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

.gitignore

@@ -1,50 +1,43 @@
-# Vim
+# spaCy
-*.swp
+spacy/data/
-*.sw*
-Profile.prof
-tmp/
-.dev
-.denv
-.pypyenv
-.eggs
-*.tgz
-.sass-cache
-.python-version
-
-MANIFEST
-
 corpora/
 models/
 keys/
 
-spacy/syntax/*.cpp
+# Website
-spacy/syntax/*.html
+website/www/
-spacy/en/*.cpp
+website/_deploy.sh
-spacy/tokens/*.cpp
+website/package.json
-spacy/serialize/*.cpp
+website/announcement.jade
-spacy/en/data/*
+website/.gitignore
-spacy/*.cpp
-spacy/ner/*.cpp
-spacy/orthography/*.cpp
-ext/murmurhash.cpp
-ext/sparsehash.cpp
 
-/spacy/data/
+# Cython / C extensions
-
-_build/
-.env/
-tmp/
 cythonize.json
-
+spacy/*.html
-# Byte-compiled / optimized / DLL files
+*.cpp
-__pycache__/
-*.py[cod]
-
-# C extensions
 *.so
 
-# Distribution / packaging
+# Vim / VSCode / editors
+*.swp
+*.sw*
+Profile.prof
+.vscode
+.sass-cache
+
+# Python
 .Python
+.python-version
+__pycache__/
+*.py[cod]
+.env/
+.~env/
+.venv
+venv/
+.dev
+.denv
+.pypyenv
+
+# Distribution / packaging
 env/
 bin/
 build/
@@ -59,6 +52,12 @@ var/
 *.egg-info/
 .installed.cfg
 *.egg
+.eggs
+MANIFEST
+
+# Temporary files
+*.~*
+tmp/
 
 # Installer logs
 pip-log.txt
@@ -87,25 +86,16 @@ coverage.xml
 *.log
 *.pot
 
-# Windows local helper files
+# Windows
 *.bat
+Thumbs.db
+Desktop.ini
 
 # Mac OS X
 *.DS_Store
 
-# Temporary files / Dropbox hack
-*.~*
-
 # Komodo project files
 *.komodoproject
 
-# Website
+# Other
-website/_deploy.sh
+*.tgz
-website/package.json
-website/announcement.jade
-website/www/
-website/.gitignore
-
-# Python virtualenv
-venv
-venv/*

spacy/compat.py

@@ -16,6 +16,22 @@ try:
 except ImportError:
     import copyreg as copy_reg
 
+try:
+    from cupy.cuda.stream import Stream as CudaStream
+except ImportError:
+    CudaStream = None
+
+try:
+    import cupy
+except ImportError:
+    cupy = None
+
+
+pickle = pickle
+copy_reg = copy_reg
+CudaStream = CudaStream
+cupy = cupy
+fix_text = ftfy.fix_text
 
 is_python2 = six.PY2
 is_python3 = six.PY3
@@ -23,8 +39,6 @@ is_windows = sys.platform.startswith('win')
 is_linux = sys.platform.startswith('linux')
 is_osx = sys.platform == 'darwin'
 
-fix_text = ftfy.fix_text
-
 
 if is_python2:
     bytes_ = str

spacy/displacy/__init__.py

@@ -3,13 +3,14 @@ from __future__ import unicode_literals
 
 from .render import DependencyRenderer, EntityRenderer
 from ..tokens import Doc
-from ..util import prints
+from ..util import prints, is_in_jupyter
 
 
 _html = {}
+IS_JUPYTER = is_in_jupyter()
 
 
-def render(docs, style='dep', page=False, minify=False, jupyter=False, options={}):
+def render(docs, style='dep', page=False, minify=False, jupyter=IS_JUPYTER, options={}):
     """Render displaCy visualisation.
 
     docs (list or Doc): Document(s) to visualise.

spacy/util.py

@@ -11,20 +11,12 @@ import sys
 import textwrap
 
 from .symbols import ORTH
-from .compat import path2str, basestring_, input_, unicode_
+from .compat import cupy, CudaStream, path2str, basestring_, input_, unicode_
 
 
 LANGUAGES = {}
 _data_path = Path(__file__).parent / 'data'
-try:
-    from cupy.cuda.stream import Stream as CudaStream
-except ImportError:
-    CudaStream = None
 
-try:
-    import cupy
-except ImportError:
-    cupy = None
 
 def get_lang_class(lang):
     """Import and load a Language class.
@@ -151,6 +143,20 @@ def parse_package_meta(package_path, require=True):
         return None
 
 
+def is_in_jupyter():
+    """Check if user is in a Jupyter notebook. Mainly used for displaCy.
+
+    RETURNS (bool): True if in Jupyter, False if not.
+    """
+    try:
+        cfg = get_ipython().config
+        if cfg['IPKernelApp']['parent_appname'] == 'ipython-notebook':
+            return True
+    except NameError:
+        return False
+    return False
+
+
 def get_cuda_stream(require=False):
     # TODO: Error and tell to install chainer if not found
     # Requires GPU

website/assets/css/_components/_quickstart.sass

@@ -10,7 +10,10 @@
     padding: 2rem 3rem
 
 .c-quickstart__input
-    display: none
+    @include size(0)
+    opacity: 0
+    position: absolute
+    left: -9999px
 
 .c-quickstart__label
     cursor: pointer
@@ -25,6 +28,9 @@
     &:hover
         background: lighten($color-theme-light, 5)
 
+    .c-quickstart__input:focus + &
+        border: 1px solid $color-theme
+
     .c-quickstart__input--radio:checked + &
         color: $color-back
         border-color: $color-theme
@@ -36,8 +42,6 @@
         display: inline-block
         width: 20px
         height: 20px
-        position: relative
-        bottom: 0.2rem
         border: 1px solid $color-subtle
         vertical-align: middle
         margin-right: 1rem

website/assets/js/quickstart.js

@@ -4,4 +4,4 @@
  * @author Ines Montani <ines@ines.io>
  * @version 0.0.1
  * @license MIT
- */'use strict';var _createClass=function(){function a(b,c){for(var e,d=0;d<c.length;d++)e=c[d],e.enumerable=e.enumerable||!1,e.configurable=!0,'value'in e&&(e.writable=!0),Object.defineProperty(b,e.key,e)}return function(b,c,d){return c&&a(b.prototype,c),d&&a(b,d),b}}();function _toConsumableArray(a){if(Array.isArray(a)){for(var b=0,c=Array(a.length);b<a.length;b++)c[b]=a[b];return c}return Array.from(a)}function _classCallCheck(a,b){if(!(a instanceof b))throw new TypeError('Cannot call a class as a function')}var Quickstart=function(){function a(){var b=0<arguments.length&&void 0!==arguments[0]?arguments[0]:'#quickstart',d=arguments[1],c=2<arguments.length&&void 0!==arguments[2]?arguments[2]:{};_classCallCheck(this,a),this.container='string'==typeof b?this._$(b):b,this.groups=d,this.pfx=c.prefix||'qs',this.dpfx='data-'+this.pfx,this.init=this.init.bind(this),c.noInit||document.addEventListener('DOMContentLoaded',this.init)}return _createClass(a,[{key:'init',value:function init(){this.updateContainer(),this.container.style.display='block',this.container.classList.add(''+this.pfx);var b=this.groups;b instanceof Array?b.reverse().forEach(this.createGroup.bind(this)):this._$$('['+this.dpfx+'-group]').forEach(this.updateGroup.bind(this))}},{key:'initGroup',value:function initGroup(b,c){b.addEventListener('change',this.update.bind(this)),b.dispatchEvent(new CustomEvent('change',{detail:c}))}},{key:'updateGroup',value:function updateGroup(b){var c=b.getAttribute(this.dpfx+'-group'),d=this.createStyles(c);b.insertBefore(d,b.firstChild),this.initGroup(b,c)}},{key:'update',value:function update(b){var f=this,c=b.detail||b.target.name,d=this._$$('[name='+c+']').filter(function(h){return h.checked}).map(function(h){return h.value}),e=d.map(function(h){return':not(['+f.dpfx+'-'+c+'="'+h+'"])'}).join(''),g='['+this.dpfx+'-results]>['+this.dpfx+'-'+c+']'+e+' {display: none}';this._$('['+this.dpfx+'-style="'+c+'"]').textContent=g}},{key:'updateContainer',value:function updateContainer(){if(!this._$('['+this.dpfx+'-results]')){var b=this.childNodes(this.container,'pre'),c=b?b[0]:this._c('pre',this.pfx+'-code'),d=this.childNodes(c,'code')||this.childNodes(this.container,'code'),e=d?d[0]:this._c('code',this.pfx+'-results');e.setAttribute(this.dpfx+'-results','');var f=this.childNodes(e,'span')||this.childNodes(c,'span')||this.childNodes(this.container,'span');f&&f.forEach(function(g){return e.appendChild(g)}),c.appendChild(e),this.container.appendChild(c)}}},{key:'createGroup',value:function createGroup(b){var d=this,c=this._c('div',this.pfx+'-group');c.setAttribute(this.dpfx+'-group',b.id),c.innerHTML=this.createStyles(b.id).outerHTML,c.innerHTML+='<div class="'+this.pfx+'-legend">'+b.title+'</div>',c.innerHTML+='<div class="'+this.pfx+'-fields">'+b.options.map(function(e){var f=b.multiple?'checkbox':'radio';return'<input class="'+d.pfx+'-input '+d.pfx+'-input--'+f+'" type="'+f+'" name="'+b.id+'" id="'+e.id+'" value="'+e.id+'" '+(e.checked?'checked':'')+' /><label class="'+d.pfx+'-label" for="'+e.id+'">'+e.title+'</label>'}).join('')+'</div>',this.container.insertBefore(c,this.container.firstChild),this.initGroup(c,b.id)}},{key:'createStyles',value:function createStyles(b){var c=this._c('style');return c.setAttribute(this.dpfx+'-style',b),c.textContent='['+this.dpfx+'-results]>['+this.dpfx+'-'+b+'] {display: none}',c}},{key:'childNodes',value:function childNodes(b,c){var d=c.toUpperCase();if(!b.hasChildNodes)return!1;var e=[].concat(_toConsumableArray(b.childNodes)).filter(function(f){return f.nodeName===d});return!!e.length&&e}},{key:'_$',value:function _$(b){return document.querySelector(b)}},{key:'_$$',value:function _$$(b){return[].concat(_toConsumableArray(document.querySelectorAll(b)))}},{key:'_c',value:function _c(b,c){var d=document.createElement(b);return c&&(d.className=c),d}}]),a}();
+ */'use strict';var _createClass=function(){function a(b,c){for(var e,d=0;d<c.length;d++)e=c[d],e.enumerable=e.enumerable||!1,e.configurable=!0,'value'in e&&(e.writable=!0),Object.defineProperty(b,e.key,e)}return function(b,c,d){return c&&a(b.prototype,c),d&&a(b,d),b}}();function _toConsumableArray(a){if(Array.isArray(a)){for(var b=0,c=Array(a.length);b<a.length;b++)c[b]=a[b];return c}return Array.from(a)}function _classCallCheck(a,b){if(!(a instanceof b))throw new TypeError('Cannot call a class as a function')}var Quickstart=function(){function a(){var b=0<arguments.length&&void 0!==arguments[0]?arguments[0]:'#quickstart',d=arguments[1],c=2<arguments.length&&void 0!==arguments[2]?arguments[2]:{};_classCallCheck(this,a),this.container='string'==typeof b?this._$(b):b,this.groups=d,this.pfx=c.prefix||'qs',this.dpfx='data-'+this.pfx,this.init=this.init.bind(this),c.noInit||document.addEventListener('DOMContentLoaded',this.init)}return _createClass(a,[{key:'init',value:function init(){this.updateContainer(),this.container.style.display='block',this.container.classList.add(''+this.pfx);var b=this.groups;b instanceof Array?b.reverse().forEach(this.createGroup.bind(this)):this._$$('['+this.dpfx+'-group]').forEach(this.updateGroup.bind(this))}},{key:'initGroup',value:function initGroup(b,c){b.addEventListener('change',this.update.bind(this)),b.dispatchEvent(new CustomEvent('change',{detail:c}))}},{key:'updateGroup',value:function updateGroup(b){var c=b.getAttribute(this.dpfx+'-group'),d=this.createStyles(c);b.insertBefore(d,b.firstChild),this.initGroup(b,c)}},{key:'update',value:function update(b){var f=this,c=b.detail||b.target.name,d=this._$$('[name='+c+']:checked').map(function(h){return h.value}),e=d.map(function(h){return':not(['+f.dpfx+'-'+c+'="'+h+'"])'}).join(''),g='['+this.dpfx+'-results]>['+this.dpfx+'-'+c+']'+e+' {display: none}';this._$('['+this.dpfx+'-style="'+c+'"]').textContent=g}},{key:'updateContainer',value:function updateContainer(){if(!this._$('['+this.dpfx+'-results]')){var b=this.childNodes(this.container,'pre'),c=b?b[0]:this._c('pre',this.pfx+'-code'),d=this.childNodes(c,'code')||this.childNodes(this.container,'code'),e=d?d[0]:this._c('code',this.pfx+'-results');e.setAttribute(this.dpfx+'-results','');var f=this.childNodes(e,'span')||this.childNodes(c,'span')||this.childNodes(this.container,'span');f&&f.forEach(function(g){return e.appendChild(g)}),c.appendChild(e),this.container.appendChild(c)}}},{key:'createGroup',value:function createGroup(b){var d=this,c=this._c('fieldset',this.pfx+'-group');c.setAttribute(this.dpfx+'-group',b.id),c.innerHTML=this.createStyles(b.id).outerHTML,c.innerHTML+='<legend class="'+this.pfx+'-legend">'+b.title+'</legend>',c.innerHTML+=b.options.map(function(e){var f=b.multiple?'checkbox':'radio';return'<input class="'+d.pfx+'-input '+d.pfx+'-input--'+f+'" type="'+f+'" name="'+b.id+'" id="'+e.id+'" value="'+e.id+'" '+(e.checked?'checked':'')+' /><label class="'+d.pfx+'-label" for="'+e.id+'">'+e.title+'</label>'}).join(''),this.container.insertBefore(c,this.container.firstChild),this.initGroup(c,b.id)}},{key:'createStyles',value:function createStyles(b){var c=this._c('style');return c.setAttribute(this.dpfx+'-style',b),c.textContent='['+this.dpfx+'-results]>['+this.dpfx+'-'+b+'] {display: none}',c}},{key:'childNodes',value:function childNodes(b,c){var d=c.toUpperCase();if(!b.hasChildNodes)return!1;var e=[].concat(_toConsumableArray(b.childNodes)).filter(function(f){return f.nodeName===d});return!!e.length&&e}},{key:'_$',value:function _$(b){return document.querySelector(b)}},{key:'_$$',value:function _$$(b){return[].concat(_toConsumableArray(document.querySelectorAll(b)))}},{key:'_c',value:function _c(b,c){var d=document.createElement(b);return c&&(d.className=c),d}}]),a}();

website/docs/api/displacy.jade

@@ -101,9 +101,9 @@ p Render a dependency parse tree or named entity visualization.
         +cell #[code jupyter]
         +cell bool
         +cell
-            |  Returns markup using #[+a("http://jupyter.org/") Jupyter]'s
+            |  Explicitly enable "#[+a("http://jupyter.org/") Jupyter] mode" to
-            |  internal methods, ready to be rendered in a notebook.
+            |  return markup ready to be rendered in a notebook.
-        +cell #[code False]
+        +cell detected automatically
 
     +row
         +cell #[code options]

website/docs/usage/visualizers.jade

@@ -11,8 +11,12 @@ p
     |  process. Instead of printing a list of dependency labels or entity spans,
     |  you can simply pass your #[code Doc] objects to #[code displacy] and view
     |  the visualizations in your browser, or export them as HTML files or
-    |  vector graphics. displaCy also comes with a #[+a("#jupyter") Jupyter hook]
+    |  vector graphics.
-    |  that returns the markup in a format ready to be rendered in a notebook.
+
+p
+    |  If you're running a #[+a("https://jupyter.org") Jupyter] notebook,
+    |  displaCy will detect this and return the markup in a format
+    |  #[+a("#jupyter") ready to be rendered and exported].
 
 +aside("What about the old visualizers?")
     |  Our JavaScript-based visualizers #[+src(gh("displacy")) displacy.js] and
@@ -219,10 +223,10 @@ p
 +h(2, "jupyter") Using displaCy in Jupyter notebooks
 
 p
-    |  If you're working with a #[+a("https://jupyter.org") Jupyter] notebook,
+    |  displaCy is able to detect whether you're within a
-    |  you can use displaCy's "Jupyter mode" to return markup that can be
+    |  #[+a("https://jupyter.org") Jupyter] notebook, and will return markup
-    |  rendered in a cell straight away. When you export your notebook, the
+    |  that can be rendered in a cell straight away. When you export your
-    |  visualizations will be included as HTML.
+    |  notebook, the visualizations will be included as HTML.
 
 +code("Jupyter Example").
     # don't forget to install a model, e.g.: python -m spacy download en
@@ -230,10 +234,15 @@ p
     from spacy import displacy
 
     doc = nlp(u'Rats are various medium-sized, long-tailed rodents.')
-    displacy.render(doc, style='dep', jupyter=True)
+    displacy.render(doc, style='dep')
 
     doc2 = nlp(LONG_NEWS_ARTICLE)
-    displacy.render(doc2, style='ent', jupyter=True)
+    displacy.render(doc2, style='ent')
+
++aside("Enabling or disabling Jupyter mode")
+    |  To explicitly enable or disable "Jupyter mode", you can use the
+    |  #[code jupyter] keyword argument – e.g. to return raw HTML in a notebook,
+    |  or to force Jupyter rendering if auto-detection fails.
 
 +image("/assets/img/docs/displacy_jupyter.jpg", 700, false, "Example of using the displaCy dependency and named entity visualizer in a Jupyter notebook")