diff mbox series

[05/13] fetch2: remove duplicated code in url decode and encode

Message ID 20250207124701.14787-5-stefan.herbrechtsmeier-oss@weidmueller.com
State Accepted, archived
Commit a5d569c94700f04b8193c6bccae5af619931b00f
Headers show
Series [01/13] fetch2: do not decode user from file URI | expand

Commit Message

Stefan Herbrechtsmeier Feb. 7, 2025, 12:46 p.m. UTC 
From: Stefan Herbrechtsmeier <stefan.herbrechtsmeier@weidmueller.com>

Use the URI class to decode and encode an URL. Remove duplicate code and
unify the behavior.

Signed-off-by: Stefan Herbrechtsmeier <stefan.herbrechtsmeier@weidmueller.com>
---

 lib/bb/fetch2/__init__.py | 66 +++++++++------------------------------
 1 file changed, 14 insertions(+), 52 deletions(-)
diff mbox series

Patch

diff --git a/lib/bb/fetch2/__init__.py b/lib/bb/fetch2/__init__.py
index ab992b7ea..2a60e94ed 100644
--- a/lib/bb/fetch2/__init__.py
+++ b/lib/bb/fetch2/__init__.py
@@ -353,49 +353,9 @@  def decodeurl(url):
     user, password, parameters).
     """
 
-    m = re.compile('(?P<type>[^:]*)://((?P<user>[^/;]+)@)?(?P<location>[^;]+)(;(?P<parm>.*))?').match(url)
-    if not m:
-        raise MalformedUrl(url)
-
-    type = m.group('type')
-    location = m.group('location')
-    if not location:
-        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:]
-    elif type.lower() == 'file':
-        host = ""
-        path = location
-        if user:
-            path = user + '@' + path
-            user = ""
-    else:
-        host = location
-        path = "/"
-    if user:
-        m = re.compile('(?P<user>[^:]+)(:?(?P<pswd>.*))').match(user)
-        if m:
-            user = m.group('user')
-            pswd = m.group('pswd')
-    else:
-        user = ''
-        pswd = ''
-
-    p = collections.OrderedDict()
-    if parm:
-        for s in parm.split(';'):
-            if s:
-                if not '=' in s:
-                    raise MalformedUrl(url, "The URL: '%s' is invalid: parameter %s does not specify a value (missing '=')" % (url, s))
-                s1, s2 = s.split('=', 1)
-                p[s1] = s2
-
-    return type, host, urllib.parse.unquote(path), user, pswd, p
+    uri = URI(url)
+    path = uri.path if uri.path else "/"
+    return uri.scheme, uri.hostport, path, uri.username, uri.password, uri.params
 
 def encodeurl(decoded):
     """Encodes a URL from tokens (scheme, network location, path,
@@ -406,24 +366,26 @@  def encodeurl(decoded):
 
     if not type:
         raise MissingParameterError('type', "encoded from the data %s" % str(decoded))
-    url = ['%s://' % type]
+    uri = URI()
+    uri.scheme = type
     if user and type != "file":
-        url.append("%s" % user)
+        uri.username = user
         if pswd:
-            url.append(":%s" % pswd)
-        url.append("@")
+            uri.password = pswd
     if host and type != "file":
-        url.append("%s" % host)
+        uri.hostname = host
     if path:
         # Standardise path to ensure comparisons work
         while '//' in path:
             path = path.replace("//", "/")
-        url.append("%s" % urllib.parse.quote(path))
+        uri.path = path
+        if type == "file":
+            # Use old not IETF compliant style
+            uri.relative = False
     if p:
-        for parm in p:
-            url.append(";%s=%s" % (parm, p[parm]))
+        uri.params = p
 
-    return "".join(url)
+    return str(uri)
 
 def uri_replace(ud, uri_find, uri_replace, replacements, d, mirrortarball=None):
     if not ud.url or not uri_find or not uri_replace: