cPyparsing_test.py 文件源码

def runTest(self):

        import cPyparsing as pp
        import sys
        if PY3:
            unichr = chr
        else:
            from __builtin__ import unichr

        a = '\u00bfC\u00f3mo esta usted?'
        if not JYTHON_ENV:
            ualphas = "".join( unichr(i) for i in range(sys.maxunicode)
                                if unichr(i).isalpha() )
        else:
            ualphas = "".join( unichr(i) for i in list(range(0xd800)) + list(range(0xe000,sys.maxunicode))
                                if unichr(i).isalpha() )
        uword = pp.Word(ualphas).setParseAction(pp.upcaseTokens)

        print = lambda *args: None
        print(uword.searchString(a))

        uword = pp.Word(ualphas).setParseAction(pp.downcaseTokens)

        print(uword.searchString(a))

        kw = pp.Keyword('mykey', caseless=True).setParseAction(pp.upcaseTokens).setResultsName('rname')
        ret = kw.parseString('mykey')
        print(ret.rname)
        assert ret.rname=='MYKEY', "failed to upcase with named result"

        kw = pp.Keyword('mykey', caseless=True).setParseAction(pp.pyparsing_common.upcaseTokens).setResultsName('rname')
        ret = kw.parseString('mykey')
        print(ret.rname)
        assert ret.rname=='MYKEY', "failed to upcase with named result (pyparsing_common)"

        kw = pp.Keyword('MYKEY', caseless=True).setParseAction(pp.pyparsing_common.downcaseTokens).setResultsName('rname')
        ret = kw.parseString('mykey')
        print(ret.rname)
        assert ret.rname=='mykey', "failed to upcase with named result"

        if not IRON_PYTHON_ENV:
            #test html data
            html = "<TR class=maintxt bgColor=#ffffff> \
                <TD vAlign=top>?????????????, ??????</TD> \
                <TD vAlign=top><STRONG>BenQ-Siemens CF61</STRONG></TD> \
            "#.decode('utf-8')

            # u'Manufacturer, model
            text_manuf = '?????????????, ??????'
            manufacturer = pp.Literal(text_manuf)

            td_start, td_end = pp.makeHTMLTags("td")
            manuf_body =  td_start.suppress() + manufacturer + pp.SkipTo(td_end)("cells*") + td_end.suppress()

            #~ manuf_body.setDebug()

            #~ for tokens in manuf_body.scanString(html):
                #~ print(tokens)