# Copyright (C) 2001,2002 Python Software Foundation
# csv package unit tests

import sys
import unittest
from StringIO import StringIO
import csv
import _csv

class Test_Csv(unittest.TestCase):
    """
    Test the underlying C csv parser in ways that are not appropriate 
    from the high level interface.
    """
    def test_init(self):
        "test that the module returns a parser"
        parser = _csv.parser()
        self.failUnless(hasattr(parser, 'parse'))

    def test_parameter_validation(self):
        self.assertRaises(TypeError, _csv.parser, FlibbleWort = 0)
        self.assertRaises(ValueError, _csv.parser, quoting = -1)
        self.assertRaises(ValueError, _csv.parser, quoting = csv.QUOTE_NONE + 1)
        self.assertRaises(TypeError, _csv.parser, delimiter = None)
        self.assertRaises(TypeError, _csv.parser, skipinitialspace = None)

    def test_parameter(self):
        parser = _csv.parser(delimiter = "\t")
        self.assertEqual(parser.delimiter, "\t")

        parser = _csv.parser(quotechar = "'")
        self.assertEqual(parser.quotechar, "'")

    def test_attr_validation(self):
        parser = _csv.parser()
        self.assertRaises(AttributeError, delattr, parser, 'quoting')
        self.assertRaises(TypeError, setattr, parser, 'quoting', -1)
        self.assertRaises(TypeError, setattr, parser, 'quoting', 
                          csv.QUOTE_NONE + 1)
        self.assertRaises(TypeError, setattr, parser, 'quotechar', 0)
        self.assertRaises(TypeError, setattr, parser, 'escapechar', 0)
        self.assertRaises(TypeError, setattr, parser, 'lineterminator', None)

    def test_setattr(self):
        parser = _csv.parser()
        parser.delimiter = "\t"
        self.assertEqual(parser.delimiter, "\t")

        parser = _csv.parser()
        parser.quotechar = "'"
        self.assertEqual(parser.quotechar, "'")

    def test_join_bigfield(self):
        # This exercises the buffer realloc functionality
        parser = _csv.parser()
        bigstring = 'X' * 50000
        result = parser.join([bigstring,bigstring])
        self.assertEqual(result, '%s,%s%s' % \
                         (bigstring, bigstring, parser.lineterminator))

    def test_join_quoting(self):
        parser = _csv.parser()
        self.assertEqual(parser.join(['a','1','p,q']), 'a,1,"p,q"\r\n')
        parser = _csv.parser(quoting = csv.QUOTE_NONE)
        self.assertRaises(_csv.Error, parser.join, ['a','1','p,q'])
        parser = _csv.parser(quoting = csv.QUOTE_MINIMAL)
        self.assertEqual(parser.join(['a','1','p,q']), 'a,1,"p,q"\r\n')
        parser = _csv.parser(quoting = csv.QUOTE_NONNUMERIC)
        self.assertEqual(parser.join(['a','1','p,q']), '"a",1,"p,q"\r\n')
        parser = _csv.parser(quoting = csv.QUOTE_ALL)
        self.assertEqual(parser.join(['a','1','p,q']), '"a","1","p,q"\r\n')

    def test_join_escape(self):
        parser = _csv.parser(escapechar='\\')
        self.assertEqual(parser.join(['a','1','p,q']), 'a,1,"p,q"\r\n')
        parser.doublequote = 0
        self.assertEqual(parser.join(['a','1','p,"q"']), 'a,1,"p,\\"q"\r\n')
        parser.quoting = csv.QUOTE_NONE
        self.assertEqual(parser.join(['a','1','p,q']), 'a,1,p\\,q\r\n')

    def test_parse(self):
        parser = _csv.parser()
        self.assertRaises(TypeError, parser.parse, None)
        self.assertEqual(parser.parse(''), [])

    def test_parse_eol(self):
        parser = _csv.parser()
        self.assertEqual(parser.parse('a,b'), ['a','b'])
        self.assertEqual(parser.parse('a,b\n'), ['a','b'])
        self.assertEqual(parser.parse('a,b\r\n'), ['a','b'])
        self.assertEqual(parser.parse('a,b\r'), ['a','b'])
        self.assertRaises(csv.Error, parser.parse, 'a,b\rc,d')
        self.assertRaises(csv.Error, parser.parse, 'a,b\nc,d')
        self.assertRaises(csv.Error, parser.parse, 'a,b\r\nc,d')

    def test_parse_escape(self):
        parser = _csv.parser(escapechar='\\')
        self.assertEqual(parser.parse('a,\\b,c'), ['a', '\\b', 'c'])
        self.assertEqual(parser.parse('a,b\\,c'), ['a', 'b,c'])
        self.assertEqual(parser.parse('a,"b\\,c"'), ['a', 'b,c'])
        self.assertEqual(parser.parse('a,"b,\\c"'), ['a', 'b,\\c'])
        self.assertEqual(parser.parse('a,"b,c\\""'), ['a', 'b,c"'])
        self.assertEqual(parser.parse('a,"b,c"\\'), ['a', 'b,c\\'])

    def test_parse_bigfield(self):
        # This exercises the buffer realloc functionality
        parser = _csv.parser()
        bigstring = 'X' * 50000
        bigline = '%s,%s%s' % (bigstring, bigstring, parser.lineterminator)
        self.assertEqual(parser.parse(bigline), [bigstring, bigstring])

class TestCsvBase(unittest.TestCase):
    def readerAssertEqual(self, input, expected_result):
        reader = csv.reader(StringIO(input), dialect = self.dialect)
        fields = list(reader)
        self.assertEqual(fields, expected_result)

    def writerAssertEqual(self, input, expected_result):
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect = self.dialect)
        writer.writerows(input)
        self.assertEqual(fileobj.getvalue(), expected_result)

class TestDialectExcel(TestCsvBase):
    dialect = 'excel'

    def test_single(self):
        self.readerAssertEqual('abc', [['abc']])

    def test_simple(self):
        self.readerAssertEqual('1,2,3,4,5', [['1','2','3','4','5']])

    def test_blankline(self):
        self.readerAssertEqual('', [])

    def test_empty_fields(self):
        self.readerAssertEqual(',', [['', '']])

    def test_singlequoted(self):
        self.readerAssertEqual('""', [['']])

    def test_singlequoted_left_empty(self):
        self.readerAssertEqual('"",', [['','']])

    def test_singlequoted_right_empty(self):
        self.readerAssertEqual(',""', [['','']])

    def test_single_quoted_quote(self):
        self.readerAssertEqual('""""', [['"']])

    def test_quoted_quotes(self):
        self.readerAssertEqual('""""""', [['""']])

    def test_inline_quote(self):
        self.readerAssertEqual('a""b', [['a""b']])

    def test_inline_quotes(self):
        self.readerAssertEqual('a"b"c', [['a"b"c']])

    def test_quotes_and_more(self):
        self.readerAssertEqual('"a"b', [['ab']])

    def test_lone_quote(self):
        self.readerAssertEqual('a"b', [['a"b']])

    def test_quote_and_quote(self):
        self.readerAssertEqual('"a" "b"', [['a "b"']])

    def test_space_and_quote(self):
        self.readerAssertEqual(' "a"', [[' "a"']])

    def test_quoted(self):
        self.readerAssertEqual('1,2,3,"I think, therefore I am",5,6', 
                               [['1', '2', '3', 
                                 'I think, therefore I am', 
                                 '5', '6']])

    def test_quoted_quote(self):
        self.readerAssertEqual('1,2,3,"""I see,"" said the blind man","as he picked up his hammer and saw"',
                               [['1', '2', '3', 
                                 '"I see," said the blind man', 
                                 'as he picked up his hammer and saw']])

    def test_quoted_nl(self):
        input = '''\
1,2,3,"""I see,""
said the blind man","as he picked up his
hammer and saw"
9,8,7,6'''
        self.readerAssertEqual(input,
                               [['1', '2', '3', 
                                   '"I see,"\nsaid the blind man', 
                                   'as he picked up his\nhammer and saw'],
                                ['9','8','7','6']])

    def test_dubious_quote(self):
        self.readerAssertEqual('12,12,1",', [['12', '12', '1"', '']])

    def test_null(self):
        self.writerAssertEqual([], '')

    def test_single(self):
        self.writerAssertEqual([['abc']], 'abc\r\n')

    def test_simple(self):
        self.writerAssertEqual([[1, 2, 'abc', 3, 4]], '1,2,abc,3,4\r\n')

    def test_quotes(self):
        self.writerAssertEqual([[1, 2, 'a"bc"', 3, 4]], '1,2,"a""bc""",3,4\r\n')

    def test_quote_fieldsep(self):
        self.writerAssertEqual([['abc,def']], '"abc,def"\r\n')

    def test_newlines(self):
        self.writerAssertEqual([[1, 2, 'a\nbc', 3, 4]], '1,2,"a\nbc",3,4\r\n')

class EscapedExcel(csv.excel):
    quoting = csv.QUOTE_NONE
    escapechar = '\\'

class TestEscapedExcel(TestCsvBase):
    dialect = EscapedExcel()

    def test_escape_fieldsep(self):
        self.writerAssertEqual([['abc,def']], 'abc\\,def\r\n')

    def test_read_escape_fieldsep(self):
        self.readerAssertEqual('abc\\,def\r\n', [['abc,def']])

class QuotedEscapedExcel(csv.excel):
    quoting = csv.QUOTE_NONNUMERIC
    escapechar = '\\'

class TestQuotedEscapedExcel(TestCsvBase):
    dialect = QuotedEscapedExcel()

    def test_write_escape_fieldsep(self):
        self.writerAssertEqual([['abc,def']], '"abc,def"\r\n')

    def test_read_escape_fieldsep(self):
        self.readerAssertEqual('"abc\\,def"\r\n', [['abc,def']])

class TestDictFields(unittest.TestCase):
    def test_write_simple_dict(self):
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect="excel",
                            fieldnames = ["f1", "f2", "f3"])
        writer.writerow({"f1": 10, "f3": "abc"})
        self.assertEqual(fileobj.getvalue(), "10,,abc\r\n")

    def test_write_no_fields(self):
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect="excel")
        self.assertRaises(csv.Error, writer.writerow, {"f1": 10, "f3": "abc"})

    def test_read_dict_fields(self):
        reader = csv.reader(StringIO("1,2,abc\r\n"), dialect="excel",
                            fieldnames=["f1", "f2", "f3"])
        self.assertEqual(reader.next(), {"f1": '1', "f2": '2', "f3": 'abc'})

    def test_read_short(self):
        reader = csv.reader(StringIO("1,2,abc,4,5,6\r\n"), dialect="excel",
                            fieldnames=["f1", "f2"])
        self.assertEqual(reader.next(), {"f1": '1', "f2": '2'})

    def test_read_short_with_rest(self):
        reader = csv.reader(StringIO("1,2,abc,4,5,6\r\n"), dialect="excel",
                            fieldnames=["f1", "f2"], restfield="_rest")
        self.assertEqual(reader.next(), {"f1": '1', "f2": '2',
                                         "_rest": ["abc", "4", "5", "6"]})

class TestArrayWrites(unittest.TestCase):
    def test_int_write(self):
        import array
        contents = [(20-i) for i in range(20)]
        a = array.array('i', contents)
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect="excel")
        writer.writerow(a)
        expected = ",".join([str(i) for i in a])+"\r\n"
        self.assertEqual(fileobj.getvalue(), expected)

    def test_double_write(self):
        import array
        contents = [(20-i)*0.1 for i in range(20)]
        a = array.array('d', contents)
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect="excel")
        writer.writerow(a)
        expected = ",".join([str(i) for i in a])+"\r\n"
        self.assertEqual(fileobj.getvalue(), expected)

    def test_float_write(self):
        import array
        contents = [(20-i)*0.1 for i in range(20)]
        a = array.array('f', contents)
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect="excel")
        writer.writerow(a)
        expected = ",".join([str(i) for i in a])+"\r\n"
        self.assertEqual(fileobj.getvalue(), expected)

    def test_char_write(self):
        import array, string
        a = array.array('c', string.letters)
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect="excel")
        writer.writerow(a)
        expected = ",".join(a)+"\r\n"
        self.assertEqual(fileobj.getvalue(), expected)

class TestDialects(unittest.TestCase):
    def test_register(self):
        class myexceltsv(csv.excel):
            delimiter = "\t"
        csv.register_dialect("myexceltsv", myexceltsv)
        self.assertEqual(isinstance(csv.get_dialect("myexceltsv"),
                                    myexceltsv), 1==1)
        csv.unregister_dialect("myexceltsv")

    def test_get(self):
        self.assertEqual(isinstance(csv.get_dialect("excel"),
                                    csv.excel), 1==1)

    def test_list(self):
        for dname in csv.list_dialects():
            d = csv.get_dialect(dname)
            self.assertEqual(d._name, dname)

    def test_bad_register(self):
        class myexceltsv:
            delimiter = "\t"
        self.assertRaises(TypeError, csv.register_dialect,
                          "myexceltsv", myexceltsv)

    def test_incomplete_dialect(self):
        class myexceltsv(csv.Dialect):
            delimiter = "\t"
        self.assertRaises(csv.Error, myexceltsv)

    def test_dialect_class(self):
        class myexceltsv(csv.excel):
            delimiter = "\t"
        fileobj = StringIO()
        writer = csv.writer(fileobj, dialect=myexceltsv())
        writer.writerow([1,2,3])
        self.assertEqual(fileobj.getvalue(), "1\t2\t3\r\n")

            
def _testclasses():
    mod = sys.modules[__name__]
    return [getattr(mod, name) for name in dir(mod) if name.startswith('Test')]

def suite():
    suite = unittest.TestSuite()
    for testclass in _testclasses():
        suite.addTest(unittest.makeSuite(testclass))
    return suite

if __name__ == '__main__':
    unittest.main(defaultTest='suite')