* Upd tests for new meaning of 'string'

tests/test_contractions.py

@@ -18,24 +18,24 @@ def test_possess(EN):
 def test_apostrophe(EN):
     tokens = EN("schools'")
     assert len(tokens) == 2
-    assert tokens[1].string == "'"
+    assert tokens[1].orth_ == "'"
-    assert tokens[0].string == "schools"
+    assert tokens[0].orth_ == "schools"
 
 
 def test_LL(EN):
     tokens = EN("we'll")
     assert len(tokens) == 2
-    assert tokens[1].string == "'ll"
+    assert tokens[1].orth_ == "'ll"
     assert tokens[1].lemma_ == "will"
-    assert tokens[0].string == "we"
+    assert tokens[0].orth_ == "we"
 
 
 def test_aint(EN):
     tokens = EN("ain't")
     assert len(tokens) == 2
-    assert tokens[0].string == "ai"
+    assert tokens[0].orth_ == "ai"
     assert tokens[0].lemma_ == "be"
-    assert tokens[1].string == "n't"
+    assert tokens[1].orth_ == "n't"
     assert tokens[1].lemma_ == "not"
 
 
@@ -46,7 +46,7 @@ def test_capitalized(EN):
     assert len(tokens) == 2
     tokens = EN("Ain't")
     assert len(tokens) == 2
-    assert tokens[0].string == "Ai"
+    assert tokens[0].orth_ == "Ai"
     assert tokens[0].lemma_ == "be"
 
 

tests/test_emoticons.py

@@ -11,28 +11,28 @@ def EN():
 def test_tweebo_challenge(EN):
     text = u""":o :/ :'( >:o (: :) >.< XD -__- o.O ;D :-) @_@ :P 8D :1 >:( :D =| ") :> ...."""
     tokens = EN(text)
-    assert tokens[0].string == ":o"
+    assert tokens[0].orth_ == ":o"
-    assert tokens[1].string == ":/"
+    assert tokens[1].orth_ == ":/"
-    assert tokens[2].string == ":'("
+    assert tokens[2].orth_ == ":'("
-    assert tokens[3].string == ">:o"
+    assert tokens[3].orth_ == ">:o"
-    assert tokens[4].string == "(:"
+    assert tokens[4].orth_ == "(:"
-    assert tokens[5].string == ":)"
+    assert tokens[5].orth_ == ":)"
-    assert tokens[6].string == ">.<"
+    assert tokens[6].orth_ == ">.<"
-    assert tokens[7].string == "XD"
+    assert tokens[7].orth_ == "XD"
-    assert tokens[8].string == "-__-"
+    assert tokens[8].orth_ == "-__-"
-    assert tokens[9].string == "o.O"
+    assert tokens[9].orth_ == "o.O"
-    assert tokens[10].string == ";D"
+    assert tokens[10].orth_ == ";D"
-    assert tokens[11].string == ":-)"
+    assert tokens[11].orth_ == ":-)"
-    assert tokens[12].string == "@_@"
+    assert tokens[12].orth_ == "@_@"
-    assert tokens[13].string == ":P"
+    assert tokens[13].orth_ == ":P"
-    assert tokens[14].string == "8D"
+    assert tokens[14].orth_ == "8D"
-    assert tokens[15].string == ":1"
+    assert tokens[15].orth_ == ":1"
-    assert tokens[16].string == ">:("
+    assert tokens[16].orth_ == ">:("
-    assert tokens[17].string == ":D"
+    assert tokens[17].orth_ == ":D"
-    assert tokens[18].string == "=|"
+    assert tokens[18].orth_ == "=|"
-    assert tokens[19].string == '")'
+    assert tokens[19].orth_ == '")'
-    assert tokens[20].string == ':>'
+    assert tokens[20].orth_ == ':>'
-    assert tokens[21].string == '....'
+    assert tokens[21].orth_ == '....'
 
 
 def test_false_positive(EN):

tests/test_pre_punct.py

@@ -21,8 +21,8 @@ def test_open(open_puncts, EN):
         string = p + word_str
         tokens = EN(string)
         assert len(tokens) == 2
-        assert tokens[0].string == p
+        assert tokens[0].orth_ == p
-        assert tokens[1].string == word_str
+        assert tokens[1].orth_ == word_str
 
 
 def test_two_different_open(open_puncts, EN):
@@ -31,9 +31,9 @@ def test_two_different_open(open_puncts, EN):
         string = p + "`" + word_str
         tokens = EN(string)
         assert len(tokens) == 3
-        assert tokens[0].string == p
+        assert tokens[0].orth_ == p
-        assert tokens[1].string == "`"
+        assert tokens[1].orth_ == "`"
-        assert tokens[2].string == word_str
+        assert tokens[2].orth_ == word_str
 
 
 def test_three_same_open(open_puncts, EN):
@@ -42,12 +42,12 @@ def test_three_same_open(open_puncts, EN):
         string = p + p + p + word_str
         tokens = EN(string)
         assert len(tokens) == 4
-        assert tokens[0].string == p
+        assert tokens[0].orth_ == p
-        assert tokens[3].string == word_str
+        assert tokens[3].orth_ == word_str
 
 
 def test_open_appostrophe(EN):
     string = "'The"
     tokens = EN(string)
     assert len(tokens) == 2
-    assert tokens[0].string == "'"
+    assert tokens[0].orth_ == "'"

tests/test_string_loading.py

@@ -13,9 +13,9 @@ def EN():
 
 def test_one(EN):
     tokens = EN('Betty Botter bought a pound of butter.')
-    assert tokens[0].string == 'Betty'
+    assert tokens[0].orth_ == 'Betty'
     tokens2 = EN('Betty also bought a pound of butter.')
-    assert tokens2[0].string == 'Betty'
+    assert tokens2[0].orth_ == 'Betty'
 
 
 

tests/test_surround_punct.py

@@ -21,9 +21,9 @@ def test_token(paired_puncts, EN):
         string = open_ + word_str + close_
         tokens = EN(string)
         assert len(tokens) == 3
-        assert tokens[0].string == open_
+        assert tokens[0].orth_ == open_
-        assert tokens[1].string == word_str
+        assert tokens[1].orth_ == word_str
-        assert tokens[2].string == close_
+        assert tokens[2].orth_ == close_
 
 
 def test_two_different(paired_puncts, EN):
@@ -32,9 +32,9 @@ def test_two_different(paired_puncts, EN):
         string = "`" + open_ + word_str + close_ + "'"
         tokens = EN(string)
         assert len(tokens) == 5
-        assert tokens[0].string == "`"
+        assert tokens[0].orth_ == "`"
-        assert tokens[1].string == open_
+        assert tokens[1].orth_ == open_
-        assert tokens[2].string == word_str
+        assert tokens[2].orth_ == word_str
-        assert tokens[2].string == word_str
+        assert tokens[2].orth_ == word_str
-        assert tokens[3].string == close_
+        assert tokens[3].orth_ == close_
-        assert tokens[4].string == "'"
+        assert tokens[4].orth_ == "'"

tests/test_tokenizer.py

@@ -12,22 +12,22 @@ def EN():
 
 def test_single_word(EN):
     tokens = EN(u'hello')
-    assert tokens[0].string == 'hello'
+    assert tokens[0].orth_ == 'hello'
 
 
 def test_two_words(EN):
     tokens = EN('hello possums')
     assert len(tokens) == 2
-    assert tokens[0].string != tokens[1].string
+    assert tokens[0].orth_ != tokens[1].orth_
 
 
 def test_punct(EN):
     tokens = EN('hello, possums.')
     assert len(tokens) == 4
-    assert tokens[0].string == 'hello'
+    assert tokens[0].orth_ == 'hello'
-    assert tokens[1].string == ','
+    assert tokens[1].orth_ == ','
-    assert tokens[2].string == 'possums'
+    assert tokens[2].orth_ == 'possums'
-    assert tokens[1].string != 'hello'
+    assert tokens[1].orth_ != 'hello'
 
 
 def test_digits(EN):
@@ -87,14 +87,14 @@ def test_cnts2(EN):
 def test_cnts3(EN):
     text = u"“Isn't it?”"
     tokens = EN(text)
-    words = [t.string for t in tokens]
+    words = [t.orth_ for t in tokens]
     assert len(words) == 6
 
 
 def test_cnts4(EN):
     text = u"""Yes! "I'd rather have a walk", Ms. Comble sighed. """
     tokens = EN(text)
-    words = [t.string for t in tokens]
+    words = [t.orth_ for t in tokens]
     assert len(words) == 15
 
 
@@ -107,13 +107,13 @@ def test_cnts5(EN):
 def test_cnts6(EN):
     text = u'They ran about 10km.'
     tokens = EN(text)
-    words = [t.string for t in tokens]
+    words = [t.orth_ for t in tokens]
     assert len(words) == 6
 
 def test_bracket_period(EN):
     text = u'(And a 6a.m. run through Washington Park).'
     tokens = EN(text)
-    assert tokens[len(tokens) - 1].string == u'.'
+    assert tokens[len(tokens) - 1].orth_ == u'.'
 
 #def test_cnts7():
 #    text = 'But then the 6,000-year ice age came...'

tests/test_tokens_from_list.py

@@ -13,4 +13,4 @@ def test1(EN):
     words = ['JAPAN', 'GET', 'LUCKY']
     tokens = EN.tokenizer.tokens_from_list(words)
     assert len(tokens) == 3
-    assert tokens[0].string == 'JAPAN'
+    assert tokens[0].orth_ == 'JAPAN'

tests/test_whitespace.py

@@ -18,7 +18,7 @@ def test_single_space(EN):
 def test_double_space(EN):
     tokens = EN('hello  possums')
     assert len(tokens) == 3
-    assert tokens[1].string == ' '
+    assert tokens[1].orth_ == ' '
 
 
 def test_newline(EN):