Restore the convert_dict method, as requested in #1329

stanza/tests/common/test_data_conversion.py

@@ -499,3 +499,22 @@ def test_read_multiple_doc_ids():
     assert len(docs[1].sentences) == 1
     assert len(docs[2].sentences) == 2
 
+ENGLISH_TEST_SENTENCE = """
+# text = This is a test
+# sent_id = 0
+1	This	this	PRON	DT	Number=Sing|PronType=Dem	4	nsubj	_	start_char=0|end_char=4
+2	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	start_char=5|end_char=7
+3	a	a	DET	DT	Definite=Ind|PronType=Art	4	det	_	start_char=8|end_char=9
+4	test	test	NOUN	NN	Number=Sing	0	root	_	start_char=10|end_char=14|SpaceAfter=No
+""".lstrip()
+
+def test_convert_dict():
+    doc = CoNLL.conll2doc(input_str=ENGLISH_TEST_SENTENCE)
+    converted = CoNLL.convert_dict(doc.to_dict())
+
+    expected = [[['1', 'This', 'this', 'PRON', 'DT', 'Number=Sing|PronType=Dem', '4', 'nsubj', '_', 'start_char=0|end_char=4'],
+                 ['2', 'is', 'be', 'AUX', 'VBZ', 'Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin', '4', 'cop', '_', 'start_char=5|end_char=7'],
+                 ['3', 'a', 'a', 'DET', 'DT', 'Definite=Ind|PronType=Art', '4', 'det', '_', 'start_char=8|end_char=9'],
+                 ['4', 'test', 'test', 'NOUN', 'NN', 'Number=Sing', '0', 'root', '_', 'SpaceAfter=No|start_char=10|end_char=14']]]
+
+    assert converted == expected

stanza/utils/conll.py

@@ -75,6 +75,23 @@ def convert_conll(doc_conll):
             doc_empty.append(sent_empty)
         return doc_dict, doc_empty
 
+    @staticmethod
+    def convert_dict(doc_dict):
+        """ Convert the dictionary format input data to the CoNLL-U format output data.
+
+        This is the reverse function of `convert_conll`, but does not include sentence level annotations or comments.
+
+        Can call this on a Document using `CoNLL.convert_dict(doc.to_dict())`
+
+        Input: dictionary format data, which is a list of list of dictionaries for each token in each sentence in the data.
+        Output: CoNLL-U format data as a list of list of list for each token in each sentence in the data.
+        """
+        doc = Document(doc_dict)
+        text = "{:c}".format(doc)
+        sentences = text.split("\n\n")
+        doc_conll = [[x.split("\t") for x in sentence.split("\n")] for sentence in sentences]
+        return doc_conll
+
     @staticmethod
     def convert_conll_token(token_conll):
         """ Convert the CoNLL-U format input token to the dictionary format output token.