Remove Python 2 compatibility code (#401)

Author: kurtmckee

LICENSE

@@ -18,41 +18,3 @@ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
 LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
 OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
 WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-
-compat code from IPython py3compat.py and encoding.py, which is licensed
-the terms of the Modified BSD License (also known as New or
-Revised or 3-Clause BSD)
-
-- Copyright (c) 2008-2014, IPython Development Team
-- Copyright (c) 2001-2007, Fernando Perez <fernando.perez@colorado.edu>
-- Copyright (c) 2001, Janko Hauser <jhauser@zscout.de>
-- Copyright (c) 2001, Nathaniel Gray <n8gray@caltech.edu>
-
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are
-met:
-
-Redistributions of source code must retain the above copyright notice,
-this list of conditions and the following disclaimer.
-
-Redistributions in binary form must reproduce the above copyright notice,
-this list of conditions and the following disclaimer in the documentation
-and/or other materials provided with the distribution.
-
-Neither the name of the IPython Development Team nor the names of its
-contributors may be used to endorse or promote products derived from this
-software without specific prior written permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
-IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
-CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
-PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

pypandoc/__init__.py

@@ -5,12 +5,14 @@
 import sys
 import tempfile
 import textwrap
+import typing
+import urllib.parse
+import urllib.request
 from pathlib import Path
 from typing import Iterable, Iterator, Union
 
 from .handler import _check_log_handler, logger
 from .pandoc_download import DEFAULT_TARGET_FOLDER, download_pandoc
-from .py3compat import cast_bytes, cast_unicode, url2path, urlparse
 
 __author__ = "Juho Vepsäläinen"
 __author_email__ = "bebraw@gmail.com"
@@ -53,7 +55,7 @@
 
 
 def convert_text(
-    source: str,
+    source: typing.Union[str, bytes],
     to: str,
     format: str,
     extra_args: Iterable = (),
@@ -66,7 +68,7 @@ def convert_text(
 ) -> str:
     """Converts given `source` from `format` to `to`.
 
-    :param str source: Unicode string or bytes (see encoding)
+    :param source: Unicode string or bytes (see encoding)
 
     :param str to: format into which the input should be converted;
         can be one of `pypandoc.get_pandoc_formats()[1]`
@@ -106,7 +108,10 @@ def convert_text(
         if pandoc is not found; make sure it has been installed
         and is available at path.
     """
-    source = _as_unicode(source, encoding)
+
+    if isinstance(source, bytes):
+        source = source.decode(encoding, errors="ignore")
+
     return _convert_input(
         source,
         format,
@@ -286,7 +291,7 @@ def _identify_path(source) -> bool:
     if not is_path:
         try:
             # check if it's an URL
-            result = urlparse(source)
+            result = urllib.parse.urlparse(source)
             if result.scheme in ["http", "https"]:
                 is_path = True
             elif result.scheme and result.netloc and result.path:
@@ -303,7 +308,7 @@ def _identify_path(source) -> bool:
 def _is_network_path(source):
     try:
         # check if it's an URL
-        result = urlparse(source)
+        result = urllib.parse.urlparse(source)
         if result.scheme in ["http", "https"]:
             return True
         elif result.scheme and result.netloc and result.path:
@@ -320,17 +325,6 @@ def _identify_format_from_path(sourcefile: str, format: str) -> str:
     return format or os.path.splitext(sourcefile)[1].strip(".")
 
 
-def _as_unicode(source: any, encoding: str) -> any:
-    if encoding != "utf-8":
-        # if a source and a different encoding is given,
-        # try to decode the source into a string
-        try:
-            source = cast_unicode(source, encoding=encoding)
-        except (UnicodeDecodeError, UnicodeEncodeError):
-            pass
-    return source
-
-
 def normalize_format(fmt):
     formats = {
         "dbk": "docbook",
@@ -404,7 +398,7 @@ def _validate_formats(format, to, outputfile):
 
 
 def _convert_input(
-    source,
+    source: str,
     format,
     input_type,
     to,
@@ -509,19 +503,9 @@ def _convert_input(
         )
 
     if string_input:
-        try:
-            source = cast_bytes(source, encoding="utf-8")
-        except (UnicodeDecodeError, UnicodeEncodeError):
-            # assume that it is already a utf-8 encoded string
-            pass
-    try:
-        stdout, stderr = p.communicate(source if string_input else None)
-    except OSError:
-        # this is happening only on Py2.6 when pandoc dies before reading all
-        # the input. We treat that the same as when we exit with an error...
-        raise RuntimeError(
-            'Pandoc died with exitcode "%s" during conversion.' % (p.returncode)
-        )
+        if isinstance(source, str):
+            source = source.encode("utf-8")
+    stdout, stderr = p.communicate(source if string_input else None)
 
     try:
         if not (to in ["odt", "docx", "epub", "epub3", "pdf"] and outputfile == "-"):
@@ -957,6 +941,10 @@ def ensure_pandoc_installed(
         _ensure_pandoc_path()
 
 
+def url2path(url):
+    return urllib.request.url2pathname(urllib.parse.urlparse(url).path)
+
+
 # -----------------------------------------------------------------------------
 # Internal state management
 # -----------------------------------------------------------------------------

pypandoc/pandoc_download.py

@@ -6,14 +6,10 @@
 import subprocess
 import sys
 import tempfile
-import urllib
+import urllib.error
+import urllib.request
 from typing import Union
 
-try:
-    from urllib.request import urlopen
-except ImportError:
-    from urllib import urlopen
-
 from .handler import _check_log_handler, logger
 
 DEFAULT_TARGET_FOLDER = {
@@ -47,13 +43,13 @@ def _get_pandoc_urls(version="latest"):
     )
     # try to open the url
     try:
-        response = urlopen(url)
+        response = urllib.request.urlopen(url)
         version_url_frags = response.url.split("/")
         version = version_url_frags[-1]
     except urllib.error.HTTPError:
         raise RuntimeError(f"Invalid pandoc version {version}.")
     # read the HTML content
-    response = urlopen(
+    response = urllib.request.urlopen(
         f"https://github.com/jgm/pandoc/releases/expanded_assets/{version}"
     )
     content = response.read()
@@ -264,7 +260,7 @@ def download_pandoc(
     else:
         logger.info(f"Downloading pandoc from {url} ...")
         # https://stackoverflow.com/questions/30627937/
-        response = urlopen(url)
+        response = urllib.request.urlopen(url)
         with open(filename, "wb") as out_file:
             shutil.copyfileobj(response, out_file)
 

pypandoc/py3compat.py

@@ -13,9 +13,10 @@
 import unittest
 import warnings
 from pathlib import Path
+from urllib.parse import urljoin
+from urllib.request import pathname2url
 
 import pypandoc
-from pypandoc.py3compat import path2url
 
 
 @contextlib.contextmanager
@@ -239,7 +240,7 @@ def test_basic_conversion_from_file_url(self):
             expected = "some title{0}=========={0}{0}".format(os.linesep)
             # this keeps the : (which should be '|' on windows but pandoc
             # doesn't like it
-            file_url = path2url(file_name)
+            file_url = urljoin("file:", pathname2url(file_name))
             assert pypandoc._identify_path(file_url)
 
             received = pypandoc.convert_file(file_url, "rst")