|
1 /* |
|
2 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER. |
|
3 * |
|
4 * Copyright 2016 Mike Becker. All rights reserved. |
|
5 * |
|
6 * Redistribution and use in source and binary forms, with or without |
|
7 * modification, are permitted provided that the following conditions are met: |
|
8 * |
|
9 * 1. Redistributions of source code must retain the above copyright |
|
10 * notice, this list of conditions and the following disclaimer. |
|
11 * |
|
12 * 2. Redistributions in binary form must reproduce the above copyright |
|
13 * notice, this list of conditions and the following disclaimer in the |
|
14 * documentation and/or other materials provided with the distribution. |
|
15 * |
|
16 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" |
|
17 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
|
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
|
19 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE |
|
20 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR |
|
21 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF |
|
22 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS |
|
23 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN |
|
24 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) |
|
25 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
|
26 * POSSIBILITY OF SUCH DAMAGE. |
|
27 * |
|
28 */ |
|
29 |
|
30 #include "highlighter.h" |
|
31 |
|
32 HighlighterData* new_highlighter_data() { |
|
33 HighlighterData* hd = malloc(sizeof(HighlighterData)); |
|
34 if (hd == NULL) { |
|
35 return NULL; |
|
36 } else { |
|
37 hd->multiline_comment = 0; |
|
38 hd->primary_buffer = ucx_buffer_new(NULL, 256, UCX_BUFFER_AUTOEXTEND); |
|
39 hd->secondary_buffer = ucx_buffer_new(NULL, 32, UCX_BUFFER_AUTOEXTEND); |
|
40 return hd; |
|
41 } |
|
42 } |
|
43 |
|
44 void free_highlighter_data(HighlighterData *hd) { |
|
45 ucx_buffer_free(hd->primary_buffer); |
|
46 ucx_buffer_free(hd->secondary_buffer); |
|
47 free(hd); |
|
48 } |
|
49 |
|
50 static void put_htmlescaped(UcxBuffer *dest, char c) { |
|
51 if (c == '>') { |
|
52 ucx_buffer_puts(dest, ">"); |
|
53 } else if (c == '<') { |
|
54 ucx_buffer_puts(dest, "<"); |
|
55 } else { |
|
56 ucx_buffer_putc(dest, c); |
|
57 } |
|
58 } |
|
59 |
|
60 static void put_htmlescapedstr(UcxBuffer *dest, sstr_t s) { |
|
61 for (int i = 0 ; i < s.length ; i++) { |
|
62 put_htmlescaped(dest, s.ptr[i]); |
|
63 } |
|
64 } |
|
65 |
|
66 static int check_keyword(sstr_t word, const char** keywords) { |
|
67 for (int i = 0 ; keywords[i] ; i++) { |
|
68 if (sstrcmp(word, sstr((char*)keywords[i])) == 0) { |
|
69 return 1; |
|
70 } |
|
71 } |
|
72 return 0; |
|
73 } |
|
74 |
|
75 static int check_capsonly(sstr_t word) { |
|
76 for (size_t i = 0 ; i < word.length ; i++) { |
|
77 if (!isupper(word.ptr[i]) && !isdigit(word.ptr[i]) |
|
78 && word.ptr[i] != '_') { |
|
79 return 0; |
|
80 } |
|
81 } |
|
82 return 1; |
|
83 } |
|
84 |
|
85 /* Plaintext Highlighter */ |
|
86 |
|
87 void plain_highlighter(char *src, UcxBuffer *dest, HighlighterData *hd) { |
|
88 while (*src && *src != '\n') { |
|
89 put_htmlescaped(dest, *src); |
|
90 src++; |
|
91 } |
|
92 ucx_buffer_putc(dest, '\n'); |
|
93 } |
|
94 |
|
95 /* C Highlighter */ |
|
96 |
|
97 static const char* ckeywords[] = { |
|
98 "auto", "break", "case", "char", "const", "continue", "default", "do", |
|
99 "double", "else", "enum", "extern", "float", "for", "goto", "if", "int", |
|
100 "long", "register", "return", "short", "signed", "sizeof", "static", |
|
101 "struct", "switch", "typedef", "union", "unsigned", "void", "volatile", |
|
102 "while", NULL |
|
103 }; |
|
104 |
|
105 void c_highlighter(char *src, UcxBuffer *dest, HighlighterData *hd) { |
|
106 /* reset buffers without clearing them */ |
|
107 hd->primary_buffer->size = hd->primary_buffer->pos = 0; |
|
108 hd->secondary_buffer->size = hd->secondary_buffer->pos = 0; |
|
109 |
|
110 /* alias the buffers for better handling */ |
|
111 UcxBuffer *wbuf = hd->primary_buffer; |
|
112 UcxBuffer *ifilebuf = hd->secondary_buffer; |
|
113 |
|
114 /* local information */ |
|
115 size_t sp = (size_t)-1; |
|
116 int isstring = 0, iscomment = 0, isinclude = 0, parseinclude = 0; |
|
117 char quote = '\0'; |
|
118 int isescaping = 0; |
|
119 |
|
120 /* continue a multi line comment highlighting */ |
|
121 if (hd->multiline_comment) { |
|
122 iscomment = 1; |
|
123 ucx_buffer_puts(dest, "<span class=\"c2html-comment\">"); |
|
124 } |
|
125 |
|
126 char c; |
|
127 do { |
|
128 c = src[++sp]; |
|
129 if (!c) break; |
|
130 |
|
131 /* comments */ |
|
132 if (!isstring && c == '/') { |
|
133 if (hd->multiline_comment && sp > 0 && src[sp-1] == '*') { |
|
134 iscomment = 0; |
|
135 hd->multiline_comment = 0; |
|
136 ucx_buffer_puts(dest, "/</span>"); |
|
137 continue; |
|
138 } else if (!iscomment && (src[sp+1] == '/' || src[sp+1] == '*')) { |
|
139 iscomment = 1; |
|
140 hd->multiline_comment = (src[sp+1] == '*'); |
|
141 ucx_buffer_puts(dest, "<span class=\"c2html-comment\">"); |
|
142 } |
|
143 } |
|
144 |
|
145 if (iscomment) { |
|
146 if (c == '\n') { |
|
147 ucx_buffer_puts(dest, "</span>\n"); |
|
148 } else { |
|
149 put_htmlescaped(dest, c); |
|
150 } |
|
151 } else if (isinclude) { |
|
152 if (c == '<') { |
|
153 ucx_buffer_puts(dest, |
|
154 "<span class=\"c2html-stdinclude\"><"); |
|
155 } else if (c == '\"') { |
|
156 if (parseinclude) { |
|
157 ucx_buffer_puts(dest, "\">"); |
|
158 ucx_buffer_write(ifilebuf->space, 1, ifilebuf->size, dest); |
|
159 ucx_buffer_puts(dest, "\"</a>"); |
|
160 parseinclude = 0; |
|
161 } else { |
|
162 ucx_buffer_puts(dest, |
|
163 "<a class=\"c2html-userinclude\" href=\""); |
|
164 ucx_buffer_putc(ifilebuf, '\"'); |
|
165 parseinclude = 1; |
|
166 } |
|
167 } else if (c == '>') { |
|
168 ucx_buffer_puts(dest, "></span>"); |
|
169 } else { |
|
170 if (parseinclude) { |
|
171 ucx_buffer_putc(ifilebuf, c); |
|
172 } |
|
173 put_htmlescaped(dest, c); |
|
174 } |
|
175 } else { |
|
176 /* strings */ |
|
177 if (!isescaping && (c == '\'' || c == '\"')) { |
|
178 if (isstring) { |
|
179 put_htmlescaped(dest, c); |
|
180 if (c == quote) { |
|
181 isstring = 0; |
|
182 ucx_buffer_puts(dest, "</span>"); |
|
183 } else { |
|
184 put_htmlescaped(dest, c); |
|
185 } |
|
186 } else { |
|
187 isstring = 1; |
|
188 quote = c; |
|
189 ucx_buffer_puts(dest, "<span class=\"c2html-string\">"); |
|
190 put_htmlescaped(dest, c); |
|
191 } |
|
192 } else { |
|
193 if (isstring) { |
|
194 put_htmlescaped(dest, c); |
|
195 } else if (!isalnum(c) && c!='_' && c!='#') { |
|
196 /* write buffered word, if any */ |
|
197 if (wbuf->size > 0) { |
|
198 sstr_t word = sstrn(wbuf->space, wbuf->size); |
|
199 int closespan = 1; |
|
200 sstr_t typesuffix = ST("_t"); |
|
201 if (check_keyword(word, ckeywords)) { |
|
202 ucx_buffer_puts(dest, |
|
203 "<span class=\"c2html-keyword\">"); |
|
204 } else if (sstrsuffix(word, typesuffix)) { |
|
205 ucx_buffer_puts(dest, |
|
206 "<span class=\"c2html-type\">"); |
|
207 } else if (word.ptr[0] == '#') { |
|
208 isinclude = !sstrcmp(word, S("#include")); |
|
209 ucx_buffer_puts(dest, |
|
210 "<span class=\"c2html-directive\">"); |
|
211 } else if (check_capsonly(word)) { |
|
212 ucx_buffer_puts(dest, |
|
213 "<span class=\"c2html-macroconst\">"); |
|
214 } else { |
|
215 closespan = 0; |
|
216 } |
|
217 put_htmlescapedstr(dest, word); |
|
218 if (closespan) { |
|
219 ucx_buffer_puts(dest, "</span>"); |
|
220 } |
|
221 } |
|
222 wbuf->pos = wbuf->size = 0; /* reset word buffer */ |
|
223 |
|
224 /* write current character */ |
|
225 put_htmlescaped(dest, c); |
|
226 } else { |
|
227 /* buffer the current word */ |
|
228 ucx_buffer_putc(wbuf, c); |
|
229 } |
|
230 } |
|
231 |
|
232 isescaping = !isescaping & (c == '\\'); |
|
233 } |
|
234 } while (c != '\n'); |
|
235 } |
|
236 |
|
237 /* Java Highlighter */ |
|
238 |
|
239 static const char* jkeywords[] = { |
|
240 "abstract", "continue", "for", "new", "switch", "assert", "default", "goto", |
|
241 "package", "synchronized", "boolean", "do", "if", "private", "this", |
|
242 "break", "double", "implements", "protected", "throw", "byte", "else", |
|
243 "import", "public", "throws", "case", "enum", "instanceof", "return", |
|
244 "transient", "catch", "extends", "int", "short", "try", "char", "final", |
|
245 "interface", "static", "void", "class", "finally", "long", "strictfp", |
|
246 "volatile", "const", "float", "native", "super", "while", NULL |
|
247 }; |
|
248 |
|
249 void java_highlighter(char *src, UcxBuffer *dest, HighlighterData *hd) { |
|
250 /* reset buffers without clearing them */ |
|
251 hd->primary_buffer->size = hd->primary_buffer->pos = 0; |
|
252 hd->secondary_buffer->size = hd->secondary_buffer->pos = 0; |
|
253 |
|
254 /* alias the buffers for better handling */ |
|
255 UcxBuffer *wbuf = hd->primary_buffer; |
|
256 |
|
257 /* local information */ |
|
258 size_t sp = (size_t)-1; |
|
259 int isstring = 0, iscomment = 0, isimport = 0; |
|
260 char quote = '\0'; |
|
261 int isescaping = 0; |
|
262 |
|
263 if (hd->multiline_comment) { |
|
264 iscomment = 1; |
|
265 ucx_buffer_puts(dest, "<span class=\"c2html-comment\">"); |
|
266 } |
|
267 |
|
268 char c; |
|
269 do { |
|
270 c = src[++sp]; |
|
271 if (!c) break; |
|
272 |
|
273 /* comments */ |
|
274 if (!isstring && c == '/') { |
|
275 if (hd->multiline_comment && sp > 0 && src[sp-1] == '*') { |
|
276 iscomment = 0; |
|
277 hd->multiline_comment = 0; |
|
278 ucx_buffer_puts(dest, "/</span>"); |
|
279 continue; |
|
280 } else if (!iscomment && (src[sp+1] == '/' || src[sp+1] == '*')) { |
|
281 iscomment = 1; |
|
282 hd->multiline_comment = (src[sp+1] == '*'); |
|
283 ucx_buffer_puts(dest, "<span class=\"c2html-comment\">"); |
|
284 } |
|
285 } |
|
286 |
|
287 if (iscomment) { |
|
288 if (c == '\n') { |
|
289 ucx_buffer_puts(dest, "</span>\n"); |
|
290 } else { |
|
291 put_htmlescaped(dest, c); |
|
292 } |
|
293 } else if (isimport) { |
|
294 /* TODO: local imports */ |
|
295 } else { |
|
296 /* strings */ |
|
297 if (!isescaping && (c == '\'' || c == '\"')) { |
|
298 if (isstring) { |
|
299 put_htmlescaped(dest, c); |
|
300 if (c == quote) { |
|
301 isstring = 0; |
|
302 ucx_buffer_puts(dest, "</span>"); |
|
303 } else { |
|
304 put_htmlescaped(dest, c); |
|
305 } |
|
306 } else { |
|
307 isstring = 1; |
|
308 quote = c; |
|
309 ucx_buffer_puts(dest, |
|
310 "<span class=\"c2html-string\">"); |
|
311 put_htmlescaped(dest, c); |
|
312 } |
|
313 } else { |
|
314 if (isstring) { |
|
315 put_htmlescaped(dest, c); |
|
316 } else if (!isalnum(c) && c!='_' && c!='@') { |
|
317 /* write buffered word, if any */ |
|
318 if (wbuf->size > 0) { |
|
319 sstr_t word = sstrn(wbuf->space, wbuf->size); |
|
320 int closespan = 1; |
|
321 if (check_keyword(word, jkeywords)) { |
|
322 ucx_buffer_puts(dest, |
|
323 "<span class=\"c2html-keyword\">"); |
|
324 } else if (isupper(word.ptr[0])) { |
|
325 ucx_buffer_puts(dest, |
|
326 "<span class=\"c2html-type\">"); |
|
327 } else if (word.ptr[0] == '@') { |
|
328 ucx_buffer_puts(dest, |
|
329 "<span class=\"c2html-directive\">"); |
|
330 } else if (check_capsonly(word)) { |
|
331 ucx_buffer_puts(dest, |
|
332 "<span class=\"c2html-macroconst\">"); |
|
333 } else { |
|
334 closespan = 0; |
|
335 } |
|
336 put_htmlescapedstr(dest, word); |
|
337 |
|
338 if (closespan) { |
|
339 ucx_buffer_puts(dest, "</span>"); |
|
340 } |
|
341 } |
|
342 wbuf->pos = wbuf->size = 0; /* reset buffer */ |
|
343 |
|
344 /* write current character */ |
|
345 put_htmlescaped(dest, c); |
|
346 } else { |
|
347 /* buffer the current word */ |
|
348 ucx_buffer_putc(wbuf, c); |
|
349 } |
|
350 } |
|
351 |
|
352 isescaping = !isescaping & (c == '\\'); |
|
353 } |
|
354 } while (c != '\n'); |
|
355 } |
|
356 |