include data from xc rebuild

README.md

@@ -48,13 +48,13 @@ frequency as a decimal between 0 and 1.
     1.07e-05
 
     >>> word_frequency('café', 'en')
-    5.89e-06
+    5.75e-06
 
     >>> word_frequency('cafe', 'fr')
     1.51e-06
 
     >>> word_frequency('café', 'fr')
-    5.25e-05
+    5.13e-05
 
 
 `zipf_frequency` is a variation on `word_frequency` that aims to return the
@@ -78,10 +78,10 @@ one occurrence per billion words.
     5.29
 
     >>> zipf_frequency('frequency', 'en')
-    4.42
+    4.43
 
     >>> zipf_frequency('zipf', 'en')
-    1.55
+    1.57
 
     >>> zipf_frequency('zipf', 'en', wordlist='small')
     0.0
@@ -300,7 +300,7 @@ into multiple tokens:
     >>> zipf_frequency('New York', 'en')
     5.28
     >>> zipf_frequency('北京地铁', 'zh')  # "Beijing Subway"
-    3.57
+    3.61
 
 The word frequencies are combined with the half-harmonic-mean function in order
 to provide an estimate of what their combined frequency would be. In Chinese,

tests/test_at_sign.py

@@ -41,6 +41,14 @@ def test_gender_neutral_at():
     assert tokenize(text, "en") == ["@s", "membr@s", "da", "comunidade", "virtual"]
 
 
+def test_at_in_corpus():
+    # We have a word frequency for "l@s"
+    assert word_frequency('l@s', 'es') > 0
+
+    # It's not just treated as a word break
+    assert word_frequency('l@s', 'es') < word_frequency('l s', 'es')
+
+
 def test_punctuation_at():
     # If the @ appears alone in a word, we consider it to be punctuation
     text = "operadores de canal, que são aqueles que têm um @ ao lado do nick"

tests/test_chinese.py

@@ -59,7 +59,7 @@ def test_tokens():
 
 def test_combination():
     xiexie_freq = word_frequency('谢谢', 'zh')   # "Thanks"
-    assert word_frequency('谢谢谢谢', 'zh') == pytest.approx(xiexie_freq / 20)
+    assert word_frequency('谢谢谢谢', 'zh') == pytest.approx(xiexie_freq / 20, rel=0.01)
 
 
 def test_alternate_codes():