git 1.19.1 → 3.1.1

data/lib/git/command_line.rb

@@ -0,0 +1,287 @@
+# frozen_string_literal: true
+
+require 'git/base'
+require 'git/command_line_result'
+require 'git/errors'
+require 'stringio'
+
+module Git
+  # Runs a git command and returns the result
+  #
+  # @api public
+  #
+  class CommandLine
+    # Create a Git::CommandLine object
+    #
+    # @example
+    #   env = { 'GIT_DIR' => '/path/to/git/dir' }
+    #   binary_path = '/usr/bin/git'
+    #   global_opts = %w[--git-dir /path/to/git/dir]
+    #   logger = Logger.new(STDOUT)
+    #   cli = CommandLine.new(env, binary_path, global_opts, logger)
+    #   cli.run('version') #=> #<Git::CommandLineResult:0x00007f9b0c0b0e00
+    #
+    # @param env [Hash<String, String>] environment variables to set
+    # @param global_opts [Array<String>] global options to pass to git
+    # @param logger [Logger] the logger to use
+    #
+    def initialize(env, binary_path, global_opts, logger)
+      @env = env
+      @binary_path = binary_path
+      @global_opts = global_opts
+      @logger = logger
+    end
+
+    # @attribute [r] env
+    #
+    # Variables to set (or unset) in the git command's environment
+    #
+    # @example
+    #   env = { 'GIT_DIR' => '/path/to/git/dir' }
+    #   command_line = Git::CommandLine.new(env, '/usr/bin/git', [], Logger.new(STDOUT))
+    #   command_line.env #=> { 'GIT_DIR' => '/path/to/git/dir' }
+    #
+    # @return [Hash<String, String>]
+    #
+    # @see https://ruby-doc.org/3.2.1/Process.html#method-c-spawn Process.spawn
+    #   for details on how to set environment variables using the `env` parameter
+    #
+    attr_reader :env
+
+    # @attribute [r] binary_path
+    #
+    # The path to the command line binary to run
+    #
+    # @example
+    #   binary_path = '/usr/bin/git'
+    #   command_line = Git::CommandLine.new({}, binary_path, ['version'], Logger.new(STDOUT))
+    #   command_line.binary_path #=> '/usr/bin/git'
+    #
+    # @return [String]
+    #
+    attr_reader :binary_path
+
+    # @attribute [r] global_opts
+    #
+    # The global options to pass to git
+    #
+    # These are options that are passed to git before the command name and
+    # arguments. For example, in `git --git-dir /path/to/git/dir version`, the
+    # global options are %w[--git-dir /path/to/git/dir].
+    #
+    # @example
+    #   env = {}
+    #   global_opts = %w[--git-dir /path/to/git/dir]
+    #   logger = Logger.new(nil)
+    #   cli = CommandLine.new(env, '/usr/bin/git', global_opts, logger)
+    #   cli.global_opts #=> %w[--git-dir /path/to/git/dir]
+    #
+    # @return [Array<String>]
+    #
+    attr_reader :global_opts
+
+    # @attribute [r] logger
+    #
+    # The logger to use for logging git commands and results
+    #
+    # @example
+    #   env = {}
+    #   global_opts = %w[]
+    #   logger = Logger.new(STDOUT)
+    #   cli = CommandLine.new(env, '/usr/bin/git', global_opts, logger)
+    #   cli.logger == logger #=> true
+    #
+    # @return [Logger]
+    #
+    attr_reader :logger
+
+    # Execute a git command, wait for it to finish, and return the result
+    #
+    # NORMALIZATION
+    #
+    # The command output is returned as a Unicde string containing the binary output
+    # from the command. If the binary output is not valid UTF-8, the output will
+    # cause problems because the encoding will be invalid.
+    #
+    # Normalization is a process that trys to convert the binary output to a valid
+    # UTF-8 string. It uses the `rchardet` gem to detect the encoding of the binary
+    # output and then converts it to UTF-8.
+    #
+    # Normalization is not enabled by default. Pass `normalize: true` to Git::CommandLine#run
+    # to enable it. Normalization will only be performed on stdout and only if the `out:`` option
+    # is nil or is a StringIO object. If the out: option is set to a file or other IO object,
+    # the normalize option will be ignored.
+    #
+    # @example Run a command and return the output
+    #   cli.run('version') #=> "git version 2.39.1\n"
+    #
+    # @example The args array should be splatted into the parameter list
+    #   args = %w[log -n 1 --oneline]
+    #   cli.run(*args) #=> "f5baa11 beginning of Ruby/Git project\n"
+    #
+    # @example Run a command and return the chomped output
+    #   cli.run('version', chomp: true) #=> "git version 2.39.1"
+    #
+    # @example Run a command and without normalizing the output
+    #   cli.run('version', normalize: false) #=> "git version 2.39.1\n"
+    #
+    # @example Capture stdout in a temporary file
+    #   require 'tempfile'
+    #   tempfile = Tempfile.create('git') do |file|
+    #     cli.run('version', out: file)
+    #     file.rewind
+    #     file.read #=> "git version 2.39.1\n"
+    #   end
+    #
+    # @example Capture stderr in a StringIO object
+    #   require 'stringio'
+    #   stderr = StringIO.new
+    #   begin
+    #     cli.run('log', 'nonexistent-branch', err: stderr)
+    #   rescue Git::FailedError => e
+    #     stderr.string #=> "unknown revision or path not in the working tree.\n"
+    #   end
+    #
+    # @param args [Array<String>] the command line arguements to pass to git
+    #
+    #   This array should be splatted into the parameter list.
+    #
+    # @param out [#write, nil] the object to write stdout to or nil to ignore stdout
+    #
+    #   If this is a 'StringIO' object, then `stdout_writer.string` will be returned.
+    #
+    #   In general, only specify a `stdout_writer` object when you want to redirect
+    #   stdout to a file or some other object that responds to `#write`. The default
+    #   behavior will return the output of the command.
+    #
+    # @param err [#write] the object to write stderr to or nil to ignore stderr
+    #
+    #   If this is a 'StringIO' object and `merged_output` is `true`, then
+    #   `stderr_writer.string` will be merged into the output returned by this method.
+    #
+    # @param normalize [Boolean] whether to normalize the output to a valid encoding
+    #
+    # @param chomp [Boolean] whether to chomp the output
+    #
+    # @param merge [Boolean] whether to merge stdout and stderr in the string returned
+    #
+    # @param chdir [String] the directory to run the command in
+    #
+    # @param timeout [Numeric, nil] the maximum seconds to wait for the command to complete
+    #
+    #   If timeout is zero, the timeout will not be enforced.
+    #
+    #   If the command times out, it is killed via a `SIGKILL` signal and `Git::TimeoutError` is raised.
+    #
+    #   If the command does not respond to SIGKILL, it will hang this method.
+    #
+    # @return [Git::CommandLineResult] the output of the command
+    #
+    #   This result of running the command.
+    #
+    # @raise [ArgumentError] if `args` is not an array of strings
+    #
+    # @raise [Git::SignaledError] if the command was terminated because of an uncaught signal
+    #
+    # @raise [Git::FailedError] if the command returned a non-zero exitstatus
+    #
+    # @raise [Git::ProcessIOError] if an exception was raised while collecting subprocess output
+    #
+    # @raise [Git::TimeoutError] if the command times out
+    #
+    def run(*args, out: nil, err: nil, normalize:, chomp:, merge:, chdir: nil, timeout: nil)
+      git_cmd = build_git_cmd(args)
+      begin
+        result = ProcessExecuter.run(env, *git_cmd, out: out, err: err, merge:, chdir: (chdir || :not_set), timeout: timeout, raise_errors: false)
+      rescue ProcessExecuter::Command::ProcessIOError => e
+        raise Git::ProcessIOError.new(e.message), cause: e.exception.cause
+      end
+      process_result(result, normalize, chomp, timeout)
+    end
+
+    private
+
+    # Build the git command line from the available sources to send to `Process.spawn`
+    # @return [Array<String>]
+    # @api private
+    #
+    def build_git_cmd(args)
+      raise ArgumentError.new('The args array can not contain an array') if args.any? { |a| a.is_a?(Array) }
+
+      [binary_path, *global_opts, *args].map { |e| e.to_s }
+    end
+
+    # Process the result of the command and return a Git::CommandLineResult
+    #
+    # Post process output, log the command and result, and raise an error if the
+    # command failed.
+    #
+    # @param result [ProcessExecuter::Command::Result] the result it is a Process::Status and include command, stdout, and stderr
+    # @param normalize [Boolean] whether to normalize the output of each writer
+    # @param chomp [Boolean] whether to chomp the output of each writer
+    # @param timeout [Numeric, nil] the maximum seconds to wait for the command to complete
+    #
+    # @return [Git::CommandLineResult] the result of the command to return to the caller
+    #
+    # @raise [Git::FailedError] if the command failed
+    # @raise [Git::SignaledError] if the command was signaled
+    # @raise [Git::TimeoutError] if the command times out
+    # @raise [Git::ProcessIOError] if an exception was raised while collecting subprocess output
+    #
+    # @api private
+    #
+    def process_result(result, normalize, chomp, timeout)
+      command = result.command
+      processed_out, processed_err = post_process_all([result.stdout, result.stderr], normalize, chomp)
+      logger.info { "#{command} exited with status #{result}" }
+      logger.debug { "stdout:\n#{processed_out.inspect}\nstderr:\n#{processed_err.inspect}" }
+      Git::CommandLineResult.new(command, result, processed_out, processed_err).tap do |processed_result|
+        raise Git::TimeoutError.new(processed_result, timeout) if result.timeout?
+        raise Git::SignaledError.new(processed_result) if result.signaled?
+        raise Git::FailedError.new(processed_result) unless result.success?
+      end
+    end
+
+    # Post-process command output and return an array of the results
+    #
+    # @param raw_outputs [Array] the output to post-process
+    # @param normalize [Boolean] whether to normalize the output of each writer
+    # @param chomp [Boolean] whether to chomp the output of each writer
+    #
+    # @return [Array<String, nil>] the processed output of each command output object that supports `#string`
+    #
+    # @api private
+    #
+    def post_process_all(raw_outputs, normalize, chomp)
+      Array.new.tap do |result|
+        raw_outputs.each { |raw_output| result << post_process(raw_output, normalize, chomp) }
+      end
+    end
+
+    # Determine the output to return in the `CommandLineResult`
+    #
+    # If the writer can return the output by calling `#string` (such as a StringIO),
+    # then return the result of normalizing the encoding and chomping the output
+    # as requested.
+    #
+    # If the writer does not support `#string`, then return nil. The output is
+    # assumed to be collected by the writer itself such as when the  writer
+    # is a file instead of a StringIO.
+    #
+    # @param raw_output [#string] the output to post-process
+    # @return [String, nil]
+    #
+    # @api private
+    #
+    def post_process(raw_output, normalize, chomp)
+      if raw_output.respond_to?(:string)
+        output = raw_output.string.dup
+        output = output.lines.map { |l| Git::EncodingUtils.normalize_encoding(l) }.join if normalize
+        output.chomp! if chomp
+        output
+      else
+        nil
+      end
+    end
+  end
+end

data/lib/git/config.rb

@@ -1,12 +1,15 @@
+# frozen_string_literal: true
+
 module Git
 
   class Config
 
-    attr_writer :binary_path, :git_ssh
+    attr_writer :binary_path, :git_ssh, :timeout
 
     def initialize
       @binary_path = nil
       @git_ssh = nil
+      @timeout = nil
     end
 
     def binary_path
@@ -17,6 +20,9 @@ module Git
       @git_ssh || ENV['GIT_SSH']
     end
 
+    def timeout
+      @timeout || (ENV['GIT_TIMEOUT'] && ENV['GIT_TIMEOUT'].to_i)
+    end
   end
 
 end

data/lib/git/diff.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Git
 
   # object that holds the last X commits on given branch

data/lib/git/errors.rb

@@ -0,0 +1,206 @@
+# frozen_string_literal: true
+
+module Git
+  # Base class for all custom git module errors
+  #
+  # The git gem will only raise an `ArgumentError` or an error that is a subclass of
+  # `Git::Error`. It does not explicitly raise any other types of errors.
+  #
+  # It is recommended to rescue `Git::Error` to catch any runtime error raised by
+  # this gem unless you need more specific error handling.
+  #
+  # Git's custom errors are arranged in the following class heirarchy:
+  #
+  # ```text
+  # StandardError
+  # └─> Git::Error
+  #     ├─> Git::CommandLineError
+  #     │   ├─> Git::FailedError
+  #     │   └─> Git::SignaledError
+  #     │       └─> Git::TimeoutError
+  #     ├─> Git::ProcessIOError
+  #     └─> Git::UnexpectedResultError
+  # ```
+  #
+  # | Error Class | Description |
+  # | --- | --- |
+  # | `Error` | This catch-all error serves as the base class for other custom errors raised by the git gem. |
+  # | `CommandLineError` | A subclass of this error is raised when there is a problem executing the git command line. |
+  # | `FailedError` | This error is raised when the git command line exits with a non-zero status code that is not expected by the git gem. |
+  # | `SignaledError` | This error is raised when the git command line is terminated as a result of receiving a signal. This could happen if the process is forcibly terminated or if there is a serious system error. |
+  # | `TimeoutError` | This is a specific type of `SignaledError` that is raised when the git command line operation times out and is killed via the SIGKILL signal. This happens if the operation takes longer than the timeout duration configured in `Git.config.timeout` or via the `:timeout` parameter given in git methods that support timeouts. |
+  # | `ProcessIOError` | An error was encountered reading or writing to a subprocess. |
+  # | `UnexpectedResultError` | The command line ran without error but did not return the expected results. |
+  #
+  # @example Rescuing a generic error
+  #   begin
+  #     # some git operation
+  #   rescue Git::Error => e
+  #     puts "An error occurred: #{e.message}"
+  #   end
+  #
+  # @example Rescuing a timeout error
+  #   begin
+  #     timeout_duration = 0.001 # seconds
+  #     repo = Git.clone('https://github.com/ruby-git/ruby-git', 'ruby-git-temp', timeout: timeout_duration)
+  #   rescue Git::TimeoutError => e # Catch the more specific error first!
+  #     puts "Git clone took too long and timed out #{e}"
+  #   rescue Git::Error => e
+  #     puts "Received the following error: #{e}"
+  #   end
+  #
+  # @see Git::CommandLineError
+  # @see Git::FailedError
+  # @see Git::SignaledError
+  # @see Git::TimeoutError
+  # @see Git::ProcessIOError
+  # @see Git::UnexpectedResultError
+  #
+  # @api public
+  #
+  class Error < StandardError; end
+
+  # An alias for Git::Error
+  #
+  # Git::GitExecuteError error class is an alias for Git::Error for backwards
+  # compatibility. It is recommended to use Git::Error directly.
+  #
+  # @deprecated Use Git::Error instead
+  #
+  GitExecuteError = ActiveSupport::Deprecation::DeprecatedConstantProxy.new('Git::GitExecuteError', 'Git::Error', Git::Deprecation)
+
+  # Raised when a git command fails or exits because of an uncaught signal
+  #
+  # The git command executed, status, stdout, and stderr are available from this
+  # object.
+  #
+  # The Gem will raise a more specific error for each type of failure:
+  #
+  # * {Git::FailedError}: when the git command exits with a non-zero status
+  # * {Git::SignaledError}: when the git command exits because of an uncaught signal
+  # * {Git::TimeoutError}: when the git command times out
+  #
+  # @api public
+  #
+  class CommandLineError < Git::Error
+    # Create a CommandLineError object
+    #
+    # @example
+    #   `exit 1` # set $? appropriately for this example
+    #   result = Git::CommandLineResult.new(%w[git status], $?, 'stdout', 'stderr')
+    #   error = Git::CommandLineError.new(result)
+    #   error.to_s #=> '["git", "status"], status: pid 89784 exit 1, stderr: "stderr"'
+    #
+    # @param result [Git::CommandLineResult] the result of the git command including
+    #   the git command, status, stdout, and stderr
+    #
+    def initialize(result)
+      @result = result
+      super(error_message)
+    end
+
+    # The human readable representation of this error
+    #
+    # @example
+    #   error.error_message #=> '["git", "status"], status: pid 89784 exit 1, stderr: "stderr"'
+    #
+    # @return [String]
+    #
+    def error_message = <<~MESSAGE.chomp
+      #{result.git_cmd}, status: #{result.status}, stderr: #{result.stderr.inspect}
+    MESSAGE
+
+    # @attribute [r] result
+    #
+    # The result of the git command including the git command and its status and output
+    #
+    # @example
+    #   error.result #=> #<Git::CommandLineResult:0x00000001046bd488 ...>
+    #
+    # @return [Git::CommandLineResult]
+    #
+    attr_reader :result
+  end
+
+  # This error is raised when a git command returns a non-zero exitstatus
+  #
+  # The git command executed, status, stdout, and stderr are available from this
+  # object.
+  #
+  # @api public
+  #
+  class FailedError < Git::CommandLineError; end
+
+  # This error is raised when a git command exits because of an uncaught signal
+  #
+  # @api public
+  #
+  class SignaledError < Git::CommandLineError; end
+
+  # This error is raised when a git command takes longer than the configured timeout
+  #
+  # The git command executed, status, stdout, and stderr, and the timeout duration
+  # are available from this object.
+  #
+  # result.status.timeout? will be `true`
+  #
+  # @api public
+  #
+  class TimeoutError < Git::SignaledError
+    # Create a TimeoutError object
+    #
+    # @example
+    #   command = %w[sleep 10]
+    #   timeout_duration = 1
+    #   status = ProcessExecuter.spawn(*command, timeout: timeout_duration)
+    #   result = Git::CommandLineResult.new(command, status, 'stdout', 'err output')
+    #   error = Git::TimeoutError.new(result, timeout_duration)
+    #   error.error_message #=> '["sleep", "10"], status: pid 70144 SIGKILL (signal 9), stderr: "err output", timed out after 1s'
+    #
+    # @param result [Git::CommandLineResult] the result of the git command including
+    #   the git command, status, stdout, and stderr
+    #
+    # @param timeout_duration [Numeric] the amount of time the subprocess was allowed
+    #   to run before being killed
+    #
+    def initialize(result, timeout_duration)
+      @timeout_duration = timeout_duration
+      super(result)
+    end
+
+    # The human readable representation of this error
+    #
+    # @example
+    #   error.error_message #=> '["sleep", "10"], status: pid 88811 SIGKILL (signal 9), stderr: "err output", timed out after 1s'
+    #
+    # @return [String]
+    #
+    def error_message = <<~MESSAGE.chomp
+      #{super}, timed out after #{timeout_duration}s
+    MESSAGE
+
+    # The amount of time the subprocess was allowed to run before being killed
+    #
+    # @example
+    #   `kill -9 $$` # set $? appropriately for this example
+    #   result = Git::CommandLineResult.new(%w[git status], $?, '', "killed")
+    #   error = Git::TimeoutError.new(result, 10)
+    #   error.timeout_duration #=> 10
+    #
+    # @return [Numeric]
+    #
+    attr_reader :timeout_duration
+  end
+
+  # Raised when the output of a git command can not be read
+  #
+  # @api public
+  #
+  class ProcessIOError < Git::Error; end
+
+  # Raised when the git command result was not as expected
+  #
+  # @api public
+  #
+  class UnexpectedResultError < Git::Error; end
+end

data/lib/git/escaped_path.rb

@@ -3,7 +3,7 @@
 module Git
   # Represents an escaped Git path string
   #
-  # Git commands that output paths (e.g. ls-files, diff), will escape usual
+  # Git commands that output paths (e.g. ls-files, diff), will escape unusual
   # characters in the path with backslashes in the same way C escapes control
   # characters (e.g. \t for TAB, \n for LF, \\ for backslash) or bytes with values
   # larger than 0x80 (e.g. octal \302\265 for "micro" in UTF-8).

data/lib/git/index.rb

@@ -1,5 +1,6 @@
+# frozen_string_literal: true
+
 module Git
   class Index < Git::Path
-    
   end
 end