Added multi threading
This commit is contained in:
+117
-45
@@ -11,12 +11,41 @@ import multiprocessing
|
|||||||
import time
|
import time
|
||||||
import io
|
import io
|
||||||
import cpuinfo
|
import cpuinfo
|
||||||
|
import queue
|
||||||
|
import threading
|
||||||
|
import time
|
||||||
|
|
||||||
cpu_info = cpuinfo.get_cpu_info()
|
cpu_info = cpuinfo.get_cpu_info()
|
||||||
num_cores = multiprocessing.cpu_count()
|
num_cores = multiprocessing.cpu_count()
|
||||||
print(num_cores)
|
print(num_cores)
|
||||||
|
|
||||||
filelist = []
|
filelist = []
|
||||||
|
exitFlag = 0
|
||||||
|
queueLock = threading.Lock()
|
||||||
|
workQueue = queue.Queue(0)
|
||||||
|
threads = []
|
||||||
|
class myThread (threading.Thread):
|
||||||
|
def __init__(self, threadID, name, q):
|
||||||
|
threading.Thread.__init__(self)
|
||||||
|
self.threadID = threadID
|
||||||
|
self.name = name
|
||||||
|
self.q = q
|
||||||
|
def run(self):
|
||||||
|
print ("Starting " + self.name)
|
||||||
|
process_data(self.name, self.q)
|
||||||
|
print ("Exiting " + self.name)
|
||||||
|
|
||||||
|
def process_data(threadName, q):
|
||||||
|
while not exitFlag:
|
||||||
|
queueLock.acquire()
|
||||||
|
if not workQueue.empty():
|
||||||
|
data = q.get()
|
||||||
|
process_file(data)
|
||||||
|
queueLock.release()
|
||||||
|
print ("%s processing %s" % (threadName, data))
|
||||||
|
else:
|
||||||
|
queueLock.release()
|
||||||
|
time.sleep(1)
|
||||||
|
|
||||||
def sourcedir_filecnt(sourcedir):
|
def sourcedir_filecnt(sourcedir):
|
||||||
### Return the number of files, ending with '.h', in sourcedir - including subdirectories ###
|
### Return the number of files, ending with '.h', in sourcedir - including subdirectories ###
|
||||||
@@ -32,50 +61,53 @@ def sourcedir_filecnt(sourcedir):
|
|||||||
def process_files(sourcedir, destdir):
|
def process_files(sourcedir, destdir):
|
||||||
global filelist
|
global filelist
|
||||||
for f in filelist:
|
for f in filelist:
|
||||||
outfile = ''
|
process_file(f)
|
||||||
inputfile = f
|
|
||||||
encodings = ['utf-8', 'latin-1', 'windows-1250', 'windows-1252', 'ascii',
|
def process_file(data):
|
||||||
'big5', 'big5hkscs', 'cp037', 'cp273', 'cp424', 'cp437', 'cp500',
|
outfile = ''
|
||||||
'cp720', 'cp737', 'cp775', 'cp850', 'cp852', 'cp855', 'cp856',
|
inputfile = data
|
||||||
'cp857', 'cp858', 'cp860', 'cp861', 'cp862', 'cp863', 'cp864', 'cp865',
|
encodings = ['utf-8', 'latin-1', 'windows-1250', 'windows-1252', 'ascii',
|
||||||
'cp866', 'cp869', 'cp874', 'cp875', 'cp932', 'cp949', 'cp950', 'cp1006',
|
'big5', 'big5hkscs', 'cp037', 'cp273', 'cp424', 'cp437', 'cp500',
|
||||||
'cp1026', 'cp1125', 'cp1140', 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254',
|
'cp720', 'cp737', 'cp775', 'cp850', 'cp852', 'cp855', 'cp856',
|
||||||
'cp1255', 'cp1256', 'cp1257', 'cp1258', 'cp65001', 'euc-jp', 'euc-jis-2004',
|
'cp857', 'cp858', 'cp860', 'cp861', 'cp862', 'cp863', 'cp864', 'cp865',
|
||||||
'euc-jisx0213', 'euc-kr', 'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022-jp',
|
'cp866', 'cp869', 'cp874', 'cp875', 'cp932', 'cp949', 'cp950', 'cp1006',
|
||||||
'iso2022-jp-1', 'iso2022-jp-2', 'iso2022-jp-2004', 'iso2022-jp-3',
|
'cp1026', 'cp1125', 'cp1140', 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254',
|
||||||
'iso2022-jp-ext', 'iso2022-kr', 'iso8859-2', 'iso8859-3', 'iso8859-4',
|
'cp1255', 'cp1256', 'cp1257', 'cp1258', 'cp65001', 'euc-jp', 'euc-jis-2004',
|
||||||
'iso8859-5', 'iso8859-6', 'iso8859-7', 'iso8859-8', 'iso8859-9', 'iso8859-10',
|
'euc-jisx0213', 'euc-kr', 'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022-jp',
|
||||||
'iso8859-11', 'iso8859-13', 'iso8859-14', 'iso8859-15', 'iso8859-16', 'johab',
|
'iso2022-jp-1', 'iso2022-jp-2', 'iso2022-jp-2004', 'iso2022-jp-3',
|
||||||
'koi8-r', 'koi8-t', 'koi8-u', 'kz1048', 'mac-cyrillic', 'mac-greek',
|
'iso2022-jp-ext', 'iso2022-kr', 'iso8859-2', 'iso8859-3', 'iso8859-4',
|
||||||
'mac-iceland', 'mac-latin2', 'mac-roman', 'mac-turkish', 'ptcp154',
|
'iso8859-5', 'iso8859-6', 'iso8859-7', 'iso8859-8', 'iso8859-9', 'iso8859-10',
|
||||||
'shift-jis', 'shift-jis-2004', 'shift-jisx0213', 'utf-32', 'utf-32-be',
|
'iso8859-11', 'iso8859-13', 'iso8859-14', 'iso8859-15', 'iso8859-16', 'johab',
|
||||||
'utf-32-le', 'utf-16', 'utf-16-be', 'utf-16-le', 'utf-7', 'utf-8-sig']
|
'koi8-r', 'koi8-t', 'koi8-u', 'kz1048', 'mac-cyrillic', 'mac-greek',
|
||||||
for e in encodings:
|
'mac-iceland', 'mac-latin2', 'mac-roman', 'mac-turkish', 'ptcp154',
|
||||||
try:
|
'shift-jis', 'shift-jis-2004', 'shift-jisx0213', 'utf-32', 'utf-32-be',
|
||||||
fh = io.open(f, 'r', encoding=e)
|
'utf-32-le', 'utf-16', 'utf-16-be', 'utf-16-le', 'utf-7', 'utf-8-sig']
|
||||||
fh.readlines()
|
for e in encodings:
|
||||||
fh.seek(0)
|
try:
|
||||||
except UnicodeDecodeError:
|
fh = io.open(data, 'r', encoding=e)
|
||||||
print('got unicode error with %s , trying different encoding' % e)
|
fh.readlines()
|
||||||
else:
|
fh.seek(0)
|
||||||
print('opening the file with encoding: %s ' % e)
|
except UnicodeDecodeError:
|
||||||
break
|
print('got unicode error with %s , trying different encoding' % e)
|
||||||
print(os.path.basename(f))
|
else:
|
||||||
for lines in fh:
|
print('opening the file with encoding: %s ' % e)
|
||||||
outfile = outfile+lines
|
break
|
||||||
fh.close()
|
print(os.path.basename(data))
|
||||||
outputfile = os.path.splitext(inputfile)[0]+'.inc'
|
for lines in fh:
|
||||||
outputfile = str(outputfile).replace(sourcedir, destdir)
|
outfile = outfile+lines
|
||||||
print(outputfile)
|
fh.close()
|
||||||
if not os.path.exists(os.path.dirname(outputfile)):
|
outputfile = os.path.splitext(inputfile)[0]+'.inc'
|
||||||
try:
|
outputfile = str(outputfile).replace(sourcedir, destdir)
|
||||||
os.makedirs(os.path.dirname(outputfile))
|
print(outputfile)
|
||||||
except OSError as exc: # Guard against race condition
|
if not os.path.exists(os.path.dirname(outputfile)):
|
||||||
if exc.errno != errno.EEXIST:
|
try:
|
||||||
raise
|
os.makedirs(os.path.dirname(outputfile))
|
||||||
newfile = open(outputfile, "w")
|
except OSError as exc: # Guard against race condition
|
||||||
newfile.write(outfile)
|
if exc.errno != errno.EEXIST:
|
||||||
newfile.close()
|
raise
|
||||||
|
newfile = open(outputfile, "w")
|
||||||
|
newfile.write(outfile)
|
||||||
|
newfile.close()
|
||||||
|
|
||||||
def single_thread():
|
def single_thread():
|
||||||
t1 = time.time()
|
t1 = time.time()
|
||||||
@@ -84,10 +116,50 @@ def single_thread():
|
|||||||
process_files(sourcedir, destdir)
|
process_files(sourcedir, destdir)
|
||||||
print('Single thread process time: '+str(time.time()-t1))
|
print('Single thread process time: '+str(time.time()-t1))
|
||||||
|
|
||||||
|
def multi_thread():
|
||||||
|
global filelist
|
||||||
|
global exitFlag
|
||||||
|
|
||||||
|
t1 = time.time()
|
||||||
|
cnt = sourcedir_filecnt(sourcedir)
|
||||||
|
threadList = ["thread 1", "thread 2", "thread 3", "thread 4", "thread 5"]
|
||||||
|
nameList = filelist
|
||||||
|
threadID = 0
|
||||||
|
|
||||||
|
# Create new threads
|
||||||
|
for tName in threadList:
|
||||||
|
thread = myThread(threadID, tName, workQueue)
|
||||||
|
thread.start()
|
||||||
|
threads.append(thread)
|
||||||
|
threadID += 1
|
||||||
|
|
||||||
|
# Fill the queue
|
||||||
|
queueLock.acquire()
|
||||||
|
for word in nameList:
|
||||||
|
workQueue.put(word)
|
||||||
|
queueLock.release()
|
||||||
|
|
||||||
|
# Wait for queue to empty
|
||||||
|
while not workQueue.empty():
|
||||||
|
pass
|
||||||
|
|
||||||
|
# Notify threads it's time to exit
|
||||||
|
exitFlag = 1
|
||||||
|
|
||||||
|
# Wait for all threads to complete
|
||||||
|
for t in threads:
|
||||||
|
t.join()
|
||||||
|
print ("Exiting Main Thread")
|
||||||
|
print('Files in: '+str(cnt))
|
||||||
|
print('Multi thread process time: '+str(time.time()-t1))
|
||||||
|
|
||||||
#sourcedir = 'C:/Users/dksojlg/Documents/gtk+-3.22.26'
|
#sourcedir = 'C:/Users/dksojlg/Documents/gtk+-3.22.26'
|
||||||
sourcedir = '/usr/include'
|
sourcedir = '/usr/include'
|
||||||
#destdir = 'C:/Users/dksojlg/Documents/include'
|
#destdir = 'C:/Users/dksojlg/Documents/include'
|
||||||
destdir = '/data_2/include'
|
destdir = '/data_2/include'
|
||||||
|
|
||||||
print(cpu_info)
|
print(cpu_info)
|
||||||
single_thread() #2543 files - Single thread process time: 32.53886866569519
|
single_thread() #2543 files - Single thread process time: 1.3732633590698242
|
||||||
|
|
||||||
|
multi_thread()
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user