Remove six dependency

README.rst

@@ -11,8 +11,7 @@ Background
 
 This library provides a fast, standalone way to read and write `WARC
 Format <https://en.wikipedia.org/wiki/Web_ARChive>`__ commonly used in
-web archives. Python 3.7+ (minimally only needing
-`six <https://pythonhosted.org/six/>`__ as an external dependency)
+web archives. Python 3.7+.
 
 warcio supports reading and writing of WARC files compliant with both the `WARC 1.0 <http://bibnum.bnf.fr/WARC/WARC_ISO_28500_version1_latestdraft.pdf>`__
 and `WARC 1.1 <http://bibnum.bnf.fr/WARC/WARC_ISO_28500_version1-1_latestdraft.pdf>`__ ISO standards.
@@ -59,7 +58,7 @@ the format (ARC or WARC), record type, the record headers, http headers
 
 .. code:: python
 
-    class ArcWarcRecord(object):
+    class ArcWarcRecord:
         def __init__(self, *args):
             (self.format, self.rec_type, self.rec_headers, self.raw_stream,
              self.http_headers, self.content_type, self.length) = args

setup.py

@@ -19,9 +19,7 @@
     provides=[
         'warcio',
         ],
-    install_requires=[
-        'six',
-        ],
+    install_requires=[],
     zip_safe=True,
     entry_points="""
         [console_scripts]

test/test_archiveiterator.py

@@ -16,7 +16,7 @@
 
 
 #==============================================================================
-class TestArchiveIterator(object):
+class TestArchiveIterator:
     def _load_archive(self, filename, offset=0, cls=ArchiveIterator,
                      errs_expected=0, **kwargs):
 

test/test_bufferedreaders.py

@@ -101,8 +101,6 @@
 
 from contextlib import closing
 
-import six
-
 import zlib
 import pytest
 
@@ -177,7 +175,7 @@ def test_err_chunk_cut_off():
 
 
 def print_str(string):
-    return string.decode('utf-8') if six.PY3 else string
+    return string.decode('utf-8')
 
 
 

test/test_capture_http.py

@@ -21,7 +21,7 @@
 
 
 # ==================================================================
-class TestCaptureHttpBin(object):
+class TestCaptureHttpBin:
     @classmethod
     def setup_class(cls):
         from httpbin import app as httpbin_app

test/test_check_digest_examples.py

@@ -21,7 +21,7 @@ def pytest_generate_tests(metafunc):
         metafunc.parametrize('test_filename', files)
 
 
-class TestExamplesDigest(object):
+class TestExamplesDigest:
     def check_helper(self, args, expected_exit_value, capsys):
         exit_value = None
         try:

test/test_limitreader.py

@@ -3,7 +3,7 @@
 
 from io import BytesIO
 
-class TestLimitReader(object):
+class TestLimitReader:
     def test_limit_reader_1(self):
         assert b'abcdefghji' == LimitReader(BytesIO(b'abcdefghjiklmnopqrstuvwxyz'), 10).read(26)
 

test/test_statusandheaders.py

@@ -91,7 +91,7 @@
 
 
 from warcio.statusandheaders import StatusAndHeadersParser, StatusAndHeaders
-from six import StringIO
+from io import StringIO
 import pytest
 
 

test/test_utils.py

@@ -14,7 +14,7 @@
     pass
 
 
-class TestUtils(object):
+class TestUtils:
     def test_headers_to_str_headers(self):
         result = [('foo', 'bar'), ('baz', 'barf')]
 
@@ -77,14 +77,14 @@ def test_to_native_str(self):
     def test_open_exclusive(self):
         temp_dir = tempfile.mkdtemp('warctest')
         full_name = os.path.join(temp_dir, 'foo.txt')
-        with utils.open(full_name, 'xb') as fh:
+        with open(full_name, 'xb') as fh:
             fh.write(b'test\r\nfoo')
 
         with pytest.raises(OSError):
-            with utils.open(full_name, 'xb') as fh:
+            with open(full_name, 'xb') as fh:
                 fh.write(b'test\r\nfoo')
 
-        with utils.open(full_name, 'rb') as fh:
+        with open(full_name, 'rb') as fh:
             assert fh.read() == b'test\r\nfoo'
 
         os.remove(full_name)

test/test_writer.py

@@ -560,7 +560,7 @@ def record_sampler(request):
 
 
 # ============================================================================
-class TestWarcWriter(object):
+class TestWarcWriter:
     @classmethod
     def _validate_record_content_len(cls, stream):
         for record in ArchiveIterator(stream, no_record_parse=True):

warcio/archiveiterator.py

@@ -6,7 +6,6 @@
 from warcio.utils import BUFF_SIZE
 
 import sys
-import six
 
 # ============================================================================
 class UnseekableYetTellable:
@@ -23,7 +22,7 @@ def read(self, size=-1):
         return result
 
 # ============================================================================
-class ArchiveIterator(six.Iterator):
+class ArchiveIterator:
     """ Iterate over records in WARC and ARC files, both gzip chunk
     compressed and uncompressed
 
@@ -91,7 +90,7 @@ def __iter__(self):
         return self.the_iter
 
     def __next__(self):
-        return six.next(self.the_iter)
+        return next(self.the_iter)
 
     def close(self):
         self.record = None

warcio/bufferedreaders.py

@@ -37,7 +37,7 @@ def brotli_decompressor():
 
 
 #=================================================================
-class BufferedReader(object):
+class BufferedReader:
     """
     A wrapping line reader which wraps an existing reader.
     Read operations operate on underlying buffer, which is filled to

warcio/capture_http.py

@@ -2,13 +2,13 @@
 
 from io import BytesIO
 
-from six.moves import http_client as httplib
+import http.client as httplib
 
 from contextlib import contextmanager
 
 from array import array
 
-from warcio.utils import to_native_str, BUFF_SIZE, open
+from warcio.utils import to_native_str, BUFF_SIZE
 from warcio.warcwriter import WARCWriter, BufferWARCWriter
 
 from tempfile import SpooledTemporaryFile
@@ -19,7 +19,7 @@
 
 
 # ============================================================================
-class RecordingStream(object):
+class RecordingStream:
     def __init__(self, fp, recorder):
         self.fp = fp
         self.recorder = recorder
@@ -130,7 +130,7 @@ def putrequest(self, *args, **kwargs):
 
 
 # ============================================================================
-class RequestRecorder(object):
+class RequestRecorder:
     def __init__(self, writer, filter_func=None, record_ip=True):
         self.writer = writer
         self.filter_func = filter_func

warcio/checker.py

@@ -11,7 +11,7 @@ def _read_entire_stream(stream):
             break
 
 
-class Checker(object):
+class Checker:
     def __init__(self, cmd):
         self.inputs = cmd.inputs
         self.verbose = cmd.verbose

warcio/digestverifyingreader.py

@@ -7,7 +7,7 @@
 
 
 # ============================================================================
-class DigestChecker(object):
+class DigestChecker:
     def __init__(self, kind=None):
         self._problem = []
         self._passed = None

warcio/extractor.py

@@ -5,7 +5,7 @@
 
 
 # ============================================================================
-class Extractor(object):
+class Extractor:
     READ_SIZE = BUFF_SIZE * 4
 
     def __init__(self, filename, offset):

warcio/indexer.py

@@ -9,7 +9,7 @@
 
 
 # ============================================================================
-class Indexer(object):
+class Indexer:
     field_names = {}
 
     def __init__(self, fields, inputs, output, verify_http=False):

warcio/limitreader.py

@@ -1,5 +1,5 @@
 # ============================================================================
-class LimitReader(object):
+class LimitReader:
     """
     A reader which will not read more than specified limit
     """

warcio/recompressor.py

@@ -11,7 +11,7 @@
 
 
 # ============================================================================
-class Recompressor(object):
+class Recompressor:
     def __init__(self, filename, output, verbose=False):
         self.filename = filename
         self.output = output

warcio/recordbuilder.py

@@ -1,4 +1,3 @@
-import six
 import tempfile
 
 from datetime import datetime, timezone
@@ -10,7 +9,7 @@
 from warcio.utils import to_native_str, BUFF_SIZE, Digester
 
 #=================================================================
-class RecordBuilder(object):
+class RecordBuilder:
     REVISIT_PROFILE = 'http://netpreserve.org/warc/1.0/revisit/identical-payload-digest'
     REVISIT_PROFILE_1_1 = 'http://netpreserve.org/warc/1.1/revisit/identical-payload-digest'
 
@@ -44,7 +43,7 @@ def create_warcinfo_record(self, filename, info):
         warc_headers.add_header('WARC-Date', self.curr_warc_date())
 
         warcinfo = BytesIO()
-        for name, value in six.iteritems(info):
+        for name, value in info.items():
             if not value:
                 continue
 

warcio/recordloader.py

@@ -10,14 +10,12 @@
 
 from warcio.timeutils import timestamp_to_iso_date
 
-from six.moves import zip
-
 import logging
 logger = logging.getLogger(__name__)
 
 
 #=================================================================
-class ArcWarcRecord(object):
+class ArcWarcRecord:
     def __init__(self, *args, **kwargs):
         (self.format, self.rec_type, self.rec_headers, self.raw_stream,
          self.http_headers, self.content_type, self.length) = args
@@ -45,7 +43,7 @@ def content_stream(self):
 
 
 #=================================================================
-class ArcWarcRecordLoader(object):
+class ArcWarcRecordLoader:
     WARC_TYPES = ['WARC/1.1', 'WARC/1.0', 'WARC/0.17', 'WARC/0.18']
 
     HTTP_TYPES = ['HTTP/1.0', 'HTTP/1.1']
@@ -269,7 +267,7 @@ def _ensure_target_uri_format(self, rec_headers):
 
 
 #=================================================================
-class ARCHeadersParser(object):
+class ARCHeadersParser:
     # ARC 1.0 headers
     ARC_HEADERS = ["uri", "ip-address", "archive-date",
                        "content-type", "length"]

warcio/statusandheaders.py

@@ -2,17 +2,15 @@
 Representation and parsing of HTTP-style status + headers
 """
 
-from six.moves import range
-from six import iteritems
 from warcio.utils import to_native_str, headers_to_str_headers
 import uuid
 
-from six.moves.urllib.parse import quote
+from urllib.parse import quote
 import re
 
 
 #=================================================================
-class StatusAndHeaders(object):
+class StatusAndHeaders:
     ENCODE_HEADER_RX = re.compile(r'[=]["\']?([^;"]+)["\']?(?=[;]?)')
     """
     Representation of parsed http-style status line and headers
@@ -224,7 +222,7 @@ def _strip_count(string, total_read):
 
 
 #=================================================================
-class StatusAndHeadersParser(object):
+class StatusAndHeadersParser:
     """
     Parser which consumes a stream support readline() to read
     status and headers and return a StatusAndHeaders object