From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from localhost (localhost [127.0.0.1]) by olra.theworths.org (Postfix) with ESMTP id B87E4431FD0 for ; Thu, 15 Sep 2011 10:41:16 -0700 (PDT) X-Virus-Scanned: Debian amavisd-new at olra.theworths.org X-Spam-Flag: NO X-Spam-Score: -0.799 X-Spam-Level: X-Spam-Status: No, score=-0.799 tagged_above=-999 required=5 tests=[DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_LOW=-0.7] autolearn=disabled Received: from olra.theworths.org ([127.0.0.1]) by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id KyW6qRfeKQJb for ; Thu, 15 Sep 2011 10:41:15 -0700 (PDT) Received: from mail-qy0-f174.google.com (mail-qy0-f174.google.com [209.85.216.174]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (No client certificate requested) by olra.theworths.org (Postfix) with ESMTPS id 02724431FB6 for ; Thu, 15 Sep 2011 10:41:14 -0700 (PDT) Received: by qyk30 with SMTP id 30so5566718qyk.5 for ; Thu, 15 Sep 2011 10:41:14 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date :message-id:mime-version:x-mailer; bh=juxIYkA40P8ffh4j3FmgXR/aKSAEVBudgWnVX2PzXKw=; b=wd2jTzBokDPLh7bvXThGYgnMJIZ7QmHnE8b6CL4V7fBgI0U/it/w2yKzFfJo4wzu3o QcgLnRdyA+gfyDCJ0OorsgaA1OvMHKB2oO4ACtSQ/ZJKzri62JXW3FXa+uqpxjBiopzd 52/O2w4sGkTG1zJDziOvCF4G1rmyi1ovNPe7I= Received: by 10.224.212.129 with SMTP id gs1mr1123495qab.104.1316108474355; Thu, 15 Sep 2011 10:41:14 -0700 (PDT) Received: from [192.168.1.190] (pool-68-163-190-45.bos.east.verizon.net. [68.163.190.45]) by mx.google.com with ESMTPS id gz3sm8015793qab.18.2011.09.15.10.41.12 (version=SSLv3 cipher=OTHER); Thu, 15 Sep 2011 10:41:13 -0700 (PDT) Subject: Python Unicode Was: Not much database creation error From: Martin Owens To: Sebastian Spaeth In-Reply-To: <8739g7gnb4.fsf@SSpaeth.de> References: <1315110898.32058.13.camel@delen> <87vct7t7m4.fsf@SSpaeth.de> <1315373219.32058.157.camel@delen> <8739g7gnb4.fsf@SSpaeth.de> Content-Type: multipart/mixed; boundary="=-0VlEcVbZa7gbgZ+lT5kJ" Date: Thu, 15 Sep 2011 13:41:11 -0400 Message-ID: <1316108471.2201.24.camel@delen> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Cc: Notmuch developer list , Paul Tagliamonte X-BeenThere: notmuch@notmuchmail.org X-Mailman-Version: 2.1.13 Precedence: list List-Id: "Use and development of the notmuch mail system." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Sep 2011 17:41:16 -0000 --=-0VlEcVbZa7gbgZ+lT5kJ Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Hello Sebastian, I've attached a diff for some proposed changes to help make dealing with unicode and strings in the bindings more regular. I noticed some of the methods were protected and others were not. Let me know. Best Regards, Martin Owens On Thu, 2011-09-08 at 15:45 +0200, Sebastian Spaeth wrote: > I have to admit, I am not deep into the libnotmuch/xapian internals, > so > I might be the wrong person to ask (I just do some python bindings to > whatever libnotmuch provides). --=-0VlEcVbZa7gbgZ+lT5kJ Content-Disposition: attachment; filename="unicode.patch" Content-Type: text/x-patch; name="unicode.patch"; charset="UTF-8" Content-Transfer-Encoding: 7bit diff --git a/bindings/python/notmuch/database.py b/bindings/python/notmuch/database.py index b070019..4f44de0 100644 --- a/bindings/python/notmuch/database.py +++ b/bindings/python/notmuch/database.py @@ -19,12 +19,11 @@ Copyright 2010 Sebastian Spaeth ' import os from ctypes import c_int, c_char_p, c_void_p, c_uint, c_long, byref -from notmuch.globals import nmlib, STATUS, NotmuchError, Enum +from notmuch.globals import nmlib, STATUS, NotmuchError, Enum, _str from notmuch.thread import Threads from notmuch.message import Messages, Message from notmuch.tag import Tags - class Database(object): """Represents a notmuch database (wraps notmuch_database_t) @@ -105,7 +104,6 @@ class Database(object): Database._std_db_path = self._get_user_default_db() path = Database._std_db_path - assert isinstance(path, basestring), 'Path must be a string or None.' if create == False: self.open(path, mode) else: @@ -136,7 +134,7 @@ class Database(object): raise NotmuchError(message="Cannot create db, this Database() " "already has an open one.") - res = Database._create(path, Database.MODE.READ_WRITE) + res = Database._create(_str(path), Database.MODE.READ_WRITE) if res is None: raise NotmuchError( @@ -156,9 +154,7 @@ class Database(object): :exception: Raises :exc:`NotmuchError` in case of any failure (after printing an error message on stderr). """ - if isinstance(path, unicode): - path = path.encode('utf-8') - res = Database._open(path, mode) + res = Database._open(_str(path), mode) if res is None: raise NotmuchError( @@ -263,12 +259,10 @@ class Database(object): #we got a relative path, make it absolute abs_dirpath = os.path.abspath(os.path.join(self.get_path(), path)) - if isinstance(path, unicode): - path = path.encode('UTF-8') - dir_p = Database._get_directory(self._db, path) + dir_p = Database._get_directory(self._db, _str(path)) # return the Directory, init it with the absolute path - return Directory(abs_dirpath, dir_p, self) + return Directory(_str(abs_dirpath), dir_p, self) def add_message(self, filename, sync_maildir_flags=False): """Adds a new message to the database @@ -325,7 +319,7 @@ class Database(object): msg_p = c_void_p() status = nmlib.notmuch_database_add_message(self._db, - filename, + _str(filename), byref(msg_p)) if not status in [STATUS.SUCCESS, STATUS.DUPLICATE_MESSAGE_ID]: @@ -394,7 +388,7 @@ class Database(object): # Raise a NotmuchError if not initialized self._verify_initialized_db() - msg_p = Database._find_message(self._db, msgid) + msg_p = Database._find_message(self._db, _str(msgid)) if msg_p is None: return None return Message(msg_p, self) @@ -404,8 +398,7 @@ class Database(object): with this filename. """ self._verify_initialized_db() - - msg_p = Database._find_message_by_filename(self._db, filename) + msg_p = Database._find_message_by_filename(self._db, _str(filename)) return msg_p and Message(msg_p, self) or None def get_all_tags(self): @@ -558,11 +551,8 @@ class Query(object): raise NotmuchError(STATUS.NOT_INITIALIZED) # create reference to parent db to keep it alive self._db = db - if isinstance(querystr, unicode): - # xapian takes utf-8 encoded byte arrays - querystr = querystr.encode('utf-8') # create query, return None if too little mem available - query_p = Query._create(db.db_p, querystr) + query_p = Query._create(db.db_p, _str(querystr)) if query_p is None: NotmuchError(STATUS.NULL_POINTER) self._query = query_p diff --git a/bindings/python/notmuch/globals.py b/bindings/python/notmuch/globals.py index 77f2905..5c81076 100644 --- a/bindings/python/notmuch/globals.py +++ b/bindings/python/notmuch/globals.py @@ -98,3 +98,13 @@ class NotmuchError(Exception): return self.args[0] else: return STATUS.status2str(self.args[1]) + +# C++ code expects strings to be well formatted and +# unicode strings to have no null bytes. +def _str(value): + if not isinstance(value, basestring): + raise TypeError("Expected str or unicode, got %s" % str(type(value))) + if isinstance(value, unicode): + return value.encode('UTF-8') + return str(value) + diff --git a/bindings/python/notmuch/message.py b/bindings/python/notmuch/message.py index ae6ae1b..4f93a2a 100644 --- a/bindings/python/notmuch/message.py +++ b/bindings/python/notmuch/message.py @@ -21,7 +21,7 @@ Copyright 2010 Sebastian Spaeth ' from ctypes import c_char_p, c_void_p, c_long, c_uint, c_int from datetime import date -from notmuch.globals import nmlib, STATUS, NotmuchError, Enum +from notmuch.globals import nmlib, STATUS, NotmuchError, Enum, _str from notmuch.tag import Tags from notmuch.filename import Filenames import sys @@ -505,7 +505,7 @@ class Message(object): if self._msg is None: raise NotmuchError(STATUS.NOT_INITIALIZED) - status = nmlib.notmuch_message_add_tag(self._msg, tag) + status = nmlib.notmuch_message_add_tag(self._msg, _str(tag)) # bail out on failure if status != STATUS.SUCCESS: @@ -549,7 +549,7 @@ class Message(object): if self._msg is None: raise NotmuchError(STATUS.NOT_INITIALIZED) - status = nmlib.notmuch_message_remove_tag(self._msg, tag) + status = nmlib.notmuch_message_remove_tag(self._msg, _str(tag)) # bail out on error if status != STATUS.SUCCESS: raise NotmuchError(status) --=-0VlEcVbZa7gbgZ+lT5kJ--