Commit0019d7d

committed

Added unicode handling for author names. They will now be properly encoded into the byte stream, as well as decoded from it

1 parent0f88fb9 commit0019d7dCopy full SHA for 0019d7d

File tree

+47

-2

lines changed

+47

-2

lines changed

Lines changed: 4 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -2,6 +2,10 @@`
`2`	`2`	`Changelog`
`3`	`3`	`=========`
`4`	`4`
	`5`	`+0.3.0 Beta 3`
	`6`	`+============`
	`7`	`+* Added unicode support for author names. Commit.author.name is now unicode instead of string.`
	`8`	`+`
`5`	`9`	`0.3.0 Beta 2`
`6`	`10`	`============`
`7`	`11`	`* Added python 2.4 support`

Lines changed: 14 additions & 2 deletions

Original file line number	Diff line number	Diff line change
`@@ -368,9 +368,14 @@ def _serialize(self, stream):`
`368`	`368`	`write("parent %s\n"%p)`
`369`	`369`
`370`	`370`	`a=self.author`
	`371`	`+aname=a.name`
	`372`	`+ifisinstance(aname,unicode):`
	`373`	`+aname=aname.encode(self.encoding)`
	`374`	`+# END handle unicode in name`
	`375`	`+`
`371`	`376`	`c=self.committer`
`372`	`377`	`fmt="%s %s <%s> %s %s\n"`
`373`		`-write(fmt% ("author",a.name,a.email,`
	`378`	`+write(fmt% ("author",aname,a.email,`
`374`	`379`	`self.authored_date,`
`375`	`380`	`altz_to_utctz_str(self.author_tz_offset)))`
`376`	`381`
`@@ -425,12 +430,19 @@ def _deserialize(self, stream):`
`425`	`430`	`readline()`
`426`	`431`	`# END handle encoding`
`427`	`432`
	`433`	`+# decode the authors name`
	`434`	`+try:`
	`435`	`+self.author.name=self.author.name.decode(self.encoding)`
	`436`	`+exceptUnicodeDecodeError:`
	`437`	`+print>>sys.stderr,"Failed to decode author name: %s"%self.author.name`
	`438`	`+# END handle author's encoding`
	`439`	`+`
`428`	`440`	`# a stream from our data simply gives us the plain message`
`429`	`441`	`# The end of our message stream is marked with a newline that we strip`
`430`	`442`	`self.message=stream.read()`
`431`	`443`	`try:`
`432`	`444`	`self.message=self.message.decode(self.encoding)`
`433`		`-exceptException:`
	`445`	`+exceptUnicodeDecodeError:`
`434`	`446`	`print>>sys.stderr,"Failed to decode message: %s"%self.message`
`435`	`447`	`# END exception handling`
`436`	`448`	`returnself`

Lines changed: 29 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -242,3 +242,32 @@ def test_serialization(self, rwrepo):`
`242`	`242`	`# create all commits of our repo`
`243`	`243`	`assert_commit_serialization(rwrepo,'0.1.6')`
`244`	`244`
	`245`	`+deftest_serialization_unicode_support(self):`
	`246`	`+assertCommit.default_encoding.lower()=='utf-8'`
	`247`	`+`
	`248`	`+# create a commit with unicode in the message, and the author's name`
	`249`	`+# Verify its serialization and deserialization`
	`250`	`+cmt=self.rorepo.commit('0.1.6')`
	`251`	`+assertisinstance(cmt.message,unicode)# it automatically decodes it as such`
	`252`	`+assertisinstance(cmt.author.name,unicode)# same here`
	`253`	`+`
	`254`	`+cmt.message="üäêèß".decode("utf-8")`
	`255`	`+assertlen(cmt.message)==5`
	`256`	`+`
	`257`	`+cmt.author.name="äüß".decode("utf-8")`
	`258`	`+assertlen(cmt.author.name)==3`
	`259`	`+`
	`260`	`+cstream=StringIO()`
	`261`	`+cmt._serialize(cstream)`
	`262`	`+cstream.seek(0)`
	`263`	`+assertlen(cstream.getvalue())`
	`264`	`+`
	`265`	`+ncmt=Commit(self.rorepo,cmt.binsha)`
	`266`	`+ncmt._deserialize(cstream)`
	`267`	`+`
	`268`	`+assertcmt.author.name==ncmt.author.name`
	`269`	`+assertcmt.message==ncmt.message`
	`270`	`+# actually, it can't be printed in a shell as repr wants to have ascii only`
	`271`	`+# it appears`
	`272`	`+cmt.author.__repr__()`
	`273`	`+`

Comments

(0)