Merge branch 'master' into spacy.io

setup.py

@@ -265,6 +265,7 @@ def setup_package():
                 # Language tokenizers with external dependencies
                 "ja": ["mecab-python3==0.7"],
                 "ko": ["natto-py==0.9.0"],
+                "th": ["pythainlp>=2.0"],
             },
             python_requires=">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*",
             classifiers=[

website/meta/universe.json

@@ -1715,7 +1715,36 @@
                 "\tprint(ent.text, ent.start_char, ent.end_char, ent.label_)"
             ],
             "author": "Stefan Daniel Dumitrescu, Andrei-Marius Avram"
+        },
+        {
+            "id": "num_fh",
+            "title": "Numeric Fused-Head",
+            "slogan": "Numeric Fused-Head Identificaiton and Resolution in English",
+            "description": "This package provide a wrapper for the Numeric Fused-Head in English. It provides another information layer on numbers that refer to another entity which is not obvious from the syntactic tree.",
+            "github": "yanaiela/num_fh",
+            "pip": "num_fh",
+            "category": ["pipeline", "research"],
+            "code_example": [
+                "import spacy",
+                "from num_fh import NFH",
+                "nlp = spacy.load('en_core_web_sm')",
+                "nfh = NFH(nlp)",
+                "nlp.add_pipe(nfh, first=False)",
+                "doc = nlp(\"I told you two, that only one of them is the one who will get 2 or 3 icecreams\")",
+                "",
+                "assert doc[16]._.is_nfh == True",
+                "assert doc[18]._.is_nfh == False",
+                "assert doc[3]._.is_deter_nfh == True",
+                "assert doc[16]._.is_deter_nfh == False",
+                "assert len(doc._.nfh) == 4",
+            ],
+            "author": "Yanai Elazar",
+            "author_links": {
+                "github": "yanaiela",
+                "twitter": "yanaiela",
+                "website": "https://yanaiela.github.io"
             }
+        },
     ],
 
     "categories": [