Fix typos, long integers and tests

spacy/tests/test_matcher.py

@@ -20,6 +20,40 @@ def matcher(en_vocab):
     return matcher
 
 
+def test_matcher_from_api_docs(en_vocab):
+    matcher = Matcher(en_vocab)
+    pattern = [{'ORTH': 'test'}]
+    assert len(matcher) == 0
+    matcher.add('Rule', None, pattern)
+    assert len(matcher) == 1
+    matcher.remove('Rule')
+    assert 'Rule' not in matcher
+    matcher.add('Rule', None, pattern)
+    assert 'Rule' in matcher
+    on_match, patterns = matcher.get('Rule')
+    assert len(patterns[0])
+
+
+def test_matcher_from_usage_docs(en_vocab):
+    text = "Wow 😀 This is really cool! 😂 😂"
+    doc = get_doc(en_vocab, words=text.split(' '))
+    pos_emoji = [u'😀', u'😃', u'😂', u'🤣', u'😊', u'😍']
+    pos_patterns = [[{'ORTH': emoji}] for emoji in pos_emoji]
+
+    def label_sentiment(matcher, doc, i, matches):
+        match_id, start, end = matches[i]
+        if doc.vocab.strings[match_id] == 'HAPPY':
+            doc.sentiment += 0.1
+        span = doc[start : end]
+        token = span.merge(norm='happy emoji')
+
+    matcher = Matcher(en_vocab)
+    matcher.add('HAPPY', label_sentiment, *pos_patterns)
+    matches = matcher(doc)
+    assert doc.sentiment != 0
+    assert doc[1].norm_ == 'happy emoji'
+
+
 @pytest.mark.parametrize('words', [["Some", "words"]])
 def test_matcher_init(en_vocab, words):
     matcher = Matcher(en_vocab)

website/docs/api/matcher.jade

@@ -5,7 +5,6 @@ include ../../_includes/_mixins
 p Match sequences of tokens, based on pattern rules.
 
 +infobox("⚠️ Deprecation note")
-    .o-block
     |  As of spaCy 2.0, #[code Matcher.add_pattern] and #[code Matcher.add_entity]
     |  are deprecated and have been replaced with a simpler
     |  #[+api("matcher#add") #[code Matcher.add]] that lets you add a list of
@@ -146,9 +145,9 @@ p Check whether the matcher contains rules for a match ID.
 
 +aside-code("Example").
     matcher = Matcher(nlp.vocab)
-    assert 'Rule' in matcher == False
+    assert 'Rule' not in matcher
     matcher.add('Rule', None, [{'ORTH': 'test'}])
-    assert 'Rule' in matcher == True
+    assert 'Rule' in matcher
 
 +table(["Name", "Type", "Description"])
     +row
@@ -226,9 +225,9 @@ p
 
 +aside-code("Example").
     matcher.add('Rule', None, [{'ORTH': 'test'}])
-    assert 'Rule' in matcher == True
+    assert 'Rule' in matcher
     matcher.remove('Rule')
-    assert 'Rule' in matcher == False
+    assert 'Rule' not in matcher
 
 +table(["Name", "Type", "Description"])
     +row
@@ -248,8 +247,7 @@ p
 +aside-code("Example").
     pattern = [{'ORTH': 'test'}]
     matcher.add('Rule', None, pattern)
-    (on_match, patterns) = matcher.get('Rule')
-    assert patterns = [pattern]
+    on_match, patterns = matcher.get('Rule')
 
 +table(["Name", "Type", "Description"])
     +row

website/docs/api/stringstore.jade

@@ -51,7 +51,7 @@ p Retrieve a string from a given hash, or vice versa.
 +aside-code("Example").
     stringstore = StringStore([u'apple', u'orange'])
     apple_hash = stringstore[u'apple']
-    assert apple_hash == 8566208034543834098L
+    assert apple_hash == 8566208034543834098
     assert stringstore[apple_hash] == u'apple'
 
 +table(["Name", "Type", "Description"])
@@ -72,8 +72,8 @@ p Check whether a string is in the store.
 
 +aside-code("Example").
     stringstore = StringStore([u'apple', u'orange'])
-    assert u'apple' in stringstore == True
-    assert u'cherry' in stringstore == False
+    assert u'apple' in stringstore
+    assert not u'cherry' in stringstore
 
 +table(["Name", "Type", "Description"])
     +row
@@ -115,7 +115,7 @@ p Add a string to the #[code StringStore].
     stringstore = StringStore([u'apple', u'orange'])
     banana_hash = stringstore.add(u'banana')
     assert len(stringstore) == 3
-    assert banana_hash == 2525716904149915114L
+    assert banana_hash == 2525716904149915114
     assert stringstore[banana_hash] == u'banana'
     assert stringstore[u'banana'] == banana_hash
 
@@ -215,3 +215,25 @@ p Load state from a binary string.
         +cell returns
         +cell #[code StringStore]
         +cell The #[code StringStore] object.
+
++h(2, "util") Utilities
+
++h(3, "hash_string") strings.hash_string
+    +tag function
+
+p Get a 64-bit hash for a given string.
+
++aside-code("Example").
+    from spacy.strings import hash_string
+    assert hash_string(u'apple') == 8566208034543834098
+
++table(["Name", "Type", "Description"])
+    +row
+        +cell #[code string]
+        +cell unicode
+        +cell The string to hash.
+
+    +footrow
+        +cell returns
+        +cell uint64
+        +cell The hash.

website/docs/api/vocab.jade

@@ -34,10 +34,10 @@ p Create the vocabulary.
 
     +row
         +cell #[code strings]
-        +cell #[code StringStore]
+        +cell #[code StringStore] or list
         +cell
-            |  A #[code StringStore] that maps strings to hash values, and vice
-            |  versa.
+            |  A #[+api("stringstore") #[code StringStore]] that maps
+            |  strings to hash values, and vice versa, or a list of strings.
 
     +footrow
         +cell returns

website/docs/usage/_spacy-101/_vocab.jade

@@ -5,7 +5,7 @@ p
     |  #[+api("vocab") #[code Vocab]], that will be
     |  #[strong shared by multiple documents]. To save memory, spaCy also
     |  encodes all strings to #[strong hash values] – in this case for example,
-    |  "coffee" has the hash #[code 3197928453018144401L]. Entity labels like
+    |  "coffee" has the hash #[code 3197928453018144401]. Entity labels like
     |  "ORG" and part-of-speech tags like "VERB" are also encoded. Internally,
     |  spaCy only "speaks" in hash values.
 
@@ -17,7 +17,7 @@ p
     |  #[strong Doc]: A processed container of tokens in context.#[br]
     |  #[strong Vocab]: The collection of lexemes.#[br]
     |  #[strong StringStore]: The dictionary mapping hash values to strings, for
-    |  example #[code 3197928453018144401L] → "coffee".
+    |  example #[code 3197928453018144401] → "coffee".
 
 +image
     include ../../../assets/img/docs/vocab_stringstore.svg
@@ -35,8 +35,8 @@ p
 
 +code.
     doc = nlp(u'I like coffee')
-    assert doc.vocab.strings[u'coffee'] == 3197928453018144401L
-    assert doc.vocab.strings[3197928453018144401L] == u'coffee'
+    assert doc.vocab.strings[u'coffee'] == 3197928453018144401
+    assert doc.vocab.strings[3197928453018144401] == u'coffee'
 
 p
     |  Now that all strings are encoded, the entries in the vocabulary
@@ -65,9 +65,9 @@ p
 
 +table(["text", "orth", "shape", "prefix", "suffix", "is_alpha", "is_digit"])
     - var style = [0, 1, 1, 0, 0, 1, 1]
-    +annotation-row(["I", "4690420944186131903L", "X", "I", "I", true, false], style)
-    +annotation-row(["love", "3702023516439754181L", "xxxx", "l", "ove", true, false], style)
-    +annotation-row(["coffee", "3197928453018144401L", "xxxx", "c", "ffe", true, false], style)
+    +annotation-row(["I", "4690420944186131903", "X", "I", "I", true, false], style)
+    +annotation-row(["love", "3702023516439754181", "xxxx", "l", "ove", true, false], style)
+    +annotation-row(["coffee", "3197928453018144401", "xxxx", "c", "ffe", true, false], style)
 
 p
     |  The mapping of words to hashes doesn't depend on any state. To make sure
@@ -79,7 +79,7 @@ p
 
 p
     |  However, hashes #[strong cannot be reversed] and there's no way to
-    |  resolve #[code 3197928453018144401L] back to "coffee". All spaCy can do
+    |  resolve #[code 3197928453018144401] back to "coffee". All spaCy can do
     |  is look it up in the vocabulary. That's why you always need to make
     |  sure all objects you create have access to the same vocabulary. If they
     |  don't, spaCy might not be able to find the strings it needs.
@@ -89,17 +89,17 @@ p
     from spacy.vocab import Vocab
 
     doc = nlp(u'I like coffee') # original Doc
-    assert doc.vocab.strings[u'coffee'] == 3197928453018144401L # get hash
-    assert doc.vocab.strings[3197928453018144401L] == u'coffee' # 👍
+    assert doc.vocab.strings[u'coffee'] == 3197928453018144401 # get hash
+    assert doc.vocab.strings[3197928453018144401] == u'coffee' # 👍
 
     empty_doc = Doc(Vocab()) # new Doc with empty Vocab
-    # doc.vocab.strings[3197928453018144401L] will raise an error :(
+    # doc.vocab.strings[3197928453018144401] will raise an error :(
 
     empty_doc.vocab.strings.add(u'coffee') # add "coffee" and generate hash
-    assert doc.vocab.strings[3197928453018144401L] == u'coffee' # 👍
+    assert doc.vocab.strings[3197928453018144401] == u'coffee' # 👍
 
     new_doc = Doc(doc.vocab) # create new doc with first doc's vocab
-    assert doc.vocab.strings[3197928453018144401L] == u'coffee' # 👍
+    assert doc.vocab.strings[3197928453018144401] == u'coffee' # 👍
 
 p
     |  If the vocabulary doesn't contain a hash for "coffee", spaCy will

website/docs/usage/lightning-tour.jade

@@ -53,9 +53,9 @@ p
 +code.
     doc = nlp(u'Apple is looking at buying U.K. startup for $1 billion')
     apple = doc[0]
-    assert [apple.pos_, apple.pos] == [u'PROPN', 17049293600679659579L]
-    assert [apple.tag_, apple.tag] == [u'NNP', 15794550382381185553L]
-    assert [apple.shape_, apple.shape] == [u'Xxxxx', 16072095006890171862L]
+    assert [apple.pos_, apple.pos] == [u'PROPN', 17049293600679659579]
+    assert [apple.tag_, apple.tag] == [u'NNP', 15794550382381185553]
+    assert [apple.shape_, apple.shape] == [u'Xxxxx', 16072095006890171862]
     assert apple.is_alpha == True
     assert apple.is_punct == False
 
@@ -72,16 +72,16 @@ p
 
 +code.
     doc = nlp(u'I love coffee')
-    coffee_hash = nlp.vocab.strings[u'coffee'] # 3197928453018144401L
+    coffee_hash = nlp.vocab.strings[u'coffee'] # 3197928453018144401
     coffee_text = nlp.vocab.strings[coffee_hash] # 'coffee'
 
-    assert doc[2].orth == coffee_hash == 3197928453018144401L
+    assert doc[2].orth == coffee_hash == 3197928453018144401
     assert doc[2].text == coffee_text == u'coffee'
 
-    beer_hash = doc.vocab.strings.add(u'beer') # 3073001599257881079L
+    beer_hash = doc.vocab.strings.add(u'beer') # 3073001599257881079
     beer_text = doc.vocab.strings[beer_hash] # 'beer'
 
-    unicorn_hash = doc.vocab.strings.add(u'🦄 ') # 18234233413267120783L
+    unicorn_hash = doc.vocab.strings.add(u'🦄 ') # 18234233413267120783
     unicorn_text = doc.vocab.strings[unicorn_hash] # '🦄 '
 
 +infobox