Translate NBSP to and from its UD escape code (UniversalDependencies/…

…docs#982)

stanza/server/java_protobuf_requests.py

@@ -329,6 +329,8 @@ def space_after_to_misc(space):
             spaces.append('\\p')
         elif char == '\\':
             spaces.append('\\\\')
+        elif char == ' ':
+            spaces.append('\\u00A0')
         else:
             spaces.append(char)
     space_after = "".join(spaces)
@@ -380,9 +382,9 @@ def misc_to_space_after(misc):
                 elif misc_space[pos:pos+2] == '\\\\':
                     spaces.append('\\')
                     pos += 2
-                elif misc_space[pos:pos+3] == '" "':
+                elif misc_space[pos:pos+6] == '\\u00A0':
                     spaces.append(' ')
-                    pos += 3
+                    pos += 6
                 else:
                     spaces.append(misc_space[pos])
                     pos += 1

stanza/tests/server/test_java_protobuf_requests.py

@@ -55,3 +55,35 @@ def test_convert_networkx_graph():
     edges = sorted(edges)
     expected_edges = [(1, 'cc'), (3, 'obl'), (5, 'advmod'), (6, 'obl'), (7, 'punct')]
     assert edges == expected_edges
+
+ENGLISH_NBSP_SAMPLE="""
+# sent_id = newsgroup-groups.google.com_n3td3v_e874a1e5eb995654_ENG_20060120_052200-0011
+# text = Please note that neither the e-mail address nor name of the sender have been verified.
+1	Please	please	INTJ	UH	_	2	discourse	_	_
+2	note	note	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
+3	that	that	SCONJ	IN	_	15	mark	_	_
+4	neither	neither	CCONJ	CC	_	7	cc:preconj	_	_
+5	the	the	DET	DT	Definite=Def|PronType=Art	7	det	_	_
+6	e-mail	e-mail	NOUN	NN	Number=Sing	7	compound	_	_
+7	address	address	NOUN	NN	Number=Sing	15	nsubj:pass	_	_
+8	nor	nor	CCONJ	CC	_	9	cc	_	_
+9	name	name	NOUN	NN	Number=Sing	7	conj	_	_
+10	of	of	ADP	IN	_	12	case	_	_
+11	the	the	DET	DT	Definite=Def|PronType=Art	12	det	_	_
+12	sender	sender	NOUN	NN	Number=Sing	7	nmod	_	_
+13	have	have	AUX	VBP	Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	15	aux	_	SpacesAfter=\\u00A0
+14	been	be	AUX	VBN	Tense=Past|VerbForm=Part	15	aux:pass	_	_
+15	verified	verify	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	2	ccomp	_	SpaceAfter=No
+16	.	.	PUNCT	.	_	2	punct	_	_
+""".lstrip()
+
+def test_nbsp_doc():
+    """
+    Test that the space conversion methods will convert to and from NBSP
+    """
+    doc = CoNLL.conll2doc(input_str=ENGLISH_NBSP_SAMPLE)
+
+    assert doc.sentences[0].text == "Please note that neither the e-mail address nor name of the sender have been verified."
+    assert doc.sentences[0].words[12].misc == "SpacesAfter=\\u00A0"
+    assert java_protobuf_requests.misc_to_space_after(doc.sentences[0].words[12].misc) == ' '
+    assert java_protobuf_requests.space_after_to_misc(' ') == "SpacesAfter=\\u00A0"