python - 使用 python xml.sax 解析 XML 实体

Question

使用 xml.sax 使用 python 解析 XML，但我的代码无法捕获实体。为什么skippedEntity()或resolveEntity()不报告以下内容:

import os
import cStringIO
import xml.sax
from xml.sax.handler import ContentHandler,EntityResolver,DTDHandler

#Class to parse and run test XML files
class TestHandler(ContentHandler,EntityResolver,DTDHandler):

    #SAX handler - Entity resolver
    def resolveEntity(self,publicID,systemID):
        print "TestHandler.resolveEntity: %s  %s" % (publicID,systemID)

    def skippedEntity(self, name):
        print "TestHandler.skippedEntity: %s" % (name)

    def unparsedEntityDecl(self,publicID,systemID,ndata):
        print "TestHandler.unparsedEntityDecl: %s  %s" % (publicID,systemID)

    def startElement(self,name,attrs):
        # name = string.lower(name)
        summary = '' + attrs.get('summary','')
        arg = '' + attrs.get('arg','')
        print 'TestHandler.startElement(), %s : %s (%s)' % (name,summary,arg)


def run(xml_string):
    try:
        parser = xml.sax.make_parser()
        stream = cStringIO.StringIO(xml_string)

        curHandler = TestHandler()
        parser.setContentHandler(curHandler)
        parser.setDTDHandler( curHandler )
        parser.setEntityResolver( curHandler )

        parser.parse(stream)
        stream.close()
    except (xml.sax.SAXParseException), e:
        print "*** PARSER error: %s" % e;

def main():
    try:
        XML = "<!DOCTYPE page[ <!ENTITY num 'foo'> ]><test summary='step: &num;'>Entity: &not;</test>"
        run(XML)
    except Exception, e:
      print 'FATAL ERROR: %s' % (str(e))

if __name__== '__main__':
    main()

运行时，我看到的是:

 TestHandler.startElement(), step: foo ()
 *** PARSER error: <unknown>:1:36: undefined entity

为什么我看不到#num; 的resolveEntity 打印内容？或 ¬?

的跳过条目打印

Answer 1

我认为resolveEntity 和skippedEntity 仅为外部DTD 调用。我通过修改 XML 使其工作。

XML = """<?xml version="1.0" encoding="utf-8" ?>
<!DOCTYPE test SYSTEM "external.dtd" >
<test summary='step: &foo; &bar;'>Entity: &not;</test>
"""

external.dtd包含两个简单的实体声明。

<!ENTITY foo "bar">
<!ENTITY bar "foo">

此外，我摆脱了resolveEntity。

这输出 -

TestHandler.startElement(), test : step: bar foo ()
TestHandler.skippedEntity: not

希望这有帮助。