Add eff_bdecode.py

diff --git a/eff_bdecode.py b/eff_bdecode.py
new file mode 100644 (file)
index 0000000..5f5b93b
--- /dev/null
+++ b/eff_bdecode.py
@@ -0,0 +1,71 @@
+# http://effbot.org/zone/bencode.htm
+# http://effbot.org/zone/copyright.htm
+#
+# Copyright (C) 1995-2013 by Fredrik Lundh
+#
+# By obtaining, using, and/or copying this software and/or its associated
+# documentation, you agree that you have read, understood, and will comply with
+# the following terms and conditions:
+#
+# Permission to use, copy, modify, and distribute this software and its
+# associated documentation for any purpose and without fee is hereby granted,
+# provided that the above copyright notice appears in all copies, and that both
+# that copyright notice and this permission notice appear in supporting
+# documentation, and that the name of Secret Labs AB or the author not be used
+# in advertising or publicity pertaining to distribution of the software
+# without specific, written prior permission.
+#
+# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS
+# SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN
+# NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR ANY SPECIAL,
+# INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
+# LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
+# OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+# PERFORMANCE OF THIS SOFTWARE.
+
+import re
+
+def tokenize(text, match=re.compile("([idel])|(\d+):|(-?\d+)").match):
+    i = 0
+    while i < len(text):
+        m = match(text, i)
+        s = m.group(m.lastindex)
+        i = m.end()
+        if m.lastindex == 2:
+            yield "s"
+            yield text[i:i+int(s)]
+            i = i + int(s)
+        else:
+            yield s
+
+def decode_item(next, token):
+    if token == "i":
+        # integer: "i" value "e"
+        data = int(next())
+        if next() != "e":
+            raise ValueError
+    elif token == "s":
+        # string: "s" value (virtual tokens)
+        data = next()
+    elif token == "l" or token == "d":
+        # container: "l" (or "d") values "e"
+        data = []
+        tok = next()
+        while tok != "e":
+            data.append(decode_item(next, tok))
+            tok = next()
+        if token == "d":
+            data = dict(zip(data[0::2], data[1::2]))
+    else:
+        raise ValueError
+    return data
+
+def decode(text):
+    try:
+        src = tokenize(text)
+        data = decode_item(src.next, src.next())
+        for token in src: # look for more tokens
+            raise SyntaxError("trailing junk")
+    except (AttributeError, ValueError, StopIteration):
+        raise SyntaxError("syntax error")
+    return data