Merge pull request #3024 from mroutis/unicode-str

py3: remove string compat related code

dvc/analytics.py

@@ -17,7 +17,7 @@ from dvc.lock import Lock, LockError
 from dvc.repo import Repo
 from dvc.scm import SCM
 from dvc.utils import env2bool, is_binary, makedirs
-from dvc.utils.compat import str, FileNotFoundError
+from dvc.utils.compat import FileNotFoundError
 
 
 logger = logging.getLogger(__name__)

dvc/api.py

@@ -9,7 +9,7 @@ try:
 except ImportError:
     from contextlib import GeneratorContextManager as GCM
 
-from dvc.utils.compat import urlparse, builtin_str
+from dvc.utils.compat import urlparse
 
 import ruamel.yaml
 from voluptuous import Schema, Required, Invalid
@@ -188,8 +188,6 @@ def _import_string(import_name):
 
     :return: imported object
     """
-    import_name = builtin_str(import_name)
-
     if "." in import_name:
         module, obj = import_name.rsplit(".", 1)
     else:

dvc/cache.py

@@ -5,7 +5,6 @@ from collections import defaultdict
 from funcy import cached_property
 
 from dvc.config import Config
-from dvc.utils.compat import builtin_str
 
 
 class CacheConfig(object):
@@ -54,7 +53,7 @@ def _make_remote_property(name):
 
         return Remote(self.repo, name=remote)
 
-    getter.__name__ = builtin_str(name)
+    getter.__name__ = str(name)
     return cached_property(getter)
 
 

dvc/command/pipeline.py

@@ -1,6 +1,5 @@
 import argparse
 import logging
-from dvc.utils.compat import str
 
 from dvc.command.base import CmdBase, append_doc_link, fix_subparsers
 from dvc.exceptions import DvcException
@@ -102,7 +101,7 @@ class CmdPipelineShow(CmdBase):
         tree.show()
 
     def __write_dot(self, target, commands, outs):
-        from dvc.utils.compat import StringIO
+        import io
         import networkx
         from networkx.drawing.nx_pydot import write_dot
 
@@ -112,7 +111,7 @@ class CmdPipelineShow(CmdBase):
         simple_g = networkx.DiGraph()
         simple_g.add_edges_from(edges)
 
-        dot_file = StringIO()
+        dot_file = io.StringIO()
         write_dot(simple_g, dot_file)
         logger.info(dot_file.getvalue())
 

dvc/command/status.py

@@ -1,7 +1,6 @@
 import logging
 
 from dvc.command.data_sync import CmdDataBase
-from dvc.utils.compat import str
 
 
 logger = logging.getLogger(__name__)

dvc/config.py

@@ -12,7 +12,7 @@ from voluptuous import All, Any, Lower, Range, Coerce, Match
 
 from dvc.exceptions import DvcException
 from dvc.exceptions import NotDvcRepoError
-from dvc.utils.compat import open, str
+from dvc.utils.compat import open
 
 logger = logging.getLogger(__name__)
 

dvc/dependency/repo.py

@@ -7,7 +7,6 @@ from funcy import merge
 
 from .local import DependencyLOCAL
 from dvc.external_repo import external_repo
-from dvc.utils.compat import str
 from dvc.exceptions import OutputNotFoundError
 from dvc.exceptions import PathMissingError
 from dvc.utils.fs import fs_copy

dvc/exceptions.py

@@ -3,8 +3,6 @@
 import traceback
 
 from dvc.utils import relpath
-from dvc.utils.compat import builtin_str
-from dvc.utils.compat import str
 
 
 class DvcException(Exception):
@@ -38,7 +36,7 @@ class OutputDuplicationError(DvcException):
     """
 
     def __init__(self, output, stages):
-        assert isinstance(output, (str, builtin_str))
+        assert isinstance(output, str)
         assert all(hasattr(stage, "relpath") for stage in stages)
         msg = (
             "file/directory '{}' is specified as an output in more than one "
@@ -75,7 +73,7 @@ class StagePathAsOutputError(DvcException):
     """
 
     def __init__(self, stage, output):
-        assert isinstance(output, (str, builtin_str))
+        assert isinstance(output, str)
         super(StagePathAsOutputError, self).__init__(
             "'{stage}' is within an output '{output}' of another stage".format(
                 stage=stage.relpath, output=output
@@ -92,7 +90,7 @@ class CircularDependencyError(DvcException):
     """
 
     def __init__(self, dependency):
-        assert isinstance(dependency, (str, builtin_str))
+        assert isinstance(dependency, str)
 
         msg = (
             "file/directory '{}' is specified as an output and as a "
@@ -110,7 +108,7 @@ class ArgumentDuplicationError(DvcException):
     """
 
     def __init__(self, path):
-        assert isinstance(path, (str, builtin_str))
+        assert isinstance(path, str)
         msg = "file '{}' is specified more than once."
         super(ArgumentDuplicationError, self).__init__(msg.format(path))
 

dvc/logger.py

@@ -1,5 +1,6 @@
 """Manages logging configuration for dvc repo."""
 
+import io
 import logging.config
 import logging.handlers
 
@@ -7,8 +8,6 @@ import colorama
 
 from dvc.progress import Tqdm
 from dvc.utils.compat import RecursionError
-from dvc.utils.compat import str
-from dvc.utils.compat import StringIO
 
 
 FOOTER = (
@@ -105,7 +104,7 @@ class ColorFormatter(logging.Formatter):
     def _walk_exc(self, exc_info):
         import traceback
 
-        buffer = StringIO()
+        buffer = io.StringIO()
 
         traceback.print_exception(*exc_info, file=buffer)
 

dvc/output/__init__.py

@@ -11,7 +11,6 @@ from dvc.remote.hdfs import RemoteHDFS
 from dvc.remote.local import RemoteLOCAL
 from dvc.remote.s3 import RemoteS3
 from dvc.scheme import Schemes
-from dvc.utils.compat import str
 from dvc.utils.compat import urlparse
 
 OUTS = [

dvc/output/base.py

@@ -8,7 +8,6 @@ from dvc.cache import NamedCache
 from dvc.exceptions import CollectCacheError
 from dvc.exceptions import DvcException
 from dvc.remote.base import RemoteBASE
-from dvc.utils.compat import str
 from dvc.utils.compat import urlparse
 
 

dvc/output/local.py

@@ -7,7 +7,6 @@ from dvc.output.base import OutputBase
 from dvc.remote.local import RemoteLOCAL
 from dvc.utils import relpath
 from dvc.utils.compat import fspath_py35
-from dvc.utils.compat import str
 from dvc.utils.compat import urlparse
 from dvc.utils.fs import path_isin
 

dvc/path_info.py

@@ -4,16 +4,13 @@ import posixpath
 from funcy import cached_property
 
 from dvc.utils import relpath
-from dvc.utils.compat import basestring
-from dvc.utils.compat import builtin_str
 from dvc.utils.compat import pathlib
-from dvc.utils.compat import str
 from dvc.utils.compat import urlparse
 
 
 class _BasePath(object):
     def overlaps(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         elif self.__class__ != other.__class__:
             return False
@@ -54,7 +51,7 @@ class PathInfo(pathlib.PurePath, _BasePath):
         return relpath(path)
 
     def __repr__(self):
-        return builtin_str("{}: '{}'").format(type(self).__name__, self)
+        return str("{}: '{}'").format(type(self).__name__, self)
 
     # This permits passing it to file utils directly in Python 3.6+
     # With Python 2.7, Python 3.5+ we are stuck with path_info.fspath for now
@@ -71,7 +68,7 @@ class PathInfo(pathlib.PurePath, _BasePath):
         return self.__class__(relpath(self, other))
 
     def isin(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         elif self.__class__ != other.__class__:
             return False
@@ -135,13 +132,13 @@ class URLInfo(_BasePath):
 
     def fill_parts(self, scheme, host, user, port, path):
         assert scheme != "remote"
-        assert isinstance(path, (basestring, _URLPathInfo))
+        assert isinstance(path, (str, bytes, _URLPathInfo))
 
         self.scheme, self.host, self.user = scheme, host, user
         self.port = int(port) if port else self.DEFAULT_PORTS.get(self.scheme)
 
         if isinstance(path, _URLPathInfo):
-            self._spath = builtin_str(path)
+            self._spath = str(path)
             self._path = path
         else:
             if path and path[0] != "/":
@@ -170,7 +167,7 @@ class URLInfo(_BasePath):
         return "{}: '{}'".format(type(self).__name__, self)
 
     def __eq__(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         return (
             self.__class__ == other.__class__
@@ -220,7 +217,7 @@ class URLInfo(_BasePath):
         return _URLPathParents(self)
 
     def relative_to(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         if self.__class__ != other.__class__:
             msg = "'{}' has incompatible class with '{}'".format(self, other)
@@ -231,7 +228,7 @@ class URLInfo(_BasePath):
         return self._path.relative_to(other._path)
 
     def isin(self, other):
-        if isinstance(other, basestring):
+        if isinstance(other, (str, bytes)):
             other = self.__class__(other)
         elif self.__class__ != other.__class__:
             return False

dvc/remote/base.py

@@ -1,6 +1,6 @@
 import errno
 
-from dvc.utils.compat import basestring, FileNotFoundError, str, urlparse
+from dvc.utils.compat import FileNotFoundError, urlparse
 
 import itertools
 import json
@@ -153,7 +153,7 @@ class RemoteBASE(object):
 
     @classmethod
     def supported(cls, config):
-        if isinstance(config, basestring):
+        if isinstance(config, (str, bytes)):
             url = config
         else:
             url = config[Config.SECTION_REMOTE_URL]

dvc/remote/local.py

@@ -30,7 +30,6 @@ from dvc.utils import tmp_fname
 from dvc.utils import walk_files
 from dvc.utils.compat import fspath_py35
 from dvc.utils.compat import open
-from dvc.utils.compat import str
 from dvc.utils.fs import move
 from dvc.utils.fs import remove
 
@@ -411,7 +410,7 @@ class RemoteLOCAL(RemoteBASE):
     def _unprotect_file(path):
         if System.is_symlink(path) or System.is_hardlink(path):
             logger.debug("Unprotecting '{}'".format(path))
-            tmp = os.path.join(os.path.dirname(path), "." + str(uuid()))
+            tmp = os.path.join(os.path.dirname(path), "." + uuid())
 
             # The operations order is important here - if some application
             # would access the file during the process of copyfile then it

dvc/remote/ssh/__init__.py

@@ -17,7 +17,6 @@ from dvc.remote.base import RemoteBASE
 from dvc.remote.pool import get_connection
 from dvc.scheme import Schemes
 from dvc.utils import to_chunks
-from dvc.utils.compat import StringIO
 from dvc.utils.compat import urlparse
 
 logger = logging.getLogger(__name__)
@@ -104,7 +103,7 @@ class RemoteSSH(RemoteBASE):
             ssh_config = paramiko.SSHConfig()
             with open(user_config_file) as f:
                 # For whatever reason parsing directly from f is unreliable
-                f_copy = StringIO(f.read())
+                f_copy = io.StringIO(f.read())
                 ssh_config.parse(f_copy)
             user_ssh_config = ssh_config.lookup(hostname)
         return user_ssh_config

dvc/repo/metrics/show.py

@@ -3,16 +3,15 @@ import errno
 import json
 import logging
 import os
+import io
 
 from jsonpath_ng.ext import parse
 
 from dvc.exceptions import NoMetricsError
 from dvc.exceptions import OutputNotFoundError
 from dvc.repo import locked
-from dvc.utils.compat import builtin_str
 from dvc.utils.compat import csv_reader
 from dvc.utils.compat import open
-from dvc.utils.compat import StringIO
 
 NO_METRICS_FILE_AT_REFERENCE_WARNING = (
     "Metrics file '{}' does not exist at the reference '{}'."
@@ -48,7 +47,7 @@ def _read_metric_hxsv(fd, hxsv_path, delimiter):
     row = indices[0]
     row = int(row) if row else None
     col = indices[1] if len(indices) > 1 and indices[1] else None
-    reader = list(csv.DictReader(fd, delimiter=builtin_str(delimiter)))
+    reader = list(csv.DictReader(fd, delimiter=delimiter))
     return _do_read_metric_xsv(reader, row, col)
 
 
@@ -57,7 +56,7 @@ def _read_metric_xsv(fd, xsv_path, delimiter):
     row = indices[0]
     row = int(row) if row else None
     col = int(indices[1]) if len(indices) > 1 and indices[1] else None
-    reader = list(csv.reader(fd, delimiter=builtin_str(delimiter)))
+    reader = list(csv.reader(fd, delimiter=delimiter))
     return _do_read_metric_xsv(reader, row, col)
 
 
@@ -102,7 +101,7 @@ def _format_csv(content, delimiter):
         "0.67528    0.289545        testing\n"
         "0.671502   0.297848        validation\n"
     """
-    reader = csv_reader(StringIO(content), delimiter=builtin_str(delimiter))
+    reader = csv_reader(io.StringIO(content), delimiter=delimiter)
     rows = [row for row in reader]
     max_widths = [max(map(len, column)) for column in zip(*rows)]
 
@@ -128,10 +127,10 @@ def _format_output(content, typ):
         str: Content in a raw or tabular format.
     """
 
-    if "csv" in str(typ):
+    if "csv" in typ:
         return _format_csv(content, delimiter=",")
 
-    if "tsv" in str(typ):
+    if "tsv" in typ:
         return _format_csv(content, delimiter="\t")
 
     return content

dvc/scm/git/__init__.py

@@ -19,7 +19,6 @@ from dvc.utils import relpath
 from dvc.utils.fs import path_isin
 from dvc.utils.compat import cast_bytes_py2
 from dvc.utils.compat import open
-from dvc.utils.compat import str
 
 
 logger = logging.getLogger(__name__)

dvc/scm/git/tree.py

@@ -1,11 +1,10 @@
+import io
 import errno
 import os
 
 from dvc.exceptions import DvcException
 from dvc.scm.tree import BaseTree
 from dvc.utils import relpath
-from dvc.utils.compat import BytesIO
-from dvc.utils.compat import StringIO
 
 
 # see git-fast-import(1)
@@ -63,8 +62,8 @@ class GitTree(BaseTree):
         # and `open` with default "r" mode returns str)
         data = obj.data_stream.read()
         if mode == "rb":
-            return BytesIO(data)
-        return StringIO(data.decode(encoding))
+            return io.BytesIO(data)
+        return io.StringIO(data.decode(encoding))
 
     def exists(self, path):
         return self.git_object_by_path(path) is not None

dvc/stage.py

@@ -1,4 +1,4 @@
-from dvc.utils.compat import pathlib, str
+from dvc.utils.compat import pathlib
 import logging
 import os
 import re

dvc/system.py

@@ -5,7 +5,6 @@ import shutil
 
 from dvc.utils.compat import fspath
 from dvc.utils.compat import open
-from dvc.utils.compat import str
 
 
 logger = logging.getLogger(__name__)

dvc/utils/__init__.py

@@ -8,20 +8,18 @@ import os
 import re
 import sys
 import time
+import io
 
 import colorama
 import nanotime
 from ruamel.yaml import YAML
 from shortuuid import uuid
 
-from dvc.utils.compat import builtin_str
 from dvc.utils.compat import cast_bytes_py2
 from dvc.utils.compat import fspath
 from dvc.utils.compat import fspath_py35
 from dvc.utils.compat import makedirs as _makedirs
 from dvc.utils.compat import open
-from dvc.utils.compat import str
-from dvc.utils.compat import StringIO
 
 
 logger = logging.getLogger(__name__)
@@ -92,16 +90,14 @@ def dict_filter(d, exclude=()):
     Exclude specified keys from a nested dict
     """
 
-    def fix_key(k):
-        return str(k) if isinstance(k, builtin_str) else k
-
     if isinstance(d, list):
         return [dict_filter(e, exclude) for e in d]
 
     if isinstance(d, dict):
-        items = ((fix_key(k), v) for k, v in d.items())
         return {
-            k: dict_filter(v, exclude) for k, v in items if k not in exclude
+            k: dict_filter(v, exclude)
+            for k, v in d.items()
+            if k not in exclude
         }
 
     return d
@@ -268,7 +264,7 @@ def fix_env(env=None):
 
 def tmp_fname(fname):
     """ Temporary name for a partial download """
-    return fspath(fname) + "." + str(uuid()) + ".tmp"
+    return fspath(fname) + "." + uuid() + ".tmp"
 
 
 def current_timestamp():
@@ -276,11 +272,11 @@ def current_timestamp():
 
 
 def from_yaml_string(s):
-    return YAML().load(StringIO(s))
+    return YAML().load(io.StringIO(s))
 
 
 def to_yaml_string(data):
-    stream = StringIO()
+    stream = io.StringIO()
     yaml = YAML()
     yaml.default_flow_style = False
     yaml.dump(data, stream)

dvc/utils/fs.py

@@ -13,7 +13,6 @@ from dvc.utils import dict_md5
 from dvc.utils import fspath
 from dvc.utils import fspath_py35
 from dvc.utils import relpath
-from dvc.utils.compat import str
 
 
 logger = logging.getLogger(__name__)
@@ -101,7 +100,7 @@ def move(src, dst, mode=None):
     dst = fspath_py35(dst)
 
     dst = os.path.abspath(dst)
-    tmp = "{}.{}".format(dst, str(uuid()))
+    tmp = "{}.{}".format(dst, uuid())
 
     if os.path.islink(src):
         shutil.copy(os.readlink(src), tmp)

tests/basic_env.py

@@ -13,7 +13,6 @@ from git.exc import GitCommandNotFound
 
 from dvc.repo import Repo as DvcRepo
 from dvc.utils.compat import open
-from dvc.utils.compat import str
 from dvc.utils.fs import remove
 
 

tests/dir_helpers.py

@@ -49,7 +49,7 @@ import pytest
 from funcy.py3 import lmap, retry
 
 from dvc.utils import makedirs
-from dvc.utils.compat import basestring, pathlib, fspath, fspath_py35, bytes
+from dvc.utils.compat import pathlib, fspath, fspath_py35
 
 
 __all__ = ["tmp_dir", "scm", "dvc", "repo_template", "run_copy", "erepo_dir"]
@@ -87,7 +87,7 @@ class TmpDir(pathlib.Path):
             )
 
     def gen(self, struct, text=""):
-        if isinstance(struct, (basestring, pathlib.PurePath)):
+        if isinstance(struct, (str, bytes, pathlib.PurePath)):
             struct = {struct: text}
 
         self._gen(struct)
@@ -142,7 +142,7 @@ class TmpDir(pathlib.Path):
 
 
 def _coerce_filenames(filenames):
-    if isinstance(filenames, (basestring, pathlib.PurePath)):
+    if isinstance(filenames, (str, bytes, pathlib.PurePath)):
         filenames = [filenames]
     return lmap(fspath, filenames)
 

tests/func/test_data_cloud.py

@@ -25,7 +25,6 @@ from dvc.remote.base import STATUS_DELETED
 from dvc.remote.base import STATUS_NEW
 from dvc.remote.base import STATUS_OK
 from dvc.utils import file_md5
-from dvc.utils.compat import str
 from dvc.utils.stage import dump_stage_file
 from dvc.utils.stage import load_stage_file
 from tests.basic_env import TestDvc

tests/func/test_import_url.py

@@ -8,7 +8,6 @@ from mock import patch
 import dvc
 from dvc.main import main
 from dvc.utils import makedirs
-from dvc.utils.compat import str
 from tests.basic_env import TestDvc
 from tests.utils import spy
 

tests/func/test_repro.py

@@ -29,7 +29,6 @@ from dvc.system import System
 from dvc.utils import file_md5
 from dvc.utils import relpath
 from dvc.utils.compat import pathlib
-from dvc.utils.compat import str
 from dvc.utils.compat import urljoin
 from dvc.utils.stage import dump_stage_file
 from dvc.utils.stage import load_stage_file

tests/func/test_scm.py

@@ -6,7 +6,6 @@ from dvc.scm import Git
 from dvc.scm import NoSCM
 from dvc.scm import SCM
 from dvc.system import System
-from dvc.utils.compat import str  # noqa: F401
 from tests.basic_env import TestDir
 from tests.basic_env import TestGit
 from tests.basic_env import TestGitSubmodule

tests/func/test_state.py

@@ -6,7 +6,6 @@ from dvc.main import main
 from dvc.path_info import PathInfo
 from dvc.state import State
 from dvc.utils import file_md5
-from dvc.utils.compat import str
 
 
 def test_state(dvc_repo, repo_dir):

tests/unit/test_analytics.py

@@ -7,10 +7,6 @@ from voluptuous import Schema, Any
 
 from dvc import analytics
 from dvc.cli import parse_args
-from dvc.utils.compat import str, builtin_str
-
-
-string = Any(str, builtin_str)
 
 
 @pytest.fixture
@@ -51,10 +47,10 @@ def test_collect_and_send_report(mock_json, mock_daemon, tmp_global_config):
 def test_runtime_info(tmp_global_config):
     schema = Schema(
         {
-            "dvc_version": string,
+            "dvc_version": str,
             "is_binary": bool,
             "scm_class": Any("Git", None),
-            "user_id": string,
+            "user_id": str,
             "system_info": dict,
         },
         required=True,
@@ -109,19 +105,19 @@ def test_system_info():
                 "windows_version_build": int,
                 "windows_version_major": int,
                 "windows_version_minor": int,
-                "windows_version_service_pack": string,
+                "windows_version_service_pack": str,
             }
         )
 
     if system == "Darwin":
-        schema = schema.extend({"mac_version": string})
+        schema = schema.extend({"mac_version": str})
 
     if system == "Linux":
         schema = schema.extend(
             {
-                "linux_distro": string,
-                "linux_distro_like": string,
-                "linux_distro_version": string,
+                "linux_distro": str,
+                "linux_distro_like": str,
+                "linux_distro_version": str,
             }
         )
 

tests/unit/utils/test_fs.py

@@ -10,7 +10,6 @@ from dvc.path_info import PathInfo
 from dvc.scm.tree import WorkingTree
 from dvc.system import System
 from dvc.utils import relpath
-from dvc.utils.compat import str
 from dvc.utils.fs import BasePathNotInCheckedPathException
 from dvc.utils.fs import contains_symlink_up_to
 from dvc.utils.fs import get_inode