3j;~dZddlmZgdZddlZddlZddlZddlZddlZddl Z ddl Z ejdZ ejdZ ddZdddZddd Zddd Zddd Zddd Z dd ZddZddZd dZej0GddZ d! d"dZedk(rddlZej:yy)#z Tools for working with strings ) annotations) whitespaceEqual getNumFromStrhyphenToCamelCasecamelCaseToHyphenspaceCamelCasegetMd5 formatStr stripAccentsnormalizeFilenameremovePunctuationparenthesesMatchParenthesesMatchNz\s+z +ctjd|}tjd|}tjd|}tjd|}||k(ryy)a returns True if a and b are equal except for whitespace differences >>> a = ' hello \n there ' >>> b = 'hello there' >>> c = ' bye there ' >>> common.whitespaceEqual(a, b) True >>> common.whitespaceEqual(a, c) False TF) WHITESPACEsubLINEFEED)abs G/DATA/.local/lib/python3.12/site-packages/music21/common/stringTools.pyrr,sQ r1Ar1A RA RAAvcg}g}|D])}||vr|j||j|+dj|dj|fS)a$ Given a string, extract any numbers. Return two strings, the numbers (as strings) and the remaining characters. >>> common.getNumFromStr('23a') ('23', 'a') >>> common.getNumFromStr('23a954Hello') ('23954', 'aHello') >>> common.getNumFromStr('') ('', '') r)appendjoin)usrStrnumbersfoundremainchars rrrCsT E F 7? LL  MM$   775>2776? **rcd}t|j|D] \}}|dk(r|}||jz }"|S)a Given a hyphen-connected-string, change it to a camelCaseConnectedString. The replacement can be specified to be something besides a hyphen. >>> common.hyphenToCamelCase('movement-name') 'movementName' >>> common.hyphenToCamelCase('movement_name', replacement='_') 'movementName' Safe to call on a string lacking the replacement character: >>> common.hyphenToCamelCase('voice') 'voice' And on "words" beginning with numbers: >>> common.hyphenToCamelCase('music-21') 'music21' rr) enumeratesplit capitalize)r replacementpostiwords rrrZsI. DV\\+674 6D DOO% %D 8 Krct|dk7r td|j|k7r tdtjdd|zdz|}tjdd|zdz|jS)aF Given a camel-cased string, or a mixture of numbers and characters, create a space separated string. The replacement can be specified to be something besides a hyphen, but only a single character and not (for internal reasons) an uppercase character. code from https://stackoverflow.com/questions/1175208/elegant-python-function-to-convert-camelcase-to-snake-case >>> common.camelCaseToHyphen('movementName') 'movement-name' First letter can be uppercase as well: >>> common.camelCaseToHyphen('MovementName') 'movement-name' >>> common.camelCaseToHyphen('movementNameName') 'movement-name-name' >>> common.camelCaseToHyphen('fileName', replacement='_') 'file_name' Some things you cannot do: >>> common.camelCaseToHyphen('fileName', replacement='NotFound') Traceback (most recent call last): ValueError: Replacement must be a single character. >>> common.camelCaseToHyphen('fileName', replacement='A') Traceback (most recent call last): ValueError: Replacement cannot be an uppercase character. z'Replacement must be a single character.z-Replacement cannot be an uppercase character.z(.)([A-Z][a-z]+)z\1z\2z([a-z0-9])([A-Z]))len ValueErrorlowerrer)rr%s1s rrrzsF ;1BCCk)HII "EK$7%$? HB 66%u{':U'BB G M M OOrcd}d}d}d}d}g}|d} n|} |D]r} | |vrd}nd}|r|s|sd}nd}|s|s|rd}nd}|r7| js|s|r|jd|j| n|j| |rd}qd}tdj|} | D]%} dj| } | j| | } '|r| jdd} | S)a Given a camel-cased string, or a mixture of numbers and characters, create a space separated string. If replaceUnderscore is True (default) then underscores also become spaces (but without the _) >>> common.spaceCamelCase('thisIsATest') 'this Is A Test' >>> common.spaceCamelCase('ThisIsATest') 'This Is A Test' >>> common.spaceCamelCase('movement3') 'movement 3' >>> common.spaceCamelCase('opus41no1') 'opus 41 no 1' >>> common.spaceCamelCase('opus23402no219235') 'opus 23402 no 219235' >>> common.spaceCamelCase('opus23402no219235').title() 'Opus 23402 No 219235' There is a small list called fixMeList that can fix mistakes. >>> common.spaceCamelCase('PMFC22') 'PMFC 22' >>> common.spaceCamelCase('hello_myke') 'hello myke' >>> common.spaceCamelCase('hello_myke', replaceUnderscore=False) 'hello_myke' z 0123456789.F)PMFCT r_)isupperrrreplace)rreplaceUnderscore fixMeListrfirstNum firstCharisNumber lastIsNumr& fixupListr postStrfixMe fixMeSpaceds rrrs<GHIHID   7?HH HYHH iII ||~Y C KK  KK  II78ggdmGhhuo //+u5//#s+ Nrcd|;ttjttjz}tj} |j ||jS#t $r2|j |jdY|jSwxYw)z Return an md5 hash from a string. If no value is given then the current time plus a random number is encoded. >>> common.getMd5('test') '098f6bcd4621d373cade4e832627b4f6' UTF-8) strtimerandomhashlibmd5update TypeErrorencode hexdigest)valuems rr r s }DIIK 3v}}#77 A(  ;;= ( g&' ;;=(sA44)B/.B/cj|g|}tt|D]K}||}t|tr|j d||<t|t r= t |||<Mdj|dzS#t$r- |j d||<n#t$rd||<YnwxYwYwxYw)a DEPRECATED: do not use. May be removed at any time. Format one or more data elements into string suitable for printing straight to stderr or other outputs >>> a = common.formatStr('test', '1', 2, 3) >>> print(a) test 1 2 3 zutf-8rr2 ) ranger+ isinstancebytesdecoderBreprrHAttributeErrorr)msgrest_of_messagekeywordsr'xs rr r s  ! !C 3s8_ F a XXg&CF!S! aA  88C=4    XXg.CF% CF  s6A<< B2BB2B,)B2+B,,B21B2cBtjd|jddjddjddjddjd d}d j|Dcgc]}tj|r|c}Scc}w) u removes accents from unicode strings. >>> s = 'trés vite' >>> 'é' in s True >>> common.stripAccents(s) 'tres vite' Also handles the German Eszett and smart quotes >>> common.stripAccents('Muß') 'Muss' >>> common.stripAccents('Süss, “êtré”') 'Suss, "etre"' Note -- it is still possible to have non-Ascii characters after this, like in this Japanese expression for music: >>> common.stripAccents('音楽') '音楽' NFKDßssu“"u”u‘'u’r) unicodedata normalizer5r combining) inputString nfkd_formcs rr r (s0 fk2 t           77yIy! 0E0Ea0HAyI JJIs 6BBcd}t|}|dkDr!|ddk(rt||dz d}|d|dz }t|}|jddj d}t j d d |j}|||z }|S) u take a name that might contain unicode characters, punctuation, or spaces and normalize it so that it is POSIX compliant (except for the limit on length). Takes in a string or unicode string and returns a string (unicode in Py3) without any accented characters. >>> common.normalizeFilename('03-Niccolò all’lessandra.not really.xml') '03-Niccolo_all_lessandra_not_really.xml' N.asciiignorerAz[^\w-]r3)r+rBr rIrRr.rstrip)name extensionlenNames rr r JsI$iG{tBx3Wq[\*+ LWq[!  D ;;w ) 0 0 9D 66)S$ ' - - /D  Krcrtjddtj}|j |}|S)z Remove all punctuation from a string. >>> common.removePunctuation('This, is! my (face).') 'This is my face' r)rB maketransstring punctuation translate)srqouts rr r fs/ b"f&8&89I ++i C Jrc6eZdZUded<ded<ded<ded<y) rintstartendrBtextlist[ParenthesesMatch]nestedN)__name__ __module__ __qualname____annotations__rrrrqs J H I ""rrc |r|s tdtdddg}|g}d}d}|t|kr|sN|||t|z|k(r:t|t|zddg}|j||t|z }_|s|||t|z|k(r{t|dkrtd|d|d |d |j }||_||j ||_|djj||t|z }||d k(r| }nd}|dz }|t|krt|dkDr"td |d |dj dz d |jS)ap Utility tool to return a list of parentheses matches for a string using a dataclass called `ParenthesesMatch` which has indices of the `start` and `end` of the match, and the `text` of the match, and a set of `nested` ParenthesesMatch objects (which may have their own nested objects). >>> st = r'Bologne wrote (a (whole) (lot) \(of\)) sym\(ph(on)ies\) concertantes.' >>> common.stringTools.parenthesesMatch(st) [ParenthesesMatch(start=15, end=37, text='a (whole) (lot) \\(of\\)', nested=[ParenthesesMatch(start=18, end=23, text='whole', nested=[]), ParenthesesMatch(start=26, end=29, text='lot', nested=[])]), ParenthesesMatch(start=47, end=49, text='on', nested=[])] Other brackets can be used: >>> st = r'[Whammy bars] and [oboes] do [not [mix] very] [well.]' >>> common.stringTools.parenthesesMatch(st, open='[', close=']') [ParenthesesMatch(start=1, end=12, text='Whammy bars', nested=[]), ParenthesesMatch(start=19, end=24, text='oboes', nested=[]), ParenthesesMatch(start=30, end=44, text='not [mix] very', nested=[ParenthesesMatch(start=35, end=38, text='mix', nested=[])]), ParenthesesMatch(start=47, end=52, text='well.', nested=[])] The `open` and `close` parameters can be multiple characters: >>> st = r'Did you eat <> today <>>>' >>> common.stringTools.parenthesesMatch(st, open='<<', close='>>') [ParenthesesMatch(start=14, end=19, text='beans', nested=[]), ParenthesesMatch(start=30, end=46, text='Pythagoreas<>', nested=[ParenthesesMatch(start=43, end=44, text='?', nested=[])])] They cannot, however, be empty: >>> common.stringTools.parenthesesMatch(st, open='', close='') Traceback (most recent call last): ValueError: Neither open nor close can be empty. Unmatched opening or closing parentheses will raise a ValueError: >>> common.stringTools.parenthesesMatch('My (parentheses (sometimes (continue',) Traceback (most recent call last): ValueError: Opening '(' at index 3 was never closed >>> common.stringTools.parenthesesMatch('This is a example>', open='<', close='>') Traceback (most recent call last): ValueError: Closing '>' without '<' at index 23. Note that using multiple characters like a prefix can have unintended consequences: >>> st = r'[Pitch("C4"), [Pitch("D5"), Pitch("E6")], Pitch("Pity("Z9")")]' >>> common.stringTools.parenthesesMatch(st, open='Pitch("', close='")') Traceback (most recent call last): ValueError: Closing '")' without 'Pitch("' at index 59. So to do something like this, you might need to get creative: >>> out = common.stringTools.parenthesesMatch(st, open='("', close='")') >>> out [ParenthesesMatch(start=8, end=10, text='C4', nested=[]), ParenthesesMatch(start=22, end=24, text='D5', nested=[]), ParenthesesMatch(start=35, end=37, text='E6', nested=[]), ParenthesesMatch(start=49, end=59, text='Pity("Z9")', nested=[ParenthesesMatch(start=55, end=57, text='Z9', nested=[])])] >>> extractedPitches = [] >>> for match in out: ... if st[match.start - 7:match.start] == 'Pitch("': ... extractedPitches.append(match.text) >>> extractedPitches ['C4', 'D5', 'E6', 'Pity("Z9")'] * New in v9.3. z$Neither open nor close can be empty.rFrr*zClosing z without z at index rh\zOpening z was never closed) r,rr+rpoprzryr{r})ruopenclose mainMatchstacklastCharWasBackslashr'curPMs rrrxsZ u?@@ RR0I%.KE  A c!f*$aCI &$.$QT]BB?E LL  TNA &Aa#e*n%.5zQ 8E9IdXZPQsRS!TUUIIKEEI5;;q)EJ "I   # #E * UOA  Q44<';#; #(  Q- c!f*0 5zA~8D8:eAhnnq6H5IIZ[\\   r__main__)rrBrrBreturnbool) 0123456789)rrBrrBrztuple[str, str])-)rrBr%rBrrB)TN)rrBrrB)N)rrB)rbrBrrB)rmrBrrB)rurBrrB)())rurBrrBrrBrr|)__doc__ __future__r__all__ dataclassesrErDr.rCrrr_compilerrrrrrrr r r r r dataclassrrr~music21mainTestrrrrs#  RZZ  2::e .+.@(PVNb(   <KD8  ###q q q q qj zGr