OOoUtils.py 19.3 KB
1 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 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559
##############################################################################
#
# Copyright (c) 2003-2005 Nexedi SARL and Contributors. All Rights Reserved.
#                         Kevin DELDYCKE    <kevin@nexedi.com>
#                         Guillaume MICHON  <guillaume@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.
#
##############################################################################

import sys

from Acquisition import Implicit

from Products.PythonScripts.Utility import allow_class
from ZPublisher.HTTPRequest import FileUpload
from xml.dom import Node
from AccessControl import ClassSecurityInfo
from Globals import InitializeClass, get_request
from zipfile import ZipFile, ZIP_DEFLATED
try:
  from cStringIO import StringIO
except ImportError:
  from StringIO import StringIO
import imghdr
import random
from Products.ERP5Type import Permissions
from zLOG import LOG, INFO
from zLOG import PROBLEM

from OFS.Image import Pdata

try:
  from Ft.Xml import Parse
except ImportError:
  LOG('OOoUtils', INFO, "Can't import Parse")
  class Parse:
    def __init__(self, *args, **kw):
      raise ImportError, "Sorry, it was not possible to import Ft library, python2.4-4Suite-XML is not installed"


class CorruptedOOoFile(Exception): pass

OOo_mimeType_dict = {
  'sxw' : 'application/vnd.sun.xml.writer',
  'stw' : 'application/vnd.sun.xml.writer.template',
  'sxg' : 'application/vnd.sun.xml.writer.global',
  'sxc' : 'application/vnd.sun.xml.calc',
  'stc' : 'application/vnd.sun.xml.calc.template',
  'sxi' : 'application/vnd.sun.xml.impress',
  'sti' : 'application/vnd.sun.xml.impress.template',
  'sxd' : 'application/vnd.sun.xml.draw',
  'std' : 'application/vnd.sun.xml.draw.template',
  'sxm' : 'application/vnd.sun.xml.math',
}

class OOoBuilder(Implicit):
  """
  Tool that allows to reinject new files in a ZODB OOo document.
  """
  __allow_access_to_unprotected_subobjects__ = 1

  def __init__(self, document):
    if hasattr(document, 'data') :
      self._document = StringIO()

      if isinstance(document.data, Pdata):
        # Handle image included in the style
        dat = document.data
        while dat is not None:
          self._document.write(dat.data)
          dat = dat.next
      else:
        # Default behaviour
        self._document.write(document.data)
          
    elif hasattr(document, 'read') :
      self._document = document
    else :
      self._document = StringIO()
      self._document.write(document)
    self._image_count = 0    
    self._manifest_additions_list = []

  def replace(self, filename, stream):
    """
    Replaces the content of filename by stream in the archive.
    Creates a new file if filename was not already there.
    """
    try:
      zf = ZipFile(self._document, mode='a', compression=ZIP_DEFLATED)
    except RuntimeError:
      zf = ZipFile(self._document, mode='a')
    try:
      # remove the file first if it exists
      fi = zf.getinfo(filename)
      zf.filelist.remove( fi )
    except KeyError:
      # This is a new file
      pass
    zf.writestr(filename, stream)
    zf.close()

  def extract(self, filename):
    """
    Extracts a file from the archive
    """
    try:
      zf = ZipFile(self._document, mode='r', compression=ZIP_DEFLATED)
    except RuntimeError:
      zf = ZipFile(self._document, mode='r')
    return zf.read(filename)

  def getNameList(self):
    try:
      zf = ZipFile(self._document, mode='r', compression=ZIP_DEFLATED)
    except RuntimeError:
      zf = ZipFile(self._document, mode='r')
    li = zf.namelist()
    zf.close()
    return li

  def getMimeType(self):
    return self.extract('mimetype')

  def prepareContentXml(self, ooo_xml_file_id, xsl_content=None):
    """
      extracts content.xml text and prepare it :
        - add tal namespace
        - indent the xml
    """
    content_xml = self.extract(ooo_xml_file_id)
    output = StringIO()
    try:
      import libxml2
      import libxslt
      if xsl_content is None:
        raise ImportError
      stylesheet_doc = libxml2.parseDoc(xsl_content)
      stylesheet = libxslt.parseStylesheetDoc(stylesheet_doc)
      content_doc = libxml2.parseDoc(content_xml)
      result_doc = stylesheet.applyStylesheet(content_doc, None)
      #Declare zope namespaces
      root = result_doc.getRootElement()
      tal = root.newNs('http://xml.zope.org/namespaces/tal', 'tal')
      i18n = root.newNs('http://xml.zope.org/namespaces/i18n', 'i18n')
      metal = root.newNs('http://xml.zope.org/namespaces/metal', 'metal')
      root.setNsProp(tal, 'attributes', 'dummy python:request.RESPONSE.setHeader(\'Content-Type\', \'text/html;; charset=utf-8\')')
      buff = libxml2.createOutputBuffer(output, 'utf-8')
      result_doc.saveFormatFileTo(buff, 'utf-8', 1)
      stylesheet_doc.freeDoc(); content_doc.freeDoc(); result_doc.freeDoc()
      return output.getvalue()
    except ImportError:
      document = Parse(content_xml)
      document_element = document.documentElement
      tal = document.createAttributeNS('http://www.w3.org/2000/xmlns/', 'xmlns:tal')
      tal.value = u'http://xml.zope.org/namespaces/tal'
      i18n = document.createAttributeNS('http://www.w3.org/2000/xmlns/', 'xmlns:i18n')
      i18n.value = u'http://xml.zope.org/namespaces/i18n'
      metal = document.createAttributeNS('http://www.w3.org/2000/xmlns/', 'xmlns:metal')
      metal.value = u'http://xml.zope.org/namespaces/metal'
      document_element.setAttributeNodeNS(tal)
      document_element.setAttributeNodeNS(i18n)
      document_element.setAttributeNodeNS(metal)
      document_element.setAttributeNS(None, 'tal:attributes', 'dummy python:request.RESPONSE.setHeader("Content-Type", "text/html;; charset=utf-8")')
      from xml.dom.ext import PrettyPrint
      PrettyPrint(document_element, output)
      return output.getvalue()

  def addFileEntry(self, full_path, media_type, content=None):
      """ Add a file entry to the manifest and possibly is content """
      self.addManifest(full_path, media_type)
      if content:
          self.replace(full_path, content)

  def addManifest(self, full_path, media_type):
    """ Add a path to the manifest """
    li = '<manifest:file-entry manifest:media-type="%s" manifest:full-path="%s"/>'%(media_type, full_path)
    self._manifest_additions_list.append(li)

  def updateManifest(self):
    """ Add a path to the manifest """
    MANIFEST_FILENAME = 'META-INF/manifest.xml'
    meta_infos = self.extract(MANIFEST_FILENAME)
    # prevent some duplicates
    for meta_line in meta_infos.split('\n'):
        for new_meta_line in self._manifest_additions_list:
            if meta_line.strip() == new_meta_line:
                self._manifest_additions_list.remove(new_meta_line)

    # add the new lines
    self._manifest_additions_list.append('</manifest:manifest>')
    meta_infos = meta_infos.replace( self._manifest_additions_list[-1], '\n'.join(self._manifest_additions_list) )
    self.replace(MANIFEST_FILENAME, meta_infos)
    self._manifest_additions_list = []

  def addImage(self, image, format='png'):
    """
    Add an image to the current document and return its id
    """
    count = self._image_count
    self._image_count += 1
    name = "Picture/%s.%s" % (count, format)
    self.replace(name, image)
    is_legacy = ('oasis.opendocument' not in self.getMimeType())
    return "%s%s" % (is_legacy and '#' or '', name,)

  def render(self, name='', extension='sxw'):
    """
    returns the OOo document
    """
    request = get_request()
    if name:
      request.response.setHeader('Content-Disposition', 'inline; filename=%s.%s' % (name, extension))

    self._document.seek(0)
    return self._document.read()

allow_class(OOoBuilder)

class OOoParser(Implicit):
  """
    General purpose tools to parse and handle OpenOffice v1.x documents.
  """
  __allow_access_to_unprotected_subobjects__ = 1 
  def __init__(self):
    self.oo_content_dom = None
    self.oo_styles_dom  = None
    self.oo_files = {}
    self.pictures = {}
    self.ns = {}
    self.filename = None

  def openFromString(self, text_content):
    return self.openFile(StringIO(text_content))

  def openFile(self, file_descriptor):
    """
      Load all files in the zipped OpenOffice document
    """
    # Try to unzip the Open Office doc
    try:
      oo_unzipped = ZipFile(file_descriptor, mode="r")
    except:
      LOG('ERP5OOo', PROBLEM, 'Error in openFile', error=sys.exc_info())
      raise CorruptedOOoFile()
    # Test the integrity of the file
    if oo_unzipped.testzip() != None:
      raise CorruptedOOoFile()

    # Get the filename
    self.filename = getattr(file_descriptor, 'filename', 'default_filename')

    # List and load the content of the zip file
    for name in oo_unzipped.namelist():
      self.oo_files[name] = oo_unzipped.read(name)
    oo_unzipped.close()

    # Get the main content and style definitions
    self.oo_content_dom = Parse(self.oo_files["content.xml"])
    self.oo_styles_dom  = Parse(self.oo_files["styles.xml"])

    # Create a namespace table
    xpath = './/*[name() = "office:document-styles"]'
    doc_ns = self.oo_styles_dom.xpath(xpath)
    for i in range(doc_ns[0].attributes.length)[1:]:
        if doc_ns[0].attributes.item(i).nodeType == Node.ATTRIBUTE_NODE:
            name = doc_ns[0].attributes.item(i).name
            if name[:5] == "xmlns":
                self.ns[name[6:]] = doc_ns[0].attributes.item(i).value

  def getFilename(self):
    """
      Return the name of the OpenOffice file
    """
    return self.filename

  def getPicturesMapping(self):
    """
      Return a dictionnary of all pictures in the document
    """
    if len(self.pictures) <= 0:
      for file_name in self.oo_files:
        raw_data = self.oo_files[file_name]
        pict_type = imghdr.what(None, raw_data)
        if pict_type != None:
          self.pictures[file_name] = raw_data
    return self.pictures

  def getContentDom(self):
    """
      Return the DOM tree of the main OpenOffice content
    """
    return self.oo_content_dom

  def getSpreadsheetsDom(self, include_embedded=False):
    """
      Return a list of DOM tree spreadsheets (optionnaly included embedded ones)
    """
    spreadsheets = []
    spreadsheets = self.getPlainSpreadsheetsDom()
    if include_embedded == True:
      spreadsheets += self.getEmbeddedSpreadsheetsDom()
    return spreadsheets

  def getSpreadsheetsMapping(self, include_embedded=False, no_empty_lines=False, normalize=True):
    """
      Return a list of table-like spreadsheets (optionnaly included embedded ones)
    """
    tables = {}
    tables = self.getPlainSpreadsheetsMapping(no_empty_lines, normalize)
    if include_embedded == True:
      embedded_tables = self.getEmbeddedSpreadsheetsMapping(no_empty_lines, normalize)
      tables = self._getTableListUnion(tables, embedded_tables)
    return tables

  def getPlainSpreadsheetsDom(self):
    """
      Retrieve every spreadsheets from the document and get they DOM tree
    """
    spreadsheets = []
    # List all spreadsheets
    for table in self.oo_content_dom.xpath('.//*[name() = "table:table"]'):
      spreadsheets.append(table)
    return spreadsheets

  def getPlainSpreadsheetsMapping(self, no_empty_lines=False, normalize=True):
    """
      Return a list of plain spreadsheets from the document and transform them as table
    """
    tables = {}
    for spreadsheet in self.getPlainSpreadsheetsDom():
      new_table = self.getSpreadsheetMapping(spreadsheet, no_empty_lines, normalize)
      if new_table != None:
        tables = self._getTableListUnion(tables, new_table)
    return tables

  def getEmbeddedSpreadsheetsDom(self):
    """
      Return a list of existing embedded spreadsheets in the file as DOM tree
    """
    spreadsheets = []
    # List all embedded spreadsheets
    emb_objects = self.oo_content_dom.xpath('.//*[name() = "draw:object"]')
    for embedded in emb_objects:
        document = embedded.getAttributeNS(self.ns["xlink"], "href")
        if document:
            try:
                
                object_content = Parse(self.oo_files[document[3:] + '/content.xml'])
                xpath = './/*[name() = "table:table"]'
                tables = self.oo_content_dom.xpath(xpath)
                if tables:
                    for table in tables:
                        spreadsheets.append(table)
                else: # XXX: insert the link to OLE document ?
                    pass
            except:
                pass
    return spreadsheets

  def getEmbeddedSpreadsheetsMapping(self, no_empty_lines=False, normalize=True):
    """
      Return a list of embedded spreadsheets in the document as table
    """
    tables = {}
    for spreadsheet in self.getEmbeddedSpreadsheetsDom():
      new_table = self.getSpreadsheetMapping(spreadsheet, no_empty_lines, normalize)
      if new_table != None:
        tables = self._getTableListUnion(tables, new_table)
    return tables

  def getSpreadsheetMapping(self, spreadsheet=None, no_empty_lines=False, normalize=True):
    """
      This method convert an OpenOffice spreadsheet to a simple table.
      This code is based on the oo2pt tool (http://cvs.sourceforge.net/viewcvs.py/collective/CMFReportTool/oo2pt).
    """
    if spreadsheet == None or spreadsheet.nodeName != 'table:table':
      return None

    table = []

    # Get the table name
    table_name = spreadsheet.getAttributeNS(self.ns["table"], "name")

    # Scan table and store usable informations
    for line in spreadsheet.xpath('.//*[name() = "table:table-row"]'):

      # TODO : to the same as cell about abusive repeated lines

      line_group_found = line.getAttributeNS(self.ns["table"], "number-rows-repeated")
      if not line_group_found:
        lines_to_repeat = 1
      else:
        lines_to_repeat = int(line_group_found)

      for i in range(lines_to_repeat):
        table_line = []

        # Get all cells
        cells = line.xpath('.//*[name() = "table:table-cell"]')
        cell_index_range = range(len(cells))

        for cell_index in cell_index_range:
          cell = cells[cell_index]

          # If the cell as no child, cells have no content
          # And if the cell is the last of the row, we don't need to add it to the line
          # So we can go to the next line (= exit this cells loop)
          #
          # I must do this test because sometimes the following cell group
          #   can be found in OOo documents : <table:table-cell table:number-columns-repeated='246'/>
          # This is bad because it create too much irrevelent content that slow down the process
          # So it's a good idea to break the loop in this case
          if len(cell.childNodes) == 0 and cell_index == cell_index_range[-1]:
            break

          # Handle cells group
          cell_group_found = cell.getAttributeNS(self.ns["table"], "number-columns-repeated")
          if not cell_group_found:
            cells_to_repeat = 1
          else:
            cells_to_repeat = int(cell_group_found)

          # Ungroup repeated cells
          for j in range(cells_to_repeat):
            # Get the cell content
            cell_text = None
            text_tags = cell.xpath('.//*[name() = "text:p"]')
            if len(text_tags):
              cell_text = ''.join([text.xpath('string(.)')
                                   for text in text_tags])

            # Add the cell to the line
            table_line.append(cell_text)

        # Delete empty lines if needed
        if no_empty_lines:
          empty_cell = 0
          for table_cell in table_line:
            if table_cell == None:
              empty_cell += 1
          if empty_cell == len(table_line):
            table_line = None

        # Add the line to the table
        if table_line != None:
          table.append(table_line)
        else:
          # If the line is empty here, the repeated line will also be empty, so
          # no need to loop.
          break

    # Reduce the table to the minimum
    new_table = self._getReducedTable(table)

    # Get a homogenized table
    if normalize:
      table_size = self._getTableSizeDict(new_table)
      new_table = self._getNormalizedBoundsTable( table  = new_table
                                                , width  = table_size['width']
                                                , height = table_size['height']
                                                )
    return {table_name: new_table}

  def _getReducedTable(self, table):
    """
      Reduce the table to its minimum size
    """
    empty_lines = 0
    no_more_empty_lines = 0

    # Eliminate all empty cells at the ends of lines and columns
    # Browse the table starting from the bottom for easy empty lines count
    for line in range(len(table)-1, -1, -1):
      empty_cells = 0
      line_content = table[line]
      for cell in range(len(line_content)-1, -1, -1):
        if line_content[cell] in ('', None):
          empty_cells += 1
        else:
          break

      if (not no_more_empty_lines) and (empty_cells == len(line_content)):
        empty_lines += 1
      else:
        line_size = len(line_content) - empty_cells
        table[line] = line_content[:line_size]
        no_more_empty_lines = 1

    table_height = len(table) - empty_lines

    return table[:table_height]

  def _getTableSizeDict(self, table):
    """
      Get table dimension as dictionnary contain both height and width
    """
    max_cols = 0
    for line_index in range(len(table)):
      line = table[line_index]
      if len(line) > max_cols:
        max_cols = len(line)

    return { 'width' : max_cols
           , 'height': len(table)
           }

  def _getNormalizedBoundsTable(self, table, width=0, height=0):
    """
      Add necessary cells and lines to obtain given bounds
    """
    while height > len(table):
      table.append([])
    for line in range(height):
      while width > len(table[line]):
        table[line].append(None)
    return table

  def _getTableListUnion(self, list1, list2):
    """
      Coerce two dict containing tables structures.
      We need to use this method because a OpenOffice document can hold
        several embedded spreadsheets with the same id. This explain the
        use of random suffix in such extreme case.
    """
    for list2_key in list2.keys():
      # Generate a new table ID if needed
      new_key = list2_key
      while new_key in list1.keys():
        new_key = list2_key + '_' + str(random.randint(1000,9999))
      list1[new_key] = list2[list2_key]
    return list1

allow_class(OOoParser)
allow_class(CorruptedOOoFile)

def newOOoParser(container):
  return OOoParser().__of__(container)