Fri, 30 Aug 2013 10:51:49 +0200
formatted with 4 spaces
1 /*
2 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
3 *
4 * Copyright 2013 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 */
30 #include <stdio.h>
31 #include <stdlib.h>
32 #include <string.h>
33 #include <fcntl.h>
34 #include <unistd.h>
35 #include <ctype.h>
37 #define INPUTBUF_SIZE 2048
38 #define WORDBUF_SIZE 64
40 const char* ckeywords[] = {
41 "auto", "break", "case", "char", "const", "continue", "default", "do",
42 "double", "else", "enum", "extern", "float", "for", "goto", "if", "int",
43 "long", "register", "return", "short", "signed", "sizeof", "static",
44 "struct", "switch", "typedef", "union", "unsigned", "void", "volatile",
45 "while", NULL
46 };
48 const char* jkeywords[] = {
49 "abstract", "continue", "for", "new", "switch", "assert", "default", "goto",
50 "package", "synchronized", "boolean", "do", "if", "private", "this",
51 "break", "double", "implements", "protected", "throw", "byte", "else",
52 "import", "public", "throws", "case", "enum", "instanceof", "return",
53 "transient", "catch", "extends", "int", "short", "try", "char", "final",
54 "interface", "static", "void", "class", "finally", "long", "strictfp",
55 "volatile", "const", "float", "native", "super", "while", NULL
56 };
58 #define iswordcharacter(c) (isalnum(c) || c=='_' || c=='#' || c=='@')
60 int isctype(char *word, size_t len) {
61 return (word[len-2] == '_' && word[len-1] == 't');
62 }
64 int iscdirective(char *word) {
65 return (word[0] == '#');
66 }
68 int isjtype(char *word, size_t len) {
69 return isupper(word[0]);
70 }
72 int isjdirective(char *word) {
73 return word[0] == '@';
74 }
76 typedef struct {
77 const char** keywords;
78 int(*istype)(char*,size_t);
79 int(*isdirective)(char*);
80 } highlighter_t;
82 typedef struct {
83 char* outfilename;
84 char* infilename;
85 int highlight;
86 } settings_t;
88 typedef struct {
89 size_t count;
90 size_t capacity;
91 size_t maxlinewidth;
92 char** lines;
93 } inputfile_t;
95 inputfile_t *inputfilebuffer(size_t capacity) {
96 inputfile_t *inputfile = (inputfile_t*) malloc(sizeof(inputfile_t));
97 inputfile->lines = (char**) malloc(capacity * sizeof(char*));
98 inputfile->capacity = capacity;
99 inputfile->count = 0;
100 inputfile->maxlinewidth = 0;
102 return inputfile;
103 }
105 void addline(inputfile_t *inputfile, char* line, size_t width) {
106 char *l = (char*) malloc(width+1);
107 memcpy(l, line, width);
108 l[width] = 0;
109 if (inputfile->count >= inputfile->capacity) {
110 inputfile->capacity <<= 1;
111 inputfile->lines = realloc(inputfile->lines, inputfile->capacity);
112 }
113 inputfile->lines[inputfile->count] = l;
114 inputfile->maxlinewidth =
115 width > inputfile->maxlinewidth ? width : inputfile->maxlinewidth;
116 inputfile->count++;
117 }
119 void freeinputfilebuffer(inputfile_t *inputfile) {
120 for (int i = 0 ; i < inputfile->count ; i++) {
121 free(inputfile->lines[i]);
122 }
123 free(inputfile->lines);
124 free(inputfile);
125 }
127 inputfile_t *readinput(char *filename) {
129 int fd = open(filename, O_RDONLY);
130 if (fd == -1) return NULL;
132 inputfile_t *inputfile = inputfilebuffer(512);
134 char buf[INPUTBUF_SIZE];
135 ssize_t r;
137 size_t maxlinewidth = 256;
138 char *line = (char*) malloc(maxlinewidth);
139 size_t col = 0;
141 while ((r = read(fd, buf, INPUTBUF_SIZE)) > 0) {
142 for (size_t i = 0 ; i < r ; i++) {
143 if (col >= maxlinewidth-4) {
144 maxlinewidth <<= 1;
145 line = realloc(line, maxlinewidth);
146 }
148 if (buf[i] == '\n') {
149 line[col++] = '\n';
150 line[col] = 0;
151 addline(inputfile, line, col);
152 col = 0;
153 } else {
154 line[col++] = buf[i];
155 }
156 }
157 }
159 free(line);
161 close(fd);
163 return inputfile;
164 }
166 size_t writeescapedchar(char *dest, size_t dp, char c) {
167 if (c == '>') {
168 dest[dp++] = '&'; dest[dp++] = 'g'; dest[dp++] = 't'; dest[dp++] = ';';
169 } else if (c == '<') {
170 dest[dp++] = '&'; dest[dp++] = 'l'; dest[dp++] = 't'; dest[dp++] = ';';
171 } else {
172 dest[dp++] = c;
173 }
175 return dp;
176 }
178 int iskeyword(char *word, const char** keywords) {
179 for (int i = 0 ; keywords[i] ; i++) {
180 if (strncmp(keywords[i], word, WORDBUF_SIZE) == 0) {
181 return 1;
182 }
183 }
184 return 0;
185 }
187 int iscapsonly(char *word, size_t wp) {
188 for (size_t i = 0 ; i < wp ; i++) {
189 if (!isupper(word[i]) && word[i] != '_') {
190 return 0;
191 }
192 }
193 return 1;
194 }
196 void parseline(char *src, char *dest, highlighter_t *highlighter) {
197 size_t sp = 0, dp = 0;
198 /* indent */
199 while (isspace(src[sp])) {
200 dest[dp++] = src[sp++];
201 }
203 static char word[WORDBUF_SIZE];
204 static char includefile[FILENAME_MAX];
206 memset(word, 0, WORDBUF_SIZE);
207 size_t wp = 0, ifp = 0;
208 int isstring = 0, iscomment = 0, isinclude = 0, parseinclude = 0;
209 static int iscommentml;
210 int isescaping = 0;
212 if (iscommentml) {
213 iscomment = 1;
214 memcpy(&(dest[dp]), "<span class=\"c2html-comment\">", 29);
215 dp += 29;
216 }
218 for (char c = src[sp] ; c ; c=src[++sp]) {
219 /* comments */
220 if (c == '/') {
221 if (iscommentml && sp > 0 && src[sp-1] == '*') {
222 iscomment = 0;
223 iscommentml = 0;
224 memcpy(&(dest[dp]), "/</span>", 8);
225 dp += 8;
226 continue;
227 } else if (!iscomment && (src[sp+1] == '/' || src[sp+1] == '*')) {
228 iscomment = 1;
229 iscommentml = (src[sp+1] == '*');
230 memcpy(&(dest[dp]), "<span class=\"c2html-comment\">", 29);
231 dp += 29;
232 }
233 }
235 if (iscomment) {
236 if (c == '\n') {
237 memcpy(&(dest[dp]), "</span>", 7);
238 dp += 7;
239 }
240 dp = writeescapedchar(dest, dp, c);
241 } else if (isinclude) {
242 if (c == '<') {
243 memcpy(&(dest[dp]), "<span class=\"c2html-stdinclude\">", 32);
244 dp += 32;
245 dp = writeescapedchar(dest, dp, c);
246 } else if (c == '\"') {
247 if (parseinclude) {
248 dest[dp++] = '\"';
249 dest[dp++] = '>';
250 memcpy(&(dest[dp]), includefile, ifp);
251 dp += ifp;
253 dp = writeescapedchar(dest, dp, c);
254 memcpy(&(dest[dp]), "</a>", 4);
255 dp += 4;
256 parseinclude = 0;
257 } else {
258 memcpy(&(dest[dp]),
259 "<a class=\"c2html-userinclude\" href=", 35);
260 dp += 35;
261 dp = writeescapedchar(dest, dp, c);
262 ifp = 0;
263 includefile[ifp++] = '\"';
264 parseinclude = 1;
265 }
266 } else if (c == '>') {
267 dp = writeescapedchar(dest, dp, c);
268 memcpy(&(dest[dp]), "</span>", 7);
269 dp += 7;
270 } else {
271 if (parseinclude) {
272 includefile[ifp++] = c;
273 }
274 dp = writeescapedchar(dest, dp, c);
275 }
276 } else {
277 /* strings */
278 if (!isescaping && (c == '\'' || c == '\"')) {
279 isstring ^= 1;
280 if (isstring) {
281 memcpy(&(dest[dp]), "<span class=\"c2html-string\">", 28);
282 dp += 28;
283 dp = writeescapedchar(dest, dp, c);
284 } else {
285 dp = writeescapedchar(dest, dp, c);
286 memcpy(&(dest[dp]), "</span>", 7);
287 dp += 7;
288 }
289 } else {
290 if (isstring) {
291 dp = writeescapedchar(dest, dp, c);
292 } else if (!iswordcharacter(c)) {
293 /* interpret word int_t */
294 if (wp > 0 && wp < WORDBUF_SIZE) {
295 int closespan = 1;
296 if (iskeyword(word, highlighter->keywords)) {
297 memcpy(&(dest[dp]),
298 "<span class=\"c2html-keyword\">", 29);
299 dp += 29;
300 } else if (highlighter->istype(word, wp)) {
301 memcpy(&(dest[dp]),
302 "<span class=\"c2html-type\">", 26);
303 dp += 26;
304 } else if (highlighter->isdirective(word)) {
305 isinclude = !strncmp(
306 "#include", word, WORDBUF_SIZE);
307 memcpy(&(dest[dp]),
308 "<span class=\"c2html-directive\">", 31);
309 dp += 31;
310 } else if (iscapsonly(word, wp)) {
311 memcpy(&(dest[dp]),
312 "<span class=\"c2html-macroconst\">", 32);
313 dp += 32;
314 } else {
315 closespan = 0;
316 }
317 for (int i = 0 ; i < wp ; i++) {
318 dp = writeescapedchar(dest, dp, word[i]);
319 }
320 if (closespan) {
321 memcpy(&(dest[dp]), "</span>", 7);
322 dp += 7;
323 }
324 }
325 memset(word, 0, WORDBUF_SIZE);
326 wp = 0;
327 dp = writeescapedchar(dest, dp, c);
328 } else {
329 /* read word */
330 if (wp < WORDBUF_SIZE) {
331 word[wp++] = c;
332 } else if (wp == WORDBUF_SIZE) {
333 for (int i = 0 ; i < WORDBUF_SIZE ; i++) {
334 dp = writeescapedchar(dest, dp, word[i]);
335 }
336 wp++;
337 dp = writeescapedchar(dest, dp, c);
338 } else {
339 dp = writeescapedchar(dest, dp, c);
340 }
341 }
342 }
344 isescaping = !isescaping & (c == '\\');
345 }
346 }
347 dest[dp] = 0;
348 }
350 void printhelp() {
351 printf("Formats source code using HTML.\n\nUsage:\n"
352 " c2html [Options] FILE\n\n"
353 " Options:\n"
354 " -h Prints this help message\n"
355 " -j Highlight Java instead of C source code\n"
356 " -o <output> Output file (stdout, if not specified)\n"
357 " -p Disable highlighting (plain text)\n"
358 "\n");
361 }
363 int lnint(size_t lnc) {
364 int w = 1, p = 1;
365 while ((p*=10) < lnc) w++;
366 return w;
367 }
369 int main(int argc, char** argv) {
371 settings_t settings;
372 settings.outfilename = NULL;
373 settings.highlight = 1;
375 highlighter_t highlighter;
376 highlighter.isdirective = iscdirective;
377 highlighter.istype = isctype;
378 highlighter.keywords = ckeywords;
380 char optc;
381 while ((optc = getopt(argc, argv, "hjo:p")) != -1) {
382 switch (optc) {
383 case 'o':
384 if (!(optarg[0] == '-' && optarg[1] == 0)) {
385 settings.outfilename = optarg;
386 }
387 break;
388 case 'j':
389 highlighter.isdirective = isjdirective;
390 highlighter.istype = isjtype;
391 highlighter.keywords = jkeywords;
392 break;
393 case 'p':
394 settings.highlight = 0;
395 break;
396 case 'h':
397 printhelp();
398 return 0;
399 default:
400 return 1;
401 }
402 }
404 if (optind != argc-1) {
405 printhelp();
406 return 1;
407 } else {
408 settings.infilename = argv[optind];
410 inputfile_t *inputfile = readinput(settings.infilename);
411 if (inputfile) {
412 FILE *fout;
413 char *line;
414 if (settings.highlight) {
415 line = (char*) malloc(inputfile->maxlinewidth*64);
416 } else {
417 line = NULL;
418 }
419 if (settings.outfilename) {
420 fout = fopen(settings.outfilename, "w");
421 } else {
422 fout = stdout;
423 }
424 fprintf(fout, "<pre>\n");
425 int lnw = lnint(inputfile->count);
426 for (int i = 0 ; i < inputfile->count ; i++) {
427 if (settings.highlight) {
428 parseline(inputfile->lines[i], line, &highlighter);
429 } else {
430 line = inputfile->lines[i];
431 }
432 fprintf(fout, "<span class=\"c2html-lineno\">%*d:</span> %s",
433 lnw, i+1, line);
434 }
435 if (settings.highlight) {
436 free(line);
437 }
438 fprintf(fout, "</pre>\n");
440 if (fout != stdout) {
441 fclose(fout);
442 }
444 freeinputfilebuffer(inputfile);
445 }
447 return 0;
448 }
449 }