Skip to content

fix: properly parse UTF-8(multibyte) file paths in git output #839

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 20, 2025
Merged

fix: properly parse UTF-8(multibyte) file paths in git output #839

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c06eb4f
fix: properly parse UTF-8(multibyte) file paths in git output
kaorukobo Aug 16, 2025
4c4c8f9
chore: update ClassLength max in .rubocop_todo.yml for CI passing
kaorukobo Aug 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .rubocop_todo.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# This configuration was generated by
# `rubocop --auto-gen-config`
# on 2025-07-06 21:08:14 UTC using RuboCop version 1.77.0.
# on 2025-08-17 04:52:22 UTC using RuboCop version 1.79.2.
# The point is for the user to remove these configuration records
# one by one as the offenses are removed from the code base.
# Note that changes in the inspected code, or installation of new
Expand All @@ -9,4 +9,4 @@
# Offense count: 2
# Configuration parameters: CountComments, CountAsOne.
Metrics/ClassLength:
Max: 1032
Max: 1039
22 changes: 15 additions & 7 deletions lib/git/lib.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,7 +643,7 @@ def ls_tree(sha, opts = {})
args << opts[:path] if opts[:path]

command_lines('ls-tree', *args).each do |line|
(info, filenm) = line.split("\t")
(info, filenm) = split_status_line(line)
(mode, type, sha) = info.split
data[type][filenm] = { mode: mode, sha: sha }
end
Expand Down Expand Up @@ -905,9 +905,9 @@ def ls_files(location = nil)
location ||= '.'
{}.tap do |files|
command_lines('ls-files', '--stage', location).each do |line|
(info, file) = line.split("\t")
(info, file) = split_status_line(line)
(mode, sha, stage) = info.split
files[unescape_quoted_path(file)] = {
files[file] = {
path: file, mode_index: mode, sha_index: sha, stage: stage
}
end
Expand Down Expand Up @@ -956,7 +956,9 @@ def ignored_files
end

def untracked_files
command_lines('ls-files', '--others', '--exclude-standard', chdir: @git_work_dir)
command_lines('ls-files', '--others', '--exclude-standard', chdir: @git_work_dir).map do |f|
unescape_quoted_path(f)
end
end

def config_remote(name)
Expand Down Expand Up @@ -1602,7 +1604,7 @@ def self.warn_if_old_command(lib) # rubocop:disable Naming/PredicateMethod

def parse_diff_path_status(args)
command_lines('diff', *args).each_with_object({}) do |line, memo|
status, path = line.split("\t")
status, path = split_status_line(line)
memo[path] = status
end
end
Expand Down Expand Up @@ -1727,7 +1729,7 @@ def parse_diff_stats_output(lines)

def parse_stat_lines(lines)
lines.map do |line|
insertions_s, deletions_s, filename = line.split("\t")
insertions_s, deletions_s, filename = split_status_line(line)
{
filename: filename,
insertions: insertions_s.to_i,
Expand All @@ -1736,6 +1738,12 @@ def parse_stat_lines(lines)
end
end

def split_status_line(line)
parts = line.split("\t")
parts[-1] = unescape_quoted_path(parts[-1]) if parts.any?
parts
end

def build_final_stats_hash(file_stats)
{
total: build_total_stats(file_stats),
Expand Down Expand Up @@ -1965,7 +1973,7 @@ def diff_as_hash(diff_command, opts = [])
# update index before diffing to avoid spurious diffs
command('status')
command_lines(diff_command, *opts).each_with_object({}) do |line, memo|
info, file = line.split("\t")
info, file = split_status_line(line)
mode_src, mode_dest, sha_src, sha_dest, type = info.split

memo[file] = {
Expand Down
50 changes: 50 additions & 0 deletions tests/units/test_status.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,4 +235,54 @@ def test_changed_cache
assert(!git.status.changed?('test_file_1'))
end
end

def test_multibyte_path
# a name consisting of UTF-8 characters
multibyte_name = "\u30DE\u30EB\u30C1\u30D0\u30A4\u30C8\u6587\u5B57\u30D5\u30A1\u30A4\u30EB\u263A"

in_temp_dir do |_path|
`git init`

File.write('file1', 'contents1')
`git add file1`
`git commit -m "my message"`

git = Git.open('.')

# Test added
File.write("#{multibyte_name}_added.txt", 'contents_mb_added')
`git add #{multibyte_name}_added.txt`

status = git.status
assert_equal(1, status.added.size)
assert_equal(["#{multibyte_name}_added.txt"], status.added.keys)

# Test untracked
File.write("#{multibyte_name}_untracked.txt", 'contents_mb_untracked')

status = git.status
assert_equal(1, status.untracked.size)
assert_equal(["#{multibyte_name}_untracked.txt"], status.untracked.keys)

# Test changed
File.write("#{multibyte_name}_changed.txt", 'original_content')
`git add #{multibyte_name}_changed.txt`
`git commit -m "add multibyte file"`
File.write("#{multibyte_name}_changed.txt", 'modified_content')

status = git.status
assert_equal(1, status.changed.size)
assert_equal(["#{multibyte_name}_changed.txt"], status.changed.keys)

# Test deleted
File.write("#{multibyte_name}_deleted.txt", 'to_be_deleted')
`git add #{multibyte_name}_deleted.txt`
`git commit -m "add file to be deleted"`
File.delete("#{multibyte_name}_deleted.txt")

status = git.status
assert_equal(1, status.deleted.size)
assert_equal(["#{multibyte_name}_deleted.txt"], status.deleted.keys)
end
end
end
Loading