc
index bef945d54..97ef35b51 100644
--- a/src/libfetchers/git.cc
+++ b/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 {
diff --git a/src/libfetchers/memory-input-accessor.cc b/src/libfetchers/memory-input-accessor.cc
index 88a2e34e8..34a801f67 100644
--- a/src/libfetchers/memory-input-accessor.cc
+++ b/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;
+}
+
 }
diff --git a/src/libfetchers/memory-input-accessor.hh b/src/libfetchers/memory-input-accessor.hh
index 508b07722..63afadd2a 100644
--- a/src/libfetchers/memory-input-accessor.hh
+++ b/src/libfetchers/memory-input-accessor.hh
@@ -13,4 +13,6 @@ struct MemoryInputAccessor : InputAccessor
 
 ref<MemoryInputAccessor> makeMemoryInputAccessor();
 
+ref<InputAccessor> makeEmptyInputAccessor();
+
 }
diff --git a/tests/functional/fetchGit.sh b/tests/functional/fetchGit.sh
index ea90f8ebe..0583774c4 100644
--- a/tests/functional/fetchGit.sh
+++ b/tests/functional/fetchGit.sh
@@ -268,3 +268,28 @@ 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"