TextDocument.py 16.1 KB
Newer Older
Nicolas Delaby's avatar
Nicolas Delaby committed
1
# -*- coding: utf-8 -*-
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
##############################################################################
#
# Copyright (c) 2002 Nexedi SARL and Contributors. All Rights Reserved.
#                    Jean-Paul Smets-Solanes <jp@nexedi.com>
#
# WARNING: This program as such is intended to be used by professional
# programmers who take the whole responsability of assessing all potential
# consequences resulting from its eventual inadequacies and bugs
# End users who are looking for a ready-to-use solution with commercial
# garantees and support are strongly adviced to contract a Free Software
# Service Company
#
# 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 2
# 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, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
#
##############################################################################

30
from AccessControl.ZopeGuards import guarded_getattr
31
from AccessControl import ClassSecurityInfo
32
from zLOG import LOG, WARNING
33
from Products.ERP5Type.Base import WorkflowMethod
34
from Products.CMFCore.utils import getToolByName
35
from Products.CMFCore.utils import _setCacheHeaders, _ViewEmulator
36
from OFS.Image import Pdata
37
from Products.ERP5Type import Permissions, PropertySheet
38 39 40
from Products.ERP5.Document.Document import Document, ConversionError,\
                                            NotConvertedError
from Products.ERP5.Document.File import File
41
from Products.ERP5Type.WebDAVSupport import TextContent
Jean-Paul Smets's avatar
Jean-Paul Smets committed
42
import re
43
import md5
44
import cStringIO
Jean-Paul Smets's avatar
Jean-Paul Smets committed
45

46 47
# Mixin Import
from Products.ERP5.mixin.cached_convertable import CachedConvertableMixin
48
from Products.ERP5.mixin.base_convertable import BaseConvertableFileMixin
49 50 51 52 53
try:
  from string import Template
except ImportError:
  from Products.ERP5Type.patches.string import Template

54 55
DEFAULT_CONTENT_TYPE = 'text/html'
_MARKER = []
56

57 58
class TextDocument(CachedConvertableMixin, BaseConvertableFileMixin,
                                                            TextContent, File):
59 60
    """A TextDocument impletents IDocument, IFile, IBaseConvertable, ICachedconvertable
    and ITextConvertable
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
    """

    meta_type = 'ERP5 Text Document'
    portal_type = 'Text Document'
    add_permission = Permissions.AddPortalContent

    # Declarative security
    security = ClassSecurityInfo()
    security.declareObjectProtected(Permissions.AccessContentsInformation)

    # Declarative properties
    property_sheets = ( PropertySheet.Base
                      , PropertySheet.XMLObject
                      , PropertySheet.CategoryCore
                      , PropertySheet.DublinCore
                      , PropertySheet.Version
                      , PropertySheet.Document
Jean-Paul Smets's avatar
Jean-Paul Smets committed
78 79 80
                      , PropertySheet.Snapshot
                      , PropertySheet.ExternalDocument
                      , PropertySheet.Url
81
                      , PropertySheet.TextDocument
82
                      , PropertySheet.Data
83
                      , PropertySheet.Reference
84 85
                      )

86
    def _substituteTextContent(self, text, safe_substitute=True, **kw):
87 88 89 90 91
      # If a method for string substitutions of the text content, perform it.
      # Decode everything into unicode before the substitutions, in order to
      # avoid encoding errors.
      method_id = self.getTextContentSubstitutionMappingMethodId()
      if method_id:
92 93 94
        try:
          mapping = guarded_getattr(self, method_id)(**kw)
        except AttributeError:
95 96
          LOG('TextDocument', WARNING, 'could not get the substitution'
              ' mapping method %s from %r, so the content will not be'
97
              ' substituted.' % (method_id, self.getRelativeUrl()))
Yoshinori Okuji's avatar
Yoshinori Okuji committed
98
          return text
99 100 101 102 103 104 105 106 107 108 109 110 111

        is_str = isinstance(text, str)
        if is_str:
          text = text.decode('utf-8')

        unicode_mapping = {}
        for k, v in mapping.iteritems():
          if isinstance(v, str):
            v = v.decode('utf-8')
          elif not isinstance(v, unicode):
            v = str(v).decode('utf-8')
          unicode_mapping[k] = v

112 113 114 115
        if safe_substitute:
          text = Template(text).safe_substitute(unicode_mapping)
        else:
          text = Template(text).substitute(unicode_mapping)
116 117 118 119 120 121 122 123

        # If the original was a str, convert it back to str.
        if is_str:
          text = text.encode('utf-8')

      return text

    security.declareProtected(Permissions.View, 'asSubjectText')
124
    def asSubjectText(self, substitution_method_parameter_dict=None, safe_substitute=True, **kw):
125 126 127 128 129 130
      """
        Converts the subject of the document to a textual representation.
      """
      subject = TextDocument.inheritedAttribute('asSubjectText')(self, **kw)
      if substitution_method_parameter_dict is None:
        substitution_method_parameter_dict = {}
131 132
      return self._substituteTextContent(subject, safe_substitute=safe_substitute,
                                         **substitution_method_parameter_dict)
133

134
    def _convert(self, format, substitution_method_parameter_dict=None,
135
                safe_substitute=True, charset=None, text_content=None, **kw):
Jean-Paul Smets's avatar
Jean-Paul Smets committed
136
      """
137
        Convert text using portal_transforms or oood
Jean-Paul Smets's avatar
Jean-Paul Smets committed
138
      """
139 140 141 142 143 144
      src_mimetype = self.getContentType()
      if not format and src_mimetype == 'text/html':
        format = 'html' # Force safe_html
      if not format:
        # can return document without conversion
        return src_mimetype, self.getTextContent()
145
      portal = self.getPortalObject()
146 147 148 149 150 151
      mime_type = getToolByName(portal, 'mimetypes_registry').\
                                            lookupExtension('name.%s' % format)
      original_mime_type = mime_type = str(mime_type)
      if text_content is None:
        # check if document has set text_content and convert if necessary
        text_content = self.getTextContent()
152
      if text_content:
153 154
        kw['format'] = format
        if not self.hasConversion(**kw):
155
          portal_transforms = getToolByName(portal, 'portal_transforms')
156
          filename = self.getSourceReference(self.getTitleOrId())
157 158
          if mime_type == 'text/html':
            mime_type = 'text/x-html-safe'
Nicolas Delaby's avatar
Nicolas Delaby committed
159 160
          result = portal_transforms.convertToData(mime_type, text_content,
                                                   object=self, context=self,
161
                                                   filename=filename,
162 163
                                                   mimetype=src_mimetype,
                                                   encoding=charset)
Nicolas Delaby's avatar
Nicolas Delaby committed
164 165
          if result is None:
            raise ConversionError('TextDocument conversion error. '
166
                                  'portal_transforms failed to convert '\
167
                                  'to %s: %r' % (mime_type, self))
168
          self.setConversion(result, original_mime_type, **kw)
Nicolas Delaby's avatar
Nicolas Delaby committed
169
        else:
170
          mime_type, result = self.getConversion(**kw)
171 172
        if substitution_method_parameter_dict is None:
          substitution_method_parameter_dict = {}
173 174
        result = self._substituteTextContent(result, safe_substitute=safe_substitute,
                                             **substitution_method_parameter_dict)
175
        return original_mime_type, result
176 177
      else:
        # text_content is not set, return empty string instead of None
178
        return original_mime_type, ''
179

Jean-Paul Smets's avatar
Jean-Paul Smets committed
180
    def __call__(self):
181
      _setCacheHeaders(_ViewEmulator().__of__(self), {})
Jean-Paul Smets's avatar
Jean-Paul Smets committed
182
      return Document.__call__(self)
183 184 185 186 187 188 189

    security.declareProtected(Permissions.AccessContentsInformation, 'getContentBaseURL')
    def getContentBaseURL(self):
      """
        Returns the content base URL based on the actual content
        (in HTML)
      """
190
      if self.hasTextContent():
Jean-Paul Smets's avatar
Jean-Paul Smets committed
191 192 193 194
        html = self._asHTML()
        base_list = re.findall(self.base_parser, str(html))
        if base_list:
          return base_list[0]
195
      return Document.getContentBaseURL(self)
196

197
    security.declareProtected(Permissions.AccessContentsInformation, 'hasBaseData')
198
    def hasBaseData(self):
199
      """
200 201
        A TextDocument store its base_data in the "text_content" property.
        Having base_data is equivalent to having some text_content.
202 203
      """
      return self.hasTextContent()
204

205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
    security.declareProtected(Permissions.ModifyPortalContent, 'setBaseData')
    def setBaseData(self, value):
      """Store base_data into text_content
      """
      self._setTextContent(value)

    security.declareProtected(Permissions.ModifyPortalContent, '_setBaseData')
    _setBaseData = setBaseData

    security.declareProtected(Permissions.ModifyPortalContent,
                                                            '_baseSetBaseData')
    _baseSetBaseData = _setBaseData

    security.declareProtected(Permissions.ModifyPortalContent,
                                                          'setBaseContentType')
    def setBaseContentType(self, value):
      """store value into content_type
      """
      self._setContentType(value)

    security.declareProtected(Permissions.ModifyPortalContent,
                                                         '_setBaseContentType')
    _setBaseContentType = setBaseContentType

    security.declareProtected(Permissions.ModifyPortalContent,
                                                     '_baseSetBaseContentType')
    _baseSetBaseContentType = _setBaseContentType

    security.declareProtected(Permissions.AccessContentsInformation,
                                                                 'getBaseData')
    def getBaseData(self, default=_MARKER):
      """
      """
238
      self._checkConversionFormatPermission(None, **kw)
239 240 241 242 243 244 245 246 247 248 249 250 251
      if default is _MARKER:
        return self.getTextContent()
      else:
        return self.getTextContent(default=default)

    security.declareProtected(Permissions.AccessContentsInformation,
                                                                 'hasBaseData')
    def hasBaseData(self):
      """
      """
      return self.hasTextContent()

    security.declareProtected(Permissions.AccessContentsInformation,
Nicolas Delaby's avatar
Nicolas Delaby committed
252
                                                              'getContentType')
253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357
    def getContentType(self, default=_MARKER):
      """Backward compatibility, read content_type
      from text_format property
      """
      if not self.hasContentType():
        # getProperty can not be used
        # because text_format is not registered in local_properties
        if default is _MARKER:
          return getattr(self, 'text_format', None)
        else:
          return getattr(self, 'text_format', default)
      else:
        if default is _MARKER:
          return self._baseGetContentType()
        else:
          return self._baseGetContentType(default)

    # base_convertable support
    security.declareProtected(Permissions.AccessContentsInformation,
                                                 'isSupportBaseDataConversion')
    def isSupportBaseDataConversion(self):
      """
      """
      return True

    def _convertToBaseFormat(self):
      """Conversion to base format for TextDocument consist
      to convert file content into utf-8
      """
      def guessCharsetAndConvert(document, text_content, content_type):
        """
        return encoded content_type and message if encoding
        is not utf-8
        """
        codec = document._guessEncoding(text_content, content_type)
        if codec is not None:
          try:
            text_content = text_content.decode(codec).encode('utf-8')
          except (UnicodeDecodeError, LookupError):
            message = 'Conversion to base format with codec %r fails' % codec
            # try again with another guesser based on file command
            codec = document._guessEncoding(text_content, 'text/plain')
            if codec is not None:
              try:
                text_content = text_content.decode(codec).encode('utf-8')
              except (UnicodeDecodeError, LookupError):
                message = 'Conversion to base format with codec %r fails'\
                                                                        % codec
              else:
                message = 'Conversion to base format with codec %r succeeds'\
                                                                        % codec
          else:
            message = 'Conversion to base format with codec %r succeeds'\
                                                                        % codec
        else:
          message = 'Conversion to base format without codec fails'
        return text_content, message

      content_type = self.getContentType() or DEFAULT_CONTENT_TYPE
      text_content = self.getData()
      if content_type == 'text/html':
        re_match = self.charset_parser.search(text_content)
        message = 'Conversion to base format succeeds'
        if re_match is not None:
          charset = re_match.group('charset')
          if charset.lower() != 'utf-8':
            try:
              # Use encoding in html document
              text_content = text_content.decode(charset).encode('utf-8')
            except (UnicodeDecodeError, LookupError):
              # Encoding read from document is wrong
              text_content, message = guessCharsetAndConvert(self,
                                                    text_content, content_type)
            else:
              message = 'Conversion to base format with charset %r succeeds'\
                                                                      % charset
              charset = 'utf-8' # Override charset if convertion succeeds
              # change charset value in html_document as well
              def subCharset(matchobj):
                keyword = matchobj.group('keyword')
                charset = matchobj.group('charset')
                if not (keyword or charset):
                  # no match, return same string
                  return matchobj.group(0)
                elif keyword:
                  # if keyword is present, replace charset just after
                  return keyword + 'utf-8'
              text_content = self.charset_parser.sub(subCharset, text_content)
        else:
          text_content, message = guessCharsetAndConvert(self,
                                                    text_content, content_type)
      else:
        # generaly text/plain
        try:
          # if succeeds, not need to change encoding
          # it's already utf-8
          text_content.decode('utf-8')
        except (UnicodeDecodeError, LookupError), error_message:
          text_content, message = guessCharsetAndConvert(self,
                                                    text_content, content_type)
        else:
          message = 'Conversion to base format succeeds'
      self._setBaseData(text_content)
      self._setBaseContentType(content_type)
      return message
358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384

    # Backward compatibility for replacement of text_format by content_type
    security.declareProtected(Permissions.AccessContentsInformation,
                                                               'getTextFormat')
    def getTextFormat(self, default=_MARKER):
      """
      """
      LOG('TextDocument', WARNING,
                'Usage of text_format is deprecated, use text_content instead')
      return self.getContentType(default)

    security.declareProtected(Permissions.ModifyPortalContent, 'setTextFormat')
    def setTextFormat(self, value):
      """
      """
      LOG('TextDocument', WARNING,
                'Usage of text_format is deprecated, use text_content instead')
      return self.setContentType(value)

    security.declareProtected(Permissions.ModifyPortalContent,
                                                              '_setTextFormat')
    def _setTextFormat(self, value):
      """
      """
      LOG('TextDocument', WARNING,
                'Usage of text_format is deprecated, use text_content instead')
      return self._setContentType(value)