#this use only by _main_ import os import sys ############################################################# # tnz # ############################################################# # tnz(str) # tnz_cstr(str) # tnz_str(str) r=[tokenType,tokenValue] # tnz_frame(tokrns) # tnz_print(tnz_str) //print # tnz_fprint(filePath) # # # # # # # # # # # # # # # # # # # # # ############################################################# color_list = [ '#dcdcaa', '#559cd6', '#b5cea8', '#16a085', '#c586c0', '#d7ba7d', '#ce9178', '#ffffff', '#cccccc', '#6a9955', '#899b7f', '#9cdcfe', '#5190c5', '#4ec9b0', ] token_color = { # key: #fff -flag # flag ( b bold | i italic | u underline | s spellcheck) # flag ( U upper| L lower | T title ) 'default' : '#cccccc', #default #col color 'C0':'#dcdcaa', 'C1':'#559cd6', 'C2':'#b5cea8', 'C3':'#16a085', 'C4':'#c586c0', 'C5':'#d7ba7d', 'C6':'#ce9178', 'C7':'#ffffff', 'C8':'#cccccc', 'C9':'#6a9955', 'd' : '#b5cea8', #digit 'n' : '#b5cea8', #number 'w' : '#9cdcfe', #-s #word 's' : '#ce9178', #string '/' : '#dcdcaa', 'path': '#dcdcaa', # path / .~/ ../ ../ '_' : ' ', #space 'n' : '#899b7f', #newline 'C' : '#6a9955', #comment 'e' : '#d7ba7d', #escape_code 'U' : '#16a085', #upper case '>' : '#16a085', #cmd # ! '~' : '#ffffff', #other char '&' : '#c586c0', #attr '@' : '#d7ba7d', #-b @tpp '#' : '#899b7f', #-b #id #cccccc '$' : '#4fc1ff', #'#4ed3d5', # $var # % '.' : '#d7ba7d', #\\\'#4ec9b0', # .classname .fileExt .domain obj.method.method2 '-' : '#559cd6', 'tag' : '#559cd6', #tag 'attr' : "#FFA621", #attr #pogroming 'v' : '#9cdcfe', #variable 'K' : '#5190c5', #key 'F' : '#dcdcaa', #function #keyword 'w' : '#cccccc', 'w0' : '#c586c0', #if|elif|import color- 'w1' : '#559cd6', #def color-blue 'w2' : '#4ec9b0', #type|str|list etc color-green 'w9' : '#4ec9b0', #type|str|list etc color-green #combination of token 'l' : '#559cd6', # link:// 'url' : '#559cd6', # url:// 'str-type': '#559cd6', # r'regex' | f'format' | b16|b32|b64'baseEncode' #hex #octal #binary 'cmd' : '#00bf00', } configType = { 'bg':'#1f1f1f', 'title':{ # #hasgtag # @ # num # url # email # word # ~ 'allow':'wdf@#--', 'w_flag': '0aA_-', }, '.tnz':{ # #hasgtag # @ # num # url # email # word # ~ 'allow':'wdnl@#$/-:;.k,', #: use for key 'w_flag': '0aA_-', 'types':{ #token_value: end toke_type '//*': ['\n', 'C'], }, }, '.des':{ # #hasgtag # @ # num # url # email # word # ~ 'allow':'wdnl@#$/-;.k', 'w_flag': '0aA_-', 'types':{ #token_value: end toke_type '//': ['\n', 'C'], }, }, 'url':{ 'allow':',wd@#!-', 'w_flag': '0aA_-', }, '.css':{ 'allow':'Fwd@#$%-k', 'w_flag': '0aA_-', }, '.csv':{ 'allow':',wd------'}, '.html':{ 'w_flag': '0aA_-', 'keywords':{}, }, '.py':{ 'allow' :'-wdfaAb+!^Fk', 'w_flag': '0aA_', 'w9':['from', 'import'], 'keywords':{ 'if' :'w0', 'elif' :'w0', 'else' :'w0', 'break' :'w0', 'continue':'w0', 'as' :'w0', 'return':'w0', 'try' :'w0', 'except':'w0', 'for' :'w0', 'while' :'w0', 'import':'w0', 'from' :'w0', 'def' : 'w1', 'async' : 'w1', 'in' : 'w1', 'not' : 'w1', 'with' : 'w1', 'None' : 'w1', 'global': 'w1', 'and' :'w1', 'or' :'w1', 'type' : 'w2', 'zip' : 'w2', 'list' : 'w2', 'dict' : 'w2', 'str' : 'w2', 'int' : 'w2', 'float' : 'w2', 'Exception':'w2', 'rise':'v2,' }, 'types':{ #token_value: end, toke_type '#': ['\n', 'C'] } }, '.js':{ 'allow' :'-wdaAb+!^fp.F', 'w_flag': '0aA_', 'keywords':{ 'as' :'w0', 'raise' :'w0', 'from' :'w0', 'import' :'w0', 'export' :'w0', 'return' :'w0', 'break' :'w0', 'if' :'w0', 'else' :'w0', 'function' :'w0', 'throw':'w0', 'for':'w0', 'const' :'w1', 'class' :'w1', 'this' :'w1', 'new' :'w1', 'static':'w1', 'let' :'w1', 'new' :'w1', 'null' :'w1', 'false' :'w1', 'true' :'w1', 'construction':'w1', 'instanceof':'w1', 'typeof':'w1', 'of':'w1', 'FormData':'w2', 'Array':'w2', 'Object':'w2', 'Error':'w2', 'JSON':'w2', }, 'types':{ #token_value: end toke_type '/*': ['\n', 'C'], '//': ['\n', 'C'], }, }, '.c':{ 'allow' :'-wdfp#', 'w_flag': '0aA_', 'keywords':{ 'export' :'w0', 'return' :'w0', 'struct' :'w1', 'void' :'w1', 'int' :'w1', 'const' :'w1', 'class' :'w1', 'this' :'w1', 'new' :'w1', 'static' :'w1', 'let' :'w1', 'new' :'w1', 'null' :'w1', 'false' :'w1', 'true' :'w1', 'construction':'w1', }, 'types':{ #token_value: end toke_type '//': ['\n', 'C'] }, }, } #background def print_arr(ln='11:', arr=[], end='\n' ): print('323:', '-'*48, end=end ) if type(arr) != list: return for elm in arr: print(f'{ln} {elm}', end=end) print('323:', '-'*48, end=end ) def print_kv(ln='11:', obj=[], end='\n' ): print('323:', '-'*48, end=end ) if type(obj) != dict: return for k,v in obj.items(): print(f'{ln} {k:12}: {v}', end=end) print('323:', '-'*48, end=end ) def hex_to_rgb(hex_color): def is_valid_hex_color(hex_color): # Remove the hash symbol if it exists hex_color = hex_color.lstrip('#') # Check the length of the hex color if len(hex_color) not in (3, 6): return False # Check if all characters are valid hexadecimal digits valid_chars = "0123456789abcdefABCDEF" for char in hex_color: if char not in valid_chars: return False return True if not is_valid_hex_color(hex_color): hex_color = token_color.get('defult', '#c6c6c6') # Remove the hash symbol if it exists hex_color = hex_color.lstrip('#') # If it's a 3-digit hex code, convert it to 6-digit if len(hex_color) == 3: hex_color = ''.join([c * 2 for c in hex_color]) # Convert the hex values to RGB r = int(hex_color[0:2], 16) g = int(hex_color[2:4], 16) b = int(hex_color[4:6], 16) return r, g, b ############################################################ # tnz # ############################################################ #priary function use to tnz string def tnz(s:str, w='',ln=0): """ Docstring for tnz :param s: Description w_config alpha aA alpnum 0aA word 0aA_ alpha 0aA_- tnz_type primary_type d 0 digit a aA alpha s '' string space newline w 0aA_ word e 0aA_- extend word n -+d.d num p ./ ~/ ../ path token_config ./ ~/ p path mk_ w word aA_ M01 w word 0aA m0-R_ w word 0aA_- mk-5 w-n word-num 5i64 d-w-d 567 d digit +5 n num -5.5 d """ tokens = [] preType = '' si = 0 s = '\n'+s+'\n' endChar = None #jump to lineNum #if ln: # for i, c in enumerate(s): # if c == '\n': si+=i # if si == ln : break lns = [] #line num for i in range(si, len(s)): c = s[i] if endChar: if c == endChar: endChar=None continue elif c >= '0' and c <= '9': tokenType = 'd' elif c >= 'a' and c <= 'z': tokenType = 'w' elif c >= 'A' and c <= 'Z': tokenType = 'w' elif c == '_' : tokenType = 'w' #alpha elif c in ' \t' : tokenType = ' ' #space elif c in '\n' : tokenType = '\n'; lns.append(len(tokens)) #newline elif c in '\'"`' : tokenType = 's' ; endChar=c #newline else : tokenType = c #misc #sperator ,; store each char if tokenType in ',;' and preType == tokenType : tokens.append([c, c]); si=i elif preType != tokenType and preType != '': # type-num +-d.d if preType in '+-' and tokenType == 'd' : preType ='n'; tokenType='n'; continue if preType == 'd' and tokenType == '.' : preType ='n'; tokenType='n'; continue if preType == 'n' and tokenType in '.d': tokenType='n'; continue # type-path ~/ ./ ../ if preType in '.~' and tokenType == '/' : preType='/'; tokenType='/'; continue # type-word aA0_- #if preType == 'w' and tokenType == '_': continue if preType == 'w' and tokenType == '-' and not s[i+1].isdigit() : continue if preType == 'w' and tokenType == 'd' and tokens[-1][0] not in 'nd': continue #if preType == 'w' and tokenType == 'd' : continue token_value = s[si:i] tokens.append([preType, token_value ]) si = i if preType == '#' and tokenType == 'd': tokenType = 'w'; preType = tokenType return tokens[1:] def tnz_cstr(s:str): #cmd str to tokens tokens = tnz(s)+[[' ', ' ']] si = 0 r = [] #print_arr('433:', tokens) types = [] value = [] for i in range(0, len(tokens)): #this use in query if i != 0 and tokens[i][0] in '=' : value = ''.join([_[1] for _ in tokens[si:i]]) r.append([_type, value]) #_type, _value = tokens[i] #r.append([_type, value]) si=i #if _type == '/' and tokens[i-2] == '.' : r.append(['.', tokens[i-1]]) elif tokens[i][0] == ' ' : _type, _value = tokens[si] value = ''.join([_[1] for _ in tokens[si:i]]) #print('446:', si,i, _type,_value, value) if si == 0 and _type == 'w': _type = '>' #elif _type == '-' : _type = '-' #elif _value == '--': _type = '--' #elif _type == '/' : _type = '/' #elif _type == '&' : _type = '&' #elif _type == '=' : _type = '=' #elif _type == 's' : _type = 's' if _type != ' ': r.append([_type, value]) #if _type == '/' and tokens[i-2] == '.' : r.append(['.', tokens[i-1]]) r.append([' ', tokens[i][1]]) si=i+1 #print_arr('453:', r,'\r\n') return r[:-1] #secondry function to tnz further classfication def tnz_str(s:str, kv={}): """ misc logic airth == + >> left-shift != - << right-shift <= / && and >= * || or > ++ & bitwise-and < -- | bitwise-or ! % ^ bitwise-xor num_suffix size KB K killo 12y years MB M million 1m month GB B billion 3w week TB T triloon 24d day """ tokens = tnz(s) ext = kv.get('ext', '') config = configType.get(ext,{}) kw_dict = config.get('keywords',{}) #keyword_dict mw = config.get('w9',[]) w9 = [] wd = {} #{word: wtype} preType, preValue = '', '' #print_arr('433:', tokens) """ wtype //prefix @w import $w var $0 args w word|var dw num_suffic .w class|prop|method !w bId ] # //4 byte each use one byte # - bg # - fg #rgba # - flag # - c # # b bold # u underline # i italic # I inverse # U upper # L lower # # L show lineNum # _ show spaceChar # I inverse # # PF == 0: return frame # PF == 1: print() # PF == -1: retuen print_str ln = kv.get('ln', 0) # start line_num la = kv.get('la', 0) # active line_num config = kv.get('config', 'lI') # lineNum lI_ f = kv.get('f', []) # f[x y w h] ext = kv.get('ext','defult') # lang ext LF = kv.get('LF', '\n') # lineFeed ##################################################### bracket= [] frame = [] colNum = None flag = '' bg,fg = kv.get('bg', '#000000'),'' for i,token in enumerate([['\n', '\n']] + tokens): _type, _value = token #print('890:', _type, _value) #show space char if _type == '0': continue #print space_char if _type == ' ' and '_' in config: if _value[0] == ' ' : _value = '•'* len(_value) if _value[0] == '\t': _value = '>'* len(_value) fg = '#7f7f7f' # line_num elif _type == '\n': fg, s = '#7f7f7f', '' flag = '' if _type == '\n': colNum = None #show lineNum for c in _value: ln+=1 s+='\n' #active line heighlight #if ln==la : print_tokens.append(f'\033[7m') if 'l' in config: s+= f'{ln:3} ' for c in s: if c == '\n': c = LF else : _type = 'ln' if ln == la : flag = 'I' frame.append([bg,fg,flag,c, _type]) continue # color bracket elif _type in '[{()}]': for c in _value: if c in '({[': bracket.append(c) fg = color_list[len(bracket)] if c in ']})' and bracket: fg = color_list[len(bracket)] bracket.pop() frame.append([bg,fg,flag,c,_type]) continue #elif _type == 'w': # and 'v' in colorDict: #fg = token_color.get('','#ffffff' ) #elif colNum : fg = token_color[colNum] elif colNum : fg = token_color[colNum] elif _type == 'w' : fg = token_color['v'] elif _type in token_color: fg = token_color[_type] else : fg = token_color['~'] if _type[0] == 'C' : colNum = _type for c in _value: frame.append([bg,fg,flag,c, _type]) #print flag true than prit if PF: print_tokens = [] #frame[0] newLine char for elm in frame[1:]: bg,fg,flag,c,_type = elm r,g,b = hex_to_rgb(fg) FEC = '' #flag escape code if 'I' in flag: FEC= '7;' print_tokens.append(f'\033[{FEC}38;2;{r};{g};{b}m{c}\033[0m') r = ''.join(print_tokens) if PF == 1: print(r) #print frame if PF == -1: return r #print frame str #print_arr('750:', frame) else: return frame #tokenz string print def tnz_print(txt,kv={'config':'l_', 'LF': '\r\n'}): tokens = tnz_str(txt) tnz_frame(tokens, kv, 1) #file print def tnz_fprint(filePath,kv={'config':'l_', 'LF': '\r\n'}): if not os.path.isfile(filePath): print(f'\r805: [Error] path not exit "{filePath}"') return '' with open(filePath, 'r') as file: txt = file.read() kv = {'config':'l_', 'LF': '\r\n'} tokens = tnz_str(txt) tnz_frame(tokens, kv, 1) return '' ############################################################# # zparse # ############################################################# def zparse(s, PF=0): def getStr(tokens): return ('' .join([_[1] for _ in tokens])).strip() obj,arr = {},[] zli,yli = [],{} zls,yls = [],[] #r_zls,r_yls = zls, yls zobj = {'/zls':zls, '/yls':yls} z = zobj si = 1 CF,key = 'zpath', '' preType = '' #print('840:',s, CF) tokens = tnz(s)+[['\n', '\n'], [' ', ' ']] for i in range(1, len(tokens)): _type, _value = tokens[i] #print('837:', i, hex(ord(_type)), _value) #line = line.replace('\t', ' ') #line = (line.split(' //'))[0].strip() if _type == ' ' : continue elif CF+_type == 'zpath\n': z['zpath']= getStr(tokens[si:i]) # elif CF+_type== '$:' : key = getStr(tokens[si:i]); #obj elif CF+_type== '$\n'and key: zobj[key] = getStr(tokens[si:i]) elif CF+_type== '.{' : key = getStr(tokens[si:i]); obj={}; zobj[key]=obj elif CF+_type=='{:' : key = getStr(tokens[si:i]); #obj elif CF+_type=='{;' and key: obj[key] = getStr(tokens[si:i]); #yli elif CF+_type=='!:' : key = getStr(tokens[si:i]); #yli elif CF+_type=='!;' and key: yli[key] = getStr(tokens[si:i]); #yli elif CF+_type=='!\n' and key: yli[key] = getStr(tokens[si:i]); #yli elif CF+_type=='::' : key = getStr(tokens[si:i]); #zli-obj elif CF+_type==':;' and key: zli[key] = getStr(tokens[si:i]); #yli elif CF+_type==':\n' and key: zli[key] = getStr(tokens[si:i]); #yli elif CF+_type=='-;' and preType+_type != '\n;': zli.append(getStr(tokens[si:i])); si=i+1 elif CF+_type=='-\n': zli.append(getStr(tokens[si:i])); si=i+1 #yli # create zobj elif CF+_type=='/\n': key = getStr(tokens[si:i]); if key in ['/zls' , 'yls']: zobj = z zls, yls = z.get('/zls', []), z.get('/yls', []) else: zls,yls = [],[] zobj = {'/zls':zls, '/yls':yls}; z[key] = zobj #set C_flag if _type == '{': CF='{'; si=i+1; key='' ; # {obj} elif preType+_value == '\n/': CF='/'; si=i ; key='' ; # zobj elif preType+_type == '\n.': CF='.'; si=i ; key='' ; # .class elif preType+_type == '\n$': CF='$'; si=i ; key='' ; # $var elif preType+_type == '\n!': CF='!'; si=i ; key='_'; yli= {}; yls.append(yli) elif preType+_type == '\n:': CF=':'; si=i+1; key='_'; zli= {}; zls.append(zli) elif preType+_type == '\n-': CF='-'; si=i+1; zli= []; zls.append(zli) elif preType == '\n': if CF != '{' and _type != ';' : CF=''; if _type == ';': si =i+1 #insert bId if CF+_type == '!;' and key == '_': bId = '!'+tokens[si+1][1] zobj[bId] = zli if _type in '{\n:;': si=i+1; if _type == '\n;' : key='' preType = _type if PF: print('869:','-'*32) for k,v in z.items(): print(f'869: {k:12}: {v}') return z def tnzm(s, txt=''): kv = {} #{'path, flag, fn, ext} path = '' fn = '' #function name r,emsg = None, '' tokens = tnz_cstr(s) for token in tokens: _type, _value = token if _type == '/' : kv['path'] = _value; path = _value elif _type == '-' : kv['flag'] = _value elif _type == '.' : kv['ext'] = _value elif _type == 's' : kv['str'] = _value elif _value.startswith('fn:'): kv['fn'] = _value; fn= _value #get which str you want tnz if path: if os.path.isfile(path): with open(path, 'r') as file: txt = file.read() else: emsg = f'805: [Error] path not exit "{path}"' else: txt = kv.get('str', '')[1:-1] #print debug data if 0: print_arr('862:', tokens) for k,v in kv.items(): print(f'864:{k:12}: {v}') print('867:', '-'*32) print('866: cmd_str', s) print('867: path', path, ) #print('868: txt\n', txt) print('869:', '-'*32) #################################################### if emsg: return r, emsg elif fn == 'fn:tnz_cstr': tokens = tnz_cstr(txt) print('838:', txt) print_arr('838:', tokens) elif fn == 'fn:tnz_fprint': kv['config'] = 'l_' tokens = tnz_str(txt) tnz_frame(tokens, kv, 1) #print_arr('838:', tokens) elif fn == 'fn:zparse': print('922:') r = zparse(txt) if not r: emsg = f'800: [Error] zparse() has issue' elif fn == 'fn:tnz_frame': tokens = tnz_str(txt) ftokens = tnz_frame(tokens) print('838:', txt) print_arr('838:', tokens) print_arr('838:', ftokens) r = ftokens else: emsg = f'805: [Error] fn not exit "{fn}"' return r, emsg def test(): txt = 'input ./path ../path1 "OPPO A52" ~/path2 -flag' #parse_cstr(txt) txt="""def print_arr(ln='11:', arr=[] ): print('604:', '-'*32 ) if type(arr) != list: return for elm in arr: print(f'{ln} {elm}') """ #r = tnz_print(txt, {'ext':'.py', 'config':'\n_'}) #txt = 'input [()]./path ../path1 "OPPO A52" ~/path2 -flag' #config = {'ext':'.py', 'config':'\n_'} #tokens = tnz_str(txt,config) #tnz_frame(tokens, config) tokens = tnz('http://zshlo.com:7856/:rx/r/resp/lib-js/tnz.js') print_arr('959:', tokens) test() if __name__ == "__main__": s = ' '.join(sys.argv) tnzm(s)