reverting to python2
This commit is contained in:
parent
3163720fef
commit
e1fbd87b51
@ -1,12 +1,11 @@
|
|||||||
#!/usr/bin/python3
|
#!/usr/bin/python
|
||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
import json
|
import json
|
||||||
import requests
|
import urllib2
|
||||||
import sys
|
import sys
|
||||||
import host
|
import host
|
||||||
import time
|
import time
|
||||||
import codecs
|
|
||||||
|
|
||||||
BUFFER_SIZE = 500
|
BUFFER_SIZE = 500
|
||||||
LEAVE_OUT = 1 # that does not leave out anything
|
LEAVE_OUT = 1 # that does not leave out anything
|
||||||
@ -14,8 +13,6 @@ LEAVE_OUT = 1 # that does not leave out anything
|
|||||||
address = 'http://'+host.concordia_host
|
address = 'http://'+host.concordia_host
|
||||||
if len(host.concordia_port) > 0:
|
if len(host.concordia_port) > 0:
|
||||||
address += ':'+host.concordia_port
|
address += ':'+host.concordia_port
|
||||||
headers = {"content-type" : "application/json;charset=UTF-8" }
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
def file_len(fname):
|
def file_len(fname):
|
||||||
@ -25,7 +22,10 @@ def file_len(fname):
|
|||||||
return i + 1
|
return i + 1
|
||||||
|
|
||||||
def add_examples(examplesData):
|
def add_examples(examplesData):
|
||||||
response = requests.post(address, data=json.dumps(examplesData, ensure_ascii=False).encode('utf-8'), headers=headers).json()
|
req = urllib2.Request(address)
|
||||||
|
req.add_header('Content-Type', 'application/json')
|
||||||
|
response = json.loads(urllib2.urlopen(req, json.dumps(examplesData), timeout = 3600).read())
|
||||||
|
print(response)
|
||||||
if response['status'] == 'error':
|
if response['status'] == 'error':
|
||||||
raise Exception(response['message'])
|
raise Exception(response['message'])
|
||||||
|
|
||||||
@ -62,10 +62,12 @@ data = {
|
|||||||
'tmLemmatized':True
|
'tmLemmatized':True
|
||||||
}
|
}
|
||||||
|
|
||||||
response = requests.post(address, json=data, headers=headers).json()
|
req = urllib2.Request(address)
|
||||||
|
req.add_header('Content-Type', 'application/json')
|
||||||
|
response = json.loads(urllib2.urlopen(req, json.dumps(data), timeout = 3600).read())
|
||||||
print(response)
|
print(response)
|
||||||
tmId = int(response['newTmId'])
|
tmId = int(response['newTmId'])
|
||||||
print("Added new tm: %d" % tmId)
|
print "Added new tm: %d" % tmId
|
||||||
|
|
||||||
data = {
|
data = {
|
||||||
'operation': 'addSentences',
|
'operation': 'addSentences',
|
||||||
@ -74,7 +76,7 @@ data = {
|
|||||||
|
|
||||||
examples = []
|
examples = []
|
||||||
start = time.time()
|
start = time.time()
|
||||||
with codecs.open(sourceFile, "r", "utf-8", errors='replace') as source_file, codecs.open(lemmatizedSourceFile, "r", "utf-8", errors='replace') as lemmatized_source_file, codecs.open(targetFile, "r", "utf-8", errors='replace') as target_file, open(alignmentsFile) as alignments_file, open(sourceIdsFile) as source_ids_file:
|
with open(sourceFile) as source_file, open(lemmatizedSourceFile) as lemmatized_source_file, open(targetFile) as target_file, open(alignmentsFile) as alignments_file, open(sourceIdsFile) as source_ids_file:
|
||||||
addedCount = 0
|
addedCount = 0
|
||||||
for lineNumber in range(sourceFileLength):
|
for lineNumber in range(sourceFileLength):
|
||||||
if lineNumber % LEAVE_OUT == 0:
|
if lineNumber % LEAVE_OUT == 0:
|
||||||
@ -90,7 +92,7 @@ with codecs.open(sourceFile, "r", "utf-8", errors='replace') as source_file, cod
|
|||||||
data['examples'] = examples
|
data['examples'] = examples
|
||||||
add_examples(data)
|
add_examples(data)
|
||||||
mark = time.time()
|
mark = time.time()
|
||||||
print("Added %d of %d lemmatized examples. Time elapsed: %.4f s, current speed: %.4f examples/second" % (addedCount, totalExamples, mark-start, addedCount/(mark-start)))
|
print "Added %d of %d lemmatized examples. Time elapsed: %.4f s, current speed: %.4f examples/second" % (addedCount, totalExamples, mark-start, addedCount/(mark-start))
|
||||||
examples = []
|
examples = []
|
||||||
|
|
||||||
|
|
||||||
@ -99,15 +101,17 @@ if len(examples) > 0:
|
|||||||
add_examples(data)
|
add_examples(data)
|
||||||
|
|
||||||
end = time.time()
|
end = time.time()
|
||||||
print("Added all %d lemmatized sentences. Time elapsed: %.4f s, overall speed: %.4f sentences/second" % (addedCount, end-start, addedCount/(end-start)))
|
print "Added all %d lemmatized sentences. Time elapsed: %.4f s, overall speed: %.4f sentences/second" % (addedCount, end-start, addedCount/(end-start))
|
||||||
|
|
||||||
print("Generating index...")
|
print "Generating index..."
|
||||||
start = time.time()
|
start = time.time()
|
||||||
data = {
|
data = {
|
||||||
'operation': 'refreshIndex',
|
'operation': 'refreshIndex',
|
||||||
'tmId' : tmId
|
'tmId' : tmId
|
||||||
}
|
}
|
||||||
requests.post(address, json=data, headers=headers)
|
req = urllib2.Request(address)
|
||||||
|
req.add_header('Content-Type', 'application/json')
|
||||||
|
urllib2.urlopen(req, json.dumps(data), timeout = 3600).read()
|
||||||
|
|
||||||
end = time.time()
|
end = time.time()
|
||||||
print("Index regeneration complete. The operation took %.4f s" % (end - start))
|
print "Index regeneration complete. The operation took %.4f s" % (end - start)
|
||||||
|
Loading…
Reference in New Issue
Block a user