Skip to content

gh-53144: Use encodings.aliases in email mod #136701

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 5 additions & 28 deletions Lib/email/charset.py
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@

from email import errors
from email.encoders import encode_7or8bit
from encodings.aliases import aliases as ALIASES


# Flags for types of header encodings
Expand Down Expand Up @@ -61,35 +62,11 @@
'utf-8': (SHORTEST, BASE64, 'utf-8'),
}

# Aliases for other commonly-used names for character sets. Map
# them to the real ones used in email.
ALIASES = {
'latin_1': 'iso-8859-1',
# The email module uses the slower latin-1 encoding
ALIASES.update({
'latin-1': 'iso-8859-1',
'latin_2': 'iso-8859-2',
'latin-2': 'iso-8859-2',
'latin_3': 'iso-8859-3',
'latin-3': 'iso-8859-3',
'latin_4': 'iso-8859-4',
'latin-4': 'iso-8859-4',
'latin_5': 'iso-8859-9',
'latin-5': 'iso-8859-9',
'latin_6': 'iso-8859-10',
'latin-6': 'iso-8859-10',
'latin_7': 'iso-8859-13',
'latin-7': 'iso-8859-13',
'latin_8': 'iso-8859-14',
'latin-8': 'iso-8859-14',
'latin_9': 'iso-8859-15',
'latin-9': 'iso-8859-15',
'latin_10':'iso-8859-16',
'latin-10':'iso-8859-16',
'cp949': 'ks_c_5601-1987',
'euc_jp': 'euc-jp',
'euc_kr': 'euc-kr',
'ascii': 'us-ascii',
}

'latin_1': 'iso-8859-1',
})

# Map charsets to their Unicode codec strings.
CODEC_MAP = {
Expand Down
9 changes: 9 additions & 0 deletions Lib/encodings/aliases.py
Original file line number Diff line number Diff line change
Expand Up @@ -318,6 +318,7 @@
'iso_ir_157' : 'iso8859_10',
'l6' : 'iso8859_10',
'latin6' : 'iso8859_10',
'latin_6' : 'iso8859_10',

# iso8859_11 codec
'thai' : 'iso8859_11',
Expand All @@ -328,6 +329,7 @@
'iso_8859_13' : 'iso8859_13',
'l7' : 'iso8859_13',
'latin7' : 'iso8859_13',
'latin_7' : 'iso8859_13',

# iso8859_14 codec
'iso_8859_14' : 'iso8859_14',
Expand All @@ -336,18 +338,21 @@
'iso_ir_199' : 'iso8859_14',
'l8' : 'iso8859_14',
'latin8' : 'iso8859_14',
'latin_8' : 'iso8859_14',

# iso8859_15 codec
'iso_8859_15' : 'iso8859_15',
'l9' : 'iso8859_15',
'latin9' : 'iso8859_15',
'latin_9' : 'iso8859_15',

# iso8859_16 codec
'iso_8859_16' : 'iso8859_16',
'iso_8859_16_2001' : 'iso8859_16',
'iso_ir_226' : 'iso8859_16',
'l10' : 'iso8859_16',
'latin10' : 'iso8859_16',
'latin_10' : 'iso8859_16',

# iso8859_2 codec
'csisolatin2' : 'iso8859_2',
Expand All @@ -356,6 +361,7 @@
'iso_ir_101' : 'iso8859_2',
'l2' : 'iso8859_2',
'latin2' : 'iso8859_2',
'latin_2' : 'iso8859_2',

# iso8859_3 codec
'csisolatin3' : 'iso8859_3',
Expand All @@ -364,6 +370,7 @@
'iso_ir_109' : 'iso8859_3',
'l3' : 'iso8859_3',
'latin3' : 'iso8859_3',
'latin_3' : 'iso8859_3',

# iso8859_4 codec
'csisolatin4' : 'iso8859_4',
Expand All @@ -372,6 +379,7 @@
'iso_ir_110' : 'iso8859_4',
'l4' : 'iso8859_4',
'latin4' : 'iso8859_4',
'latin_4' : 'iso8859_4',

# iso8859_5 codec
'csisolatincyrillic' : 'iso8859_5',
Expand Down Expand Up @@ -415,6 +423,7 @@
'iso_ir_148' : 'iso8859_9',
'l5' : 'iso8859_9',
'latin5' : 'iso8859_9',
'latin_5' : 'iso8859_9',

# johab codec
'cp1361' : 'johab',
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
:mod:`email`: Use :mod:`!encodings.aliases` for alias lookup
:mod:`!encodings.aliases`: Add ``latin_*`` aliases.
Loading