Commit e0e4926982dec15818a6981a291e5e34e0c6e423
1 parent
ac1275835c
Exists in
master
and in
1 other branch
Passage au processor Step 1
Showing 2 changed files with 14 additions and 26 deletions Inline Diff
static/js/application.js
1 | // Some general UI pack related JS | 1 | // Some general UI pack related JS |
2 | $(document).ready(function() { | 2 | $(document).ready(function() { |
3 | tagging(); | 3 | tagging(); |
4 | }); | 4 | }); |
5 | 5 | ||
6 | 6 | ||
7 | 7 | ||
8 | function tagging(){ | 8 | function tagging(){ |
9 | $('#go').click(function(){ | 9 | $('#go').click(function(){ |
10 | data=JSON.stringify({ "string" : $('#data').val() }); | 10 | data=JSON.stringify({ "string" : $('#data').val() }); |
11 | console.log(data); | 11 | console.log(data); |
12 | $.ajax({ | 12 | $.ajax({ |
13 | type: "POST", | 13 | type: "POST", |
14 | url: "tagger", | 14 | url: "tagger", |
15 | data: data, | 15 | data: data, |
16 | success: function(data){ | 16 | success: function(data){ |
17 | data = JSON.parse(data); | 17 | //data = JSON.parse(data); |
18 | result=$('#result'); | 18 | result=$('#result'); |
19 | 19 | ||
20 | _.each(data, function(element, index, list){ | 20 | //_.each(data, function(element, index, list){ |
21 | console.log(element); | 21 | // console.log(element); |
22 | result.append(_.escape(element["word"])+" "); | 22 | // result.append(_.escape(element["word"])+" "); |
23 | result.append(_.escape(element["markup"]+" ")); | 23 | // result.append(_.escape(element["markup"]+" ")); |
24 | result.append(_.escape(element["lemm"]+"\n")); | 24 | // result.append(_.escape(element["lemm"]+"\n")); |
25 | }); | 25 | //}); |
26 | result.append(_.escape(data)); | ||
26 | console.log(_.escape(data)); | 27 | console.log(_.escape(data)); |
27 | console.log("resultat"); | 28 | console.log("resultat"); |
28 | }, | 29 | }, |
29 | error: function(){ | 30 | error: function(){ |
30 | alert("error"); | 31 | alert("error"); |
31 | }, | 32 | }, |
32 | dataType: "text", | 33 | dataType: "text", |
33 | contentType:"application/json; charset=UTF-8" | 34 | contentType:"application/json; charset=UTF-8" |
34 | }); | 35 | }); |
35 | }); | 36 | }); |
36 | } | 37 | } |
37 | 38 |
webtagger.py
1 | # -*- coding: utf-8 -*- | 1 | # -*- coding: utf-8 -*- |
2 | import subprocess | 2 | import subprocess |
3 | import os | 3 | import os |
4 | import json | 4 | import json |
5 | from flask import Flask, request, render_template | 5 | from flask import Flask, request, render_template |
6 | from processor.LiaTools import * | ||
6 | app = Flask(__name__) | 7 | app = Flask(__name__) |
7 | 8 | ||
8 | @app.route("/") | 9 | @app.route("/") |
9 | def docs(): | 10 | def docs(): |
10 | return render_template('index.html') | 11 | return render_template('index.html') |
11 | 12 | ||
12 | @app.route("/tagger",methods=['POST']) | 13 | @app.route("/tagger",methods=['POST']) |
13 | def cleaner(): | 14 | def cleaner(): |
15 | tagger = Tagger() | ||
14 | # Receive String from post parametre Raw text ( Json ) | 16 | # Receive String from post parametre Raw text ( Json ) |
15 | dirtyString= request.json[u'string'] | 17 | dirtyString= request.json[u'string'] |
16 | # send the String throught LIA_TAGG script thank's to pipe | 18 | # send the String throught LIA_TAGG script thank's to pip |
17 | # lia_clean split a word by line et markup the sentences | 19 | # lia_clean split a word by line et markup the sentences |
18 | p=subprocess.Popen([os.environ["LIA_TAGG"]+'/script/lia_clean'],stdin=subprocess.PIPE,stdout=subprocess.PIPE) | 20 | cleanString= tagger.clean(dirtyString) |
19 | (cleanString, err) = p.communicate(input=dirtyString.encode('iso8859-1','backslashreplace')) | 21 | taggedString= tagger.tagg(cleanString) |
20 | #lia_tagg+lemm tagg words with function and give the lemm for each word | 22 | return taggedString |
21 | p2=subprocess.Popen([os.environ["LIA_TAGG"]+'/script/lia_tagg+lemm','-guess'],stdin=subprocess.PIPE,stdout=subprocess.PIPE) | ||
22 | (taggedString,err) =p2.communicate(input=cleanString) | ||
23 | # This is used beceause lia_tagg deal with iso8859 only | ||
24 | taggedString = taggedString.decode('iso8859').encode("utf8") | ||
25 | textTable = taggedString.split('\n') | ||
26 | # Creating a dictionary in order to encode it into Json | ||
27 | textDictionary = list() | ||
28 | for line in textTable : | ||
29 | lineTable =line.split() | ||
30 | #print lineTable | ||
31 | if lineTable: | ||
32 | wordDict=dict([('word',lineTable[0]),('markup',lineTable[1]),('lemm',lineTable[2])]) | ||
33 | textDictionary.append(wordDict) | ||
34 | textJson = json.JSONEncoder().encode(textDictionary) | ||
35 | return textJson | ||
36 | if __name__ == '__main__': | 23 | if __name__ == '__main__': |
37 | app.debug = True | 24 | app.debug = True |