def fetch(doc): """Fetch document (if necessary). Parameters ---------- doc : {dict, string} A dictionary representing a handle returned by es_document, or a plain string. A Unicode string (Python 2 unicode, Python 3 str) will be returned as-is. A byte string (Python 2 str, Python 3 bytes) will be run through chardet to guess the encoding, then decoded with errors="replace". Returns ------- content : string Document contents. """ if isinstance(doc, dict) and set(doc.keys()) == set(_ES_DOC_FIELDS): idx, typ, id, field = [doc[k] for k in _ES_DOC_FIELDS] return _es().get_source(index=idx, doc_type=typ, id=id)[field] elif isinstance(doc, unicode): return doc elif isinstance(doc, str): enc = chardetect(doc)['encoding'] return doc.decode(enc, errors="replace") else: raise TypeError("fetch expected es_document or string, got %s" % type(doc))
def fetch(doc): """Fetch document (if necessary). Parameters ---------- doc : {dict, string} A dictionary representing a handle returned by es_document, or a plain string. A Unicode string (Python 2 unicode, Python 3 str) will be returned as-is. A byte string (Python 2 str, Python 3 bytes) will be run through chardet to guess the encoding, then decoded with errors="replace". Returns ------- content : string Document contents. """ if isinstance(doc, dict) and set(doc.keys()) == set(_ES_DOC_FIELDS): idx, typ, id, field = [doc[k] for k in _ES_DOC_FIELDS] return _es().get_source(index=idx, doc_type=typ, id=id)[field] elif isinstance(doc, unicode): return doc elif isinstance(doc, str): enc = chardetect(doc)['encoding'] return doc.decode(enc, errors="replace") else: raise TypeError("fetch expected es_document or string, got %s" % type(doc))
def _readline_decoder(self , bytes_): global _ENCODING try: return bytes_.decode(_ENCODING).replace('\r','\n') except: _encoding = chardetect(bytes_)['encoding'] _ENCODING = _encoding return bytes_.decode(_encoding).replace('\r','\n')
def _unicode_noerrs(self, string): if not string: return u"" if type(string) == type(unicode()): return string try: return unicode(string, encoding=chardetect(string)["encoding"]) except: raise UnicodeWarning("EXCEPTION IN FileChooserThumbView._unicode_noerrs skipped.\nThis means that file list might not contain all the files that are really present in the directory.\nThis was the exception:") traceback.print_exc() return u""
def is_text_file(string): if ('defkeymap.map' in string): pass path = ut.join_path(c['sourcedir'], string) inpt = open(path, "rb") fsiz = ut.file_size(path) abuf = inpt.read(min(1024, fsiz)) inpt.close() ret = chardetect(abuf) return (isinstance(ret, dict) and ('encoding' in ret) and (ret['encoding'] is not None))
def is_text_file(string): if ('defkeymap.map' in string): pass path = ut.join_path(c['sourcedir'], string) inpt = open(path, "rb") fsiz = ut.file_size(path) abuf = inpt.read(min(1024, fsiz)) inpt.close() ret = chardetect(abuf) return (isinstance(ret, dict) and ('encoding' in ret) and (ret['encoding'] is not None))
def _unicode_noerrs(self, string): if not string: return u"" if type(string) == type(unicode()): return string try: return unicode(string, encoding=chardetect(string)["encoding"]) except: raise UnicodeWarning( "EXCEPTION IN FileChooserThumbView._unicode_noerrs skipped.\nThis means that file list might not contain all the files that are really present in the directory.\nThis was the exception:" ) traceback.print_exc() return u""
def _unicode_noerrs(self, string): if not string: return u"" return unicode(string, encoding=chardetect(string)["encoding"])