dZdZdZdZdZdZdZddlZGd d eZ e Z e ja gd Z dd Zdd ZdZdZdZdZdZdZdZdZdZdZy)z_ smartypants module ================== :func:`smartypants` is the core of smartypants module. z Yu-Jie Linzlivibetter@gmail.comz2.0.0z BSD Licensez/https://bitbucket.org/livibetter/smartypants.pyzPython with the SmartyPantsNceZdZdZdZ dZ dezZ eezZdZ dezZ dezZ ee ze zZ dZ d Z d Z d Z d Z eezezZd Z eezeze zZ eeze ze zZ eeze ze zZ edZej0dZy)_AttrzC class for instantiation of module attribute :attr:`Attr`.  @iirctS)z7Default value of attributes, same value as :attr:`set1`default_smartypants_attr)selfs 0/usr/lib/python3.12/site-packages/smartypants.pydefaultz _Attr.defaults ('c|ayNr)rattrs rrz _Attr.defaults $( rN)__name__ __module__ __qualname____doc__qbBmask_bdDimask_dewuhsmask_oset0set1set2set3propertyrsetterrrrrs2 A A  A UFA  A  A UQYFA A  A A A UQYF D1 q519q=DA q519q=D q519q=D ((  ^^((rr)presampcodettkbdscriptstylemathc|t}t|ttfrdj |}t j d|zt jS)z Convert a list of skipped tags into regular expression The default *tags* are :attr:`tags_to_skip`. >>> f = _tags_to_skip_regex >>> print(f(['foo', 'bar']).pattern) <(/)?(foo|bar)[^>]*> |z<(/)?(%s)[^>]*>) tags_to_skip isinstancelisttuplejoinrecompileI)tagss r_tags_to_skip_regexrDsD |$u &xx~ ::'$. 55rc"g}|tj}|tjz}|tjz}|tjz}|tj z}|tj z}|tjz}t|} g} d} d} t} | D]X}|ddk(r| j|d| j|d}|s7|jds1|j|jdjd} yt|dkDr9|d }|jdj|k(r|jn t|dk(sd} |d}|d d}| sgt!|}|rt#j$d d |}|rZ|tj&k(r t)|}|tj*k(r t-|}|tj.k(r t1|}|r t3|}|tj4k(r t7|}|tj8k(r t;|}|rM|d k(rt#jd | rd}n/d}n,|d k(rt#jd | rd}nd}n t=|}|rM|tj>k(rdn+|tj@k(rdn|tjBk(rdnd}tE||}|} | j|[djG| S)z SmartyPants function >>> print(smartypants('"foo" -- bar')) “foo” — bar >>> print(smartypants('"foo" -- bar', Attr.d)) "foo" — bar NFrtagrrTz""'z\S’‘”“)$Attrrrrr#r$r)r% _tokenizerDappendmatchgrouplowerlenpopprocess_escapesr@subr convert_dashesr!convert_dashes_oldschoolr"!convert_dashes_oldschool_invertedconvert_ellipsesrconvert_backticksrconvert_single_backticksconvert_quotesr&r'r(convert_entitiesr?)textrskipped_tag_stack do_quotes do_backticks do_dashes do_ellipses do_entities convert_quottokensresultin_preprev_token_last_chartags_to_skip_regex cur_token skip_match_tagt last_charmodes r smartypantsrus |||tvv I$++%Lt{{"I-K$K$&&=L t_F F F-. Q<5  MM)A, '+11)A,?J!''*%,,Z-=-=a-@-F-F-HI!F,-104%++A.446$>-113 ,-2!&! A"#I#A&xa0A DFF**1- DFF*4Q7 DFF*=a@(+A 466))!,A466)03ACx88D*>? )A )Ac88D*>? )A )A+1-!,!6A!,!6A!,!6A)D1A#, MM! WZ 776?rcd}tjd|dd|}tjd|dd|}tjdd|}tjd d |}tjd d|}d }d }tjd|dtj}|jd|}tjd|dtj}|jd|}tjd|dtj}|jd|}tjdd|}tjd|dtj}|jd|}tjd|dtj}|jd|}tjd|dtj}|jd|}tjdd|}|S) z Convert quotes in *text* into HTML curly quote entities. >>> print(convert_quotes('"Isn\'t this fun?"')) “Isn’t this fun?” z)[!"#\$\%'()*+,-.\/:;<=>?\@\[\\\]\^_`{|}~]z^'(?=z\\B)rKz^"(?=rMz"'(?=\w)z“‘z'"(?=\w)z‘“z \b'(?=\d{2}s)z[^\ \t\r\n\[\{\(\-]z–|—z ( \s | # a whitespace char, or   | # a non-breaking space entity, or -- | # dashes, or &[mn]dash; | # named dash entities z | # or decimal entities &\#x201[34]; # or hex ) ' # the quote (?=\w) # followed by a word character z \1‘z (z:) ' (?!\s | s\b | \d) z \1’z3) ' (\s | s\b) z \1’\2rJrLz | # or decimal entities &\#x201[34]; # or hex ) " # the quote (?=\w) # followed by a word character z \1“z #(zi)? # character that indicates the quote should be closing " (?=\s) zU) # character that indicates the quote should be closing " z \1”rIrN)r@rYrAVERBOSE)rb punct_class close_class dec_dashesopening_single_quotes_regexclosing_single_quotes_regexopening_double_quotes_regexclosing_double_quotes_regexs rr`r`*sCK 66 5y$ GD 66 5y$ GD 66/#3T :D 66/#3T :D 66& 4 8D(K"J#%** . "$ #- ' * *< >D"$** .!#%** #. ' * *< >D"$** .!#%** #. ' * *>4 @D 66#y$ 'D#%** . "$ #- ' * *< >D#%** .!#%** #. ' * *9d ;D"$**.!#%**#. ' * *< >D 66#y$ 'D Krcbtjdd|}tjdd|}|S)z Convert ````backticks''``-style double quotes in *text* into HTML curly quote entities. >>> print(convert_backticks("``Isn't this fun?''")) “Isn't this fun?” z``rNz''rMr@rYrbs rr^r^s- 66$ 4 (D 66$ 4 (D Krcbtjdd|}tjdd|}|S)z Convert ```backticks'``-style single quotes in *text* into HTML curly quote entities. >>> print(convert_single_backticks("`Isn't this fun?'")) ‘Isn’t this fun?’ `rLrJrKrrs rr_r_s- 66#y$ 'D 66#y$ 'D Krc4tjdd|}|S)z Convert ``--`` in *text* into em-dash HTML entities. >>> quote = 'Nothing endures but change. -- Heraclitus' >>> print(convert_dashes(quote)) Nothing endures but change. — Heraclitus --—rrs rrZrZs 66$ 4 (D Krcbtjdd|}tjdd|}|S)a3 Convert ``--`` and ``---`` in *text* into en-dash and em-dash HTML entities, respectively. >>> quote = 'Life itself is the proper binge. --- Julia Child (1912--2004)' >>> print(convert_dashes_oldschool(quote)) Life itself is the proper binge. — Julia Child (1912–2004) ---rr–rrs rr[r[s- 66%D )D 66$ 4 (D Krcbtjdd|}tjdd|}|S)u Convert ``--`` and ``---`` in *text* into em-dash and en-dash HTML entities, respectively. Two reasons why: * First, unlike the en- and em-dash syntax supported by :func:`convert_dashes_oldschool`, it's compatible with existing entries written before SmartyPants 1.1, back when ``--`` was only used for em-dashes. * Second, em-dashes are more common than en-dashes, and so it sort of makes sense that the shortcut should be shorter to type. (Thanks to Aaron Swartz for the idea.) >>> quote = 'Dare to be naïve. -- Buckminster Fuller (1895---1983)' >>> print(convert_dashes_oldschool_inverted(quote)) Dare to be naïve. — Buckminster Fuller (1895–1983) rrrrrrs rr\r\s-( 66%D )D 66$ 4 (D Krcbtjdd|}tjdd|}|S)z{ Convert ``...`` in *text* into ellipsis HTML entities >>> print(convert_ellipses('Huh...?')) Huh…? z\.\.\.…z\. \. \.rrs rr]r]s- 66-D 1D 66/9d 3D Krctdddddddd}|jD]\}}|j|||}|S) u Convert numeric character references to, if *mode* is - *0*: Unicode characters - *1*: HTML named entities - *2*: ASCII equivalents >>> print(convert_entities('‘', 0)) ‘ >>> print(convert_entities('‘SmartyPants’', 1)) ‘SmartyPants’ >>> print(convert_entities('“Hello — world.”', 2)) "Hello -- world." )u–z–-)u—z—r)u‘z‘rJ)u’z’rJ)u“z“rI)u”z”rI)u…z…z...)rrrLrKrNrMr)itemsreplace)rbrtCTBLkvs rrarasQ"++****- D 1||Aqw' Krctjdd|}tjdd|}tjdd|}tjdd|}tjd d |}tjd d |}|S) aq Processe the following backslash escape sequences in *text*. This is useful if you want to force a "dumb" quote or other character to appear. +--------+-----------+-----------+ | Escape | Value | Character | +========+===========+===========+ | ``\\`` | ``\`` | ``\`` | +--------+-----------+-----------+ | ``\"`` | ``"`` | ``"`` | +--------+-----------+-----------+ | ``\'`` | ``'`` | ``'`` | +--------+-----------+-----------+ | ``\.`` | ``.`` | ``.`` | +--------+-----------+-----------+ | ``\-`` | ``-`` | ``-`` | +--------+-----------+-----------+ | ``\``` | ````` | ``\``` | +--------+-----------+-----------+ >>> print(process_escapes(r'\\')) \ >>> print(smartypants(r'"smarty" \"pants\"')) “smarty” "pants" z\\\\z\z\\"z"z\\'z'z\\\.z.z\\-z-z\\`z`rrs rrXrXsu6 66'7D )D 66&'4 (D 66&'4 (D 66'7D )D 66&'4 (D 66&'4 (D Krchg}tjdtj}|j|}d}|r|j dr"|j d|j dg|j d}d}|j dr5d|d d jd jjd vrd}|j ||g|j}|j||j}|r|t|kr|j d||d g|S) a Reference to an array of the tokens comprising the input string. Each token is either a tag (possibly with nested, tags contained therein, such as ````, or a run of text between tags. Each element of the array is a two-element array; the first is either 'tag' or 'text'; the second is the actual value. Based on the _tokenize() subroutine from `Brad Choate's MTRegex plugin`__. __ http://www.bradchoate.com/past/mtregex.php z([^<]*)(