Merge branch 'sh-rugged-get-tree-entry' into 'master'

Bring back Rugged implementation of TreeEntry

See merge request gitlab-org/gitlab-ce!25706

4 files changed, 132 insertions, 1 deletions

diff --git a/changelogs/unreleased/sh-rugged-get-tree-entry.yml b/changelogs/unreleased/sh-rugged-get-tree-entry.yml
new file mode 100644
index 00000000000..4d46b764022
--- /dev/null
+++ b/changelogs/unreleased/sh-rugged-get-tree-entry.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of TreeEntry
+merge_request: 25706
+author:
+type: other
diff --git a/lib/gitlab/git/blob.rb b/lib/gitlab/git/blob.rb
index 259a2b7911a..10df4ed72d9 100644
--- a/lib/gitlab/git/blob.rb
+++ b/lib/gitlab/git/blob.rb
@@ -23,6 +23,10 @@ module Gitlab
 
       class << self
         def find(repository, sha, path, limit: MAX_DATA_DISPLAY_SIZE)
+          tree_entry(repository, sha, path, limit)
+        end
+
+        def tree_entry(repository, sha, path, limit)
           return unless path
 
           path = path.sub(%r{\A/*}, '')
@@ -179,3 +183,5 @@ module Gitlab
     end
   end
 end
+
+Gitlab::Git::Blob.singleton_class.prepend Gitlab::Git::RuggedImpl::Blob::ClassMethods
diff --git a/lib/gitlab/git/rugged_impl/blob.rb b/lib/gitlab/git/rugged_impl/blob.rb
new file mode 100644
index 00000000000..11ee4ebda4b
--- /dev/null
+++ b/lib/gitlab/git/rugged_impl/blob.rb
@@ -0,0 +1,106 @@
+# frozen_string_literal: true
+
+# NOTE: This code is legacy. Do not add/modify code here unless you have
+# discussed with the Gitaly team.  See
+# https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code
+# for more details.
+
+module Gitlab
+  module Git
+    module RuggedImpl
+      module Blob
+        module ClassMethods
+          extend ::Gitlab::Utils::Override
+
+          override :tree_entry
+          def tree_entry(repository, sha, path, limit)
+            if Feature.enabled?(:rugged_tree_entry)
+              rugged_tree_entry(repository, sha, path, limit)
+            else
+              super
+            end
+          end
+
+          private
+
+          def rugged_tree_entry(repository, sha, path, limit)
+            return unless path
+
+            # Strip any leading / characters from the path
+            path = path.sub(%r{\A/*}, '')
+
+            rugged_commit = repository.lookup(sha)
+            root_tree = rugged_commit.tree
+
+            blob_entry = find_entry_by_path(repository, root_tree.oid, *path.split('/'))
+
+            return unless blob_entry
+
+            if blob_entry[:type] == :commit
+              submodule_blob(blob_entry, path, sha)
+            else
+              blob = repository.lookup(blob_entry[:oid])
+
+              if blob
+                new(
+                  id: blob.oid,
+                  name: blob_entry[:name],
+                  size: blob.size,
+                  # Rugged::Blob#content is expensive; don't call it if we don't have to.
+                  data: limit.zero? ? '' : blob.content(limit),
+                  mode: blob_entry[:filemode].to_s(8),
+                  path: path,
+                  commit_id: sha,
+                  binary: blob.binary?
+                )
+              end
+            end
+          rescue Rugged::ReferenceError
+            nil
+          end
+
+          # Recursive search of blob id by path
+          #
+          # Ex.
+          #   blog/            # oid: 1a
+          #     app/           # oid: 2a
+          #       models/      # oid: 3a
+          #       file.rb      # oid: 4a
+          #
+          #
+          # Blob.find_entry_by_path(repo, '1a', 'blog', 'app', 'file.rb') # => '4a'
+          #
+          def find_entry_by_path(repository, root_id, *path_parts)
+            root_tree = repository.lookup(root_id)
+
+            entry = root_tree.find do |entry|
+              entry[:name] == path_parts[0]
+            end
+
+            return unless entry
+
+            if path_parts.size > 1
+              return unless entry[:type] == :tree
+
+              path_parts.shift
+              find_entry_by_path(repository, entry[:oid], *path_parts)
+            else
+              [:blob, :commit].include?(entry[:type]) ? entry : nil
+            end
+          end
+
+          def submodule_blob(blob_entry, path, sha)
+            new(
+              id: blob_entry[:oid],
+              name: blob_entry[:name],
+              size: 0,
+              data: '',
+              path: path,
+              commit_id: sha
+            )
+          end
+        end
+      end
+    end
+  end
+end
diff --git a/spec/lib/gitlab/git/blob_spec.rb b/spec/lib/gitlab/git/blob_spec.rb
index a1b5cea88c0..10bc82e24d1 100644
--- a/spec/lib/gitlab/git/blob_spec.rb
+++ b/spec/lib/gitlab/git/blob_spec.rb
@@ -18,7 +18,7 @@ describe Gitlab::Git::Blob, :seed_helper do
     end
   end
 
-  describe '.find' do
+  shared_examples '.find' do
     context 'nil path' do
       let(:blob) { Gitlab::Git::Blob.find(repository, SeedRepo::Commit::ID, nil) }
 
@@ -128,6 +128,20 @@ describe Gitlab::Git::Blob, :seed_helper do
     end
   end
 
+  describe '.find with Gitaly enabled' do
+    it_behaves_like '.find'
+  end
+
+  describe '.find with Rugged enabled', :enable_rugged do
+    it 'calls out to the Rugged implementation' do
+      allow_any_instance_of(Rugged).to receive(:rev_parse).with(SeedRepo::Commit::ID).and_call_original
+
+      described_class.find(repository, SeedRepo::Commit::ID, 'files/images/6049019_460s.jpg')
+    end
+
+    it_behaves_like '.find'
+  end
+
   describe '.raw' do
     let(:raw_blob) { Gitlab::Git::Blob.raw(repository, SeedRepo::RubyBlob::ID) }
     let(:bad_blob) { Gitlab::Git::Blob.raw(repository, SeedRepo::BigCommit::ID) }