Add a simple parser for content type specifications.

1 files changed, 27 insertions, 0 deletions

diff --git a/libmproxy/utils.py b/libmproxy/utils.py
index 02bc49cb..0eaada7c 100644
--- a/libmproxy/utils.py
+++ b/libmproxy/utils.py
@@ -265,6 +265,33 @@ def parse_proxy_spec(url):
     return p[:3]
 
 
+def parse_content_type(c):
+    """
+        A simple parser for content-type values. Returns a (type, subtype,
+        parameters) tuple, where type and subtype are strings, and parameters
+        is a dict. If the string could not be parsed, return None.
+
+        E.g. the following string:
+
+            text/html; charset=UTF-8
+
+        Returns:
+
+            ("text", "html", {"charset": "UTF-8"})
+    """
+    parts = c.split(";", 1)
+    ts = parts[0].split("/", 1)
+    if len(ts) != 2:
+        return None
+    d = {}
+    if len(parts) == 2:
+        for i in parts[1].split(";"):
+            clause = i.split("=", 1)
+            if len(clause) == 2:
+                d[clause[0].strip()] = clause[1].strip()
+    return ts[0], ts[1], d
+
+
 def hostport(scheme, host, port):
     """
         Returns the host component, with a port specifcation if needed.