Python unicodecsv.reader方法代码示例

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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} 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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) 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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. 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
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) 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
def __init__(self, s3_config, s3_path, unicode_csv, **kwargs):
        self.s3file = s3_config.fs_open(_strip_schema(s3_path))
        self.gzfile = TextIOWrapper(
            GzipFile(fileobj=self.s3file, mode='rb'),
            encoding='utf-8',
            newline='',
        )
        self.reader = get_csv_reader(self.gzfile, unicode_csv, **kwargs) 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
def __iter__(self):
        return self.reader.__iter__() 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
def next(self):
        return self.reader.next() 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
def get_csv_reader(iterable, unicode_csv, **kwargs):
    # The csv module works fine with unicode on Python 3, we will use `unicodecsv` only for Python2.
    if unicode_csv and sys.version_info.major == 2:
        return unicodecsv.reader(_encode_rows_to_utf8(iterable), **kwargs)

    return csv.reader(iterable, **kwargs) 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
def import_csv_to_list(filename, headers = False, astuple = False):
    data = []
    with open(filename, 'rb') as file:
        reader = unicodecsv.reader(file, delimiter = ',', quotechar = '"')
        if headers == True:
            next(reader, None) # Skip header row.
        for row in reader:
            if(astuple):
                data.append(tuple(row))
            else:
                data.append(row)
    return data 

# 需要导入模块: import unicodecsv [as 别名]
# 或者: from unicodecsv import reader [as 别名]
def import_csv_to_dict(filename, params = None, headers = False):
    data = []
    with open(filename, 'rU') as file:
        reader = unicodecsv.reader(file, delimiter = ',', quotechar = '"')
        if(headers):
            params = reader.next()
        for row in reader:
            data.append(dict(zip(params, row)))
    return data