A non-blocking read on a subprocess.PIPE in Python

Question

I\'m using the subprocess module to start a subprocess and connect to its output stream (standard output). I want to be able to execute non-blocking reads on its standard ou

Answer 1

why bothering thread&queue? unlike readline(), BufferedReader.read1() wont block waiting for \r\n, it returns ASAP if there is any output coming in.

#!/usr/bin/python
from subprocess import Popen, PIPE, STDOUT
import io

def __main__():
    try:
        p = Popen( ["ping", "-n", "3", "127.0.0.1"], stdin=PIPE, stdout=PIPE, stderr=STDOUT )
    except: print("Popen failed"); quit()
    sout = io.open(p.stdout.fileno(), 'rb', closefd=False)
    while True:
        buf = sout.read1(1024)
        if len(buf) == 0: break
        print buf,

if __name__ == '__main__':
    __main__()

Answer 2

This solution uses the select module to "read any available data" from an IO stream. This function blocks initially until data is available, but then reads only the data that is available and doesn't block further.

Given the fact that it uses the select module, this only works on Unix.

The code is fully PEP8-compliant.

import select


def read_available(input_stream, max_bytes=None):
    """
    Blocks until any data is available, then all available data is then read and returned.
    This function returns an empty string when end of stream is reached.

    Args:
        input_stream: The stream to read from.
        max_bytes (int|None): The maximum number of bytes to read. This function may return fewer bytes than this.

    Returns:
        str
    """
    # Prepare local variables
    input_streams = [input_stream]
    empty_list = []
    read_buffer = ""

    # Initially block for input using 'select'
    if len(select.select(input_streams, empty_list, empty_list)[0]) > 0:

        # Poll read-readiness using 'select'
        def select_func():
            return len(select.select(input_streams, empty_list, empty_list, 0)[0]) > 0

        # Create while function based on parameters
        if max_bytes is not None:
            def while_func():
                return (len(read_buffer) < max_bytes) and select_func()
        else:
            while_func = select_func

        while True:
            # Read single byte at a time
            read_data = input_stream.read(1)
            if len(read_data) == 0:
                # End of stream
                break
            # Append byte to string buffer
            read_buffer += read_data
            # Check if more data is available
            if not while_func():
                break

    # Return read buffer
    return read_buffer

Answer 3

Python 3.4 introduces new provisional API for asynchronous IO -- asyncio module.

The approach is similar to twisted-based answer by @Bryan Ward -- define a protocol and its methods are called as soon as data is ready:

#!/usr/bin/env python3
import asyncio
import os

class SubprocessProtocol(asyncio.SubprocessProtocol):
    def pipe_data_received(self, fd, data):
        if fd == 1: # got stdout data (bytes)
            print(data)

    def connection_lost(self, exc):
        loop.stop() # end loop.run_forever()

if os.name == 'nt':
    loop = asyncio.ProactorEventLoop() # for subprocess' pipes on Windows
    asyncio.set_event_loop(loop)
else:
    loop = asyncio.get_event_loop()
try:
    loop.run_until_complete(loop.subprocess_exec(SubprocessProtocol, 
        "myprogram.exe", "arg1", "arg2"))
    loop.run_forever()
finally:
    loop.close()

See "Subprocess" in the docs.

There is a high-level interface asyncio.create_subprocess_exec() that returns Process objects that allows to read a line asynchroniosly using StreamReader.readline() coroutine (with async/await Python 3.5+ syntax):

#!/usr/bin/env python3.5
import asyncio
import locale
import sys
from asyncio.subprocess import PIPE
from contextlib import closing

async def readline_and_kill(*args):
    # start child process
    process = await asyncio.create_subprocess_exec(*args, stdout=PIPE)

    # read line (sequence of bytes ending with b'\n') asynchronously
    async for line in process.stdout:
        print("got line:", line.decode(locale.getpreferredencoding(False)))
        break
    process.kill()
    return await process.wait() # wait for the child process to exit


if sys.platform == "win32":
    loop = asyncio.ProactorEventLoop()
    asyncio.set_event_loop(loop)
else:
    loop = asyncio.get_event_loop()

with closing(loop):
    sys.exit(loop.run_until_complete(readline_and_kill(
        "myprogram.exe", "arg1", "arg2")))

readline_and_kill() performs the following tasks:

• start subprocess, redirect its stdout to a pipe
• read a line from subprocess' stdout asynchronously
• kill subprocess
• wait for it to exit

Each step could be limited by timeout seconds if necessary.

Answer 4

One solution is to make another process to perform your read of the process, or make a thread of the process with a timeout.

Here's the threaded version of a timeout function:

http://code.activestate.com/recipes/473878/

However, do you need to read the stdout as it's coming in? Another solution may be to dump the output to a file and wait for the process to finish using p.wait().

f = open('myprogram_output.txt','w')
p = subprocess.Popen('myprogram.exe', stdout=f)
p.wait()
f.close()


str = open('myprogram_output.txt','r').read()

Answer 5

I add this problem to read some subprocess.Popen stdout. Here is my non blocking read solution:

import fcntl

def non_block_read(output):
    fd = output.fileno()
    fl = fcntl.fcntl(fd, fcntl.F_GETFL)
    fcntl.fcntl(fd, fcntl.F_SETFL, fl | os.O_NONBLOCK)
    try:
        return output.read()
    except:
        return ""

# Use example
from subprocess import *
sb = Popen("echo test && sleep 1000", shell=True, stdout=PIPE)
sb.kill()

# sb.stdout.read() # <-- This will block
non_block_read(sb.stdout)
'test\n'