Go to most recent revision | Details | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 1913 | jaeger | 1 | class Token: |
| 2 | def __init__(self,pos=(0,0),type='symbol',val=None,items=None): |
||
| 3 | self.pos,self.type,self.val,self.items=pos,type,val,items |
||
| 4 | |||
| 5 | def u_error(ctx,s,i): |
||
| 6 | y,x = i |
||
| 7 | line = s.split('\n')[y-1] |
||
| 8 | p = '' |
||
| 9 | if y < 10: p += ' ' |
||
| 10 | if y < 100: p += ' ' |
||
| 11 | r = p + str(y) + ": " + line + "\n" |
||
| 12 | r += " "+" "*x+"^" +'\n' |
||
| 13 | raise 'error: '+ctx+'\n'+r |
||
| 14 | |||
| 15 | ISYMBOLS = '`-=[];,./~!@$%^&*()+{}:<>?' |
||
| 16 | SYMBOLS = [ |
||
| 17 | 'def','class','yield','return','pass','and','or','not','in','import', |
||
| 18 | 'is','while','break','for','continue','if','else','elif','try', |
||
| 19 | 'except','raise','True','False','None','global','del','from', |
||
| 20 | '-','+','*','**','/','%','<<','>>', |
||
| 21 | '-=','+=','*=','/=','=','==','!=','<','>', |
||
| 22 | '<=','>=','[',']','{','}','(',')','.',':',',',';','&','|','!', |
||
| 23 | ] |
||
| 24 | B_BEGIN,B_END = ['[','(','{'],[']',')','}'] |
||
| 25 | |||
| 26 | class TData: |
||
| 27 | def __init__(self): |
||
| 28 | self.y,self.yi,self.nl = 1,0,True |
||
| 29 | self.res,self.indent,self.braces = [],[0],0 |
||
| 30 | def add(self,t,v): self.res.append(Token(self.f,t,v)) |
||
| 31 | |||
| 32 | def clean(s): |
||
| 33 | s = s.replace('\r\n','\n') |
||
| 34 | s = s.replace('\r','\n') |
||
| 35 | return s |
||
| 36 | |||
| 37 | def tokenize(s): |
||
| 38 | s = clean(s) |
||
| 39 | try: return do_tokenize(s) |
||
| 40 | except: u_error('tokenize',s,T.f) |
||
| 41 | |||
| 42 | def do_tokenize(s): |
||
| 43 | global T |
||
| 44 | T,i,l = TData(),0,len(s) |
||
| 45 | T.f = (T.y,i-T.yi+1) |
||
| 46 | while i < l: |
||
| 47 | c = s[i]; T.f = (T.y,i-T.yi+1) |
||
| 48 | if T.nl: T.nl = False; i = do_indent(s,i,l) |
||
| 49 | elif c == '\n': i = do_nl(s,i,l) |
||
| 50 | elif c in ISYMBOLS: i = do_symbol(s,i,l) |
||
| 51 | elif c >= '0' and c <= '9': i = do_number(s,i,l) |
||
| 52 | elif (c >= 'a' and c <= 'z') or \ |
||
| 53 | (c >= 'A' and c <= 'Z') or c == '_': i = do_name(s,i,l) |
||
| 54 | elif c=='"' or c=="'": i = do_string(s,i,l) |
||
| 55 | elif c=='#': i = do_comment(s,i,l) |
||
| 56 | elif c == '\\' and s[i+1] == '\n': |
||
| 57 | i += 2; T.y,T.yi = T.y+1,i |
||
| 58 | elif c == ' ' or c == '\t': i += 1 |
||
| 59 | else: u_error('tokenize',s,T.f) |
||
| 60 | indent(0) |
||
| 61 | r = T.res; T = None |
||
| 62 | return r |
||
| 63 | |||
| 64 | def do_nl(s,i,l): |
||
| 65 | if not T.braces: |
||
| 66 | T.add('nl',None) |
||
| 67 | i,T.nl = i+1,True |
||
| 68 | T.y,T.yi = T.y+1,i |
||
| 69 | return i |
||
| 70 | |||
| 71 | def do_indent(s,i,l): |
||
| 72 | v = 0 |
||
| 73 | while i |
||
| 74 | c = s[i] |
||
| 75 | if c != ' ' and c != '\t': break |
||
| 76 | i,v = i+1,v+1 |
||
| 77 | if c != '\n' and c != '#' and not T.braces: indent(v) |
||
| 78 | return i |
||
| 79 | |||
| 80 | def indent(v): |
||
| 81 | if v == T.indent[-1]: pass |
||
| 82 | elif v > T.indent[-1]: |
||
| 83 | T.indent.append(v) |
||
| 84 | T.add('indent',v) |
||
| 85 | elif v < T.indent[-1]: |
||
| 86 | n = T.indent.index(v) |
||
| 87 | while len(T.indent) > n+1: |
||
| 88 | v = T.indent.pop() |
||
| 89 | T.add('dedent',v) |
||
| 90 | |||
| 91 | |||
| 92 | def do_symbol(s,i,l): |
||
| 93 | symbols = [] |
||
| 94 | v,f,i = s[i],i,i+1 |
||
| 95 | if v in SYMBOLS: symbols.append(v) |
||
| 96 | while i |
||
| 97 | c = s[i] |
||
| 98 | if not c in ISYMBOLS: break |
||
| 99 | v,i = v+c,i+1 |
||
| 100 | if v in SYMBOLS: symbols.append(v) |
||
| 101 | v = symbols.pop(); n = len(v); i = f+n |
||
| 102 | T.add('symbol',v) |
||
| 103 | if v in B_BEGIN: T.braces += 1 |
||
| 104 | if v in B_END: T.braces -= 1 |
||
| 105 | return i |
||
| 106 | |||
| 107 | def do_number(s,i,l): |
||
| 108 | v,i,c =s[i],i+1,s[i] |
||
| 109 | while i |
||
| 110 | c = s[i] |
||
| 111 | if (c < '0' or c > '9') and (c < 'a' or c > 'f') and c != 'x': break |
||
| 112 | v,i = v+c,i+1 |
||
| 113 | if c == '.': |
||
| 114 | v,i = v+c,i+1 |
||
| 115 | while i |
||
| 116 | c = s[i] |
||
| 117 | if c < '0' or c > '9': break |
||
| 118 | v,i = v+c,i+1 |
||
| 119 | T.add('number',v) |
||
| 120 | return i |
||
| 121 | |||
| 122 | def do_name(s,i,l): |
||
| 123 | v,i =s[i],i+1 |
||
| 124 | while i |
||
| 125 | c = s[i] |
||
| 126 | if (c < 'a' or c > 'z') and (c < 'A' or c > 'Z') and (c < '0' or c > '9') and c != '_': break |
||
| 127 | v,i = v+c,i+1 |
||
| 128 | if v in SYMBOLS: T.add('symbol',v) |
||
| 129 | else: T.add('name',v) |
||
| 130 | return i |
||
| 131 | |||
| 132 | def do_string(s,i,l): |
||
| 133 | v,q,i = '',s[i],i+1 |
||
| 134 | if (l-i) >= 5 and s[i] == q and s[i+1] == q: # """ |
||
| 135 | i += 2 |
||
| 136 | while i |
||
| 137 | c = s[i] |
||
| 138 | if c == q and s[i+1] == q and s[i+2] == q: |
||
| 139 | i += 3 |
||
| 140 | T.add('string',v) |
||
| 141 | break |
||
| 142 | else: |
||
| 143 | v,i = v+c,i+1 |
||
| 144 | if c == '\n': T.y,T.yi = T.y+1,i |
||
| 145 | else: |
||
| 146 | while i |
||
| 147 | c = s[i] |
||
| 148 | if c == "\\": |
||
| 149 | i = i+1; c = s[i] |
||
| 150 | if c == "n": c = '\n' |
||
| 151 | if c == "r": c = chr(13) |
||
| 152 | if c == "t": c = "\t" |
||
| 153 | if c == "0": c = "\0" |
||
| 154 | v,i = v+c,i+1 |
||
| 155 | elif c == q: |
||
| 156 | i += 1 |
||
| 157 | T.add('string',v) |
||
| 158 | break |
||
| 159 | else: |
||
| 160 | v,i = v+c,i+1 |
||
| 161 | return i |
||
| 162 | |||
| 163 | def do_comment(s,i,l): |
||
| 164 | i += 1 |
||
| 165 | while i |
||
| 166 | c = s[i] |
||
| 167 | if c == '\n': break |
||
| 168 | i += 1 |
||
| 169 | return i |
||
| 170 | |||
| 171 |