diff --git a/.travis.yml b/.travis.yml
index 0575f12..807650e 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,6 +1,5 @@
language: python
python:
- - "2.7"
- "3.4"
- "3.5"
- "3.6"
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6e85906..ecd0bc3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [Unreleased]
+## Removed
+- Support for Python 2 ([#346](https://github.com/pdfminer/pdfminer.six/pull/346))
+
### Changed
- Enforce pep8 coding style by adding flake8 to CI ([#345](https://github.com/pdfminer/pdfminer.six/pull/345))
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index e56866a..071a306 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -29,8 +29,9 @@ Any contribution is appreciated! You might want to:
* Pull requests should be merged to develop, not master. This ensures that master always equals the released version.
* Include unit tests when possible. In case of bugs, this will help to prevent the same mistake in the future. In case
of features, this will show that your code works correctly.
-* Code should work for Python 2.7 and Python 3.x (for now), conform to PEP8 code style (enforced by
- [flake8](http://flake8.pycqa.org/en/latest/)) and properly documented with docstrings.
+* Code should work for Python 3.4+.
+* Code should conform to PEP8 coding style.
+* New features should be well documented using docstrings.
* Check spelling and grammar.
* Don't forget to update the [CHANGELOG.md](CHANGELOG.md#[Unreleased])
diff --git a/README.md b/README.md
index 6ea2015..1b2d755 100644
--- a/README.md
+++ b/README.md
@@ -37,8 +37,8 @@ Features
How to use
----------
- * Install Python 2.7 or newer. Note that Python 2 support is dropped at
- January, 2020.
+ * Install Python 3.4 or newer
+ * Install
`pip install pdfminer.six`
diff --git a/pdfminer/__init__.py b/pdfminer/__init__.py
index 9fbee72..4e12f18 100644
--- a/pdfminer/__init__.py
+++ b/pdfminer/__init__.py
@@ -1,6 +1,5 @@
-# -*- coding: utf-8 -*-
"""
-Fork of PDFMiner using six for Python 2+3 compatibility
+Fork of PDFMiner
PDFMiner is a tool for extracting information from PDF documents.
Unlike other PDF-related tools, it focuses entirely on getting and analyzing
@@ -10,18 +9,8 @@ It includes a PDF converter that can transform PDF files into other text
formats (such as HTML). It has an extensible PDF parser that can be used for
other purposes instead of text analysis.
"""
-import sys
-import warnings
__version__ = '20191110'
-
-if sys.version_info < (3, 0):
- warnings.warn('On January 1st, 2020, '
- 'pdfminer.six will stop supporting Python 2. '
- 'Please upgrade to Python 3. '
- 'For more information see '
- 'https://github.com/pdfminer/pdfminer.six/issues/194')
-
if __name__ == '__main__':
print(__version__)
diff --git a/pdfminer/arcfour.py b/pdfminer/arcfour.py
index c09a370..c771c0b 100644
--- a/pdfminer/arcfour.py
+++ b/pdfminer/arcfour.py
@@ -1,15 +1,11 @@
-
-
""" Python implementation of Arcfour encryption algorithm.
See https://en.wikipedia.org/wiki/RC4
This code is in the public domain.
"""
-import six # Python 2+3 compatibility
-
-class Arcfour(object):
+class Arcfour:
def __init__(self, key):
# because Py3 range is not indexable
@@ -17,7 +13,7 @@ class Arcfour(object):
j = 0
klen = len(key)
for i in range(256):
- j = (j + s[i] + six.indexbytes(key, i % klen)) % 256
+ j = (j + s[i] + key[i % klen]) % 256
(s[i], s[j]) = (s[j], s[i])
self.s = s
(self.i, self.j) = (0, 0)
@@ -27,12 +23,12 @@ class Arcfour(object):
(i, j) = (self.i, self.j)
s = self.s
r = b''
- for c in six.iterbytes(data):
+ for c in iter(data):
i = (i+1) % 256
j = (j+s[i]) % 256
(s[i], s[j]) = (s[j], s[i])
k = s[(s[i]+s[j]) % 256]
- r += six.int2byte(c ^ k)
+ r += bytes((c ^ k,))
(self.i, self.j) = (i, j)
return r
diff --git a/pdfminer/ascii85.py b/pdfminer/ascii85.py
index 35be786..cde3f90 100644
--- a/pdfminer/ascii85.py
+++ b/pdfminer/ascii85.py
@@ -1,5 +1,3 @@
-
-
""" Python implementation of ASCII85/ASCIIHex decoder (Adobe version).
This code is in the public domain.
@@ -9,8 +7,6 @@ This code is in the public domain.
import re
import struct
-import six # Python 2+3 compatibility
-
# ascii85decode(data)
def ascii85decode(data):
@@ -26,8 +22,8 @@ def ascii85decode(data):
"""
n = b = 0
out = b''
- for i in six.iterbytes(data):
- c = six.int2byte(i)
+ for i in iter(data):
+ c = bytes((i,))
if b'!' <= c and c <= b'u':
n += 1
b = b*85+(ord(c)-33)
@@ -47,9 +43,8 @@ def ascii85decode(data):
# asciihexdecode(data)
-hex_re = re.compile(b'([a-f0-9]{2})', re.IGNORECASE)
-trail_re = re.compile(b'^(?:[a-f0-9]{2}|[ \t\n\r\f\v])*'
- b'([a-f0-9])[ \t\n\r\f\v>]*$', re.IGNORECASE)
+hex_re = re.compile(br'([a-f\d]{2})', re.IGNORECASE)
+trail_re = re.compile(br'^(?:[a-f\d]{2}|\s)*([a-f\d])[\s>]*$', re.IGNORECASE)
def asciihexdecode(data):
@@ -64,7 +59,7 @@ def asciihexdecode(data):
"""
def decode(x):
i = int(x, 16)
- return six.int2byte(i)
+ return bytes((i,))
out = b''
for x in hex_re.findall(data):
diff --git a/pdfminer/ccitt.py b/pdfminer/ccitt.py
index b4a4612..1c00eb0 100644
--- a/pdfminer/ccitt.py
+++ b/pdfminer/ccitt.py
@@ -1,4 +1,3 @@
-
# CCITT Fax decoder
#
# Bugs: uncompressed mode untested.
@@ -15,20 +14,12 @@
import sys
import array
-import six # Python 2+3 compatibility
-if six.PY3:
- def get_bytes(data):
- for byte in data:
- yield byte
-else:
- def get_bytes(data):
- for char in data:
- yield ord(char)
+def get_bytes(data):
+ yield from data
-class BitParser(object):
-
+class BitParser:
def __init__(self):
self._pos = 0
return
diff --git a/pdfminer/cmapdb.py b/pdfminer/cmapdb.py
index 0c246e8..7c0b772 100644
--- a/pdfminer/cmapdb.py
+++ b/pdfminer/cmapdb.py
@@ -13,10 +13,7 @@ import sys
import os
import os.path
import gzip
-try:
- import cPickle as pickle
-except ImportError:
- import pickle as pickle
+import pickle as pickle
import struct
import logging
from .psparser import PSStackParser
@@ -29,7 +26,6 @@ from .encodingdb import name2unicode
from .utils import choplist
from .utils import nunpack
-import six
log = logging.getLogger(__name__)
@@ -38,7 +34,7 @@ class CMapError(Exception):
pass
-class CMapBase(object):
+class CMapBase:
debug = 0
@@ -77,7 +73,7 @@ class CMap(CMapBase):
assert isinstance(cmap, CMap), str(type(cmap))
def copy(dst, src):
- for (k, v) in six.iteritems(src):
+ for (k, v) in src.items():
if isinstance(v, dict):
d = {}
dst[k] = d
@@ -90,7 +86,7 @@ class CMap(CMapBase):
def decode(self, code):
log.debug('decode: %r, %r', self, code)
d = self.code2cid
- for i in six.iterbytes(code):
+ for i in iter(code):
if i in d:
d = d[i]
if isinstance(d, int):
@@ -104,7 +100,7 @@ class CMap(CMapBase):
if code2cid is None:
code2cid = self.code2cid
code = ()
- for (k, v) in sorted(six.iteritems(code2cid)):
+ for (k, v) in sorted(code2cid.items()):
c = code+(k,)
if isinstance(v, int):
out.write('code %r = cid %d\n' % (c, v))
@@ -148,7 +144,7 @@ class UnicodeMap(CMapBase):
return self.cid2unichr[cid]
def dump(self, out=sys.stdout):
- for (k, v) in sorted(six.iteritems(self.cid2unichr)):
+ for (k, v) in sorted(self.cid2unichr.items()):
out.write('cid %d = unicode %r\n' % (k, v))
return
@@ -183,7 +179,7 @@ class FileUnicodeMap(UnicodeMap):
# Interpret as UTF-16BE.
self.cid2unichr[cid] = code.decode('UTF-16BE', 'ignore')
elif isinstance(code, int):
- self.cid2unichr[cid] = six.unichr(code)
+ self.cid2unichr[cid] = chr(code)
else:
raise TypeError(code)
return
@@ -211,7 +207,7 @@ class PyUnicodeMap(UnicodeMap):
return
-class CMapDB(object):
+class CMapDB:
_cmap_cache = {}
_umap_cache = {}
diff --git a/pdfminer/converter.py b/pdfminer/converter.py
index fb333a2..1dc9583 100644
--- a/pdfminer/converter.py
+++ b/pdfminer/converter.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
import logging
import re
import sys
@@ -23,7 +22,6 @@ from .utils import enc
from .utils import bbox2str
from . import utils
-import six
log = logging.getLogger(__name__)
@@ -115,7 +113,7 @@ class PDFLayoutAnalyzer(PDFTextDevice):
graphicstate):
try:
text = font.to_unichr(cid)
- assert isinstance(text, six.text_type), str(type(text))
+ assert isinstance(text, str), str(type(text))
except PDFUnicodeNotDefined:
text = self.handle_undefined_char(font, cid)
textwidth = font.char_width(cid)
@@ -168,7 +166,7 @@ class PDFConverter(PDFLayoutAnalyzer):
self.outfp_binary = False
else:
try:
- self.outfp.write(u"é")
+ self.outfp.write("é")
self.outfp_binary = False
except TypeError:
self.outfp_binary = True
@@ -186,7 +184,7 @@ class TextConverter(PDFConverter):
def write_text(self, text):
text = utils.compatible_encode_method(text, self.codec, 'ignore')
- if six.PY3 and self.outfp_binary:
+ if self.outfp_binary:
text = text.encode()
self.outfp.write(text)
return
@@ -285,7 +283,7 @@ class HTMLConverter(PDFConverter):
return
def write_footer(self):
- page_links = ['%s' % (i, i)
+ page_links = ['{}'.format(i, i)
for i in range(1, self.pageno)]
s = '
Page: %s
\n' % \
', '.join(page_links)
@@ -385,8 +383,8 @@ class HTMLConverter(PDFConverter):
if self.showpageno:
self.write('