ebcdic 2.0.0__tar.gz

ebcdic-2.0.0/LICENSE.txt

@@ -0,0 +1,24 @@
+Copyright (c) 2013 - 2026, Thomas Aglassinger
+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.
+
+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 HOLDER 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.

ebcdic-2.0.0/PKG-INFO

@@ -0,0 +1,128 @@
+Metadata-Version: 2.4
+Name: ebcdic
+Version: 2.0.0
+Summary: Additional EBCDIC codecs
+Keywords: codec,text,unicode,ebcdic
+Author-email: Thomas Aglassinger <roskakori@users.sourceforge.net>
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-Expression: BSD-2-Clause
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Text Processing
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+License-File: LICENSE.txt
+Project-URL: Changes, https://github.com/roskakori/CodecMapper/blob/master/CHANGES.md
+Project-URL: Documentation, https://github.com/roskakori/CodecMapper/blob/master/ebcdic/README.md
+Project-URL: Donate, https://roskakori.at/donate/donate-python-ebcdic/
+Project-URL: Homepage, https://pypi.python.org/pypi/ebcdic
+Project-URL: Issue Tracker, https://github.com/roskakori/CodecMapper/issues
+Project-URL: Source, https://github.com/roskakori/CodecMapper.git
+
+# ebcdic
+
+`ebcdic` is a Python package adding additional EBCDIC codecs for data exchange with legacy systems.
+
+[EBCDIC](https://en.wikipedia.org/wiki/EBCDIC) is short for "Extended Binary Coded Decimal Interchange Code" and is a family of character encodings that is mainly used on mainframe computers. There is no real point in using it unless you have to exchange data with legacy systems.
+
+This package requires Python 3.9 or later.
+
+For compatibility with Python 2.7 to 3.3, use [version 1.1.1](https://pypi.org/project/ebcdic/1.1.1/).
+
+For compatibility with Python 2.6 to 3.2, use [version 1.0.0](https://pypi.org/project/ebcdic/1.0.0/).
+
+## Installation
+
+The `ebcdic` package is available from <https://pypi.python.org/pypi/ebcdic> and can be installed using pip:
+
+```console
+pip install ebcdic
+```
+
+## Example usage
+
+To encode `'hello world'` on EBCDIC systems in German-speaking countries, use:
+
+```pycon
+>>> import ebcdic
+>>> 'hello world'.encode('cp1141')
+b'\x88\x85\x93\x93\x96@\xa6\x96\x99\x93\x84O'
+```
+
+## Supported codecs
+
+The `ebcdic` package includes EBCDIC codecs for the following regions:
+
+- cp290 - Japan (Katakana)
+- cp420 - Arabic bilingual
+- cp424 - Israel (Hebrew)
+- cp833 - Korea Extended (single byte)
+- cp838 - Thailand
+- cp870 - Eastern Europe (Poland, Hungary, Czech, Slovakia, Slovenia, Croatian, Serbia, Bulgarian); represents Latin-2
+- cp1097 - Iran (Farsi)
+- cp1140 - Australia, Brazil, Canada, New Zealand, Portugal, South Africa, USA
+- cp1141 - Austria, Germany, Switzerland
+- cp1142 - Denmark, Norway
+- cp1143 - Finland, Sweden
+- cp1144 - Italy
+- cp1145 - Latin America, Spain
+- cp1146 - Great Britain, Ireland, North Ireland
+- cp1147 - France
+- cp1148 - International
+- cp1148ms - International, Microsoft interpretation; similar to cp1148 except that 0x15 is mapped to 0x85 ("next line") instead of 0x0a ("linefeed")
+- cp1149 - Iceland
+
+It also includes legacy codecs:
+
+- cp037 - Australia, Brazil, Canada, New Zealand, Portugal, South Africa; similar to cp1140 but without Euro sign
+- cp273 - Austria, Germany, Switzerland; similar to cp1141 but without Euro sign
+- cp277 - Denmark, Norway; similar to cp1142 but without Euro sign
+- cp278 - Finland, Sweden; similar to cp1143 but without Euro sign
+- cp280 - Italy; similar to cp1141 but without Euro sign
+- cp284 - Latin America, Spain; similar to cp1145 but without Euro sign
+- cp285 - Great Britain, Ireland, North Ireland; similar to cp1146 but without Euro sign
+- cp297 - France; similar to cp1147 but without Euro sign
+- cp500 - International; similar to cp1148 but without Euro sign
+- cp500ms - International, Microsoft interpretation; identical to codecs.cp500 similar to ebcdic.cp500 except that 0x15 is mapped to 0x85 ("next line") instead of 0x0a ("linefeed")
+- cp871 - Iceland; similar to cp1149 but without Euro sign
+- cp875 - Greece; similar to cp9067 but without Euro sign and a few other characters
+- cp1025 - Cyrillic
+- cp1047 - Open Systems (MVS C compiler)
+- cp1112 - Estonia, Latvia, Lithuania (Baltic)
+- cp1122 - Estonia; similar to cp1157 but without Euro sign
+- cp1123 - Ukraine; similar to cp1158 but without Euro sign
+
+Codecs in the standard library overrule some of these codecs. At the time of this writing this concerns cp037, cp273 (since 3.4), cp500 and cp1140.
+
+To see get a list of EBCDIC codecs that are already provided by different sources, use `ebcdic.ignored_codec_names()`. For example, with Python 3.13 the result is:
+
+```pycon
+>>> ebcdic.ignored_codec_names()
+['cp037', 'cp1140', 'cp273', 'cp424', 'cp500', 'cp875']
+```
+
+## Unsupported codecs
+
+According to a [comprehensive list of code pages](https://www.aivosto.com/articles/charsets-codepages.html), there are additional codecs this package does not support yet. Possible reasons and solutions are:
+
+1. It's a double byte codec e.g., cp834 (Korea). Technically `CodecMapper` can support them by increasing the mapping size from 256 to 65536. Due to lack of test data and access to Asian mainframes this was deemed too experimental for now.
+2. The codec contains combining characters e.g., cp1132 (Lao) which allows representing more than 256 characters combining several characters.
+3. Java does not include a mapping for the respective code page e.g., cp410/880 (Cyrillic). You can add such a codec based on the information found at the link above and submit an enhancement request for the Java standard library. Once it is released, add the new codec to the `build.xml` as described below.
+4. I missed a codec. Open an issue on GitHub at <https://github.com/roskakori/CodecMapper/issues>, and it will be added with the next version.
+
+## Source code
+
+These codecs have been generated using CodecMapper, available from <https://github.com/roskakori/CodecMapper>. Read the [CONTRIBUTING.md](https://github.com/roskakori/CodecMapper/blob/master/CONTRIBUTING.md) to build the ebcdic package from the source and learn how to add more codecs.
+
+## License
+
+Copyright (c) 2013 - 2026, Thomas Aglassinger
+All rights reserved.
+
+Distributed under the BSD license, see [LICENSE.txt](https://github.com/roskakori/CodecMapper/blob/master/LICENSE.txt) for more information.
+

ebcdic-2.0.0/README.md

@@ -0,0 +1,101 @@
+# ebcdic
+
+`ebcdic` is a Python package adding additional EBCDIC codecs for data exchange with legacy systems.
+
+[EBCDIC](https://en.wikipedia.org/wiki/EBCDIC) is short for "Extended Binary Coded Decimal Interchange Code" and is a family of character encodings that is mainly used on mainframe computers. There is no real point in using it unless you have to exchange data with legacy systems.
+
+This package requires Python 3.9 or later.
+
+For compatibility with Python 2.7 to 3.3, use [version 1.1.1](https://pypi.org/project/ebcdic/1.1.1/).
+
+For compatibility with Python 2.6 to 3.2, use [version 1.0.0](https://pypi.org/project/ebcdic/1.0.0/).
+
+## Installation
+
+The `ebcdic` package is available from <https://pypi.python.org/pypi/ebcdic> and can be installed using pip:
+
+```console
+pip install ebcdic
+```
+
+## Example usage
+
+To encode `'hello world'` on EBCDIC systems in German-speaking countries, use:
+
+```pycon
+>>> import ebcdic
+>>> 'hello world'.encode('cp1141')
+b'\x88\x85\x93\x93\x96@\xa6\x96\x99\x93\x84O'
+```
+
+## Supported codecs
+
+The `ebcdic` package includes EBCDIC codecs for the following regions:
+
+- cp290 - Japan (Katakana)
+- cp420 - Arabic bilingual
+- cp424 - Israel (Hebrew)
+- cp833 - Korea Extended (single byte)
+- cp838 - Thailand
+- cp870 - Eastern Europe (Poland, Hungary, Czech, Slovakia, Slovenia, Croatian, Serbia, Bulgarian); represents Latin-2
+- cp1097 - Iran (Farsi)
+- cp1140 - Australia, Brazil, Canada, New Zealand, Portugal, South Africa, USA
+- cp1141 - Austria, Germany, Switzerland
+- cp1142 - Denmark, Norway
+- cp1143 - Finland, Sweden
+- cp1144 - Italy
+- cp1145 - Latin America, Spain
+- cp1146 - Great Britain, Ireland, North Ireland
+- cp1147 - France
+- cp1148 - International
+- cp1148ms - International, Microsoft interpretation; similar to cp1148 except that 0x15 is mapped to 0x85 ("next line") instead of 0x0a ("linefeed")
+- cp1149 - Iceland
+
+It also includes legacy codecs:
+
+- cp037 - Australia, Brazil, Canada, New Zealand, Portugal, South Africa; similar to cp1140 but without Euro sign
+- cp273 - Austria, Germany, Switzerland; similar to cp1141 but without Euro sign
+- cp277 - Denmark, Norway; similar to cp1142 but without Euro sign
+- cp278 - Finland, Sweden; similar to cp1143 but without Euro sign
+- cp280 - Italy; similar to cp1141 but without Euro sign
+- cp284 - Latin America, Spain; similar to cp1145 but without Euro sign
+- cp285 - Great Britain, Ireland, North Ireland; similar to cp1146 but without Euro sign
+- cp297 - France; similar to cp1147 but without Euro sign
+- cp500 - International; similar to cp1148 but without Euro sign
+- cp500ms - International, Microsoft interpretation; identical to codecs.cp500 similar to ebcdic.cp500 except that 0x15 is mapped to 0x85 ("next line") instead of 0x0a ("linefeed")
+- cp871 - Iceland; similar to cp1149 but without Euro sign
+- cp875 - Greece; similar to cp9067 but without Euro sign and a few other characters
+- cp1025 - Cyrillic
+- cp1047 - Open Systems (MVS C compiler)
+- cp1112 - Estonia, Latvia, Lithuania (Baltic)
+- cp1122 - Estonia; similar to cp1157 but without Euro sign
+- cp1123 - Ukraine; similar to cp1158 but without Euro sign
+
+Codecs in the standard library overrule some of these codecs. At the time of this writing this concerns cp037, cp273 (since 3.4), cp500 and cp1140.
+
+To see get a list of EBCDIC codecs that are already provided by different sources, use `ebcdic.ignored_codec_names()`. For example, with Python 3.13 the result is:
+
+```pycon
+>>> ebcdic.ignored_codec_names()
+['cp037', 'cp1140', 'cp273', 'cp424', 'cp500', 'cp875']
+```
+
+## Unsupported codecs
+
+According to a [comprehensive list of code pages](https://www.aivosto.com/articles/charsets-codepages.html), there are additional codecs this package does not support yet. Possible reasons and solutions are:
+
+1. It's a double byte codec e.g., cp834 (Korea). Technically `CodecMapper` can support them by increasing the mapping size from 256 to 65536. Due to lack of test data and access to Asian mainframes this was deemed too experimental for now.
+2. The codec contains combining characters e.g., cp1132 (Lao) which allows representing more than 256 characters combining several characters.
+3. Java does not include a mapping for the respective code page e.g., cp410/880 (Cyrillic). You can add such a codec based on the information found at the link above and submit an enhancement request for the Java standard library. Once it is released, add the new codec to the `build.xml` as described below.
+4. I missed a codec. Open an issue on GitHub at <https://github.com/roskakori/CodecMapper/issues>, and it will be added with the next version.
+
+## Source code
+
+These codecs have been generated using CodecMapper, available from <https://github.com/roskakori/CodecMapper>. Read the [CONTRIBUTING.md](https://github.com/roskakori/CodecMapper/blob/master/CONTRIBUTING.md) to build the ebcdic package from the source and learn how to add more codecs.
+
+## License
+
+Copyright (c) 2013 - 2026, Thomas Aglassinger
+All rights reserved.
+
+Distributed under the BSD license, see [LICENSE.txt](https://github.com/roskakori/CodecMapper/blob/master/LICENSE.txt) for more information.

ebcdic-2.0.0/ebcdic/__init__.py

@@ -0,0 +1,99 @@
+"""
+EBCDIC codecs for data exchange with legacy systems.
+
+For more information, visit <https://pypi.python.org/pypi/ebcdic/>.
+"""
+# Copyright (c) 2013 - 2026, Thomas Aglassinger
+# 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.
+#
+# 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 HOLDER 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.
+
+import codecs
+
+from ._version import __version__, __version_info__
+
+__all__ = [
+    "codec_names",
+    "ignored_codec_names",
+    "lookup",
+    "__version__",
+    "__version_info__",
+]
+
+
+def _codec_names():
+    """
+    Names of the codecs included in the ebcdic package.
+    """
+    import glob
+    import os.path
+
+    package_folder = os.path.dirname(__file__)
+    for codec_path in glob.glob(os.path.join(package_folder, "cp*.py")):
+        codec_name = os.path.splitext(os.path.basename(codec_path))[0]
+        yield codec_name
+
+
+def _create_codec_name_to_info_map():
+    result = {}
+    for codec_name in codec_names:
+        codec_module = __import__("ebcdic." + codec_name, globals(), locals(), ["getregentry"])
+        result[codec_name] = codec_module.getregentry()
+    return result
+
+
+def _find_ebcdic_codec(code_name):
+    """
+    The `codec.CodecInfo` matching `codec_name` provided it is part of the
+    package, otherwise `None`.
+    """
+    return _codec_name_to_info_map.get(code_name)
+
+
+def ignored_codec_names():
+    """
+    A list of codec names in this package that are ignored because they are
+    already provided by other means, e.g. the standard library.
+    """
+    return [
+        codec_name
+        for codec_name, codec_info in sorted(_codec_name_to_info_map.items())
+        if codec_info != codecs.lookup(codec_name)
+    ]
+
+
+def lookup(codec_name):
+    """
+    The `codecs.CodecInfo` for the EBCDIC codec `codec_name`. An unknown
+    `codecs_name` raises a `LookupError`.
+    """
+    result = _find_ebcdic_codec(codec_name)
+    if result is None:
+        raise LookupError(f"EBCDIC codec is {codec_name!r} but must be one of: {codec_names}")
+    return result
+
+
+# Names of the codecs included in the ebcdic package.
+codec_names = sorted(_codec_names())
+_codec_name_to_info_map = _create_codec_name_to_info_map()
+codecs.register(_find_ebcdic_codec)

ebcdic-2.0.0/ebcdic/_version.py

@@ -0,0 +1,2 @@
+__version__ = "2.0.0"
+__version_info__ = tuple(int(item) if item.isdigit() else item for item in __version__.split("."))

ebcdic-2.0.0/ebcdic/cp037.py

@@ -0,0 +1,311 @@
+"""
+Python Character Mapping Codec cp037 generated from 'temp/cp037.txt' with gencodec.py.
+"""
+
+import codecs
+
+
+# Codec APIs
+class Codec(codecs.Codec):
+    def encode(self, text, errors='strict'):
+        return codecs.charmap_encode(text, errors, encoding_table)
+
+    def decode(self, data, errors='strict'):
+        return codecs.charmap_decode(data, errors, decoding_table)
+
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+    def encode(self, text, final=False):
+        return codecs.charmap_encode(text, self.errors, encoding_table)[0]
+
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+    def decode(self, data, final=False):
+        return codecs.charmap_decode(data, self.errors, decoding_table)[0]
+
+
+class StreamWriter(Codec, codecs.StreamWriter):
+    pass
+
+
+class StreamReader(Codec, codecs.StreamReader):
+    pass
+
+
+# encodings module API
+def getregentry():
+    return codecs.CodecInfo(
+        name='cp037',
+        encode=Codec().encode,
+        decode=Codec().decode,
+        incrementalencoder=IncrementalEncoder,
+        incrementaldecoder=IncrementalDecoder,
+        streamreader=StreamReader,
+        streamwriter=StreamWriter,
+    )
+
+
+# Decoding Table
+
+decoding_table = (
+    '\x00'      # 0x00 -> NULL
+    '\x01'      # 0x01 -> START OF HEADING
+    '\x02'      # 0x02 -> START OF TEXT
+    '\x03'      # 0x03 -> END OF TEXT
+    '\x9c'      # 0x04 -> STRING TERMINATOR
+    '\t'        # 0x05 -> CHARACTER TABULATION
+    '\x86'      # 0x06 -> START OF SELECTED AREA
+    '\x7f'      # 0x07 -> DELETE
+    '\x97'      # 0x08 -> END OF GUARDED AREA
+    '\x8d'      # 0x09 -> REVERSE LINE FEED
+    '\x8e'      # 0x0A -> SINGLE SHIFT TWO
+    '\x0b'      # 0x0B -> LINE TABULATION
+    '\x0c'      # 0x0C -> FORM FEED (FF)
+    '\r'        # 0x0D -> CARRIAGE RETURN (CR)
+    '\x0e'      # 0x0E -> SHIFT OUT
+    '\x0f'      # 0x0F -> SHIFT IN
+    '\x10'      # 0x10 -> DATA LINK ESCAPE
+    '\x11'      # 0x11 -> DEVICE CONTROL ONE
+    '\x12'      # 0x12 -> DEVICE CONTROL TWO
+    '\x13'      # 0x13 -> DEVICE CONTROL THREE
+    '\x9d'      # 0x14 -> OPERATING SYSTEM COMMAND
+    '\n'        # 0x15 -> LINE FEED (LF)
+    '\x08'      # 0x16 -> BACKSPACE
+    '\x87'      # 0x17 -> END OF SELECTED AREA
+    '\x18'      # 0x18 -> CANCEL
+    '\x19'      # 0x19 -> END OF MEDIUM
+    '\x92'      # 0x1A -> PRIVATE USE TWO
+    '\x8f'      # 0x1B -> SINGLE SHIFT THREE
+    '\x1c'      # 0x1C -> INFORMATION SEPARATOR FOUR
+    '\x1d'      # 0x1D -> INFORMATION SEPARATOR THREE
+    '\x1e'      # 0x1E -> INFORMATION SEPARATOR TWO
+    '\x1f'      # 0x1F -> INFORMATION SEPARATOR ONE
+    '\x80'      # 0x20 -> PADDING CHARACTER
+    '\x81'      # 0x21 -> HIGH OCTET PRESET
+    '\x82'      # 0x22 -> BREAK PERMITTED HERE
+    '\x83'      # 0x23 -> NO BREAK HERE
+    '\x84'      # 0x24 -> LATIN 1 SUPPLEMENT 84
+    '\n'        # 0x25 -> LINE FEED (LF)
+    '\x17'      # 0x26 -> END OF TRANSMISSION BLOCK
+    '\x1b'      # 0x27 -> ESCAPE
+    '\x88'      # 0x28 -> CHARACTER TABULATION SET
+    '\x89'      # 0x29 -> CHARACTER TABULATION WITH JUSTIFICATION
+    '\x8a'      # 0x2A -> LINE TABULATION SET
+    '\x8b'      # 0x2B -> PARTIAL LINE FORWARD
+    '\x8c'      # 0x2C -> PARTIAL LINE BACKWARD
+    '\x05'      # 0x2D -> ENQUIRY
+    '\x06'      # 0x2E -> ACKNOWLEDGE
+    '\x07'      # 0x2F -> BEL
+    '\x90'      # 0x30 -> DEVICE CONTROL STRING
+    '\x91'      # 0x31 -> PRIVATE USE ONE
+    '\x16'      # 0x32 -> SYNCHRONOUS IDLE
+    '\x93'      # 0x33 -> SET TRANSMIT STATE
+    '\x94'      # 0x34 -> CANCEL CHARACTER
+    '\x95'      # 0x35 -> MESSAGE WAITING
+    '\x96'      # 0x36 -> START OF GUARDED AREA
+    '\x04'      # 0x37 -> END OF TRANSMISSION
+    '\x98'      # 0x38 -> START OF STRING
+    '\x99'      # 0x39 -> SINGLE GRAPHIC CHARACTER INTRODUCER
+    '\x9a'      # 0x3A -> SINGLE CHARACTER INTRODUCER
+    '\x9b'      # 0x3B -> CONTROL SEQUENCE INTRODUCER
+    '\x14'      # 0x3C -> DEVICE CONTROL FOUR
+    '\x15'      # 0x3D -> NEGATIVE ACKNOWLEDGE
+    '\x9e'      # 0x3E -> PRIVACY MESSAGE
+    '\x1a'      # 0x3F -> SUBSTITUTE
+    ' '         # 0x40 -> SPACE
+    '\xa0'      # 0x41 -> NO-BREAK SPACE
+    '\xe2'      # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+    '\xe4'      # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
+    '\xe0'      # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
+    '\xe1'      # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
+    '\xe3'      # 0x46 -> LATIN SMALL LETTER A WITH TILDE
+    '\xe5'      # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
+    '\xe7'      # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
+    '\xf1'      # 0x49 -> LATIN SMALL LETTER N WITH TILDE
+    '\xa2'      # 0x4A -> CENT SIGN
+    '.'         # 0x4B -> FULL STOP
+    '<'         # 0x4C -> LESS-THAN SIGN
+    '('         # 0x4D -> LEFT PARENTHESIS
+    '+'         # 0x4E -> PLUS SIGN
+    '|'         # 0x4F -> VERTICAL LINE
+    '&'         # 0x50 -> AMPERSAND
+    '\xe9'      # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
+    '\xea'      # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+    '\xeb'      # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
+    '\xe8'      # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
+    '\xed'      # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
+    '\xee'      # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+    '\xef'      # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
+    '\xec'      # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
+    '\xdf'      # 0x59 -> LATIN SMALL LETTER SHARP S
+    '!'         # 0x5A -> EXCLAMATION MARK
+    '$'         # 0x5B -> DOLLAR SIGN
+    '*'         # 0x5C -> ASTERISK
+    ')'         # 0x5D -> RIGHT PARENTHESIS
+    ';'         # 0x5E -> SEMICOLON
+    '\xac'      # 0x5F -> NOT SIGN
+    '-'         # 0x60 -> HYPHEN-MINUS
+    '/'         # 0x61 -> SOLIDUS
+    '\xc2'      # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+    '\xc4'      # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+    '\xc0'      # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
+    '\xc1'      # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
+    '\xc3'      # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
+    '\xc5'      # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+    '\xc7'      # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
+    '\xd1'      # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
+    '\xa6'      # 0x6A -> BROKEN BAR
+    ','         # 0x6B -> COMMA
+    '%'         # 0x6C -> PERCENT SIGN
+    '_'         # 0x6D -> LOW LINE
+    '>'         # 0x6E -> GREATER-THAN SIGN
+    '?'         # 0x6F -> QUESTION MARK
+    '\xf8'      # 0x70 -> LATIN SMALL LETTER O WITH STROKE
+    '\xc9'      # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
+    '\xca'      # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+    '\xcb'      # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+    '\xc8'      # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
+    '\xcd'      # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
+    '\xce'      # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+    '\xcf'      # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+    '\xcc'      # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
+    '`'         # 0x79 -> GRAVE ACCENT
+    ':'         # 0x7A -> COLON
+    '#'         # 0x7B -> NUMBER SIGN
+    '@'         # 0x7C -> COMMERCIAL AT
+    "'"         # 0x7D -> APOSTROPHE
+    '='         # 0x7E -> EQUALS SIGN
+    '"'         # 0x7F -> QUOTATION MARK
+    '\xd8'      # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
+    'a'         # 0x81 -> LATIN SMALL LETTER A
+    'b'         # 0x82 -> LATIN SMALL LETTER B
+    'c'         # 0x83 -> LATIN SMALL LETTER C
+    'd'         # 0x84 -> LATIN SMALL LETTER D
+    'e'         # 0x85 -> LATIN SMALL LETTER E
+    'f'         # 0x86 -> LATIN SMALL LETTER F
+    'g'         # 0x87 -> LATIN SMALL LETTER G
+    'h'         # 0x88 -> LATIN SMALL LETTER H
+    'i'         # 0x89 -> LATIN SMALL LETTER I
+    '\xab'      # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+    '\xbb'      # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+    '\xf0'      # 0x8C -> LATIN SMALL LETTER ETH
+    '\xfd'      # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
+    '\xfe'      # 0x8E -> LATIN SMALL LETTER THORN
+    '\xb1'      # 0x8F -> PLUS-MINUS SIGN
+    '\xb0'      # 0x90 -> DEGREE SIGN
+    'j'         # 0x91 -> LATIN SMALL LETTER J
+    'k'         # 0x92 -> LATIN SMALL LETTER K
+    'l'         # 0x93 -> LATIN SMALL LETTER L
+    'm'         # 0x94 -> LATIN SMALL LETTER M
+    'n'         # 0x95 -> LATIN SMALL LETTER N
+    'o'         # 0x96 -> LATIN SMALL LETTER O
+    'p'         # 0x97 -> LATIN SMALL LETTER P
+    'q'         # 0x98 -> LATIN SMALL LETTER Q
+    'r'         # 0x99 -> LATIN SMALL LETTER R
+    '\xaa'      # 0x9A -> FEMININE ORDINAL INDICATOR
+    '\xba'      # 0x9B -> MASCULINE ORDINAL INDICATOR
+    '\xe6'      # 0x9C -> LATIN SMALL LETTER AE
+    '\xb8'      # 0x9D -> CEDILLA
+    '\xc6'      # 0x9E -> LATIN CAPITAL LETTER AE
+    '\xa4'      # 0x9F -> CURRENCY SIGN
+    '\xb5'      # 0xA0 -> MICRO SIGN
+    '~'         # 0xA1 -> TILDE
+    's'         # 0xA2 -> LATIN SMALL LETTER S
+    't'         # 0xA3 -> LATIN SMALL LETTER T
+    'u'         # 0xA4 -> LATIN SMALL LETTER U
+    'v'         # 0xA5 -> LATIN SMALL LETTER V
+    'w'         # 0xA6 -> LATIN SMALL LETTER W
+    'x'         # 0xA7 -> LATIN SMALL LETTER X
+    'y'         # 0xA8 -> LATIN SMALL LETTER Y
+    'z'         # 0xA9 -> LATIN SMALL LETTER Z
+    '\xa1'      # 0xAA -> INVERTED EXCLAMATION MARK
+    '\xbf'      # 0xAB -> INVERTED QUESTION MARK
+    '\xd0'      # 0xAC -> LATIN CAPITAL LETTER ETH
+    '\xdd'      # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
+    '\xde'      # 0xAE -> LATIN CAPITAL LETTER THORN
+    '\xae'      # 0xAF -> REGISTERED SIGN
+    '^'         # 0xB0 -> CIRCUMFLEX ACCENT
+    '\xa3'      # 0xB1 -> POUND SIGN
+    '\xa5'      # 0xB2 -> YEN SIGN
+    '\xb7'      # 0xB3 -> MIDDLE DOT
+    '\xa9'      # 0xB4 -> COPYRIGHT SIGN
+    '\xa7'      # 0xB5 -> SECTION SIGN
+    '\xb6'      # 0xB6 -> PILCROW SIGN
+    '\xbc'      # 0xB7 -> VULGAR FRACTION ONE QUARTER
+    '\xbd'      # 0xB8 -> VULGAR FRACTION ONE HALF
+    '\xbe'      # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+    '['         # 0xBA -> LEFT SQUARE BRACKET
+    ']'         # 0xBB -> RIGHT SQUARE BRACKET
+    '\xaf'      # 0xBC -> MACRON
+    '\xa8'      # 0xBD -> DIAERESIS
+    '\xb4'      # 0xBE -> ACUTE ACCENT
+    '\xd7'      # 0xBF -> MULTIPLICATION SIGN
+    '{'         # 0xC0 -> LEFT CURLY BRACKET
+    'A'         # 0xC1 -> LATIN CAPITAL LETTER A
+    'B'         # 0xC2 -> LATIN CAPITAL LETTER B
+    'C'         # 0xC3 -> LATIN CAPITAL LETTER C
+    'D'         # 0xC4 -> LATIN CAPITAL LETTER D
+    'E'         # 0xC5 -> LATIN CAPITAL LETTER E
+    'F'         # 0xC6 -> LATIN CAPITAL LETTER F
+    'G'         # 0xC7 -> LATIN CAPITAL LETTER G
+    'H'         # 0xC8 -> LATIN CAPITAL LETTER H
+    'I'         # 0xC9 -> LATIN CAPITAL LETTER I
+    '\xad'      # 0xCA -> SOFT HYPHEN
+    '\xf4'      # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+    '\xf6'      # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
+    '\xf2'      # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
+    '\xf3'      # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
+    '\xf5'      # 0xCF -> LATIN SMALL LETTER O WITH TILDE
+    '}'         # 0xD0 -> RIGHT CURLY BRACKET
+    'J'         # 0xD1 -> LATIN CAPITAL LETTER J
+    'K'         # 0xD2 -> LATIN CAPITAL LETTER K
+    'L'         # 0xD3 -> LATIN CAPITAL LETTER L
+    'M'         # 0xD4 -> LATIN CAPITAL LETTER M
+    'N'         # 0xD5 -> LATIN CAPITAL LETTER N
+    'O'         # 0xD6 -> LATIN CAPITAL LETTER O
+    'P'         # 0xD7 -> LATIN CAPITAL LETTER P
+    'Q'         # 0xD8 -> LATIN CAPITAL LETTER Q
+    'R'         # 0xD9 -> LATIN CAPITAL LETTER R
+    '\xb9'      # 0xDA -> SUPERSCRIPT ONE
+    '\xfb'      # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+    '\xfc'      # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
+    '\xf9'      # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
+    '\xfa'      # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
+    '\xff'      # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
+    '\\'        # 0xE0 -> REVERSE SOLIDUS
+    '\xf7'      # 0xE1 -> DIVISION SIGN
+    'S'         # 0xE2 -> LATIN CAPITAL LETTER S
+    'T'         # 0xE3 -> LATIN CAPITAL LETTER T
+    'U'         # 0xE4 -> LATIN CAPITAL LETTER U
+    'V'         # 0xE5 -> LATIN CAPITAL LETTER V
+    'W'         # 0xE6 -> LATIN CAPITAL LETTER W
+    'X'         # 0xE7 -> LATIN CAPITAL LETTER X
+    'Y'         # 0xE8 -> LATIN CAPITAL LETTER Y
+    'Z'         # 0xE9 -> LATIN CAPITAL LETTER Z
+    '\xb2'      # 0xEA -> SUPERSCRIPT TWO
+    '\xd4'      # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+    '\xd6'      # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
+    '\xd2'      # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
+    '\xd3'      # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
+    '\xd5'      # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
+    '0'         # 0xF0 -> DIGIT ZERO
+    '1'         # 0xF1 -> DIGIT ONE
+    '2'         # 0xF2 -> DIGIT TWO
+    '3'         # 0xF3 -> DIGIT THREE
+    '4'         # 0xF4 -> DIGIT FOUR
+    '5'         # 0xF5 -> DIGIT FIVE
+    '6'         # 0xF6 -> DIGIT SIX
+    '7'         # 0xF7 -> DIGIT SEVEN
+    '8'         # 0xF8 -> DIGIT EIGHT
+    '9'         # 0xF9 -> DIGIT NINE
+    '\xb3'      # 0xFA -> SUPERSCRIPT THREE
+    '\xdb'      # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+    '\xdc'      # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+    '\xd9'      # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
+    '\xda'      # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
+    '\x9f'      # 0xFF -> APPLICATION PROGRAM COMMAND
+)
+
+
+# Encoding table
+encoding_table = codecs.charmap_build(decoding_table)