[bitbake-devel] [RFC PATCH] bitbake: Rewrite fetch2.decodeurl() to use urlparse.urlsplit()

[Phil Blundell]

This means that it now understands "standard" URI syntax as well as
the slightly odd legacy bitbake variant.

There are other places in bitbake (e.g. Local.urldata_init) that also 
need fixing, but this is a start.

Signed-off-by: Phil Blundell <pb at pbcl.net>
---
 lib/bb/fetch2/__init__.py | 60 ++++++++++++++++++++++++++---------------------
 1 file changed, 33 insertions(+), 27 deletions(-)

diff --git a/lib/bb/fetch2/__init__.py b/lib/bb/fetch2/__init__.py
index 260fb37..4886dae 100644
--- a/lib/bb/fetch2/__init__.py
+++ b/lib/bb/fetch2/__init__.py
@@ -329,40 +329,46 @@ def decodeurl(url):
     user, password, parameters).
     """
 
-    m = re.compile('(?P<type>[^:]*)://((?P<user>.+)@)?(?P<location>[^;]+)(;(?P<parm>.*))?').match(url)
-    if not m:
+    if url.startswith("file://"):
+        # This is an old-style bitbake URL.  Fix it up.
+        url = "file:" + url[7:]
+
+    import urlparse
+    d = urlparse.urlsplit(url)
+    if not d.scheme:
         raise MalformedUrl(url)
 
-    type = m.group('type')
-    location = m.group('location')
-    if not location:
+    netloc = d.netloc
+    path = d.path
+
+    if not path:
         raise MalformedUrl(url)
-    user = m.group('user')
-    parm = m.group('parm')
 
-    locidx = location.find('/')
-    if locidx != -1 and type.lower() != 'file':
-        host = location[:locidx]
-        path = location[locidx:]
-    else:
-        host = ""
-        path = location
-    if user:
-        m = re.compile('(?P<user>[^:]+)(:?(?P<pswd>.*))').match(user)
-        if m:
-            user = m.group('user')
-            pswd = m.group('pswd')
-    else:
-        user = ''
-        pswd = ''
+    user = ''
+    pswd = ''
+    host = ''
+
+    if netloc:
+        m = re.compile('((?P<user>[^:@]+)(:(?P<pswd>[^@]+))?@)?(?P<host>.+)').match(netloc)
+        if not m:
+            raise MalformedUrl(url)
+
+        user = m.group('user')
+        pswd = m.group('pswd')
+        host = m.group('host')
 
     p = {}
-    if parm:
-        for s in parm.split(';'):
-            s1, s2 = s.split('=')
-            p[s1] = s2
+    sep = path.find(";")
+    if sep != -1:
+        for s in path[sep+1:].split(';'):
+            try:
+                s1, s2 = s.split('=')
+                p[s1] = s2
+            except ValueError:
+                raise MalformedUrl(url)
+        path = path[:sep]
 
-    return type, host, urllib.unquote(path), user, pswd, p
+    return d.scheme, host, urllib.unquote(path), user, pswd, p
 
 def encodeurl(decoded):
     """Encodes a URL from tokens (scheme, network location, path,
-- 
1.8.5