PNG  IHDRxsBIT|d pHYs+tEXtSoftwarewww.inkscape.org<,tEXtComment File Manager

File Manager

Path: /opt/alt/python311/lib/python3.11/site-packages/markdown_it/common/

Viewing File: utils.py

"""Utilities for parsing source text"""

from __future__ import annotations

import re
from re import Match
from typing import TypeVar
import unicodedata

from .entities import entities


def charCodeAt(src: str, pos: int) -> int | None:
    """
    Returns the Unicode value of the character at the specified location.

    @param - index The zero-based index of the desired character.
    If there is no character at the specified index, NaN is returned.

    This was added for compatibility with python
    """
    try:
        return ord(src[pos])
    except IndexError:
        return None


def charStrAt(src: str, pos: int) -> str | None:
    """
    Returns the Unicode value of the character at the specified location.

    @param - index The zero-based index of the desired character.
    If there is no character at the specified index, NaN is returned.

    This was added for compatibility with python
    """
    try:
        return src[pos]
    except IndexError:
        return None


_ItemTV = TypeVar("_ItemTV")


def arrayReplaceAt(
    src: list[_ItemTV], pos: int, newElements: list[_ItemTV]
) -> list[_ItemTV]:
    """
    Remove element from array and put another array at those position.
    Useful for some operations with tokens
    """
    return src[:pos] + newElements + src[pos + 1 :]


def isValidEntityCode(c: int) -> bool:
    # broken sequence
    if c >= 0xD800 and c <= 0xDFFF:
        return False
    # never used
    if c >= 0xFDD0 and c <= 0xFDEF:
        return False
    if ((c & 0xFFFF) == 0xFFFF) or ((c & 0xFFFF) == 0xFFFE):
        return False
    # control codes
    if c >= 0x00 and c <= 0x08:
        return False
    if c == 0x0B:
        return False
    if c >= 0x0E and c <= 0x1F:
        return False
    if c >= 0x7F and c <= 0x9F:
        return False
    # out of range
    return not (c > 0x10FFFF)


def fromCodePoint(c: int) -> str:
    """Convert ordinal to unicode.

    Note, in the original Javascript two string characters were required,
    for codepoints larger than `0xFFFF`.
    But Python 3 can represent any unicode codepoint in one character.
    """
    return chr(c)


# UNESCAPE_MD_RE = re.compile(r'\\([!"#$%&\'()*+,\-.\/:;<=>?@[\\\]^_`{|}~])')
# ENTITY_RE_g       = re.compile(r'&([a-z#][a-z0-9]{1,31})', re.IGNORECASE)
UNESCAPE_ALL_RE = re.compile(
    r'\\([!"#$%&\'()*+,\-.\/:;<=>?@[\\\]^_`{|}~])' + "|" + r"&([a-z#][a-z0-9]{1,31});",
    re.IGNORECASE,
)
DIGITAL_ENTITY_BASE10_RE = re.compile(r"#([0-9]{1,8})")
DIGITAL_ENTITY_BASE16_RE = re.compile(r"#x([a-f0-9]{1,8})", re.IGNORECASE)


def replaceEntityPattern(match: str, name: str) -> str:
    """Convert HTML entity patterns,
    see https://spec.commonmark.org/0.30/#entity-references
    """
    if name in entities:
        return entities[name]

    code: None | int = None
    if pat := DIGITAL_ENTITY_BASE10_RE.fullmatch(name):
        code = int(pat.group(1), 10)
    elif pat := DIGITAL_ENTITY_BASE16_RE.fullmatch(name):
        code = int(pat.group(1), 16)

    if code is not None and isValidEntityCode(code):
        return fromCodePoint(code)

    return match


def unescapeAll(string: str) -> str:
    def replacer_func(match: Match[str]) -> str:
        escaped = match.group(1)
        if escaped:
            return escaped
        entity = match.group(2)
        return replaceEntityPattern(match.group(), entity)

    if "\\" not in string and "&" not in string:
        return string
    return UNESCAPE_ALL_RE.sub(replacer_func, string)


ESCAPABLE = r"""\\!"#$%&'()*+,./:;<=>?@\[\]^`{}|_~-"""
ESCAPE_CHAR = re.compile(r"\\([" + ESCAPABLE + r"])")


def stripEscape(string: str) -> str:
    """Strip escape \\ characters"""
    return ESCAPE_CHAR.sub(r"\1", string)


def escapeHtml(raw: str) -> str:
    """Replace special characters "&", "<", ">" and '"' to HTML-safe sequences."""
    # like html.escape, but without escaping single quotes
    raw = raw.replace("&", "&amp;")  # Must be done first!
    raw = raw.replace("<", "&lt;")
    raw = raw.replace(">", "&gt;")
    raw = raw.replace('"', "&quot;")
    return raw


# //////////////////////////////////////////////////////////////////////////////

REGEXP_ESCAPE_RE = re.compile(r"[.?*+^$[\]\\(){}|-]")


def escapeRE(string: str) -> str:
    string = REGEXP_ESCAPE_RE.sub("\\$&", string)
    return string


# //////////////////////////////////////////////////////////////////////////////


def isSpace(code: int | None) -> bool:
    """Check if character code is a whitespace."""
    return code in (0x09, 0x20)


def isStrSpace(ch: str | None) -> bool:
    """Check if character is a whitespace."""
    return ch in ("\t", " ")


MD_WHITESPACE = {
    0x09,  # \t
    0x0A,  # \n
    0x0B,  # \v
    0x0C,  # \f
    0x0D,  # \r
    0x20,  # space
    0xA0,
    0x1680,
    0x202F,
    0x205F,
    0x3000,
}


def isWhiteSpace(code: int) -> bool:
    r"""Zs (unicode class) || [\t\f\v\r\n]"""
    if code >= 0x2000 and code <= 0x200A:
        return True
    return code in MD_WHITESPACE


# //////////////////////////////////////////////////////////////////////////////


def isPunctChar(ch: str) -> bool:
    """Check if character is a punctuation character."""
    return unicodedata.category(ch).startswith(("P", "S"))


MD_ASCII_PUNCT = {
    0x21,  # /* ! */
    0x22,  # /* " */
    0x23,  # /* # */
    0x24,  # /* $ */
    0x25,  # /* % */
    0x26,  # /* & */
    0x27,  # /* ' */
    0x28,  # /* ( */
    0x29,  # /* ) */
    0x2A,  # /* * */
    0x2B,  # /* + */
    0x2C,  # /* , */
    0x2D,  # /* - */
    0x2E,  # /* . */
    0x2F,  # /* / */
    0x3A,  # /* : */
    0x3B,  # /* ; */
    0x3C,  # /* < */
    0x3D,  # /* = */
    0x3E,  # /* > */
    0x3F,  # /* ? */
    0x40,  # /* @ */
    0x5B,  # /* [ */
    0x5C,  # /* \ */
    0x5D,  # /* ] */
    0x5E,  # /* ^ */
    0x5F,  # /* _ */
    0x60,  # /* ` */
    0x7B,  # /* { */
    0x7C,  # /* | */
    0x7D,  # /* } */
    0x7E,  # /* ~ */
}


def isMdAsciiPunct(ch: int) -> bool:
    """Markdown ASCII punctuation characters.

    ::

        !, ", #, $, %, &, ', (, ), *, +, ,, -, ., /, :, ;, <, =, >, ?, @, [, \\, ], ^, _, `, {, |, }, or ~

    See http://spec.commonmark.org/0.15/#ascii-punctuation-character

    Don't confuse with unicode punctuation !!! It lacks some chars in ascii range.

    """
    return ch in MD_ASCII_PUNCT


def normalizeReference(string: str) -> str:
    """Helper to unify [reference labels]."""
    # Trim and collapse whitespace
    #
    string = re.sub(r"\s+", " ", string.strip())

    # In node v10 'ẞ'.toLowerCase() === 'Ṿ', which is presumed to be a bug
    # fixed in v12 (couldn't find any details).
    #
    # So treat this one as a special case
    # (remove this when node v10 is no longer supported).
    #
    # if ('ẞ'.toLowerCase() === 'Ṿ') {
    #   str = str.replace(/ẞ/g, 'ß')
    # }

    # .toLowerCase().toUpperCase() should get rid of all differences
    # between letter variants.
    #
    # Simple .toLowerCase() doesn't normalize 125 code points correctly,
    # and .toUpperCase doesn't normalize 6 of them (list of exceptions:
    # İ, ϴ, ẞ, Ω, K, Å - those are already uppercased, but have differently
    # uppercased versions).
    #
    # Here's an example showing how it happens. Lets take greek letter omega:
    # uppercase U+0398 (Θ), U+03f4 (ϴ) and lowercase U+03b8 (θ), U+03d1 (ϑ)
    #
    # Unicode entries:
    # 0398;GREEK CAPITAL LETTER THETA;Lu;0;L;;;;;N;;;;03B8
    # 03B8;GREEK SMALL LETTER THETA;Ll;0;L;;;;;N;;;0398;;0398
    # 03D1;GREEK THETA SYMBOL;Ll;0;L;<compat> 03B8;;;;N;GREEK SMALL LETTER SCRIPT THETA;;0398;;0398
    # 03F4;GREEK CAPITAL THETA SYMBOL;Lu;0;L;<compat> 0398;;;;N;;;;03B8
    #
    # Case-insensitive comparison should treat all of them as equivalent.
    #
    # But .toLowerCase() doesn't change ϑ (it's already lowercase),
    # and .toUpperCase() doesn't change ϴ (already uppercase).
    #
    # Applying first lower then upper case normalizes any character:
    # '\u0398\u03f4\u03b8\u03d1'.toLowerCase().toUpperCase() === '\u0398\u0398\u0398\u0398'
    #
    # Note: this is equivalent to unicode case folding; unicode normalization
    # is a different step that is not required here.
    #
    # Final result should be uppercased, because it's later stored in an object
    # (this avoid a conflict with Object.prototype members,
    # most notably, `__proto__`)
    #
    return string.lower().upper()


LINK_OPEN_RE = re.compile(r"^<a[>\s]", flags=re.IGNORECASE)
LINK_CLOSE_RE = re.compile(r"^</a\s*>", flags=re.IGNORECASE)


def isLinkOpen(string: str) -> bool:
    return bool(LINK_OPEN_RE.search(string))


def isLinkClose(string: str) -> bool:
    return bool(LINK_CLOSE_RE.search(string))
b IDATxytVսϓ22 A@IR :hCiZ[v*E:WũZA ^dQeQ @ !jZ'>gsV仿$|?g)&x-EIENT ;@xT.i%-X}SvS5.r/UHz^_$-W"w)Ɗ/@Z &IoX P$K}JzX:;` &, ŋui,e6mX ԵrKb1ԗ)DADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADA݀!I*]R;I2$eZ#ORZSrr6mteffu*((Pu'v{DIߔ4^pIm'77WEEE;vƎ4-$]'RI{\I&G :IHJ DWBB=\WR޽m o$K(V9ABB.}jѢv`^?IOȅ} ڶmG}T#FJ`56$-ھ}FI&v;0(h;Б38CӧOWf!;A i:F_m9s&|q%=#wZprrrla A &P\\СC[A#! {olF} `E2}MK/vV)i{4BffV\|ۭX`b@kɶ@%i$K z5zhmX[IXZ` 'b%$r5M4º/l ԃߖxhʔ)[@=} K6IM}^5k㏷݆z ΗÿO:gdGBmyT/@+Vɶ纽z񕏵l.y޴it뭷zV0[Y^>Wsqs}\/@$(T7f.InݺiR$푔n.~?H))\ZRW'Mo~v Ov6oԃxz! S,&xm/yɞԟ?'uaSѽb,8GלKboi&3t7Y,)JJ c[nzӳdE&KsZLӄ I?@&%ӟ۶mSMMњ0iؐSZ,|J+N ~,0A0!5%Q-YQQa3}$_vVrf9f?S8`zDADADADADADADADADAdqP,تmMmg1V?rSI꒟]u|l RCyEf٢9 jURbztѰ!m5~tGj2DhG*{H9)꒟ר3:(+3\?/;TUݭʴ~S6lڧUJ*i$d(#=Yݺd{,p|3B))q:vN0Y.jkק6;SɶVzHJJЀ-utѹսk>QUU\޲~]fFnK?&ߡ5b=z9)^|u_k-[y%ZNU6 7Mi:]ۦtk[n X(e6Bb."8cۭ|~teuuw|ήI-5"~Uk;ZicEmN/:]M> cQ^uiƞ??Ңpc#TUU3UakNwA`:Y_V-8.KKfRitv޲* 9S6ֿj,ՃNOMߤ]z^fOh|<>@Å5 _/Iu?{SY4hK/2]4%it5q]GGe2%iR| W&f*^]??vq[LgE_3f}Fxu~}qd-ږFxu~I N>\;͗O֊:̗WJ@BhW=y|GgwܷH_NY?)Tdi'?խwhlmQi !SUUsw4kӺe4rfxu-[nHtMFj}H_u~w>)oV}(T'ebʒv3_[+vn@Ȭ\S}ot}w=kHFnxg S 0eޢm~l}uqZfFoZuuEg `zt~? b;t%>WTkķh[2eG8LIWx,^\thrl^Ϊ{=dž<}qV@ ⠨Wy^LF_>0UkDuʫuCs$)Iv:IK;6ֲ4{^6եm+l3>݆uM 9u?>Zc }g~qhKwڭeFMM~pМuqǿz6Tb@8@Y|jx](^]gf}M"tG -w.@vOqh~/HII`S[l.6nØXL9vUcOoB\xoǤ'T&IǍQw_wpv[kmO{w~>#=P1Pɞa-we:iǏlHo׈꒟f9SzH?+shk%Fs:qVhqY`jvO'ρ?PyX3lх]˾uV{ݞ]1,MzYNW~̈́ joYn}ȚF߾׮mS]F z+EDxm/d{F{-W-4wY듏:??_gPf ^3ecg ҵs8R2מz@TANGj)}CNi/R~}c:5{!ZHӋӾ6}T]G]7W6^n 9*,YqOZj:P?Q DFL|?-^.Ɵ7}fFh׶xe2Pscz1&5\cn[=Vn[ĶE鎀uˌd3GII k;lNmشOuuRVfBE]ۣeӶu :X-[(er4~LHi6:Ѻ@ԅrST0trk%$Č0ez" *z"T/X9|8.C5Feg}CQ%͞ˣJvL/?j^h&9xF`њZ(&yF&Iݻfg#W;3^{Wo^4'vV[[K';+mӍִ]AC@W?1^{එyh +^]fm~iԵ]AB@WTk̏t uR?l.OIHiYyԶ]Aˀ7c:q}ힽaf6Z~қm(+sK4{^6}T*UUu]n.:kx{:2 _m=sAߤU@?Z-Vކеz왍Nэ{|5 pڶn b p-@sPg]0G7fy-M{GCF'%{4`=$-Ge\ eU:m+Zt'WjO!OAF@ik&t݆ϥ_ e}=]"Wz_.͜E3leWFih|t-wZۍ-uw=6YN{6|} |*={Ѽn.S.z1zjۻTH]흾 DuDvmvK.`V]yY~sI@t?/ϓ. m&["+P?MzovVЫG3-GRR[(!!\_,^%?v@ҵő m`Y)tem8GMx.))A]Y i`ViW`?^~!S#^+ѽGZj?Vģ0.))A꨷lzL*]OXrY`DBBLOj{-MH'ii-ϰ ok7^ )쭡b]UXSְmռY|5*cֽk0B7镹%ڽP#8nȎq}mJr23_>lE5$iwui+ H~F`IjƵ@q \ @#qG0".0" l`„.0! ,AQHN6qzkKJ#o;`Xv2>,tێJJ7Z/*A .@fفjMzkg @TvZH3Zxu6Ra'%O?/dQ5xYkU]Rֽkق@DaS^RSּ5|BeHNN͘p HvcYcC5:y #`οb;z2.!kr}gUWkyZn=f Pvsn3p~;4p˚=ē~NmI] ¾ 0lH[_L hsh_ғߤc_њec)g7VIZ5yrgk̞W#IjӪv>՞y睝M8[|]\շ8M6%|@PZڨI-m>=k='aiRo-x?>Q.}`Ȏ:Wsmu u > .@,&;+!!˱tﭧDQwRW\vF\~Q7>spYw$%A~;~}6¾ g&if_=j,v+UL1(tWake:@Ș>j$Gq2t7S?vL|]u/ .(0E6Mk6hiۺzښOrifޱxm/Gx> Lal%%~{lBsR4*}{0Z/tNIɚpV^#Lf:u@k#RSu =S^ZyuR/.@n&΃z~B=0eg뺆#,Þ[B/?H uUf7y Wy}Bwegל`Wh(||`l`.;Ws?V@"c:iɍL֯PGv6zctM̠':wuW;d=;EveD}9J@B(0iհ bvP1{\P&G7D޴Iy_$-Qjm~Yrr&]CDv%bh|Yzni_ˆR;kg}nJOIIwyuL}{ЌNj}:+3Y?:WJ/N+Rzd=hb;dj͒suݔ@NKMԄ jqzC5@y°hL m;*5ezᕏ=ep XL n?מ:r`۵tŤZ|1v`V뽧_csج'ߤ%oTuumk%%%h)uy]Nk[n 'b2 l.=͜E%gf$[c;s:V-͞WߤWh-j7]4=F-X]>ZLSi[Y*We;Zan(ӇW|e(HNNP5[= r4tP &0<pc#`vTNV GFqvTi*Tyam$ߏWyE*VJKMTfFw>'$-ؽ.Ho.8c"@DADADADADADADADADA~j*֘,N;Pi3599h=goضLgiJ5փy~}&Zd9p֚ e:|hL``b/d9p? fgg+%%hMgXosج, ΩOl0Zh=xdjLmhݻoO[g_l,8a]٭+ӧ0$I]c]:粹:Teꢢ"5a^Kgh,&= =՟^߶“ߢE ܹS J}I%:8 IDAT~,9/ʃPW'Mo}zNƍ쨓zPbNZ~^z=4mswg;5 Y~SVMRXUյڱRf?s:w ;6H:ºi5-maM&O3;1IKeamZh͛7+##v+c ~u~ca]GnF'ټL~PPPbn voC4R,ӟgg %hq}@#M4IÇ Oy^xMZx ) yOw@HkN˖-Sǎmb]X@n+i͖!++K3gd\$mt$^YfJ\8PRF)77Wא!Cl$i:@@_oG I{$# 8磌ŋ91A (Im7֭>}ߴJq7ޗt^ -[ԩSj*}%]&' -ɓ'ꫯVzzvB#;a 7@GxI{j޼ƌ.LÇWBB7`O"I$/@R @eee@۷>}0,ɒ2$53Xs|cS~rpTYYY} kHc %&k.], @ADADADADADADADADA@lT<%''*Lo^={رc5h %$+CnܸQ3fҥK}vUVVs9G R,_{xˇ3o߾;TTTd}馛]uuuG~iԩ@4bnvmvfϞ /Peeeq}}za I~,誫{UWW뮻}_~YƍSMMMYχ֝waw\ďcxꩧtEƍկ_?۷5@u?1kNׯWzz/wy>}zj3 k(ٺuq_Zvf̘:~ ABQ&r|!%KҥKgԞ={<_X-z !CyFUUz~ ABQIIIjݺW$UXXDٳZ~ ABQƍecW$<(~<RSSvZujjjԧOZQu@4 8m&&&jԩg$ď1h ͟?_{768@g =@`)))5o6m3)ѣƌJ;wҿUTT /KZR{~a=@0o<*狔iFɶ[ˎ;T]]OX@?K.ۈxN pppppppppppppppppPfl߾] ,{ァk۶mڿo5BTӦMӴiӴ|r DB2e|An!Dy'tkΝ[A $***t5' "!駟oaDnΝ:t֭[gDШQ06qD;@ x M6v(PiizmZ4ew"@̴ixf [~-Fٱc&IZ2|n!?$@{[HTɏ#@hȎI# _m(F /6Z3z'\r,r!;w2Z3j=~GY7"I$iI.p_"?pN`y DD?: _  Gÿab7J !Bx@0 Bo cG@`1C[@0G @`0C_u V1 aCX>W ` | `!<S `"<. `#c`?cAC4 ?c p#~@0?:08&_MQ1J h#?/`7;I  q 7a wQ A 1 Hp !#<8/#@1Ul7=S=K.4Z?E_$i@!1!E4?`P_  @Bă10#: "aU,xbFY1 [n|n #'vEH:`xb #vD4Y hi.i&EΖv#O H4IŶ}:Ikh @tZRF#(tXҙzZ ?I3l7q@õ|ۍ1,GpuY Ꮿ@hJv#xxk$ v#9 5 }_$c S#=+"K{F*m7`#%H:NRSp6I?sIՖ{Ap$I$I:QRv2$Z @UJ*$]<FO4IENDB`