From 102d22dd40988f0a1b3aa581c4f32eed4de81379 Mon Sep 17 00:00:00 2001
From: Jordan Suchow <suchow@post.harvard.edu>
Date: Thu, 22 Jan 2015 01:06:00 -0800
Subject: [PATCH] Allow memoization to disk for shared processing

#20
---
 .gitignore                        |  1 +
 proselint/checks/example_check.py |  3 ++
 proselint/memoize.py              | 53 +++++++++++++++++++++++++++++++
 proselint/reverse.py              |  6 ++++
 4 files changed, 63 insertions(+)
 create mode 100644 proselint/memoize.py
 create mode 100644 proselint/reverse.py

diff --git a/.gitignore b/.gitignore
index 66dbf51bd..83e9a1e1c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 *.egg-info
 *.pyc
+cached_func_calls/*
diff --git a/proselint/checks/example_check.py b/proselint/checks/example_check.py
index 2f36c22bb..cbd46d042 100644
--- a/proselint/checks/example_check.py
+++ b/proselint/checks/example_check.py
@@ -14,10 +14,13 @@
 The first line always is always wrong.
 
 """
+from proselint.reverse import reverse
 
 
 def check(text):
 
+    reversed_text = reverse(text)
+
     error_code = "PL000"
     msg = "First line always has an error."
 
diff --git a/proselint/memoize.py b/proselint/memoize.py
new file mode 100644
index 000000000..c413a2536
--- /dev/null
+++ b/proselint/memoize.py
@@ -0,0 +1,53 @@
+import os
+import shelve
+import inspect
+import functools
+
+cache_dirname = 'cached_func_calls'
+
+
+def memoize(f):
+    if not os.path.isdir(cache_dirname):
+        os.mkdir(cache_dirname)
+        print 'Created cache directory %s' \
+            % os.path.join(os.path.abspath(__file__), cache_dirname)
+
+    cache_filename = f.__module__ + f.__name__
+    cachepath = os.path.join(cache_dirname, cache_filename)
+
+    try:
+        cache = shelve.open(cachepath, protocol=2)
+    except:
+        print 'Could not open cache file %s, maybe name collision' % cachepath
+        cache = None
+
+    @functools.wraps(f)
+    def wrapped(*args, **kwargs):
+        argdict = {}
+
+        # handle instance methods
+        if hasattr(f, '__self__'):
+            args = args[1:]
+            # argdict['classname'] = f.__self__.__class__
+
+        tempargdict = inspect.getcallargs(f, *args, **kwargs)
+
+        # handle numpy arrays
+        for k, v in tempargdict.iteritems():
+            argdict[k] = v
+
+        key = str(hash(frozenset(argdict.items())))
+
+        try:
+            return cache[key]
+        except KeyError:
+            value = f(*args, **kwargs)
+            cache[key] = value
+            cache.sync()
+            return value
+        except TypeError:
+            print 'Warning: could not disk cache call to %s; it probably has unhashable args' \
+                % (f.__module__ + '.' + f.__name__)
+            return f(*args, **kwargs)
+
+    return wrapped
diff --git a/proselint/reverse.py b/proselint/reverse.py
new file mode 100644
index 000000000..458060b00
--- /dev/null
+++ b/proselint/reverse.py
@@ -0,0 +1,6 @@
+from memoize import memoize
+
+
+@memoize
+def reverse(text):
+    return text[::-1]