rjawor/concordia-server
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

cat corrections

Browse Source
This commit is contained in:
rjawor 2015-10-21 09:02:40 +02:00
parent b8d6484738
commit a3fa732c70
9 changed files with 21 additions and 188 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
cat/index.html_pattern
View File

@ -6,6 +6,21 @@
<meta charset="UTF-8"> <meta charset="UTF-8">
</head> </head>
<body> <body>
<script>
var concordiaUrl = 'http://@concordia_host@:@concordia_port@';
$(document).ready(function() {
$('#searchInput').bind("enterKey",function(e){
searchHandle(@tmid@);
});
$('#searchInput').keyup(function(e){
if(e.keyCode == 13) {
$(this).trigger("enterKey");
}
});
});
</script>
<div id="header"> <div id="header">
</div> </div>
<div id="content"> <div id="content">

13
cat/js/cat.js
View File

@ -1,16 +1,3 @@
var concordiaUrl = 'http://localhost';
$(document).ready(function() {
$('#searchInput').bind("enterKey",function(e){
searchHandle();
});
$('#searchInput').keyup(function(e){
if(e.keyCode == 13) {
$(this).trigger("enterKey");
}
});
});
function searchHandle(tmid) { function searchHandle(tmid) {
var concordiaRequest = { var concordiaRequest = {
operation: 'concordiaSearch', operation: 'concordiaSearch',

4
cat/versions/jrc_enes.cfg
View File

@ -1,5 +1,7 @@
dir@#@jrc_enes dir@#@jrc_enes
tmid@#@1 concordia_host@#@concordia.vm.wmi.amu.edu.pl
concordia_port@#@8800
tmid@#@2
desc@#@Welcome to the interactive Concordia demo. The system finds the longest matches of the pattern sentence in its translation memory. This translation memory is 200 000 sentences taken from English-Spanish corpus of European Law. Please enter an English sentence in the field below and press Enter (or use the search button). This instance of Concordia works best with law sentences, but is very likely to output some results for any English sentence. You can also use predefined samples, simply use the link "show/hide samples" and apply one of the sample sentences. desc@#@Welcome to the interactive Concordia demo. The system finds the longest matches of the pattern sentence in its translation memory. This translation memory is 200 000 sentences taken from English-Spanish corpus of European Law. Please enter an English sentence in the field below and press Enter (or use the search button). This instance of Concordia works best with law sentences, but is very likely to output some results for any English sentence. You can also use predefined samples, simply use the link "show/hide samples" and apply one of the sample sentences.
prompt@#@Enter search pattern (English sentence): prompt@#@Enter search pattern (English sentence):
suggestion@#@Every ship in the European Union must have a crew of 50 or more workers. suggestion@#@Every ship in the European Union must have a crew of 50 or more workers.

4
cat/versions/setimes_hren.cfg
View File

@ -1,5 +1,7 @@
dir@#@setimes_hren dir@#@setimes_hren
tmid@#@2 concordia_host@#@concordia.vm.wmi.amu.edu.pl
concordia_port@#@8800
tmid@#@1
desc@#@Welcome to Concordia. The system finds the longest matches of the pattern sentence in its translation memory. This translation memory is 200 000 sentences taken from the SETIMES2 Croatian-English corpus (<a href="http://opus.lingfil.uu.se/SETIMES2.php" target="_blank">link</a>). Please enter a Croatian sentence in the field below and press Enter (or use the search button). You can test the system on predefined samples, simply use the link "show/hide samples" and apply one of the sample sentences. desc@#@Welcome to Concordia. The system finds the longest matches of the pattern sentence in its translation memory. This translation memory is 200 000 sentences taken from the SETIMES2 Croatian-English corpus (<a href="http://opus.lingfil.uu.se/SETIMES2.php" target="_blank">link</a>). Please enter a Croatian sentence in the field below and press Enter (or use the search button). You can test the system on predefined samples, simply use the link "show/hide samples" and apply one of the sample sentences.
prompt@#@Enter search pattern (Croatian sentence): prompt@#@Enter search pattern (Croatian sentence):
suggestion@#@Kazna medijskom mogulu obnovila raspravu u Makedoniji suggestion@#@Kazna medijskom mogulu obnovila raspravu u Makedoniji

73
tests/remote/addFile.py
View File

@ -1,73 +0,0 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
import unittest
import json
import urllib2
import sys
import time
BUFFER_SIZE = 500
def file_len(fname):
with open(fname) as f:
for i, l in enumerate(f):
pass
return i + 1
def add_data(data):
req = urllib2.Request('http://concordia.vm.wmi.amu.edu.pl:8800/')
req.add_header('Content-Type', 'application/json')
urllib2.urlopen(req, json.dumps(data)).read()
sourceFile = sys.argv[1]
targetFile = sys.argv[2]
tmId = int(sys.argv[3])
totalLines = file_len(sourceFile)
if file_len(targetFile) != totalLines:
print "File lengths do not match"
sys.exit(1)
data = {
'operation': 'addSentences'
}
sentences = []
start = time.time()
with open(sys.argv[1]) as sourceSentences:
with open(sys.argv[2]) as targetSentences:
lineNumber = 0
for sourceSentence in sourceSentences:
lineNumber += 1
targetSentence = targetSentences.readline()
sentences.append([tmId, sourceSentence, targetSentence])
if lineNumber % BUFFER_SIZE == 0:
data['sentences'] = sentences
sentences = []
add_data(data)
mark = time.time()
print "Added %d of %d sentences. Time elapsed: %.4f s, current speed: %.4f sentences/second" % (lineNumber, totalLines, mark-start, lineNumber/(mark-start))
if len(sentences) > 0:
data['sentences'] = sentences
add_data(data)
end = time.time()
print "Added all %d sentences. Time elapsed: %.4f s, overall speed: %.4f sentences/second" % (lineNumber, end-start, lineNumber/(end-start))
print "Generating index..."
start = time.time()
data = {
'operation': 'refreshIndex'
}
req = urllib2.Request('http://concordia.vm.wmi.amu.edu.pl:8800/')
req.add_header('Content-Type', 'application/json')
urllib2.urlopen(req, json.dumps(data)).read()
end = time.time()
print "Index regeneration complete. The operation took %.4f s" % (end - start)

27
tests/remote/addSentence.py
View File

@ -1,27 +0,0 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
import unittest
import json
import urllib2
import sys
import time
data = {
'operation': 'addSentence',
'sourceSentence':sys.argv[1],
'targetSentence':sys.argv[2],
'tmId':sys.argv[3]
}
start = time.time()
req = urllib2.Request('http://concordia.vm.wmi.amu.edu.pl:8800/')
req.add_header('Content-Type', 'application/json')
response = json.loads(urllib2.urlopen(req, json.dumps(data)).read())
end = time.time()
print "Execution time: %.4f seconds." % (end-start)
print "Result: "
print response

25
tests/remote/concordiaSearch.py
View File

@ -1,25 +0,0 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
import unittest
import json
import urllib2
import sys
import time
data = {
'operation': 'concordiaSearch',
'pattern':sys.argv[1]
}
start = time.time()
req = urllib2.Request('http://concordia.vm.wmi.amu.edu.pl:8800/')
req.add_header('Content-Type', 'application/json')
response = json.loads(urllib2.urlopen(req, json.dumps(data)).read())
end = time.time()
print "Execution time: %.4f seconds." % (end-start)
print "Result: "
print response

23
tests/remote/generateIndex.py
View File

@ -1,23 +0,0 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
import unittest
import json
import urllib2
import sys
import time
print "Generating index..."
start = time.time()
data = {
'operation': 'refreshIndex'
}
req = urllib2.Request('http://concordia.vm.wmi.amu.edu.pl:8800/')
req.add_header('Content-Type', 'application/json')
urllib2.urlopen(req, json.dumps(data)).read()
end = time.time()
print "Index regeneration complete. The operation took %.4f s" % (end - start)

25
tests/remote/simpleSearch.py
View File

@ -1,25 +0,0 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-
import unittest
import json
import urllib2
import sys
import time
data = {
'operation': 'simpleSearch',
'pattern':sys.argv[1]
}
start = time.time()
req = urllib2.Request('http://concordia.vm.wmi.amu.edu.pl:8800/')
req.add_header('Content-Type', 'application/json')
response = json.loads(urllib2.urlopen(req, json.dumps(data)).read())
end = time.time()
print "Execution time: %.4f seconds." % (end-start)
print "Result: "
print response