Mercurial > repos > rhope

comparison lex.rhope @ 2:73e978d590c7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Adding WIP compiler code
author Mike Pavone <pavone@retrodev.com>
date Wed, 29 Apr 2009 02:58:03 -0400
parents
children 0a4682be2db2
comparison
equal deleted inserted replaced
1:b3f71490858c 2:73e978d590c7
1 Import extendlib.rhope
2
3 Blueprint Token
4 {
5 Type
6 Raw Text
7 Text
8 }
9
10 Token[type,raw,text:out]
11 {
12 out <- [[[Build["Token"]]Type <<[type]]Raw Text <<[raw]]Text <<[text]
13 }
14
15 _Type Match[val, test type, type:out]
16 {
17 If[[test type]=[type]]
18 {
19 out <- Yes
20 }{
21 out <- Val[val]
22 }
23 }
24
25 Type Match@Token[token,type:match,nomatch]
26 {
27 match,nomatch <- If[Fold[["_Type Match"]Set Input[2, [token]Type >>], No, As List[type]]]
28 }
29
30 String Literal[string, raw string, escapes, text, simple tokens, token list:out]
31 {
32 first,rest <- [text]Slice[1]
33 If[[first] = ["\""]]
34 {
35 out <- _Lex[rest, [first]Slice[0], simple tokens, [token list]Append[Token["String Literal", raw string, string]]]
36 }{
37 next raw <- [raw string]Append[first]
38 If[[first] = ["\\"]]
39 {
40 second,next text <- [rest]Slice[1]
41 char <- [escapes]Index[To String[second]] {}
42 {
43 char <- Val[second]
44 }
45 next string <- [string]Append[char]
46 }{
47 next string <- [string]Append[first]
48 next text <- Val[rest]
49 }
50 out <- String Literal[next string, next raw, escapes, next text, simple tokens, token list]
51 }
52 }
53
54 Line Comment[start comment, text, simple tokens, token list:out]
55 {
56 next text, comment <- [text]Get DString["\n"] {} {} {}
57 {
58 next text <- ""
59 }
60 out <- _Lex[next text, [next text]Slice[0], simple tokens, [token list]Append[Token["Line Comment", [start comment]Append[comment], comment]]]
61
62 }
63
64 Block Comment[comment,raw comment, depth, text, simple tokens, token list:out]
65 {
66 Print[["Block Comment: Depth="]Append[depth]]
67 If[[depth] > [0]]
68 {
69 next text, chunk, delim <- [text]Get DString[("/*","*/")] {} {} {}
70 {
71 next text <- ""
72 delim <- ""
73 }
74 If[[delim] = ["/*"]]
75 {
76 next depth <- [depth] + [1]
77 }{
78 next depth <- [depth] - [1]
79 }
80 If[[next depth] = [0]]
81 {
82 next comment <- [comment]Append[chunk]
83 }{
84 next comment <- [[comment]Append[chunk]]Append[delim]
85 }
86 out <- Block Comment[next comment, [[raw comment]Append[chunk]]Append[delim], next depth, next text, simple tokens, token list]
87 }{
88 out <- _Lex[text, [raw comment]Slice[0], simple tokens, [token list]Append[Token["Block Comment", raw comment, comment]]]
89 }
90 }
91
92 Numeric Literal[literal, text, simple tokens, token list:out]
93 {
94 first,rest <- [text]Slice[1]
95 If[[first] In ["01234567890.x"]]
96 {
97 out <- Numeric Literal[[literal]Append[first], rest, simple tokens, token list]
98 }{
99 out <- _Lex[text, [first]Slice[0], simple tokens, [token list]Append[Token["Numeric Literal", literal, literal]]]
100 }
101 }
102
103 Add Token[token, text, simple tokens, token list:out]
104 {
105 out <- _Lex[text, [text]Slice[0], simple tokens, [token list]Append[token]]
106 }
107
108 _Lex[text, symbol, simple tokens,token list:out]
109 {
110 If[[[text]Length] > [0]]
111 {
112 first,rest <- [text]Slice[1]
113 [simple tokens]Index[To String[first]]
114 {
115 token worker <- [["Add Token"]Set Input[0, Token[~, first, ""]]]Set Input[1, rest]
116 }{
117 If[[first] = ["\""]]
118 {
119 escapes <- [[[New@Dictionary[]]Set["n","\n"]]Set["r","\r"]]Set["t","\t"]
120 token worker <- [[[["String Literal"]Set Input[0, [first]Slice[0]]]Set Input[1, first]]Set Input[2, escapes]]Set Input[3, rest]
121 //out <- String Literal["", first, rest, simple tokens, token list, escapes]
122 }{
123 second,second rest <- [rest]Slice[1]
124 If[[[first] = ["<"]] And [[second]=["-"]]]
125 {
126 [first]Append[second]
127 {
128 token worker <- [["Add Token"]Set Input[0, Token["Assignment", ~, ~]]]Set Input[1, second rest]
129 }
130 }{
131
132 If[[[first] = ["/"]] And [[second] = ["*"]]]
133 {
134 token worker <- [[[["Block Comment"]Set Input[0, [first]Slice[0]]]Set Input[1, [first]Append[second]]]Set Input[2, 1]]Set Input[3, second rest]
135 //out <- Block Comment[next text, simple tokens, token list, 1]
136 }{
137 If[[[first] = ["/"]] And [[second] = ["/"]]]
138 {
139 token worker <- [["Line Comment"]Set Input[0, [first]Append[second]]]Set Input[1, second rest]
140 //out <- Line Comment["", [first]Append[second], next text, simple tokens, token list]
141 }{
142 If[[[first]In["0123456789"]] Or [[[first] = ["-"]] And [[second]In["0123456789"]]]]
143 {
144 token worker <- [["Numeric Literal"]Set Input[0, first]]Set Input[1, rest]
145 //out <- Numeric Literal[text, simple tokens, token list]
146 }{
147 out <- _Lex[rest, [symbol]Append[first], simple tokens, token list]
148 }
149 }
150 }
151 }
152
153 }
154 }
155 Val[token worker]
156 {
157 trimmed <- Trim[symbol, " \t\r\n"]
158 If[[trimmed] = [""]]
159 {
160 next list <- Val[token list]
161 }{
162 next list <- [token list]Append[Token["Symbol", trimmed, trimmed]]
163 }
164 out <- [[token worker]Do[
165 [[()]Append[simple tokens]]Append[next list]]
166 ]Index[0]
167 }
168 }{
169 out <- token list
170 }
171 }
172
173 Lex[text:out]
174 {
175 simple tokens <- [[[[[[[[[[[New@Dictionary[]
176 ]Set["{", "Block Begin"]
177 ]Set["}", "Block End"]
178 ]Set["(", "List Begin"]
179 ]Set[")", "List End"]
180 ]Set["[", "Args Begin"]
181 ]Set["]", "Args End"]
182 ]Set[",", "List Separator"]
183 ]Set[":", "Name Separator"]
184 ]Set["@", "Method Separator"]
185 ]Set["`", "Binary Operation"]
186 ]Set["\n", "Newline"]
187 out <- _Lex[text, [text]Slice[0], simple tokens, ()]
188 }