gitlab-org--gitlab-foss/app/models/merge_request_diff.rb

323 lines
9.1 KiB
Ruby
Raw Normal View History

class MergeRequestDiff < ActiveRecord::Base
include Sortable
include Importable
Use latest_merge_request_diff association Compared to the merge_request_diff association: 1. It's simpler to query. The query uses a foreign key to the merge_request_diffs table, so no ordering is necessary. 2. It's faster for preloading. The merge_request_diff association has to load every diff for the MRs in the set, then discard all but the most recent for each. This association means that Rails can just query for N diffs from N MRs. 3. It's more complicated to update. This is a bidirectional foreign key, so we need to update two tables when adding a diff record. This also means we need to handle this as a special case when importing a GitLab project. There is some juggling with this association in the merge request model: * `MergeRequest#latest_merge_request_diff` is _always_ the latest diff. * `MergeRequest#merge_request_diff` reuses `MergeRequest#latest_merge_request_diff` unless: * Arguments are passed. These are typically to force-reload the association. * It doesn't exist. That means we might be trying to implicitly create a diff. This only seems to happen in specs. * The association is already loaded. This is important for the reasons explained in the comment, which I'll reiterate here: if we a) load a non-latest diff, then b) get its `merge_request`, then c) get that MR's `merge_request_diff`, we should get the diff we loaded in c), even though that's not the latest diff. Basically, `MergeRequest#merge_request_diff` is the latest diff in most cases, but not quite all.
2017-11-15 12:22:18 -05:00
include ManualInverseAssociation
include IgnorableColumn
include EachBatch
# Don't display more than 100 commits at once
COMMITS_SAFE_SIZE = 100
ignore_column :st_commits,
:st_diffs
belongs_to :merge_request
Use latest_merge_request_diff association Compared to the merge_request_diff association: 1. It's simpler to query. The query uses a foreign key to the merge_request_diffs table, so no ordering is necessary. 2. It's faster for preloading. The merge_request_diff association has to load every diff for the MRs in the set, then discard all but the most recent for each. This association means that Rails can just query for N diffs from N MRs. 3. It's more complicated to update. This is a bidirectional foreign key, so we need to update two tables when adding a diff record. This also means we need to handle this as a special case when importing a GitLab project. There is some juggling with this association in the merge request model: * `MergeRequest#latest_merge_request_diff` is _always_ the latest diff. * `MergeRequest#merge_request_diff` reuses `MergeRequest#latest_merge_request_diff` unless: * Arguments are passed. These are typically to force-reload the association. * It doesn't exist. That means we might be trying to implicitly create a diff. This only seems to happen in specs. * The association is already loaded. This is important for the reasons explained in the comment, which I'll reiterate here: if we a) load a non-latest diff, then b) get its `merge_request`, then c) get that MR's `merge_request_diff`, we should get the diff we loaded in c), even though that's not the latest diff. Basically, `MergeRequest#merge_request_diff` is the latest diff in most cases, but not quite all.
2017-11-15 12:22:18 -05:00
manual_inverse_association :merge_request, :merge_request_diff
has_many :merge_request_diff_files, -> { order(:merge_request_diff_id, :relative_order) }
has_many :merge_request_diff_commits, -> { order(:merge_request_diff_id, :relative_order) }
state_machine :state, initial: :empty do
event :clean do
transition any => :without_files
end
state :collected
2016-03-03 12:38:44 -05:00
state :overflow
# Diff files have been deleted by the system
state :without_files
2016-03-03 12:38:44 -05:00
# Deprecated states: these are no longer used but these values may still occur
# in the database.
state :timeout
state :overflow_commits_safe_size
state :overflow_diff_files_limit
state :overflow_diff_lines_limit
end
scope :with_files, -> { without_states(:without_files, :empty) }
scope :viewable, -> { without_state(:empty) }
scope :by_commit_sha, ->(sha) do
joins(:merge_request_diff_commits).where(merge_request_diff_commits: { sha: sha }).reorder(nil)
end
scope :recent, -> { order(id: :desc).limit(100) }
# All diff information is collected from repository after object is created.
# It allows you to override variables like head_commit_sha before getting diff.
after_create :save_git_content, unless: :importing?
2017-04-06 18:13:28 -04:00
def self.find_by_diff_refs(diff_refs)
2017-04-06 18:24:51 -04:00
find_by(start_commit_sha: diff_refs.start_sha, head_commit_sha: diff_refs.head_sha, base_commit_sha: diff_refs.base_sha)
2017-04-06 18:13:28 -04:00
end
def viewable?
collected? || without_files? || overflow?
end
# Collect information about commits and diff from repository
# and save it to the database as serialized data
def save_git_content
MergeRequest
.where('id = ? AND COALESCE(latest_merge_request_diff_id, 0) < ?', self.merge_request_id, self.id)
.update_all(latest_merge_request_diff_id: self.id)
ensure_commit_shas
save_commits
save_diffs
save
keep_around_commits
end
def ensure_commit_shas
self.start_commit_sha ||= merge_request.target_branch_sha
self.head_commit_sha ||= merge_request.source_branch_sha
self.base_commit_sha ||= find_base_sha
end
# Override head_commit_sha to keep compatibility with merge request diff
# created before version 8.4 that does not store head_commit_sha in separate db field.
def head_commit_sha
if persisted? && super.nil?
last_commit_sha
else
super
end
end
# This method will rely on repository branch sha
# in case start_commit_sha is nil. Its necesarry for old merge request diff
# created before version 8.4 to work
def safe_start_commit_sha
start_commit_sha || merge_request.target_branch_sha
end
2016-03-03 12:38:44 -05:00
def size
real_size.presence || raw_diffs.size
end
def raw_diffs(options = {})
2016-03-03 12:38:44 -05:00
if options[:ignore_whitespace_change]
@diffs_no_whitespace ||= compare.diffs(options)
2016-03-03 12:38:44 -05:00
else
@raw_diffs ||= {}
@raw_diffs[options] ||= load_diffs(options)
2016-03-03 12:38:44 -05:00
end
end
def commits
@commits ||= load_commits
end
def last_commit_sha
commit_shas.first
end
def first_commit
commits.last
end
def base_commit
return unless base_commit_sha
project.commit_by(oid: base_commit_sha)
end
def start_commit
return unless start_commit_sha
project.commit_by(oid: start_commit_sha)
end
def head_commit
return unless head_commit_sha
project.commit_by(oid: head_commit_sha)
end
def commit_shas
merge_request_diff_commits.map(&:sha)
end
2017-04-10 16:17:47 -04:00
def diff_refs=(new_diff_refs)
2017-04-11 11:51:48 -04:00
self.base_commit_sha = new_diff_refs&.base_sha
self.start_commit_sha = new_diff_refs&.start_sha
self.head_commit_sha = new_diff_refs&.head_sha
2017-04-10 16:17:47 -04:00
end
def diff_refs
return unless start_commit_sha || base_commit_sha
Gitlab::Diff::DiffRefs.new(
base_sha: base_commit_sha,
start_sha: start_commit_sha,
head_sha: head_commit_sha
)
end
# MRs created before 8.4 don't store their true diff refs (start and base),
# but we need to get a commit SHA for the "View file @ ..." link by a file,
2017-05-16 19:58:23 -04:00
# so we use an approximation of the diff refs if we can't get the actual one.
#
# These will not be the actual diff refs if the target branch was merged into
# the source branch after the merge request was created, but it is good enough
# for the specific purpose of linking to a commit.
2017-05-16 19:58:23 -04:00
#
# It is not good enough for highlighting diffs, so we can't simply pass
# these as `diff_refs.`
def fallback_diff_refs
real_refs = diff_refs
return real_refs if real_refs
likely_base_commit_sha = (first_commit&.parent || first_commit)&.sha
Gitlab::Diff::DiffRefs.new(
base_sha: likely_base_commit_sha,
start_sha: safe_start_commit_sha,
head_sha: head_commit_sha
)
end
def diff_refs_by_sha?
base_commit_sha? && head_commit_sha? && start_commit_sha?
end
def diffs(diff_options = nil)
if without_files? && comparison = diff_refs&.compare_in(project)
# It should fetch the repository when diffs are cleaned by the system.
# We don't keep these for storage overload purposes.
# See https://gitlab.com/gitlab-org/gitlab-ce/issues/37639
comparison.diffs(diff_options)
else
diffs_collection(diff_options)
end
end
# Should always return the DB persisted diffs collection
# (e.g. Gitlab::Diff::FileCollection::MergeRequestDiff.
# It's useful when trying to invalidate old caches through
# FileCollection::MergeRequestDiff#clear_cache!
def diffs_collection(diff_options = nil)
Gitlab::Diff::FileCollection::MergeRequestDiff.new(self, diff_options: diff_options)
end
def project
merge_request.target_project
end
def compare
@compare ||=
Gitlab::Git::Compare.new(
repository.raw_repository,
safe_start_commit_sha,
head_commit_sha
)
end
def latest?
Use latest_merge_request_diff association Compared to the merge_request_diff association: 1. It's simpler to query. The query uses a foreign key to the merge_request_diffs table, so no ordering is necessary. 2. It's faster for preloading. The merge_request_diff association has to load every diff for the MRs in the set, then discard all but the most recent for each. This association means that Rails can just query for N diffs from N MRs. 3. It's more complicated to update. This is a bidirectional foreign key, so we need to update two tables when adding a diff record. This also means we need to handle this as a special case when importing a GitLab project. There is some juggling with this association in the merge request model: * `MergeRequest#latest_merge_request_diff` is _always_ the latest diff. * `MergeRequest#merge_request_diff` reuses `MergeRequest#latest_merge_request_diff` unless: * Arguments are passed. These are typically to force-reload the association. * It doesn't exist. That means we might be trying to implicitly create a diff. This only seems to happen in specs. * The association is already loaded. This is important for the reasons explained in the comment, which I'll reiterate here: if we a) load a non-latest diff, then b) get its `merge_request`, then c) get that MR's `merge_request_diff`, we should get the diff we loaded in c), even though that's not the latest diff. Basically, `MergeRequest#merge_request_diff` is the latest diff in most cases, but not quite all.
2017-11-15 12:22:18 -05:00
self.id == merge_request.latest_merge_request_diff_id
end
def compare_with(sha)
# When compare merge request versions we want diff A..B instead of A...B
# so we handle cases when user does squash and rebase of the commits between versions.
# For this reason we set straight to true by default.
CompareService.new(project, head_commit_sha).execute(project, sha, straight: true)
end
private
def create_merge_request_diff_files(diffs)
rows = diffs.map.with_index do |diff, index|
diff_hash = diff.to_hash.merge(
binary: false,
merge_request_diff_id: self.id,
relative_order: index
)
# Compatibility with old diffs created with Psych.
diff_hash.tap do |hash|
diff_text = hash[:diff]
if diff_text.encoding == Encoding::BINARY && !diff_text.ascii_only?
hash[:binary] = true
hash[:diff] = [diff_text].pack('m0')
end
end
end
Gitlab::Database.bulk_insert('merge_request_diff_files', rows)
end
def load_diffs(options)
raw = merge_request_diff_files.map(&:to_hash)
if paths = options[:paths]
raw = raw.select do |diff|
paths.include?(diff[:old_path]) || paths.include?(diff[:new_path])
end
end
Gitlab::Git::DiffCollection.new(raw, options)
end
def load_commits
commits = merge_request_diff_commits.map { |commit| Commit.from_hash(commit.to_hash, project) }
CommitCollection
.new(merge_request.source_project, commits, merge_request.source_branch)
end
def save_diffs
new_attributes = {}
if compare.commits.size.zero?
new_attributes[:state] = :empty
else
diff_collection = compare.diffs(Commit.max_diff_options)
new_attributes[:real_size] = diff_collection.real_size
2016-03-03 12:38:44 -05:00
if diff_collection.any?
new_attributes[:state] = :collected
create_merge_request_diff_files(diff_collection)
end
# Set our state to 'overflow' to make the #empty? and #collected?
# methods (generated by StateMachine) return false.
#
# This attribution has to come at the end of the method so 'overflow'
# state does not get overridden by 'collected'.
new_attributes[:state] = :overflow if diff_collection.overflow?
end
assign_attributes(new_attributes)
end
def save_commits
MergeRequestDiffCommit.create_bulk(self.id, compare.commits.reverse)
# merge_request_diff_commits.reload is preferred way to reload associated
# objects but it returns cached result for some reason in this case
commits = merge_request_diff_commits(true)
self.commits_count = commits.size
end
def repository
project.repository
end
def find_base_sha
return unless head_commit_sha && start_commit_sha
project.merge_base_commit(head_commit_sha, start_commit_sha).try(:sha)
end
def keep_around_commits
[repository, merge_request.source_project.repository].uniq.each do |repo|
repo.keep_around(start_commit_sha)
repo.keep_around(head_commit_sha)
repo.keep_around(base_commit_sha)
end
end
end