Changed findArtist to use the musicbrainzngs library, the output is identical.

(old musicbrainz 2 library is deprecated and broken)

headphones/mb.py

@@ -13,6 +13,8 @@ import headphones
 from headphones import logger, db
 from headphones.helpers import multikeysort, replace_all
 
+import lib.musicbrainzngs as musicbrainzngs
+
 mb_lock = threading.Lock()
 
 
@@ -46,6 +48,12 @@ def startmb(forcemb=False):
         mbport = 5000
         sleepytime = 0
     
+    musicbrainzngs.set_useragent("headphones","0.0","https://github.com/doskir/headphones")
+    logger.info("set user agent")
+    musicbrainzngs.set_hostname(mbhost + ":" + str(mbport))
+    logger.info("set host and port")
+
+    #q = musicbrainzngs
     service = ws.WebService(host=mbhost, port=mbport, username=mbuser, password=mbpass, mirror=headphones.MIRROR)
     q = ws.Query(service)
     
@@ -56,7 +64,7 @@ def startmb(forcemb=False):
 def findArtist(name, limit=1):
 
     with mb_lock:
-	
+        limit = 25
         artistlist = []
         attempt = 0
         artistResults = None
@@ -68,11 +76,10 @@ def findArtist(name, limit=1):
         q, sleepytime = startmb(forcemb=True)
         
         while attempt < 5:        
-		
             try:
-				artistResults = q.getArtists(ws.ArtistFilter(query=name, limit=limit))
+                artistResults = musicbrainzngs.search_artists(query=name,limit=limit)['artist-list']
                 break
-			except WebServiceError, e:
+            except WebServiceError, e:#need to update the exceptions
                 logger.warn('Attempt to query MusicBrainz for %s failed (%s)' % (name, str(e)))
                 attempt += 1
                 time.sleep(10)
@@ -81,36 +88,33 @@ def findArtist(name, limit=1):
         
         if not artistResults:
             return False        
-		
         for result in artistResults:
-		
+            if 'disambiguation' in result:
-			if result.artist.name != result.artist.getUniqueName() and limit == 1:
+                uniquename = unicode(result['sort-name'] + " (" + result['disambiguation'] + ")")
-				
+            else:
+                uniquename = unicode(result['sort-name'])
+            if result['name'] != uniquename and limit == 1:
                 logger.debug('Found an artist with a disambiguation: %s - doing an album based search' % name)
                 artistdict = findArtistbyAlbum(name)                
-				
                 if not artistdict:
                     logger.debug('Cannot determine the best match from an artist/album search. Using top match instead')
                     artistlist.append({
-						'name': 			result.artist.name,
+                        'name':             unicode(result['sort-name']),
-						'uniquename':		result.artist.getUniqueName(),
+                        'uniquename':        uniquename,
-						'id':				u.extractUuid(result.artist.id),
+                        'id':                unicode(result['id']),
-						'url': 				result.artist.id,
+                        'url':                 unicode("http://musicbrainz.org/artist/" + result['id']),#probably needs to be changed
-						'score':			result.score
+                        'score':            int(result['ext:score'])
                         })                    
-					
                 else:
                     artistlist.append(artistdict)
-			
             else:                
                 artistlist.append({
-						'name': 			result.artist.name,
+                        'name':             unicode(result['sort-name']),
-						'uniquename':		result.artist.getUniqueName(),
+                        'uniquename':        uniquename,
-						'id':				u.extractUuid(result.artist.id),
+                        'id':                unicode(result['id']),
-						'url': 				result.artist.id,
+                        'url':                 unicode("http://musicbrainz.org/artist/" + result['id']),#probably needs to be changed
-						'score':			result.score
+                        'score':            int(result['ext:score'])
                         })
-			
         return artistlist
         
 def findRelease(name, limit=1):

lib/musicbrainzngs/__init__.py

@@ -1 +1 @@
-from musicbrainz import *
+from lib.musicbrainzngs.musicbrainz import *

lib/musicbrainzngs/compat.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+# Copyright (c) 2012 Kenneth Reitz.
+
+# Permission to use, copy, modify, and/or distribute this software for any
+# purpose with or without fee is hereby granted, provided that the above
+# copyright notice and this permission notice appear in all copies.
+
+# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+"""
+pythoncompat
+"""
+
+
+import sys
+
+# -------
+# Pythons
+# -------
+
+# Syntax sugar.
+_ver = sys.version_info
+
+#: Python 2.x?
+is_py2 = (_ver[0] == 2)
+
+#: Python 3.x?
+is_py3 = (_ver[0] == 3)
+
+# ---------
+# Specifics
+# ---------
+
+if is_py2:
+	from StringIO import StringIO
+	from urllib2 import HTTPPasswordMgr, HTTPDigestAuthHandler, Request,\
+						HTTPHandler, build_opener, HTTPError, URLError,\
+						build_opener
+	from httplib import BadStatusLine, HTTPException
+	from urlparse import urlunparse
+	from urllib import urlencode
+
+	bytes = str
+	unicode = unicode
+	basestring = basestring
+elif is_py3:
+	from io import StringIO
+	from urllib.request import HTTPPasswordMgr, HTTPDigestAuthHandler, Request,\
+								HTTPHandler, build_opener
+	from urllib.error import HTTPError, URLError
+	from http.client import HTTPException, BadStatusLine
+	from urllib.parse import urlunparse, urlencode
+
+	unicode = str
+	bytes = bytes
+	basestring = (str,bytes)

lib/musicbrainzngs/mbxml.py

@@ -4,9 +4,11 @@
 # See the COPYING file for more information.
 
 import xml.etree.ElementTree as ET
-import string
-import StringIO
 import logging
+
+from lib.musicbrainzngs import compat
+from lib.musicbrainzngs import util
+
 try:
 	from ET import fixtag
 except:
@@ -16,7 +18,7 @@ except:
 		# tag and namespace declaration, if any
 		if isinstance(tag, ET.QName):
 			tag = tag.text
-		namespace_uri, tag = string.split(tag[1:], "}", 1)
+		namespace_uri, tag = tag[1:].split("}", 1)
 		prefix = namespaces.get(namespace_uri)
 		if prefix is None:
 			prefix = "ns%d" % len(namespaces)
@@ -29,6 +31,7 @@ except:
 			xmlns = None
 		return "%s:%s" % (prefix, tag), xmlns
 
+
 NS_MAP = {"http://musicbrainz.org/ns/mmd-2.0#": "ws2",
           "http://musicbrainz.org/ns/ext#-2.0": "ext"}
 _log = logging.getLogger("python-musicbrainz-ngs")
@@ -113,9 +116,7 @@ def parse_inner(inner_els, element):
 	return result
 
 def parse_message(message):
-	s = message.read()
+	tree = util.bytes_to_elementtree(message)
-	f = StringIO.StringIO(s)
-	tree = ET.ElementTree(file=f)
 	root = tree.getroot()
 	result = {}
 	valid_elements = {"artist": parse_artist,
@@ -176,7 +177,8 @@ def parse_artist_list(al):
 def parse_artist(artist):
 	result = {}
 	attribs = ["id", "type", "ext:score"]
-	elements = ["name", "sort-name", "country", "user-rating", "disambiguation"]
+	elements = ["name", "sort-name", "country", "user-rating",
+				"disambiguation", "gender", "ipi"]
 	inner_els = {"life-span": parse_artist_lifespan,
 	             "recording-list": parse_recording_list,
 	             "release-list": parse_release_list,
@@ -199,7 +201,8 @@ def parse_label_list(ll):
 def parse_label(label):
 	result = {}
 	attribs = ["id", "type", "ext:score"]
-	elements = ["name", "sort-name", "country", "label-code", "user-rating"]
+	elements = ["name", "sort-name", "country", "label-code", "user-rating",
+				"ipi", "disambiguation"]
 	inner_els = {"life-span": parse_artist_lifespan,
 	             "release-list": parse_release_list,
 	             "tag-list": parse_tag_list,

lib/musicbrainzngs/musicbrainz.py

@@ -3,19 +3,18 @@
 # This file is distributed under a BSD-2-Clause type license.
 # See the COPYING file for more information.
 
-import urlparse
-import urllib2
-import urllib
-import mbxml
 import re
 import threading
 import time
 import logging
-import httplib
 import socket
 import xml.etree.ElementTree as etree
 from xml.parsers import expat
 
+from lib.musicbrainzngs import mbxml
+from lib.musicbrainzngs import util
+from lib.musicbrainzngs import compat
+
 _version = "0.3dev"
 _log = logging.getLogger("musicbrainzngs")
 
@@ -74,6 +73,7 @@ VALID_INCLUDES = {
     'puid': ["artists", "releases", "puids", "echoprints", "isrcs"],
     'isrc': ["artists", "releases", "puids", "echoprints", "isrcs"],
     'iswc': ["artists"],
+    'collection': ['releases'],
 }
 VALID_RELEASE_TYPES = [
     "nat", "album", "single", "ep", "compilation", "soundtrack", "spokenword",
@@ -83,29 +83,33 @@ VALID_RELEASE_STATUSES = ["official", "promotion", "bootleg", "pseudo-release"]
 VALID_SEARCH_FIELDS = {
     'artist': [
         'arid', 'artist', 'sortname', 'type', 'begin', 'end', 'comment',
-		'alias', 'country', 'gender', 'tag'
+        'alias', 'country', 'gender', 'tag', 'ipi', 'artistaccent'
     ],
     'release-group': [
         'rgid', 'releasegroup', 'reid', 'release', 'arid', 'artist',
-		'artistname', 'creditname', 'type', 'tag'
+        'artistname', 'creditname', 'type', 'tag', 'releasegroupaccent',
+        'releases', 'comment'
     ],
     'release': [
         'reid', 'release', 'arid', 'artist', 'artistname', 'creditname',
         'type', 'status', 'tracks', 'tracksmedium', 'discids',
         'discidsmedium', 'mediums', 'date', 'asin', 'lang', 'script',
-		'country', 'date', 'label', 'catno', 'barcode', 'puid'
+        'country', 'date', 'label', 'catno', 'barcode', 'puid', 'comment',
+        'format', 'releaseaccent', 'rgid'
     ],
     'recording': [
         'rid', 'recording', 'isrc', 'arid', 'artist', 'artistname',
         'creditname', 'reid', 'release', 'type', 'status', 'tracks',
-		'tracksrelease', 'dur', 'qdur', 'tnum', 'position', 'tag'
+        'tracksrelease', 'dur', 'qdur', 'tnum', 'position', 'tag', 'comment',
+        'country', 'date' 'format', 'recordingaccent'
     ],
     'label': [
         'laid', 'label', 'sortname', 'type', 'code', 'country', 'begin',
-		'end', 'comment', 'alias', 'tag'
+        'end', 'comment', 'alias', 'tag', 'ipi', 'labelaccent'
     ],
     'work': [
-		'wid', 'work', 'iswc', 'type', 'arid', 'artist', 'alias', 'tag'
+        'wid', 'work', 'iswc', 'type', 'arid', 'artist', 'alias', 'tag',
+        'comment', 'workaccent'
     ],
 }
 
@@ -186,9 +190,9 @@ def _check_filter_and_make_params(entity, includes, release_status=[], release_t
     the filters can be used with the given includes. Return a params
     dict that can be passed to _do_mb_query.
     """
-	if isinstance(release_status, basestring):
+    if isinstance(release_status, compat.basestring):
         release_status = [release_status]
-	if isinstance(release_type, basestring):
+    if isinstance(release_type, compat.basestring):
         release_type = [release_type]
     _check_filter(release_status, VALID_RELEASE_STATUSES)
     _check_filter(release_type, VALID_RELEASE_TYPES)
@@ -226,8 +230,8 @@ def auth(u, p):
     password = p
 
 def set_useragent(app, version, contact=None):
-    """ Set the User-Agent to be used for requests to the MusicBrainz webservice.
+    """Set the User-Agent to be used for requests to the MusicBrainz webservice.
-    This should be set before requests are made."""
+    This must be set before requests are made."""
     global _useragent, _client
     if contact is not None:
         _useragent = "%s/%s python-musicbrainz-ngs/%s ( %s )" % (app, version, _version, contact)
@@ -237,6 +241,8 @@ def set_useragent(app, version, contact=None):
     _log.debug("set user-agent to %s" % _useragent)
 
 def set_hostname(new_hostname):
+    """Set the base hostname for MusicBrainz webservice requests.
+    Defaults to 'musicbrainz.org'."""
     global hostname
     hostname = new_hostname
 
@@ -244,17 +250,26 @@ def set_hostname(new_hostname):
 
 limit_interval = 1.0
 limit_requests = 1
+do_rate_limit = True
 
-def set_rate_limit(new_interval=1.0, new_requests=1):
+def set_rate_limit(rate_limit=True, new_interval=1.0, new_requests=1):
     """Sets the rate limiting behavior of the module. Must be invoked
-	before the first Web service call.  Specify the number of requests
+    before the first Web service call.
-	(`new_requests`) that may be made per given interval
+    If the `rate_limit` parameter is set to True, then only a set number
-	(`new_interval`).
+    of requests (`new_requests`) will be made per given interval
+    (`new_interval`). If `rate_limit` is False, then no rate limiting
+    will occur.
     """
     global limit_interval
     global limit_requests
+    global do_rate_limit
+    if new_interval <= 0.0:
+        raise ValueError("new_interval can't be less than 0")
+    if new_requests <= 0:
+        raise ValueError("new_requests can't be less than 0")
     limit_interval = new_interval
     limit_requests = new_requests
+    do_rate_limit = rate_limit
 
 class _rate_limit(object):
     """A decorator that limits the rate at which the function may be
@@ -290,6 +305,7 @@ class _rate_limit(object):
 
     def __call__(self, *args, **kwargs):
         with self.lock:
+            if do_rate_limit:
                 self._update_remaining()
 
                 # Delay if necessary.
@@ -302,11 +318,8 @@ class _rate_limit(object):
                 self.remaining_requests -= 1.0
             return self.fun(*args, **kwargs)
 
-
-# Generic support for making HTTP requests.
-
 # From pymb2
-class _RedirectPasswordMgr(urllib2.HTTPPasswordMgr):
+class _RedirectPasswordMgr(compat.HTTPPasswordMgr):
     def __init__(self):
         self._realms = { }
 
@@ -321,18 +334,18 @@ class _RedirectPasswordMgr(urllib2.HTTPPasswordMgr):
         # ignoring the uri parameter intentionally
         self._realms[realm] = (username, password)
 
-class _DigestAuthHandler(urllib2.HTTPDigestAuthHandler):
+class _DigestAuthHandler(compat.HTTPDigestAuthHandler):
     def get_authorization (self, req, chal):
         qop = chal.get ('qop', None)
         if qop and ',' in qop and 'auth' in qop.split (','):
             chal['qop'] = 'auth'
 
-		return urllib2.HTTPDigestAuthHandler.get_authorization (self, req, chal)
+        return compat.HTTPDigestAuthHandler.get_authorization (self, req, chal)
 
-class _MusicbrainzHttpRequest(urllib2.Request):
+class _MusicbrainzHttpRequest(compat.Request):
     """ A custom request handler that allows DELETE and PUT"""
     def __init__(self, method, url, data=None):
-		urllib2.Request.__init__(self, url, data)
+        compat.Request.__init__(self, url, data)
         allowed_m = ["GET", "POST", "DELETE", "PUT"]
         if method not in allowed_m:
             raise ValueError("invalid method: %s" % method)
@@ -362,8 +375,8 @@ def _safe_open(opener, req, body=None, max_retries=8, retry_delay_delta=2.0):
             else:
                 f = opener.open(req)
 
-		except urllib2.HTTPError, exc:
+        except compat.HTTPError as exc:
-			if exc.code in (400, 404):
+            if exc.code in (400, 404, 411):
                 # Bad request, not found, etc.
                 raise ResponseError(cause=exc)
             elif exc.code in (503, 502, 500):
@@ -374,19 +387,23 @@ def _safe_open(opener, req, body=None, max_retries=8, retry_delay_delta=2.0):
                 # retrying for now.
                 _log.debug("unknown HTTP error %i" % exc.code)
             last_exc = exc
-		except httplib.BadStatusLine, exc:
+        except compat.BadStatusLine as exc:
             _log.debug("bad status line")
             last_exc = exc
-		except httplib.HTTPException, exc:
+        except compat.HTTPException as exc:
             _log.debug("miscellaneous HTTP exception: %s" % str(exc))
             last_exc = exc
-		except urllib2.URLError, exc:
+        except compat.URLError as exc:
             if isinstance(exc.reason, socket.error):
                 code = exc.reason.errno
                 if code == 104: # "Connection reset by peer."
                     continue
             raise NetworkError(cause=exc)
-		except IOError, exc:
+        except socket.error as exc:
+            if exc.errno == 104:
+                continue
+            raise NetworkError(cause=exc)
+        except IOError as exc:
             raise NetworkError(cause=exc)
         else:
             # No exception! Yay!
@@ -425,23 +442,23 @@ def _mb_request(path, method='GET', auth_required=False, client_required=False,
 
     # Encode Unicode arguments using UTF-8.
     for key, value in args.items():
-		if isinstance(value, unicode):
+        if isinstance(value, compat.unicode):
             args[key] = value.encode('utf8')
 
     # Construct the full URL for the request, including hostname and
     # query string.
-	url = urlparse.urlunparse((
+    url = compat.urlunparse((
         'http',
         hostname,
         '/ws/2/%s' % path,
         '',
-		urllib.urlencode(args),
+        compat.urlencode(args),
         ''
     ))
     _log.debug("%s request for %s" % (method, url))
 
     # Set up HTTP request handler and URL opener.
-	httpHandler = urllib2.HTTPHandler(debuglevel=0)
+    httpHandler = compat.HTTPHandler(debuglevel=0)
     handlers = [httpHandler]
 
     # Add credentials if required.
@@ -455,7 +472,7 @@ def _mb_request(path, method='GET', auth_required=False, client_required=False,
         authHandler.add_password("musicbrainz.org", (), user, password)
         handlers.append(authHandler)
 
-	opener = urllib2.build_opener(*handlers)
+    opener = compat.build_opener(*handlers)
 
     # Make request.
     req = _MusicbrainzHttpRequest(method, url, data)
@@ -463,6 +480,10 @@ def _mb_request(path, method='GET', auth_required=False, client_required=False,
     _log.debug("requesting with UA %s" % _useragent)
     if body:
         req.add_header('Content-Type', 'application/xml; charset=UTF-8')
+    elif not data and not req.has_header('Content-Length'):
+        # Explicitly indicate zero content length if no request data
+        # will be sent (avoids HTTP 411 error).
+        req.add_header('Content-Length', '0')
     f = _safe_open(opener, req, body)
 
     # Parse the response.
@@ -496,6 +517,8 @@ def _do_mb_query(entity, id, includes=[], params={}):
     response is parsed and returned.
     """
     # Build arguments.
+    if not isinstance(includes, list):
+        includes = [includes]
     _check_includes(entity, includes)
     auth_required = _is_auth_required(entity, includes)
     args = dict(params)
@@ -507,15 +530,28 @@ def _do_mb_query(entity, id, includes=[], params={}):
     path = '%s/%s' % (entity, id)
     return _mb_request(path, 'GET', auth_required, args=args)
 
-def _do_mb_search(entity, query='', fields={}, limit=None, offset=None):
+def _do_mb_search(entity, query='', fields={},
+          limit=None, offset=None, strict=False):
     """Perform a full-text search on the MusicBrainz search server.
-	`query` is a free-form query string and `fields` is a dictionary
+    `query` is a lucene query string when no fields are set,
+    but is escaped when any fields are given. `fields` is a dictionary
     of key/value query parameters. They keys in `fields` must be valid
     for the given entity type.
     """
     # Encode the query terms as a Lucene query string.
-	query_parts = [query.replace('\x00', '').strip()]
+    query_parts = []
-	for key, value in fields.iteritems():
+    if query:
+        clean_query = util._unicode(query)
+        if fields:
+            clean_query = re.sub(r'([+\-&|!(){}\[\]\^"~*?:\\])',
+                    r'\\\1', clean_query)
+            if strict:
+                query_parts.append('"%s"' % clean_query)
+            else:
+                query_parts.append(clean_query.lower())
+        else:
+            query_parts.append(clean_query)
+    for key, value in fields.items():
         # Ensure this is a valid search field.
         if key not in VALID_SEARCH_FIELDS[entity]:
             raise InvalidSearchFieldError(
@@ -523,12 +559,19 @@ def _do_mb_search(entity, query='', fields={}, limit=None, offset=None):
             )
 
         # Escape Lucene's special characters.
+        value = util._unicode(value)
         value = re.sub(r'([+\-&|!(){}\[\]\^"~*?:\\])', r'\\\1', value)
-		value = value.replace('\x00', '').strip()
-		value = value.lower() # Avoid binary operators like OR.
         if value:
-			query_parts.append(u'%s:(%s)' % (key, value))
+            if strict:
-	full_query = u' '.join(query_parts).strip()
+                query_parts.append('%s:"%s"' % (key, value))
+            else:
+                value = value.lower() # avoid AND / OR
+                query_parts.append('%s:(%s)' % (key, value))
+    if strict:
+        full_query = ' AND '.join(query_parts).strip()
+    else:
+        full_query = ' '.join(query_parts).strip()
+
     if not full_query:
         raise ValueError('at least one query term is required')
 
@@ -562,23 +605,23 @@ def _do_mb_post(path, body):
 
 # Single entity by ID
 def get_artist_by_id(id, includes=[], release_status=[], release_type=[]):
-	params = _check_filter_and_make_params(includes, release_status, release_type)
+    params = _check_filter_and_make_params("artist", includes, release_status, release_type)
     return _do_mb_query("artist", id, includes, params)
 
 def get_label_by_id(id, includes=[], release_status=[], release_type=[]):
-	params = _check_filter_and_make_params(includes, release_status, release_type)
+    params = _check_filter_and_make_params("label", includes, release_status, release_type)
     return _do_mb_query("label", id, includes, params)
 
 def get_recording_by_id(id, includes=[], release_status=[], release_type=[]):
-	params = _check_filter_and_make_params(includes, release_status, release_type)
+    params = _check_filter_and_make_params("recording", includes, release_status, release_type)
     return _do_mb_query("recording", id, includes, params)
 
 def get_release_by_id(id, includes=[], release_status=[], release_type=[]):
-	params = _check_filter_and_make_params(includes, release_status, release_type)
+    params = _check_filter_and_make_params("release", includes, release_status, release_type)
     return _do_mb_query("release", id, includes, params)
 
 def get_release_group_by_id(id, includes=[], release_status=[], release_type=[]):
-	params = _check_filter_and_make_params(includes, release_status, release_type)
+    params = _check_filter_and_make_params("release-group", includes, release_status, release_type)
     return _do_mb_query("release-group", id, includes, params)
 
 def get_work_by_id(id, includes=[]):
@@ -587,54 +630,68 @@ def get_work_by_id(id, includes=[]):
 
 # Searching
 
-def search_artists(query='', limit=None, offset=None, **fields):
+def search_artists(query='', limit=None, offset=None, strict=False, **fields):
-	"""Search for artists by a free-form `query` string and/or any of
+    """Search for artists by a free-form `query` string or any of
     the following keyword arguments specifying field queries:
     arid, artist, sortname, type, begin, end, comment, alias, country,
     gender, tag
+    When `fields` are set, special lucene characters are escaped
+    in the `query`.
     """
-	return _do_mb_search('artist', query, fields, limit, offset)
+    return _do_mb_search('artist', query, fields, limit, offset, strict)
 
-def search_labels(query='', limit=None, offset=None, **fields):
+def search_labels(query='', limit=None, offset=None, strict=False, **fields):
-	"""Search for labels by a free-form `query` string and/or any of
+    """Search for labels by a free-form `query` string or any of
     the following keyword arguments specifying field queries:
     laid, label, sortname, type, code, country, begin, end, comment,
     alias, tag
+    When `fields` are set, special lucene characters are escaped
+    in the `query`.
     """
-	return _do_mb_search('label', query, fields, limit, offset)
+    return _do_mb_search('label', query, fields, limit, offset, strict)
 
-def search_recordings(query='', limit=None, offset=None, **fields):
+def search_recordings(query='', limit=None, offset=None, strict=False, **fields):
-	"""Search for recordings by a free-form `query` string and/or any of
+    """Search for recordings by a free-form `query` string or any of
     the following keyword arguments specifying field queries:
     rid, recording, isrc, arid, artist, artistname, creditname, reid,
     release, type, status, tracks, tracksrelease, dur, qdur, tnum,
     position, tag
+    When `fields` are set, special lucene characters are escaped
+    in the `query`.
     """
-	return _do_mb_search('recording', query, fields, limit, offset)
+    return _do_mb_search('recording', query, fields, limit, offset, strict)
 
-def search_releases(query='', limit=None, offset=None, **fields):
+def search_releases(query='', limit=None, offset=None, strict=False, **fields):
-	"""Search for releases by a free-form `query` string and/or any of
+    """Search for releases by a free-form `query` string or any of
     the following keyword arguments specifying field queries:
     reid, release, arid, artist, artistname, creditname, type, status,
     tracks, tracksmedium, discids, discidsmedium, mediums, date, asin,
     lang, script, country, date, label, catno, barcode, puid
+    When `fields` are set, special lucene characters are escaped
+    in the `query`.
     """
-	return _do_mb_search('release', query, fields, limit, offset)
+    return _do_mb_search('release', query, fields, limit, offset, strict)
 
-def search_release_groups(query='', limit=None, offset=None, **fields):
+def search_release_groups(query='', limit=None, offset=None,
-	"""Search for release groups by a free-form `query` string and/or
+              strict=False, **fields):
+    """Search for release groups by a free-form `query` string or
     any of the following keyword arguments specifying field queries:
     rgid, releasegroup, reid, release, arid, artist, artistname,
     creditname, type, tag
+    When `fields` are set, special lucene characters are escaped
+    in the `query`.
     """
-	return _do_mb_search('release-group', query, fields, limit, offset)
+    return _do_mb_search('release-group', query, fields,
+                 limit, offset, strict)
 
-def search_works(query='', limit=None, offset=None, **fields):
+def search_works(query='', limit=None, offset=None, strict=False, **fields):
-	"""Search for works by a free-form `query` string and/or any of
+    """Search for works by a free-form `query` string or any of
     the following keyword arguments specifying field queries:
     wid, work, iswc, type, arid, artist, alias, tag
+    When `fields` are set, special lucene characters are escaped
+    in the `query`.
     """
-	return _do_mb_search('work', query, fields, limit, offset)
+    return _do_mb_search('work', query, fields, limit, offset, strict)
 
 
 # Lists of entities
@@ -721,35 +778,40 @@ def get_releases_in_collection(collection):
 # Submission methods
 
 def submit_barcodes(barcodes):
-	"""
+    """Submits a set of {release1: barcode1, release2:barcode2}
-	Submits a set of {release1: barcode1, release2:barcode2}
+
-	Must call auth(user, pass) first
+    Must call auth(user, pass) first"""
-	"""
     query = mbxml.make_barcode_request(barcodes)
     return _do_mb_post("release", query)
 
 def submit_puids(puids):
+    """Submit PUIDs.
+
+    Must call auth(user, pass) first"""
     query = mbxml.make_puid_request(puids)
     return _do_mb_post("recording", query)
 
 def submit_echoprints(echoprints):
+    """Submit echoprints.
+
+    Must call auth(user, pass) first"""
     query = mbxml.make_echoprint_request(echoprints)
     return _do_mb_post("recording", query)
 
 def submit_isrcs(recordings_isrcs):
-    """
+    """Submit ISRCs.
-    Submit ISRCs.
+    Submits a set of {recording-id: [isrc1, isrc1, ...]}
-    Submits a set of {recording-id: [isrc1, irc1]}
+
-    Must call auth(user, pass) first
+    Must call auth(user, pass) first"""
-    """
     query = mbxml.make_isrc_request(recordings_isrcs=recordings_isrcs)
     return _do_mb_post("recording", query)
 
 def submit_tags(artist_tags={}, recording_tags={}):
-	""" Submit user tags.
+    """Submit user tags.
     Artist or recording parameters are of the form:
     {'entityid': [taglist]}
-	"""
+
+    Must call auth(user, pass) first"""
     query = mbxml.make_tag_request(artist_tags, recording_tags)
     return _do_mb_post("tag", query)
 
@@ -757,15 +819,24 @@ def submit_ratings(artist_ratings={}, recording_ratings={}):
     """ Submit user ratings.
     Artist or recording parameters are of the form:
     {'entityid': rating}
-	"""
+
+    Must call auth(user, pass) first"""
     query = mbxml.make_rating_request(artist_ratings, recording_ratings)
     return _do_mb_post("rating", query)
 
 def add_releases_to_collection(collection, releases=[]):
+    """Add releases to a collection.
+    Collection and releases should be identified by their MBIDs
+
+    Must call auth(user, pass) first"""
     # XXX: Maximum URI length of 16kb means we should only allow ~400 releases
     releaselist = ";".join(releases)
     _do_mb_put("collection/%s/releases/%s" % (collection, releaselist))
 
 def remove_releases_from_collection(collection, releases=[]):
+    """Remove releases from a collection.
+    Collection and releases should be identified by their MBIDs
+
+    Must call auth(user, pass) first"""
     releaselist = ";".join(releases)
     _do_mb_delete("collection/%s/releases/%s" % (collection, releaselist))

lib/musicbrainzngs/util.py

@@ -0,0 +1,37 @@
+# This file is part of the musicbrainzngs library
+# Copyright (C) Alastair Porter, Adrian Sampson, and others
+# This file is distributed under a BSD-2-Clause type license.
+# See the COPYING file for more information.
+
+import sys
+import locale
+import xml.etree.ElementTree as ET
+
+from . import compat
+
+def _unicode(string, encoding=None):
+    """Try to decode byte strings to unicode.
+    This can only be a guess, but this might be better than failing.
+    It is safe to use this on numbers or strings that are already unicode.
+    """
+    if isinstance(string, compat.unicode):
+        unicode_string = string
+    elif isinstance(string, compat.bytes):
+        # use given encoding, stdin, preferred until something != None is found
+        if encoding is None:
+            encoding = sys.stdin.encoding
+        if encoding is None:
+            encoding = locale.getpreferredencoding()
+        unicode_string = string.decode(encoding, "ignore")
+    else:
+        unicode_string = compat.unicode(string)
+    return unicode_string.replace('\x00', '').strip()
+
+def bytes_to_elementtree(_bytes):
+    if compat.is_py3:
+        s = _unicode(_bytes.read(), "utf-8")
+    else:
+        s = _bytes.read()
+    f = compat.StringIO(s)
+    tree = ET.ElementTree(file=f)
+    return tree