m ]j~addlZddlZddlmZmZddlmZddlmZm Z ddl Z ddl m Z m Z mZedeDZedeDZed e DZeed d gzZej(d Zhd Zej(dZiZdZGddZGddeZGddeZGddZGddZdZ y)N)BytesIOStringIO)Path) ascii_lettersascii_uppercase)EOF ReparseErrorspace_charactersc#<K|]}|jywNencode.0items L/var/www/zogu/zoguvenv/lib/python3.12/site-packages/tinyhtml5/inputstream.py r s"NT4;;="Nc#<K|]}|jywr rrs rrr sH$ Hrc#<K|]}|jywr rrs rrrs!LD$++-!Lr>   z[ - -/:-@\[-`{-~]c t|trJt|dkrI&II FD !%f&6&6&8CFCC gff&=FKKN63 O%f777$V6v66cHeZdZdZdZdZdZdZdZdZ dZ d d Z d Z y ) rAzProvides a Unicode stream of characters to the HTMLTokenizer. This class takes care of character encoding and removing or replacing incorrect byte-sequences and also provides column and line tracking. c dg|_tddf|_|j||_|j y)zInitialise the HTMLInputStream. Create a normalized stream from source for use by tinyhtml5. source can be either a file-object, local filename or a string. rutf-8certainN) new_lineslookup_encodingencoding open_streamstreamreset)selfrErFs r__init__zHTMLUnicodeInputStream.__init__9s9(19= &&v.  rHcfd|_d|_d|_g|_d|_d|_d|_y)Nr)chunk chunk_size chunk_offseterrorsprevious_number_linesprevious_number_columns_buffered_characterrSs rrRzHTMLUnicodeInputStream.resetIs;  &'"'($$( rHc4t|dr|St|S)zuProduce a file object from source. source can be either a file object, local filename or a string. r<)rCrrSrEs rrPz"HTMLUnicodeInputStream.open_streamWs !0vFhv6FFrHc|j}|jdd|}|j|z}|jdd|}|dk(r|j|z}||fS||dzz }||fS)N rr)rWcountr[rfindr\)rSoffsetrW number_lines position_linelast_line_positionposition_columns r _positionz HTMLUnicodeInputStream._position_s {{4F3 22\A "[[q&9  #"::VCO//%(:Q(>?O//rHcL|j|j\}}|dz|fS)z9Return (line, col) of the current position in the stream.r)rkrY)rSlinecolumns rpositionzHTMLUnicodeInputStream.positionjs)~~d&7&78 fq&!!rHc|j|jk\r|jstS|j}|j|}|dz|_|S)zlRead one character from the stream or queue if available. Return EOF when EOF is reached. r)rYrX read_chunkr rW)rSrY characters rrrz HTMLUnicodeInputStream.characterosQ    /??$ (( JJ|, (1,rHc|j|j\|_|_d|_d|_d|_|j jd}|jr|j|z}d|_n|syt|dkDr0t|d}|dk(sd|cxkrd krnn|d|_|dd}tttj|D]}|jjd |j!d d }|j!d d }||_t||_y)NrVri(Frrc iizinvalid-codepointz rb T)rkrXr[r\rWrYrQr<r]r?ordrangeinvalid_unicode_refindallrZappendreplace)rSdatalast_s rrqz!HTMLUnicodeInputStream.read_chunks+CG>> OOD@"D$@ {{&  # #++d2D'+D $ t9q=tBx=Dt|v77+/8(CRys-55d;<= 4A KK  2 3 4||FD)||D$' d)rHc  t||f}g} |j |j|j}||j|jk7rPn|j}||jk7r0|j|j|j|||_n:|j|j|jd|jsndj|S#t$rcdj|Dcgc]}dt|dncc}wc}}|sd|}t j d|d}|x}t||f<YJwxYw)aReturn a string of characters from the stream. String goes up to but does not include any character in 'characters' or EOF. 'characters' must be a container that supports the 'in' method and iteration over its characters. rVz\x02x^[z]+N) characters_until_regexKeyErrorjoinrvrecompilematchrWrYrXendrzrq)rS charactersoppositerrregexresultrrs r chars_untilz"HTMLUnicodeInputStream.chars_untilsS P/X0FGJ$$TZZ1B1BCE}$$7iik$//)MM$**T->->s"CD(+D% MM$**T%6%6%78 9??$+.wwvA PGGTIs3y>#"67TTUEE7 JJ5'}-EJO OJ/X0FG  Ps C,,ED :EEc|turm|jdk(r*||jz|_|xjdz c_y|xjdzc_|j|j|k(sJyy)Nrr)r rYrWrX)rSchars rungetzHTMLUnicodeInputStream.ungetsl s?  A% "DJJ. 1$!!Q&!zz$"3"34<<< rHN)F) __name__ __module__ __qualname____doc__rTrRrPrkrorrrqrrrHrrArA1s7 (G 0" "#J,\ =rHrAcNeZdZdZ d dZfdZdZdZdZdZ dZ xZ S) rDzProvide a binary stream of characters to the HTMLTokenizer. This class takes care of character encoding and removing or replacing incorrect byte-sequences and also provides column and line tracking. c |j||_d|_||_||_||_||_||_|j|_ |jdJ|jy)Nir) rP raw_streamnumber_bytes_metaoverride_encodingtransport_encodingsame_origin_parent_encodinglikely_encodingdefault_encodingdetermine_encodingrOrR)rSrErrrrrrFs rrTzHTMLBinaryInputStream.__init__sz **62 "&!2"4+F(. 0//1 }}Q+++ rHc|jdjj}||jd|_t |y)Nrr{)rO codec_info streamreaderrrQsuperrR)rSr __class__s rrRzHTMLBinaryInputStream.resets8}}Q'22?? "4??I>   rHct|dr.t|dr|jr|S|j}t|S)Nr<seekable)rCrr<rr`s rrPz!HTMLBinaryInputStream.open_stream s9 66 "vz*v/@ [[]FvrHc|jdf}|d|St|jdf}|d|St|jdf}|d|S|j df}|d|St|j df}|d |dj jds|St|jdf}|d|St|jdf}|d|StddfS)NrLr tentativezutf-16 windows-1252) detect_bomrNrrdetect_encoding_metarname startswithrr)rSrOs rrz(HTMLBinaryInputStream.determine_encodings/??$i/ A; "O#4#9#9:IE A; "O#4#:#:;YF A; "O,,. ; A; "O#4#C#CDkQ A; "8A;+;+;+F+Fx+PO#4#7#78+E A; "O#4#8#89;F A; "O~. ;;rHcx|jddk7sJt|x}y|jdvrtd}|Jy||jdk(r|jddf|_y|jj d|df|_|j t d|jdd|)NrrLutf-16beutf-16lerKrzEncoding changed from z to )rOrNrrseekrRr )rS new_encodings rchange_encodingz%HTMLBinaryInputStream.change_encoding8s}}Q9,,,+L9 9L B     8 8*73L+ ++ T]]1- -!]]1-y9DM OO  #)95DM JJL(q)9(:$|nMO OrHc tjdtjdtjdtjdtj di}|j jd}t|tsJdD]@}|j|d|x}s|j j|t|cS|j jd y) zAttempt to detect at BOM at the start of the stream. If an encoding can be determined from the BOM return the name of the encoding otherwise return None. rKrrzutf-32lezutf-32be)rNr) codecsBOM_UTF8 BOM_UTF16_LE BOM_UTF16_BE BOM_UTF32_LE BOM_UTF32_BErr<r=bytesgetrrN)rSbomsstringrrOs rrz HTMLBinaryInputStream.detect_bomHs OOW              %%a(&%((( 1D88F5DM22x2$$T*&x00  1 QrHc|jj|j}t|tsJt |}|jj d|j}||jdvr td}|S)z1Report the encoding declared by the meta element.rrrK) rr<rr=rEncodingParserr get_encodingrrN)rSbufferparserrOs rrz*HTMLBinaryInputStream.detect_encoding_metaesw%%d&<&<=&%(((' Q&&(  HMM5M$M&w/HrH)NNNNr) rrrrrTrRrPrrrr __classcell__)rs@rrDrDs:KOCG"02 & s4y  HX\**rHc>|jdz x|_}|||dzSrrrs rpreviouszEncodingBytes.previouss($(NNQ$66HX\**rHcb|jt|k\rttd||_yNr)rkr?rmaxrs r set_positionzEncodingBytes.set_positions& >>SY & Q)rHcv|jt|k\rt|jdk\r |jSyrrr^s r get_positionzEncodingBytes.get_positions3 >>SY &  >>Q >> ! rHc:||j|jdzSr)ror^s r current_bytezEncodingBytes.current_bytesDMM$--!"344rHc|j}|t|kr)|||dz}||vr ||_|S|dz }|t|kr)||_y)zSkip past a list of characters.rNror?rkrSrrorrs rskipzEncodingBytes.skips_==T"Xhl3I *!)  MH T" "rHc|j}|t|kr)|||dz}||vr ||_|S|dz }|t|kr)||_yrrrs r skip_untilzEncodingBytes.skip_untils_==T"Xhl3IJ&!)  MH T" "rHc~|j||jx}r|xjt|z c_|S)zLook for a sequence of bytes at the start of a string. If the bytes are found return True and advance the position to the byte after the match. Otherwise return False and leave the position alone. )rror?)rSrrs r match_byteszEncodingBytes.match_bytess5__UDMM: :6 : MMSZ 'M rHc |j||jt|zdz |_y#t$rt wxYw)zLook for the next sequence of bytes matching a given sequence. If a match is found advance the position to the last byte of the match. rT)indexror?rk ValueErrorr)rSrs rjump_tozEncodingBytes.jump_tosG  !ZZt}}=E JQNDN   s 03AN)rrrrrrTrrrrpropertyrorspace_characters_bytesrrrrrrHrrrss^1+ +* "  l3H 555    rHrcFeZdZdZdZdZdZdZdZdZ dZ d Z d Z y ) rz@Mini parser for detecting character encoding from meta elements.c2t||_d|_yr )rr|rOrSr|s rrTzEncodingParser.__init__s!$'  rHcd|jvry|j|j|j|j|j|j d}|jD]l}d} |jj d|jD]*\}}|jj|s" |}n|ra|jS|jS#t$rY|jSwxYw#t$rd}YFwxYw)Nr|rr^s rrzEncodingParser.handle_commentsyy  ((rHc~|jjtvryd}d} |jx}y|ddk(r|ddk(}|rv|t||_y|ddk(r|d}t |}|R||_y|ddk(rBt t|d}|jx}t |}| |r||_y|}) NTFrs http-equivrs content-typecharsetscontent) r|rr get_attributerOrNContentAttributeParserrparse)rS has_pragmapending_encoding attributetentative_encodingcodeccontent_parsers rrzEncodingParser.handle_metas 99 ! !)? ? !//11 :|},&q\_< "2">$4DM 1+%.q\"'(:;$$)DM 1+!7 iPQl8S!T*8*>*>*@@&M+,>?E(%,1DM#(+0(1rHc&|jdS)NFend_tag)handle_possible_tagr^s rrz(EncodingParser.handle_possible_start_tags'''66rHcPt|j|jdS)NTr)nextr|rr^s rrz&EncodingParser.handle_possible_end_tags! TYY'''55rHc|j}|jtvr#|r |j|j y|j t }|dk(r|jy |j y)NTr)r|rascii_letters_bytesrrrspaces_angle_bracketsr)rSrr|rrs rrz"EncodingParser.handle_possible_tags}yy   $7 7 !!#OO$9:   MMO %%'/rHc8|jjdS)Nrrr^s rrzEncodingParser.handle_other5syy  &&rHc|j}|jttdgz}|t |dk(sJ|dvryg}g} |dk(r|rnx|tvr|j}n_|dvrdj |dfS|t vr |j|jn|y|j|t|}|dk7r#|jdj |dfSt||j}|x}dvrx t|}||k(r-t|dj |dj |fS|t vr |j|jn|j|w|d k(rdj |dfS|t vr |j|jn|y|j| t|}|tvr"dj |dj |fS|t vr |j|jn|y|j|r) z{Return a (name, value) pair for the next attribute in the stream. If no attribute is found, return None. /Nr)rN=)rrrH)'"r) r|rr frozensetr?rascii_uppercase_bytesrzrrrr)rSr|rrattribute_nameattribute_valuequotes rrzEncodingParser.get_attribute8sJ yyII4y$7HHI  C Na$777  $D ^44 IIK l*xx/4433%%ioo&78"%%i0T I!$   MMO88N+S0 0 T IIK  E< / J %J88N3SXXo5NNN"77#**9??+<=$**95$ 88N+S0 0 / /  " "9??#4 5    " "9 -T I11xx//1JJJ33&&y'89"&&y1rHN) rrrrrTrrrrrrrrrrHrrrs4J>)1B76.'L2rHrceZdZdZdZy)rc6t|tsJ||_yr )r=rr|rs rrTzContentAttributeParser.__init__s$&&& rHc |jjd|jxjdz c_|jj|jjdk(sy|jxjdz c_|jj|jjdvr|jj}|jxjdz c_|jj}|jj|r#|j||jjSy|jj} |jj t |j||jjS#t$r|j|dcYSwxYw#t$rYywxYw)Nrrr)rr)r|rrorrrrr)rSr  old_positions rrzContentAttributeParser.parses`  II  j ) II  ! #  IINN 99))T1 II  ! #  IINN yy%%5 .. ""a'"#yy11 99$$U+99\$))2D2DEE $yy11 4II(()?@99\$))2D2DEE$499\]334  s>A-G0CG G"AF$$F?<G>F??G G GN)rrrrTrrrHrrrs rHrct|tr |jd}| t j |Sy#t$rYywxYw#t $rYywxYw)zReturn the Python codec name corresponding to an encoding. Return None if the string doesn't correspond to a valid encoding. asciiN)r=rdecodeUnicodeDecodeError webencodingslookupAttributeError)rOs rrNrNsk (E" w/H &&x0 0"     s <A AA AA)!rriorrpathlibrrrrr) constantsr r r rrrrrrrxnon_bmp_invalid_codepointsascii_punctuation_rerrGrArDrrrrrNrrHrr1s 1::#"N=M"NNH-HH!!LO!LL.D$<1HHRZZ=>N "rzzOQ7o=o=dM2M`VEVrx2x2v##LrH