XmlUtil.py :  » Web-Frameworks » Maki » maki-20030512 » spb » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Web Frameworks » Maki 
Maki » maki 20030512 » spb » XmlUtil.py
# Copyright (c) 2001 Samuel Brauer.  All Rights Reserved.  NO WARRANTY.
# $Revision: 1.21 $

import cStringIO
import string
import sys
import types

import xml.sax
import xml.sax.handler
import xml.sax.saxutils
import xml.sax.saxlib
import xml.sax.xmlreader

import spb.xmlEncoding
import codecs

################################################################
# Some functions for dealing with xml files in various encodings.
################################################################

def getEncodingFromFilename(filename):
  f = open(filename)
  try:
    s = f.readline()
  finally:
    f.close()
  return getEncodingFromString(s)

def getEncodingFromString(s):
  enc = 'utf-8'
  idx = s.find('?>')
  if(idx > 4):
    s = s[:idx+2]
    enc = spb.xmlEncoding.autoDetectXMLEncoding(s)
  enc = enc.lower()
  if(enc == 'utf_8'): enc = 'utf-8'
  return enc

def getUTF8StringFromFilename(fullpath):
  enc = getEncodingFromFilename(fullpath)
  if(enc == 'utf-8'):
    f = open(fullpath)
    try:
      data = f.read()
    finally:
      f.close()
  else:
    f = codecs.open(fullpath, 'r', enc)
    try:
      uni = f.read()
    finally:
      f.close()
    data = uni.encode('utf-8')
  # if the document starts with an <?xml?> header, strip the encoding
  # from that header
  if(data[0:5] == '<?xml'):
    idx = data.find('?>')
    if(idx > 4):
      header = data[:idx]
      out = []
      for part in header.split():
        if(not part.startswith("encoding=")): out.append(part)
      out.append('?>')
      return string.join(out, " ") + data[idx+2:]
  return data


################################################################
# Some functions for coercing objects
################################################################

def objectToText(obj):
  """coerce an object to text, returning either a string (utf-8)"""
  output = None
  if(obj == None):
    output = ""
  elif(isinstance(obj, types.StringType)):
    output = obj
  elif(isinstance(obj, types.UnicodeType)):
    output = obj.encode('utf-8')
  elif(isinstance(obj, types.ListType) or isinstance(obj, types.TupleType)):
    output = ""
    for item in obj:
      if(output): output += ' '
      output += objectToText(item)
  else:
    output = str(obj)
  return output


def objectToSaxEvents(handler, obj, keyStyle="attribute"):
  """Generate SAX2 events representing obj.
  If object appears to have a "toSaxEvents()" method, try to call it.
  Else if obj is a dictionary, create an element for each key.
  Else if obj is a list/tuple, create an element for each item.
  Otherwise, coerce the object to a string and write as characters.
  keyStyle should be either "attribute" or "element", and determines
  how dictionaries are serialized.
  """
  if(obj == None): return
  if(hasattr(obj, "toSaxEvents")):
    return obj.toSaxEvents(handler)

  if(isinstance(obj, types.DictType)):
    xml_dict = XmlableDict(obj, keyStyle)
    objectToSaxEvents(handler, xml_dict, keyStyle)
      
  elif(isinstance(obj, types.ListType) or isinstance(obj, types.TupleType)):
    for item in obj:
      handler.startElementNS((None, 'item'), 'item', {})
      objectToSaxEvents(handler, item, keyStyle)
      handler.endElementNS((None, 'item'), 'item')
  else:
    handler.characters(objectToText(obj))


class PrintHandler(xml.sax.saxlib.ContentHandler):
  """A handler that prints the XML as text to an output stream."""
  def __init__(self, out=sys.stdout, prefixMappings={}, uriMappings={}, undeclaredPrefixes=[]):
    self.out = out
    self.prefixMappings = prefixMappings
    self.uriMappings = uriMappings
    self.undeclaredPrefixes = undeclaredPrefixes

  def writeCharacters(self, chars, escape=0):
    if(isinstance(chars, types.UnicodeType)): chars = chars.encode('utf-8')
    if(escape): self.out.write(xml.sax.saxutils.escape(chars))
    else: self.out.write(chars)

  def startPrefixMapping(self, prefix, uri):
    mappings = self.prefixMappings.get(prefix, [])
    mappings.append(uri)
    self.prefixMappings[prefix] = mappings

    mappings = self.uriMappings.get(uri, [])
    mappings.append(prefix)
    self.uriMappings[uri] = mappings

    if(prefix not in self.undeclaredPrefixes):
      self.undeclaredPrefixes.append(prefix)


  def endPrefixMapping(self, prefix):
    mappings = self.prefixMappings.get(prefix)
    uri = mappings.pop()
    mappings = self.uriMappings.get(uri)
    mappings.pop()

  def startDocument(self):
    self.out.write('<?xml version="1.0" encoding="utf-8"?>\n')
    

  def startElementNS(self, name, qname, attrs):
    uri = name[0]
    lname = name[1]
    self.out.write('<')
    if(uri):
      #self.out.write(self.uriMappings[uri][-1])
      self.writeCharacters(self.uriMappings[uri][-1])
      self.out.write(':')
    #self.out.write(lname)
    self.writeCharacters(lname)

    attdict = {}
    for prefix in self.undeclaredPrefixes:
      if(self.prefixMappings[prefix]):
        attdict['xmlns:'+prefix] = self.prefixMappings[prefix][-1]
    self.undeclaredPrefixes = []

    for pair in attrs.items():
      attname = pair[0]
      attvalue = pair[1]
      atturi = attname[0]
      attlname = attname[1]
      qname = ''
      if(atturi):
        prefix = self.uriMappings[atturi][-1]
        qname = prefix+':'
      qname += attlname
      attdict[qname] = attvalue

    for key in attdict.keys():
      self.writeCharacters(' %s' % key)
      self.out.write('="')
      self.writeCharacters(attdict[key], 1)
      self.out.write('"')

    self.out.write('>')

  def endElementNS(self, name, qname):
    uri = name[0]
    lname = name[1]
    self.out.write('</')
    if(uri):
      #self.out.write(self.uriMappings[uri][-1])
      self.writeCharacters(self.uriMappings[uri][-1])
      self.out.write(':')
    #self.out.write(lname)
    self.writeCharacters(lname)
    self.out.write('>')

  def characters(self, content):
    self.writeCharacters(content, 1)

  def ignorableWhitespace(self, content):
    self.out.write(content)

  def processingInstruction(self, target, data):
    self.out.write('<?')
    self.writeCharacters(target)
    self.out.write(' ')
    self.writeCharacters(data)
    self.out.write('?>')

  def startElement(self, name, attrs):
    nsattrs = {}
    for key in attrs.keys():
      nsattrs[(None, key)] = attrs[key]
    self.startElementNS((None, name), name, nsattrs)

  def endElement(self, name):
    self.endElementNS((None, name), name)


class PrettyPrintHandler(PrintHandler):
  def __init__(self, out=sys.stdout, prefixMappings={}, uriMappings={}, undeclaredPrefixes=[]):
    PrintHandler.__init__(self, out, prefixMappings, uriMappings, undeclaredPrefixes)
    self.indent = 0
    self.newline = 1

  def startElementNS(self, name, qname, attrs):
    if(self.newline): self.out.write("\n")
    self.newline = 1
    self.out.write("  " * self.indent)
    PrintHandler.startElementNS(self, name, qname, attrs)
    self.indent += 1

  def endElementNS(self, name, qname):
    self.indent -= 1
    if(not self.newline): self.out.write("  " * self.indent)
    PrintHandler.endElementNS(self, name, qname)
    self.out.write("\n")
    self.newline = 0


class FilterHandler(xml.sax.saxlib.ContentHandler):
  """This handler is used to filter the sending of events to another handler.
  'handler' is the other handler.
  'documentEvents' is a flag specifying whether or not to send startDocument() and endDocument().
  'skipElements' is a number of elements to skip the sending of startElementNS() and endElementNS() events for.
  'skipCharacters' is a number of elements whose characters() events should be skipped.
  'processingInstructions' is a flag specifying whether or not to send processingInstruction().
  """
  def __init__(self, handler, documentEvents, skipElements, skipCharacters, processingInstructions):
    self.handler = handler
    self.documentEvents = documentEvents
    self.skipElements = skipElements
    self.skipCharacters = skipCharacters
    self.processingInstructions = processingInstructions
    self.elements = 0

  def startPrefixMapping(self, prefix, uri):
    self.handler.startPrefixMapping(prefix, uri)

  def endPrefixMapping(self, prefix):
    self.handler.endPrefixMapping(prefix)

  def startDocument(self):
    if(self.documentEvents): self.handler.startDocument()

  def endDocument(self):
    if(self.documentEvents): self.handler.endDocument()

  def startElementNS(self, name, qname, attrs):
    self.elements += 1
    if(self.elements > self.skipElements): self.handler.startElementNS(name, qname, attrs)

  def endElementNS(self, name, qname):
    if(self.elements > self.skipElements): self.handler.endElementNS(name, qname)
    self.elements -= 1

  def characters(self, content):
    if(self.elements > self.skipCharacters): self.handler.characters(content)

  def ignorableWhitespace(self, content):
    if(self.elements > self.skipElements): self.handler.ignorableWhitespace(content)

  def processingInstruction(self, target, data):
    if(self.processingInstructions): self.handler.processingInstruction(target, data)

  def startElement(self, name, attrs):
    nsattrs = {}
    for key in attrs.keys():
      nsattrs[(None, key)] = attrs[key]
    self.startElementNS((None, name), name, nsattrs)

  def endElement(self, name):
    self.endElementNS((None, name), name)



class XmlableText:
  def __init__(self, text, style='xml'):
    if(style not in ('br', 'brbr', 'p', 'xhtml', 'xml', 'ul', 'ol')):
      raise RuntimeError, "XmlableText constructor passed unrecognized value for 'style'."
    if(text):
      self.text = text.replace("\r\n", "\n").replace("\r", "\n")
    else:
      self.text = ""
    self.style = style
  
  def toSaxEvents(self, handler):
    if(self.style == 'br'):
      for s in string.split(self.text, "\n"):
        handler.characters(s)
        handler.startElementNS((None, 'br'), 'br', {})
        handler.endElementNS((None, 'br'), 'br')
    elif(self.style == 'brbr'):
      chunks = self.text.split("\n\n")
      for i in xrange(len(chunks)):
        s = chunks[i]
        handler.characters(s)
        if(len(chunks) - i > 1):
          handler.startElementNS((None, 'br'), 'br', {})
          handler.endElementNS((None, 'br'), 'br')
          handler.startElementNS((None, 'br'), 'br', {})
          handler.endElementNS((None, 'br'), 'br')
    elif(self.style == 'p'):
      for s in self.text.split("\n\n"):
        handler.startElementNS((None, 'p'), 'p', {})
        handler.characters(s)
        handler.endElementNS((None, 'p'), 'p')
    elif(self.style in ('ul', 'ol')):
      handler.startElementNS((None, self.style), self.style, {})
      for s in self.text.split("\n\n"):
        handler.startElementNS((None, 'li'), 'li', {})
        handler.characters(s)
        handler.endElementNS((None, 'li'), 'li')
      handler.endElementNS((None, self.style), self.style)
    elif(self.style in ('xhtml', 'xml')):
      source = '<temp>'
      if(isinstance(self.text, types.UnicodeType)):
        source += self.text.encode('utf-8')
      else:
        source += self.text
      source += '</temp>'
      if(isWellFormed(source)):
        # parse the text using the handler, but filter which events we pass to the handler (skip document events and events for the first element <temp/>)
        myhandler = FilterHandler(handler, 0, 1, 0, 0)
        parseString(source, myhandler, 1)
      else:
        #sys.stderr.write("XmlableText does not contain valid xhtml\n")
        handler.characters(self.text)

class XmlableDict:
  def __init__(self, dict, keyStyle='attribute'):
    if(keyStyle not in ('attribute', 'element')):
      raise RuntimeError, "XmlableDict constructor passed unrecognized value for 'keyStyle'."
    self.dict = dict
    self.style = keyStyle
  
  def toSaxEvents(self, handler):
    for key in self.dict.keys():
      keystring = str(key)
      if(self.style == 'element'):
        handler.startElementNS((None, keystring), keystring, {})
        objectToSaxEvents(handler, self.dict[key], self.style)
        handler.endElementNS((None, keystring), keystring)
      else:
        handler.startElementNS((None, 'item'), 'item', {(None, 'key'): keystring})
        objectToSaxEvents(handler, self.dict[key], self.style)
        handler.endElementNS((None, 'item'), 'item')

def parseStream(input, handler=None, namespaces=1):
  parser = xml.sax.make_parser()
  parser.setFeature(xml.sax.handler.feature_namespaces, namespaces)
  if(handler): parser.setContentHandler(handler)
  inputsource = xml.sax.xmlreader.InputSource()
  inputsource.setByteStream(input)
  inputsource.setEncoding('utf-8')
  parser.parse(inputsource)

def parseString(input, handler=None, namespaces=1):
  inbuffer = cStringIO.StringIO()
  inbuffer.write(input)
  inbuffer.seek(0)
  try:
    parseStream(inbuffer, handler, namespaces)
  finally:
    inbuffer.close()

def isWellFormed(val):
  try:
    parseString(val)
  except:
    return 0
  return 1

www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.