U {h~(@sddlZddlZdjZGdddZGdddZGdddZGd d d eZd d Z d dZ Gddde Z ddZ ddZddZddddddddjZdeeeed Zd!d"Zd#d$ZeZd%d&Zd'd(Zd.d*d+Zd,d-ZdS)/Nc@sTeZdZdZddZddZejdkr0ddZnd dZd d Z d d Z ddZ dS)UnicodeLiteralBuilderzAssemble a unicode string. cCs g|_dSN)charsselfrB/tmp/pip-unpacked-wheel-fhl22ezh/Cython/Compiler/StringEncoding.py__init__szUnicodeLiteralBuilder.__init__cCs,t|tstdt||j|dS)NzExpected str, got ) isinstancestrAssertionErrortyperappendr charactersrrr rszUnicodeLiteralBuilder.appendcCsV|dkrB|d8}|jt|dd|jt|ddn|jt|dS)Nrrrchrr char_numberrrr append_charvals z$UnicodeLiteralBuilder.append_charvalcCs|jt|dSrrrrrr r!scCs||dSr)rrrZ escape_stringrrr append_uescape$sz$UnicodeLiteralBuilder.append_uescapecCstd|jS)N) EncodedStringjoinrrrrr getstring'szUnicodeLiteralBuilder.getstringcCs d|fSrr!rrrr getstrings*sz 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 1szBytesLiteralBuilder.__init__cCs@t|tr||j}t|ts0ttt||j|dSr) r r encoder+bytesr rrrrrrr r5s  zBytesLiteralBuilder.appendcCs|jt|ddS)N ISO-8859-1)rrrr-rrrr r;sz"BytesLiteralBuilder.append_charvalcCs||dSr)rrrrr r>sz"BytesLiteralBuilder.append_uescapecCstt|j|jSr) bytes_literal join_bytesrr+rrrr r!AszBytesLiteralBuilder.getstringcCs|Srr"rrrr getcharEszBytesLiteralBuilder.getcharcCs |dfSrr"rrrr r#IszBytesLiteralBuilder.getstringsN) r$r%r&r'r rrrr!r2r#rrrr r*.sr*c@s8eZdZdZddZddZddZdd Zd d Zd S) StrLiteralBuilderzDAssemble both a bytes and a unicode representation of a string. cCst||_t|_dSr)r*_bytesr_unicoder,rrr r Ps zStrLiteralBuilder.__init__cCs|j||j|dSr)r4rr5rrrr rTs zStrLiteralBuilder.appendcCs|j||j|dSr)r4rr5rrrr rXs z StrLiteralBuilder.append_charvalcCs|j||j|dSr)r4rr5rrrrr r\s z StrLiteralBuilder.append_uescapecCs|j|jfSr)r4r!r5rrrr r#`szStrLiteralBuilder.getstringsN) r$r%r&r'r rrrr#rrrr r3Ms r3c@sLeZdZdZddZddZddZedd Zd d Z d d Z ddZ dS)rNcCs|Srrrmemorrr __deepcopy__jszEncodedString.__deepcopy__cCs|jdk st||jSrencodingr r-rrrr byteencodemszEncodedString.byteencodecCs|jdkst|dS)NzUTF-8r9rrrr utf8encodeqszEncodedString.utf8encodecCs |jdkSr)r:rrrr is_unicodeuszEncodedString.is_unicodecCst|Sr)string_contains_surrogatesrrrr contains_surrogatesysz!EncodedString.contains_surrogatescCst|dS)Nutf8)r0r<rrrr as_utf8_string|szEncodedString.as_utf8_stringcCs,|jdkr|}nt||j}|Sr)r:rAr0r;as_c_string_literal)rsrrr rBs  z!EncodedString.as_c_string_literal) r$r%r&r:r8r;r<propertyr=r?rArBrrrr rds rcCs@tt|D]0}|dkrdSd|kr0dkr nq dSq dS)z Check if the unicode string contains surrogate code points on a CPython platform with wide (UCS-4) or narrow (UTF-16) Unicode, i.e. characters that would be spelled as two separate code units on a narrow platform. rTrF)mapord)ustringcrrr r>s r>cCsnd}tjdk}tt|D]P}|dks,|dkr8|rhdSq|sBdS|dkrZ|rTdSd}q|sddSd}q|S)a  Check if the unicode string contains lone surrogate code points on a CPython platform with wide (UCS-4) or narrow (UTF-16) Unicode, i.e. characters that would be spelled as two separate code units on a narrow platform, but that do not form a pair. FrrrET)r(r)rFrG)rHZlast_was_startZunicode_uses_surrogate_encodingrIrrr string_contains_lone_surrogatess  rKc@s<eZdZdZddZddZddZdd Zd Zd d Z dS) BytesLiteralNcCs|Srrr6rrr r8szBytesLiteral.__deepcopy__cCst|Sr)r.rrrr r;szBytesLiteral.byteencodecCsdstd|dS)NFz this is not a unicode string: %r)r rrrr r<szBytesLiteral.utf8encodecCs |dS)zcFake-decode the byte string to unicode to support % formatting of unicode strings. r/)decoderrrr __str__szBytesLiteral.__str__FcCstt|}d|S)Nz"%s")split_string_literalescape_byte_string)rvaluerrr rBs z BytesLiteral.as_c_string_literal) r$r%r&r:r8r;r<rNr=rBrrrr rLsrLcCs t|tstt|}||_|Sr)r r.r rLr:rCr:rrr r0sr0cCs,t|ttfstt|}|dk r(||_|Sr)r r r.r rr:rRrrr encoded_strings rScCs"t|trt||St||SdSr)r r.r0rSrRrrr encoded_string_or_bytes_literals  rT     )z\az\bz\fz\nz\rz\tz\v)\z??" cCsH|dkrt|ddS|dkr$dS|dkr0dSdd d |DSdS) Nz r]z\"r\\\rcSsg|]}dt|dqS)r\Z03o)rG.0rIrrr sz'_to_escape_sequence..)reprr rCrrr _to_escape_sequencesrgcsg}itD]:}ddd|D}||t|d|d<q tdd|djfddfd d }|S) NrcSsg|]}d|ddqS)z[%s]r\ra)replacerbrrr rdsz,_build_specials_replacer..ASCIIz(%s)|cs|dS)Nr_)group)m) replacementsrr replace_specialssz2_build_specials_replacer..replace_specialscs |Srrrf)rnsubrr rhsz)_build_specials_replacer..replace) _c_specialr rrgr-recompilero)Zsubexpsspecialregexprhr)rnrmror _build_specials_replacers  rucCsV|d}|dkr"t|ddS|dkr.dSt|}|dksF|dkrNd |S|SdS) Nr/z \r_r`'z\'r^z\x%02X)rMrerG)rInrrr escape_char s rycCspt|}z |dWStk r(YnXt}|j|j}}|D]"}|dkr\|d|qB||qB|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. rirws\%03o)_replace_specialsrMUnicodeDecodeError bytearrayrextend)rCZs_newrr}brrr rPs  rPcCst||kr|Sd}g}|t|kr||}t||dkrd||d|kr|d||d|d8}||ddkr|d8}||krn|||dd}qqn|||||}qd|SdS)Nrr\r_z"")lenfindrr )rClimitstartchunksendrrr rO/s   $rOcCs&ttt|dg}tjdkrvg|}}|D]F}|dkrht|dd\}}||d||dq,||q,n|g}}|D]r}d|krdkrnnL|rd|dkrdkrnn,|d|}}|d @d >|d @d|d<q||q||krg}d tt|d tt|fS) zBCreate Py_UNICODE[] representation of a given unicode string. rrrrrrEr`rJi ,) listrFrGr(r)divmodrr r )rCutf16utf32 code_pointhighlowZ code_unitrrr encode_pyunicode_stringDs$   8  r)r)rqr(r r1rr*r3r rr>rKr.rLr0rSrTgetZchar_from_escape_sequencetuplerFrrangerprgrurzryrPrOrrrrr s8"$