From 606879b217b0b1eb96f29386c1284e7f57d76e30 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Sun, 28 May 2017 19:42:44 +0200
Subject: [PATCH] Update hash strings examples

---
 website/docs/api/stringstore.jade          |  6 ++++--
 website/docs/usage/entity-recognition.jade | 19 ++++++++++---------
 website/docs/usage/lightning-tour.jade     | 16 +++++++++++-----
 website/docs/usage/v2.jade                 |  5 +++--
 4 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/website/docs/api/stringstore.jade b/website/docs/api/stringstore.jade
index 0665f6060..969c8a6a5 100644
--- a/website/docs/api/stringstore.jade
+++ b/website/docs/api/stringstore.jade
@@ -113,9 +113,11 @@ p Add a string to the #[code StringStore].
 
 +aside-code("Example").
     stringstore = StringStore([u'apple', u'orange'])
-    stringstore.add(u'banana')
+    banana_hash = stringstore.add(u'banana')
     assert len(stringstore) == 3
-    assert stringstore[u'banana'] == 2525716904149915114L
+    assert banana_hash == 2525716904149915114L
+    assert stringstore[banana_hash] == u'banana'
+    assert stringstore[u'banana'] == banana_hash
 
 +table(["Name", "Type", "Description"])
     +row
diff --git a/website/docs/usage/entity-recognition.jade b/website/docs/usage/entity-recognition.jade
index f9bfd4df9..f33ef70df 100644
--- a/website/docs/usage/entity-recognition.jade
+++ b/website/docs/usage/entity-recognition.jade
@@ -52,15 +52,15 @@ p
     assert ent_san == [u'San', u'B', u'GPE']
     assert ent_francisco == [u'Francisco', u'I', u'GPE']
 
-+table(["Text", "ent_iob", "ent_iob_", "ent_type", "ent_type_", "Description"])
++table(["Text", "ent_iob", "ent_iob_", "ent_type_", "Description"])
     - var style = [0, 1, 1, 1, 1, 0]
-    +annotation-row(["San", 3, "B", 381, "GPE", "beginning of an entity"], style)
-    +annotation-row(["Francisco", 1, "I", 381, "GPE", "inside an entity"], style)
-    +annotation-row(["considers", 2, "O", 0, '""', "outside an entity"], style)
-    +annotation-row(["banning", 2, "O", 0, '""', "outside an entity"], style)
-    +annotation-row(["sidewalk", 2, "O", 0, '""', "outside an entity"], style)
-    +annotation-row(["delivery", 2, "O", 0, '""', "outside an entity"], style)
-    +annotation-row(["robots", 2, "O", 0, '""', "outside an entity"], style)
+    +annotation-row(["San", 3, "B", "GPE", "beginning of an entity"], style)
+    +annotation-row(["Francisco", 1, "I", "GPE", "inside an entity"], style)
+    +annotation-row(["considers", 2, "O", '""', "outside an entity"], style)
+    +annotation-row(["banning", 2, "O", '""', "outside an entity"], style)
+    +annotation-row(["sidewalk", 2, "O", '""', "outside an entity"], style)
+    +annotation-row(["delivery", 2, "O", '""', "outside an entity"], style)
+    +annotation-row(["robots", 2, "O", '""', "outside an entity"], style)
 
 +h(2, "setting") Setting entity annotations
 
@@ -148,6 +148,8 @@ include ../api/_annotation/_named-entities
 
 +h(2, "updating") Training and updating
 
++under-construction
+
 p
     |  To provide training examples to the entity recogniser, you'll first need
     |  to create an instance of the #[+api("goldparse") #[code GoldParse]] class.
@@ -173,7 +175,6 @@ p
 
             nlp.tagger(doc)
             ner.update(doc, gold)
-    ner.model.end_training()
 
 p
     |  If a character offset in your entity annotations don't fall on a token
diff --git a/website/docs/usage/lightning-tour.jade b/website/docs/usage/lightning-tour.jade
index a87e763a6..f144b4f05 100644
--- a/website/docs/usage/lightning-tour.jade
+++ b/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', 94]
-    assert [apple.tag_, apple.tag] == [u'NNP', 475]
-    assert [apple.shape_, apple.shape] == [u'Xxxxx', 684]
+    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.is_alpha == True
     assert apple.is_punct == False
 
@@ -78,10 +78,16 @@ p
     assert doc[2].orth == coffee_hash == 3197928453018144401L
     assert doc[2].text == coffee_text == u'coffee'
 
-    doc.vocab.strings.add(u'beer')
-    beer_hash = doc.vocab.strings[u'beer'] # 3073001599257881079L
+    beer_hash = doc.vocab.strings.add(u'beer') # 3073001599257881079L
     beer_text = doc.vocab.strings[beer_hash] # 'beer'
 
+    unicorn_hash = doc.vocab.strings.add(u'🦄 ') # 18234233413267120783L
+    unicorn_text = doc.vocab.strings[unicorn_hash] # '🦄 '
+
++infobox
+    |  #[strong API:] #[+api("stringstore") #[code stringstore]]
+    |  #[strong Usage:] #[+a("/docs/usage/spacy-101#vocab") Vocab, hashes and lexemes 101]
+
 +h(2, "examples-entities") Recongnise and update named entities
     +tag-model("NER")
 
diff --git a/website/docs/usage/v2.jade b/website/docs/usage/v2.jade
index c28863d6c..7b9f282a6 100644
--- a/website/docs/usage/v2.jade
+++ b/website/docs/usage/v2.jade
@@ -57,8 +57,9 @@ p
     assert doc.vocab.strings[u'coffee'] == 3197928453018144401L
     assert doc.vocab.strings[3197928453018144401L] == u'coffee'
 
-    doc.vocab.strings.add(u'beer')
-    assert doc.vocab.strings[u'beer'] == 3073001599257881079L
+    beer_hash = doc.vocab.strings.add(u'beer')
+    assert doc.vocab.strings[u'beer'] == beer_hash
+    assert doc.vocab.strings[beer_hash] == u'beer'
 
 p
     |  The #[+api("stringstore") #[code StringStore]] now resolves all strings