Merge branch 'develop' of https://github.com/explosion/spaCy into develop

spacy/lang/es/__init__.py

@@ -5,6 +5,7 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .tag_map import TAG_MAP
 from .stop_words import STOP_WORDS
 from .lemmatizer import LOOKUP
+from .syntax_iterators import SYNTAX_ITERATORS
 
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
 from ..norm_exceptions import BASE_NORMS
@@ -22,6 +23,7 @@ class SpanishDefaults(Language.Defaults):
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
     tag_map = dict(TAG_MAP)
     stop_words = set(STOP_WORDS)
+    sytax_iterators = dict(SYNTAX_ITERATORS)
 
     @classmethod
     def create_lemmatizer(cls, nlp=None):

spacy/util.py

@@ -478,7 +478,7 @@ def print_table(data, title=None):
     if isinstance(data, dict):
         data = list(data.items())
     tpl_row = '    {:<15}' * len(data[0])
-    table = '\n'.join([tpl_row.format(l, v) for l, v in data])
+    table = '\n'.join([tpl_row.format(l, unicode_(v)) for l, v in data])
     if title:
         print('\n    \033[93m{}\033[0m'.format(title))
     print('\n{}\n'.format(table))
@@ -491,11 +491,12 @@ def print_markdown(data, title=None):
     title (unicode or None): Title, will be rendered as headline 2.
     """
     def excl_value(value):
-        return Path(value).exists() # contains path (personal info)
+        # contains path, i.e. personal info
+        return isinstance(value, basestring_) and Path(value).exists()
 
     if isinstance(data, dict):
         data = list(data.items())
-    markdown = ["* **{}:** {}".format(l, v) for l, v in data if not excl_value(v)]
+    markdown = ["* **{}:** {}".format(l, unicode_(v)) for l, v in data if not excl_value(v)]
     if title:
         print("\n## {}".format(title))
     print('\n{}\n'.format('\n'.join(markdown)))

website/docs/usage/_spacy-101/_language-data.jade

@@ -78,6 +78,14 @@ p
             |  #[code like_num], which includes language-specific words like "ten"
             |  or "hundred".
 
+    +row
+        +cell #[strong Syntax iterators]
+            |  #[+src(gh("spaCy", "spacy/lang/en/syntax_iterators.py")) syntax_iterators.py]
+        +cell
+            |  Functions that compute views of a #[code Doc] object based on its
+            |  syntax. At the moment, only used for
+            |  #[+a("/docs/usage/dependency-parse#noun-chunks") noun chunks].
+
     +row
         +cell #[strong Lemmatizer]
             |  #[+src(gh("spacy-dev-resources", "templates/new_language/lemmatizer.py")) lemmatizer.py]