ENH: Check for whitespace (#616)

.gitignore

@@ -4,5 +4,6 @@ dist
 ld
 codespell.egg-info
 *.pyc
+*.orig
 .cache/
 .pytest_cache/

codespell_lib/data/dictionary.txt

@@ -1,6 +1,4 @@
 1nd->1st
-a a->a
-a bout->about, a bout,
 aare->are
 abailable->available
 abandonded->abandoned
@@ -419,7 +417,6 @@ affilate->affiliate
 affilliate->affiliate
 affort->afford, effort,
 affraid->afraid
-afore mentioned->aforementioned
 aforememtioned->aforementioned
 aforementionned->aforementioned
 aformentioned->aforementioned
@@ -678,12 +675,6 @@ amoutns->amounts
 amuch->much
 amung->among
 amunition->ammunition
-an an->an
-an other->another
-an we->and we
-an will->and will
-an window->a window
-an with->and with
 analagous->analogous
 analises->analysis, analyses,
 analitic->analytic
@@ -711,7 +702,6 @@ ancapsulate->encapsulate
 ancestory->ancestry
 anchord->anchored
 ancilliary->ancillary
-and and->and
 andd->and
 andlers->handlers, antlers,
 androgenous->androgynous
@@ -1398,7 +1388,6 @@ basicly->basically
 batery->battery
 bcak->back
 bcause->because
-be be->be
 beacause->because
 beachead->beachhead
 beacuse->because
@@ -2197,7 +2186,6 @@ cnat->can't
 cnter->center
 co-incided->coincided
 cobvers->covers
-Coca Cola->Coca-Cola
 coctail->cocktail
 codepoitn->codepoint
 codespel->codespell
@@ -4169,7 +4157,6 @@ dota->data
 doub->doubt, daub,
 doube->double
 doubel->double
-double click->double-click
 doubleclick->double-click
 doucment->document
 doulbe->double
@@ -4200,7 +4187,6 @@ dreasm->dreams
 dreawn->drawn
 driectly->directly
 drnik->drink
-drop down->drop-down
 dropable->droppable
 droped->dropped
 droping->dropping
@@ -5988,7 +5974,6 @@ idicates->indicates
 idicating->indicating
 idiosyncracy->idiosyncrasy
 idividual->individual
-if if->if
 iff->if, disabled due to valid mathematical concept
 ignonre->ignore
 ignorence->ignorance
@@ -6925,7 +6910,6 @@ irrelvant->irrelevant
 irreplacable->irreplaceable
 irresistable->irresistible
 irresistably->irresistibly
-is is->is, it is, is it,
 is'nt->isn't
 isconnection->isconnected
 iserting->inserting
@@ -6948,7 +6932,6 @@ istance->instance
 istead->instead
 istener->listeners
 isue->issue
-it it->it, it is, is it,
 iteger->integer
 iterater->iterator
 iteratered->iterated
@@ -6967,7 +6950,6 @@ itializing->initializing
 itnernal->internal
 itnervals->intervals
 itnroduced->introduced
-its is->it is, it's,
 itsef->itself
 itselfs->itself
 itselt->itself
@@ -7889,7 +7871,6 @@ muscial->musical
 muscician->musician
 muscicians->musicians
 musn't->mustn't
-must aligned->must align, must be aligned,
 mustator->mutator
 muste->must
 mut->must, mutt, moot,
@@ -8065,8 +8046,6 @@ normnal->normal
 northen->northern
 northereastern->northeastern
 nortmally->normally
-not either->neither
-not quit->not quite
 notabley->notably
 notaion->notation
 notasion->notation
@@ -8233,7 +8212,6 @@ ocurrence->occurrence
 ocurrences->occurrences
 oder->order, odor,
 oen->one
-of of->of
 offcers->officers
 offcially->officially
 offereings->offerings
@@ -8389,7 +8367,6 @@ optmizations->optimizations
 optmize->optimize
 optmized->optimized
 optomism->optimism
-or or->or
 orded->ordered
 orderd->ordered
 orgamise->organise
@@ -8481,7 +8458,6 @@ ouputarea->outputarea
 ouputs->outputs
 ouputted->outputted
 ouputting->outputting
-our our->our
 ourselfs->ourselves
 ourselve->ourselves
 ourselvs->ourselves
@@ -11862,14 +11838,12 @@ thansk->thanks
 thant->than
 thare->there
 thast->that, that's,
-that that->that that, that, that the, that they, that this,
 that;s->that's
 thatn->that, than,
 thats'->that's
 thats->that's
 thats;->that's
 thck->thick
-the the->the
 theather->theater
 theer->there
 theese->these
@@ -11899,7 +11873,6 @@ thess->this, these,
 thest->test
 thether->tether, whether,
 thev->the
-they they->they
 theyre->they're
 thgat->that
 thge->the
@@ -11917,7 +11890,6 @@ thikns->thinks
 thimngs->things
 thinigs->things
 thinn->thin
-this this->this, this is, is this,
 thise->these
 thist->this
 thiunk->think
@@ -11959,7 +11931,6 @@ thron->thrown, throne,
 throrough->thorough
 throttoling->throttling
 throug->through
-through out->throughout
 throughly->thoroughly
 throught->thought, through, throughout,
 througout->throughout
@@ -12023,7 +11994,6 @@ tkae->take
 tkaes->takes
 tkaing->taking
 tlaking->talking
-to to->to, to do,
 tobbaco->tobacco
 tobot->robot
 toches->touches
@@ -12958,8 +12928,6 @@ warnig->warning
 warnigs->warnings
 warrent->warrant
 warrriors->warriors
-was occured->has occurred
-was occurred->has occurred
 was'nt->wasn't
 was't->wasn't
 was;t->wasn't
@@ -12978,7 +12946,6 @@ wavelenght->wavelength
 wavelenghts->wavelengths
 wavelnes->wavelines
 wayword->wayward
-we we->we
 weant->want, wean,
 weaponary->weaponry
 weas->was

codespell_lib/tests/test_basic.py

@@ -6,7 +6,6 @@
 import os
 import os.path as op
 import subprocess
-import re
 import sys
 import tempfile
 import warnings
@@ -398,37 +397,6 @@ def FakeStdin(text):
         sys.stdin = oldin
 
 
-def test_dictionary_formatting():
-    """Test that all dictionary entries are in lower case and non-empty."""
-    err_dict = dict()
-    with open(op.join(op.dirname(__file__), '..', 'data',
-                      'dictionary.txt'), 'rb') as fid:
-        for line in fid:
-            err, rep = line.decode('utf-8').split('->')
-            err = err.lower()
-            assert err not in err_dict, 'entry already exists'
-            rep = rep.rstrip('\n')
-            assert len(rep) > 0, ('%s: correction %r must be non-empty'
-                                  % (err, rep))
-            assert not re.match('^\s.*', rep), ('%s: correction %r cannot '
-                                                'start with whitespace'
-                                                % (err, rep))
-            if rep.count(','):
-                if not rep.endswith(','):
-                    assert 'disabled' in rep.split(',')[-1], \
-                        ('currently corrections must end with trailing "," (if'
-                         ' multiple corrections are available) or '
-                         'have "disabled" in the comment')
-            err_dict[err] = rep
-            reps = [r.strip() for r in rep.lower().split(',')]
-            reps = [r for r in reps if len(r)]
-            unique = list()
-            for r in reps:
-                if r not in unique:
-                    unique.append(r)
-            assert reps == unique, 'entries are not (lower-case) unique'
-
-
 def test_case_handling(reload_codespell_lib):
     """Test that capitalized entries get detected properly."""
     # Some simple Unicode things

codespell_lib/tests/test_dictionary.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+
+import os.path as op
+import re
+
+
+def test_dictionary_formatting():
+    """Test that all dictionary entries are in lower case and non-empty."""
+    err_dict = dict()
+    ws = re.compile(r'.*\s.*')  # whitespace
+    with open(op.join(op.dirname(__file__), '..', 'data',
+                      'dictionary.txt'), 'rb') as fid:
+        for line in fid:
+            err, rep = line.decode('utf-8').split('->')
+            err = err.lower()
+            assert err not in err_dict, 'error %r already exists' % err
+            assert ws.match(err) is None, 'error %r has whitespace' % err
+            rep = rep.rstrip('\n')
+            assert len(rep) > 0, ('error %s: correction %r must be non-empty'
+                                  % (err, rep))
+            assert not re.match('^\s.*', rep), ('error %s: correction %r '
+                                                'cannot start with whitespace'
+                                                % (err, rep))
+            if rep.count(','):
+                if not rep.endswith(','):
+                    assert 'disabled' in rep.split(',')[-1], \
+                        ('currently corrections must end with trailing "," (if'
+                         ' multiple corrections are available) or '
+                         'have "disabled" in the comment')
+            err_dict[err] = rep
+            reps = [r.strip() for r in rep.lower().split(',')]
+            reps = [r for r in reps if len(r)]
+            unique = list()
+            for r in reps:
+                if r not in unique:
+                    unique.append(r)
+            assert reps == unique, 'entries are not (lower-case) unique'