diff options
| author | xmo-odoo <xmo-odoo@users.noreply.github.com> | 2014-05-23 12:21:33 +0200 |
|---|---|---|
| committer | xmo-odoo <xmo-odoo@users.noreply.github.com> | 2014-05-23 12:21:33 +0200 |
| commit | 576b00a196cd3a2f786cc660d636f4732f530484 (patch) | |
| tree | ee3c208f354a45fea2ee6606dda1ad46ea6a88f0 /addons/document_page/web | |
| parent | c69f0260efb496806696c25d1c8eea5725d52da7 (diff) | |
| parent | 9f6f9853a0326e55a9f5b8ad19919f121a6e1a89 (diff) | |
Merge pull request #174 from odoo-dev/tnx-remains
Various ex-module remains
Diffstat (limited to 'addons/document_page/web')
29 files changed, 0 insertions, 5780 deletions
diff --git a/addons/document_page/web/__init__.py b/addons/document_page/web/__init__.py deleted file mode 100644 index 6fb28f7f2ad..00000000000 --- a/addons/document_page/web/__init__.py +++ /dev/null @@ -1,4 +0,0 @@ -import widgets -import controllers - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/controllers/__init__.py b/addons/document_page/web/controllers/__init__.py deleted file mode 100644 index e1edf0f0f96..00000000000 --- a/addons/document_page/web/controllers/__init__.py +++ /dev/null @@ -1,3 +0,0 @@ -import wiki - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/controllers/wiki.py b/addons/document_page/web/controllers/wiki.py deleted file mode 100644 index 2f147827f24..00000000000 --- a/addons/document_page/web/controllers/wiki.py +++ /dev/null @@ -1,65 +0,0 @@ -############################################################################### -# -# Copyright (C) 2007-TODAY Tiny ERP Pvt Ltd. All Rights Reserved. -# -# $Id$ -# -# Developed by Tiny (http://openerp.com) and Axelor (http://axelor.com). -# -# The OpenERP web client is distributed under the "OpenERP Public License". -# It's based on Mozilla Public License Version (MPL) 1.1 with following -# restrictions: -# -# - All names, links and logos of Tiny, OpenERP and Axelor must be -# kept as in original distribution without any changes in all software -# screens, especially in start-up page and the software header, even if -# the application source code has been changed or updated or code has been -# added. -# -# - All distributions of the software must keep source code with OEPL. -# -# - All integrations to any other software must keep source code with OEPL. -# -# If you need commercial licence to remove this kind of restriction please -# contact us. -# -# You can see the MPL licence at: http://www.mozilla.org/MPL/MPL-1.1.html -# -############################################################################### -import base64 - -import cherrypy - -import openobject -from openobject.tools import expose - -from openerp.controllers import SecuredController - - -class WikiView(SecuredController): - _cp_path = "/wiki/wiki" - - def get_attachment(self, **kwargs): - attachments = openobject.rpc.RPCProxy('ir.attachment') - file_name = kwargs.get('file').replace("'", '').strip() - id = kwargs.get('id').strip() - - ids = attachments.search([('datas_fname', '=', file_name), - ('res_model', '=', 'wiki.wiki'), - ('res_id', '=', id)]) - - res = attachments.read(ids, ['datas'])[0].get('datas') - return res, file_name - - @expose(content_type='application/octet') - def getImage(self, *kw, **kws): - res, _ = self.get_attachment(**kws) - return base64.decodestring(res) - - @expose(content_type='application/octet') - def getfile(self, *kw, **kws): - res, file_name = self.get_attachment(**kws) - cherrypy.response.headers['Content-Disposition'] = 'filename="%s"' % (file_name,) - return base64.decodestring(res) - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/locales/bg.po b/addons/document_page/web/locales/bg.po deleted file mode 100644 index d331ed5de7f..00000000000 --- a/addons/document_page/web/locales/bg.po +++ /dev/null @@ -1,22 +0,0 @@ -# Bulgarian translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-02-11 01:13+0000\n" -"Last-Translator: Dimitar Markov <Unknown>\n" -"Language-Team: Bulgarian <bg@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-02-12 06:06+0000\n" -"X-Generator: Launchpad (build 12351)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Съдържание" diff --git a/addons/document_page/web/locales/ca.po b/addons/document_page/web/locales/ca.po deleted file mode 100644 index a946dab86ec..00000000000 --- a/addons/document_page/web/locales/ca.po +++ /dev/null @@ -1,22 +0,0 @@ -# Catalan translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-03-12 20:33+0000\n" -"Last-Translator: mgaja (GrupoIsep.com) <Unknown>\n" -"Language-Team: Catalan <ca@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-03-13 06:16+0000\n" -"X-Generator: Launchpad (build 12559)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Índex" diff --git a/addons/document_page/web/locales/da.po b/addons/document_page/web/locales/da.po deleted file mode 100644 index 35d12ed6632..00000000000 --- a/addons/document_page/web/locales/da.po +++ /dev/null @@ -1,22 +0,0 @@ -# Danish translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-04-29 12:05+0000\n" -"Last-Translator: Hans Henrik Gabelgaard <Unknown>\n" -"Language-Team: Danish <da@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-04-30 06:08+0000\n" -"X-Generator: Launchpad (build 12758)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Indholdsfortegnelse" diff --git a/addons/document_page/web/locales/de.po b/addons/document_page/web/locales/de.po deleted file mode 100644 index 8718cd9713d..00000000000 --- a/addons/document_page/web/locales/de.po +++ /dev/null @@ -1,22 +0,0 @@ -# German translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-02-11 11:54+0000\n" -"Last-Translator: Ferdinand @ Camptocamp <Unknown>\n" -"Language-Team: German <de@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-02-12 06:06+0000\n" -"X-Generator: Launchpad (build 12351)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Inhaltsverzeichnis" diff --git a/addons/document_page/web/locales/de_DE/LC_MESSAGES/javascript.po b/addons/document_page/web/locales/de_DE/LC_MESSAGES/javascript.po deleted file mode 100644 index ea8fd6999df..00000000000 --- a/addons/document_page/web/locales/de_DE/LC_MESSAGES/javascript.po +++ /dev/null @@ -1,20 +0,0 @@ -# German (Germany) translations for PROJECT. -# Copyright (C) 2009 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2009. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2009-11-18 17:21+0530\n" -"PO-Revision-Date: 2010-08-02 17:53+0530\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: de_DE <LL@li.org>\n" -"Plural-Forms: nplurals=2; plural=(n != 1)\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - diff --git a/addons/document_page/web/locales/de_DE/LC_MESSAGES/messages.po b/addons/document_page/web/locales/de_DE/LC_MESSAGES/messages.po deleted file mode 100644 index 79b06791b65..00000000000 --- a/addons/document_page/web/locales/de_DE/LC_MESSAGES/messages.po +++ /dev/null @@ -1,24 +0,0 @@ -# German (Germany) translations for PROJECT. -# Copyright (C) 2009 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2009. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2009-11-18 17:21+0530\n" -"PO-Revision-Date: 2010-08-02 17:53+0530\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: de_DE <LL@li.org>\n" -"Plural-Forms: nplurals=2; plural=(n != 1)\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "" - diff --git a/addons/document_page/web/locales/es_CR.po b/addons/document_page/web/locales/es_CR.po deleted file mode 100644 index d64a49bccbb..00000000000 --- a/addons/document_page/web/locales/es_CR.po +++ /dev/null @@ -1,23 +0,0 @@ -# Translations template for PROJECT. -# Copyright (C) 2010 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2010. -# -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2012-02-08 03:00-0600\n" -"Last-Translator: Carlos Vásquez - CLEARCORP <carlos.vasquez@clearcorp.co.cr>\n" -"Language-Team: LANGUAGE <LL@li.org>\n" -"Language: \n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "" - diff --git a/addons/document_page/web/locales/es_ES/LC_MESSAGES/javascript.po b/addons/document_page/web/locales/es_ES/LC_MESSAGES/javascript.po deleted file mode 100644 index 0c44218f06a..00000000000 --- a/addons/document_page/web/locales/es_ES/LC_MESSAGES/javascript.po +++ /dev/null @@ -1,20 +0,0 @@ -# Spanish (Spain) translations for PROJECT. -# Copyright (C) 2009 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2009. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2009-11-18 17:21+0530\n" -"PO-Revision-Date: 2010-08-02 17:53+0530\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: es_ES <LL@li.org>\n" -"Plural-Forms: nplurals=2; plural=(n != 1)\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - diff --git a/addons/document_page/web/locales/es_ES/LC_MESSAGES/messages.po b/addons/document_page/web/locales/es_ES/LC_MESSAGES/messages.po deleted file mode 100644 index 72f8c72bbf0..00000000000 --- a/addons/document_page/web/locales/es_ES/LC_MESSAGES/messages.po +++ /dev/null @@ -1,24 +0,0 @@ -# Spanish (Spain) translations for PROJECT. -# Copyright (C) 2009 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2009. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2009-11-18 17:21+0530\n" -"PO-Revision-Date: 2010-08-02 17:53+0530\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: es_ES <LL@li.org>\n" -"Plural-Forms: nplurals=2; plural=(n != 1)\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "" - diff --git a/addons/document_page/web/locales/es_PY.po b/addons/document_page/web/locales/es_PY.po deleted file mode 100644 index c76f7a3362a..00000000000 --- a/addons/document_page/web/locales/es_PY.po +++ /dev/null @@ -1,22 +0,0 @@ -# Spanish (Paraguay) translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-03-21 16:31+0000\n" -"Last-Translator: fadel <Unknown>\n" -"Language-Team: Spanish (Paraguay) <es_PY@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-03-22 06:23+0000\n" -"X-Generator: Launchpad (build 12559)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Tabla de Contenido" diff --git a/addons/document_page/web/locales/fr.po b/addons/document_page/web/locales/fr.po deleted file mode 100644 index 18a1611dac0..00000000000 --- a/addons/document_page/web/locales/fr.po +++ /dev/null @@ -1,22 +0,0 @@ -# French translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-02-11 20:16+0000\n" -"Last-Translator: lolivier <olivier.lenoir@free.fr>\n" -"Language-Team: French <fr@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-02-12 06:06+0000\n" -"X-Generator: Launchpad (build 12351)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Table des matières" diff --git a/addons/document_page/web/locales/fr_FR/LC_MESSAGES/javascript.po b/addons/document_page/web/locales/fr_FR/LC_MESSAGES/javascript.po deleted file mode 100644 index 31f9c5eda45..00000000000 --- a/addons/document_page/web/locales/fr_FR/LC_MESSAGES/javascript.po +++ /dev/null @@ -1,20 +0,0 @@ -# French (France) translations for PROJECT. -# Copyright (C) 2009 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2009. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2009-11-18 17:21+0530\n" -"PO-Revision-Date: 2010-08-02 17:53+0530\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: fr_FR <LL@li.org>\n" -"Plural-Forms: nplurals=2; plural=(n > 1)\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - diff --git a/addons/document_page/web/locales/fr_FR/LC_MESSAGES/messages.po b/addons/document_page/web/locales/fr_FR/LC_MESSAGES/messages.po deleted file mode 100644 index 181738f734f..00000000000 --- a/addons/document_page/web/locales/fr_FR/LC_MESSAGES/messages.po +++ /dev/null @@ -1,24 +0,0 @@ -# French (France) translations for PROJECT. -# Copyright (C) 2009 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2009. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2009-11-18 17:21+0530\n" -"PO-Revision-Date: 2010-08-02 17:53+0530\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: fr_FR <LL@li.org>\n" -"Plural-Forms: nplurals=2; plural=(n > 1)\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "" - diff --git a/addons/document_page/web/locales/gl.po b/addons/document_page/web/locales/gl.po deleted file mode 100644 index 645a5607fb5..00000000000 --- a/addons/document_page/web/locales/gl.po +++ /dev/null @@ -1,22 +0,0 @@ -# Galician translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-03-02 23:19+0000\n" -"Last-Translator: Santi (Pexego) <santiago@pexego.es>\n" -"Language-Team: Galician <gl@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-03-03 06:01+0000\n" -"X-Generator: Launchpad (build 12351)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Índice" diff --git a/addons/document_page/web/locales/javascript.pot b/addons/document_page/web/locales/javascript.pot deleted file mode 100644 index 725ce7a4883..00000000000 --- a/addons/document_page/web/locales/javascript.pot +++ /dev/null @@ -1,19 +0,0 @@ -# Translations template for PROJECT. -# Copyright (C) 2010 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2010. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: LANGUAGE <LL@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - diff --git a/addons/document_page/web/locales/messages.pot b/addons/document_page/web/locales/messages.pot deleted file mode 100644 index 16c76567441..00000000000 --- a/addons/document_page/web/locales/messages.pot +++ /dev/null @@ -1,23 +0,0 @@ -# Translations template for PROJECT. -# Copyright (C) 2010 ORGANIZATION -# This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2010. -# -#, fuzzy -msgid "" -msgstr "" -"Project-Id-Version: PROJECT VERSION\n" -"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" -"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: LANGUAGE <LL@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=utf-8\n" -"Content-Transfer-Encoding: 8bit\n" -"Generated-By: Babel None\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "" - diff --git a/addons/document_page/web/locales/ru.po b/addons/document_page/web/locales/ru.po deleted file mode 100644 index 6c609b49c41..00000000000 --- a/addons/document_page/web/locales/ru.po +++ /dev/null @@ -1,22 +0,0 @@ -# Russian translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-03-16 00:17+0000\n" -"Last-Translator: Stanislav Hanzhin <Unknown>\n" -"Language-Team: Russian <ru@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-03-17 06:12+0000\n" -"X-Generator: Launchpad (build 12559)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Содержание" diff --git a/addons/document_page/web/locales/sk.po b/addons/document_page/web/locales/sk.po deleted file mode 100644 index f101cf6928a..00000000000 --- a/addons/document_page/web/locales/sk.po +++ /dev/null @@ -1,22 +0,0 @@ -# Slovak translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-02-21 13:05+0000\n" -"Last-Translator: Radoslav Sloboda <rado.sloboda@gmail.com>\n" -"Language-Team: Slovak <sk@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-02-22 14:27+0000\n" -"X-Generator: Launchpad (build 12351)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "Obsah" diff --git a/addons/document_page/web/locales/tr.po b/addons/document_page/web/locales/tr.po deleted file mode 100644 index baa56e0f9db..00000000000 --- a/addons/document_page/web/locales/tr.po +++ /dev/null @@ -1,22 +0,0 @@ -# Turkish translation for openobject-addons -# Copyright (c) 2011 Rosetta Contributors and Canonical Ltd 2011 -# This file is distributed under the same license as the openobject-addons package. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2011. -# -msgid "" -msgstr "" -"Project-Id-Version: openobject-addons\n" -"Report-Msgid-Bugs-To: FULL NAME <EMAIL@ADDRESS>\n" -"POT-Creation-Date: 2010-08-02 17:52+0530\n" -"PO-Revision-Date: 2011-02-08 21:20+0000\n" -"Last-Translator: Ahmet Altınışık <Unknown>\n" -"Language-Team: Turkish <tr@li.org>\n" -"MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" -"Content-Transfer-Encoding: 8bit\n" -"X-Launchpad-Export-Date: 2011-02-09 06:02+0000\n" -"X-Generator: Launchpad (build 12177)\n" - -#: widgets/wikimarkup/__init__.py:1981 -msgid "Table of Contents" -msgstr "İçindekiler" diff --git a/addons/document_page/web/static/css/wiki.css b/addons/document_page/web/static/css/wiki.css deleted file mode 100644 index 51a649354d6..00000000000 --- a/addons/document_page/web/static/css/wiki.css +++ /dev/null @@ -1,32 +0,0 @@ -.wikiwidget #toc { - border:1px solid #aaaaaa; - background-color:#f9f9f9; - padding:5px; -} - -h1, h2, h3, h4, h5, h6 { - color: black; - background: none; - font-weight: normal; - margin: 0; - padding-top: .5em; - padding-bottom: .17em; - border-bottom: 1px solid #aaa; -} -h1 { font-size: 188%; } -h2 { font-size: 150%; } -h3, h4, h5, h6 { - border-bottom: none; -} -h3 { font-size: 132%; } -h4 { font-size: 116%; } -h5 { font-size: 100%; } -h6 { font-size: 80%; } - -pre { - background-color:#F9F9F9; - border:1px dashed #2F6FAB; - color:black; - line-height:1.1em; - padding:1em; -} diff --git a/addons/document_page/web/widgets/__init__.py b/addons/document_page/web/widgets/__init__.py deleted file mode 100644 index 4b2c273d02a..00000000000 --- a/addons/document_page/web/widgets/__init__.py +++ /dev/null @@ -1,3 +0,0 @@ -from wiki import WikiWidget - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/widgets/rss/__init__.py b/addons/document_page/web/widgets/rss/__init__.py deleted file mode 100644 index ff95e8bd52a..00000000000 --- a/addons/document_page/web/widgets/rss/__init__.py +++ /dev/null @@ -1,3 +0,0 @@ -import feedparser - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/widgets/rss/feedparser.py b/addons/document_page/web/widgets/rss/feedparser.py deleted file mode 100755 index 35cbb975d3f..00000000000 --- a/addons/document_page/web/widgets/rss/feedparser.py +++ /dev/null @@ -1,2860 +0,0 @@ -#!/usr/bin/env python -"""Universal feed parser - -Handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds - -Visit http://feedparser.org/ for the latest version -Visit http://feedparser.org/docs/ for the latest documentation - -Required: Python 2.1 or later -Recommended: Python 2.3 or later -Recommended: CJKCodecs and iconv_codec <http://cjkpython.i18n.org/> -""" - -__version__ = "4.1"# + "$Revision: 1.92 $"[11:15] + "-cvs" -__license__ = """Copyright (c) 2002-2006, Mark Pilgrim, All rights reserved. - -Redistribution and use in source and binary forms, with or without modification, -are permitted provided that the following conditions are met: - -* Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. -* Redistributions in binary form must reproduce the above copyright notice, - this list of conditions and the following disclaimer in the documentation - and/or other materials provided with the distribution. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS' -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE.""" -__author__ = "Mark Pilgrim <http://diveintomark.org/>" -__contributors__ = ["Jason Diamond <http://injektilo.org/>", - "John Beimler <http://john.beimler.org/>", - "Fazal Majid <http://www.majid.info/mylos/weblog/>", - "Aaron Swartz <http://aaronsw.com/>", - "Kevin Marks <http://epeus.blogspot.com/>"] -_debug = 0 - -# HTTP "User-Agent" header to send to servers when downloading feeds. -# If you are embedding feedparser in a larger application, you should -# change this to your application name and URL. -USER_AGENT = "UniversalFeedParser/%s +http://feedparser.org/" % __version__ - -# HTTP "Accept" header to send to servers when downloading feeds. If you don't -# want to send an Accept header, set this to None. -ACCEPT_HEADER = "application/atom+xml,application/rdf+xml,application/rss+xml,application/x-netcdf,application/xml;q=0.9,text/xml;q=0.2,*/*;q=0.1" - -# List of preferred XML parsers, by SAX driver name. These will be tried first, -# but if they're not installed, Python will keep searching through its own list -# of pre-installed parsers until it finds one that supports everything we need. -PREFERRED_XML_PARSERS = ["drv_libxml2"] - -# If you want feedparser to automatically run HTML markup through HTML Tidy, set -# this to 1. Requires mxTidy <http://www.egenix.com/files/python/mxTidy.html> -# or utidylib <http://utidylib.berlios.de/>. -TIDY_MARKUP = 0 - -# List of Python interfaces for HTML Tidy, in order of preference. Only useful -# if TIDY_MARKUP = 1 -PREFERRED_TIDY_INTERFACES = ["uTidy", "mxTidy"] - -# ---------- required modules (should come with any Python distribution) ---------- -import sgmllib, re, sys, copy, urlparse, time, rfc822, types, cgi, urllib, urllib2 -try: - from cStringIO import StringIO as _StringIO -except: - from StringIO import StringIO as _StringIO - -# ---------- optional modules (feedparser will work without these, but with reduced functionality) ---------- - -# gzip is included with most Python distributions, but may not be available if you compiled your own -try: - import gzip -except: - gzip = None -try: - import zlib -except: - zlib = None - -# If a real XML parser is available, feedparser will attempt to use it. feedparser has -# been tested with the built-in SAX parser, PyXML, and libxml2. On platforms where the -# Python distribution does not come with an XML parser (such as Mac OS X 10.2 and some -# versions of FreeBSD), feedparser will quietly fall back on regex-based parsing. -try: - import xml.sax - xml.sax.make_parser(PREFERRED_XML_PARSERS) # test for valid parsers - from xml.sax.saxutils import escape as _xmlescape - _XML_AVAILABLE = 1 -except: - _XML_AVAILABLE = 0 - def _xmlescape(data): - data = data.replace('&', '&') - data = data.replace('>', '>') - data = data.replace('<', '<') - return data - -# base64 support for Atom feeds that contain embedded binary data -try: - import base64, binascii -except: - base64 = binascii = None - -# cjkcodecs and iconv_codec provide support for more character encodings. -# Both are available from http://cjkpython.i18n.org/ -try: - import cjkcodecs.aliases -except: - pass -try: - import iconv_codec -except: - pass - -# chardet library auto-detects character encodings -# Download from http://chardet.feedparser.org/ -try: - import chardet - if _debug: - import chardet.constants - chardet.constants._debug = 1 -except: - chardet = None - -# ---------- don't touch these ---------- -class ThingsNobodyCaresAboutButMe(Exception): pass -class CharacterEncodingOverride(ThingsNobodyCaresAboutButMe): pass -class CharacterEncodingUnknown(ThingsNobodyCaresAboutButMe): pass -class NonXMLContentType(ThingsNobodyCaresAboutButMe): pass -class UndeclaredNamespace(Exception): pass - -sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*') -sgmllib.special = re.compile('<!') -sgmllib.charref = re.compile('&#(x?[0-9A-Fa-f]+)[^0-9A-Fa-f]') - -SUPPORTED_VERSIONS = {'': 'unknown', - 'rss090': 'RSS 0.90', - 'rss091n': 'RSS 0.91 (Netscape)', - 'rss091u': 'RSS 0.91 (Userland)', - 'rss092': 'RSS 0.92', - 'rss093': 'RSS 0.93', - 'rss094': 'RSS 0.94', - 'rss20': 'RSS 2.0', - 'rss10': 'RSS 1.0', - 'rss': 'RSS (unknown version)', - 'atom01': 'Atom 0.1', - 'atom02': 'Atom 0.2', - 'atom03': 'Atom 0.3', - 'atom10': 'Atom 1.0', - 'atom': 'Atom (unknown version)', - 'cdf': 'CDF', - 'hotrss': 'Hot RSS' - } - -try: - UserDict = dict -except NameError: - # Python 2.1 does not have dict - from UserDict import UserDict - def dict(aList): - rc = {} - for k, v in aList: - rc[k] = v - return rc - -class FeedParserDict(UserDict): - keymap = {'channel': 'feed', - 'items': 'entries', - 'guid': 'id', - 'date': 'updated', - 'date_parsed': 'updated_parsed', - 'description': ['subtitle', 'summary'], - 'url': ['href'], - 'modified': 'updated', - 'modified_parsed': 'updated_parsed', - 'issued': 'published', - 'issued_parsed': 'published_parsed', - 'copyright': 'rights', - 'copyright_detail': 'rights_detail', - 'tagline': 'subtitle', - 'tagline_detail': 'subtitle_detail'} - def __getitem__(self, key): - if key == 'category': - return UserDict.__getitem__(self, 'tags')[0]['term'] - if key == 'categories': - return [(tag['scheme'], tag['term']) for tag in UserDict.__getitem__(self, 'tags')] - realkey = self.keymap.get(key, key) - if type(realkey) == types.ListType: - for k in realkey: - if UserDict.has_key(self, k): - return UserDict.__getitem__(self, k) - if UserDict.has_key(self, key): - return UserDict.__getitem__(self, key) - return UserDict.__getitem__(self, realkey) - - def __setitem__(self, key, value): - for k in self.keymap.keys(): - if key == k: - key = self.keymap[k] - if type(key) == types.ListType: - key = key[0] - return UserDict.__setitem__(self, key, value) - - def get(self, key, default=None): - if self.has_key(key): - return self[key] - else: - return default - - def setdefault(self, key, value): - if not self.has_key(key): - self[key] = value - return self[key] - - def has_key(self, key): - try: - return hasattr(self, key) or UserDict.has_key(self, key) - except AttributeError: - return False - - def __getattr__(self, key): - try: - return self.__dict__[key] - except KeyError: - pass - try: - assert not key.startswith('_') - return self.__getitem__(key) - except: - raise AttributeError, "Object has no attribute '%s'" % key - - def __setattr__(self, key, value): - if key.startswith('_') or key == 'data': - self.__dict__[key] = value - else: - return self.__setitem__(key, value) - - def __contains__(self, key): - return self.has_key(key) - -def zopeCompatibilityHack(): - global FeedParserDict - del FeedParserDict - def FeedParserDict(aDict=None): - rc = {} - if aDict: - rc.update(aDict) - return rc - -_ebcdic_to_ascii_map = None -def _ebcdic_to_ascii(s): - global _ebcdic_to_ascii_map - if not _ebcdic_to_ascii_map: - emap = ( - 0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15, - 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31, - 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7, - 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26, - 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33, - 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94, - 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63, - 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34, - 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200,201, - 202,106,107,108,109,110,111,112,113,114,203,204,205,206,207,208, - 209,126,115,116,117,118,119,120,121,122,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231, - 123,65,66,67,68,69,70,71,72,73,232,233,234,235,236,237, - 125,74,75,76,77,78,79,80,81,82,238,239,240,241,242,243, - 92,159,83,84,85,86,87,88,89,90,244,245,246,247,248,249, - 48,49,50,51,52,53,54,55,56,57,250,251,252,253,254,255 - ) - import string - _ebcdic_to_ascii_map = string.maketrans( \ - ''.join(map(chr, range(256))), ''.join(map(chr, emap))) - return s.translate(_ebcdic_to_ascii_map) - -_urifixer = re.compile('^([A-Za-z][A-Za-z0-9+-.]*://)(/*)(.*?)') -def _urljoin(base, uri): - uri = _urifixer.sub(r'\1\3', uri) - return urlparse.urljoin(base, uri) - -class _FeedParserMixin: - namespaces = {'': '', - 'http://backend.userland.com/rss': '', - 'http://blogs.law.harvard.edu/tech/rss': '', - 'http://purl.org/rss/1.0/': '', - 'http://my.netscape.com/rdf/simple/0.9/': '', - 'http://example.com/newformat#': '', - 'http://example.com/necho': '', - 'http://purl.org/echo/': '', - 'uri/of/echo/namespace#': '', - 'http://purl.org/pie/': '', - 'http://purl.org/atom/ns#': '', - 'http://www.w3.org/2005/Atom': '', - 'http://purl.org/rss/1.0/modules/rss091#': '', - - 'http://webns.net/mvcb/': 'admin', - 'http://purl.org/rss/1.0/modules/aggregation/': 'ag', - 'http://purl.org/rss/1.0/modules/annotate/': 'annotate', - 'http://media.tangent.org/rss/1.0/': 'audio', - 'http://backend.userland.com/blogChannelModule': 'blogChannel', - 'http://web.resource.org/cc/': 'cc', - 'http://backend.userland.com/creativeCommonsRssModule': 'creativeCommons', - 'http://purl.org/rss/1.0/modules/company': 'co', - 'http://purl.org/rss/1.0/modules/content/': 'content', - 'http://my.theinfo.org/changed/1.0/rss/': 'cp', - 'http://purl.org/dc/elements/1.1/': 'dc', - 'http://purl.org/dc/terms/': 'dcterms', - 'http://purl.org/rss/1.0/modules/email/': 'email', - 'http://purl.org/rss/1.0/modules/event/': 'ev', - 'http://rssnamespace.org/feedburner/ext/1.0': 'feedburner', - 'http://freshmeat.net/rss/fm/': 'fm', - 'http://xmlns.com/foaf/0.1/': 'foaf', - 'http://www.w3.org/2003/01/geo/wgs84_pos#': 'geo', - 'http://postneo.com/icbm/': 'icbm', - 'http://purl.org/rss/1.0/modules/image/': 'image', - 'http://www.itunes.com/DTDs/PodCast-1.0.dtd': 'itunes', - 'http://example.com/DTDs/PodCast-1.0.dtd': 'itunes', - 'http://purl.org/rss/1.0/modules/link/': 'l', - 'http://search.yahoo.com/mrss': 'media', - 'http://madskills.com/public/xml/rss/module/pingback/': 'pingback', - 'http://prismstandard.org/namespaces/1.2/basic/': 'prism', - 'http://www.w3.org/1999/02/22-rdf-syntax-ns#': 'rdf', - 'http://www.w3.org/2000/01/rdf-schema#': 'rdfs', - 'http://purl.org/rss/1.0/modules/reference/': 'ref', - 'http://purl.org/rss/1.0/modules/richequiv/': 'reqv', - 'http://purl.org/rss/1.0/modules/search/': 'search', - 'http://purl.org/rss/1.0/modules/slash/': 'slash', - 'http://schemas.xmlsoap.org/soap/envelope/': 'soap', - 'http://purl.org/rss/1.0/modules/servicestatus/': 'ss', - 'http://hacks.benhammersley.com/rss/streaming/': 'str', - 'http://purl.org/rss/1.0/modules/subscription/': 'sub', - 'http://purl.org/rss/1.0/modules/syndication/': 'sy', - 'http://purl.org/rss/1.0/modules/taxonomy/': 'taxo', - 'http://purl.org/rss/1.0/modules/threading/': 'thr', - 'http://purl.org/rss/1.0/modules/textinput/': 'ti', - 'http://madskills.com/public/xml/rss/module/trackback/':'trackback', - 'http://wellformedweb.org/commentAPI/': 'wfw', - 'http://purl.org/rss/1.0/modules/wiki/': 'wiki', - 'http://www.w3.org/1999/xhtml': 'xhtml', - 'http://www.w3.org/XML/1998/namespace': 'xml', - 'http://schemas.pocketsoap.com/rss/myDescModule/': 'szf' -} - _matchnamespaces = {} - - can_be_relative_uri = ['link', 'id', 'wfw_comment', 'wfw_commentrss', 'docs', 'url', 'href', 'comments', 'license', 'icon', 'logo'] - can_contain_relative_uris = ['content', 'title', 'summary', 'info', 'tagline', 'subtitle', 'copyright', 'rights', 'description'] - can_contain_dangerous_markup = ['content', 'title', 'summary', 'info', 'tagline', 'subtitle', 'copyright', 'rights', 'description'] - html_types = ['text/html', 'application/xhtml+xml'] - - def __init__(self, baseuri=None, baselang=None, encoding='utf-8'): - if _debug: sys.stderr.write('initializing FeedParser\n') - if not self._matchnamespaces: - for k, v in self.namespaces.items(): - self._matchnamespaces[k.lower()] = v - self.feeddata = FeedParserDict() # feed-level data - self.encoding = encoding # character encoding - self.entries = [] # list of entry-level data - self.version = '' # feed type/version, see SUPPORTED_VERSIONS - self.namespacesInUse = {} # dictionary of namespaces defined by the feed - - # the following are used internally to track state; - # this is really out of control and should be refactored - self.infeed = 0 - self.inentry = 0 - self.incontent = 0 - self.intextinput = 0 - self.inimage = 0 - self.inauthor = 0 - self.incontributor = 0 - self.inpublisher = 0 - self.insource = 0 - self.sourcedata = FeedParserDict() - self.contentparams = FeedParserDict() - self._summaryKey = None - self.namespacemap = {} - self.elementstack = [] - self.basestack = [] - self.langstack = [] - self.baseuri = baseuri or '' - self.lang = baselang or None - if baselang: - self.feeddata['language'] = baselang - - def unknown_starttag(self, tag, attrs): - if _debug: sys.stderr.write('start %s with %s\n' % (tag, attrs)) - # normalize attrs - attrs = [(k.lower(), v) for k, v in attrs] - attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] - - # track xml:base and xml:lang - attrsD = dict(attrs) - baseuri = attrsD.get('xml:base', attrsD.get('base')) or self.baseuri - self.baseuri = _urljoin(self.baseuri, baseuri) - lang = attrsD.get('xml:lang', attrsD.get('lang')) - if lang == '': - # xml:lang could be explicitly set to '', we need to capture that - lang = None - elif lang is None: - # if no xml:lang is specified, use parent lang - lang = self.lang - if lang: - if tag in ('feed', 'rss', 'rdf:RDF'): - self.feeddata['language'] = lang - self.lang = lang - self.basestack.append(self.baseuri) - self.langstack.append(lang) - - # track namespaces - for prefix, uri in attrs: - if prefix.startswith('xmlns:'): - self.trackNamespace(prefix[6:], uri) - elif prefix == 'xmlns': - self.trackNamespace(None, uri) - - # track inline content - if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): - # element declared itself as escaped markup, but it isn't really - self.contentparams['type'] = 'application/xhtml+xml' - if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': - # Note: probably shouldn't simply recreate localname here, but - # our namespace handling isn't actually 100% correct in cases where - # the feed redefines the default namespace (which is actually - # the usual case for inline content, thanks Sam), so here we - # cheat and just reconstruct the element based on localname - # because that compensates for the bugs in our namespace handling. - # This will horribly munge inline content with non-empty qnames, - # but nobody actually does that, so I'm not fixing it. - tag = tag.split(':')[-1] - return self.handle_data('<%s%s>' % (tag, ''.join([' %s="%s"' % t for t in attrs])), escape=0) - - # match namespaces - if tag.find(':') <> -1: - prefix, suffix = tag.split(':', 1) - else: - prefix, suffix = '', tag - prefix = self.namespacemap.get(prefix, prefix) - if prefix: - prefix = prefix + '_' - - # special hack for better tracking of empty textinput/image elements in illformed feeds - if (not prefix) and tag not in ('title', 'link', 'description', 'name'): - self.intextinput = 0 - if (not prefix) and tag not in ('title', 'link', 'description', 'url', 'href', 'width', 'height'): - self.inimage = 0 - - # call special handler (if defined) or default handler - methodname = '_start_' + prefix + suffix - try: - method = getattr(self, methodname) - return method(attrsD) - except AttributeError: - return self.push(prefix + suffix, 1) - - def unknown_endtag(self, tag): - if _debug: sys.stderr.write('end %s\n' % tag) - # match namespaces - if tag.find(':') <> -1: - prefix, suffix = tag.split(':', 1) - else: - prefix, suffix = '', tag - prefix = self.namespacemap.get(prefix, prefix) - if prefix: - prefix = prefix + '_' - - # call special handler (if defined) or default handler - methodname = '_end_' + prefix + suffix - try: - method = getattr(self, methodname) - method() - except AttributeError: - self.pop(prefix + suffix) - - # track inline content - if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): - # element declared itself as escaped markup, but it isn't really - self.contentparams['type'] = 'application/xhtml+xml' - if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml': - tag = tag.split(':')[-1] - self.handle_data('</%s>' % tag, escape=0) - - # track xml:base and xml:lang going out of scope - if self.basestack: - self.basestack.pop() - if self.basestack and self.basestack[-1]: - self.baseuri = self.basestack[-1] - if self.langstack: - self.langstack.pop() - if self.langstack: # and (self.langstack[-1] is not None): - self.lang = self.langstack[-1] - - def handle_charref(self, ref): - # called for each character reference, e.g. for ' ', ref will be '160' - if not self.elementstack: return - ref = ref.lower() - if ref in ('34', '38', '39', '60', '62', 'x22', 'x26', 'x27', 'x3c', 'x3e'): - text = '&#%s;' % ref - else: - if ref[0] == 'x': - c = int(ref[1:], 16) - else: - c = int(ref) - text = unichr(c).encode('utf-8') - self.elementstack[-1][2].append(text) - - def handle_entityref(self, ref): - # called for each entity reference, e.g. for '©', ref will be 'copy' - if not self.elementstack: return - if _debug: sys.stderr.write('entering handle_entityref with %s\n' % ref) - if ref in ('lt', 'gt', 'quot', 'amp', 'apos'): - text = '&%s;' % ref - else: - # entity resolution graciously donated by Aaron Swartz - def name2cp(k): - import htmlentitydefs - if hasattr(htmlentitydefs, 'name2codepoint'): # requires Python 2.3 - return htmlentitydefs.name2codepoint[k] - k = htmlentitydefs.entitydefs[k] - if k.startswith('&#') and k.endswith(';'): - return int(k[2:-1]) # not in latin-1 - return ord(k) - try: name2cp(ref) - except KeyError: text = '&%s;' % ref - else: text = unichr(name2cp(ref)).encode('utf-8') - self.elementstack[-1][2].append(text) - - def handle_data(self, text, escape=1): - # called for each block of plain text, i.e. outside of any tag and - # not containing any character or entity references - if not self.elementstack: return - if escape and self.contentparams.get('type') == 'application/xhtml+xml': - text = _xmlescape(text) - self.elementstack[-1][2].append(text) - - def handle_comment(self, text): - # called for each comment, e.g. <!-- insert message here --> - pass - - def handle_pi(self, text): - # called for each processing instruction, e.g. <?instruction> - pass - - def handle_decl(self, text): - pass - - def parse_declaration(self, i): - # override internal declaration handler to handle CDATA blocks - if _debug: sys.stderr.write('entering parse_declaration\n') - if self.rawdata[i:i+9] == '<![CDATA[': - k = self.rawdata.find(']]>', i) - if k == -1: k = len(self.rawdata) - self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0) - return k+3 - else: - k = self.rawdata.find('>', i) - return k+1 - - def mapContentType(self, contentType): - contentType = contentType.lower() - if contentType == 'text': - contentType = 'text/plain' - elif contentType == 'html': - contentType = 'text/html' - elif contentType == 'xhtml': - contentType = 'application/xhtml+xml' - return contentType - - def trackNamespace(self, prefix, uri): - loweruri = uri.lower() - if (prefix, loweruri) == (None, 'http://my.netscape.com/rdf/simple/0.9/') and not self.version: - self.version = 'rss090' - if loweruri == 'http://purl.org/rss/1.0/' and not self.version: - self.version = 'rss10' - if loweruri == 'http://www.w3.org/2005/atom' and not self.version: - self.version = 'atom10' - if loweruri.find('backend.userland.com/rss') <> -1: - # match any backend.userland.com namespace - uri = 'http://backend.userland.com/rss' - loweruri = uri - if self._matchnamespaces.has_key(loweruri): - self.namespacemap[prefix] = self._matchnamespaces[loweruri] - self.namespacesInUse[self._matchnamespaces[loweruri]] = uri - else: - self.namespacesInUse[prefix or ''] = uri - - def resolveURI(self, uri): - return _urljoin(self.baseuri or '', uri) - - def decodeEntities(self, element, data): - return data - - def push(self, element, expectingText): - self.elementstack.append([element, expectingText, []]) - - def pop(self, element, stripWhitespace=1): - if not self.elementstack: return - if self.elementstack[-1][0] != element: return - - element, expectingText, pieces = self.elementstack.pop() - output = ''.join(pieces) - if stripWhitespace: - output = output.strip() - if not expectingText: return output - - # decode base64 content - if base64 and self.contentparams.get('base64', 0): - try: - output = base64.decodestring(output) - except binascii.Error: - pass - except binascii.Incomplete: - pass - - # resolve relative URIs - if (element in self.can_be_relative_uri) and output: - output = self.resolveURI(output) - - # decode entities within embedded markup - if not self.contentparams.get('base64', 0): - output = self.decodeEntities(element, output) - - # remove temporary cruft from contentparams - try: - del self.contentparams['mode'] - except KeyError: - pass - try: - del self.contentparams['base64'] - except KeyError: - pass - - # resolve relative URIs within embedded markup - if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: - if element in self.can_contain_relative_uris: - output = _resolveRelativeURIs(output, self.baseuri, self.encoding) - - # sanitize embedded markup - if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types: - if element in self.can_contain_dangerous_markup: - output = _sanitizeHTML(output, self.encoding) - - if self.encoding and type(output) != type(u''): - try: - output = unicode(output, self.encoding) - except: - pass - - # categories/tags/keywords/whatever are handled in _end_category - if element == 'category': - return output - - # store output in appropriate place(s) - if self.inentry and not self.insource: - if element == 'content': - self.entries[-1].setdefault(element, []) - contentparams = copy.deepcopy(self.contentparams) - contentparams['value'] = output - self.entries[-1][element].append(contentparams) - elif element == 'link': - self.entries[-1][element] = output - if output: - self.entries[-1]['links'][-1]['href'] = output - else: - if element == 'description': - element = 'summary' - self.entries[-1][element] = output - if self.incontent: - contentparams = copy.deepcopy(self.contentparams) - contentparams['value'] = output - self.entries[-1][element + '_detail'] = contentparams - elif (self.infeed or self.insource) and (not self.intextinput) and (not self.inimage): - context = self._getContext() - if element == 'description': - element = 'subtitle' - context[element] = output - if element == 'link': - context['links'][-1]['href'] = output - elif self.incontent: - contentparams = copy.deepcopy(self.contentparams) - contentparams['value'] = output - context[element + '_detail'] = contentparams - return output - - def pushContent(self, tag, attrsD, defaultContentType, expectingText): - self.incontent += 1 - self.contentparams = FeedParserDict({ - 'type': self.mapContentType(attrsD.get('type', defaultContentType)), - 'language': self.lang, - 'base': self.baseuri}) - self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams) - self.push(tag, expectingText) - - def popContent(self, tag): - value = self.pop(tag) - self.incontent -= 1 - self.contentparams.clear() - return value - - def _mapToStandardPrefix(self, name): - colonpos = name.find(':') - if colonpos <> -1: - prefix = name[:colonpos] - suffix = name[colonpos+1:] - prefix = self.namespacemap.get(prefix, prefix) - name = prefix + ':' + suffix - return name - - def _getAttribute(self, attrsD, name): - return attrsD.get(self._mapToStandardPrefix(name)) - - def _isBase64(self, attrsD, contentparams): - if attrsD.get('mode', '') == 'base64': - return 1 - if self.contentparams['type'].startswith('text/'): - return 0 - if self.contentparams['type'].endswith('+xml'): - return 0 - if self.contentparams['type'].endswith('/xml'): - return 0 - return 1 - - def _itsAnHrefDamnIt(self, attrsD): - href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None))) - if href: - try: - del attrsD['url'] - except KeyError: - pass - try: - del attrsD['uri'] - except KeyError: - pass - attrsD['href'] = href - return attrsD - - def _save(self, key, value): - context = self._getContext() - context.setdefault(key, value) - - def _start_rss(self, attrsD): - versionmap = {'0.91': 'rss091u', - '0.92': 'rss092', - '0.93': 'rss093', - '0.94': 'rss094'} - if not self.version: - attr_version = attrsD.get('version', '') - version = versionmap.get(attr_version) - if version: - self.version = version - elif attr_version.startswith('2.'): - self.version = 'rss20' - else: - self.version = 'rss' - - def _start_dlhottitles(self, attrsD): - self.version = 'hotrss' - - def _start_channel(self, attrsD): - self.infeed = 1 - self._cdf_common(attrsD) - _start_feedinfo = _start_channel - - def _cdf_common(self, attrsD): - if attrsD.has_key('lastmod'): - self._start_modified({}) - self.elementstack[-1][-1] = attrsD['lastmod'] - self._end_modified() - if attrsD.has_key('href'): - self._start_link({}) - self.elementstack[-1][-1] = attrsD['href'] - self._end_link() - - def _start_feed(self, attrsD): - self.infeed = 1 - versionmap = {'0.1': 'atom01', - '0.2': 'atom02', - '0.3': 'atom03'} - if not self.version: - attr_version = attrsD.get('version') - version = versionmap.get(attr_version) - if version: - self.version = version - else: - self.version = 'atom' - - def _end_channel(self): - self.infeed = 0 - _end_feed = _end_channel - - def _start_image(self, attrsD): - self.inimage = 1 - self.push('image', 0) - context = self._getContext() - context.setdefault('image', FeedParserDict()) - - def _end_image(self): - self.pop('image') - self.inimage = 0 - - def _start_textinput(self, attrsD): - self.intextinput = 1 - self.push('textinput', 0) - context = self._getContext() - context.setdefault('textinput', FeedParserDict()) - _start_textInput = _start_textinput - - def _end_textinput(self): - self.pop('textinput') - self.intextinput = 0 - _end_textInput = _end_textinput - - def _start_author(self, attrsD): - self.inauthor = 1 - self.push('author', 1) - _start_managingeditor = _start_author - _start_dc_author = _start_author - _start_dc_creator = _start_author - _start_itunes_author = _start_author - - def _end_author(self): - self.pop('author') - self.inauthor = 0 - self._sync_author_detail() - _end_managingeditor = _end_author - _end_dc_author = _end_author - _end_dc_creator = _end_author - _end_itunes_author = _end_author - - def _start_itunes_owner(self, attrsD): - self.inpublisher = 1 - self.push('publisher', 0) - - def _end_itunes_owner(self): - self.pop('publisher') - self.inpublisher = 0 - self._sync_author_detail('publisher') - - def _start_contributor(self, attrsD): - self.incontributor = 1 - context = self._getContext() - context.setdefault('contributors', []) - context['contributors'].append(FeedParserDict()) - self.push('contributor', 0) - - def _end_contributor(self): - self.pop('contributor') - self.incontributor = 0 - - def _start_dc_contributor(self, attrsD): - self.incontributor = 1 - context = self._getContext() - context.setdefault('contributors', []) - context['contributors'].append(FeedParserDict()) - self.push('name', 0) - - def _end_dc_contributor(self): - self._end_name() - self.incontributor = 0 - - def _start_name(self, attrsD): - self.push('name', 0) - _start_itunes_name = _start_name - - def _end_name(self): - value = self.pop('name') - if self.inpublisher: - self._save_author('name', value, 'publisher') - elif self.inauthor: - self._save_author('name', value) - elif self.incontributor: - self._save_contributor('name', value) - elif self.intextinput: - context = self._getContext() - context['textinput']['name'] = value - _end_itunes_name = _end_name - - def _start_width(self, attrsD): - self.push('width', 0) - - def _end_width(self): - value = self.pop('width') - try: - value = int(value) - except: - value = 0 - if self.inimage: - context = self._getContext() - context['image']['width'] = value - - def _start_height(self, attrsD): - self.push('height', 0) - - def _end_height(self): - value = self.pop('height') - try: - value = int(value) - except: - value = 0 - if self.inimage: - context = self._getContext() - context['image']['height'] = value - - def _start_url(self, attrsD): - self.push('href', 1) - _start_homepage = _start_url - _start_uri = _start_url - - def _end_url(self): - value = self.pop('href') - if self.inauthor: - self._save_author('href', value) - elif self.incontributor: - self._save_contributor('href', value) - elif self.inimage: - context = self._getContext() - context['image']['href'] = value - elif self.intextinput: - context = self._getContext() - context['textinput']['link'] = value - _end_homepage = _end_url - _end_uri = _end_url - - def _start_email(self, attrsD): - self.push('email', 0) - _start_itunes_email = _start_email - - def _end_email(self): - value = self.pop('email') - if self.inpublisher: - self._save_author('email', value, 'publisher') - elif self.inauthor: - self._save_author('email', value) - elif self.incontributor: - self._save_contributor('email', value) - _end_itunes_email = _end_email - - def _getContext(self): - if self.insource: - context = self.sourcedata - elif self.inentry: - context = self.entries[-1] - else: - context = self.feeddata - return context - - def _save_author(self, key, value, prefix='author'): - context = self._getContext() - context.setdefault(prefix + '_detail', FeedParserDict()) - context[prefix + '_detail'][key] = value - self._sync_author_detail() - - def _save_contributor(self, key, value): - context = self._getContext() - context.setdefault('contributors', [FeedParserDict()]) - context['contributors'][-1][key] = value - - def _sync_author_detail(self, key='author'): - context = self._getContext() - detail = context.get('%s_detail' % key) - if detail: - name = detail.get('name') - email = detail.get('email') - if name and email: - context[key] = '%s (%s)' % (name, email) - elif name: - context[key] = name - elif email: - context[key] = email - else: - author = context.get(key) - if not author: return - emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))''', author) - if not emailmatch: return - email = emailmatch.group(0) - # probably a better way to do the following, but it passes all the tests - author = author.replace(email, '') - author = author.replace('()', '') - author = author.strip() - if author and (author[0] == '('): - author = author[1:] - if author and (author[-1] == ')'): - author = author[:-1] - author = author.strip() - context.setdefault('%s_detail' % key, FeedParserDict()) - context['%s_detail' % key]['name'] = author - context['%s_detail' % key]['email'] = email - - def _start_subtitle(self, attrsD): - self.pushContent('subtitle', attrsD, 'text/plain', 1) - _start_tagline = _start_subtitle - _start_itunes_subtitle = _start_subtitle - - def _end_subtitle(self): - self.popContent('subtitle') - _end_tagline = _end_subtitle - _end_itunes_subtitle = _end_subtitle - - def _start_rights(self, attrsD): - self.pushContent('rights', attrsD, 'text/plain', 1) - _start_dc_rights = _start_rights - _start_copyright = _start_rights - - def _end_rights(self): - self.popContent('rights') - _end_dc_rights = _end_rights - _end_copyright = _end_rights - - def _start_item(self, attrsD): - self.entries.append(FeedParserDict()) - self.push('item', 0) - self.inentry = 1 - self.guidislink = 0 - id = self._getAttribute(attrsD, 'rdf:about') - if id: - context = self._getContext() - context['id'] = id - self._cdf_common(attrsD) - _start_entry = _start_item - _start_product = _start_item - - def _end_item(self): - self.pop('item') - self.inentry = 0 - _end_entry = _end_item - - def _start_dc_language(self, attrsD): - self.push('language', 1) - _start_language = _start_dc_language - - def _end_dc_language(self): - self.lang = self.pop('language') - _end_language = _end_dc_language - - def _start_dc_publisher(self, attrsD): - self.push('publisher', 1) - _start_webmaster = _start_dc_publisher - - def _end_dc_publisher(self): - self.pop('publisher') - self._sync_author_detail('publisher') - _end_webmaster = _end_dc_publisher - - def _start_published(self, attrsD): - self.push('published', 1) - _start_dcterms_issued = _start_published - _start_issued = _start_published - - def _end_published(self): - value = self.pop('published') - self._save('published_parsed', _parse_date(value)) - _end_dcterms_issued = _end_published - _end_issued = _end_published - - def _start_updated(self, attrsD): - self.push('updated', 1) - _start_modified = _start_updated - _start_dcterms_modified = _start_updated - _start_pubdate = _start_updated - _start_dc_date = _start_updated - - def _end_updated(self): - value = self.pop('updated') - parsed_value = _parse_date(value) - self._save('updated_parsed', parsed_value) - _end_modified = _end_updated - _end_dcterms_modified = _end_updated - _end_pubdate = _end_updated - _end_dc_date = _end_updated - - def _start_created(self, attrsD): - self.push('created', 1) - _start_dcterms_created = _start_created - - def _end_created(self): - value = self.pop('created') - self._save('created_parsed', _parse_date(value)) - _end_dcterms_created = _end_created - - def _start_expirationdate(self, attrsD): - self.push('expired', 1) - - def _end_expirationdate(self): - self._save('expired_parsed', _parse_date(self.pop('expired'))) - - def _start_cc_license(self, attrsD): - self.push('license', 1) - value = self._getAttribute(attrsD, 'rdf:resource') - if value: - self.elementstack[-1][2].append(value) - self.pop('license') - - def _start_creativecommons_license(self, attrsD): - self.push('license', 1) - - def _end_creativecommons_license(self): - self.pop('license') - - def _addTag(self, term, scheme, label): - context = self._getContext() - tags = context.setdefault('tags', []) - if (not term) and (not scheme) and (not label): return - value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label}) - if value not in tags: - tags.append(FeedParserDict({'term': term, 'scheme': scheme, 'label': label})) - - def _start_category(self, attrsD): - if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD)) - term = attrsD.get('term') - scheme = attrsD.get('scheme', attrsD.get('domain')) - label = attrsD.get('label') - self._addTag(term, scheme, label) - self.push('category', 1) - _start_dc_subject = _start_category - _start_keywords = _start_category - - def _end_itunes_keywords(self): - for term in self.pop('itunes_keywords').split(): - self._addTag(term, 'http://www.itunes.com/', None) - - def _start_itunes_category(self, attrsD): - self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None) - self.push('category', 1) - - def _end_category(self): - value = self.pop('category') - if not value: return - context = self._getContext() - tags = context['tags'] - if value and len(tags) and not tags[-1]['term']: - tags[-1]['term'] = value - else: - self._addTag(value, None, None) - _end_dc_subject = _end_category - _end_keywords = _end_category - _end_itunes_category = _end_category - - def _start_cloud(self, attrsD): - self._getContext()['cloud'] = FeedParserDict(attrsD) - - def _start_link(self, attrsD): - attrsD.setdefault('rel', 'alternate') - attrsD.setdefault('type', 'text/html') - attrsD = self._itsAnHrefDamnIt(attrsD) - if attrsD.has_key('href'): - attrsD['href'] = self.resolveURI(attrsD['href']) - expectingText = self.infeed or self.inentry or self.insource - context = self._getContext() - context.setdefault('links', []) - context['links'].append(FeedParserDict(attrsD)) - if attrsD['rel'] == 'enclosure': - self._start_enclosure(attrsD) - if attrsD.has_key('href'): - expectingText = 0 - if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types): - context['link'] = attrsD['href'] - else: - self.push('link', expectingText) - _start_producturl = _start_link - - def _end_link(self): - value = self.pop('link') - context = self._getContext() - if self.intextinput: - context['textinput']['link'] = value - if self.inimage: - context['image']['link'] = value - _end_producturl = _end_link - - def _start_guid(self, attrsD): - self.guidislink = (attrsD.get('ispermalink', 'true') == 'true') - self.push('id', 1) - - def _end_guid(self): - value = self.pop('id') - self._save('guidislink', self.guidislink and not self._getContext().has_key('link')) - if self.guidislink: - # guid acts as link, but only if 'ispermalink' is not present or is 'true', - # and only if the item doesn't already have a link element - self._save('link', value) - - def _start_title(self, attrsD): - self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) - _start_dc_title = _start_title - _start_media_title = _start_title - - def _end_title(self): - value = self.popContent('title') - context = self._getContext() - if self.intextinput: - context['textinput']['title'] = value - elif self.inimage: - context['image']['title'] = value - _end_dc_title = _end_title - _end_media_title = _end_title - - def _start_description(self, attrsD): - context = self._getContext() - if context.has_key('summary'): - self._summaryKey = 'content' - self._start_content(attrsD) - else: - self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource) - - def _start_abstract(self, attrsD): - self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource) - - def _end_description(self): - if self._summaryKey == 'content': - self._end_content() - else: - value = self.popContent('description') - context = self._getContext() - if self.intextinput: - context['textinput']['description'] = value - elif self.inimage: - context['image']['description'] = value - self._summaryKey = None - _end_abstract = _end_description - - def _start_info(self, attrsD): - self.pushContent('info', attrsD, 'text/plain', 1) - _start_feedburner_browserfriendly = _start_info - - def _end_info(self): - self.popContent('info') - _end_feedburner_browserfriendly = _end_info - - def _start_generator(self, attrsD): - if attrsD: - attrsD = self._itsAnHrefDamnIt(attrsD) - if attrsD.has_key('href'): - attrsD['href'] = self.resolveURI(attrsD['href']) - self._getContext()['generator_detail'] = FeedParserDict(attrsD) - self.push('generator', 1) - - def _end_generator(self): - value = self.pop('generator') - context = self._getContext() - if context.has_key('generator_detail'): - context['generator_detail']['name'] = value - - def _start_admin_generatoragent(self, attrsD): - self.push('generator', 1) - value = self._getAttribute(attrsD, 'rdf:resource') - if value: - self.elementstack[-1][2].append(value) - self.pop('generator') - self._getContext()['generator_detail'] = FeedParserDict({'href': value}) - - def _start_admin_errorreportsto(self, attrsD): - self.push('errorreportsto', 1) - value = self._getAttribute(attrsD, 'rdf:resource') - if value: - self.elementstack[-1][2].append(value) - self.pop('errorreportsto') - - def _start_summary(self, attrsD): - context = self._getContext() - if context.has_key('summary'): - self._summaryKey = 'content' - self._start_content(attrsD) - else: - self._summaryKey = 'summary' - self.pushContent(self._summaryKey, attrsD, 'text/plain', 1) - _start_itunes_summary = _start_summary - - def _end_summary(self): - if self._summaryKey == 'content': - self._end_content() - else: - self.popContent(self._summaryKey or 'summary') - self._summaryKey = None - _end_itunes_summary = _end_summary - - def _start_enclosure(self, attrsD): - attrsD = self._itsAnHrefDamnIt(attrsD) - self._getContext().setdefault('enclosures', []).append(FeedParserDict(attrsD)) - href = attrsD.get('href') - if href: - context = self._getContext() - if not context.get('id'): - context['id'] = href - - def _start_source(self, attrsD): - self.insource = 1 - - def _end_source(self): - self.insource = 0 - self._getContext()['source'] = copy.deepcopy(self.sourcedata) - self.sourcedata.clear() - - def _start_content(self, attrsD): - self.pushContent('content', attrsD, 'text/plain', 1) - src = attrsD.get('src') - if src: - self.contentparams['src'] = src - self.push('content', 1) - - def _start_prodlink(self, attrsD): - self.pushContent('content', attrsD, 'text/html', 1) - - def _start_body(self, attrsD): - self.pushContent('content', attrsD, 'application/xhtml+xml', 1) - _start_xhtml_body = _start_body - - def _start_content_encoded(self, attrsD): - self.pushContent('content', attrsD, 'text/html', 1) - _start_fullitem = _start_content_encoded - - def _end_content(self): - copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types) - value = self.popContent('content') - if copyToDescription: - self._save('description', value) - _end_body = _end_content - _end_xhtml_body = _end_content - _end_content_encoded = _end_content - _end_fullitem = _end_content - _end_prodlink = _end_content - - def _start_itunes_image(self, attrsD): - self.push('itunes_image', 0) - self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')}) - _start_itunes_link = _start_itunes_image - - def _end_itunes_block(self): - value = self.pop('itunes_block', 0) - self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0 - - def _end_itunes_explicit(self): - value = self.pop('itunes_explicit', 0) - self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0 - -if _XML_AVAILABLE: - class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler): - def __init__(self, baseuri, baselang, encoding): - if _debug: sys.stderr.write('trying StrictFeedParser\n') - xml.sax.handler.ContentHandler.__init__(self) - _FeedParserMixin.__init__(self, baseuri, baselang, encoding) - self.bozo = 0 - self.exc = None - - def startPrefixMapping(self, prefix, uri): - self.trackNamespace(prefix, uri) - - def startElementNS(self, name, qname, attrs): - namespace, localname = name - lowernamespace = str(namespace or '').lower() - if lowernamespace.find('backend.userland.com/rss') <> -1: - # match any backend.userland.com namespace - namespace = 'http://backend.userland.com/rss' - lowernamespace = namespace - if qname and qname.find(':') > 0: - givenprefix = qname.split(':')[0] - else: - givenprefix = None - prefix = self._matchnamespaces.get(lowernamespace, givenprefix) - if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix): - raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix - if prefix: - localname = prefix + ':' + localname - localname = str(localname).lower() - if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname)) - - # qname implementation is horribly broken in Python 2.1 (it - # doesn't report any), and slightly broken in Python 2.2 (it - # doesn't report the xml: namespace). So we match up namespaces - # with a known list first, and then possibly override them with - # the qnames the SAX parser gives us (if indeed it gives us any - # at all). Thanks to MatejC for helping me test this and - # tirelessly telling me that it didn't work yet. - attrsD = {} - for (namespace, attrlocalname), attrvalue in attrs._attrs.items(): - lowernamespace = (namespace or '').lower() - prefix = self._matchnamespaces.get(lowernamespace, '') - if prefix: - attrlocalname = prefix + ':' + attrlocalname - attrsD[str(attrlocalname).lower()] = attrvalue - for qname in attrs.getQNames(): - attrsD[str(qname).lower()] = attrs.getValueByQName(qname) - self.unknown_starttag(localname, attrsD.items()) - - def characters(self, text): - self.handle_data(text) - - def endElementNS(self, name, qname): - namespace, localname = name - lowernamespace = str(namespace or '').lower() - if qname and qname.find(':') > 0: - givenprefix = qname.split(':')[0] - else: - givenprefix = '' - prefix = self._matchnamespaces.get(lowernamespace, givenprefix) - if prefix: - localname = prefix + ':' + localname - localname = str(localname).lower() - self.unknown_endtag(localname) - - def error(self, exc): - self.bozo = 1 - self.exc = exc - - def fatalError(self, exc): - self.error(exc) - raise exc - -class _BaseHTMLProcessor(sgmllib.SGMLParser): - elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr', - 'img', 'input', 'isindex', 'link', 'meta', 'param'] - - def __init__(self, encoding): - self.encoding = encoding - if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding) - sgmllib.SGMLParser.__init__(self) - - def reset(self): - self.pieces = [] - sgmllib.SGMLParser.reset(self) - - def _shorttag_replace(self, match): - tag = match.group(1) - if tag in self.elements_no_end_tag: - return '<' + tag + ' />' - else: - return '<' + tag + '></' + tag + '>' - - def feed(self, data): - data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'<!\1', data) - #data = re.sub(r'<(\S+?)\s*?/>', self._shorttag_replace, data) # bug [ 1399464 ] Bad regexp for _shorttag_replace - data = re.sub(r'<([^<\s]+?)\s*/>', self._shorttag_replace, data) - data = data.replace(''', "'") - data = data.replace('"', '"') - if self.encoding and type(data) == type(u''): - data = data.encode(self.encoding) - sgmllib.SGMLParser.feed(self, data) - - def normalize_attrs(self, attrs): - # utility method to be called by descendants - attrs = [(k.lower(), v) for k, v in attrs] - attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs] - return attrs - - def unknown_starttag(self, tag, attrs): - # called for each start tag - # attrs is a list of (attr, value) tuples - # e.g. for <pre class='screen'>, tag='pre', attrs=[('class', 'screen')] - if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag) - uattrs = [] - # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds - for key, value in attrs: - if type(value) != type(u''): - value = unicode(value, self.encoding) - uattrs.append((unicode(key, self.encoding), value)) - strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]).encode(self.encoding) - if tag in self.elements_no_end_tag: - self.pieces.append('<%(tag)s%(strattrs)s />' % locals()) - else: - self.pieces.append('<%(tag)s%(strattrs)s>' % locals()) - - def unknown_endtag(self, tag): - # called for each end tag, e.g. for </pre>, tag will be 'pre' - # Reconstruct the original end tag. - if tag not in self.elements_no_end_tag: - self.pieces.append("</%(tag)s>" % locals()) - - def handle_charref(self, ref): - # called for each character reference, e.g. for ' ', ref will be '160' - # Reconstruct the original character reference. - self.pieces.append('&#%(ref)s;' % locals()) - - def handle_entityref(self, ref): - # called for each entity reference, e.g. for '©', ref will be 'copy' - # Reconstruct the original entity reference. - self.pieces.append('&%(ref)s;' % locals()) - - def handle_data(self, text): - # called for each block of plain text, i.e. outside of any tag and - # not containing any character or entity references - # Store the original text verbatim. - if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text) - self.pieces.append(text) - - def handle_comment(self, text): - # called for each HTML comment, e.g. <!-- insert Javascript code here --> - # Reconstruct the original comment. - self.pieces.append('<!--%(text)s-->' % locals()) - - def handle_pi(self, text): - # called for each processing instruction, e.g. <?instruction> - # Reconstruct original processing instruction. - self.pieces.append('<?%(text)s>' % locals()) - - def handle_decl(self, text): - # called for the DOCTYPE, if present, e.g. - # <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" - # "http://www.w3.org/TR/html4/loose.dtd"> - # Reconstruct original DOCTYPE - self.pieces.append('<!%(text)s>' % locals()) - - _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match - def _scan_name(self, i, declstartpos): - rawdata = self.rawdata - n = len(rawdata) - if i == n: - return None, -1 - m = self._new_declname_match(rawdata, i) - if m: - s = m.group() - name = s.strip() - if (i + len(s)) == n: - return None, -1 # end of buffer - return name.lower(), m.end() - else: - self.handle_data(rawdata) -# self.updatepos(declstartpos, i) - return None, -1 - - def output(self): - '''Return processed HTML as a single string''' - return ''.join([str(p) for p in self.pieces]) - -class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor): - def __init__(self, baseuri, baselang, encoding): - sgmllib.SGMLParser.__init__(self) - _FeedParserMixin.__init__(self, baseuri, baselang, encoding) - - def decodeEntities(self, element, data): - data = data.replace('<', '<') - data = data.replace('<', '<') - data = data.replace('>', '>') - data = data.replace('>', '>') - data = data.replace('&', '&') - data = data.replace('&', '&') - data = data.replace('"', '"') - data = data.replace('"', '"') - data = data.replace(''', ''') - data = data.replace(''', ''') - if self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'): - data = data.replace('<', '<') - data = data.replace('>', '>') - data = data.replace('&', '&') - data = data.replace('"', '"') - data = data.replace(''', "'") - return data - -class _RelativeURIResolver(_BaseHTMLProcessor): - relative_uris = [('a', 'href'), - ('applet', 'codebase'), - ('area', 'href'), - ('blockquote', 'cite'), - ('body', 'background'), - ('del', 'cite'), - ('form', 'action'), - ('frame', 'longdesc'), - ('frame', 'src'), - ('iframe', 'longdesc'), - ('iframe', 'src'), - ('head', 'profile'), - ('img', 'longdesc'), - ('img', 'src'), - ('img', 'usemap'), - ('input', 'src'), - ('input', 'usemap'), - ('ins', 'cite'), - ('link', 'href'), - ('object', 'classid'), - ('object', 'codebase'), - ('object', 'data'), - ('object', 'usemap'), - ('q', 'cite'), - ('script', 'src')] - - def __init__(self, baseuri, encoding): - _BaseHTMLProcessor.__init__(self, encoding) - self.baseuri = baseuri - - def resolveURI(self, uri): - return _urljoin(self.baseuri, uri) - - def unknown_starttag(self, tag, attrs): - attrs = self.normalize_attrs(attrs) - attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs] - _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) - -def _resolveRelativeURIs(htmlSource, baseURI, encoding): - if _debug: sys.stderr.write('entering _resolveRelativeURIs\n') - p = _RelativeURIResolver(baseURI, encoding) - p.feed(htmlSource) - return p.output() - -class _HTMLSanitizer(_BaseHTMLProcessor): - acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', 'b', 'big', - 'blockquote', 'br', 'button', 'caption', 'center', 'cite', 'code', 'col', - 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'fieldset', - 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', - 'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu', 'ol', 'optgroup', - 'option', 'p', 'pre', 'q', 's', 'samp', 'select', 'small', 'span', 'strike', - 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th', - 'thead', 'tr', 'tt', 'u', 'ul', 'var'] - - acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey', - 'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing', - 'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'cols', - 'colspan', 'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', - 'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', - 'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method', - 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', - 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', - 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type', - 'usemap', 'valign', 'value', 'vspace', 'width'] - - unacceptable_elements_with_end_tag = ['script', 'applet'] - - def reset(self): - _BaseHTMLProcessor.reset(self) - self.unacceptablestack = 0 - - def unknown_starttag(self, tag, attrs): - if not tag in self.acceptable_elements: - if tag in self.unacceptable_elements_with_end_tag: - self.unacceptablestack += 1 - return - attrs = self.normalize_attrs(attrs) - attrs = [(key, value) for key, value in attrs if key in self.acceptable_attributes] - _BaseHTMLProcessor.unknown_starttag(self, tag, attrs) - - def unknown_endtag(self, tag): - if not tag in self.acceptable_elements: - if tag in self.unacceptable_elements_with_end_tag: - self.unacceptablestack -= 1 - return - _BaseHTMLProcessor.unknown_endtag(self, tag) - - def handle_pi(self, text): - pass - - def handle_decl(self, text): - pass - - def handle_data(self, text): - if not self.unacceptablestack: - _BaseHTMLProcessor.handle_data(self, text) - -def _sanitizeHTML(htmlSource, encoding): - p = _HTMLSanitizer(encoding) - p.feed(htmlSource) - data = p.output() - if TIDY_MARKUP: - # loop through list of preferred Tidy interfaces looking for one that's installed, - # then set up a common _tidy function to wrap the interface-specific API. - _tidy = None - for tidy_interface in PREFERRED_TIDY_INTERFACES: - try: - if tidy_interface == "uTidy": - from tidy import parseString as _utidy - def _tidy(data, **kwargs): - return str(_utidy(data, **kwargs)) - break - elif tidy_interface == "mxTidy": - from mx.Tidy import Tidy as _mxtidy - def _tidy(data, **kwargs): - nerrors, nwarnings, data, errordata = _mxtidy.tidy(data, **kwargs) - return data - break - except: - pass - if _tidy: - utf8 = type(data) == type(u'') - if utf8: - data = data.encode('utf-8') - data = _tidy(data, output_xhtml=1, numeric_entities=1, wrap=0, char_encoding="utf8") - if utf8: - data = unicode(data, 'utf-8') - if data.count('<body'): - data = data.split('<body', 1)[1] - if data.count('>'): - data = data.split('>', 1)[1] - if data.count('</body'): - data = data.split('</body', 1)[0] - data = data.strip().replace('\r\n', '\n') - return data - -class _FeedURLHandler(urllib2.HTTPDigestAuthHandler, urllib2.HTTPRedirectHandler, urllib2.HTTPDefaultErrorHandler): - def http_error_default(self, req, fp, code, msg, headers): - if ((code / 100) == 3) and (code != 304): - return self.http_error_302(req, fp, code, msg, headers) - infourl = urllib.addinfourl(fp, headers, req.get_full_url()) - infourl.status = code - return infourl - - def http_error_302(self, req, fp, code, msg, headers): - if headers.dict.has_key('location'): - infourl = urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers) - else: - infourl = urllib.addinfourl(fp, headers, req.get_full_url()) - if not hasattr(infourl, 'status'): - infourl.status = code - return infourl - - def http_error_301(self, req, fp, code, msg, headers): - if headers.dict.has_key('location'): - infourl = urllib2.HTTPRedirectHandler.http_error_301(self, req, fp, code, msg, headers) - else: - infourl = urllib.addinfourl(fp, headers, req.get_full_url()) - if not hasattr(infourl, 'status'): - infourl.status = code - return infourl - - http_error_300 = http_error_302 - http_error_303 = http_error_302 - http_error_307 = http_error_302 - - def http_error_401(self, req, fp, code, msg, headers): - # Check if - # - server requires digest auth, AND - # - we tried (unsuccessfully) with basic auth, AND - # - we're using Python 2.3.3 or later (digest auth is irreparably broken in earlier versions) - # If all conditions hold, parse authentication information - # out of the Authorization header we sent the first time - # (for the username and password) and the WWW-Authenticate - # header the server sent back (for the realm) and retry - # the request with the appropriate digest auth headers instead. - # This evil genius hack has been brought to you by Aaron Swartz. - host = urlparse.urlparse(req.get_full_url())[1] - try: - assert sys.version.split()[0] >= '2.3.3' - assert base64 != None - user, passw = base64.decodestring(req.headers['Authorization'].split(' ')[1]).split(':') - realm = re.findall('realm="([^"]*)"', headers['WWW-Authenticate'])[0] - self.add_password(realm, host, user, passw) - retry = self.http_error_auth_reqed('www-authenticate', host, req, headers) - self.reset_retry_count() - return retry - except: - return self.http_error_default(req, fp, code, msg, headers) - -def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers): - """URL, filename, or string --> stream - - This function lets you define parsers that take any input source - (URL, pathname to local or network file, or actual data as a string) - and deal with it in a uniform manner. Returned object is guaranteed - to have all the basic stdio read methods (read, readline, readlines). - Just .close() the object when you're done with it. - - If the etag argument is supplied, it will be used as the value of an - If-None-Match request header. - - If the modified argument is supplied, it must be a tuple of 9 integers - as returned by gmtime() in the standard Python time module. This MUST - be in GMT (Greenwich Mean Time). The formatted date/time will be used - as the value of an If-Modified-Since request header. - - If the agent argument is supplied, it will be used as the value of a - User-Agent request header. - - If the referrer argument is supplied, it will be used as the value of a - Referer[sic] request header. - - If handlers is supplied, it is a list of handlers used to build a - urllib2 opener. - """ - - if hasattr(url_file_stream_or_string, 'read'): - return url_file_stream_or_string - - if url_file_stream_or_string == '-': - return sys.stdin - - if urlparse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp'): - if not agent: - agent = USER_AGENT - # test for inline user:password for basic auth - auth = None - if base64: - urltype, rest = urllib.splittype(url_file_stream_or_string) - realhost, rest = urllib.splithost(rest) - if realhost: - user_passwd, realhost = urllib.splituser(realhost) - if user_passwd: - url_file_stream_or_string = '%s://%s%s' % (urltype, realhost, rest) - auth = base64.encodestring(user_passwd).strip() - # try to open with urllib2 (to use optional headers) - request = urllib2.Request(url_file_stream_or_string) - request.add_header('User-Agent', agent) - if etag: - request.add_header('If-None-Match', etag) - if modified: - # format into an RFC 1123-compliant timestamp. We can't use - # time.strftime() since the %a and %b directives can be affected - # by the current locale, but RFC 2616 states that dates must be - # in English. - short_weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] - months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] - request.add_header('If-Modified-Since', '%s, %02d %s %04d %02d:%02d:%02d GMT' % (short_weekdays[modified[6]], modified[2], months[modified[1] - 1], modified[0], modified[3], modified[4], modified[5])) - if referrer: - request.add_header('Referer', referrer) - if gzip and zlib: - request.add_header('Accept-encoding', 'gzip, deflate') - elif gzip: - request.add_header('Accept-encoding', 'gzip') - elif zlib: - request.add_header('Accept-encoding', 'deflate') - else: - request.add_header('Accept-encoding', '') - if auth: - request.add_header('Authorization', 'Basic %s' % auth) - if ACCEPT_HEADER: - request.add_header('Accept', ACCEPT_HEADER) - request.add_header('A-IM', 'feed') # RFC 3229 support - opener = apply(urllib2.build_opener, tuple([_FeedURLHandler()] + handlers)) - opener.addheaders = [] # RMK - must clear so we only send our custom User-Agent - try: - return opener.open(request) - finally: - opener.close() # JohnD - - # try to open with native open function (if url_file_stream_or_string is a filename) - try: - return open(url_file_stream_or_string) - except: - pass - - # treat url_file_stream_or_string as string - return _StringIO(str(url_file_stream_or_string)) - -_date_handlers = [] -def registerDateHandler(func): - '''Register a date handler function (takes string, returns 9-tuple date in GMT)''' - _date_handlers.insert(0, func) - -# ISO-8601 date parsing routines written by Fazal Majid. -# The ISO 8601 standard is very convoluted and irregular - a full ISO 8601 -# parser is beyond the scope of feedparser and would be a worthwhile addition -# to the Python library. -# A single regular expression cannot parse ISO 8601 date formats into groups -# as the standard is highly irregular (for instance is 030104 2003-01-04 or -# 0301-04-01), so we use templates instead. -# Please note the order in templates is significant because we need a -# greedy match. -_iso8601_tmpl = ['YYYY-?MM-?DD', 'YYYY-MM', 'YYYY-?OOO', - 'YY-?MM-?DD', 'YY-?OOO', 'YYYY', - '-YY-?MM', '-OOO', '-YY', - '--MM-?DD', '--MM', - '---DD', - 'CC', ''] -_iso8601_re = [ - tmpl.replace( - 'YYYY', r'(?P<year>\d{4})').replace( - 'YY', r'(?P<year>\d\d)').replace( - 'MM', r'(?P<month>[01]\d)').replace( - 'DD', r'(?P<day>[0123]\d)').replace( - 'OOO', r'(?P<ordinal>[0123]\d\d)').replace( - 'CC', r'(?P<century>\d\d$)') - + r'(T?(?P<hour>\d{2}):(?P<minute>\d{2})' - + r'(:(?P<second>\d{2}))?' - + r'(?P<tz>[+-](?P<tzhour>\d{2})(:(?P<tzmin>\d{2}))?|Z)?)?' - for tmpl in _iso8601_tmpl] -del tmpl -_iso8601_matches = [re.compile(regex).match for regex in _iso8601_re] -del regex -def _parse_date_iso8601(dateString): - '''Parse a variety of ISO-8601-compatible formats like 20040105''' - m = None - for _iso8601_match in _iso8601_matches: - m = _iso8601_match(dateString) - if m: break - if not m: return - if m.span() == (0, 0): return - params = m.groupdict() - ordinal = params.get('ordinal', 0) - if ordinal: - ordinal = int(ordinal) - else: - ordinal = 0 - year = params.get('year', '--') - if not year or year == '--': - year = time.gmtime()[0] - elif len(year) == 2: - # ISO 8601 assumes current century, i.e. 93 -> 2093, NOT 1993 - year = 100 * int(time.gmtime()[0] / 100) + int(year) - else: - year = int(year) - month = params.get('month', '-') - if not month or month == '-': - # ordinals are NOT normalized by mktime, we simulate them - # by setting month=1, day=ordinal - if ordinal: - month = 1 - else: - month = time.gmtime()[1] - month = int(month) - day = params.get('day', 0) - if not day: - # see above - if ordinal: - day = ordinal - elif params.get('century', 0) or \ - params.get('year', 0) or params.get('month', 0): - day = 1 - else: - day = time.gmtime()[2] - else: - day = int(day) - # special case of the century - is the first year of the 21st century - # 2000 or 2001 ? The debate goes on... - if 'century' in params.keys(): - year = (int(params['century']) - 1) * 100 + 1 - # in ISO 8601 most fields are optional - for field in ['hour', 'minute', 'second', 'tzhour', 'tzmin']: - if not params.get(field, None): - params[field] = 0 - hour = int(params.get('hour', 0)) - minute = int(params.get('minute', 0)) - second = int(params.get('second', 0)) - # weekday is normalized by mktime(), we can ignore it - weekday = 0 - # daylight savings is complex, but not needed for feedparser's purposes - # as time zones, if specified, include mention of whether it is active - # (e.g. PST vs. PDT, CET). Using -1 is implementation-dependent and - # and most implementations have DST bugs - daylight_savings_flag = 0 - tm = [year, month, day, hour, minute, second, weekday, - ordinal, daylight_savings_flag] - # ISO 8601 time zone adjustments - tz = params.get('tz') - if tz and tz != 'Z': - if tz[0] == '-': - tm[3] += int(params.get('tzhour', 0)) - tm[4] += int(params.get('tzmin', 0)) - elif tz[0] == '+': - tm[3] -= int(params.get('tzhour', 0)) - tm[4] -= int(params.get('tzmin', 0)) - else: - return None - # Python's time.mktime() is a wrapper around the ANSI C mktime(3c) - # which is guaranteed to normalize d/m/y/h/m/s. - # Many implementations have bugs, but we'll pretend they don't. - return time.localtime(time.mktime(tm)) -registerDateHandler(_parse_date_iso8601) - -# 8-bit date handling routines written by ytrewq1. -_korean_year = u'\ub144' # b3e2 in euc-kr -_korean_month = u'\uc6d4' # bff9 in euc-kr -_korean_day = u'\uc77c' # c0cf in euc-kr -_korean_am = u'\uc624\uc804' # bfc0 c0fc in euc-kr -_korean_pm = u'\uc624\ud6c4' # bfc0 c8c4 in euc-kr - -_korean_onblog_date_re = \ - re.compile('(\d{4})%s\s+(\d{2})%s\s+(\d{2})%s\s+(\d{2}):(\d{2}):(\d{2})' % \ - (_korean_year, _korean_month, _korean_day)) -_korean_nate_date_re = \ - re.compile(u'(\d{4})-(\d{2})-(\d{2})\s+(%s|%s)\s+(\d{,2}):(\d{,2}):(\d{,2})' % \ - (_korean_am, _korean_pm)) -def _parse_date_onblog(dateString): - '''Parse a string according to the OnBlog 8-bit date format''' - m = _korean_onblog_date_re.match(dateString) - if not m: return - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ - {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ - 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ - 'zonediff': '+09:00'} - if _debug: sys.stderr.write('OnBlog date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_onblog) - -def _parse_date_nate(dateString): - '''Parse a string according to the Nate 8-bit date format''' - m = _korean_nate_date_re.match(dateString) - if not m: return - hour = int(m.group(5)) - ampm = m.group(4) - if (ampm == _korean_pm): - hour += 12 - hour = str(hour) - if len(hour) == 1: - hour = '0' + hour - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ - {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ - 'hour': hour, 'minute': m.group(6), 'second': m.group(7),\ - 'zonediff': '+09:00'} - if _debug: sys.stderr.write('Nate date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_nate) - -_mssql_date_re = \ - re.compile('(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(\.\d+)?') -def _parse_date_mssql(dateString): - '''Parse a string according to the MS SQL date format''' - m = _mssql_date_re.match(dateString) - if not m: return - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \ - {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\ - 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\ - 'zonediff': '+09:00'} - if _debug: sys.stderr.write('MS SQL date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_mssql) - -# Unicode strings for Greek date strings -_greek_months = \ - { \ - u'\u0399\u03b1\u03bd': u'Jan', # c9e1ed in iso-8859-7 - u'\u03a6\u03b5\u03b2': u'Feb', # d6e5e2 in iso-8859-7 - u'\u039c\u03ac\u03ce': u'Mar', # ccdcfe in iso-8859-7 - u'\u039c\u03b1\u03ce': u'Mar', # cce1fe in iso-8859-7 - u'\u0391\u03c0\u03c1': u'Apr', # c1f0f1 in iso-8859-7 - u'\u039c\u03ac\u03b9': u'May', # ccdce9 in iso-8859-7 - u'\u039c\u03b1\u03ca': u'May', # cce1fa in iso-8859-7 - u'\u039c\u03b1\u03b9': u'May', # cce1e9 in iso-8859-7 - u'\u0399\u03bf\u03cd\u03bd': u'Jun', # c9effded in iso-8859-7 - u'\u0399\u03bf\u03bd': u'Jun', # c9efed in iso-8859-7 - u'\u0399\u03bf\u03cd\u03bb': u'Jul', # c9effdeb in iso-8859-7 - u'\u0399\u03bf\u03bb': u'Jul', # c9f9eb in iso-8859-7 - u'\u0391\u03cd\u03b3': u'Aug', # c1fde3 in iso-8859-7 - u'\u0391\u03c5\u03b3': u'Aug', # c1f5e3 in iso-8859-7 - u'\u03a3\u03b5\u03c0': u'Sep', # d3e5f0 in iso-8859-7 - u'\u039f\u03ba\u03c4': u'Oct', # cfeaf4 in iso-8859-7 - u'\u039d\u03bf\u03ad': u'Nov', # cdefdd in iso-8859-7 - u'\u039d\u03bf\u03b5': u'Nov', # cdefe5 in iso-8859-7 - u'\u0394\u03b5\u03ba': u'Dec', # c4e5ea in iso-8859-7 - } - -_greek_wdays = \ - { \ - u'\u039a\u03c5\u03c1': u'Sun', # caf5f1 in iso-8859-7 - u'\u0394\u03b5\u03c5': u'Mon', # c4e5f5 in iso-8859-7 - u'\u03a4\u03c1\u03b9': u'Tue', # d4f1e9 in iso-8859-7 - u'\u03a4\u03b5\u03c4': u'Wed', # d4e5f4 in iso-8859-7 - u'\u03a0\u03b5\u03bc': u'Thu', # d0e5ec in iso-8859-7 - u'\u03a0\u03b1\u03c1': u'Fri', # d0e1f1 in iso-8859-7 - u'\u03a3\u03b1\u03b2': u'Sat', # d3e1e2 in iso-8859-7 - } - -_greek_date_format_re = \ - re.compile(u'([^,]+),\s+(\d{2})\s+([^\s]+)\s+(\d{4})\s+(\d{2}):(\d{2}):(\d{2})\s+([^\s]+)') - -def _parse_date_greek(dateString): - '''Parse a string according to a Greek 8-bit date format.''' - m = _greek_date_format_re.match(dateString) - if not m: return - try: - wday = _greek_wdays[m.group(1)] - month = _greek_months[m.group(3)] - except: - return - rfc822date = '%(wday)s, %(day)s %(month)s %(year)s %(hour)s:%(minute)s:%(second)s %(zonediff)s' % \ - {'wday': wday, 'day': m.group(2), 'month': month, 'year': m.group(4),\ - 'hour': m.group(5), 'minute': m.group(6), 'second': m.group(7),\ - 'zonediff': m.group(8)} - if _debug: sys.stderr.write('Greek date parsed as: %s\n' % rfc822date) - return _parse_date_rfc822(rfc822date) -registerDateHandler(_parse_date_greek) - -# Unicode strings for Hungarian date strings -_hungarian_months = \ - { \ - u'janu\u00e1r': u'01', # e1 in iso-8859-2 - u'febru\u00e1ri': u'02', # e1 in iso-8859-2 - u'm\u00e1rcius': u'03', # e1 in iso-8859-2 - u'\u00e1prilis': u'04', # e1 in iso-8859-2 - u'm\u00e1ujus': u'05', # e1 in iso-8859-2 - u'j\u00fanius': u'06', # fa in iso-8859-2 - u'j\u00falius': u'07', # fa in iso-8859-2 - u'augusztus': u'08', - u'szeptember': u'09', - u'okt\u00f3ber': u'10', # f3 in iso-8859-2 - u'november': u'11', - u'december': u'12', - } - -_hungarian_date_format_re = \ - re.compile(u'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})((\+|-)(\d{,2}:\d{2}))') - -def _parse_date_hungarian(dateString): - '''Parse a string according to a Hungarian 8-bit date format.''' - m = _hungarian_date_format_re.match(dateString) - if not m: return - try: - month = _hungarian_months[m.group(2)] - day = m.group(3) - if len(day) == 1: - day = '0' + day - hour = m.group(4) - if len(hour) == 1: - hour = '0' + hour - except: - return - w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s%(zonediff)s' % \ - {'year': m.group(1), 'month': month, 'day': day,\ - 'hour': hour, 'minute': m.group(5),\ - 'zonediff': m.group(6)} - if _debug: sys.stderr.write('Hungarian date parsed as: %s\n' % w3dtfdate) - return _parse_date_w3dtf(w3dtfdate) -registerDateHandler(_parse_date_hungarian) - -# W3DTF-style date parsing adapted from PyXML xml.utils.iso8601, written by -# Drake and licensed under the Python license. Removed all range checking -# for month, day, hour, minute, and second, since mktime will normalize -# these later -def _parse_date_w3dtf(dateString): - def __extract_date(m): - year = int(m.group('year')) - if year < 100: - year = 100 * int(time.gmtime()[0] / 100) + int(year) - if year < 1000: - return 0, 0, 0 - julian = m.group('julian') - if julian: - julian = int(julian) - month = julian / 30 + 1 - day = julian % 30 + 1 - jday = None - while jday != julian: - t = time.mktime((year, month, day, 0, 0, 0, 0, 0, 0)) - jday = time.gmtime(t)[-2] - diff = abs(jday - julian) - if jday > julian: - if diff < day: - day = day - diff - else: - month = month - 1 - day = 31 - elif jday < julian: - if day + diff < 28: - day = day + diff - else: - month = month + 1 - return year, month, day - month = m.group('month') - day = 1 - if month is None: - month = 1 - else: - month = int(month) - day = m.group('day') - if day: - day = int(day) - else: - day = 1 - return year, month, day - - def __extract_time(m): - if not m: - return 0, 0, 0 - hours = m.group('hours') - if not hours: - return 0, 0, 0 - hours = int(hours) - minutes = int(m.group('minutes')) - seconds = m.group('seconds') - if seconds: - seconds = int(seconds) - else: - seconds = 0 - return hours, minutes, seconds - - def __extract_tzd(m): - '''Return the Time Zone Designator as an offset in seconds from UTC.''' - if not m: - return 0 - tzd = m.group('tzd') - if not tzd: - return 0 - if tzd == 'Z': - return 0 - hours = int(m.group('tzdhours')) - minutes = m.group('tzdminutes') - if minutes: - minutes = int(minutes) - else: - minutes = 0 - offset = (hours*60 + minutes) * 60 - if tzd[0] == '+': - return -offset - return offset - - __date_re = ('(?P<year>\d\d\d\d)' - '(?:(?P<dsep>-|)' - '(?:(?P<julian>\d\d\d)' - '|(?P<month>\d\d)(?:(?P=dsep)(?P<day>\d\d))?))?') - __tzd_re = '(?P<tzd>[-+](?P<tzdhours>\d\d)(?::?(?P<tzdminutes>\d\d))|Z)' - __tzd_rx = re.compile(__tzd_re) - __time_re = ('(?P<hours>\d\d)(?P<tsep>:|)(?P<minutes>\d\d)' - '(?:(?P=tsep)(?P<seconds>\d\d(?:[.,]\d+)?))?' - + __tzd_re) - __datetime_re = '%s(?:T%s)?' % (__date_re, __time_re) - __datetime_rx = re.compile(__datetime_re) - m = __datetime_rx.match(dateString) - if (m is None) or (m.group() != dateString): return - gmt = __extract_date(m) + __extract_time(m) + (0, 0, 0) - if gmt[0] == 0: return - return time.gmtime(time.mktime(gmt) + __extract_tzd(m) - time.timezone) -registerDateHandler(_parse_date_w3dtf) - -def _parse_date_rfc822(dateString): - '''Parse an RFC822, RFC1123, RFC2822, or asctime-style date''' - data = dateString.split() - if data[0][-1] in (',', '.') or data[0].lower() in rfc822._daynames: - del data[0] - if len(data) == 4: - s = data[3] - i = s.find('+') - if i > 0: - data[3:] = [s[:i], s[i+1:]] - else: - data.append('') - dateString = " ".join(data) - if len(data) < 5: - dateString += ' 00:00:00 GMT' - tm = rfc822.parsedate_tz(dateString) - if tm: - return time.gmtime(rfc822.mktime_tz(tm)) -# rfc822.py defines several time zones, but we define some extra ones. -# 'ET' is equivalent to 'EST', etc. -_additional_timezones = {'AT': -400, 'ET': -500, 'CT': -600, 'MT': -700, 'PT': -800} -rfc822._timezones.update(_additional_timezones) -registerDateHandler(_parse_date_rfc822) - -def _parse_date(dateString): - '''Parses a variety of date formats into a 9-tuple in GMT''' - for handler in _date_handlers: - try: - date9tuple = handler(dateString) - if not date9tuple: continue - if len(date9tuple) != 9: - if _debug: sys.stderr.write('date handler function must return 9-tuple\n') - raise ValueError - map(int, date9tuple) - return date9tuple - except Exception, e: - if _debug: sys.stderr.write('%s raised %s\n' % (handler.__name__, repr(e))) - pass - return None - -def _getCharacterEncoding(http_headers, xml_data): - '''Get the character encoding of the XML document - - http_headers is a dictionary - xml_data is a raw string (not Unicode) - - This is so much trickier than it sounds, it's not even funny. - According to RFC 3023 ('XML Media Types'), if the HTTP Content-Type - is application/xml, application/*+xml, - application/xml-external-parsed-entity, or application/xml-dtd, - the encoding given in the charset parameter of the HTTP Content-Type - takes precedence over the encoding given in the XML prefix within the - document, and defaults to 'utf-8' if neither are specified. But, if - the HTTP Content-Type is text/xml, text/*+xml, or - text/xml-external-parsed-entity, the encoding given in the XML prefix - within the document is ALWAYS IGNORED and only the encoding given in - the charset parameter of the HTTP Content-Type header should be - respected, and it defaults to 'us-ascii' if not specified. - - Furthermore, discussion on the atom-syntax mailing list with the - author of RFC 3023 leads me to the conclusion that any document - served with a Content-Type of text/* and no charset parameter - must be treated as us-ascii. (We now do this.) And also that it - must always be flagged as non-well-formed. (We now do this too.) - - If Content-Type is unspecified (input was local file or non-HTTP source) - or unrecognized (server just got it totally wrong), then go by the - encoding given in the XML prefix of the document and default to - 'iso-8859-1' as per the HTTP specification (RFC 2616). - - Then, assuming we didn't find a character encoding in the HTTP headers - (and the HTTP Content-type allowed us to look in the body), we need - to sniff the first few bytes of the XML data and try to determine - whether the encoding is ASCII-compatible. Section F of the XML - specification shows the way here: - http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info - - If the sniffed encoding is not ASCII-compatible, we need to make it - ASCII compatible so that we can sniff further into the XML declaration - to find the encoding attribute, which will tell us the true encoding. - - Of course, none of this guarantees that we will be able to parse the - feed in the declared character encoding (assuming it was declared - correctly, which many are not). CJKCodecs and iconv_codec help a lot; - you should definitely install them if you can. - http://cjkpython.i18n.org/ - ''' - - def _parseHTTPContentType(content_type): - '''takes HTTP Content-Type header and returns (content type, charset) - - If no charset is specified, returns (content type, '') - If no content type is specified, returns ('', '') - Both return parameters are guaranteed to be lowercase strings - ''' - content_type = content_type or '' - content_type, params = cgi.parse_header(content_type) - return content_type, params.get('charset', '').replace("'", '') - - sniffed_xml_encoding = '' - xml_encoding = '' - true_encoding = '' - http_content_type, http_encoding = _parseHTTPContentType(http_headers.get('content-type')) - # Must sniff for non-ASCII-compatible character encodings before - # searching for XML declaration. This heuristic is defined in - # section F of the XML specification: - # http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info - try: - if xml_data[:4] == '\x4c\x6f\xa7\x94': - # EBCDIC - xml_data = _ebcdic_to_ascii(xml_data) - elif xml_data[:4] == '\x00\x3c\x00\x3f': - # UTF-16BE - sniffed_xml_encoding = 'utf-16be' - xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') - elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') and (xml_data[2:4] != '\x00\x00'): - # UTF-16BE with BOM - sniffed_xml_encoding = 'utf-16be' - xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') - elif xml_data[:4] == '\x3c\x00\x3f\x00': - # UTF-16LE - sniffed_xml_encoding = 'utf-16le' - xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') - elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and (xml_data[2:4] != '\x00\x00'): - # UTF-16LE with BOM - sniffed_xml_encoding = 'utf-16le' - xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') - elif xml_data[:4] == '\x00\x00\x00\x3c': - # UTF-32BE - sniffed_xml_encoding = 'utf-32be' - xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') - elif xml_data[:4] == '\x3c\x00\x00\x00': - # UTF-32LE - sniffed_xml_encoding = 'utf-32le' - xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') - elif xml_data[:4] == '\x00\x00\xfe\xff': - # UTF-32BE with BOM - sniffed_xml_encoding = 'utf-32be' - xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') - elif xml_data[:4] == '\xff\xfe\x00\x00': - # UTF-32LE with BOM - sniffed_xml_encoding = 'utf-32le' - xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') - elif xml_data[:3] == '\xef\xbb\xbf': - # UTF-8 with BOM - sniffed_xml_encoding = 'utf-8' - xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') - else: - # ASCII-compatible - pass - xml_encoding_match = re.compile('^<\?.*encoding=[\'"](.*?)[\'"].*\?>').match(xml_data) - except: - xml_encoding_match = None - if xml_encoding_match: - xml_encoding = xml_encoding_match.groups()[0].lower() - if sniffed_xml_encoding and (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', 'iso-10646-ucs-4', 'ucs-4', 'csucs4', 'utf-16', 'utf-32', 'utf_16', 'utf_32', 'utf16', 'u16')): - xml_encoding = sniffed_xml_encoding - acceptable_content_type = 0 - application_content_types = ('application/xml', 'application/xml-dtd', 'application/xml-external-parsed-entity') - text_content_types = ('text/xml', 'text/xml-external-parsed-entity') - if (http_content_type in application_content_types) or \ - (http_content_type.startswith('application/') and http_content_type.endswith('+xml')): - acceptable_content_type = 1 - true_encoding = http_encoding or xml_encoding or 'utf-8' - elif (http_content_type in text_content_types) or \ - (http_content_type.startswith('text/')) and http_content_type.endswith('+xml'): - acceptable_content_type = 1 - true_encoding = http_encoding or 'us-ascii' - elif http_content_type.startswith('text/'): - true_encoding = http_encoding or 'us-ascii' - elif http_headers and (not http_headers.has_key('content-type')): - true_encoding = xml_encoding or 'iso-8859-1' - else: - true_encoding = xml_encoding or 'utf-8' - return true_encoding, http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type - -def _toUTF8(data, encoding): - '''Changes an XML data stream on the fly to specify a new encoding - - data is a raw sequence of bytes (not Unicode) that is presumed to be in %encoding already - encoding is a string recognized by encodings.aliases - ''' - if _debug: sys.stderr.write('entering _toUTF8, trying encoding %s\n' % encoding) - # strip Byte Order Mark (if present) - if (len(data) >= 4) and (data[:2] == '\xfe\xff') and (data[2:4] != '\x00\x00'): - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-16be': - sys.stderr.write('trying utf-16be instead\n') - encoding = 'utf-16be' - data = data[2:] - elif (len(data) >= 4) and (data[:2] == '\xff\xfe') and (data[2:4] != '\x00\x00'): - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-16le': - sys.stderr.write('trying utf-16le instead\n') - encoding = 'utf-16le' - data = data[2:] - elif data[:3] == '\xef\xbb\xbf': - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-8': - sys.stderr.write('trying utf-8 instead\n') - encoding = 'utf-8' - data = data[3:] - elif data[:4] == '\x00\x00\xfe\xff': - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-32be': - sys.stderr.write('trying utf-32be instead\n') - encoding = 'utf-32be' - data = data[4:] - elif data[:4] == '\xff\xfe\x00\x00': - if _debug: - sys.stderr.write('stripping BOM\n') - if encoding != 'utf-32le': - sys.stderr.write('trying utf-32le instead\n') - encoding = 'utf-32le' - data = data[4:] - newdata = unicode(data, encoding) - if _debug: sys.stderr.write('successfully converted %s data to unicode\n' % encoding) - declmatch = re.compile('^<\?xml[^>]*?>') - newdecl = '''<?xml version='1.0' encoding='utf-8'?>''' - if declmatch.search(newdata): - newdata = declmatch.sub(newdecl, newdata) - else: - newdata = newdecl + u'\n' + newdata - return newdata.encode('utf-8') - -def _stripDoctype(data): - '''Strips DOCTYPE from XML document, returns (rss_version, stripped_data) - - rss_version may be 'rss091n' or None - stripped_data is the same XML document, minus the DOCTYPE - ''' - entity_pattern = re.compile(r'<!ENTITY([^>]*?)>', re.MULTILINE) - data = entity_pattern.sub('', data) - doctype_pattern = re.compile(r'<!DOCTYPE([^>]*?)>', re.MULTILINE) - doctype_results = doctype_pattern.findall(data) - doctype = doctype_results and doctype_results[0] or '' - if doctype.lower().count('netscape'): - version = 'rss091n' - else: - version = None - data = doctype_pattern.sub('', data) - return version, data - -def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=[]): - '''Parse a feed from a URL, file, stream, or string''' - result = FeedParserDict() - result['feed'] = FeedParserDict() - result['entries'] = [] - if _XML_AVAILABLE: - result['bozo'] = 0 - if type(handlers) == types.InstanceType: - handlers = [handlers] - try: - f = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers) - data = f.read() - except Exception, e: - result['bozo'] = 1 - result['bozo_exception'] = e - data = '' - f = None - - # if feed is gzip-compressed, decompress it - if f and data and hasattr(f, 'headers'): - if gzip and f.headers.get('content-encoding', '') == 'gzip': - try: - data = gzip.GzipFile(fileobj=_StringIO(data)).read() - except Exception, e: - # Some feeds claim to be gzipped but they're not, so - # we get garbage. Ideally, we should re-request the - # feed without the 'Accept-encoding: gzip' header, - # but we don't. - result['bozo'] = 1 - result['bozo_exception'] = e - data = '' - elif zlib and f.headers.get('content-encoding', '') == 'deflate': - try: - data = zlib.decompress(data, -zlib.MAX_WBITS) - except Exception, e: - result['bozo'] = 1 - result['bozo_exception'] = e - data = '' - - # save HTTP headers - if hasattr(f, 'info'): - info = f.info() - result['etag'] = info.getheader('ETag') - last_modified = info.getheader('Last-Modified') - if last_modified: - result['modified'] = _parse_date(last_modified) - if hasattr(f, 'url'): - result['href'] = f.url - result['status'] = 200 - if hasattr(f, 'status'): - result['status'] = f.status - if hasattr(f, 'headers'): - result['headers'] = f.headers.dict - if hasattr(f, 'close'): - f.close() - - # there are four encodings to keep track of: - # - http_encoding is the encoding declared in the Content-Type HTTP header - # - xml_encoding is the encoding declared in the <?xml declaration - # - sniffed_encoding is the encoding sniffed from the first 4 bytes of the XML data - # - result['encoding'] is the actual encoding, as per RFC 3023 and a variety of other conflicting specifications - http_headers = result.get('headers', {}) - result['encoding'], http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type = \ - _getCharacterEncoding(http_headers, data) - if http_headers and (not acceptable_content_type): - if http_headers.has_key('content-type'): - bozo_message = '%s is not an XML media type' % http_headers['content-type'] - else: - bozo_message = 'no Content-type specified' - result['bozo'] = 1 - result['bozo_exception'] = NonXMLContentType(bozo_message) - - result['version'], data = _stripDoctype(data) - - baseuri = http_headers.get('content-location', result.get('href')) - baselang = http_headers.get('content-language', None) - - # if server sent 304, we're done - if result.get('status', 0) == 304: - result['version'] = '' - result['debug_message'] = 'The feed has not changed since you last checked, ' + \ - 'so the server sent no data. This is a feature, not a bug!' - return result - - # if there was a problem downloading, we're done - if not data: - return result - - # determine character encoding - use_strict_parser = 0 - known_encoding = 0 - tried_encodings = [] - # try: HTTP encoding, declared XML encoding, encoding sniffed from BOM - for proposed_encoding in (result['encoding'], xml_encoding, sniffed_xml_encoding): - if not proposed_encoding: continue - if proposed_encoding in tried_encodings: continue - tried_encodings.append(proposed_encoding) - try: - data = _toUTF8(data, proposed_encoding) - known_encoding = use_strict_parser = 1 - break - except: - pass - # if no luck and we have auto-detection library, try that - if (not known_encoding) and chardet: - try: - proposed_encoding = chardet.detect(data)['encoding'] - if proposed_encoding and (proposed_encoding not in tried_encodings): - tried_encodings.append(proposed_encoding) - data = _toUTF8(data, proposed_encoding) - known_encoding = use_strict_parser = 1 - except: - pass - # if still no luck and we haven't tried utf-8 yet, try that - if (not known_encoding) and ('utf-8' not in tried_encodings): - try: - proposed_encoding = 'utf-8' - tried_encodings.append(proposed_encoding) - data = _toUTF8(data, proposed_encoding) - known_encoding = use_strict_parser = 1 - except: - pass - # if still no luck and we haven't tried windows-1252 yet, try that - if (not known_encoding) and ('windows-1252' not in tried_encodings): - try: - proposed_encoding = 'windows-1252' - tried_encodings.append(proposed_encoding) - data = _toUTF8(data, proposed_encoding) - known_encoding = use_strict_parser = 1 - except: - pass - # if still no luck, give up - if not known_encoding: - result['bozo'] = 1 - result['bozo_exception'] = CharacterEncodingUnknown( \ - 'document encoding unknown, I tried ' + \ - '%s, %s, utf-8, and windows-1252 but nothing worked' % \ - (result['encoding'], xml_encoding)) - result['encoding'] = '' - elif proposed_encoding != result['encoding']: - result['bozo'] = 1 - result['bozo_exception'] = CharacterEncodingOverride( \ - 'documented declared as %s, but parsed as %s' % \ - (result['encoding'], proposed_encoding)) - result['encoding'] = proposed_encoding - - if not _XML_AVAILABLE: - use_strict_parser = 0 - if use_strict_parser: - # initialize the SAX parser - feedparser = _StrictFeedParser(baseuri, baselang, 'utf-8') - saxparser = xml.sax.make_parser(PREFERRED_XML_PARSERS) - saxparser.setFeature(xml.sax.handler.feature_namespaces, 1) - saxparser.setContentHandler(feedparser) - saxparser.setErrorHandler(feedparser) - source = xml.sax.xmlreader.InputSource() - source.setByteStream(_StringIO(data)) - if hasattr(saxparser, '_ns_stack'): - # work around bug in built-in SAX parser (doesn't recognize xml: namespace) - # PyXML doesn't have this problem, and it doesn't have _ns_stack either - saxparser._ns_stack.append({'http://www.w3.org/XML/1998/namespace':'xml'}) - try: - saxparser.parse(source) - except Exception, e: - if _debug: - import traceback - traceback.print_stack() - traceback.print_exc() - sys.stderr.write('xml parsing failed\n') - result['bozo'] = 1 - result['bozo_exception'] = feedparser.exc or e - use_strict_parser = 0 - if not use_strict_parser: - feedparser = _LooseFeedParser(baseuri, baselang, known_encoding and 'utf-8' or '') - feedparser.feed(data) - result['feed'] = feedparser.feeddata - result['entries'] = feedparser.entries - result['version'] = result['version'] or feedparser.version - result['namespaces'] = feedparser.namespacesInUse - return result - -if __name__ == '__main__': - if not sys.argv[1:]: - print __doc__ - sys.exit(0) - else: - urls = sys.argv[1:] - zopeCompatibilityHack() - from pprint import pprint - for url in urls: - print url - print - result = parse(url) - pprint(result) - print - -#REVISION HISTORY -#1.0 - 9/27/2002 - MAP - fixed namespace processing on prefixed RSS 2.0 elements, -# added Simon Fell's test suite -#1.1 - 9/29/2002 - MAP - fixed infinite loop on incomplete CDATA sections -#2.0 - 10/19/2002 -# JD - use inchannel to watch out for image and textinput elements which can -# also contain title, link, and description elements -# JD - check for isPermaLink='false' attribute on guid elements -# JD - replaced openAnything with open_resource supporting ETag and -# If-Modified-Since request headers -# JD - parse now accepts etag, modified, agent, and referrer optional -# arguments -# JD - modified parse to return a dictionary instead of a tuple so that any -# etag or modified information can be returned and cached by the caller -#2.0.1 - 10/21/2002 - MAP - changed parse() so that if we don't get anything -# because of etag/modified, return the old etag/modified to the caller to -# indicate why nothing is being returned -#2.0.2 - 10/21/2002 - JB - added the inchannel to the if statement, otherwise its -# useless. Fixes the problem JD was addressing by adding it. -#2.1 - 11/14/2002 - MAP - added gzip support -#2.2 - 1/27/2003 - MAP - added attribute support, admin:generatorAgent. -# start_admingeneratoragent is an example of how to handle elements with -# only attributes, no content. -#2.3 - 6/11/2003 - MAP - added USER_AGENT for default (if caller doesn't specify); -# also, make sure we send the User-Agent even if urllib2 isn't available. -# Match any variation of backend.userland.com/rss namespace. -#2.3.1 - 6/12/2003 - MAP - if item has both link and guid, return both as-is. -#2.4 - 7/9/2003 - MAP - added preliminary Pie/Atom/Echo support based on Sam Ruby's -# snapshot of July 1 <http://www.intertwingly.net/blog/1506.html>; changed -# project name -#2.5 - 7/25/2003 - MAP - changed to Python license (all contributors agree); -# removed unnecessary urllib code -- urllib2 should always be available anyway; -# return actual url, status, and full HTTP headers (as result['url'], -# result['status'], and result['headers']) if parsing a remote feed over HTTP -- -# this should pass all the HTTP tests at <http://diveintomark.org/tests/client/http/>; -# added the latest namespace-of-the-week for RSS 2.0 -#2.5.1 - 7/26/2003 - RMK - clear opener.addheaders so we only send our custom -# User-Agent (otherwise urllib2 sends two, which confuses some servers) -#2.5.2 - 7/28/2003 - MAP - entity-decode inline xml properly; added support for -# inline <xhtml:body> and <xhtml:div> as used in some RSS 2.0 feeds -#2.5.3 - 8/6/2003 - TvdV - patch to track whether we're inside an image or -# textInput, and also to return the character encoding (if specified) -#2.6 - 1/1/2004 - MAP - dc:author support (MarekK); fixed bug tracking -# nested divs within content (JohnD); fixed missing sys import (JohanS); -# fixed regular expression to capture XML character encoding (Andrei); -# added support for Atom 0.3-style links; fixed bug with textInput tracking; -# added support for cloud (MartijnP); added support for multiple -# category/dc:subject (MartijnP); normalize content model: 'description' gets -# description (which can come from description, summary, or full content if no -# description), 'content' gets dict of base/language/type/value (which can come -# from content:encoded, xhtml:body, content, or fullitem); -# fixed bug matching arbitrary Userland namespaces; added xml:base and xml:lang -# tracking; fixed bug tracking unknown tags; fixed bug tracking content when -# <content> element is not in default namespace (like Pocketsoap feed); -# resolve relative URLs in link, guid, docs, url, comments, wfw:comment, -# wfw:commentRSS; resolve relative URLs within embedded HTML markup in -# description, xhtml:body, content, content:encoded, title, subtitle, -# summary, info, tagline, and copyright; added support for pingback and -# trackback namespaces -#2.7 - 1/5/2004 - MAP - really added support for trackback and pingback -# namespaces, as opposed to 2.6 when I said I did but didn't really; -# sanitize HTML markup within some elements; added mxTidy support (if -# installed) to tidy HTML markup within some elements; fixed indentation -# bug in _parse_date (FazalM); use socket.setdefaulttimeout if available -# (FazalM); universal date parsing and normalization (FazalM): 'created', modified', -# 'issued' are parsed into 9-tuple date format and stored in 'created_parsed', -# 'modified_parsed', and 'issued_parsed'; 'date' is duplicated in 'modified' -# and vice-versa; 'date_parsed' is duplicated in 'modified_parsed' and vice-versa -#2.7.1 - 1/9/2004 - MAP - fixed bug handling " and '. fixed memory -# leak not closing url opener (JohnD); added dc:publisher support (MarekK); -# added admin:errorReportsTo support (MarekK); Python 2.1 dict support (MarekK) -#2.7.4 - 1/14/2004 - MAP - added workaround for improperly formed <br/> tags in -# encoded HTML (skadz); fixed unicode handling in normalize_attrs (ChrisL); -# fixed relative URI processing for guid (skadz); added ICBM support; added -# base64 support -#2.7.5 - 1/15/2004 - MAP - added workaround for malformed DOCTYPE (seen on many -# blogspot.com sites); added _debug variable -#2.7.6 - 1/16/2004 - MAP - fixed bug with StringIO importing -#3.0b3 - 1/23/2004 - MAP - parse entire feed with real XML parser (if available); -# added several new supported namespaces; fixed bug tracking naked markup in -# description; added support for enclosure; added support for source; re-added -# support for cloud which got dropped somehow; added support for expirationDate -#3.0b4 - 1/26/2004 - MAP - fixed xml:lang inheritance; fixed multiple bugs tracking -# xml:base URI, one for documents that don't define one explicitly and one for -# documents that define an outer and an inner xml:base that goes out of scope -# before the end of the document -#3.0b5 - 1/26/2004 - MAP - fixed bug parsing multiple links at feed level -#3.0b6 - 1/27/2004 - MAP - added feed type and version detection, result['version'] -# will be one of SUPPORTED_VERSIONS.keys() or empty string if unrecognized; -# added support for creativeCommons:license and cc:license; added support for -# full Atom content model in title, tagline, info, copyright, summary; fixed bug -# with gzip encoding (not always telling server we support it when we do) -#3.0b7 - 1/28/2004 - MAP - support Atom-style author element in author_detail -# (dictionary of 'name', 'url', 'email'); map author to author_detail if author -# contains name + email address -#3.0b8 - 1/28/2004 - MAP - added support for contributor -#3.0b9 - 1/29/2004 - MAP - fixed check for presence of dict function; added -# support for summary -#3.0b10 - 1/31/2004 - MAP - incorporated ISO-8601 date parsing routines from -# xml.util.iso8601 -#3.0b11 - 2/2/2004 - MAP - added 'rights' to list of elements that can contain -# dangerous markup; fiddled with decodeEntities (not right); liberalized -# date parsing even further -#3.0b12 - 2/6/2004 - MAP - fiddled with decodeEntities (still not right); -# added support to Atom 0.2 subtitle; added support for Atom content model -# in copyright; better sanitizing of dangerous HTML elements with end tags -# (script, frameset) -#3.0b13 - 2/8/2004 - MAP - better handling of empty HTML tags (br, hr, img, -# etc.) in embedded markup, in either HTML or XHTML form (<br>, <br/>, <br />) -#3.0b14 - 2/8/2004 - MAP - fixed CDATA handling in non-wellformed feeds under -# Python 2.1 -#3.0b15 - 2/11/2004 - MAP - fixed bug resolving relative links in wfw:commentRSS; -# fixed bug capturing author and contributor URL; fixed bug resolving relative -# links in author and contributor URL; fixed bug resolvin relative links in -# generator URL; added support for recognizing RSS 1.0; passed Simon Fell's -# namespace tests, and included them permanently in the test suite with his -# permission; fixed namespace handling under Python 2.1 -#3.0b16 - 2/12/2004 - MAP - fixed support for RSS 0.90 (broken in b15) -#3.0b17 - 2/13/2004 - MAP - determine character encoding as per RFC 3023 -#3.0b18 - 2/17/2004 - MAP - always map description to summary_detail (Andrei); -# use libxml2 (if available) -#3.0b19 - 3/15/2004 - MAP - fixed bug exploding author information when author -# name was in parentheses; removed ultra-problematic mxTidy support; patch to -# workaround crash in PyXML/expat when encountering invalid entities -# (MarkMoraes); support for textinput/textInput -#3.0b20 - 4/7/2004 - MAP - added CDF support -#3.0b21 - 4/14/2004 - MAP - added Hot RSS support -#3.0b22 - 4/19/2004 - MAP - changed 'channel' to 'feed', 'item' to 'entries' in -# results dict; changed results dict to allow getting values with results.key -# as well as results[key]; work around embedded illformed HTML with half -# a DOCTYPE; work around malformed Content-Type header; if character encoding -# is wrong, try several common ones before falling back to regexes (if this -# works, bozo_exception is set to CharacterEncodingOverride); fixed character -# encoding issues in BaseHTMLProcessor by tracking encoding and converting -# from Unicode to raw strings before feeding data to sgmllib.SGMLParser; -# convert each value in results to Unicode (if possible), even if using -# regex-based parsing -#3.0b23 - 4/21/2004 - MAP - fixed UnicodeDecodeError for feeds that contain -# high-bit characters in attributes in embedded HTML in description (thanks -# Thijs van de Vossen); moved guid, date, and date_parsed to mapped keys in -# FeedParserDict; tweaked FeedParserDict.has_key to return True if asking -# about a mapped key -#3.0fc1 - 4/23/2004 - MAP - made results.entries[0].links[0] and -# results.entries[0].enclosures[0] into FeedParserDict; fixed typo that could -# cause the same encoding to be tried twice (even if it failed the first time); -# fixed DOCTYPE stripping when DOCTYPE contained entity declarations; -# better textinput and image tracking in illformed RSS 1.0 feeds -#3.0fc2 - 5/10/2004 - MAP - added and passed Sam's amp tests; added and passed -# my blink tag tests -#3.0fc3 - 6/18/2004 - MAP - fixed bug in _changeEncodingDeclaration that -# failed to parse utf-16 encoded feeds; made source into a FeedParserDict; -# duplicate admin:generatorAgent/@rdf:resource in generator_detail.url; -# added support for image; refactored parse() fallback logic to try other -# encodings if SAX parsing fails (previously it would only try other encodings -# if re-encoding failed); remove unichr madness in normalize_attrs now that -# we're properly tracking encoding in and out of BaseHTMLProcessor; set -# feed.language from root-level xml:lang; set entry.id from rdf:about; -# send Accept header -#3.0 - 6/21/2004 - MAP - don't try iso-8859-1 (can't distinguish between -# iso-8859-1 and windows-1252 anyway, and most incorrectly marked feeds are -# windows-1252); fixed regression that could cause the same encoding to be -# tried twice (even if it failed the first time) -#3.0.1 - 6/22/2004 - MAP - default to us-ascii for all text/* content types; -# recover from malformed content-type header parameter with no equals sign -# ('text/xml; charset:iso-8859-1') -#3.1 - 6/28/2004 - MAP - added and passed tests for converting HTML entities -# to Unicode equivalents in illformed feeds (aaronsw); added and -# passed tests for converting character entities to Unicode equivalents -# in illformed feeds (aaronsw); test for valid parsers when setting -# XML_AVAILABLE; make version and encoding available when server returns -# a 304; add handlers parameter to pass arbitrary urllib2 handlers (like -# digest auth or proxy support); add code to parse username/password -# out of url and send as basic authentication; expose downloading-related -# exceptions in bozo_exception (aaronsw); added __contains__ method to -# FeedParserDict (aaronsw); added publisher_detail (aaronsw) -#3.2 - 7/3/2004 - MAP - use cjkcodecs and iconv_codec if available; always -# convert feed to UTF-8 before passing to XML parser; completely revamped -# logic for determining character encoding and attempting XML parsing -# (much faster); increased default timeout to 20 seconds; test for presence -# of Location header on redirects; added tests for many alternate character -# encodings; support various EBCDIC encodings; support UTF-16BE and -# UTF16-LE with or without a BOM; support UTF-8 with a BOM; support -# UTF-32BE and UTF-32LE with or without a BOM; fixed crashing bug if no -# XML parsers are available; added support for 'Content-encoding: deflate'; -# send blank 'Accept-encoding: ' header if neither gzip nor zlib modules -# are available -#3.3 - 7/15/2004 - MAP - optimize EBCDIC to ASCII conversion; fix obscure -# problem tracking xml:base and xml:lang if element declares it, child -# doesn't, first grandchild redeclares it, and second grandchild doesn't; -# refactored date parsing; defined public registerDateHandler so callers -# can add support for additional date formats at runtime; added support -# for OnBlog, Nate, MSSQL, Greek, and Hungarian dates (ytrewq1); added -# zopeCompatibilityHack() which turns FeedParserDict into a regular -# dictionary, required for Zope compatibility, and also makes command- -# line debugging easier because pprint module formats real dictionaries -# better than dictionary-like objects; added NonXMLContentType exception, -# which is stored in bozo_exception when a feed is served with a non-XML -# media type such as 'text/plain'; respect Content-Language as default -# language if not xml:lang is present; cloud dict is now FeedParserDict; -# generator dict is now FeedParserDict; better tracking of xml:lang, -# including support for xml:lang='' to unset the current language; -# recognize RSS 1.0 feeds even when RSS 1.0 namespace is not the default -# namespace; don't overwrite final status on redirects (scenarios: -# redirecting to a URL that returns 304, redirecting to a URL that -# redirects to another URL with a different type of redirect); add -# support for HTTP 303 redirects -#4.0 - MAP - support for relative URIs in xml:base attribute; fixed -# encoding issue with mxTidy (phopkins); preliminary support for RFC 3229; -# support for Atom 1.0; support for iTunes extensions; new 'tags' for -# categories/keywords/etc. as array of dict -# {'term': term, 'scheme': scheme, 'label': label} to match Atom 1.0 -# terminology; parse RFC 822-style dates with no time; lots of other -# bug fixes -#4.1 - MAP - removed socket timeout; added support for chardet library - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/widgets/templates/wiki.mako b/addons/document_page/web/widgets/templates/wiki.mako deleted file mode 100644 index 54976a8c937..00000000000 --- a/addons/document_page/web/widgets/templates/wiki.mako +++ /dev/null @@ -1,23 +0,0 @@ -% if editable and not inline: - <textarea rows="10" id="${name}" name="${name}" class="${css_class}" - ${py.attrs(attrs, kind=kind)} style="width: 99%;">${value}</textarea> - <script type="text/javascript"> - if (!window.browser.isWebKit) { - new openerp.ui.TextArea('${name}'); - } - </script> -% endif - -% if editable and inline: - <input type="text" id="${name}" name="${name}" class="${css_class}" - ${py.attrs(attrs, kind=kind, value=value)}/> -% endif - -% if editable and error: - <span class="fielderror">${error}</span> -% endif - -% if not editable and value: - <div kind="${kind}" id="${name}" class="${css_class}">${data|n}</div> -% endif - diff --git a/addons/document_page/web/widgets/wiki.py b/addons/document_page/web/widgets/wiki.py deleted file mode 100644 index ccf2a75899c..00000000000 --- a/addons/document_page/web/widgets/wiki.py +++ /dev/null @@ -1,224 +0,0 @@ -############################################################################### -# -# Copyright (C) 2007-TODAY Tiny ERP Pvt Ltd. All Rights Reserved. -# -# $Id$ -# -# Developed by Tiny (http://openerp.com) and Axelor (http://axelor.com). -# -# The OpenERP web client is distributed under the "OpenERP Public License". -# It's based on Mozilla Public License Version (MPL) 1.1 with following -# restrictions: -# -# - All names, links and logos of Tiny, OpenERP and Axelor must be -# kept as in original distribution without any changes in all software -# screens, especially in start-up page and the software header, even if -# the application source code has been changed or updated or code has been -# added. -# -# - All distributions of the software must keep source code with OEPL. -# -# - All integrations to any other software must keep source code with OEPL. -# -# If you need commercial licence to remove this kind of restriction please -# contact us. -# -# You can see the MPL licence at: http://www.mozilla.org/MPL/MPL-1.1.html -# -############################################################################### - -import re - -import cherrypy -import wikimarkup - -from openobject import rpc -from openobject.widgets import CSSLink - - -from openerp.widgets import register_widget -from openerp.widgets.form import Text - - -_image = re.compile(r'img:(.*)\.(.*)', re.UNICODE) -_rss = re.compile(r'rss:(.*)\.(.*)', re.UNICODE) -_attach = re.compile(r'attach:(.*)\.(.*)', re.UNICODE) -_internalLinks = re.compile(r'\[\[.*\]\]', re.UNICODE) -_edit = re.compile(r'edit:(.*)\|(.*)', re.UNICODE) -_view = re.compile(r'view:(.*)\|(.*)', re.UNICODE) - -class WikiParser(wikimarkup.Parser): - - def parse(self, text, id): - text = text.replace(' ', 'n-b-s-p') - text = text.replace('&', 'n-a-m-p') - text = text.replace('&','&') - text = text.replace('n-b-s-p', ' ') - text = text.replace('n-a-m-p', '&') - text = text.replace('<code>', '<pre>') - text = text.replace('</code>', '</pre>') - - text = wikimarkup.to_unicode(text) - text = self.strip(text) - - text = super(WikiParser, self).parse(text) - text = self.addImage(text, id) - text = self.attachDoc(text, id) - text = self.recordLink(text) - text = self.viewRecordLink(text) - text = self.addInternalLinks(text) - #TODO : already implemented but we will implement it later after releasing the 5.0 - #text = self.addRss(text, id) - return text - - def viewRecordLink(self, text): - def record(path): - record = path.group().replace('view:','').split("|") - model = record[0] - text = record[1].replace('\r','').strip() - label = "View Record" - if len(record) > 2: - label = record[2] - proxy = rpc.RPCProxy(model) - ids = proxy.name_search(text, [], 'ilike', {}) - if len(ids): - id = ids[0][0] - else: - try: - id = int(text) - except: - id = 0 - return "[[/openerp/form/view?model=%s&id=%d | %s]]" % (model, id, label) - - bits = _view.sub(record, text) - return bits - - def addRss(self, text, id): - def addrss(path): - rssurl = path.group().replace('rss:','') - import rss.feedparser as feedparser - data = feedparser.parse(rssurl) - values = "<h2>%s</h2><br/>" % (data.feed.title) - values += "%s<br/>" % (data.channel.description) - for entry in data['entries']: - values += "<h3><a href='%s'> %s </a></h3><br/>" % (entry.link, entry.title) - values += "%s <br/>" % (entry.summary) - - return values - - bits = _rss.sub(addrss, text) - return bits - - def attachDoc(self, text, id): - def document(path): - file = path.group().replace('attach:','') - if file.startswith('http') or file.startswith('ftp'): - return "<a href='%s'>Download File</a>" % (file) - else: - proxy = rpc.RPCProxy('ir.attachment') - ids = proxy.search([('datas_fname','=',file.strip()), ('res_model','=','wiki.wiki'), ('res_id','=',id)]) - if len(ids) > 0: - return "<a href='/widget_wiki/wiki/getfile?file=%s&id=%d'>%s</a>" % (file, id, file) - else: - return """<a onclick="openobject.tools.openWindow(openobject.http.getURL('/openerp/attachment', {model: 'wiki.wiki', id: %d}), - {name : 'Wiki Attachments'})">Attach : %s </a>""" % (id, file) - bits = _attach.sub(document, text) - return bits - - def addImage(self, text, id): - def image(path): - file = path.group().replace('img:','') - if file.startswith('http') or file.startswith('ftp'): - return "<img src='%s'/>" % (file) - else: - proxy = rpc.RPCProxy('ir.attachment') - ids = proxy.search([('datas_fname','=',file.strip()), ('res_model','=','wiki.wiki'), ('res_id','=',id)]) - if len(ids) > 0: - return "<img src='/widget_wiki/wiki/getImage?file=%s&id=%d'/>" % (file, id) - else: - return """<a onclick="openobject.tools.openWindow(openobject.http.getURL('/openerp/attachment', {model: 'wiki.wiki', id: %d}), - {name : 'Wiki Attachments'})">Attach : %s </a>""" % (id, file) - #"[[/attachment/?model=wiki.wiki&id=%d | Attach:%s]]" % (id, file) - bits = _image.sub(image, text) - return bits - - def recordLink(self, text): - def record(path): - record = path.group().replace('edit:','').split("|") - model = record[0] - text = record[1].replace('\r','').strip() - label = "Edit Record" - if len(record) > 2: - label = record[2] - proxy = rpc.RPCProxy(model) - ids = proxy.name_search(text, [], '=', {}) - if len(ids): - id = ids[0][0] - else: - try: - id = int(text) - except: - id = 0 - return "[[/openerp/form/edit?model=%s&id=%d | %s]]" % (model, id, label) - - bits = _edit.sub(record, text) - return bits - - def addInternalLinks(self, text): - proxy = rpc.RPCProxy('wiki.wiki') - - def link(path): - link = path.group().replace('[','').replace('[','').replace(']','').replace(']','').split("|") - name_to_search = link[0].strip() - mids = proxy.search([('name','ilike', name_to_search)]) - link_str = "" - if mids: - if len(link) == 2: - link_str = "<a href='/openerp/form/view?model=wiki.wiki&id=%s'>%s</a>" % (mids[0], link[1]) - elif len(link) == 1: - link_str = "<a href='/openerp/form/view?model=wiki.wiki&id=%s'>%s</a>" % (mids[0], link[0]) - else: - if len(link) == 2: - link_str = "<a href='%s'>%s</a>" % (link[0], link[1]) - elif len(link) == 1: - link_str = "<a href='/openerp/form/edit?model=wiki.wiki&id=False'>%s</a>" % (link[0]) - - return link_str - - bits = _internalLinks.sub(link, text) - return bits - -def wiki2html(text, showToc, id): - p = WikiParser(show_toc=showToc) - return p.parse(text, id) - -class WikiWidget(Text): - template = "/wiki/widgets/templates/wiki.mako" - - params = ["data"] - - css = [CSSLink("wiki", "css/wiki.css")] - - data = None - - def set_value(self, value): - super(WikiWidget, self).set_value(value) - - if value: - toc = True - id = False - if hasattr(cherrypy.request, 'terp_record'): - params = cherrypy.request.terp_params - if params._terp_model == 'wiki.wiki': - proxy = rpc.RPCProxy('wiki.wiki') - toc = proxy.read([params.id], ['toc'])[0]['toc'] - id = params.id - - text = value+'\n\n' - html = wiki2html(text, toc, id) - - self.data = html - -register_widget(WikiWidget, ["text_wiki"]) - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: diff --git a/addons/document_page/web/widgets/wikimarkup/__init__.py b/addons/document_page/web/widgets/wikimarkup/__init__.py deleted file mode 100644 index f5fe67fada1..00000000000 --- a/addons/document_page/web/widgets/wikimarkup/__init__.py +++ /dev/null @@ -1,2146 +0,0 @@ -# coding: latin1 -""" -MediaWiki-style markup - -Copyright (C) 2008 David Cramer <dcramer@gmail.com> - -This program is free software: you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation, either version 3 of the License, or -(at your option) any later version. - -This program is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. - -You should have received a copy of the GNU General Public License -along with this program. If not, see <http://www.gnu.org/licenses/>. -""" - -import re, random, locale -from base64 import b64encode, b64decode - -# a few patterns we use later - -MW_COLON_STATE_TEXT = 0 -MW_COLON_STATE_TAG = 1 -MW_COLON_STATE_TAGSTART = 2 -MW_COLON_STATE_CLOSETAG = 3 -MW_COLON_STATE_TAGSLASH = 4 -MW_COLON_STATE_COMMENT = 5 -MW_COLON_STATE_COMMENTDASH = 6 -MW_COLON_STATE_COMMENTDASHDASH = 7 - -_attributePat = re.compile(ur'''(?:^|\s)([A-Za-z0-9]+)(?:\s*=\s*(?:"([^<"]*)"|'([^<']*)'|([a-zA-Z0-9!#$%&()*,\-./:;<>?@[\]^_`{|}~]+)|#([0-9a-fA-F]+)))''', re.UNICODE) -_space = re.compile(ur'\s+', re.UNICODE) -_closePrePat = re.compile(u"</pre", re.UNICODE | re.IGNORECASE) -_openPrePat = re.compile(u"<pre", re.UNICODE | re.IGNORECASE) -_openMatchPat = re.compile(u"(<table|<blockquote|<h1|<h2|<h3|<h4|<h5|<h6|<pre|<tr|<p|<ul|<ol|<li|</center|</tr|</td|</th)", re.UNICODE | re.IGNORECASE) -_tagPattern = re.compile(ur'^(/?)(\w+)([^>]*?)(/?>)([^<]*)$', re.UNICODE) - -_htmlpairs = ( # Tags that must be closed - u'b', u'del', u'i', u'ins', u'u', u'font', u'big', u'small', u'sub', u'sup', u'h1', - u'h2', u'h3', u'h4', u'h5', u'h6', u'cite', u'code', u'em', u's', - u'strike', u'strong', u'tt', u'var', u'div', u'center', - u'blockquote', u'ol', u'ul', u'dl', u'table', u'caption', u'pre', - u'ruby', u'rt' , u'rb' , u'rp', u'p', u'span', u'u', -) -_htmlsingle = ( - u'br', u'hr', u'li', u'dt', u'dd', u'img', -) -_htmlsingleonly = ( # Elements that cannot have close tags - u'br', u'hr', u'img', -) -_htmlnest = ( # Tags that can be nested--?? - u'table', u'tr', u'td', u'th', u'div', u'blockquote', u'ol', u'ul', - u'dl', u'font', u'big', u'small', u'sub', u'sup', u'span', u'img', -) -_tabletags = ( # Can only appear inside table - u'td', u'th', u'tr', -) -_htmllist = ( # Tags used by list - u'ul', u'ol', -) -_listtags = ( # Tags that can appear in a list - u'li', -) -_htmlsingleallowed = _htmlsingle + _tabletags -_htmlelements = _htmlsingle + _htmlpairs + _htmlnest - -_htmlEntities = { - u'Aacute': 193, u'aacute': 225, u'Acirc': 194, u'acirc': 226, u'acute': 180, - u'AElig': 198, u'aelig': 230, u'Agrave': 192, u'agrave': 224, u'alefsym': 8501, - u'Alpha': 913, u'alpha': 945, u'amp': 38, u'and': 8743, u'ang': 8736, u'Aring': 197, - u'aring': 229, - u'asymp': 8776, - u'Atilde': 195, - u'atilde': 227, - u'Auml': 196, - u'auml': 228, - u'bdquo': 8222, - u'Beta': 914, - u'beta': 946, - u'brvbar': 166, - u'bull': 8226, - u'cap': 8745, - u'Ccedil': 199, - u'ccedil': 231, - u'cedil': 184, - u'cent': 162, - u'Chi': 935, - u'chi': 967, - u'circ': 710, - u'clubs': 9827, - u'cong': 8773, - u'copy': 169, - u'crarr': 8629, - u'cup': 8746, - u'curren': 164, - u'dagger': 8224, - u'Dagger': 8225, - u'darr': 8595, - u'dArr': 8659, - u'deg': 176, - u'Delta': 916, - u'delta': 948, - u'diams': 9830, - u'divide': 247, - u'Eacute': 201, - u'eacute': 233, - u'Ecirc': 202, - u'ecirc': 234, - u'Egrave': 200, - u'egrave': 232, - u'empty': 8709, - u'emsp': 8195, - u'ensp': 8194, - u'Epsilon': 917, - u'epsilon': 949, - u'equiv': 8801, - u'Eta': 919, - u'eta': 951, - u'ETH': 208, - u'eth': 240, - u'Euml': 203, - u'euml': 235, - u'euro': 8364, - u'exist': 8707, - u'fnof': 402, - u'forall': 8704, - u'frac12': 189, - u'frac14': 188, - u'frac34': 190, - u'frasl': 8260, - u'Gamma': 915, - u'gamma': 947, - u'ge': 8805, - u'gt': 62, - u'harr': 8596, - u'hArr': 8660, - u'hearts': 9829, - u'hellip': 8230, - u'Iacute': 205, - u'iacute': 237, - u'Icirc': 206, - u'icirc': 238, - u'iexcl': 161, - u'Igrave': 204, - u'igrave': 236, - u'image': 8465, - u'infin': 8734, - u'int': 8747, - u'Iota': 921, - u'iota': 953, - u'iquest': 191, - u'isin': 8712, - u'Iuml': 207, - u'iuml': 239, - u'Kappa': 922, - u'kappa': 954, - u'Lambda': 923, - u'lambda': 955, - u'lang': 9001, - u'laquo': 171, - u'larr': 8592, - u'lArr': 8656, - u'lceil': 8968, - u'ldquo': 8220, - u'le': 8804, - u'lfloor': 8970, - u'lowast': 8727, - u'loz': 9674, - u'lrm': 8206, - u'lsaquo': 8249, - u'lsquo': 8216, - u'lt': 60, - u'macr': 175, - u'mdash': 8212, - u'micro': 181, - u'middot': 183, - u'minus': 8722, - u'Mu': 924, - u'mu': 956, - u'nabla': 8711, - u'nbsp': 160, - u'ndash': 8211, - u'ne': 8800, - u'ni': 8715, - u'not': 172, - u'notin': 8713, - u'nsub': 8836, - u'Ntilde': 209, - u'ntilde': 241, - u'Nu': 925, - u'nu': 957, - u'Oacute': 211, - u'oacute': 243, - u'Ocirc': 212, - u'ocirc': 244, - u'OElig': 338, - u'oelig': 339, - u'Ograve': 210, - u'ograve': 242, - u'oline': 8254, - u'Omega': 937, - u'omega': 969, - u'Omicron': 927, - u'omicron': 959, - u'oplus': 8853, - u'or': 8744, - u'ordf': 170, - u'ordm': 186, - u'Oslash': 216, - u'oslash': 248, - u'Otilde': 213, - u'otilde': 245, - u'otimes': 8855, - u'Ouml': 214, - u'ouml': 246, - u'para': 182, - u'part': 8706, - u'permil': 8240, - u'perp': 8869, - u'Phi': 934, - u'phi': 966, - u'Pi': 928, - u'pi': 960, - u'piv': 982, - u'plusmn': 177, - u'pound': 163, - u'prime': 8242, - u'Prime': 8243, - u'prod': 8719, - u'prop': 8733, - u'Psi': 936, - u'psi': 968, - u'quot': 34, - u'radic': 8730, - u'rang': 9002, - u'raquo': 187, - u'rarr': 8594, - u'rArr': 8658, - u'rceil': 8969, - u'rdquo': 8221, - u'real': 8476, - u'reg': 174, - u'rfloor': 8971, - u'Rho': 929, - u'rho': 961, - u'rlm': 8207, - u'rsaquo': 8250, - u'rsquo': 8217, - u'sbquo': 8218, - u'Scaron': 352, - u'scaron': 353, - u'sdot': 8901, - u'sect': 167, - u'shy': 173, - u'Sigma': 931, - u'sigma': 963, - u'sigmaf': 962, - u'sim': 8764, - u'spades': 9824, - u'sub': 8834, - u'sube': 8838, - u'sum': 8721, - u'sup': 8835, - u'sup1': 185, - u'sup2': 178, - u'sup3': 179, - u'supe': 8839, - u'szlig': 223, - u'Tau': 932, - u'tau': 964, - u'there4': 8756, - u'Theta': 920, - u'theta': 952, - u'thetasym': 977, - u'thinsp': 8201, - u'THORN': 222, - u'thorn': 254, - u'tilde': 732, - u'times': 215, - u'trade': 8482, - u'Uacute': 218, - u'uacute': 250, - u'uarr': 8593, - u'uArr': 8657, - u'Ucirc': 219, - u'ucirc': 251, - u'Ugrave': 217, - u'ugrave': 249, - u'uml': 168, - u'upsih': 978, - u'Upsilon': 933, - u'upsilon': 965, - u'Uuml': 220, - u'uuml': 252, - u'weierp': 8472, - u'Xi': 926, - u'xi': 958, - u'Yacute': 221, - u'yacute': 253, - u'yen': 165, - u'Yuml': 376, - u'yuml': 255, - u'Zeta': 918, - u'zeta': 950, - u'zwj': 8205, - u'zwnj': 8204 -} - -_charRefsPat = re.compile(ur'''(&([A-Za-z0-9]+);|&#([0-9]+);|&#[xX]([0-9A-Za-z]+);|(&))''', re.UNICODE) -_cssCommentPat = re.compile(ur'''\*.*?\*''', re.UNICODE) -_toUTFPat = re.compile(ur'''\\([0-9A-Fa-f]{1,6})[\s]?''', re.UNICODE) -_hackPat = re.compile(ur'''(expression|tps*://|url\s*\().*''', re.UNICODE | re.IGNORECASE) -_hrPat = re.compile(u'''^-----*''', re.UNICODE | re.MULTILINE) -_h1Pat = re.compile(u'^=(.+)=\s*$', re.UNICODE | re.MULTILINE) -_h2Pat = re.compile(u'^==(.+)==\s*$', re.UNICODE | re.MULTILINE) -_h3Pat = re.compile(u'^===(.+)===\s*$', re.UNICODE | re.MULTILINE) -_h4Pat = re.compile(u'^====(.+)====\s*$', re.UNICODE | re.MULTILINE) -_h5Pat = re.compile(u'^=====(.+)=====\s*$', re.UNICODE | re.MULTILINE) -_h6Pat = re.compile(u'^======(.+)======\s*$', re.UNICODE | re.MULTILINE) -_quotePat = re.compile(u"""(''+)""", re.UNICODE) -_removePat = re.compile(ur'\b(' + ur'|'.join((u"a", u"an", u"as", u"at", u"before", u"but", u"by", u"for", u"from", - u"is", u"in", u"into", u"like", u"of", u"off", u"on", u"onto", u"per", - u"since", u"than", u"the", u"this", u"that", u"to", u"up", u"via", - u"with")) + ur')\b', re.UNICODE | re.IGNORECASE) -_nonWordSpaceDashPat = re.compile(ur'[^\w\s\-\./]', re.UNICODE) -_multiSpacePat = re.compile(ur'[\s\-_\./]+', re.UNICODE) -_spacePat = re.compile(ur' ', re.UNICODE) -_linkPat = re.compile(ur'^(?:([A-Za-z0-9]+):)?([^\|]+)(?:\|([^\n]+?))?\]\](.*)$', re.UNICODE | re.DOTALL) -_bracketedLinkPat = re.compile(ur'(?:\[((?:mailto:|irc://|https?://|ftp://|/)[^<>\]\[' + u"\x00-\x20\x7f" + ur']*)\s*(.*?)\])', re.UNICODE) -_protocolPat = re.compile(ur'(\b(?:mailto:|irc://|https?://|ftp://))', re.UNICODE) -_specialUrlPat = re.compile(ur'^([^<>\]\[' + u"\x00-\x20\x7f" + ur']+)(.*)$', re.UNICODE) -_protocolsPat = re.compile(ur'^(mailto:|irc://|https?://|ftp://)$', re.UNICODE) -_controlCharsPat = re.compile(ur'[\]\[<>"' + u"\\x00-\\x20\\x7F" + ur']]', re.UNICODE) -_hostnamePat = re.compile(ur'^([^:]+:)(//[^/]+)?(.*)$', re.UNICODE) -_stripPat = re.compile(u'\\s|\u00ad|\u1806|\u200b|\u2060|\ufeff|\u03f4|\u034f|\u180b|\u180c|\u180d|\u200c|\u200d|[\ufe00-\ufe0f]', re.UNICODE) -_zomgPat = re.compile(ur'^(:*)\{\|(.*)$', re.UNICODE) -_headerPat = re.compile(ur"<[Hh]([1-6])(.*?)>(.*?)</[Hh][1-6] *>", re.UNICODE) -_templateSectionPat = re.compile(ur"<!--MWTEMPLATESECTION=([^&]+)&([^_]+)-->", re.UNICODE) -_tagPat = re.compile(ur"<.*?>", re.UNICODE) -_startRegexHash = {} -_endRegexHash = {} -_endCommentPat = re.compile(ur'(-->)', re.UNICODE) -_extractTagsAndParams_n = 1 -_guillemetLeftPat = re.compile(ur'(.) (\?|:|;|!|\302\273)', re.UNICODE) -_guillemetRightPat = re.compile(ur'(\302\253) ', re.UNICODE) - -def setupAttributeWhitelist(): - common = ( u'id', u'class', u'lang', u'dir', u'title', u'style' ) - block = common + (u'align',) - tablealign = ( u'align', u'char', u'charoff', u'valign' ) - tablecell = ( u'abbr', - u'axis', - u'headers', - u'scope', - u'rowspan', - u'colspan', - u'nowrap', # deprecated - u'width', # deprecated - u'height', # deprecated - u'bgcolor' # deprecated - ) - return { - u'div': block, - u'center': common, # deprecated - u'span': block, # ?? - u'h1': block, - u'h2': block, - u'h3': block, - u'h4': block, - u'h5': block, - u'h6': block, - u'em': common, - u'strong': common, - u'cite': common, - u'code': common, - u'var': common, - u'img': common + (u'src', u'alt', u'width', u'height',), - u'blockquote': common + (u'cite',), - u'sub': common, - u'sup': common, - u'p': block, - u'br': (u'id', u'class', u'title', u'style', u'clear',), - u'pre': common + (u'width',), - u'ins': common + (u'cite', u'datetime'), - u'del': common + (u'cite', u'datetime'), - u'ul': common + (u'type',), - u'ol': common + (u'type', u'start'), - u'li': common + (u'type', u'value'), - u'dl': common, - u'dd': common, - u'dt': common, - u'table': common + ( u'summary', u'width', u'border', u'frame', - u'rules', u'cellspacing', u'cellpadding', - u'align', u'bgcolor', - ), - u'caption': common + (u'align',), - u'thead': common + tablealign, - u'tfoot': common + tablealign, - u'tbody': common + tablealign, - u'colgroup': common + ( u'span', u'width' ) + tablealign, - u'col': common + ( u'span', u'width' ) + tablealign, - u'tr': common + ( u'bgcolor', ) + tablealign, - u'td': common + tablecell + tablealign, - u'th': common + tablecell + tablealign, - u'tt': common, - u'b': common, - u'i': common, - u'big': common, - u'small': common, - u'strike': common, - u's': common, - u'u': common, - u'font': common + ( u'size', u'color', u'face' ), - u'hr': common + ( u'noshade', u'size', u'width' ), - u'ruby': common, - u'rb': common, - u'rt': common, #array_merge( $common, array( 'rbspan' ) ), - u'rp': common, - } -_whitelist = setupAttributeWhitelist() -_page_cache = {} -env = {} - -def registerTagHook(tag, function): - mTagHooks[tag] = function - -class BaseParser(object): - def __init__(self): - self.uniq_prefix = u"\x07UNIQ" + unicode(random.randint(1, 1000000000)) - self.strip_state = {} - self.arg_stack = [] - self.env = env - self.keep_env = (env != {}) - - def __del__(self): - if not self.keep_env: - global env - env = {} - - ''' Used to store objects in the environment - used to prevent recursive imports ''' - def store_object(self, namespace, key, value=True): - # Store the item to not reprocess it - if namespace not in self.env: - self.env[namespace] = {} - self.env[namespace][key] = value - - def has_object(self, namespace, key): - if namespace not in self.env: - self.env[namespace] = {} - if hasattr(self, 'count'): - data = self.env[namespace] - test = key in data - self.count = True - return key in self.env[namespace] - - def retrieve_object(self, namespace, key, default=None): - if not self.env.get(namespace): - self.env[namespace] = {} - return self.env[namespace].get(key, default) - - def parse(self, text): - utf8 = isinstance(text, str) - text = to_unicode(text) - if text[-1:] != u'\n': - text = text + u'\n' - taggedNewline = True - else: - taggedNewline = False - - text = self.strip(text) - text = self.removeHtmlTags(text) - text = self.parseHorizontalRule(text) - text = self.parseAllQuotes(text) - text = self.replaceExternalLinks(text) - text = self.unstrip(text) - text = self.fixtags(text) - text = self.doBlockLevels(text, True) - text = self.unstripNoWiki(text) - text = text.split(u'\n') - text = u'\n'.join(text) - if taggedNewline and text[-1:] == u'\n': - text = text[:-1] - if utf8: - return text.encode("utf-8") - return text - - def strip(self, text, stripcomments=False, dontstrip=[]): - render = True - - commentState = {} - - elements = ['nowiki',] + mTagHooks.keys() - if True: #wgRawHtml - elements.append('html') - - # Removing $dontstrip tags from $elements list (currently only 'gallery', fixing bug 2700) - for k in dontstrip: - if k in elements: - del elements[k] - - matches = {} - text = self.extractTagsAndParams(elements, text, matches) - - for marker in matches: - element, content, params, tag = matches[marker] - if render: - tagName = element.lower() - if tagName == u'!--': - # comment - output = tag - if tag[-3:] != u'-->': - output += "-->" - elif tagName == u'html': - output = content - elif tagName == u'nowiki': - output = content.replace(u'&', u'&').replace(u'<', u'<').replace(u'>', u'>') - else: - if tagName in mTagHooks: - output = mTagHooks[tagName](self, content, params) - else: - output = content.replace(u'&', u'&').replace(u'<', u'<').replace(u'>', u'>') - else: - # Just stripping tags; keep the source - output = tag - - # Unstrip the output, because unstrip() is no longer recursive so - # it won't do it itself - output = self.unstrip(output) - - if not stripcomments and element == u'!--': - commentState[marker] = output - elif element == u'html' or element == u'nowiki': - if 'nowiki' not in self.strip_state: - self.strip_state['nowiki'] = {} - self.strip_state['nowiki'][marker] = output - else: - if 'general' not in self.strip_state: - self.strip_state['general'] = {} - self.strip_state['general'][marker] = output - - # Unstrip comments unless explicitly told otherwise. - # (The comments are always stripped prior to this point, so as to - # not invoke any extension tags / parser hooks contained within - # a comment.) - if not stripcomments: - # Put them all back and forget them - for k in commentState: - v = commentState[k] - text = text.replace(k, v) - - return text - - def removeHtmlTags(self, text): - """convert bad tags into HTML identities""" - sb = [] - text = self.removeHtmlComments(text) - bits = text.split(u'<') - sb.append(bits.pop(0)) - tagstack = [] - tablestack = tagstack - for x in bits: - m = _tagPattern.match(x) - if not m: - continue - slash, t, params, brace, rest = m.groups() - t = t.lower() - badtag = False - if t in _htmlelements: - # Check our stack - if slash: - # Closing a tag... - if t in _htmlsingleonly or len(tagstack) == 0: - badtag = True - else: - ot = tagstack.pop() - if ot != t: - if ot in _htmlsingleallowed: - # Pop all elements with an optional close tag - # and see if we find a match below them - optstack = [] - optstack.append(ot) - while True: - if len(tagstack) == 0: - break - ot = tagstack.pop() - if ot == t or ot not in _htmlsingleallowed: - break - optstack.append(ot) - if t != ot: - # No match. Push the optinal elements back again - badtag = True - tagstack += reversed(optstack) - else: - tagstack.append(ot) - # <li> can be nested in <ul> or <ol>, skip those cases: - if ot not in _htmllist and t in _listtags: - badtag = True - elif t == u'table': - if len(tablestack) == 0: - bagtag = True - else: - tagstack = tablestack.pop() - newparams = u'' - else: - # Keep track for later - if t in _tabletags and u'table' not in tagstack: - badtag = True - elif t in tagstack and t not in _htmlnest: - badtag = True - # Is it a self-closed htmlpair? (bug 5487) - elif brace == u'/>' and t in _htmlpairs: - badTag = True - elif t in _htmlsingleonly: - # Hack to force empty tag for uncloseable elements - brace = u'/>' - elif t in _htmlsingle: - # Hack to not close $htmlsingle tags - brace = None - else: - if t == u'table': - tablestack.append(tagstack) - tagstack = [] - tagstack.append(t) - newparams = self.fixTagAttributes(params, t) - if not badtag: - rest = rest.replace(u'>', u'>') - if brace == u'/>': - close = u' /' - else: - close = u'' - sb.append(u'<') - sb.append(slash) - sb.append(t) - sb.append(newparams) - sb.append(close) - sb.append(u'>') - sb.append(rest) - continue - sb.append(u'<') - sb.append(x.replace(u'>', u'>')) - - # Close off any remaining tags - while tagstack: - t = tagstack.pop() - sb.append(u'</') - sb.append(t) - sb.append(u'>\n') - if t == u'table': - if not tablestack: - break - tagstack = tablestack.pop() - - return u''.join(sb) - - def removeHtmlComments(self, text): - """remove <!-- text --> comments from given text""" - sb = [] - start = text.find(u'<!--') - last = 0 - while start != -1: - end = text.find(u'-->', start) - if end == -1: - break - end += 3 - - spaceStart = max(0, start-1) - spaceEnd = end - while text[spaceStart] == u' ' and spaceStart > 0: - spaceStart -= 1 - while text[spaceEnd] == u' ': - spaceEnd += 1 - - if text[spaceStart] == u'\n' and text[spaceEnd] == u'\n': - sb.append(text[last:spaceStart]) - sb.append(u'\n') - last = spaceEnd+1 - else: - sb.append(text[last:spaceStart+1]) - last = spaceEnd - - start = text.find(u'<!--', end) - sb.append(text[last:]) - return u''.join(sb) - - def decodeTagAttributes(self, text): - """docstring for decodeTagAttributes""" - attribs = {} - if text.strip() == u'': - return attribs - scanner = _attributePat.scanner(text) - match = scanner.search() - while match: - key, val1, val2, val3, val4 = match.groups() - value = val1 or val2 or val3 or val4 - if value: - value = _space.sub(u' ', value).strip() - else: - value = '' - attribs[key] = self.decodeCharReferences(value) - - match = scanner.search() - return attribs - - def validateTagAttributes(self, attribs, element): - """docstring for validateTagAttributes""" - out = {} - if element not in _whitelist: - return out - whitelist = _whitelist[element] - for attribute in attribs: - value = attribs[attribute] - if attribute not in whitelist: - continue - # Strip javascript "expression" from stylesheets. - # http://msdn.microsoft.com/workshop/author/dhtml/overview/recalc.asp - if attribute == u'style': - value = self.checkCss(value) - if value == False: - continue - elif attribute == u'id': - value = self.escapeId(value) - # If this attribute was previously set, override it. - # Output should only have one attribute of each name. - out[attribute] = value - return out - - def safeEncodeAttribute(self, encValue): - """docstring for safeEncodeAttribute""" - encValue = encValue.replace(u'&', u'&') - encValue = encValue.replace(u'<', u'<') - encValue = encValue.replace(u'>', u'>') - encValue = encValue.replace(u'"', u'"') - encValue = encValue.replace(u'{', u'{') - encValue = encValue.replace(u'[', u'[') - encValue = encValue.replace(u"''", u'''') - encValue = encValue.replace(u'ISBN', u'ISBN') - encValue = encValue.replace(u'RFC', u'RFC') - encValue = encValue.replace(u'PMID', u'PMID') - encValue = encValue.replace(u'|', u'|') - encValue = encValue.replace(u'__', u'__') - encValue = encValue.replace(u'\n', u' ') - encValue = encValue.replace(u'\r', u' ') - encValue = encValue.replace(u'\t', u'	') - return encValue - - def fixTagAttributes(self, text, element): - if text.strip() == u'': - return u'' - - stripped = self.validateTagAttributes(self.decodeTagAttributes(text), element) - - sb = [] - - for attribute in stripped: - value = stripped[attribute] - encAttribute = attribute.replace(u'&', u'&').replace(u'<', u'<').replace(u'>', u'>') - encValue = self.safeEncodeAttribute(value) - - sb.append(u' ') - sb.append(encAttribute) - sb.append(u'="') - sb.append(encValue) - sb.append(u'"') - - return u''.join(sb) - - def validateCodepoint(self, codepoint): - return codepoint == 0x09 \ - or codepoint == 0x0a \ - or codepoint == 0x0d \ - or (codepoint >= 0x20 and codepoint <= 0xd7ff) \ - or (codepoint >= 0xe000 and codepoint <= 0xfffd) \ - or (codepoint >= 0x10000 and codepoint <= 0x10ffff) - - def _normalizeCallback(self, match): - text, norm, dec, hexval, _ = match.groups() - if norm: - sb = [] - sb.append(u'&') - if norm not in _htmlEntities: - sb.append(u'amp;') - sb.append(norm) - sb.append(u';') - return u''.join(sb) - elif dec: - dec = int(dec) - if self.validateCodepoint(dec): - sb = [] - sb.append(u'&#') - sb.append(dec) - sb.append(u';') - return u''.join(sb) - elif hexval: - hexval = int(hexval, 16) - if self.validateCodepoint(hexval): - sb = [] - sb.append(u'&#x') - sb.append(hex(hexval)) - sb.append(u';') - return u''.join(sb) - return text.replace(u'&', u'&').replace(u'<', u'<').replace(u'>', u'>') - - def normalizeCharReferences(self, text): - """docstring for normalizeCharReferences""" - return _charRefsPat.sub(self._normalizeCallback, text) - - def _decodeCallback(self, match): - text, norm, dec, hexval, _ = match.groups() - if norm: - if norm in _htmlEntities: - return unichr(_htmlEntities[norm]) - else: - sb = [] - sb.append(u'&') - sb.append(norm) - sb.append(u';') - return u''.join(sb) - elif dec: - dec = int(dec) - if self.validateCodepoint(dec): - return unichr(dec) - return u'?' - elif hexval: - hexval = int(hexval, 16) - if self.validateCodepoint(dec): - return unichr(dec) - return u'?' - return text - - def decodeCharReferences(self, text): - """docstring for decodeCharReferences""" - if text: - return _charRefsPat.sub(self._decodeCallback, text) - return '' - - def _convertToUtf8(self, s): - return unichr(int(s.group(1), 16)) - - def checkCss(self, value): - """docstring for checkCss""" - stripped = self.decodeCharReferences(value) - - stripped = _cssCommentPat.sub(u'', stripped) - value = stripped - - stripped = _toUTFPat.sub(self._convertToUtf8, stripped) - stripped.replace(u'\\', u'') - if _hackPat.search(stripped): - # someone is haxx0ring - return False - - return value - - def escapeId(self, value): - """docstring for escapeId""" - # TODO - return safe_name(value) - - def parseHorizontalRule(self, text): - return _hrPat.sub(ur'<hr />', text) - - def parseHeaders(self, text): - text = _h6Pat.sub(ur'<h6>\1</h6>', text) - text = _h5Pat.sub(ur'<h5>\1</h5>', text) - text = _h4Pat.sub(ur'<h4>\1</h4>', text) - text = _h3Pat.sub(ur'<h3>\1</h3>', text) - text = _h2Pat.sub(ur'<h2>\1</h2>', text) - text = _h1Pat.sub(ur'<h1>\1</h1>', text) - return text - - def parseQuotes(self, text): - arr = _quotePat.split(text) - if len(arr) == 1: - return text - # First, do some preliminary work. This may shift some apostrophes from - # being mark-up to being text. It also counts the number of occurrences - # of bold and italics mark-ups. - numBold = 0 - numItalics = 0 - for i,r in zip(range(len(arr)), arr): - if i%2 == 1: - l = len(r) - if l == 4: - arr[i-1] += u"'" - arr[i] = u"'''" - elif l > 5: - arr[i-1] += u"'" * (len(arr[i]) - 5) - arr[i] = u"'''''" - if l == 2: - numItalics += 1 - elif l >= 5: - numItalics += 1 - numBold += 1 - else: - numBold += 1 - - # If there is an odd number of both bold and italics, it is likely - # that one of the bold ones was meant to be an apostrophe followed - # by italics. Which one we cannot know for certain, but it is more - # likely to be one that has a single-letter word before it. - if numBold%2 == 1 and numItalics%2 == 1: - firstSingleLetterWord = -1 - firstMultiLetterWord = -1 - firstSpace = -1 - for i,r in zip(range(len(arr)), arr): - if i%2 == 1 and len(r) == 3: - x1 = arr[i-1][-1:] - x2 = arr[i-1][-2:-1] - if x1 == u' ': - if firstSpace == -1: - firstSpace = i - elif x2 == u' ': - if firstSingleLetterWord == -1: - firstSingleLetterWord = i - else: - if firstMultiLetterWord == -1: - firstMultiLetterWord = i - - # If there is a single-letter word, use it! - if firstSingleLetterWord > -1: - arr[firstSingleLetterWord] = u"''" - arr[firstSingleLetterWord-1] += u"'" - # If not, but there's a multi-letter word, use that one. - elif firstMultiLetterWord > -1: - arr[firstMultiLetterWord] = u"''" - arr[firstMultiLetterWord-1] += u"'" - # ... otherwise use the first one that has neither. - # (notice that it is possible for all three to be -1 if, for example, - # there is only one pentuple-apostrophe in the line) - elif firstSpace > -1: - arr[firstSpace] = u"''" - arr[firstSpace-1] += u"'" - - # Now let's actually convert our apostrophic mush to HTML! - output = [] - buffer = None - state = '' - for i,r in zip(range(len(arr)), arr): - if i%2 == 0: - if state == 'both': - buffer.append(r) - else: - output.append(r) - else: - if len(r) == 2: - if state == 'i': - output.append(u"</i>") - state = '' - elif state == 'bi': - output.append(u"</i>") - state = 'b' - elif state == 'ib': - output.append(u"</b></i><b>") - state = 'b' - elif state == 'both': - output.append(u"<b><i>") - output.append(u''.join(buffer)) - buffer = None - output.append(u"</i>") - state = 'b' - elif state == 'b': - output.append(u"<i>") - state = 'bi' - else: # '' - output.append(u"<i>") - state = 'i' - elif len(r) == 3: - if state == 'b': - output.append(u"</b>") - state = '' - elif state == 'bi': - output.append(u"</i></b><i>") - state = 'i' - elif state == 'ib': - output.append(u"</b>") - state = 'i' - elif state == 'both': - output.append(u"<i><b>") - output.append(u''.join(buffer)) - buffer = None - output.append(u"</b>") - state = 'i' - elif state == 'i': - output.append(u"<b>") - state = 'ib' - else: # '' - output.append(u"<b>") - state = 'b' - elif len(r) == 5: - if state == 'b': - output.append(u"</b><i>") - state = 'i' - elif state == 'i': - output.append(u"</i><b>") - state = 'b' - elif state == 'bi': - output.append(u"</i></b>") - state = '' - elif state == 'ib': - output.append(u"</b></i>") - state = '' - elif state == 'both': - output.append(u"<i><b>") - output.append(u''.join(buffer)) - buffer = None - output.append(u"</b></i>") - state = '' - else: # '' - buffer = [] - state = 'both' - - if state == 'both': - output.append(u"<i><b>") - output.append(u''.join(buffer)) - buffer = None - output.append(u"</b></i>") - elif state != '': - if state == 'b' or state == 'ib': - output.append(u"</b>") - if state == 'i' or state == 'bi' or state == 'ib': - output.append(u"</i>") - if state == 'bi': - output.append(u"</b>") - return u''.join(output) - - def parseAllQuotes(self, text): - sb = [] - lines = text.split(u'\n') - first = True - for line in lines: - if not first: - sb.append(u'\n') - else: - first = False - sb.append(self.parseQuotes(line)) - return u''.join(sb) - - def replaceExternalLinks(self, text): - sb = [] - bits = _bracketedLinkPat.split(text) - l = len(bits) - i = 0 - num_links = 0 - while i < l: - if i%3 == 0: - #sb.append(self.replaceFreeExternalLinks(bits[i])) - sb.append(bits[i]) - i += 1 - else: - sb.append(u'<a href="') - sb.append(bits[i]) - sb.append(u'">') - if not bits[i+1]: - num_links += 1 - sb.append(to_unicode(truncate_url(bits[i]))) - else: - sb.append(bits[i+1]) - sb.append(u'</a>') - i += 2 - return ''.join(sb) - - # TODO: fix this so it actually works - def replaceFreeExternalLinks(self, text): - bits = _protocolPat.split(text) - sb = [bits.pop(0)] - i = 0 - l = len(bits) - while i < l: - protocol = bits[i] - remainder = bits[i+1] - i += 2 - match = _specialUrlPat.match(remainder) - if match: - # Found some characters after the protocol that look promising - url = protocol + match.group(1) - trail = match.group(2) - - # special case: handle urls as url args: - # http://www.example.com/foo?=http://www.example.com/bar - if len(trail) == 0 and len(bits) > i and _protocolsPat.match(bits[i]): - match = _specialUrlPat.match(remainder) - if match: - url += bits[i] + match.group(1) - i += 2 - trail = match.group(2) - - # The characters '<' and '>' (which were escaped by - # removeHTMLtags()) should not be included in - # URLs, per RFC 2396. - pos = max(url.find('<'), url.find('>')) - if pos != -1: - trail = url[pos:] + trail - url = url[0:pos] - - sep = ',;.:!?' - if '(' not in url: - sep += ')' - - i = len(url)-1 - while i >= 0: - char = url[i] - if char not in sep: - break - i -= 1 - i += 1 - - if i != len(url): - trail = url[i:] + trail - url = url[0:i] - - url = self.cleanURL(url) - - sb.append(u'<a href="') - sb.append(url) - sb.append(u'">') - sb.append(truncate_url(url)) - sb.append(u'</a>') - #sb.append(text) - sb.append(trail) - else: - sb.append(protocol) - sb.append(remainder) - return ''.join(sb) - - def urlencode(self, char): - num = ord(char) - if num == 32: - return '+' - return "%%%02x" % num - - def cleanURL(self, url): - # Normalize any HTML entities in input. They will be - # re-escaped by makeExternalLink(). - url = self.decodeCharReferences(url) - - # Escape any control characters introduced by the above step - url = _controlCharsPat.sub(self.urlencode, url) - - # Validate hostname portion - match = _hostnamePat.match(url) - if match: - protocol, host, rest = match.groups() - - # Characters that will be ignored in IDNs. - # http://tools.ietf.org/html/3454#section-3.1 - # Strip them before further processing so blacklists and such work. - - _stripPat.sub('', host) - - # @fixme: validate hostnames here - - return protocol + host + rest - else: - return url - - def unstripForHTML(self, text): - text = self.unstrip(text) - text = self.unstripNoWiki(text) - return text - - def unstrip(self, text): - if 'general' not in self.strip_state: - return text - - general = self.strip_state['general'] - for k in general: - v = general[k] - text = text.replace(k, v) - return text - - def unstripNoWiki(self, text): - if 'nowiki' not in self.strip_state: - return text - nowiki = self.strip_state['nowiki'] - for k in nowiki: - v = nowiki[k] - text = text.replace(k, v) - return text - - def extractTagsAndParams(self, elements, text, matches): - """ - Replaces all occurrences of HTML-style comments and the given tags - in the text with a random marker and returns teh next text. The output - parameter $matches will be an associative array filled with data in - the form: - 'UNIQ-xxxxx' => array( - 'element', - 'tag content', - array( 'param' => 'x' ), - '<element param="x">tag content</element>' ) ) - """ - stripped = u'' - - taglist = u'|'.join(elements) - if taglist not in _startRegexHash: - _startRegexHash[taglist] = re.compile(ur"<(" + taglist + ur")(\s+[^>]*?|\s*?)(/?>)|<(!--)", re.UNICODE | re.IGNORECASE) - start = _startRegexHash[taglist] - - while text != u'': - p = start.split(text, 1) - stripped += p[0] - if len(p) == 1: - break - elif p[4]: - # comment - element = p[4] - attributes = u'' - close = u'' - else: - element = p[1] - attributes = p[2] - close = p[3] - inside = p[5] - - global _extractTagsAndParams_n - marker = self.uniq_prefix + u'-' + element + u'-' + (u"%08X" % _extractTagsAndParams_n) + u'-QINU' - _extractTagsAndParams_n += 1 - stripped += marker - - if close == u'/>': - # empty element tag, <tag /> - content = None - text = inside - tail = None - else: - if element == u'!--': - end = _endCommentPat - else: - if element not in _endRegexHash: - _endRegexHash[element] = re.compile(ur'(</' + element + ur'\s*>)', re.UNICODE | re.IGNORECASE) - end = _endRegexHash[element] - q = end.split(inside, 1) - content = q[0] - if len(q) < 3: - # no end tag - tail = '' - text = '' - else: - tail = q[1] - text = q[2] - - matches[marker] = ( - element, - content, - self.decodeTagAttributes(attributes), - u"<" + element + attributes + close + content + tail - ) - return stripped - - def fixtags(self, text): - """Clean up special characters, only run once, next-to-last before doBlockLevels""" - # french spaces, last one Guillemet-left - # only if there is something before the space - text = _guillemetLeftPat.sub(ur'\1 \2', text) - # french spaces, Guillemet-right - text = _guillemetRightPat.sub(ur'\1 ', text) - return text - - def closeParagraph(self, mLastSection): - """Used by doBlockLevels()""" - result = u'' - if mLastSection != u'': - result = u'</' + mLastSection + u'>\n' - - return result - - def getCommon(self, st1, st2): - """ - getCommon() returns the length of the longest common substring - of both arguments, starting at the beginning of both. - """ - fl = len(st1) - shorter = len(st2) - if fl < shorter: - shorter = fl - - i = 0 - while i < shorter: - if st1[i] != st2[i]: - break - i += 1 - return i - - def openList(self, char, mLastSection): - """ - These next three functions open, continue, and close the list - element appropriate to the prefix character passed into them. - """ - result = self.closeParagraph(mLastSection) - - mDTopen = False - if char == u'*': - result += u'<ul><li>' - elif char == u'#': - result += u'<ol><li>' - elif char == u':': - result += u'<dl><dd>' - elif char == u';': - result += u'<dl><dt>' - mDTopen = True - else: - result += u'<!-- ERR 1 -->' - - return result, mDTopen - - def nextItem(self, char, mDTopen): - if char == u'*' or char == '#': - return u'</li><li>', None - elif char == u':' or char == u';': - close = u'</dd>' - if mDTopen: - close = '</dt>' - if char == u';': - return close + u'<dt>', True - else: - return close + u'<dd>', False - return u'<!-- ERR 2 -->' - - def closeList(self, char, mDTopen): - if char == u'*': - return u'</li></ul>\n' - elif char == u'#': - return u'</li></ol>\n' - elif char == u':': - if mDTopen: - return u'</dt></dl>\n' - else: - return u'</dd></dl>\n' - else: - return u'<!-- ERR 3 -->' - - def findColonNoLinks(self, text, before, after): - try: - pos = text.search(':') - except: - return False - - lt = text.find('<') - if lt == -1 or lt > pos: - # Easy; no tag nesting to worry about - before = text[0:pos] - after = text[0:pos+1] - return before, after, pos - - # Ugly state machine to walk through avoiding tags. - state = MW_COLON_STATE_TEXT; - stack = 0; - i = 0 - while i < len(text): - c = text[i]; - - if state == 0: # MW_COLON_STATE_TEXT: - if text[i] == '<': - # Could be either a <start> tag or an </end> tag - state = MW_COLON_STATE_TAGSTART - elif text[i] == ':': - if stack == 0: - # we found it - return text[0:i], text[i+1], i - else: - # Skip ahead looking for something interesting - try: - colon = text.search(':', i) - except: - return False - lt = text.find('<', i) - if stack == 0: - if lt == -1 or colon < lt: - # we found it - return text[0:colon], text[colon+1], i - if lt == -1: - break - # Skip ahead to next tag start - i = lt - state = MW_COLON_STATE_TAGSTART - elif state == 1: # MW_COLON_STATE_TAG: - # In a <tag> - if text[i] == '>': - stack += 1 - state = MW_COLON_STATE_TEXT - elif text[i] == '/': - state = MW_COLON_STATE_TAGSLASH - elif state == 2: # MW_COLON_STATE_TAGSTART: - if text[i] == '/': - state = MW_COLON_STATE_CLOSETAG - elif text[i] == '!': - state = MW_COLON_STATE_COMMENT - elif text[i] == '>': - # Illegal early close? This shouldn't happen D: - state = MW_COLON_STATE_TEXT - else: - state = MW_COLON_STATE_TAG - elif state == 3: # MW_COLON_STATE_CLOSETAG: - # In a </tag> - if text[i] == '>': - stack -= 1 - if stack < 0: - return False - state = MW_COLON_STATE_TEXT - elif state == MW_COLON_STATE_TAGSLASH: - if text[i] == '>': - # Yes, a self-closed tag <blah/> - state = MW_COLON_STATE_TEXT - else: - # Probably we're jumping the gun, and this is an attribute - state = MW_COLON_STATE_TAG - elif state == 5: # MW_COLON_STATE_COMMENT: - if text[i] == '-': - state = MW_COLON_STATE_COMMENTDASH - elif state == MW_COLON_STATE_COMMENTDASH: - if text[i] == '-': - state = MW_COLON_STATE_COMMENTDASHDASH - else: - state = MW_COLON_STATE_COMMENT - elif state == MW_COLON_STATE_COMMENTDASHDASH: - if text[i] == '>': - state = MW_COLON_STATE_TEXT - else: - state = MW_COLON_STATE_COMMENT - else: - raise - if stack > 0: - return False - return False - - def doBlockLevels(self, text, linestart): - # Parsing through the text line by line. The main thing - # happening here is handling of block-level elements p, pre, - # and making lists from lines starting with * # : etc. - lastPrefix = u'' - mDTopen = inBlockElem = False - prefixLength = 0 - paragraphStack = False - _closeMatchPat = re.compile(ur"(</table|</blockquote|</h1|</h2|</h3|</h4|</h5|</h6|<td|<th|<div|</div|<hr|</pre|</p|" + self.uniq_prefix + ur"-pre|</li|</ul|</ol|<center)", re.UNICODE | re.IGNORECASE) - mInPre = False - mLastSection = u'' - mDTopen = False - output = [] - for oLine in text.split('\n')[not linestart and 1 or 0:]: - lastPrefixLength = len(lastPrefix) - preCloseMatch = _closePrePat.search(oLine) - preOpenMatch = _openPrePat.search(oLine) - if not mInPre: - chars = u'*#:;' - prefixLength = 0 - for c in oLine: - if c in chars: - prefixLength += 1 - else: - break - pref = oLine[0:prefixLength] - - # eh? - pref2 = pref.replace(u';', u':') - t = oLine[prefixLength:] - mInPre = bool(preOpenMatch) - else: - # Don't interpret any other prefixes in preformatted text - prefixLength = 0 - pref = pref2 = u'' - t = oLine - - # List generation - if prefixLength and lastPrefix == pref2: - # Same as the last item, so no need to deal with nesting or opening stuff - tmpOutput, tmpMDTopen = self.nextItem(pref[-1:], mDTopen) - output.append(tmpOutput) - if tmpMDTopen is not None: - mDTopen = tmpMDTopen - paragraphStack = False - - if pref[-1:] == u';': - # The one nasty exception: definition lists work like this: - # ; title : definition text - # So we check for : in the remainder text to split up the - # title and definition, without b0rking links. - term = t2 = u'' - z = self.findColonNoLinks(t, term, t2) - if z != False: - term, t2 = z[1:2] - t = t2 - output.append(term) - tmpOutput, tmpMDTopen = self.nextItem(u':', mDTopen) - output.append(tmpOutput) - if tmpMDTopen is not None: - mDTopen = tmpMDTopen - - elif prefixLength or lastPrefixLength: - # Either open or close a level... - commonPrefixLength = self.getCommon(pref, lastPrefix) - paragraphStack = False - while commonPrefixLength < lastPrefixLength: - tmp = self.closeList(lastPrefix[lastPrefixLength-1], mDTopen) - output.append(tmp) - mDTopen = False - lastPrefixLength -= 1 - if prefixLength <= commonPrefixLength and commonPrefixLength > 0: - tmpOutput, tmpMDTopen = self.nextItem(pref[commonPrefixLength-1], mDTopen) - output.append(tmpOutput) - if tmpMDTopen is not None: - mDTopen = tmpMDTopen - - while prefixLength > commonPrefixLength: - char = pref[commonPrefixLength:commonPrefixLength+1] - tmpOutput, tmpMDTOpen = self.openList(char, mLastSection) - if tmpMDTOpen: - mDTopen = True - output.append(tmpOutput) - mLastSection = u'' - mInPre = False - - if char == u';': - # FIXME: This is dupe of code above - term = t2 = u'' - z = self.findColonNoLinks(t, term, t2) - if z != False: - term, t2 = z[1:2] - t = t2 - output.append(term) - tmpOutput, tmpMDTopen = self.nextItem(u':', mDTopen) - output.append(tmpOutput) - if tmpMDTopen is not None: - mDTopen = tmpMDTopen - - commonPrefixLength += 1 - - lastPrefix = pref2 - - if prefixLength == 0: - # No prefix (not in list)--go to paragraph mode - # XXX: use a stack for nestable elements like span, table and div - openmatch = _openMatchPat.search(t) - closematch = _closeMatchPat.search(t) - if openmatch or closematch: - paragraphStack = False - output.append(self.closeParagraph(mLastSection)) - mLastSection = u'' - if preCloseMatch: - mInPre = False - if preOpenMatch: - mInPre = True - inBlockElem = bool(not closematch) - elif not inBlockElem and not mInPre: - if t[0:1] == u' ' and (mLastSection == u'pre' or t.strip() != u''): - # pre - if mLastSection != u'pre': - paragraphStack = False - output.append(self.closeParagraph(u'') + u'<pre>') - mInPre = False - mLastSection = u'pre' - t = t[1:] - else: - # paragraph - if t.strip() == u'': - if paragraphStack: - output.append(paragraphStack + u'<br />') - paragraphStack = False - mLastSection = u'p' - else: - if mLastSection != u'p': - output.append(self.closeParagraph(mLastSection)) - mLastSection = u'' - mInPre = False - paragraphStack = u'<p>' - else: - paragraphStack = u'</p><p>' - else: - if paragraphStack: - output.append(paragraphStack) - paragraphStack = False - mLastSection = u'p' - elif mLastSection != u'p': - output.append(self.closeParagraph(mLastSection) + u'<p>') - mLastSection = u'p' - mInPre = False - - # somewhere above we forget to get out of pre block (bug 785) - if preCloseMatch and mInPre: - mInPre = False - - if paragraphStack == False: - output.append(t + u"\n") - - while prefixLength: - output.append(self.closeList(pref2[prefixLength-1], mDTopen)) - mDTopen = False - prefixLength -= 1 - - if mLastSection != u'': - output.append(u'</' + mLastSection + u'>') - mLastSection = u'' - - return ''.join(output) - -class Parser(BaseParser): - def __init__(self, show_toc=True): - super(Parser, self).__init__() - self.show_toc = show_toc - - def parse(self, text): - utf8 = isinstance(text, str) - text = to_unicode(text) - if text[-1:] != u'\n': - text = text + u'\n' - taggedNewline = True - else: - taggedNewline = False - - text = self.strip(text) - text = self.removeHtmlTags(text) - text = self.doTableStuff(text) - text = self.parseHorizontalRule(text) - text = self.checkTOC(text) - text = self.parseHeaders(text) - text = self.parseAllQuotes(text) - text = self.replaceExternalLinks(text) - if not self.show_toc and text.find(u"<!--MWTOC-->") == -1: - self.show_toc = False - text = self.formatHeadings(text, True) - text = self.unstrip(text) - text = self.fixtags(text) - text = self.doBlockLevels(text, True) - text = self.unstripNoWiki(text) - text = text.split(u'\n') - text = u'\n'.join(text) - if taggedNewline and text[-1:] == u'\n': - text = text[:-1] - if utf8: - return text.encode("utf-8") - return text - - def checkTOC(self, text): - if text.find(u"__NOTOC__") != -1: - text = text.replace(u"__NOTOC__", u"") - self.show_toc = False - if text.find(u"__TOC__") != -1: - text = text.replace(u"__TOC__", u"<!--MWTOC-->") - self.show_toc = True - return text - - def doTableStuff(self, text): - t = text.split(u"\n") - td = [] # Is currently a td tag open? - ltd = [] # Was it TD or TH? - tr = [] # Is currently a tr tag open? - ltr = [] # tr attributes - has_opened_tr = [] # Did this table open a <tr> element? - indent_level = 0 # indent level of the table - - for k, x in zip(range(len(t)), t): - x = x.strip() - fc = x[0:1] - matches = _zomgPat.match(x) - if matches: - indent_level = len(matches.group(1)) - - attributes = self.unstripForHTML(matches.group(2)) - - t[k] = u'<dl><dd>'*indent_level + u'<table' + self.fixTagAttributes(attributes, u'table') + u'>' - td.append(False) - ltd.append(u'') - tr.append(False) - ltr.append(u'') - has_opened_tr.append(False) - elif len(td) == 0: - pass - elif u'|}' == x[0:2]: - z = u"</table>" + x[2:] - l = ltd.pop() - if not has_opened_tr.pop(): - z = u"<tr><td></td><tr>" + z - if tr.pop(): - z = u"</tr>" + z - if td.pop(): - z = u'</' + l + u'>' + z - ltr.pop() - t[k] = z + u'</dd></dl>'*indent_level - elif u'|-' == x[0:2]: # Allows for |------------- - x = x[1:] - while x != u'' and x[0:1] == '-': - x = x[1:] - z = '' - l = ltd.pop() - has_opened_tr.pop() - has_opened_tr.append(True) - if tr.pop(): - z = u'</tr>' + z - if td.pop(): - z = u'</' + l + u'>' + z - ltr.pop() - t[k] = z - tr.append(False) - td.append(False) - ltd.append(u'') - attributes = self.unstripForHTML(x) - ltr.append(self.fixTagAttributes(attributes, u'tr')) - elif u'|' == fc or u'!' == fc or u'|+' == x[0:2]: # Caption - # x is a table row - if u'|+' == x[0:2]: - fc = u'+' - x = x[1:] - x = x[1:] - if fc == u'!': - x = x.replace(u'!!', u'||') - # Split up multiple cells on the same line. - # FIXME: This can result in improper nesting of tags processed - # by earlier parser steps, but should avoid splitting up eg - # attribute values containing literal "||". - x = x.split(u'||') - - t[k] = u'' - - # Loop through each table cell - for theline in x: - z = '' - if fc != u'+': - tra = ltr.pop() - if not tr.pop(): - z = u'<tr' + tra + u'>\n' - tr.append(True) - ltr.append(u'') - has_opened_tr.pop() - has_opened_tr.append(True) - l = ltd.pop() - if td.pop(): - z = u'</' + l + u'>' + z - if fc == u'|': - l = u'td' - elif fc == u'!': - l = u'th' - elif fc == u'+': - l = u'caption' - else: - l = u'' - ltd.append(l) - - #Cell parameters - y = theline.split(u'|', 1) - # Note that a '|' inside an invalid link should not - # be mistaken as delimiting cell parameters - if y[0].find(u'[[') != -1: - y = [theline] - - if len(y) == 1: - y = z + u"<" + l + u">" + y[0] - else: - attributes = self.unstripForHTML(y[0]) - y = z + u"<" + l + self.fixTagAttributes(attributes, l) + u">" + y[1] - - t[k] += y - td.append(True) - - while len(td) > 0: - l = ltd.pop() - if td.pop(): - t.append(u'</td>') - if tr.pop(): - t.append(u'</tr>') - if not has_opened_tr.pop(): - t.append(u'<tr><td></td></tr>') - t.append(u'</table>') - - text = u'\n'.join(t) - # special case: don't return empty table - if text == u"<table>\n<tr><td></td></tr>\n</table>": - text = u'' - - return text - - def formatHeadings(self, text, isMain): - """ - This function accomplishes several tasks: - 1) Auto-number headings if that option is enabled - 2) Add an [edit] link to sections for logged in users who have enabled the option - 3) Add a Table of contents on the top for users who have enabled the option - 4) Auto-anchor headings - - It loops through all headlines, collects the necessary data, then splits up the - string and re-inserts the newly formatted headlines. - """ - doNumberHeadings = False - showEditLink = True # Can User Edit - - if text.find(u"__NOEDITSECTION__") != -1: - showEditLink = False - text = text.replace(u"__NOEDITSECTION__", u"") - - # Get all headlines for numbering them and adding funky stuff like [edit] - # links - this is for later, but we need the number of headlines right now - matches = _headerPat.findall(text) - numMatches = len(matches) - - # if there are fewer than 4 headlines in the article, do not show TOC - # unless it's been explicitly enabled. - enoughToc = self.show_toc and (numMatches >= 4 or text.find(u"<!--MWTOC-->") != -1) - - # Allow user to stipulate that a page should have a "new section" - # link added via __NEWSECTIONLINK__ - showNewSection = False - if text.find(u"__NEWSECTIONLINK__") != -1: - showNewSection = True - text = text.replace(u"__NEWSECTIONLINK__", u"") - # if the string __FORCETOC__ (not case-sensitive) occurs in the HTML, - # override above conditions and always show TOC above first header - if text.find(u"__FORCETOC__") != -1: - self.show_toc = True - enoughToc = True - text = text.replace(u"__FORCETOC__", u"") - # Never ever show TOC if no headers - if numMatches < 1: - enoughToc = False - - # headline counter - headlineCount = 0 - sectionCount = 0 # headlineCount excluding template sections - - # Ugh .. the TOC should have neat indentation levels which can be - # passed to the skin functions. These are determined here - toc = [] - head = {} - sublevelCount = {} - levelCount = {} - toclevel = 0 - level = 0 - prevlevel = 0 - toclevel = 0 - prevtoclevel = 0 - refers = {} - refcount = {} - wgMaxTocLevel = 5 - - for match in matches: - headline = match[2] - istemplate = False - templatetitle = u'' - templatesection = 0 - numbering = [] - - m = _templateSectionPat.search(headline) - if m: - istemplate = True - templatetitle = b64decode(m[0]) - templatesection = 1 + int(b64decode(m[1])) - headline = _templateSectionPat.sub(u'', headline) - - if toclevel: - prevlevel = level - prevtoclevel = toclevel - - level = matches[headlineCount][0] - - if doNumberHeadings or enoughToc: - if level > prevlevel: - toclevel += 1 - sublevelCount[toclevel] = 0 - if toclevel < wgMaxTocLevel: - toc.append(u'\n<ul>') - elif level < prevlevel and toclevel > 1: - # Decrease TOC level, find level to jump to - - if toclevel == 2 and level < levelCount[1]: - toclevel = 1 - else: - for i in range(toclevel, 0, -1): - if levelCount[i] == level: - # Found last matching level - toclevel = i - break - elif levelCount[i] < level: - toclevel = i + 1 - break - if toclevel < wgMaxTocLevel: - toc.append(u"</li>\n") - toc.append(u"</ul>\n</li>\n" * max(prevtoclevel - toclevel, 0)) - else: - if toclevel < wgMaxTocLevel: - toc.append(u"</li>\n") - - levelCount[toclevel] = level - - # count number of headlines for each level - sublevelCount[toclevel] += 1 - for i in range(1, toclevel+1): - if sublevelCount[i]: - numbering.append(to_unicode(sublevelCount[i])) - - # The canonized header is a version of the header text safe to use for links - # Avoid insertion of weird stuff like <math> by expanding the relevant sections - canonized_headline = self.unstrip(headline) - canonized_headline = self.unstripNoWiki(canonized_headline) - - # -- don't know what to do with this yet. - # Remove link placeholders by the link text. - # <!--LINK number--> - # turns into - # link text with suffix - # $canonized_headline = preg_replace( '/<!--LINK ([0-9]*)-->/e', - # "\$this->mLinkHolders['texts'][\$1]", - # $canonized_headline ); - # $canonized_headline = preg_replace( '/<!--IWLINK ([0-9]*)-->/e', - # "\$this->mInterwikiLinkHolders['texts'][\$1]", - # $canonized_headline ); - - # strip out HTML - canonized_headline = _tagPat.sub(u'', canonized_headline) - tocline = canonized_headline.strip() - # Save headline for section edit hint before it's escaped - headline_hint = tocline - canonized_headline = self.escapeId(tocline) - refers[headlineCount] = canonized_headline - - # count how many in assoc. array so we can track dupes in anchors - if canonized_headline not in refers: - refers[canonized_headline] = 1 - else: - refers[canonized_headline] += 1 - refcount[headlineCount] = refers[canonized_headline] - - numbering = '.'.join(numbering) - - # Don't number the heading if it is the only one (looks silly) - if doNumberHeadings and numMatches > 1: - # the two are different if the line contains a link - headline = numbering + u' ' + headline - - # Create the anchor for linking from the TOC to the section - anchor = canonized_headline; - if refcount[headlineCount] > 1: - anchor += u'_' + unicode(refcount[headlineCount]) - - if enoughToc: - toc.append(u'\n<li class="toclevel-') - toc.append(to_unicode(toclevel)) - toc.append(u'"><a href="#w_') - toc.append(anchor) - toc.append(u'"><span class="tocnumber">') - toc.append(numbering) - toc.append(u'</span> <span class="toctext">') - toc.append(tocline) - toc.append(u'</span></a>') - - # if showEditLink and (not istemplate or templatetitle != u""): - # if not head[headlineCount]: - # head[headlineCount] = u'' - # - # if istemplate: - # head[headlineCount] += sk.editSectionLinkForOther(templatetile, templatesection) - # else: - # head[headlineCount] += sk.editSectionLink(mTitle, sectionCount+1, headline_hint) - - # give headline the correct <h#> tag - if headlineCount not in head: - head[headlineCount] = [] - h = head[headlineCount] - h.append(u'<h') - h.append(to_unicode(level)) - h.append(u' id="w_') - h.append(anchor) - h.append('">') - h.append(matches[headlineCount][1].strip()) - h.append(headline.strip()) - h.append(u'</h') - h.append(to_unicode(level)) - h.append(u'>') - - headlineCount += 1 - - if not istemplate: - sectionCount += 1 - - if enoughToc: - if toclevel < wgMaxTocLevel: - toc.append(u"</li>\n") - toc.append(u"</ul>\n</li>\n" * max(0, toclevel - 1)) - #TODO: use gettext - #toc.insert(0, u'<div id="toc"><h2>' + _('Table of Contents') + '</h2>') - toc.insert(0, u'<div id="toc"><h2>Table of Contents</h2>') - toc.append(u'</ul>\n</div>') - - # split up and insert constructed headlines - - blocks = _headerPat.split(text) - - i = 0 - len_blocks = len(blocks) - forceTocPosition = text.find(u"<!--MWTOC-->") - full = [] - while i < len_blocks: - j = i/4 - full.append(blocks[i]) - if enoughToc and not i and isMain and forceTocPosition == -1: - full += toc - toc = None - if j in head and head[j]: - full += head[j] - head[j] = None - i += 4 - full = u''.join(full) - if forceTocPosition != -1: - return full.replace(u"<!--MWTOC-->", u''.join(toc), 1) - else: - return full - -def parse(text, showToc=True): - """Returns HTML from MediaWiki markup""" - p = Parser(show_toc=showToc) - return p.parse(text) - -def parselite(text): - """Returns HTML from MediaWiki markup ignoring - without headings""" - p = BaseParser() - return p.parse(text) - -def truncate_url(url, length=40): - if len(url) <= length: - return url - import re - pattern = r'(/[^/]+/?)$' - match = re.search(pattern, url) - if not match: - return url - l = len(match.group(1)) - domain = url.replace(match.group(1), '') - firstpart = url[0:len(url)-l] - secondpart = match.group(1) - if firstpart == firstpart[0:length-3]: - secondpart = secondpart[0:length-3] + '...' - else: - firstpart = firstpart[0:length-3] - secondpart = '...' + secondpart - t_url = firstpart+secondpart - return t_url - -def to_unicode(text, charset=None): - """Convert a `str` object to an `unicode` object. - - If `charset` is given, we simply assume that encoding for the text, - but we'll use the "replace" mode so that the decoding will always - succeed. - If `charset` is ''not'' specified, we'll make some guesses, first - trying the UTF-8 encoding, then trying the locale preferred encoding, - in "replace" mode. This differs from the `unicode` builtin, which - by default uses the locale preferred encoding, in 'strict' mode, - and is therefore prompt to raise `UnicodeDecodeError`s. - - Because of the "replace" mode, the original content might be altered. - If this is not what is wanted, one could map the original byte content - by using an encoding which maps each byte of the input to an unicode - character, e.g. by doing `unicode(text, 'iso-8859-1')`. - """ - if not isinstance(text, str): - if isinstance(text, Exception): - # two possibilities for storing unicode strings in exception data: - try: - # custom __str__ method on the exception (e.g. PermissionError) - return unicode(text) - except UnicodeError: - # unicode arguments given to the exception (e.g. parse_date) - return ' '.join([to_unicode(arg) for arg in text.args]) - return unicode(text) - if charset: - return unicode(text, charset, 'replace') - else: - try: - return unicode(text, 'utf-8') - except UnicodeError: - return unicode(text, locale.getpreferredencoding(), 'replace') - -# tag hooks -mTagHooks = {} - -## IMPORTANT -## Make sure all hooks output CLEAN html. Escape any user input BEFORE it's returned - -# Arguments passed: -# - wiki environment instance -# - tag content -# - dictionary of attributes - -# quote example: -# <quote cite="person">quote</quote> -from cgi import escape - -def hook_quote(env, body, attributes={}): - text = [u'<div class="blockquote">'] - if 'cite' in attributes: - text.append(u"<strong class=\"cite\">%s wrote:</strong>\n" % escape(attributes['cite'])) - text.append(body.strip()) - text.append(u'</div>') - return u'\n'.join(text) -registerTagHook('quote', hook_quote) - -def safe_name(name=None, remove_slashes=True): - if name is None: - return None - name = str2url(name) - if remove_slashes: - name = re.sub(r"[^a-zA-Z0-9\-_\s\.]", "", name) - else: - name = re.sub(r"[^a-zA-Z0-9\-_\s\.\/]", "", name) - name = re.sub(r"[\s\._]", "-", name) - name = re.sub(r"[-]+", "-", name) - return name.strip("-").lower() - -def str2url(str): - """ - Takes a UTF-8 string and replaces all characters with the equivalent in 7-bit - ASCII. It returns a plain ASCII string usable in URLs. - """ - try: - str = str.encode('utf-8') - except: - pass - mfrom = "ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝßàáâãäåæçèéêëìíîï" - to = "AAAAAAECEEEEIIIIDNOOOOOOUUUUYSaaaaaaaceeeeiiii" - mfrom += "ñòóôõöøùúûüýÿĀāĂ㥹ĆćĈĉĊċČčĎďĐđĒēĔĕĖėĘęĚěĜĝĞğĠġĢģ" - to += "noooooouuuuyyaaaaaaccccccccddddeeeeeeeeeegggggggg" - mfrom += "ĤĥĦħĨĩĪīĬĭĮįİıĴĵĶķĸĹĺĻļĽľĿŀŁłŃńŅņŇňʼnŊŋŌōŎŏŐőŒœŔŕŖŗŘř" - to += "hhhhiiiiiiiiiijjkkkllllllllllnnnnnnnnnoooooooorrrrrr" - mfrom += "ŚśŜŝŞşŠšŢţŤťŦŧŨũŪūŬŭŮůŰűŲųŴŵŶŷŸŹźŻżŽžſƀƂƃƄƅƇƈƉƊƐƑƒƓƔ" - to += "ssssssssttttttuuuuuuuuuuuuwwyyyzzzzzzfbbbbbccddeffgv" - mfrom += "ƖƗƘƙƚƝƞƟƠƤƦƫƬƭƮƯưƱƲƳƴƵƶǍǎǏǐǑǒǓǔǕǖǗǘǙǚǛǜǝǞǟǠǡǢǣǤǥǦǧǨǩ" - to += "likklnnoopettttuuuuyyzzaaiioouuuuuuuuuueaaaaeeggggkk" - mfrom += "ǪǫǬǭǰǴǵǷǸǹǺǻǼǽǾǿȀȁȂȃȄȅȆȇȈȉȊȋȌȍȎȏȐȑȒȓȔȕȖȗȘșȚțȞȟȤȥȦȧȨȩ" - to += "oooojggpnnaaeeooaaaaeeeeiiiioooorrrruuuusstthhzzaaee" - mfrom += "ȪȫȬȭȮȯȰȱȲȳḀḁḂḃḄḅḆḇḈḉḊḋḌḍḎḏḐḑḒḓḔḕḖḗḘḙḚḛḜḝḞḟḠḡḢḣḤḥḦḧḨḩḪḫ" - to += "ooooooooyyaabbbbbbccddddddddddeeeeeeeeeeffgghhhhhhhhhh" - mfrom += "ḬḭḮḯḰḱḲḳḴḵḶḷḸḹḺḻḼḽḾḿṀṁṂṃṄṅṆṇṈṉṊṋṌṍṎṏṐṑṒṓṔṕṖṗṘṙṚṛṜṝṞṟ" - to += "iiiikkkkkkllllllllmmmmmmnnnnnnnnoooooooopppprrrrrrrr" - mfrom += "ṠṡṢṣṤṥṦṧṨṩṪṫṬṭṮṯṰṱṲṳṴṵṶṷṸṹṺṻṼṽṾṿẀẁẂẃẄẅẆẇẈẉẊẋẌẍẎẏẐẑẒẓẔẕ" - to += "ssssssssssttttttttuuuuuuuuuuvvvvwwwwwwwwwwxxxxxyzzzzzz" - mfrom += "ẖẗẘẙẚẛẠạẢảẤấẦầẨẩẪẫẬậẮắẰằẲẳẴẵẶặẸẹẺẻẼẽẾếỀềỂểỄễỆệỈỉỊị" - to += "htwyafaaaaaaaaaaaaaaaaaaaaaaaaeeeeeeeeeeeeeeeeiiii" - mfrom += "ỌọỎỏỐốỒồỔổỖỗỘộỚớỜờỞởỠỡỢợỤụỦủỨứỪừỬửỮữỰựỲỳỴỵỶỷỸỹ" - to += "oooooooooooooooooooooooouuuuuuuuuuuuuuyyyyyyyy" - for i in zip(mfrom, to): - str = str.replace(*i) - return str - -# vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: |