ZiSSKrSSKrSSKJr SSKJrJrJrJrJ r SSK J r SSK J r SSKJr SSKJr SSKJr SS KJr SS KJrJr SSKr\R0"S 5r\"S /S Q5rS\S\4SjrS\ S\4SjrS\S\\S44SjrS\S\\ S44Sjr!S\S\"4Sjr#S\S\ 4Sjr$S\S\4Sjr%S\ SS4Sjr&S\'S\ 4Sjr(S\ S\4Sjr)S\ S\4S jr*S\ S\4S!jr+S"\\ S\4S#jr,S:S"\\ S$\S%\S\\\\ \ \ \\ 44\\ 44S&jjr-S\'S\4S'jr.S\'S\4S(jr/S\'S\4S)jr0S*\'S+\'S\4S,jr1S;S-\'S.\'S/\ S\'4S0jjr2SS?S=S S._n[S@5SALa[SBU35 URUS 5nUbURSCS 5nU$g )Da8Return the codepage to use with a specific fcharsetN. Args: fcharsetN (int): The numeric argument N for a charsetN control word. Returns: (int OR None) Returns the int for a codepage if known. Returns None for unknown charsets or charsets with no corresponding codepage (such as OEM or DEFAULT.) r ANSI_CHARSET0x00)namehexdecimalidrDEFAULT_CHARSET0x01NSYMBOL_CHARSET0x02SHIFTJIS_CHARSET0x80HANGUL_CHARSET0x81GB2312_CHARSET0x86CHINESEBIG5_CHARSET0x88 GREEK_CHARSET0xA1TURKISH_CHARSET0xA2HEBREW_CHARSET0xB1ARABIC_CHARSET0xB2BALTIC_CHARSET0xBARUSSIAN_CHARSET0xCC THAI_CHARSET0xDEj EE_CHARSET0xEE OEM_CHARSET0xFFRTFDE.text_extractionTzGetting charset for r6)rrget)r.charsetscharset charset_ids r'get_codepage_num_from_fcharsetrtQs) .vt D) #&1$ G) "! F) &Vcs K ) $6CS I ) $6CS I ) )# N) O&3D I) %FSd K) $6CT J) $6CT J) $6CT J) %FSd K) N#3 G) Lv F) M$ G!)H$+,429+>?ll9d+G[[t,  cURS5n[U5nUSnURSSnSU-$![a gf=f)aExtract the font number controlword default font if it exists. If an RTF file uses a default font, the default font number is specified with the \deffN control word, which must precede the font-table group. Args: tree (Tree): A lark Tree object. Should be the DeEncapsulator.full_tree object. Returns: The default font control number if it exists from the first `\deffN`. None if not found. c[US5$)Ns\deffr )vs r'"get_default_font..s .q)LA::ab>  s8 AA font_treec0nURGHn[U[5(dMSnSnSnURHn[US5(aURnM"[US5(a%[ URSS5n[ U5nMX[US5(dMk[ URSS5nM UcMSnUb [U5nUcUb [U5nUb [U5n OSn SR[[U555n [X8X5X'GM! U$![a SnNif=f![a SnNif=f)zCreate a font tree dictionary with appropriate codeces to decode text. Args: font_tree (Tree): The .rtf font table object decoded as a tree. Returns: A dictionary which maps font numbers to appropriate python codeces needed to decode text. Nr+s \fcharset s\cpgru)rrr rr intrtcheck_codepage_numr"get_python_codecjoinr}rr) rparsed_font_treerrfcharsetcpg_numtok fchar_num codepage_numrtree_strs r'parse_font_treersY"" dD ! !DHG}}/V<<99D1#}EE #CIIabM 2I=iHH1#x@@!#))AB-0G%# ','9('C ")0C,'9''B  +,\:E EHHT*Ft*L%MN)0U)U &G#H !&,'+ , &,'+ ,s$ D4 E4 EE EErcz[R"U5n[RSR X55 U$)zReturns the python codec needed to decode bytes to unicode. Args: codepage_num (int): A codepage number. Returns: The name of the codec in the Python codec registry. Used as the name for enacoding/decoding. z6Found python codec corresponding to code page {0}: {1})r codepage2codeclogdebugformat)r text_codecs r'rrs2)),7JIIFMMlgh rucH[/SQ5nX;aU$[SUS35e)a Provide the codepage number back to you if it is valid. Args: codepage_num (int): A possible codepage number. Returns: The codepage number IF it is a valid codepage number Raises: ValueError: The codepage_num provided isn't a valid codepage number. )%iiiiiiiiiRiTiWiYiZi\i]i^i_i`iaibieifrgikr?rGrCrKiiitiuiviwixiyizi{i|i}iirkrcr2rOrSrWr[r_iiQi'i'i'i'i'i'i'i'i'i'i!'i%'i-'i_'ia'ib'i.i.i Ni!Ni"Ni#Ni$Ni%NiNiNiNiNiNi%Oi-Oi1Oi5Oi6Oi8OiM    ) 0 0 22ruc SnSn[U5GHupV[U[5(aM[U5(dM/[ UR 5(aUnUnMOUcMT[ UR 5(aUn[UR UR 5n[SUURURURURURURS9n XU'[SSURS-URS-URURURURS9n XU'SnSnGM>["R%SR'UW55 USLa2SR!XVs/sHoUR PM sn5X'GM[)S5e U$![a~n USLarSR!XVs/sHoUR PM Os snfsn5X'SR!XVs/sHoUR PM Os snfsn5UW'Sn A GM*U eSn A ff=fs snf) z Raises: ValueError: A Standalone high-surrogate was found. High surrogate followed by a illegal low-surrogate character. Nr start_posend_poslineend_linecolumn end_columnrurTrz^Standalone high-surrogate found. High surrogate followed by a illegal low-surrogate character.)rrr rrr rrr rrrrrrUnicodeDecodeErrorrrrrr") rr0use_ASCII_alternatives_on_unicode_decode_failuresurrogate_startsurrogate_highic surrogate_lowsurrogate_value surrogate_tok blank_tokr%s r'merge_surrogate_charsr s<ON" a    a %agg.."#!" ,(11$%M%*?@T@T@M@S@S+U).h.=8F8P8P6C6K6K3A3F3F7D7M7M5C5J5J9F9Q9Q)S 5B1$)(*-4B4L4LQ4N2?2G2G2I/=/B/B3@3I3I1?1F1F5B5M5M%O '0 *.)-HH]ddesuBCDG4O47HHyOh=iOh!ggOh=i4j1(*JKK[#\ O.%KtS8;S\SlAmSla''SlAm8nH5*-((YE]3^E]GGE]3^*_HQKK"$H %>js=C F9 I 9 IH<G/ . H<H$ #H<:H<<Ic[U[5(a1URS:Xa!URR S5(agg)N CONTROLWORDs\ucTF)rr rr rrs r'rr=s6$ 99 %zz$$W-- rucVURR5n[USS5nU$)N)r rr)r#cur_ucs r'rrDs( ::   D ab]F Mruc:UHn[U5(dM g g)zkChecks if an tree's children includes a hexarray tree. children (array): the children object from a tree. TF) is_hexarray)rr#s r' has_hexarrayrKs!  t   rucd[U[5(aURRS:Xagg)zhChecks if an item is a hexarray tree. item (Tree or Token): an item to check to see if its a hex array rTF)rr rr rs r'rrUs' $ 99??j ( rucpURSS5n[RUR55nU$)zVConvert hex encoded string to bytes. item (str): a hex encoded string in format \'XX s\'ru)replacebytesfromhexr)r# hexstring hex_bytess r'get_bytes_from_hex_encodedr_s1  VS)I i..01I ruc[S5SLa[SRX55 UcSnURU5nUR 5n[S5SLa[SRXU55 U$)zDecode a bytes object using a specified codec. item (bytes): A bytes object. codec (str): The name of the codec to use to decode the bytes roTzdecoding char {0} with font {1}CP1252z)char {0} decoded into {1} using codec {2})rrrrr)r#rdecodeds r'decode_hex_charrhst +,4=DDTQR }kk% GnnG+,4GNNt^cde NrucX\rSrSrS SjrS\4SjrS\4SjrS\\ 4Sjr S r S r g) TextDecoderizNcRXlX lX0lSUl/Ul0Ulg)a keep_fontdef: (bool) If False (default), will remove fontdef's from object tree once they are processed. initial_byte_count: (int) The initial Unicode Character Byte Count. Does not need to be set unless you are only providing a RTF snippet which does not contain the RTF header which sets the information. use_ASCII_alternatives_on_unicode_decode_failure: (bool) If we encounter errors when decoding unicode chars we will use the ASCII alternative since that's what they are included for. N) keep_fontdefucbcr default_font font_stack font_table)selfr!initial_byte_countrs r'__init__TextDecoder.__init__|s-)& @p=!ruobjc[U5UlUR/Ul[URS5n[ U5Ul[S5SLa[SU35 gg)J obj (Tree): A lark Tree object. Should be the DeEncapsulator.full_tree. rroTzFONT TABLE FOUND: N) rr#r$r(rrr%rr)r&r* raw_fonttbls r' set_font_infoTextDecoder.set_font_infosb -S1,,-$S\\!_5 )+6 / 0D 8 "4[M B C 9rucURU5 URnURU5Vs/sHo3PM snUlgs snf)r,N)r.riterate_on_children)r&r*rrs r'update_childrenTextDecoder.update_childrensA 3<<#'#;#;H#EF#Ea#EF Fs Arc[U5(a-[UURS9up[UUUR5nU$)N)r)rrr"r r)r&rrs r' prep_unicodeTextDecoder.prep_unicodesH !( + +#>hIM#T H -X-6-1-b-bdH ruc #L# /n[S5SLa"[S5 [S[U5-5 URU5n[S5SLa[S[U5-5 UGHn[ U5(aeUR R URR55 UR UR5 URSLaUv MwMy[U5(a[UR5R5n[SUURURUR UR"UR$UR&S9n[S5SLa[SUS U35 Uv GM[)U5(Ga SnSnSnSn Sn Sn Sn UR*Hn U c_U RnU RnU R nU R"n U R$n U R&n [-U R5n MeU RnU R"n U R&n U [-U R5- n M UR.UR S nUR0n[3X5n[SUUUUU U U S9nUv GM8[5U[65(a8UR9UR*5Vs/sHnUPM snUlUv GMUv GM UHnUR R;5 M gs snf7f) NroTz2Starting to iterate on text extraction children...z PREP-BEFORE: z PREP-AFTER: rrzUNICODE TOKEN z: )rrrr5r-r$rr r!r!rrrr rrrrrrrrrr%rrrr r1r)r&r set_fontsr#r decoded_tok_hex_start_pos _hex_end_pos_hex_start_line _hex_end_line_hex_start_column_hex_end_column base_byteshexchildcurrent_fontdef current_codec decoded_hexdecoded_hex_tokrs r'r1TextDecoder.iterate_on_childrens / 0D 8  T U X > ?$$X. / 0D 8 tH~ = >Dd##&&tzz'7'7'9:  ,$$,J-#D))/ ;BBD#H$+.2nn,0LL)--1]]+/;;/3@  78D@'.b (NO!!T""!%# "& $ $(!"&! $ H!))1););'/'7'7 *2--(0(9(9 ,4OO)*2*=*=%?%O '/'7'7 (0(9(9 *2*=*="&@&PP !.#'//$//"2E"F / 5 5 -jH "'(32@0<-<1>/@3B#D&%D$'',0,D,DT]],S T,Sq,S T   }~A OO   ! !UsKL$ L#AL$)r#r$r%r!r"r)FNF) __name__ __module__ __qualname____firstlineno__r(r r.r2rr r5r1__static_attributes__rur'rrzs?$)Y^$ D DG4GT%[ J"rur)Tr)z utf-16-le)F);codecsre collectionsrtypingrrrrroletools.commonr lark.lexerr lark.treer RTFDE.exceptionsr rrrrrlogging getLoggerrrr(boolr-rrtstrrdictrrrrrrrrrrrrrrrrr rrrrrrrrMrur'r[s "00%)449   Y M N44$4> % D $c$eCHo$N4E#d(O..t..b 3 3 bSbSb0 jc jd j"#8  4 Ed0 U t  T%[ T  :>23P$u+P26P,/P8=$)$u+tE$u+