From 244dbe3a77bf548f73d8781da7327f30e818b08a Mon Sep 17 00:00:00 2001
From: ZyX <kp-pav@yandex.ru>
Date: Sat, 25 Apr 2015 18:47:31 +0300
Subject: viminfo: First version of ShaDa file dumping

What works:

1. ShaDa file dumping: header, registers, jump list, history, search patterns,
   substitute strings, variables.
2. ShaDa file reading: registers, global marks, variables.

Most was not tested.

TODO:

1. Merging.
2. Reading history, local marks, jump and buffer lists.
3. Documentation update.
4. Converting some data from &encoding.
5. Safer variant of dumping viminfo (dump to temporary file then rename).
6. Removing old viminfo code (currently masked with `#if 0` in a ShaDa file for
   reference).
---
 scripts/shadacat.py | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)
 create mode 100755 scripts/shadacat.py

(limited to 'scripts/shadacat.py')

diff --git a/scripts/shadacat.py b/scripts/shadacat.py
new file mode 100755
index 0000000000..8f5ed276f8
--- /dev/null
+++ b/scripts/shadacat.py
@@ -0,0 +1,73 @@
+#!/usr/bin/env python3.4
+
+import sys
+import codecs
+
+from enum import Enum
+from datetime import datetime
+from functools import reduce
+
+import msgpack
+
+
+class EntryTypes(Enum):
+  Unknown = -1
+  Missing = 0
+  Header = 1
+  SearchPattern = 2
+  SubString = 3
+  HistoryEntry = 4
+  Register = 5
+  Variable = 6
+  GlobalMark = 7
+  Jump = 8
+  BufferList = 9
+  LocalMark = 10
+
+
+def strtrans_errors(e):
+  if not isinstance(e, UnicodeDecodeError):
+    raise NotImplementedError('don’t know how to handle {0} error'.format(
+      e.__class__.__name__))
+  return '<{0:x}>'.format(reduce((lambda a, b: a*0x100+b),
+                                 list(e.object[e.start:e.end]))), e.end
+
+
+codecs.register_error('strtrans', strtrans_errors)
+
+
+def idfunc(o):
+    return o
+
+
+class CharInt(int):
+    def __repr__(self):
+        return super(CharInt, self).__repr__() + ' (\'%s\')' % chr(self)
+
+
+ctable = {
+    bytes: lambda s: s.decode('utf-8', 'strtrans'),
+    dict: lambda d: dict((mnormalize(k), mnormalize(v)) for k, v in d.items()),
+    list: lambda l: list(mnormalize(i) for i in l),
+    int: lambda n: CharInt(n) if 0x20 <= n <= 0x7E else n,
+}
+
+
+def mnormalize(o):
+  return ctable.get(type(o), idfunc)(o)
+
+
+with open(sys.argv[1], 'rb') as fp:
+  unpacker = msgpack.Unpacker(file_like=fp)
+  while True:
+    try:
+      typ = EntryTypes(unpacker.unpack())
+    except msgpack.OutOfData:
+      break
+    else:
+      timestamp = unpacker.unpack()
+      time = datetime.fromtimestamp(timestamp)
+      length = unpacker.unpack()
+      entry = unpacker.unpack()
+      print('{0:13} {1} {2:5} {3!r}'.format(
+        typ.name, time.isoformat(), length, mnormalize(entry)))
-- 
cgit