Textserver wiki - New pages [en]

Batch Results Retrieval in Python3

2018-08-24T09:33:13Z

Padro:

<syntaxhighlight lang="python" line="1" >
#!/usr/bin/env python3

import requests
import xml.etree.ElementTree

# set query elements
user = raw_input('TextServer Username: ')
tkid = raw_input('TextServer Job Token ID: ')
outfname = raw_input('Output ZIP file: ')

# Create request
request_data = {'username' : user
'tokenID' : tkid
}

# service URL
url = "http://frodo.lsi.upc.edu:8080/TextWS/textservlet/ws/resultRetrieve"

# Send request and get response
resp = requests.post(url, files=request_data)

# HTTP error, raise exception
if resp.status_code != requests.codes.ok :
resp.raise_for_status()

# no error, save results to output file
outf=open(outfname, 'w+')
print(resp, file=outf)
outf.close()
print "Job finished. Results saved to",outfname
</syntaxhighlight>

Batch Results Retrieval in Python2

2018-08-24T09:29:36Z

Padro: Created page with "<syntaxhighlight lang="python" line="1" > #! /usr/bin/python ######################################################################## # # Example client to retrieve the resu..."

<syntaxhighlight lang="python" line="1" >
#! /usr/bin/python

########################################################################
#
# Example client to retrieve the results of a batch request to TextServer
#
# Output will be a ZIP file containing results for each input file in
# the requested format (XML, json, conll)
#
########################################################################

# import required libraries
import urllib2
# You may need to install "poster" python module for these two:
from poster.encode import multipart_encode
from poster.streaminghttp import register_openers
import xml.etree.ElementTree
import time

# Register the streaming http handlers with urllib2
register_openers()

# set query elements
user = raw_input('TextServer Username: ')
tkid = raw_input('TextServer Job Token ID: ')
outfname = raw_input('Output ZIP file: ')

# service URL
TextServer_URL = "http://frodo.lsi.upc.edu:8080/TextWS/textservlet/ws"

# prepare request to poll for completion and retrieve results
datagen, headers = multipart_encode({'username' : user,
'tokenID' : tkid
})
request = urllib2.Request(TextServer_URL + "/resultRetrieve",
datagen,
headers)

try:
# send request to check for results
print "Polling server for job completion..."
resp = urllib2.urlopen(request).read()

except urllib2.HTTPError, e:
if (e.code == 503 and e.read()[0:8] == "[TS-125]" ) :
# http status 503, textserver code TS-125 means the job is not finished yet.
print "Job not finished yet"
else :
# some actual error happened. abort
print e, "-", e.read()
exit()

# no error, save results to output file
outf=open(outfname, 'w+')
print >>outf, resp
outf.close()
print "Job finished. Results saved to",outfname
</syntaxhighlight>

Python3 Batch Client

2018-08-24T09:27:34Z

Padro:

<syntaxhighlight lang="python" line="1" >
#!/usr/bin/env python3

import requests
import xml.etree.ElementTree

# set query elements
fname = raw_input('Input ZIP file: ')
lang = raw_input('Language: ')
out = raw_input('Output format (xml,json,conll,naf): ')
user = raw_input('TextServer Username: ')
pwd = raw_input('TextServer Password: ')

# Create request
request_data = {'username' : user
'password' : pwd,
'file' : open(fname,"rb"),
'language': lang,
'output': out,
'interactive' : '0' }

# service URL
service = "SERVICENAME"
url = "http://frodo.lsi.upc.edu:8080/TextWS/textservlet/ws/processQuery/"+service

# Send request and get response
resp = requests.post(url, files=request_data)

# HTTP error, raise exception
if resp.status_code != requests.codes.ok :
resp.raise_for_status()

# No error. Server response should include a job tokenID, retrieve it
dom = xml.etree.ElementTree.XML(resp)
tkid = dom.text
print ("Job sumbitted. Token id=",tkid)
</syntaxhighlight>

Python2 Batch Client

2018-08-24T09:23:48Z

<syntaxhighlight lang="python" line="1" >
#! /usr/bin/python

########################################################################
#
# Example client to submit a batch request to TextServer
# SERVICENAME service, and wait for the job to be finished.
#
# Input must be a ZIP file containing one or more text files to analyze
# Output will be a ZIP file containing results for each input file in
# the requested format (XML, json, conll)
#
########################################################################

# import required libraries
import urllib2
# You may need to install "poster" python module for these two:
from poster.encode import multipart_encode
from poster.streaminghttp import register_openers
import xml.etree.ElementTree
import time

# Register the streaming http handlers with urllib2
register_openers()

# set query elements
fname = raw_input('Input ZIP file: ')
lang = raw_input('Language: ')
out = raw_input('Output format (xml,json,conll,naf): ')
user = raw_input('TextServer Username: ')
pwd = raw_input('TextServer Password: ')

# Encode query in a form-data.
# 'headers' contains the necessary Content-Type and Content-Length.
# 'datagen' is a generator object that yields the encoded parameters.
datagen, headers = multipart_encode({'username' : user,
'password' : pwd,
'file' : open(fname,"rb"),
'language' : lang,
'output' : out,
'interactive':'0'
} )
# service URL
TextServer_URL = "http://frodo.lsi.upc.edu:8080/TextWS/textservlet/ws"
service = "SERVICENAME"

# Create the Request object
request = urllib2.Request(TextServer_URL + "/processQuery/" + service,
datagen,
headers)

try:
# Actually do the request, and get the response
resp = urllib2.urlopen(request).read()

except urllib2.HTTPError, e:
# handle connection errors
print e, "-", e.read()
exit()

# Server response should include a job tokenID, retrieve it
dom = xml.etree.ElementTree.XML(resp)
tkid = dom.text
print "Job sumbitted. Token id=",tkid
</syntaxhighlight>

Python3 Interactive Client

2018-08-24T08:55:53Z

Padro:

<syntaxhighlight lang="python" line="1" >
#!/usr/bin/env python3

import requests

# set query elements
text = input('Text to analyze: ')
lang = input('Language: ')
out = input('Output format (xml,json,conll,naf): ')
user = input('TextServer Username: ')
pwd = input('TextServer Password: ')

# Create request
request_data = {'username':user,
'password':pwd,
'text_input':text,
'language':lang,
'output':out,
'interactive':'1' }

# service URL
service = "SERVICENAME"
url = "http://frodo.lsi.upc.edu:8080/TextWS/textservlet/ws/processQuery/"+service

# Send request and get response
resp = requests.post(url, files=request_data)

# HTTP error, raise exception
if resp.status_code != requests.codes.ok :
resp.raise_for_status()

# No error, appropriately process response
# (e.g. parsing XML or JSON, and doing clever stuff with the content)
print(resp.text)
</syntaxhighlight>

Python2 Interactive Client

2018-08-24T08:53:20Z

<syntaxhighlight lang="python" line="1" >
#! /usr/bin/python

########################################################################
#
# Example client to submit an interactive request to TextServer
# SERVICENAME service.
# Input may be a plain text or a text file. No ZIP files.
# Output will be in the requested format (XML, json, conll)
#
########################################################################

# import required libraries
import urllib2
# You may need to install "poster" python module for these two:
from poster.encode import multipart_encode
from poster.streaminghttp import register_openers

# Register the streaming http handlers with urllib2
register_openers()

# set query elements
text = raw_input('Text to analyze: ')
lang = raw_input('Language: ')
out = raw_input('Output format (xml,json,conll,naf): ')
user = raw_input('TextServer Username: ')
pwd = raw_input('TextServer Password: ')

# Encode query in a form-data.
# 'headers' contains the necessary Content-Type and Content-Length.
# 'datagen' is a generator object that yields the encoded parameters.
datagen, headers = multipart_encode({'username':user,
'password':pwd,
'text_input':text,
'language':lang,
'output':out,
'interactive':'1'
} )
# service URL
service = "SERVICENAME"
url = "http://frodo.lsi.upc.edu:8080/TextWS/textservlet/ws/processQuery/"+service

# Create the Request object
request = urllib2.Request(url, datagen, headers)
try:
# Actually do the request, and get the response
resp = urllib2.urlopen(request).read()

except urllib2.HTTPError, e:
# handle connection errors
print e, "-", e.read()
exit()

# No error, appropriately process response
# (e.g. parsing XML or JSON, and doing clever stuff with the content)
print resp
</syntaxhighlight>