add broken test for patrick

tests/test_modeling_bart.py

@@ -424,20 +424,6 @@ class BartModelIntegrationTest(unittest.TestCase):
             model = BartModel.from_pretrained(model_name, cache_dir=CACHE_DIR)
             self.assertIsNotNone(model)
 
-    @slow
-    def test_cnn_summarization_same_as_fairseq_easy(self):
-        hf = BartForConditionalGeneration.from_pretrained("bart-large-cnn", output_past=True,).to(torch_device)
-        tok = BartTokenizer.from_pretrained("bart-large")
-        text = " (CNN)The Palestinian Authority officially became the 123rd member of the International Criminal Court on Wednesday, a step that gives the court jurisdiction over alleged crimes in Palestinian"
-        tokens = tok.encode(text, return_tensors="pt").to(torch_device)
-        extra_len = 20
-        gen_tokens = hf.generate(
-            tokens, num_beams=4, max_length=extra_len + 2, do_sample=False
-        )  # repetition_penalty=10.,
-        expected_result = "<s>The Palestinian Authority officially became the 123rd member of the International Criminal Court on Wednesday."
-        generated = [tok.decode(g,) for g in gen_tokens]
-        self.assertEqual(expected_result, generated[0])
-
     @slow
     def test_cnn_summarization_same_as_fairseq_hard(self):
         hf = BartForConditionalGeneration.from_pretrained("bart-large-cnn", output_past=True,).to(torch_device)
@@ -456,6 +442,8 @@ class BartModelIntegrationTest(unittest.TestCase):
         ARTICLE_SUBWAY = ' New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York. A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.  Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other. In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage. Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the 2010 marriage license application, according to court documents. Prosecutors said the marriages were part of an immigration scam. On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further. After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.  All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say. Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.  Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted. The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali. Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force. If convicted, Barrientos faces up to four years in prison.  Her next court appearance is scheduled for May 18.'
         EXPECTED_SUMMARY_SUBWAY = "Liana Barrientos has been married 10 times, sometimes within two weeks of each other. Prosecutors say the marriages were part of an immigration scam. On Friday, she pleaded not guilty at State Supreme Court in the Bronx. She was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the subway."
 
+
+
         dct = tok.batch_encode_plus(
             [FRANCE_ARTICLE, SHORTER_ARTICLE, IRAN_ARTICLE, ARTICLE_SUBWAY],
             max_length=1024,
@@ -484,8 +472,49 @@ class BartModelIntegrationTest(unittest.TestCase):
         ]
 
         self.assertListEqual(
-            [EXPECTED_SUMMARY_FRANCE, EXPECTED_SUMMARY_SHORTER, EXPECTED_SUMMARY_IRAN, EXPECTED_SUMMARY_SUBWAY],
+            [
+                EXPECTED_SUMMARY_FRANCE,
+                EXPECTED_SUMMARY_SHORTER,
+                EXPECTED_SUMMARY_IRAN,
+                EXPECTED_SUMMARY_SUBWAY,
+            ],
             decoded,
         )
         # TODO(SS): run fairseq again with num_beams=2, min_len=20.
         # TODO(SS): add test case that hits max_length
+
+    @slow
+    def test_cnn_rouge_regression(self):
+        ARTICLE_9 = ' (CNN)If you\'ve been following the news lately, there are certain things you doubtless know about Mohammad Javad Zarif. He is, of course, the Iranian foreign minister. He has been U.S. Secretary of State John Kerry\'s opposite number in securing a breakthrough in nuclear discussions that could lead to an end to sanctions against Iran -- if the details can be worked out in the coming weeks. And he received a hero\'s welcome as he arrived in Iran on a sunny Friday morning. "Long live Zarif," crowds chanted as his car rolled slowly down the packed street. You may well have read that he is "polished" and, unusually for one burdened with such weighty issues, "jovial." An Internet search for "Mohammad Javad Zarif" and "jovial" yields thousands of results. He certainly has gone a long way to bring Iran in from the cold and allow it to rejoin the international community. But there are some facts about Zarif that are less well-known. Here are six: . In September 2013, Zarif tweeted "Happy Rosh Hashanah," referring to the Jewish New Year. That prompted Christine Pelosi, the daughter of House Minority Leader Nancy Pelosi, to respond with a tweet of her own: "Thanks. The New Year would be even sweeter if you would end Iran\'s Holocaust denial, sir." And, perhaps to her surprise, Pelosi got a response. "Iran never denied it," Zarif tweeted back. "The man who was perceived to be denying it is now gone. Happy New Year." The reference was likely to former Iranian President Mahmoud Ahmadinejad, who had left office the previous month. Zarif was nominated to be foreign minister by Ahmadinejad\'s successor, Hassan Rouhami. His foreign ministry notes, perhaps defensively, that "due to the political and security conditions of the time, he decided to continue his education in the United States." That is another way of saying that he was outside the country during the demonstrations against the Shah of Iran, which began in 1977, and during the Iranian Revolution, which drove the shah from power in 1979. Zarif left the country in 1977, received his undergraduate degree from San Francisco State University in 1981, his master\'s in international relations from the University of Denver in 1984 and his doctorate from the University of Denver in 1988. Both of his children were born in the United States. The website of the Iranian Foreign Ministry, which Zarif runs, cannot even agree with itself on when he was born. The first sentence of his official biography, perhaps in a nod to the powers that be in Tehran, says Zarif was "born to a religious traditional family in Tehran in 1959." Later on the same page, however, his date of birth is listed as January 8, 1960. And the Iranian Diplomacy website says he was born in in 1961 . So he is 54, 55 or maybe even 56. Whichever, he is still considerably younger than his opposite number, Kerry, who is 71. The feds investigated him over his alleged role in controlling the Alavi Foundation, a charitable organization. The U.S. Justice Department said the organization was secretly run on behalf of the Iranian government to launder money and get around U.S. sanctions. But last year, a settlement in the case, under which the foundation agreed to give a 36-story building in Manhattan along with other properties to the U.S. government, did not mention Zarif\'s name. Early in the Iranian Revolution, Zarif was among the students who took over the Iranian Consulate in San Francisco. The aim, says the website Iranian.com -- which cites Zarif\'s memoirs, titled "Mr. Ambassador" -- was to expel from the consulate people who were not sufficiently Islamic. Later, the website says, Zarif went to make a similar protest at the Iranian mission to the United Nations. In response, the Iranian ambassador to the United Nations offered him a job. In fact, he has now spent more time with Kerry than any other foreign minister in the world. And that amount of quality time will only increase as the two men, with help from other foreign ministers as well, try to meet a June 30 deadline for nailing down the details of the agreement they managed to outline this week in Switzerland.'
+        EXPECTED_SUMMARY_9 = """Mohammad Javad Zarif is the Iranian foreign minister. He has been John Kerry's opposite number in securing a breakthrough in nuclear discussions. He received a hero's welcome as he arrived in Iran on a sunny Friday morning. But there are some facts about Zarif that are less well-known."""
+        hf = BartForConditionalGeneration.from_pretrained("bart-large-cnn", output_past=True,).to(torch_device)
+        tok = BartTokenizer.from_pretrained("bart-large")
+
+        dct = tok.batch_encode_plus(
+            [ARTICLE_9],
+            max_length=1024,
+            pad_to_max_length=True,
+            return_tensors="pt",
+        )
+
+        max_length = 140
+        min_length = 55
+
+        self.assertEqual(1024, dct["input_ids"].shape[1])
+        hypotheses_batch = hf.generate(
+            input_ids=dct["input_ids"].to(torch_device),
+            attention_mask=dct["attention_mask"].to(torch_device),
+            num_beams=4,
+            length_penalty=2.0,
+            max_length=max_length + 2,
+            min_length=min_length + 1,
+            no_repeat_ngram_size=3,
+            do_sample=False,
+            early_stopping=True,
+        )
+
+        decoded = [
+            tok.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in hypotheses_batch
+        ]
+
+        self.assertEqual(decoded[0], EXPECTED_SUMMARY_9)