Changeset 391 for python/trunk/Lib/test/test_csv.py

Timestamp:

Mar 19, 2014, 11:31:01 PM (11 years ago)

Author:

dmik

Message:

python: Merge vendor 2.7.6 to trunk.

Location:

python/trunk

Files:

• . (modified) (1 prop)
• Lib/test/test_csv.py (modified) (14 diffs)

python/trunk/Lib/test/test_csv.py

@@ -10 +10 @@
 import csv
 import gc
+import io
 from test import test_support
 
@@ -167 +168 @@
         self._write_test(['a',1,'p,q'], '"a","1","p,q"',
                          quoting = csv.QUOTE_ALL)
+        self._write_test(['a\nb',1], '"a\nb","1"',
+                         quoting = csv.QUOTE_ALL)
 
     def test_write_escape(self):
@@ -205 +208 @@
             os.unlink(name)
 
+    def test_write_float(self):
+        # Issue 13573: loss of precision because csv.writer
+        # uses str() for floats instead of repr()
+        orig_row = [1.234567890123, 1.0/7.0, 'abc']
+        f = StringIO()
+        c = csv.writer(f, quoting=csv.QUOTE_NONNUMERIC)
+        c.writerow(orig_row)
+        f.seek(0)
+        c = csv.reader(f, quoting=csv.QUOTE_NONNUMERIC)
+        new_row = next(c)
+        self.assertEqual(orig_row, new_row)
+
     def _read_test(self, input, expect, **kwargs):
         reader = csv.reader(input, **kwargs)
@@ -229 +244 @@
         self.assertRaises(csv.Error, self._read_test, ['a,b\r\nc,d'], [])
 
+    def test_read_eof(self):
+        self._read_test(['a,"'], [['a', '']])
+        self._read_test(['"a'], [['a']])
+        self._read_test(['^'], [['\n']], escapechar='^')
+        self.assertRaises(csv.Error, self._read_test, ['a,"'], [], strict=True)
+        self.assertRaises(csv.Error, self._read_test, ['"a'], [], strict=True)
+        self.assertRaises(csv.Error, self._read_test,
+                          ['^'], [], escapechar='^', strict=True)
+
     def test_read_escape(self):
         self._read_test(['a,\\b,c'], [['a', 'b', 'c']], escapechar='\\')
@@ -246 +270 @@
         self._read_test([',3,"5",7.3, 9'], [['', 3, '5', 7.3, 9]],
                         quoting=csv.QUOTE_NONNUMERIC)
+        self._read_test(['"a\nb", 7'], [['a\nb', ' 7']])
         self.assertRaises(ValueError, self._read_test,
                           ['abc,3'], [[]],
@@ -282 +307 @@
             self.assertRaises(StopIteration, r.next)
             self.assertEqual(r.line_num, 3)
+
+    def test_roundtrip_quoteed_newlines(self):
+        fd, name = tempfile.mkstemp()
+        fileobj = os.fdopen(fd, "w+b")
+        try:
+            writer = csv.writer(fileobj)
+            self.assertRaises(TypeError, writer.writerows, None)
+            rows = [['a\nb','b'],['c','x\r\nd']]
+            writer.writerows(rows)
+            fileobj.seek(0)
+            for i, row in enumerate(csv.reader(fileobj)):
+                self.assertEqual(row, rows[i])
+        finally:
+            fileobj.close()
+            os.unlink(name)
 
 class TestDialectRegistry(unittest.TestCase):
@@ -308 +348 @@
         expected_dialects.sort()
         csv.register_dialect(name, myexceltsv)
-        try:
-            self.failUnless(csv.get_dialect(name).delimiter, '\t')
-            got_dialects = csv.list_dialects()
-            got_dialects.sort()
-            self.assertEqual(expected_dialects, got_dialects)
-        finally:
-            csv.unregister_dialect(name)
+        self.addCleanup(csv.unregister_dialect, name)
+        self.assertEqual(csv.get_dialect(name).delimiter, '\t')
+        got_dialects = sorted(csv.list_dialects())
+        self.assertEqual(expected_dialects, got_dialects)
 
     def test_register_kwargs(self):
         name = 'fedcba'
         csv.register_dialect(name, delimiter=';')
-        try:
-            self.failUnless(csv.get_dialect(name).delimiter, '\t')
-            self.failUnless(list(csv.reader('X;Y;Z', name)), ['X', 'Y', 'Z'])
-        finally:
-            csv.unregister_dialect(name)
+        self.addCleanup(csv.unregister_dialect, name)
+        self.assertEqual(csv.get_dialect(name).delimiter, ';')
+        self.assertEqual([['X', 'Y', 'Z']], list(csv.reader(['X;Y;Z'], name)))
 
     def test_incomplete_dialect(self):
@@ -578 +613 @@
     def test_write_simple_dict(self):
         fd, name = tempfile.mkstemp()
-        fileobj = os.fdopen(fd, "w+b")
+        fileobj = io.open(fd, 'w+b')
         try:
             writer = csv.DictWriter(fileobj, fieldnames = ["f1", "f2", "f3"])
+            writer.writeheader()
+            fileobj.seek(0)
+            self.assertEqual(fileobj.readline(), "f1,f2,f3\r\n")
             writer.writerow({"f1": 10, "f3": "abc"})
             fileobj.seek(0)
+            fileobj.readline() # header
             self.assertEqual(fileobj.read(), "10,,abc\r\n")
         finally:
@@ -767 +806 @@
             writer = csv.writer(fileobj, dialect="excel")
             writer.writerow(a)
-            expected = ",".join([str(i) for i in a])+"\r\n"
+            expected = ",".join([repr(i) for i in a])+"\r\n"
             fileobj.seek(0)
             self.assertEqual(fileobj.read(), expected)
@@ -783 +822 @@
             writer = csv.writer(fileobj, dialect="excel")
             writer.writerow(a)
-            expected = ",".join([str(i) for i in a])+"\r\n"
+            expected = ",".join([repr(i) for i in a])+"\r\n"
             fileobj.seek(0)
             self.assertEqual(fileobj.read(), expected)
@@ -874 +913 @@
 'Shark City':'Glendale Heights':'IL':'12/28/02':'Prezence'
 'Tommy''s Place':'Blue Island':'IL':'12/28/02':'Blue Sunday/White Crow'
-'Stonecutters Seafood and Chop House':'Lemont':'IL':'12/19/02':'Week Back'
+'Stonecutters ''Seafood'' and Chop House':'Lemont':'IL':'12/19/02':'Week Back'
 """
-    header = '''\
+    header1 = '''\
 "venue","city","state","date","performers"
 '''
@@ -895 +934 @@
     sample7 = "'a'|'b'|'c'\r\n'd'|e|f\r\n"
 
+# Issue 18155: Use a delimiter that is a special char to regex:
+
+    header2 = '''\
+"venue"+"city"+"state"+"date"+"performers"
+'''
+    sample8 = """\
+Harry's+ Arlington Heights+ IL+ 2/1/03+ Kimi Hayes
+Shark City+ Glendale Heights+ IL+ 12/28/02+ Prezence
+Tommy's Place+ Blue Island+ IL+ 12/28/02+ Blue Sunday/White Crow
+Stonecutters Seafood and Chop House+ Lemont+ IL+ 12/19/02+ Week Back
+"""
+    sample9 = """\
+'Harry''s'+ Arlington Heights'+ 'IL'+ '2/1/03'+ 'Kimi Hayes'
+'Shark City'+ Glendale Heights'+' IL'+ '12/28/02'+ 'Prezence'
+'Tommy''s Place'+ Blue Island'+ 'IL'+ '12/28/02'+ 'Blue Sunday/White Crow'
+'Stonecutters ''Seafood'' and Chop House'+ 'Lemont'+ 'IL'+ '12/19/02'+ 'Week Back'
+"""
+
     def test_has_header(self):
         sniffer = csv.Sniffer()
         self.assertEqual(sniffer.has_header(self.sample1), False)
-        self.assertEqual(sniffer.has_header(self.header+self.sample1), True)
+        self.assertEqual(sniffer.has_header(self.header1 + self.sample1),
+                         True)
+
+    def test_has_header_regex_special_delimiter(self):
+        sniffer = csv.Sniffer()
+        self.assertEqual(sniffer.has_header(self.sample8), False)
+        self.assertEqual(sniffer.has_header(self.header2 + self.sample8),
+                         True)
 
     def test_sniff(self):
@@ -918 +982 @@
         # I think that any character could have been 'guessed' as the
         # delimiter, depending on dictionary order
-        self.assert_(dialect.delimiter in self.sample3)
+        self.assertIn(dialect.delimiter, self.sample3)
         dialect = sniffer.sniff(self.sample3, delimiters="?,")
         self.assertEqual(dialect.delimiter, "?")
@@ -932 +996 @@
         self.assertEqual(dialect.delimiter, "|")
         self.assertEqual(dialect.quotechar, "'")
+        dialect = sniffer.sniff(self.sample8)
+        self.assertEqual(dialect.delimiter, '+')
+        dialect = sniffer.sniff(self.sample9)
+        self.assertEqual(dialect.delimiter, '+')
+        self.assertEqual(dialect.quotechar, "'")
+
+    def test_doublequote(self):
+        sniffer = csv.Sniffer()
+        dialect = sniffer.sniff(self.header1)
+        self.assertFalse(dialect.doublequote)
+        dialect = sniffer.sniff(self.header2)
+        self.assertFalse(dialect.doublequote)
+        dialect = sniffer.sniff(self.sample2)
+        self.assertTrue(dialect.doublequote)
+        dialect = sniffer.sniff(self.sample8)
+        self.assertFalse(dialect.doublequote)
+        dialect = sniffer.sniff(self.sample9)
+        self.assertTrue(dialect.doublequote)
 
 if not hasattr(sys, "gettotalrefcount"):