�
L�g?G � �� � d Z ddlZddlZddlZddlZddlmZmZmZm Z ddl
Z
ddl m Z ddl
mZmZmZmZmZmZmZmZmZmZmZ dedefd�Zdedefd �Zded
ee eef defd �Z d ee defd
�Z dedefd�Z ej d� � Z dedefd�Z!dedefd�Z"dedefd�Z#dedefd�Z$dedefd�Z% ej d� � Z& ej d� � Z'd ee defd�Z(dedefd�Z)dedefd�Z*dedefd�Z+ ej dej, ej- z � � Z.dedefd �Z/ ej d � � Z0d e1de1fd �Z2d e1de1fd �Z3dedefd!�Z4d ee defd"�Z5dedefd#�Z6dS )$a�
The `ftfy.fixes` module contains the individual fixes that :func:`ftfy.fix_text`
can perform, and provides the functions that are named in "explanations"
such as the output of :func:`ftfy.fix_and_explain`.
Two of these functions are particularly useful on their own, as more robust
versions of functions in the Python standard library:
- :func:`ftfy.fixes.decode_escapes`
- :func:`ftfy.fixes.unescape_html`
� N)�Any�List�Match�Tuple)�is_bad) �ALTERED_UTF8_RE�
C1_CONTROL_RE�
CONTROL_CHARS�DOUBLE_QUOTE_RE�
HTML_ENTITIES�HTML_ENTITY_RE� LIGATURES�
LOSSY_UTF8_RE�SINGLE_QUOTE_RE�UTF8_DETECTOR_RE� WIDTH_MAP�text�returnc �b � t j dt d�� � t j | � � S )z?
Deprecated copy of `ftfy.fix_encoding_and_explain()`.
zB`fix_encoding_and_explain()` has moved to the main module of ftfy.� ��
stacklevel)�warnings�warn�DeprecationWarning�ftfy�fix_encoding_and_explain�r s �Z/home/asafur/pinokio/api/open-webui.git/app/env/lib/python3.11/site-packages/ftfy/fixes.pyr r $ s9 � �
�M�L���� � � �
� (�� .� .�.� c �b � t j dt d�� � t j | � � S )z3
Deprecated copy of `ftfy.fix_encoding()`.
z6`fix_encoding()` has moved to the main module of ftfy.r r )r r r r � fix_encodingr s r r" r" 0 s9 � �
�M�@���� � � �
� �T� "� "�"r �planc �d � t j dt d�� � t j | |� � S )z1
Deprecated copy of `ftfy.apply_plan()`.
z4`apply_plan()` has moved to the main module of ftfy.r r )r r r r �
apply_plan)r r# s r r% r% < s: � �
�M�>���� � � �
�?�4�� &� &�&r �matchc � � | � d� � }|t v r
t | S |� d� � r t j |� � }d|v r|S |S |S )z\
Replace one matched HTML entity with the character it represents,
if possible.
r z&#�;)�groupr �
startswith�html�unescape)r& r � unescapeds r �_unescape_fixupr. H si � �
�;�;�q�>�>�D� �}� � � �T�"�"�
� � �� � �
� � �t�,�,� � �)� � ��K� � �� r c �6 � t j t | � � S )uQ
Decode HTML entities and character references, including some nonstandard
ones written in all-caps.
Python has a built-in called `html.unescape` that can decode HTML escapes,
including a bunch of messy edge cases such as decoding escapes without
semicolons such as "&".
If you know you've got HTML-escaped text, applying `html.unescape` is the
right way to convert it to plain text. But in ambiguous situations, that
would create false positives. For example, the informally written text
"this¬ that" should not automatically be decoded as "this¬ that".
In this function, we decode the escape sequences that appear in the
`html.entities.html5` dictionary, as long as they are the unambiguous ones
that end in semicolons.
We also decode all-caps versions of Latin letters and common symbols.
If a database contains the name 'P&EACUTE;REZ', we can read that and intuit
that it was supposed to say 'PÉREZ'. This is limited to a smaller set of
entities, because there are many instances where entity names are
case-sensitive in complicated ways.
>>> unescape_html('<tag>')
'<tag>'
>>> unescape_html('𝒥ohn ℋancock')
'𝒥ohn ℋancock'
>>> unescape_html('✓')
'✓'
>>> unescape_html('Pérez')
'Pérez'
>>> unescape_html('P&EACUTE;REZ')
'PÉREZ'
>>> unescape_html('BUNDESSTRA&SZLIG;E')
'BUNDESSTRASSE'
>>> unescape_html('ñ Ñ &NTILDE; &nTILDE;')
'ñ Ñ Ñ &nTILDE;'
)r
�subr. r s r �
unescape_htmlr1 ] s � �Z � �o�t� 4� 4�4r z\[((?:\d|;)*)([a-zA-Z])c �8 � t � d| � � S )a
Strip out "ANSI" terminal escape sequences, such as those that produce
colored text on Unix.
>>> print(remove_terminal_escapes(
... "\033[36;44mI'm blue, da ba dee da ba doo...\033[0m"
... ))
I'm blue, da ba dee da ba doo...
� )�ANSI_REr0 r s r �remove_terminal_escapesr5 � s � � �;�;�r�4� � � r c �R � t j dt j d| � � � � S )z�
Replace curly quotation marks with straight equivalents.
>>> print(uncurl_quotes('\u201chere\u2019s a test\u201d'))
"here's a test"
�'�")r r0 r r s r �
uncurl_quotesr9 � s$ � � � �s�O�$7��T�$B�$B� C� C�Cr c �6 � | � t � � S )uh
Replace single-character ligatures of Latin letters, such as 'fi', with the
characters that they contain, as in 'fi'. Latin ligatures are usually not
intended in text strings (though they're lovely in *rendered* text). If
you have such a ligature in your string, it is probably a result of a
copy-and-paste glitch.
We leave ligatures in other scripts alone to be safe. They may be intended,
and removing them may lose information. If you want to take apart nearly
all ligatures, use NFKC normalization.
>>> print(fix_latin_ligatures("fluffiest"))
fluffiest
)� translater r s r �fix_latin_ligaturesr< � s � � �>�>�)� $� $�$r c �6 � | � t � � S )uU
The ASCII characters, katakana, and Hangul characters have alternate
"halfwidth" or "fullwidth" forms that help text line up in a grid.
If you don't need these width properties, you probably want to replace
these characters with their standard form, which is what this function
does.
Note that this replaces the ideographic space, U+3000, with the ASCII
space, U+20.
>>> print(fix_character_width("ＬＯＵＤ ＮＯＩＳＥＳ"))
LOUD NOISES
>>> print(fix_character_width("Ｕﾀｰﾝ")) # this means "U-turn"
Uターン
)r; r r s r �fix_character_widthr> � s � �" �>�>�)� $� $�$r c �� � | � dd� � � dd� � � dd� � � dd� � � dd� � S )a8
Convert all line breaks to Unix style.
This will convert the following sequences into the standard \\n
line break:
- CRLF (\\r\\n), used on Windows and in some communication protocols
- CR (\\r), once used on Mac OS Classic, and now kept alive by misguided
software such as Microsoft Office for Mac
- LINE SEPARATOR (\\u2028) and PARAGRAPH SEPARATOR (\\u2029), defined by
Unicode and used to sow confusion and discord
- NEXT LINE (\\x85), a C1 control character that is certainly not what you
meant
The NEXT LINE character is a bit of an odd case, because it
usually won't show up if `fix_encoding` is also being run.
\\x85 is very common mojibake for \\u2026, HORIZONTAL ELLIPSIS.
>>> print(fix_line_breaks(
... "This string is made of two things:\u2029"
... "1. Unicode\u2028"
... "2. Spite"
... ))
This string is made of two things:
1. Unicode
2. Spite
For further testing and examples, let's define a function to make sure
we can see the control characters in their escaped form:
>>> def eprint(text):
... print(text.encode('unicode-escape').decode('ascii'))
>>> eprint(fix_line_breaks("Content-type: text/plain\r\n\r\nHi."))
Content-type: text/plain\n\nHi.
>>> eprint(fix_line_breaks("This is how Microsoft \r trolls Mac users"))
This is how Microsoft \n trolls Mac users
>>> eprint(fix_line_breaks("What is this \x85 I don't even"))
What is this \n I don't even
z
�
�
u
u
�
)�replacer s r �fix_line_breaksrD � sW � �X
� � �V�T�"�"� ���t� � � ���4� � � ���4� � � ���4� � � r u [���-���]u [���-���][���-���]c � � | � d� � }dt |d � � dz
dz z t |d � � dz
z }t |� � S )z�
Convert a surrogate pair to the single codepoint it represents.
This implements the formula described at:
http://en.wikipedia.org/wiki/Universal_Character_Set_characters#Surrogates
r i i � i � i � )r) �ord�chr)r& �pair�codepts r �convert_surrogate_pairrK sQ � � �;�;�q�>�>�D�
��D��G� � �v�-��6�
6�#�d�1�g�,�,��:O�
P�F� �v�;�;�r c � � t � | � � r;t � t | � � } t � d| � � } | S )uf
Replace 16-bit surrogate codepoints with the characters they represent
(when properly paired), or with � otherwise.
>>> high_surrogate = chr(0xd83d)
>>> low_surrogate = chr(0xdca9)
>>> print(fix_surrogates(high_surrogate + low_surrogate))
💩
>>> print(fix_surrogates(low_surrogate + high_surrogate))
��
The above doctest had to be very carefully written, because even putting
the Unicode escapes of the surrogates in the docstring was causing
various tools to fail, which I think just goes to show why this fixer is
necessary.
� �)� SURROGATE_RE�search�SURROGATE_PAIR_REr0 rK r s r �fix_surrogatesrQ sJ � �" ���4� � � 0� �$�$�%;�T�B�B��� � ��$�/�/�� �Kr c �6 � | � t � � S )a
Remove various control characters that you probably didn't intend to be in
your text. Many of these characters appear in the table of "Characters not
suitable for use with markup" at
http://www.unicode.org/reports/tr20/tr20-9.html.
This includes:
- ASCII control characters, except for the important whitespace characters
(U+00 to U+08, U+0B, U+0E to U+1F, U+7F)
- Deprecated Arabic control characters (U+206A to U+206F)
- Interlinear annotation characters (U+FFF9 to U+FFFB)
- The Object Replacement Character (U+FFFC)
- The byte order mark (U+FEFF)
However, these similar characters are left alone:
- Control characters that produce whitespace (U+09, U+0A, U+0C, U+0D,
U+2028, and U+2029)
- C1 control characters (U+80 to U+9F) -- even though they are basically
never used intentionally, they are important clues about what mojibake
has happened
- Control characters that affect glyph rendering, such as joiners and
right-to-left marks (U+200C to U+200F, U+202A to U+202E)
- Musical notation control characters (U+1D173 to U+1D17A) because wow if
you're using those you probably have a good reason
- Tag characters, because they are now used in emoji sequences such as
"Flag of Wales"
)r; r
r s r �remove_control_charsrS ( s � �< �>�>�-� (� (�(r c �F � | � t d� � � � S )z�
Remove a byte-order mark that was accidentally decoded as if it were part
of the text.
>>> print(remove_bom(chr(0xfeff) + "Where do you want to go today?"))
Where do you want to go today?
i�� )�lstriprH r s r �
remove_bomrV I s � � �;�;�s�6�{�{� #� #�#r a
( \\U........ # 8-digit hex escapes
| \\u.... # 4-digit hex escapes
| \\x.. # 2-digit hex escapes
| \\[0-7]{1,3} # Octal escapes
| \\N\{[^}]+\} # Unicode characters by name
| \\[\\'"abfnrtv] # Single-character escapes
)c �r � dt t dt fd�}t � || � � S )u[
Decode backslashed escape sequences, including \\x, \\u, and \\U character
references, even in the presence of other Unicode.
This function has to be called specifically. It's not run automatically by
ftfy, because escaped text is not necessarily a mistake, and there is no
way to distinguish when it is.
This is what Python's "string-escape" and "unicode-escape" codecs were
meant to do, but in contrast, this actually works. It will decode the
string exactly the same way that the Python interpreter decodes its string
literals.
>>> factoid = '\\u20a1 is the currency symbol for the colón.'
>>> print(factoid[1:])
u20a1 is the currency symbol for the colón.
>>> print(decode_escapes(factoid))
₡ is the currency symbol for the colón.
Even though Python itself can read string literals with a combination of
escapes and literal Unicode -- you're looking at one right now -- the
"unicode-escape" codec doesn't work on literal Unicode. (See
http://stackoverflow.com/a/24519338/773754 for more details.)
Instead, this function searches for just the parts of a string that
represent escape sequences, and decodes them, leaving the rest alone. All
valid escape sequences are made of ASCII characters, and this allows
"unicode-escape" to work correctly.
r& r c �R � t j | � d� � d� � S )z<Given a regex match, decode the escape sequence it contains.r zunicode-escape)�codecs�decoder) �r& s r � decode_matchz$decode_escapes.<locals>.decode_match� s � ��}�U�[�[��^�^�-=�>�>�>r )r �str�ESCAPE_SEQUENCE_REr0 )r r\ s r �decode_escapesr_ b s@ � �>?�E�#�J� ?�3� ?� ?� ?� ?� � !� !�,�� 5� 5�5r s � (?! |quele|quela|quilo|s )�bytsc � � t � d| � � } dt t dt fd�}t j || � � S )a]
Some mojibake has been additionally altered by a process that said "hmm,
byte A0, that's basically a space!" and replaced it with an ASCII space.
When the A0 is part of a sequence that we intend to decode as UTF-8,
changing byte A0 to 20 would make it fail to decode.
This process finds sequences that would convincingly decode as UTF-8 if
byte 20 were changed to A0, and puts back the A0. For the purpose of
deciding whether this is a good idea, this step gets a cost of twice
the number of bytes that are changed.
This is used as a step within `fix_encoding`.
s à r& r c �T � | � d� � � dd� � S )z.The function to apply when this regex matches.r � � �)r) rC r[ s r � replacementz$restore_byte_a0.<locals>.replacement� s" � ��{�{�1�~�~�%�%�g�w�7�7�7r )�A_GRAVE_WORD_REr0 r �bytesr )r` re s r �restore_byte_a0rh � sT � � � � �|�T� 2� 2�D�8�5��<� 8�E� 8� 8� 8� 8� � �{�D� 1� 1�1r c �R � t j d� d� � | � � S )u�
This function identifies sequences where information has been lost in
a "sloppy" codec, indicated by byte 1A, and if they would otherwise look
like a UTF-8 sequence, it replaces them with the UTF-8 sequence for U+FFFD.
A further explanation:
ftfy can now fix text in a few cases that it would previously fix
incompletely, because of the fact that it can't successfully apply the fix
to the entire string. A very common case of this is when characters have
been erroneously decoded as windows-1252, but instead of the "sloppy"
windows-1252 that passes through unassigned bytes, the unassigned bytes get
turned into U+FFFD (�), so we can't tell what they were.
This most commonly happens with curly quotation marks that appear
``“ like this �``.
We can do better by building on ftfy's "sloppy codecs" to let them handle
less-sloppy but more-lossy text. When they encounter the character ``�``,
instead of refusing to encode it, they encode it as byte 1A -- an
ASCII control code called SUBSTITUTE that once was meant for about the same
purpose. We can then apply a fixer that looks for UTF-8 sequences where
some continuation bytes have been replaced by byte 1A, and decode the whole
sequence as �; if that doesn't work, it'll just turn the byte back into �
itself.
As a result, the above text ``“ like this �`` will decode as
``“ like this �``.
If U+1A was actually in the original string, then the sloppy codecs will
not be used, and this function will not be run, so your weird control
character will be left alone but wacky fixes like this won't be possible.
This is used as a transcoder within `fix_encoding`.
rM zutf-8)r r0 �encode)r` s r �replace_lossy_sequencesrk � s$ � �H � �X�_�_�W� 5� 5�t� <� <�<r c �l � � dt t dt f� fd� }t j |� � � S )z�
Sometimes, text from one encoding ends up embedded within text from a
different one. This is common enough that we need to be able to fix it.
This is used as a transcoder within `fix_encoding`.
r& r c � �� | � d� � }t |� � t �� � k r#t |� � rt j |� � S |S )Nr )r) �lenr r r" )r& �substrr s �r �fix_embedded_mojibakez7decode_inconsistent_utf8.<locals>.fix_embedded_mojibake� sL �� ����Q� � �� �v�;�;��T��� "� "�v�f�~�~� "��$�V�,�,� ,��Mr )r r] r r0 )r rp s ` r �decode_inconsistent_utf8rq � sI �� ��U�3�Z� �C� � � � � � � � � 5�t� <� <�<r c �x � | � d� � � d� � � d� � S )Nr zlatin-1zsloppy-windows-1252)r) rj rZ r[ s r � _c1_fixerrs � s/ � � �;�;�q�>�>� � �� +� +� 2� 2�3H� I� I�Ir c �6 � t j t | � � S )z�
If text still contains C1 control characters, treat them as their
Windows-1252 equivalents. This matches what Web browsers do.
)r r0 rs r s r �fix_c1_controlsru � s � �
� �Y�� -� -�-r )7�__doc__rY r+ �rer �typingr r r r r � ftfy.badnessr �
ftfy.chardatar r r
r r r
r r r r r r] r r" r% r. r1 �compiler4 r5 r9 r< r> rD rN rP rK rQ rS rV �UNICODE�VERBOSEr^ r_ rf rg rh rk rq rs ru � r r �<module>r sQ ��
�
� �
�
�
� � � � � � � � � ���� *� *� *� *� *� *� *� *� *� *� *� *� � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � /�3� /�3� /� /� /� /� #�s� #�s� #� #� #� #� '�S� '��U�3��8�_� 5� '�#� '� '� '� '��5��:� �#� � � � �*-5�� -5�� -5� -5� -5� -5�` �"�*�4�
5�
5��
!�#�
!�#�
!�
!�
!�
!�D�� D�� D� D� D� D�%�c� %�c� %� %� %� %�$%�c� %�c� %� %� %� %�(1�#� 1�#� 1� 1� 1� 1�h �r�z�+�,�,� � �B�J� ?�@�@� � �%��*� �� � � � ��� �� � � � �. )�s� )�s� )� )� )� )�B$�S� $�S� $� $� $� $� �R�Z� � �J����
�
� �#6�� #6�� #6� #6� #6� #6�z �"�*� ?�@�@��2�%� 2�E� 2� 2� 2� 2�.$=�%� $=�E� $=� $=� $=� $=�N=�3� =�3� =� =� =� =�(J�U�3�Z� J�C� J� J� J� J�.�#� .�#� .� .� .� .� .� .r