Python unicodecsv.reader() Examples

def get_vocabulary(current_pos=1):
    """
    get_vocabulary returns a single record of the current_pos line position

    current_pos: up to number of records
    """
    vocabulary = {}
    with open(VOCABULARY_FILENAME, 'rb') as fobj:
        reader = csv.reader(fobj, delimiter=',', encoding='utf-8')
        num_of_lines = 0
        for line in reader:
            num_of_lines += 1
            if num_of_lines == current_pos:
                vocabulary = dict(list(zip(VOCABULARY_FIELDS, line)))
                break
    return vocabulary 

def test_read_dict_no_fieldnames(self):
        fd, name = tempfile.mkstemp()
        fileobj = os.fdopen(fd, "w+b")
        try:
            fileobj.write(b"f1,f2,f3\r\n1,2,abc\r\n")
            fileobj.seek(0)
            reader = csv.DictReader(fileobj)
            self.assertEqual(reader.fieldnames,
                             ["f1", "f2", "f3"])
            self.assertEqual(next(reader),
                             {"f1": '1', "f2": '2', "f3": 'abc'})
        finally:
            fileobj.close()
            os.unlink(name)

    # Two test cases to make sure existing ways of implicitly setting
    # fieldnames continue to work.  Both arise from discussion in issue3436. 

def _load_space(self, space_names):
        segs = set()
        scripts = list(set([nm.split('-')[1] for nm in space_names]))
        punc_fns = ['punc-{}.csv'.format(sc) for sc in scripts]
        for punc_fn in punc_fns:
            punc_fn = os.path.join('data', 'space', punc_fn)
            punc_fn = pkg_resources.resource_filename(__name__, punc_fn)
            with open(punc_fn, 'rb') as f:
                reader = csv.reader(f, encoding='utf-8')
                for (mark,) in reader:
                    segs.add(mark)
        for name in space_names:
            fn = os.path.join('data', 'space', name + '.csv')
            fn = pkg_resources.resource_filename(__name__, fn)
            with open(fn, 'rb') as f:
                reader = csv.reader(f, encoding='utf-8')
                for _, to_ in reader:
                    for seg in self.epi.ft.ipa_segs(to_):
                        segs.add(seg)
        enum = enumerate(sorted(list(segs)))
        return {seg: num for num, seg in enum} 

def test_space_dialect(self):
        class space(csv.excel):
            delimiter = " "
            quoting = csv.QUOTE_NONE
            escapechar = "\\"

        fd, name = tempfile.mkstemp()
        fileobj = os.fdopen(fd, "w+b")
        try:
            fileobj.write(b"abc def\nc1ccccc1 benzene\n")
            fileobj.seek(0)
            rdr = csv.reader(fileobj, dialect=space())
            self.assertEqual(next(rdr), ["abc", "def"])
            self.assertEqual(next(rdr), ["c1ccccc1", "benzene"])
        finally:
            fileobj.close()
            os.unlink(name) 

def _read_bases(self, fn, weights):
        fn = pkg_resources.resource_filename(__name__, fn)
        segments = []
        with open(fn, 'rb') as f:
            reader = csv.reader(f, encoding='utf-8')
            header = next(reader)
            names = header[1:]
            for row in reader:
                ipa = unicodedata.normalize('NFD', row[0])
                vals = [{'-': -1, '0': 0, '+': 1}[x] for x in row[1:]]
                vec = Segment(names,
                              {n: v for (n, v) in zip(names, vals)},
                              weights=weights)
                segments.append((ipa, vec))
        seg_dict = dict(segments)
        return segments, seg_dict, names 

def test_read_short(self):
        fd, name = tempfile.mkstemp()
        fileobj = os.fdopen(fd, "w+b")
        try:
            fileobj.write(b"1,2,abc,4,5,6\r\n1,2,abc\r\n")
            fileobj.seek(0)
            reader = csv.DictReader(fileobj,
                                    fieldnames="1 2 3 4 5 6".split(),
                                    restval="DEFAULT")
            self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
                                             "4": '4', "5": '5', "6": '6'})
            self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
                                             "4": 'DEFAULT', "5": 'DEFAULT',
                                             "6": 'DEFAULT'})
        finally:
            fileobj.close()
            os.unlink(name) 

def _read_table(self, filename):
        """Read the data from data/ipa_all.csv into self.segments, a
        list of 2-tuples of unicode strings and sets of feature tuples and
        self.seg_dict, a dictionary mapping from unicode segments and sets of
        feature tuples.
        """
        filename = pkg_resources.resource_filename(
            __name__, filename)
        segments = []
        with open(filename, 'rb') as f:
            reader = csv.reader(f, encoding='utf-8')
            header = next(reader)
            names = header[1:]
            for row in reader:
                seg = row[0]
                vals = row[1:]
                specs = set(zip(vals, names))
                segments.append((seg, specs))
        seg_dict = dict(segments)
        return segments, seg_dict, names 

def _assert_no_duplicates(self, input_path, encoding, sep, quotechar):

        if input_path.endswith('.csv'):
            with open(input_path, 'rb') as csvfile:
                reader = unicodecsv.reader(csvfile,
                                           encoding=encoding,
                                           delimiter=sep,
                                           quotechar=quotechar)
                fields = next(reader, [])

                for col in fields:
                    if fields.count(col) > 1:
                        raise DuplicatedField(col)

        # TODO: Implementar chequeo de que no hay duplicados para XLSX
        elif input_path.endswith('.xlsx'):
            pass 

def get_kanji(level, current_pos=1):
    """
    get_kanji returns a single record of the current_pos line position

    level: 1 - 4 (N1 to N4)
    current_pos: up to number of records
    """
    kanji = {}
    with open(KANJI_FILENAMES[level], 'rb') as fobj:
        reader = csv.reader(fobj, delimiter=',', encoding='utf-8')
        num_of_lines = 0
        for line in reader:
            num_of_lines += 1
            if num_of_lines == current_pos:
                kanji = dict(list(zip(KANJI_FIELDS, line)))
                break
    return kanji 

def test_reader_dialect_attrs(self):
        self._test_dialect_attrs(csv.reader, []) 

def _read_test(self, input, expect, **kwargs):
        reader = csv.reader(input, **kwargs)
        result = list(reader)
        self.assertEqual(result, expect) 

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) 

def test_register_kwargs(self):
        name = 'fedcba'
        csv.register_dialect(name, delimiter=';')
        try:
            self.assertNotEqual(csv.get_dialect(name).delimiter, '\t')
            self.assertEqual(list(csv.reader([b'X;Y;Z'], name)), [[u'X', u'Y', u'Z']])
        finally:
            csv.unregister_dialect(name) 

def test_reader_kw_attrs(self):
        self._test_kw_attrs(csv.reader, []) 

def test_reader_attrs(self):
        self._test_default_attrs(csv.reader, []) 

def test_reader_arg_valid(self):
        self._test_arg_valid(csv.reader, []) 

def test_bad_dialect(self):
        # Unknown parameter
        self.assertRaises(TypeError, csv.reader, [], bad_attr=0)
        # Bad values
        self.assertRaises(TypeError, csv.reader, [], delimiter=None)
        self.assertRaises(TypeError, csv.reader, [], quoting=-1)
        self.assertRaises(TypeError, csv.reader, [], quoting=100) 

def readerAssertEqual(self, input, expected_result):
        fd, name = tempfile.mkstemp()
        fileobj = os.fdopen(fd, "w+b")
        try:
            fileobj.write(input)
            fileobj.seek(0)
            reader = csv.reader(fileobj, dialect=self.dialect)
            fields = list(reader)
            self.assertEqual(fields, expected_result)
        finally:
            fileobj.close()
            os.unlink(name) 

def test_read_dict_fieldnames_from_file(self):
        fd, name = tempfile.mkstemp()
        f = os.fdopen(fd, "w+b")
        try:
            f.write(b"f1,f2,f3\r\n1,2,abc\r\n")
            f.seek(0)
            reader = csv.DictReader(f, fieldnames=next(csv.reader(f)))
            self.assertEqual(reader.fieldnames,
                             ["f1", "f2", "f3"])
            self.assertEqual(next(reader),
                             {"f1": '1', "f2": '2', "f3": 'abc'})
        finally:
            f.close()
            os.unlink(name) 

def read_xsampa_table(self):
        filename = os.path.join('data', 'ipa-xsampa.csv')
        filename = pkg_resources.resource_filename(__name__, filename)
        with open(filename, 'rb') as f:
            xs2ipa = {x[1]: x[0] for x in csv.reader(f, encoding='utf-8')}
        xs = sorted(xs2ipa.keys(), key=len, reverse=True)
        xs_regex = re.compile('|'.join(list(map(re.escape, xs))))
        return xs_regex, xs2ipa 

def test_read_dict_fieldnames_chain(self):
        import itertools
        fd, name = tempfile.mkstemp()
        f = os.fdopen(fd, "w+b")
        try:
            f.write(b"f1,f2,f3\r\n1,2,abc\r\n")
            f.seek(0)
            reader = csv.DictReader(f)
            first = next(reader)
            for row in itertools.chain([first], reader):
                self.assertEqual(reader.fieldnames, ["f1", "f2", "f3"])
                self.assertEqual(row, {"f1": '1', "f2": '2', "f3": 'abc'})
        finally:
            f.close()
            os.unlink(name) 

def test_read_long(self):
        fd, name = tempfile.mkstemp()
        fileobj = os.fdopen(fd, "w+b")
        try:
            fileobj.write(b"1,2,abc,4,5,6\r\n")
            fileobj.seek(0)
            reader = csv.DictReader(fileobj,
                                    fieldnames=["f1", "f2"])
            self.assertEqual(next(reader), {"f1": '1', "f2": '2',
                                             None: ["abc", "4", "5", "6"]})
        finally:
            fileobj.close()
            os.unlink(name) 

def test_read_long_with_rest(self):
        fd, name = tempfile.mkstemp()
        fileobj = os.fdopen(fd, "w+b")
        try:
            fileobj.write(b"1,2,abc,4,5,6\r\n")
            fileobj.seek(0)
            reader = csv.DictReader(fileobj,
                                    fieldnames=["f1", "f2"], restkey="_rest")
            self.assertEqual(next(reader), {"f1": '1', "f2": '2',
                                             "_rest": ["abc", "4", "5", "6"]})
        finally:
            fileobj.close()
            os.unlink(name) 

def test_read_multi(self):
        sample = [
            b'2147483648,43.0e12,17,abc,def\r\n',
            b'147483648,43.0e2,17,abc,def\r\n',
            b'47483648,43.0,170,abc,def\r\n'
            ]

        reader = csv.DictReader(sample,
                                fieldnames="i1 float i2 s1 s2".split())
        self.assertEqual(next(reader), {"i1": '2147483648',
                                         "float": '43.0e12',
                                         "i2": '17',
                                         "s1": 'abc',
                                         "s2": 'def'}) 

def test_read_with_blanks(self):
        reader = csv.DictReader([b"1,2,abc,4,5,6\r\n", b"\r\n",
                                 b"1,2,abc,4,5,6\r\n"],
                                fieldnames="1 2 3 4 5 6".split())
        self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
                                         "4": '4', "5": '5', "6": '6'})
        self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
                                         "4": '4', "5": '5', "6": '6'}) 

def test_read_semi_sep(self):
        reader = csv.DictReader([b"1;2;abc;4;5;6\r\n"],
                                fieldnames="1 2 3 4 5 6".split(),
                                delimiter=';')
        self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
                                         "4": '4', "5": '5', "6": '6'}) 

def test_unicode_read(self):
        f = EncodedFile(BytesIO((u"Martin von Löwis,"
                                 u"Marc André Lemburg,"
                                 u"Guido van Rossum,"
                                 u"François Pinard\r\n").encode('iso-8859-1')),
                        data_encoding='iso-8859-1')
        reader = csv.reader(f, encoding='iso-8859-1')
        self.assertEqual(list(reader), [[u"Martin von Löwis",
                                         u"Marc André Lemburg",
                                         u"Guido van Rossum",
                                         u"François Pinard"]]) 

def test_decode_error_dictreader(self):
        """Make sure the error-handling mode is obeyed on DictReaders."""
        file = EncodedFile(BytesIO(u'name,height,weight\nLöwis,2,3'.encode('iso-8859-1')),
                           data_encoding='iso-8859-1')
        reader = csv.DictReader(file, encoding='ascii', errors='ignore')
        self.assertEqual(list(reader)[0]['name'], 'Lwis') 

def convert(input_file_name, **kwargs):
    """Convert CSV file to HTML table"""
    delimiter = kwargs["delimiter"] or ","
    quotechar = kwargs["quotechar"] or "|"

    if six.PY2:
        delimiter = delimiter.encode("utf-8")
        quotechar = quotechar.encode("utf-8")

    # Read CSV and form a header and rows list
    with open(input_file_name, "rb") as input_file:
        reader = csv.reader(input_file,
                            encoding="utf-8",
                            delimiter=delimiter,
                            quotechar=quotechar)

        csv_headers = []
        if not kwargs.get("no_header"):
            # Read header from first line
            csv_headers = next(reader)

        csv_rows = [row for row in reader if row]

        # Set default column name if header is not present
        if not csv_headers and len(csv_rows) > 0:
            end = len(csv_rows[0]) + 1
            csv_headers = ["Column {}".format(n) for n in range(1, end)]

    # Render csv to HTML
    html = render_template(csv_headers, csv_rows, **kwargs)

    # Freeze all JS files in template
    return freeze_js(html) 

def _assert_correct_csv(self, actual_csv, expected_rows):
        """
        Asserts that CSV file ``actual_csv`` contains ``expected_rows``
        """
        reader = unicodecsv.reader(actual_csv.getvalue().splitlines(), encoding="utf-8")
        # preprocess expected - convert everything to strings
        expected_rows = [
            [str(item) for item in row]
            for row in expected_rows
        ]
        actual_rows = list(reader)
        self.assertEqual(actual_rows, expected_rows)