No OneTemporary
Actions

Size

39 KB

Referenced Files

None

Subscribers

None

View Options

	diff --git a/lib/majic/server.ex b/lib/majic/server.ex
	index c0925a3..4cf2669 100644
	--- a/lib/majic/server.ex
	+++ b/lib/majic/server.ex
	@@ -1,446 +1,446 @@
	defmodule Majic.Server do
	@moduledoc """
	Provides access to the underlying libmagic client, which performs file introspection.

	The Server needs to be supervised, since it will terminate if it receives any unexpected error.
	"""

	@behaviour :gen_statem
	alias Majic.Result
	alias Majic.Server.Data
	alias Majic.Server.Status
	import Kernel, except: [send: 2]
	@database_patterns [:default]
	@process_timeout Majic.Config.default_process_timeout()

	@typedoc """
	Represents the reference to the underlying server, as returned by `:gen_statem`.
	"""
	@type t :: :gen_statem.server_ref()

	@typedoc """
	Represents values accepted as startup options, which can be passed to `start_link/1`.

	- `:name`: If present, this will be the registered name for the underlying process.
	Note that `:gen_statem` requires `{:local, name}`, but given widespread GenServer convention,
	atoms are accepted and will be converted to `{:local, name}`.

	- `:startup_timeout`: Specifies how long the Server waits for the C program to initialise.
	However, if the underlying C program exits, then the process exits immediately.

	Can be set to `:infinity`.

	- `:process_timeout`: Specifies how long the Server waits for each request to complete.

	Can be set to `:infinity`.

	Please note that, if you have chosen a custom timeout value, you should also pass it when
	using `Majic.Server.perform/3`.

	- `:recycle_threshold`: Specifies the number of requests processed before the underlying C
	program is recycled.

	Can be set to `:infinity` if you do not wish for the program to be recycled.

	- `:database_patterns`: Specifies what magic databases to load; you can specify a list of files, or of
	Path Patterns (see `Path.wildcard/2`) or `:default` to instruct the C program to load the
	appropriate databases.

	For example, if you have had to add custom magics, then you can set this value to:

	[:default, "path/to/my/magic"]
	"""
	@type start_option ::
	{:name, atom() \| :gen_statem.server_name()}
	\| {:startup_timeout, timeout()}
	\| {:process_timeout, timeout()}
	\| {:recycle_threshold, non_neg_integer() \| :infinity}
	\| {:database_patterns, nonempty_list(:default \| Path.t())}

	@typedoc """
	Current state of the Server:

	- `:pending`: This is the initial state; the Server will attempt to start the underlying Port
	and the libmagic client, then automatically transition to either Available or Crashed.

	- `:available`: This is the default state. In this state the Server is able to accept requests
	and they will be replied in the same order.

	- `:processing`: This is the state the Server will be in if it is processing requests. In this
	state, further requests can still be lodged and they will be processed when the Server is
	available again.

	For proper concurrency, use a process pool like Poolboy, Sbroker, etc.

	- `:recycling`: This is the state the Server will be in, if its underlying C program needs to be
	recycled. This state is triggered whenever the cycle count reaches the defined value as per
	`:recycle_threshold`.

	In this state, the Server is able to accept requests, but they will not be processed until the
	underlying C server program has been started again.
	"""
	@type state :: :starting \| :processing \| :available \| :recycling

	@spec child_spec([start_option()]) :: Supervisor.child_spec()
	@spec start_link([start_option()]) :: :gen_statem.start_ret()
	@spec perform(t(), Majic.target(), timeout()) :: Majic.result()
	@spec status(t(), timeout()) :: {:ok, Status.t()} \| {:error, term()}
	@spec stop(t(), term(), timeout()) :: :ok

	@doc """
	Returns the default Child Specification for this Server for use in Supervisors.

	You can override this with `Supervisor.child_spec/2` as required.
	"""
	def child_spec(options) do
	%{
	id: __MODULE__,
	start: {__MODULE__, :start_link, [options]},
	type: :worker,
	restart: :permanent,
	shutdown: 500
	}
	end

	@doc """
	Starts a new Server.

	See `t:option/0` for further details.
	"""
	def start_link(options) do
	{name, options} = Keyword.pop(options, :name)

	case name do
	nil -> :gen_statem.start_link(__MODULE__, options, [])
	name when is_atom(name) -> :gen_statem.start_link({:local, name}, __MODULE__, options, [])
	{:global, _} -> :gen_statem.start_link(name, __MODULE__, options, [])
	{:via, _, _} -> :gen_statem.start_link(name, __MODULE__, options, [])
	{:local, _} -> :gen_statem.start_link(name, __MODULE__, options, [])
	end
	end

	@doc """
	Determines the type of the file provided.
	"""
	def perform(server_ref, path, timeout \\ @process_timeout) do
	case :gen_statem.call(server_ref, {:perform, path}, timeout) do
	{:ok, %Result{} = result} -> {:ok, result}
	{:error, reason} -> {:error, reason}
	end
	end

	@doc """
	Reloads a Server with a new set of databases.
	"""
	def reload(server_ref, database_patterns \\ nil, timeout \\ @process_timeout) do
	:gen_statem.call(server_ref, {:reload, database_patterns}, timeout)
	end

	@doc """
	Same as `reload/2,3` but with a full restart of the underlying C port.
	"""
	def recycle(server_ref, database_patterns \\ nil, timeout \\ @process_timeout) do
	:gen_statem.call(server_ref, {:recycle, database_patterns}, timeout)
	end

	@doc """
	Returns status of the Server.
	"""
	def status(server_ref, timeout \\ @process_timeout) do
	:gen_statem.call(server_ref, :status, timeout)
	end

	@doc """
	Stops the Server with reason `:normal` and timeout `:infinity`.
	"""
	def stop(server_ref) do
	:gen_statem.stop(server_ref)
	end

	@doc """
	Stops the Server with the specified reason and timeout.
	"""
	def stop(server_ref, reason, timeout) do
	:gen_statem.stop(server_ref, reason, timeout)
	end

	@impl :gen_statem
	def init(options) do
	import Majic.Config

	data = %Data{
	port_name: get_port_name(),
	database_patterns: Keyword.get(options, :database_patterns),
	port_options: get_port_options(options),
	startup_timeout: get_startup_timeout(options),
	process_timeout: get_process_timeout(options),
	recycle_threshold: get_recycle_threshold(options)
	}

	{:ok, :starting, data}
	end

	@impl :gen_statem
	def callback_mode do
	[:state_functions, :state_enter]
	end

	@doc false
	def starting(:enter, _, %{port: nil} = data) do
	port = Port.open(data.port_name, data.port_options)
	{:keep_state, %{data \| port: port}, data.startup_timeout}
	end

	@doc false
	def starting(:enter, _, data) do
	{:keep_state_and_data, data.startup_timeout}
	end

	@doc false
	def starting({:call, from}, :status, data) do
	handle_status_call(from, :starting, data)
	end

	@doc false
	def starting({:call, _from}, {:perform, _path}, _data) do
	{:keep_state_and_data, :postpone}
	end

	@doc false
	def starting(:info, {port, {:data, ready}}, %{port: port} = data) do
	case :erlang.binary_to_term(ready) do
	:ready -> {:next_state, :loading, data}
	end
	end

	@doc false
	def starting(:info, {port, {:exit_status, code}}, %{port: port} = data) do
	error =
	case code do
	1 -> :bad_db
	2 -> :ei_error
	3 -> :ei_bad_term
	4 -> :magic_error
	code -> {:unexpected_error, code}
	end

	{:stop, {:error, error}, data}
	end

	@doc false
	def loading(:enter, _old_state, data) do
	databases =
	Enum.flat_map(List.wrap(data.database_patterns \|\| @database_patterns), fn
	:default -> [:default]
	pattern -> Path.wildcard(pattern)
	end)

	if databases == [] do
	{:stop, {:error, :no_databases_to_load}, data}
	else
	{:keep_state, {databases, data}, {:state_timeout, 0, :load}}
	end
	end

	@doc false
	def loading(:state_timeout, :load_timeout, {[database \| _], data}) do
	{:stop, {:error, {:database_loading_timeout, database}}, data}
	end

	@doc false
	def loading(:state_timeout, :load, {[], data}) do
	{:next_state, :available, data}
	end

	@doc false
	def loading(:state_timeout, :load, {[database \| _databases], data} = state) do
	command =
	case database do
	- :default -> {:add_default_database, nil}
	- path -> {:add_database, path}
	+ :default -> {:add_database, :default}
	+ path when is_binary(path) -> {:add_database, path}
	end

	send(data.port, command)
	{:keep_state, state, {:state_timeout, data.startup_timeout, :load_timeout}}
	end

	@doc false
	def loading(:info, {port, {:data, response}}, {[database \| databases], %{port: port} = data}) do
	case :erlang.binary_to_term(response) do
	{:ok, :loaded} ->
	{:keep_state, {databases, data}, {:state_timeout, 0, :load}}

	{:error, :not_loaded} ->
	{:stop, {:error, {:database_load_failed, database}}, data}
	end
	end

	@doc false
	def loading({:call, from}, :status, {_, data}) do
	handle_status_call(from, :loading, data)
	end

	@doc false
	def loading({:call, _from}, {:perform, _path}, _data) do
	{:keep_state_and_data, :postpone}
	end

	@doc false
	def available(:enter, _old_state, %{request: {:reload, from, _}}) do
	response = {:reply, from, :ok}
	{:keep_state_and_data, response}
	end

	@doc false
	def available(:enter, _old_state, %{request: nil}) do
	:keep_state_and_data
	end

	@doc false
	def available({:call, from}, {:perform, path}, data) do
	data = %{data \| cycles: data.cycles + 1, request: {path, from, :erlang.now()}}

	arg =
	case path do
	path when is_binary(path) -> {:file, path}
	# Truncate to 50 bytes
	{:bytes, <<bytes::binary-size(50), _::binary>>} -> {:bytes, bytes}
	{:bytes, bytes} -> {:bytes, bytes}
	end

	send(data.port, arg)
	{:next_state, :processing, data}
	end

	@doc false
	def available({:call, from}, {:reload, databases}, data) do
	send(data.port, {:reload, :reload})

	{:next_state, :starting,
	%{
	data
	\| database_patterns: databases \|\| data.database_patterns,
	request: {:reload, from, :reload}
	}}
	end

	@doc false
	def available({:call, from}, {:recycle, databases}, data) do
	{:next_state, :recycling,
	%{
	data
	\| database_patterns: databases \|\| data.database_patterns,
	request: {:reload, from, :recycle}
	}}
	end

	@doc false
	def available({:call, from}, :status, data) do
	handle_status_call(from, :available, data)
	end

	@doc false
	def processing(:enter, _old_state, %{request: {_path, _from, _time}} = data) do
	{:keep_state_and_data, data.process_timeout}
	end

	@doc false
	def processing({:call, _from}, {:perform, _path}, _data) do
	{:keep_state_and_data, :postpone}
	end

	@doc false
	def processing({:call, from}, :status, data) do
	handle_status_call(from, :processing, data)
	end

	@doc false
	def processing(:state_timeout, _, %{request: {_, from, _}} = data) do
	response = {:reply, from, {:error, :timeout}}
	{:next_state, :recycling, %{data \| request: nil}, [response, :hibernate]}
	end

	@doc false
	def processing(:info, {port, {:data, response}}, %{port: port, request: {_, from, _}} = data) do
	response = {:reply, from, handle_response(response)}
	next_state = (data.cycles >= data.recycle_threshold && :recycling) \|\| :available
	{:next_state, next_state, %{data \| request: nil}, [response, :hibernate]}
	end

	@doc false
	def recycling(:enter, _, %{port: port} = data) when is_port(port) do
	send(data.port, {:stop, :recycle})
	{:keep_state_and_data, {:state_timeout, data.startup_timeout, :stop}}
	end

	@doc false
	def recycling({:call, _from}, {:perform, _path}, _data) do
	{:keep_state_and_data, :postpone}
	end

	@doc false
	def recycling({:call, from}, :status, data) do
	handle_status_call(from, :recycling, data)
	end

	@doc false
	# In case of timeout, force close.
	def recycling(:state_timeout, :stop, data) do
	Kernel.send(data.port, {self(), :close})
	{:keep_state_and_data, {:state_timeout, data.startup_timeout, :close}}
	end

	@doc false
	def recycling(:state_timeout, :close, data) do
	{:stop, {:error, :port_close_failed}, data}
	end

	@doc false
	def recycling(:info, {port, :closed}, %{port: port} = data) do
	{:next_state, :starting, %{data \| port: nil, cycles: 0}}
	end

	@doc false
	def recycling(:info, {port, {:exit_status, _}}, %{port: port} = data) do
	{:next_state, :starting, %{data \| port: nil, cycles: 0}}
	end

	@doc false
	@impl :gen_statem
	def terminate(_, _, %{port: port}) do
	Kernel.send(port, {self(), :close})
	end

	@doc false
	def terminate(_, _, _) do
	:ok
	end

	defp send(port, command) do
	Kernel.send(port, {self(), {:command, :erlang.term_to_binary(command)}})
	end

	@errnos %{
	2 => :enoent,
	13 => :eaccess,
	20 => :enotdir,
	12 => :enomem,
	24 => :emfile,
	36 => :enametoolong
	}
	@errno Map.keys(@errnos)

	defp handle_response(data) do
	case :erlang.binary_to_term(data) do
	{:ok, {mime_type, encoding, content}} -> {:ok, Result.build(mime_type, encoding, content)}
	{:error, {errno, _}} when errno in @errno -> {:error, @errnos[errno]}
	{:error, {errno, string}} -> {:error, "#{errno}: #{string}"}
	{:error, _} = error -> error
	end
	end

	defp handle_status_call(from, state, data) do
	response = {:ok, %__MODULE__.Status{state: state, cycles: data.cycles}}
	{:keep_state_and_data, {:reply, from, response}}
	end
	end
	diff --git a/src/libmagic_port.c b/src/libmagic_port.c
	index f992da9..a6c5afb 100644
	--- a/src/libmagic_port.c
	+++ b/src/libmagic_port.c
	@@ -1,457 +1,440 @@
	//
	// libmagic_port: The Sorcerer’s Apprentice
	//
	// To use this program, compile it with dynamically linked libmagic, as mirrored
	// at https://github.com/file/file. You may install it with apt-get,
	// yum or brew. Refer to the Makefile for further reference.
	//
	// This program is designed to run interactively as a backend daemon to the
	// GenMagic library.
	//
	// Communication is done over STDIN/STDOUT as binary packets of 2 bytes length
	// plus X bytes payload, where the payload is an erlang term encoded with
	// :erlang.term_to_binary/1 and decoded with :erlang.binary_to_term/1.
	//
	// Once the program is ready, it sends the `:ready` atom.
	//
	// It is then up to the Erlang side to load databases, by sending messages:
	-// - `{:add_database, path}`
	-// - `{:add_default_database, _}`
	+// - `{:add_database, :default \| path}`
	//
	// If the requested database have been loaded, an `{:ok, :loaded}` message will
	// follow. Otherwise, the process will exit (exit code 1).
	//
	// Commands are sent to the program STDIN as an erlang term of `{Operation,
	// Argument}`, and response of `{:ok \| :error, Response}`.
	//
	// The program may exit with the following exit codes:
	// - 1 if libmagic handles could not be opened,
	// - 2 if something went wrong with ei_*,
	// - 3 if you sent invalid term format,
	// - 255 if the loop exited unexpectedly.
	//
	// Invalid packets will cause the program to exit (exit code 3). This will
	// happen if your Erlang Term format doesn't match the version the program has
	// been compiled with.
	//
	// Commands:
	// {:reload, _} :: :ready
	-// {:add_database, String.t()} :: {:ok, _} \| {:error, _}
	-// {:add_default_database, _} :: {:ok, _} \| {:error, _}
	+// {:add_database, :default \| String.t()} :: {:ok, _} \| {:error, _}
	// {:file, path :: String.t()} :: {:ok, {type, encoding, name}} \| {:error,
	// :badarg} \| {:error, {errno :: integer(), String.t()}}
	// {:bytes, binary()} :: same as :file
	// {:stop, reason :: atom()} :: exit 0

	#include <arpa/inet.h>
	#include <ei.h>
	#include <errno.h>
	#include <getopt.h>
	#include <libgen.h>
	#include <magic.h>
	#include <stdarg.h>
	#include <stdbool.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <string.h>
	#include <sys/stat.h>
	#include <sys/types.h>
	#include <unistd.h>

	#define ERROR_OK 0
	#define ERROR_MAGIC 1
	#define ERROR_EI 2
	#define ERROR_BAD_TERM 3

	// We use a bigger than possible valid command length (around 4111 bytes) to
	// allow more precise errors when using too long paths.
	#define COMMAND_LEN 8000
	#define COMMAND_BUFFER_SIZE COMMAND_LEN + 1

	#define MAGIC_FLAGS_COMMON (MAGIC_CHECK \| MAGIC_ERROR)
	magic_t magic_setup(int flags);

	#define EI_ENSURE(result) \
	do { \
	if (result != 0) { \
	fprintf(stderr, "EI ERROR, line: %d", __LINE__); \
	exit(ERROR_EI); \
	} \
	} while (0);

	typedef char byte;

	void setup_environment();
	void magic_close_all();
	void magic_open_all();
	int magic_load_all(char *path);
	-int process_command(uint16_t len, byte *buf);
	+void process_command(uint16_t len, byte *buf);
	+void process_command_file(byte buf, int index, ei_x_buff result);
	+void process_command_bytes(byte buf, int index, ei_x_buff result);
	+void process_command_load(byte buf, int index, ei_x_buff result);
	void process_file(char path, ei_x_buff result);
	void process_bytes(char bytes, int size, ei_x_buff result);
	+void process_load(ei_x_buff result, char path);
	+void send_and_free(ei_x_buff *result);
	size_t read_cmd(byte *buf);
	size_t write_cmd(byte *buf, size_t len);
	void error(ei_x_buff result, const char error);
	void handle_magic_error(magic_t handle, int errn, ei_x_buff *result);
	void fdseek(uint16_t count);

	static magic_t magic_mime_type; // MAGIC_MIME_TYPE
	static magic_t magic_mime_encoding; // MAGIC_MIME_ENCODING
	static magic_t magic_type_name; // MAGIC_NONE

	bool magic_loaded = false;

	int main(int argc, char **argv) {
	EI_ENSURE(ei_init());
	setup_environment();
	magic_open_all();

	byte buf[COMMAND_BUFFER_SIZE];
	uint16_t len;
	while ((len = read_cmd(buf)) > 0) {
	process_command(len, buf);
	}

	return 255;
	}

	-int process_command(uint16_t len, byte *buf) {
	+void process_command(uint16_t len, byte *buf) {
	ei_x_buff result;
	char atom[128];
	- int index, version, arity, termtype, termsize;
	+ int index, version, arity;
	index = 0;

	// Initialize result
	EI_ENSURE(ei_x_new_with_version(&result));
	EI_ENSURE(ei_x_encode_tuple_header(&result, 2));

	- if (len >= COMMAND_LEN) {
	- error(&result, "badarg");
	- return 1;
	- }
	+ if (len >= COMMAND_LEN)
	+ return error(&result, "badarg");

	- if (ei_decode_version(buf, &index, &version) != 0) {
	+ if (ei_decode_version(buf, &index, &version) != 0)
	exit(ERROR_BAD_TERM);
	- }

	- if (ei_decode_tuple_header(buf, &index, &arity) != 0) {
	- error(&result, "badarg");
	- return 1;
	- }
	+ if (ei_decode_tuple_header(buf, &index, &arity) != 0)
	+ return error(&result, "badarg");

	- if (arity != 2) {
	- error(&result, "badarg");
	- return 1;
	- }
	+ if (arity != 2)
	+ return error(&result, "badarg");

	- if (ei_decode_atom(buf, &index, atom) != 0) {
	- error(&result, "badarg");
	- return 1;
	- }
	+ if (ei_decode_atom(buf, &index, atom) != 0)
	+ return error(&result, "badarg");

	// {:file, path}
	- if (strlen(atom) == 4 && strncmp(atom, "file", 4) == 0) {
	- if (magic_loaded) {
	- char path[4097];
	- ei_get_type(buf, &index, &termtype, &termsize);
	-
	- if (termtype == ERL_BINARY_EXT) {
	- if (termsize < 4096) {
	- long bin_length;
	- EI_ENSURE(ei_decode_binary(buf, &index, path, &bin_length));
	- path[termsize] = '\0';
	- process_file(path, &result);
	- } else {
	- error(&result, "enametoolong");
	- return 1;
	- }
	- } else {
	- error(&result, "badarg");
	- return 1;
	- }
	- } else {
	- error(&result, "magic_database_not_loaded");
	- return 1;
	- }
	- // {:bytes, bytes}
	- } else if (strlen(atom) == 5 && strncmp(atom, "bytes", 5) == 0) {
	- if (magic_loaded) {
	- int termtype;
	- int termsize;
	- char bytes[51];
	- EI_ENSURE(ei_get_type(buf, &index, &termtype, &termsize));
	-
	- if (termtype == ERL_BINARY_EXT && termsize < 51) {
	- long bin_length;
	- EI_ENSURE(ei_decode_binary(buf, &index, bytes, &bin_length));
	- bytes[termsize] = '\0';
	- process_bytes(bytes, termsize, &result);
	- } else {
	- error(&result, "badarg");
	- return 1;
	- }
	- } else {
	- error(&result, "magic_database_not_loaded");
	- return 1;
	- }
	- // {:add_database, path}
	- } else if (strlen(atom) == 12 && strncmp(atom, "add_database", 12) == 0) {
	- char path[4097];
	- ei_get_type(buf, &index, &termtype, &termsize);
	-
	- if (termtype == ERL_BINARY_EXT) {
	- if (termsize < 4096) {
	- long bin_length;
	- EI_ENSURE(ei_decode_binary(buf, &index, path, &bin_length));
	- path[termsize] = '\0';
	- if (magic_load_all(path) == 0) {
	- EI_ENSURE(ei_x_encode_atom(&result, "ok"));
	- EI_ENSURE(ei_x_encode_atom(&result, "loaded"));
	- } else {
	- EI_ENSURE(ei_x_encode_atom(&result, "error"));
	- EI_ENSURE(ei_x_encode_atom(&result, "not_loaded"));
	- }
	- } else {
	- error(&result, "enametoolong");
	- return 1;
	- }
	- } else {
	- error(&result, "badarg");
	- return 1;
	- }
	- // {:add_default_database, _}
	- } else if (strlen(atom) == 20 &&
	- strncmp(atom, "add_default_database", 20) == 0) {
	- if (magic_load_all(NULL) == 0) {
	- EI_ENSURE(ei_x_encode_atom(&result, "ok"));
	- EI_ENSURE(ei_x_encode_atom(&result, "loaded"));
	- } else {
	- EI_ENSURE(ei_x_encode_atom(&result, "error"));
	- EI_ENSURE(ei_x_encode_atom(&result, "not_loaded"));
	- }
	- // {:reload, _}
	- } else if (strlen(atom) == 6 && strncmp(atom, "reload", 6) == 0) {
	- magic_open_all();
	- return 0;
	+ if (strlen(atom) == 4 && strcmp(atom, "file") == 0)
	+ return process_command_file(buf, index, &result);
	+
	+ // {:bytes, bytes}
	+ if (strlen(atom) == 5 && strcmp(atom, "bytes") == 0)
	+ return process_command_bytes(buf, index, &result);
	+
	+ // {:add_database, path}
	+ if (strlen(atom) == 12 && strcmp(atom, "add_database") == 0)
	+ return process_command_load(buf, index, &result);
	+
	+ // {:reload, _}
	+ if (strlen(atom) == 6 && strcmp(atom, "reload") == 0)
	+ return magic_open_all();
	+
	// {:stop, _}
	- } else if (strlen(atom) == 4 && strncmp(atom, "stop", 4) == 0) {
	+ if (strlen(atom) == 4 && strcmp(atom, "stop") == 0)
	exit(ERROR_OK);
	- // badarg
	- } else {
	- error(&result, "badarg");
	- return 1;
	+
	+ error(&result, "badarg");
	+}
	+
	+void process_command_file(byte buf, int index, ei_x_buff result) {
	+ int termtype, termsize;
	+ char path[4097];
	+ long bin_length;
	+
	+ if (!magic_loaded)
	+ return error(result, "magic_database_not_loaded");
	+
	+ ei_get_type(buf, &index, &termtype, &termsize);
	+
	+ if (termtype != ERL_BINARY_EXT)
	+ return error(result, "badarg");
	+
	+ if (termsize > 4096)
	+ return error(result, "enametoolong");
	+
	+ EI_ENSURE(ei_decode_binary(buf, &index, path, &bin_length));
	+ path[termsize] = '\0';
	+ process_file(path, result);
	+}
	+
	+void process_command_bytes(byte buf, int index, ei_x_buff result) {
	+ if (!magic_loaded)
	+ return error(result, "magic_database_not_loaded");
	+
	+ int termtype, termsize;
	+ long bin_length;
	+ char bytes[51];
	+ EI_ENSURE(ei_get_type(buf, &index, &termtype, &termsize));
	+
	+ if (termtype != ERL_BINARY_EXT)
	+ return error(result, "badarg");
	+
	+ if (termsize > 50)
	+ return error(result, "toolong");
	+
	+ EI_ENSURE(ei_decode_binary(buf, &index, bytes, &bin_length));
	+ bytes[termsize] = '\0';
	+ process_bytes(bytes, termsize, result);
	+}
	+
	+void process_command_load(byte buf, int index, ei_x_buff result) {
	+ char path[4097];
	+ int termtype, termsize;
	+ ei_get_type(buf, &index, &termtype, &termsize);
	+
	+ if (termtype == ERL_BINARY_EXT) {
	+ if (termsize > 4096)
	+ return error(result, "enametoolong");
	+
	+ long bin_length;
	+ EI_ENSURE(ei_decode_binary(buf, &index, path, &bin_length));
	+ path[termsize] = '\0';
	+ return process_load(result, path);
	}

	- write_cmd(result.buff, result.index);
	+ if (termtype == ERL_ATOM_EXT) {
	+ EI_ENSURE(ei_decode_atom(buf, &index, path));
	+ if (strlen(path) == 7 && strcmp(path, "default") == 0)
	+ return process_load(result, NULL);
	+ }

	- EI_ENSURE(ei_x_free(&result));
	- return 0;
	+ error(result, "badarg");
	+}
	+
	+void process_load(ei_x_buff result, char path) {
	+ if (magic_load_all(path) == 0) {
	+ EI_ENSURE(ei_x_encode_atom(result, "ok"));
	+ EI_ENSURE(ei_x_encode_atom(result, "loaded"));
	+ } else {
	+ EI_ENSURE(ei_x_encode_atom(result, "error"));
	+ EI_ENSURE(ei_x_encode_atom(result, "not_loaded"));
	+ }
	+ send_and_free(result);
	}

	void setup_environment() { opterr = 0; }

	void magic_close_all() {
	magic_loaded = false;
	if (magic_mime_encoding) {
	magic_close(magic_mime_encoding);
	magic_mime_encoding = NULL;
	}
	if (magic_mime_type) {
	magic_close(magic_mime_type);
	magic_mime_type = NULL;
	}
	if (magic_type_name) {
	magic_close(magic_type_name);
	magic_type_name = NULL;
	}
	}

	void magic_open_all() {
	magic_close_all();
	magic_mime_encoding = magic_open(MAGIC_FLAGS_COMMON \| MAGIC_MIME_ENCODING);
	magic_mime_type = magic_open(MAGIC_FLAGS_COMMON \| MAGIC_MIME_TYPE);
	magic_type_name = magic_open(MAGIC_FLAGS_COMMON \| MAGIC_NONE);

	if (magic_mime_encoding && magic_mime_type && magic_type_name) {
	ei_x_buff ok_buf;
	EI_ENSURE(ei_x_new_with_version(&ok_buf));
	EI_ENSURE(ei_x_encode_atom(&ok_buf, "ready"));
	- write_cmd(ok_buf.buff, ok_buf.index);
	- EI_ENSURE(ei_x_free(&ok_buf));
	- } else {
	- exit(ERROR_MAGIC);
	+ return send_and_free(&ok_buf);
	}
	+
	+ exit(ERROR_MAGIC);
	}

	int magic_load_all(char *path) {
	int res;

	- if ((res = magic_load(magic_mime_encoding, path)) != 0) {
	+ if ((res = magic_load(magic_mime_encoding, path)) != 0)
	return res;
	- }
	- if ((res = magic_load(magic_mime_type, path)) != 0) {
	+ if ((res = magic_load(magic_mime_type, path)) != 0)
	return res;
	- }
	- if ((res = magic_load(magic_type_name, path)) != 0) {
	+ if ((res = magic_load(magic_type_name, path)) != 0)
	return res;
	- }
	+
	magic_loaded = true;
	return 0;
	}

	void process_bytes(char path, int size, ei_x_buff result) {
	const char *mime_type_result = magic_buffer(magic_mime_type, path, size);
	const int mime_type_errno = magic_errno(magic_mime_type);

	- if (mime_type_errno > 0) {
	- handle_magic_error(magic_mime_type, mime_type_errno, result);
	- return;
	- }
	+ if (mime_type_errno > 0)
	+ return handle_magic_error(magic_mime_type, mime_type_errno, result);

	const char *mime_encoding_result =
	magic_buffer(magic_mime_encoding, path, size);
	int mime_encoding_errno = magic_errno(magic_mime_encoding);

	- if (mime_encoding_errno > 0) {
	- handle_magic_error(magic_mime_encoding, mime_encoding_errno, result);
	- return;
	- }
	+ if (mime_encoding_errno > 0)
	+ return handle_magic_error(magic_mime_encoding, mime_encoding_errno, result);

	const char *type_name_result = magic_buffer(magic_type_name, path, size);
	int type_name_errno = magic_errno(magic_type_name);

	- if (type_name_errno > 0) {
	- handle_magic_error(magic_type_name, type_name_errno, result);
	- return;
	- }
	+ if (type_name_errno > 0)
	+ return handle_magic_error(magic_type_name, type_name_errno, result);

	EI_ENSURE(ei_x_encode_atom(result, "ok"));
	EI_ENSURE(ei_x_encode_tuple_header(result, 3));
	EI_ENSURE(
	ei_x_encode_binary(result, mime_type_result, strlen(mime_type_result)));
	EI_ENSURE(ei_x_encode_binary(result, mime_encoding_result,
	strlen(mime_encoding_result)));
	EI_ENSURE(
	ei_x_encode_binary(result, type_name_result, strlen(type_name_result)));
	- return;
	+ send_and_free(result);
	}

	void handle_magic_error(magic_t handle, int errn, ei_x_buff *result) {
	const char *error = magic_error(handle);
	EI_ENSURE(ei_x_encode_atom(result, "error"));
	EI_ENSURE(ei_x_encode_tuple_header(result, 2));
	long errlon = (long)errn;
	EI_ENSURE(ei_x_encode_long(result, errlon));
	EI_ENSURE(ei_x_encode_binary(result, error, strlen(error)));
	- return;
	+ send_and_free(result);
	}

	void process_file(char path, ei_x_buff result) {
	const char *mime_type_result = magic_file(magic_mime_type, path);
	const int mime_type_errno = magic_errno(magic_mime_type);

	- if (mime_type_errno > 0) {
	- handle_magic_error(magic_mime_type, mime_type_errno, result);
	- return;
	- }
	+ if (mime_type_errno > 0)
	+ return handle_magic_error(magic_mime_type, mime_type_errno, result);

	const char *mime_encoding_result = magic_file(magic_mime_encoding, path);
	int mime_encoding_errno = magic_errno(magic_mime_encoding);

	- if (mime_encoding_errno > 0) {
	- handle_magic_error(magic_mime_encoding, mime_encoding_errno, result);
	- return;
	- }
	+ if (mime_encoding_errno > 0)
	+ return handle_magic_error(magic_mime_encoding, mime_encoding_errno, result);

	const char *type_name_result = magic_file(magic_type_name, path);
	int type_name_errno = magic_errno(magic_type_name);

	- if (type_name_errno > 0) {
	- handle_magic_error(magic_type_name, type_name_errno, result);
	- return;
	- }
	+ if (type_name_errno > 0)
	+ return handle_magic_error(magic_type_name, type_name_errno, result);

	EI_ENSURE(ei_x_encode_atom(result, "ok"));
	EI_ENSURE(ei_x_encode_tuple_header(result, 3));
	EI_ENSURE(
	ei_x_encode_binary(result, mime_type_result, strlen(mime_type_result)));
	EI_ENSURE(ei_x_encode_binary(result, mime_encoding_result,
	strlen(mime_encoding_result)));
	EI_ENSURE(
	ei_x_encode_binary(result, type_name_result, strlen(type_name_result)));
	- return;
	+ send_and_free(result);
	}

	// Adapted from https://erlang.org/doc/tutorial/erl_interface.html
	// Changed `read_cmd`, the original one was buggy given some length (due to
	// endinaness).
	// TODO: Check if `write_cmd` exhibits the same issue.
	size_t read_exact(byte *buf, size_t len) {
	int i, got = 0;

	do {
	if ((i = read(0, buf + got, len - got)) <= 0) {
	return (i);
	}
	got += i;
	} while (got < len);

	return (len);
	}

	size_t write_exact(byte *buf, size_t len) {
	int i, wrote = 0;

	do {
	if ((i = write(1, buf + wrote, len - wrote)) <= 0)
	return (i);
	wrote += i;
	} while (wrote < len);

	return (len);
	}

	size_t read_cmd(byte *buf) {
	int i;
	if ((i = read(0, buf, sizeof(uint16_t))) <= 0) {
	return (i);
	}
	uint16_t len16 = (uint16_t )buf;
	len16 = ntohs(len16);

	// Buffer isn't large enough: just return possible len, without reading.
	// Up to the caller of verifying the size again and return an error.
	// buf left unchanged, stdin emptied of X bytes.
	if (len16 > COMMAND_LEN) {
	fdseek(len16);
	return len16;
	}

	return read_exact(buf, len16);
	}

	size_t write_cmd(byte *buf, size_t len) {
	byte li;

	li = (len >> 8) & 0xff;
	write_exact(&li, 1);

	li = len & 0xff;
	write_exact(&li, 1);

	return write_exact(buf, len);
	}

	+void send_and_free(ei_x_buff *result) {
	+ write_cmd(result->buff, result->index);
	+ EI_ENSURE(ei_x_free(result));
	+}
	+
	void error(ei_x_buff result, const char error) {
	EI_ENSURE(ei_x_encode_atom(result, "error"));
	EI_ENSURE(ei_x_encode_atom(result, error));
	- write_cmd(result->buff, result->index);
	- EI_ENSURE(ei_x_free(result));
	+ send_and_free(result);
	}

	void fdseek(uint16_t count) {
	int i = 0;
	while (i < count) {
	getchar();
	i += 1;
	}
	}
	diff --git a/test/majic/port_test.exs b/test/majic/port_test.exs
	index 931d913..8f95c6e 100644
	--- a/test/majic/port_test.exs
	+++ b/test/majic/port_test.exs
	@@ -1,204 +1,204 @@
	defmodule Majic.PortTest do
	use Majic.MagicCase

	@tmp_path "/tmp/testgenmagicx"
	require Logger

	test "sends ready" do
	port = Port.open(Majic.Config.get_port_name(), Majic.Config.get_port_options([]))
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready(port)
	end

	test "errors with non existent database with an error" do
	opts = [:use_stdio, :binary, :exit_status, {:packet, 2}, {:args, []}]
	port = Port.open(Majic.Config.get_port_name(), opts)
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready(port)

	send(
	port,
	{self(), {:command, :erlang.term_to_binary({:add_database, "/somewhere/nowhere"})}}
	)

	assert_receive {^port, {:data, data}}
	assert {:error, :not_loaded} == :erlang.binary_to_term(data)
	end

	test "loads default database" do
	opts = [:use_stdio, :binary, :exit_status, {:packet, 2}, {:args, []}]
	port = Port.open(Majic.Config.get_port_name(), opts)
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready(port)

	send(
	port,
	- {self(), {:command, :erlang.term_to_binary({:add_default_database, nil})}}
	+ {self(), {:command, :erlang.term_to_binary({:add_database, :default})}}
	)

	assert_receive {^port, {:data, data}}
	assert {:ok, :loaded} == :erlang.binary_to_term(data)
	end

	test "reloads" do
	opts = [:use_stdio, :binary, :exit_status, {:packet, 2}, {:args, []}]
	port = Port.open(Majic.Config.get_port_name(), opts)
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready_and_init_default(port)

	send(port, {self(), {:command, :erlang.term_to_binary({:reload, :reload})}})

	assert_ready(port)
	end

	test "errors when no database loaded" do
	opts = [:use_stdio, :binary, :exit_status, {:packet, 2}, {:args, []}]
	port = Port.open(Majic.Config.get_port_name(), opts)
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready(port)

	send(port, {self(), {:command, :erlang.term_to_binary({:bytes, "hello world"})}})
	assert_receive {^port, {:data, data}}
	assert {:error, :magic_database_not_loaded} = :erlang.binary_to_term(data)
	refute_receive _
	end

	test "stops" do
	port = Port.open(Majic.Config.get_port_name(), Majic.Config.get_port_options([]))
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready_and_init_default(port)
	send(port, {self(), {:command, :erlang.term_to_binary({:stop, :stop})}})
	assert_receive {^port, {:exit_status, 0}}
	end

	describe "port" do
	setup do
	port = Port.open(Majic.Config.get_port_name(), Majic.Config.get_port_options([]))
	on_exit(fn -> send(port, {self(), :close}) end)
	assert_ready_and_init_default(port)
	%{port: port}
	end

	test "exits with badly formatted erlang terms", %{port: port} do
	send(port, {self(), {:command, "i forgot to term_to_binary!!"}})
	assert_receive {^port, {:exit_status, 3}}
	end

	test "errors with wrong command", %{port: port} do
	send(port, {self(), {:command, :erlang.term_to_binary(:wrong)}})
	assert_receive {^port, {:data, data}}
	assert {:error, :badarg} = :erlang.binary_to_term(data)
	refute_receive _

	send(port, {self(), {:command, :erlang.term_to_binary({:file, 42})}})
	assert_receive {^port, {:data, data}}
	assert {:error, :badarg} = :erlang.binary_to_term(data)
	refute_receive _

	send(port, {self(), {:command, :erlang.term_to_binary("more wrong")}})
	assert_receive {^port, {:data, data}}
	assert {:error, :badarg} = :erlang.binary_to_term(data)
	refute_receive _

	send(port, {self(), {:command, :erlang.term_to_binary({"no", "no"})}})
	assert_receive {^port, {:data, data}}
	assert {:error, :badarg} = :erlang.binary_to_term(data)
	refute_receive _
	end

	test "file works", %{port: port} do
	send(port, {self(), {:command, :erlang.term_to_binary({:file, Path.expand("Makefile")})}})
	assert_receive {^port, {:data, data}}
	assert {:ok, _} = :erlang.binary_to_term(data)
	end

	test "bytes works", %{port: port} do
	send(port, {self(), {:command, :erlang.term_to_binary({:bytes, "some bytes!"})}})
	assert_receive {^port, {:data, data}}
	assert {:ok, _} = :erlang.binary_to_term(data)
	end

	test "fails with non existent file", %{port: port} do
	send(port, {self(), {:command, :erlang.term_to_binary({:file, "/path/to/nowhere"})}})
	assert_receive {^port, {:data, data}}
	assert {:error, _} = :erlang.binary_to_term(data)
	end

	test "works with big file path", %{port: port} do
	# Test with longest valid path.
	{dir, bigfile} = too_big(@tmp_path, "/a")

	case File.mkdir_p(dir) do
	:ok ->
	File.touch!(bigfile)
	on_exit(fn -> File.rm_rf!(@tmp_path) end)
	send(port, {self(), {:command, :erlang.term_to_binary({:file, bigfile})}})
	assert_receive {^port, {:data, data}}
	assert {:ok, _} = :erlang.binary_to_term(data)
	refute_receive _

	# This path should be long enough for buffers, but larger than a valid path name.
	# Magic will return an errno 36.
	file = @tmp_path <> String.duplicate("a", 256)
	send(port, {self(), {:command, :erlang.term_to_binary({:file, file})}})
	assert_receive {^port, {:data, data}}
	assert {:error, {36, _}} = :erlang.binary_to_term(data)
	refute_receive _
	# Theses filename should be too big for the path buffer.
	file = bigfile <> "aaaaaaaaaa"
	send(port, {self(), {:command, :erlang.term_to_binary({:file, file})}})
	assert_receive {^port, {:data, data}}
	assert {:error, :enametoolong} = :erlang.binary_to_term(data)
	refute_receive _
	# This call should be larger than the COMMAND_BUFFER_SIZE. Ensure nothing bad happens!
	file = String.duplicate(bigfile, 4)
	send(port, {self(), {:command, :erlang.term_to_binary({:file, file})}})
	assert_receive {^port, {:data, data}}
	assert {:error, :badarg} = :erlang.binary_to_term(data)
	refute_receive _
	# We re-run a valid call to ensure the buffer/... haven't been corrupted in port land.
	send(port, {self(), {:command, :erlang.term_to_binary({:file, bigfile})}})
	assert_receive {^port, {:data, data}}
	assert {:ok, _} = :erlang.binary_to_term(data)
	refute_receive _

	{:error, :enametoolong} ->
	Logger.info(
	"Skipping test, operating system does not support max POSIX length for directories"
	)

	:ignore
	end
	end
	end

	def assert_ready(port) do
	assert_receive {^port, {:data, data}}
	assert :ready == :erlang.binary_to_term(data)
	end

	def assert_ready_and_init_default(port) do
	assert_receive {^port, {:data, data}}
	assert :ready == :erlang.binary_to_term(data)
	- send(port, {self(), {:command, :erlang.term_to_binary({:add_default_database, nil})}})
	+ send(port, {self(), {:command, :erlang.term_to_binary({:add_database, :default})}})
	assert_receive {^port, {:data, data}}
	assert {:ok, _} = :erlang.binary_to_term(data)
	end

	def too_big(path, filename, limit \\ 4095) do
	last_len = byte_size(filename)
	path_len = byte_size(path)
	needed = limit - (last_len + path_len)
	extra = make_too_big(needed, "")
	{path <> extra, path <> extra <> filename}
	end

	def make_too_big(needed, acc) when needed <= 255 do
	acc <> "/" <> String.duplicate("a", needed - 1)
	end

	def make_too_big(needed, acc) do
	acc = acc <> "/" <> String.duplicate("a", 254)
	make_too_big(needed - 255, acc)
	end
	end

File Metadata

Mime Type: text/x-diff
Expires: Tue, Nov 26, 4:28 AM (1 d, 9 h)
Storage Engine: blob
Storage Format: Raw Data
Storage Handle: 39953
Default Alt Text: (39 KB)

No OneTemporaryActions

View Options

File Metadata

Event Timeline

No OneTemporary
Actions