Python - can I detect unicode string language code?

Question

I'm faced with a situation where I'm reading a string of text and I need to detect the language code (en, de, fr, es, etc).

Is there a simple way to do this in python?

Answer 1

If you need to detect language in response to a user action then you could use google ajax language API:

#!/usr/bin/env python
import json
import urllib, urllib2

def detect_language(text,
    userip=None,
    referrer="http://stackoverflow.com/q/4545977/4279",
    api_key=None):        

    query = {'q': text.encode('utf-8') if isinstance(text, unicode) else text}
    if userip: query.update(userip=userip)
    if api_key: query.update(key=api_key)

    url = 'https://ajax.googleapis.com/ajax/services/language/detect?v=1.0&%s'%(
        urllib.urlencode(query))

    request = urllib2.Request(url, None, headers=dict(Referer=referrer))
    d = json.load(urllib2.urlopen(request))

    if d['responseStatus'] != 200 or u'error' in d['responseData']:
        raise IOError(d)

    return d['responseData']['language']

print detect_language("Python - can I detect unicode string language code?")

Output

en

Google Translate API v2

Default limit 100000 characters/day (no more than 5000 at a time).

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import json
import urllib, urllib2

from operator import itemgetter

def detect_language_v2(chunks, api_key):
    """
    chunks: either string or sequence of strings

    Return list of corresponding language codes
    """
    if isinstance(chunks, basestring):
        chunks = [chunks] 

    url = 'https://www.googleapis.com/language/translate/v2'

    data = urllib.urlencode(dict(
        q=[t.encode('utf-8') if isinstance(t, unicode) else t 
           for t in chunks],
        key=api_key,
        target="en"), doseq=1)

    # the request length MUST be < 5000
    if len(data) > 5000:
        raise ValueError("request is too long, see "
            "http://code.google.com/apis/language/translate/terms.html")

    #NOTE: use POST to allow more than 2K characters
    request = urllib2.Request(url, data,
        headers={'X-HTTP-Method-Override': 'GET'})
    d = json.load(urllib2.urlopen(request))
    if u'error' in d:
        raise IOError(d)
    return map(itemgetter('detectedSourceLanguage'), d['data']['translations'])

Now you could request detecting a language explicitly:

def detect_language_v2(chunks, api_key):
    """
    chunks: either string or sequence of strings

    Return list of corresponding language codes
    """
    if isinstance(chunks, basestring):
        chunks = [chunks] 

    url = 'https://www.googleapis.com/language/translate/v2/detect'

    data = urllib.urlencode(dict(
        q=[t.encode('utf-8') if isinstance(t, unicode) else t
           for t in chunks],
        key=api_key), doseq=True)

    # the request length MUST be < 5000
    if len(data) > 5000:
        raise ValueError("request is too long, see "
            "http://code.google.com/apis/language/translate/terms.html")

    #NOTE: use POST to allow more than 2K characters
    request = urllib2.Request(url, data,
        headers={'X-HTTP-Method-Override': 'GET'})
    d = json.load(urllib2.urlopen(request))

    return [sorted(L, key=itemgetter('confidence'))[-1]['language']
            for L in d['data']['detections']]

Example:

print detect_language_v2(
    ["Python - can I detect unicode string language code?",
     u"матрёшка",
     u"打水"], api_key=open('api_key.txt').read().strip())

Output

[u'en', u'ru', u'zh-CN']