
...
import xml.sax

class XLSProcessData:
    def __init__(self, em, ishtml = False):
        self.em = em
        self.out = b""
        self.gotdata = 0
        self.xmldata = b""
        self.ishtml = ishtml
        
    def takeLine(self, line):
        if self.ishtml:
            self.out += line + "\n"
            return
        if not self.gotdata:
            self.out += b'''<html><head>''' + \
                        b'''<meta http-equiv="Content-Type" ''' + \
                        b'''content="text/html;charset=UTF-8">''' + \
                        b'''</head><body><pre>'''
            self.gotdata = True
        self.xmldata += line

    def wrapData(self):
        if self.ishtml:
            return self.out
        handler =  xlsxmltocsv.XlsXmlHandler()
        xml.sax.parseString(self.xmldata, handler)
        self.out += self.em.htmlescape(handler.output)
        return self.out + b'''</pre></body></html>'''

class XLSFilter:
    def __init__(self, em):
        self.em = em
        self.ntry = 0
...
            return ([], None)
        self.ntry = 1
        # Some HTML files masquerade as XLS
        try:
            data = open(fn, 'rb').read(512)
            if data.find(b'html') != -1 or data.find(b'HTML') != -1:
                return ("cat", XLSProcessData(self.em, True))
        except Exception as err:
            self.em.rclog("Error reading %s:%s" % (fn, str(err)))
            pass
        cmd = rclexecm.which("xls-dump.py")

	a/src/filters/rclxls.py		b/src/filters/rclxls.py
	...		...
13	import xml.sax	13	import xml.sax
14		14
15	class XLSProcessData:	15	class XLSProcessData:
16	def __init__(self, em, ishtml = False):	16	def __init__(self, em, ishtml = False):
17	self.em = em	17	self.em = em
18	self.out = ""	18	self.out = b""
19	self.gotdata = 0	19	self.gotdata = 0
20	self.xmldata = ""	20	self.xmldata = b""
21	self.ishtml = ishtml	21	self.ishtml = ishtml
22		22
23	def takeLine(self, line):	23	def takeLine(self, line):
24	if self.ishtml:	24	if self.ishtml:
25	self.out += line + "\n"	25	self.out += line + "\n"
26	return	26	return
27	if not self.gotdata:	27	if not self.gotdata:
28	self.out += '''<html><head>''' + \	28	self.out += b'''<html><head>''' + \
29	'''<meta http-equiv="Content-Type" ''' + \	29	b'''<meta http-equiv="Content-Type" ''' + \
30	'''content="text/html;charset=UTF-8">''' + \	30	b'''content="text/html;charset=UTF-8">''' + \
31	'''</head><body><pre>'''	31	b'''</head><body><pre>'''
32	self.gotdata = True	32	self.gotdata = True
33	self.xmldata += line	33	self.xmldata += line
34		34
35	def wrapData(self):	35	def wrapData(self):
36	if self.ishtml:	36	if self.ishtml:
37	return self.out	37	return self.out
38	handler = xlsxmltocsv.XlsXmlHandler()	38	handler = xlsxmltocsv.XlsXmlHandler()
39	data = xml.sax.parseString(self.xmldata, handler)	39	xml.sax.parseString(self.xmldata, handler)
40	self.out += self.em.htmlescape(handler.output)	40	self.out += self.em.htmlescape(handler.output)
41	return self.out + '''</pre></body></html>'''	41	return self.out + b'''</pre></body></html>'''
42		42
43	class XLSFilter:	43	class XLSFilter:
44	def __init__(self, em):	44	def __init__(self, em):
45	self.em = em	45	self.em = em
46	self.ntry = 0	46	self.ntry = 0
	...		...
54	return ([], None)	54	return ([], None)
55	self.ntry = 1	55	self.ntry = 1
56	# Some HTML files masquerade as XLS	56	# Some HTML files masquerade as XLS
57	try:	57	try:
58	data = open(fn, 'rb').read(512)	58	data = open(fn, 'rb').read(512)
59	if data.find('html') != -1 or data.find('HTML') != -1:	59	if data.find(b'html') != -1 or data.find(b'HTML') != -1:
60	return ("cat", XLSProcessData(self.em, True))	60	return ("cat", XLSProcessData(self.em, True))
61	except Exception as err:	61	except Exception as err:
62	self.em.rclog("Error reading %s:%s" % (fn, str(err)))	62	self.em.rclog("Error reading %s:%s" % (fn, str(err)))
63	pass	63	pass
64	cmd = rclexecm.which("xls-dump.py")	64	cmd = rclexecm.which("xls-dump.py")