When rebuilding sentence text in ssurgeon, use the parent's SpaceAfter=No field for a word which is part of an MWT

Author: AngledLuffa

stanza/server/ssurgeon.py

@@ -146,6 +146,8 @@ def convert_response_to_doc(doc, semgrex_response):
         mwt_tokens = []
         for word_start_idx, word in enumerate(tokens):
             if not word["is_first_mwt"]:
+                if word["is_mwt"]:
+                    word[MISC] = None
                 mwt_tokens.append(word)
                 continue
             word_end_idx = word_start_idx + 1
@@ -159,6 +161,7 @@ def convert_response_to_doc(doc, semgrex_response):
                 # use the SpaceAfter=No (or not) from the last word in the token
                 MISC: tokens[word_end_idx-1][MISC],
             }
+            word[MISC] = None
             mwt_tokens.append(mwt_token_entry)
             mwt_tokens.append(word)
 
@@ -167,7 +170,11 @@ def convert_response_to_doc(doc, semgrex_response):
 
         # TODO: look at word.parent to see if it is part of an MWT
         # once that's done, the beginning words of an MWT do not need SpaceAfter=No any more (it is implied)
-        word_text = [word.text if (word_idx == len(sentence.words) - 1 or (word.misc and "SpaceAfter=No" in word.misc)) else word.text + " "
+        word_text = [word.text if (word_idx == len(sentence.words) - 1 or
+                                   (word.misc and "SpaceAfter=No" in word.misc) or
+                                   word.id != word.parent.id[-1] or
+                                   (word.parent.misc and "SpaceAfter=No" in word.parent.misc))
+                     else word.text + " "
                      for word_idx, word in enumerate(sentence.words)]
         sentence_text = "".join(word_text)
 

stanza/tests/server/test_ssurgeon.py

@@ -106,7 +106,7 @@ def test_ssurgeon_different_length():
 # text = It's not yours!
 # comment = negation
 1-2	It's	_	_	_	_	_	_	_	_
-1	It	it	PRON	PRP	Number=Sing|Person=2|PronType=Prs	4	nsubj	_	SpaceAfter=No
+1	It	it	PRON	PRP	Number=Sing|Person=2|PronType=Prs	4	nsubj	_	_
 2	's	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	_
 3	not	not	PART	RB	Polarity=Neg	4	advmod	_	_
 4	yours	yours	PRON	PRP	Gender=Neut|Number=Sing|Person=2|Poss=Yes|PronType=Prs	0	root	_	SpaceAfter=No
@@ -150,8 +150,8 @@ def test_ssurgeon_become_mwt():
 2	of	of	ADP	IN	_	4	case	_	_
 3	“	"	PUNCT	``	_	4	punct	_	SpaceAfter=No
 4-5	NCRC4ME’s	_	_	_	_	_	_	_	SpaceAfter=No
-4	NCRC4ME	NCRC4ME	PROPN	NNP	Number=Sing	1	compound	_	SpaceAfter=No
-5	’s	's	PART	POS	_	4	case	_	SpaceAfter=No
+4	NCRC4ME	NCRC4ME	PROPN	NNP	Number=Sing	1	compound	_	_
+5	’s	's	PART	POS	_	4	case	_	_
 6	”	"	PUNCT	''	_	4	punct	_	_
 """