Commit1d9f391

committed

Fix changing encoding to actually change encoding; add test for it

1 parentc5a8007 commit1d9f391Copy full SHA for 1d9f391

File tree

+14

-1

lines changed

+14

-1

lines changed

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -509,8 +509,8 @@ def changeEncoding(self, newEncoding):`
`509`	`509`	`self.charEncoding= (self.charEncoding[0],"certain")`
`510`	`510`	`else:`
`511`	`511`	`self.rawStream.seek(0)`
`512`		`-self.reset()`
`513`	`512`	`self.charEncoding= (newEncoding,"certain")`
	`513`	`+self.reset()`
`514`	`514`	`raiseReparseException("Encoding changed from %s to %s"% (self.charEncoding[0],newEncoding))`
`515`	`515`
`516`	`516`	`defdetectBOM(self):`

Lines changed: 13 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -21,6 +21,19 @@ def test_basic_prescan_length():`
`21`	`21`	`assert'utf-8'==stream.charEncoding[0].name`
`22`	`22`
`23`	`23`
	`24`	`+deftest_parser_reparse():`
	`25`	`+data="<title>Caf\u00E9</title><!--a--><meta charset='utf-8'>".encode('utf-8')`
	`26`	`+pad=10240-len(data)+1`
	`27`	`+data=data.replace(b"-a-",b"-"+ (b"a"*pad)+b"-")`
	`28`	`+assertlen(data)==10240# Sanity`
	`29`	`+stream=inputstream.HTMLBinaryInputStream(data,chardet=False)`
	`30`	`+assert'windows-1252'==stream.charEncoding[0].name`
	`31`	`+p=HTMLParser(namespaceHTMLElements=False)`
	`32`	`+doc=p.parse(data,useChardet=False)`
	`33`	`+assert'utf-8'==p.documentEncoding`
	`34`	`+assertdoc.find(".//title").text=="Caf\u00E9"`
	`35`	`+`
	`36`	`+`
`24`	`37`	`defrunParserEncodingTest(data,encoding):`
`25`	`38`	`p=HTMLParser()`
`26`	`39`	`assertp.documentEncodingisNone`

Comments

(0)