o wi(@sddlZddlZdjZGdddZGdddZGdddZGd d d eZd d Z d dZ Gddde Z ddZ ddZddZddddddddjZdeeeed Zd!d"Zd#d$ZeZd%d&Zd'd(Zd.d*d+Zd,d-ZdS)/Nc@sTeZdZdZddZddZejdkrddZnd dZd d Z d d Z ddZ dS)UnicodeLiteralBuilderzAssemble a unicode string. cCs g|_dSN)charsselfr[/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/Cython/Compiler/StringEncoding.py__init__ zUnicodeLiteralBuilder.__init__cCs,t|tsJdt||j|dS)NzExpected str, got ) isinstancestrtyperappendr charactersrrr rszUnicodeLiteralBuilder.appendcCsX|dkr"|d8}|jt|dd|jt|dddS|jt|dS)Nrrrchrr char_numberrrr append_charvals z$UnicodeLiteralBuilder.append_charvalcCs|jt|dSrrrrrr r!cCs||dSr)rrr escape_stringrrr append_uescape$z$UnicodeLiteralBuilder.append_uescapecCstd|jS)N) EncodedStringjoinrrrrr getstring'szUnicodeLiteralBuilder.getstringcCs d|fSrr$rrrr getstrings* z UnicodeLiteralBuilder.getstringsN) __name__ __module__ __qualname____doc__r rsys maxunicoderrr$r&rrrr r s    rc@sHeZdZdZddZddZddZdd Zd d Zd d Z ddZ dS)BytesLiteralBuilderz*Assemble a byte string or char value. cCsg|_||_dSr)rtarget_encodingrr/rrr r 1s zBytesLiteralBuilder.__init__cCs@t|tr ||j}t|tsJtt||j|dSr)r r encoder/bytesrrrrrrr r5s  zBytesLiteralBuilder.appendcCs|jt|ddS)N ISO-8859-1)rrrr1rrrr r;sz"BytesLiteralBuilder.append_charvalcCs||dSr)rrrrr r>r z"BytesLiteralBuilder.append_uescapecCstt|j|jSr) bytes_literal join_bytesrr/rrrr r$AszBytesLiteralBuilder.getstringcCs|Srr%rrrr getcharEszBytesLiteralBuilder.getcharcCs |dfSrr%rrrr r&Ir'zBytesLiteralBuilder.getstringsN) r(r)r*r+r rrrr$r6r&rrrr r..s r.c@s8eZdZdZddZddZddZdd Zd d Zd S) StrLiteralBuilderzDAssemble both a bytes and a unicode representation of a string. cCst||_t|_dSr)r._bytesr_unicoder0rrr r Ps  zStrLiteralBuilder.__init__cC|j||j|dSr)r8rr9rrrr rT zStrLiteralBuilder.appendcCr:r)r8rr9rrrr rXr;z StrLiteralBuilder.append_charvalcCs|j||j|dSr)r8rr9rrrrr r\r;z StrLiteralBuilder.append_uescapecCs|j|jfSr)r8r$r9rrrr r&`rzStrLiteralBuilder.getstringsN) r(r)r*r+r rrrr&rrrr r7Ms r7c@sLeZdZdZddZddZddZedd Zd d Z d d Z ddZ dS)r"NcC|Srrrmemorrr __deepcopy__jzEncodedString.__deepcopy__cCs|jdusJ||jSrencodingr1rrrr byteencodems zEncodedString.byteencodecCs|jdusJ|dS)NzUTF-8rArrrr utf8encodeqs zEncodedString.utf8encodecCs |jduSr)rBrrrr is_unicodeus zEncodedString.is_unicodecCt|Sr)string_contains_surrogatesrrrr contains_surrogatesyz!EncodedString.contains_surrogatescCst|dS)Nutf8)r4rDrrrr as_utf8_string|r zEncodedString.as_utf8_stringcCs2|jdur |}|St||j}|Sr)rBrKr4rCas_c_string_literal)rsrrr rLs z!EncodedString.as_c_string_literal) r(r)r*rBr?rCrDpropertyrErHrKrLrrrr r"ds  r"cCs>tt|D]}|dkrdSd|krdkrdSqqdS)z Check if the unicode string contains surrogate code points on a CPython platform with wide (UCS-4) or narrow (UTF-16) Unicode, i.e. characters that would be spelled as two separate code units on a narrow platform. rTrF)mapord)ustringcrrr rGsrGcCsnd}tjdk}tt|D](}|dks|dkr|rdSq |s!dS|dkr-|r*dSd}q |s2dSd}q |S)a  Check if the unicode string contains lone surrogate code points on a CPython platform with wide (UCS-4) or narrow (UTF-16) Unicode, i.e. characters that would be spelled as two separate code units on a narrow platform, but that do not form a pair. FrrrOT)r,r-rPrQ)rRlast_was_startunicode_uses_surrogate_encodingrSrrr string_contains_lone_surrogatess" rWc@s<eZdZdZddZddZddZdd Zd Zd d Z dS) BytesLiteralNcCr<rrr=rrr r?r@zBytesLiteral.__deepcopy__cCrFr)r2rrrr rCrIzBytesLiteral.byteencodecCs Jd|)NFz this is not a unicode string: %rrrrrr rDr'zBytesLiteral.utf8encodecCs |dS)zcFake-decode the byte string to unicode to support % formatting of unicode strings. r3)decoderrrr __str__s zBytesLiteral.__str__FcCstt|}d|S)Nz"%s")split_string_literalescape_byte_string)rvaluerrr rLs z BytesLiteral.as_c_string_literal) r(r)r*rBr?rCrDrZrErLrrrr rXs rXcCs t|tsJt|}||_|Sr)r r2rXrBrMrBrrr r4sr4cCs,t|ttfs Jt|}|dur||_|Sr)r r r2r"rBr^rrr encoded_strings r_cCst|tr t||St||Sr)r r2r4r_r^rrr encoded_string_or_bytes_literals   r`     )z\az\bz\fz\nz\rz\tz\v)\z??" cCsD|dvr t|ddS|dkrdS|dkrdSdd d |DS) Nz riz\"rh\\r!cSsg|] }dt|dqS)rh03o)rQ.0rSrrr z'_to_escape_sequence..)reprr#rMrrr _to_escape_sequencesrucsg}itD]}ddd|D}||t|d|d<qtdd|djfddfd d }|S) Nr!cSsg|] }d|ddqS)z[%s]rhrm)replacerorrr rqrrz,_build_specials_replacer..ASCIIz(%s)|cs|dS)Nrk)group)m) replacementsrr replace_specialsr z2_build_specials_replacer..replace_specialscs |Srrrt)r|subrr rvr z)_build_specials_replacer..replace) _c_specialr#rrur1recompiler})subexpsspecialregexprvr)r|r{r}r _build_specials_replacers  rcCsR|d}|dvrt|ddS|dkrdSt|}|dks#|dkr'd |S|S) Nr3z \rkrl'z\'rjz\x%02X)rYrsrQ)rSnrrr escape_char s rcCsxt|}z|dWStyYnwt}|j|j}}|D]}|dkr2|d|ddq ||q |dS)zEscape a byte string so that it can be written into C code. Note that this returns a Unicode string instead which, when encoded as ASCII, will result in the correct byte sequence being written. rwrhrn)_replace_specialsrYUnicodeDecodeError bytearrayrextendr1)rMs_newrrbrrr r\s    r\cCst||kr|Sd}g}|t|krk||}t||dkrZd||d|vrZ|d||d|d8}||ddkrZ|d8}||krR|||dd}n||ddks?|||||}|t|ksd|S)Nrrhrkz"")lenfindrr#)rMlimitstartchunksendrrr r[-s$  $ r[cCs$ttt|dg}tjdkr;g|}}|D]#}|dkr4t|dd\}}||d||dq||qnA|g}}|D]9}d|krNdkrvnn&|rvd|dkr^dkrvnn|d|}}|d @d >|d @d|d<qB||qB||krg}d tt|d tt|fS) zBCreate Py_UNICODE[] representation of a given unicode string. rrrrrrOrlrTi ,) listrPrQr,r-divmodrr#r )rMutf16utf32 code_pointhighlow code_unitrrr encode_pyunicode_stringBs&    8  r)r)rr,r#r5rr.r7r r"rGrWr2rXr4r_r`getchar_from_escape_sequencetuplerPrranger~rurrrr\r[rrrrr s>"$