Merge pull request #95 from suchow/python3

Make compatible with Python 3

.gitignore

@@ -7,3 +7,5 @@ site/write/*
 tests/corpus/newyorker/*
 cache/*
 proselint/cache/*
+proselintMDP.sublime-project
+proselintMDP.sublime-workspace

app.py

@@ -6,8 +6,14 @@
 import uuid
 import os
 import re
-import urllib2
 import json
+try:
+    # For Python 3.0 and later
+    from urllib.parse import unquote
+except ImportError:
+    # Fall back to Python 2's urllib2
+    from urllib2 import unquote
+
 
 app = Flask(__name__)
 cors = CORS(app)
@@ -21,7 +27,7 @@ def lint():
     id = uuid.uuid4()
     filename = os.path.join("tmp", "{}.md".format(id))
 
-    text = urllib2.unquote(request.values['text'])
+    text = unquote(request.values['text'])
 
     with open(filename, "w+") as f:
         f.write(text)

plugins/sublime/SublimeLinter-contrib-proselint/linter.py

@@ -16,7 +16,7 @@ class Proselint(Linter):
 
     """Provides an interface to proselint."""
 
-    syntax = ('html', 'markdown', 'plain text')
+    syntax = ('html', 'markdown', 'plain text', 'multimarkdown')
     cmd = 'proselint'
     executable = None
     version_args = '--version'

proselint/checks/garner/a_vs_an.py

@@ -80,7 +80,7 @@ def starts_with_vowel_sound(word):
 
 def initialize():
     """Initialize the cache of pronunciations."""
-    print "Running initialization for garner.a_vs_an (may take a few minutes)"
+    print("Running initialization for garner.a_vs_an (may take a few minutes)")
     from nltk.corpus import cmudict
 
     global d
@@ -89,6 +89,6 @@ def initialize():
     for i, word in enumerate(d):
         starts_with_vowel_sound(word)
         if not (i % 1000):
-            print i
+            print(i)
 
     assert(d)

proselint/checks/misc/linkchecker.py

@@ -16,7 +16,7 @@
 """
 from proselint.tools import memoize
 import re
-import urllib2
+import urllib
 from socket import error as SocketError
 
 
@@ -27,7 +27,7 @@ def check(blob):
     msg = u"Broken link: {}"
 
     regex = re.compile(
-        ur"""(?i)\b((?:https?://|www\d{0,3}[.]
+        r"""(?i)\b((?:https?://|www\d{0,3}[.]
         |[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+
         |(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)
         |[^\s`!()\[\]{};:\'".,<>?\xab\xbb\u201c\u201d\u2018\u2019\u21a9]))""",
@@ -50,10 +50,11 @@ def check(blob):
 def is_broken_link(url):
     """Check if the link return a 404 error."""
     try:
-        request = urllib2.Request(url, headers={'User-Agent': 'Mozilla/5.0'})
-        urllib2.urlopen(request).read()
+        request = urllib.request.Request(
+            url, headers={'User-Agent': 'Mozilla/5.0'})
+        urllib.request.urlopen(request).read()
         return False
-    except urllib2.URLError:
+    except urllib.error.URLError:
         return True
     except SocketError:
         return True

proselint/command_line.py

@@ -100,14 +100,14 @@ def lintscore():
             fullpath = os.path.join(root, f)
 
             # Run the linter.
-            print "Linting {}".format(f)
+            print("Linting {}".format(f))
             out = subprocess.check_output(
                 "proselint {}".format(fullpath), shell=True)
 
             # Determine the number of errors.
             regex = r".+?:(?P<line>\d+):(?P<col>\d+): (?P<message>.+)"
             num_errors = len(tuple(re.finditer(regex, out)))
-            print "Found {} errors.".format(num_errors)
+            print("Found {} errors.".format(num_errors))
 
             # Open the document.
             subprocess.call("{} {}".format("open", fullpath), shell=True)
@@ -126,7 +126,7 @@ def lintscore():
                 except:
                     pass
 
-            print "Currently {} hits and {} false alarms\n---".format(tp, fp)
+            print("Currently {} hits and {} false alarms\n---".format(tp, fp))
 
     return tp * (1.0 * tp / (tp + fp)) ** 2
 
@@ -142,7 +142,7 @@ def proselint(
     """Define the linter command line API."""
     # Return the version number.
     if version:
-        print "v0.0.1"
+        print("v0.0.1")
         return
 
     # Run the intialization.
@@ -156,7 +156,7 @@ def proselint(
 
     # In debug mode, delete the cache and *.pyc files before running.
     if debug:
-        print "Deleting the cache..."
+        print("Deleting the cache...")
         subprocess.call("find . -name '*.pyc' -delete", shell=True)
         subprocess.call(
             "rm -rfv proselint/cache > /dev/null && mkdir proselint/cache",

proselint/tools.py

@@ -7,6 +7,8 @@
 import inspect
 import functools
 import re
+import hashlib
+from textblob import TextBlob
 
 
 def on_heroku():
@@ -37,23 +39,25 @@ def memoize(f):
     try:
         cache = shelve.open(cachepath, protocol=2)
     except:
-        print 'Could not open cache file %s, maybe name collision' % cachepath
+        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:]
 
         tempargdict = inspect.getcallargs(f, *args, **kwargs)
 
-        for k, v in tempargdict.iteritems():
-            argdict[k] = v
+        signature = f.__module__ + '.' + f.__name__
 
-        key = str(hash(frozenset(argdict.items())))
+        for item in tempargdict.items():
+            if isinstance(item, TextBlob):
+                signature += tempargdict['blob'].raw
+
+        key = hashlib.sha256(signature.encode('utf-8')).hexdigest()
 
         try:
             return cache[key]
@@ -64,8 +68,8 @@ def wrapped(*args, **kwargs):
             return value
         except TypeError:
             call_to = f.__module__ + '.' + f.__name__
-            print ['Warning: could not disk cache call to ',
-                   '%s; it probably has unhashable args'] % (call_to)
+            print('Warning: could not disk cache call to ',
+                  '%s; it probably has unhashable args' % (call_to))
             return f(*args, **kwargs)
 
     return wrapped