Merge pull request #1125 from Tpt/french_noun_chunks

Adds function to extract french noun chunks

spacy/lang/fr/__init__.py

@@ -5,6 +5,7 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
 from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
 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
@@ -24,6 +25,7 @@ class FrenchDefaults(Language.Defaults):
     infixes = tuple(TOKENIZER_INFIXES)
     suffixes = tuple(TOKENIZER_SUFFIXES)
     token_match = TOKEN_MATCH
+    syntax_iterators = dict(SYNTAX_ITERATORS)
 
     @classmethod
     def create_lemmatizer(cls, nlp=None):

spacy/lang/fr/syntax_iterators.py

@@ -0,0 +1,42 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from ...symbols import NOUN, PROPN, PRON
+
+
+def noun_chunks(obj):
+    """
+    Detect base noun phrases from a dependency parse. Works on both Doc and Span.
+    """
+    labels = ['nsubj', 'nsubj:pass', 'obj', 'iobj', 'ROOT', 'appos', 'nmod', 'nmod:poss']
+    doc = obj.doc  # Ensure works on both Doc and Span.
+    np_deps = [doc.vocab.strings[label] for label in labels]
+    conj = doc.vocab.strings.add('conj')
+    np_label = doc.vocab.strings.add('NP')
+    seen = set()
+    for i, word in enumerate(obj):
+        if word.pos not in (NOUN, PROPN, PRON):
+            continue
+        # Prevent nested chunks from being produced
+        if word.i in seen:
+            continue
+        if word.dep in np_deps:
+            if any(w.i in seen for w in word.subtree):
+                continue
+            seen.update(j for j in range(word.left_edge.i, word.right_edge.i+1))
+            yield word.left_edge.i, word.right_edge.i+1, np_label
+        elif word.dep == conj:
+            head = word.head
+            while head.dep == conj and head.head.i < head.i:
+                head = head.head
+            # If the head is an NP, and we're coordinated to it, we're an NP
+            if head.dep in np_deps:
+                if any(w.i in seen for w in word.subtree):
+                    continue
+                seen.update(j for j in range(word.left_edge.i, word.right_edge.i+1))
+                yield word.left_edge.i, word.right_edge.i+1, np_label
+
+
+SYNTAX_ITERATORS = {
+    'noun_chunks': noun_chunks
+}

spacy/syntax/iterators.pyx

@@ -110,5 +110,35 @@ def es_noun_chunks(obj):
         token = next_token(token)
 
 
+def french_noun_chunks(obj):
+    labels = ['nsubj', 'nsubj:pass', 'obj', 'iobj', 'ROOT', 'appos', 'nmod', 'nmod:poss']
+    doc = obj.doc  # Ensure works on both Doc and Span.
+    np_deps = [doc.vocab.strings[label] for label in labels]
+    conj = doc.vocab.strings.add('conj')
+    np_label = doc.vocab.strings.add('NP')
+    seen = set()
+    for i, word in enumerate(obj):
+        if word.pos not in (NOUN, PROPN, PRON):
+            continue
+        # Prevent nested chunks from being produced
+        if word.i in seen:
+            continue
+        if word.dep in np_deps:
+            if any(w.i in seen for w in word.subtree):
+                continue
+            seen.update(j for j in range(word.left_edge.i, word.right_edge.i+1))
+            yield word.left_edge.i, word.right_edge.i+1, np_label
+        elif word.dep == conj:
+            head = word.head
+            while head.dep == conj and head.head.i < head.i:
+                head = head.head
+            # If the head is an NP, and we're coordinated to it, we're an NP
+            if head.dep in np_deps:
+                if any(w.i in seen for w in word.subtree):
+                    continue
+                seen.update(j for j in range(word.left_edge.i, word.right_edge.i+1))
+                yield word.left_edge.i, word.right_edge.i+1, np_label
+
+
 CHUNKERS = {'en': english_noun_chunks, 'de': german_noun_chunks,
-            'es': es_noun_chunks}
+            'es': es_noun_chunks, 'fr': french_noun_chunks}