1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410
/*
* MD4C: Markdown parser for C
* (http://github.com/mity/md4c)
*
* Copyright (c) 2016 Martin Mitas
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include "md4c.h"
#include "cmdline.h"
/*********************************
*** Simple grow-able buffer ***
*********************************/
/* We render to a memory buffer instead of directly outputting the rendered
* documents, as this allows using this utility for evaluating performance
* of MD4C (--stat option). This allows us to measure just time of the parser,
* without the I/O.
*/
struct membuffer {
char* data;
MD_SIZE asize;
MD_SIZE size;
};
static void
membuf_init(struct membuffer* buf, MD_SIZE new_asize)
{
buf->size = 0;
buf->asize = new_asize;
buf->data = malloc(buf->asize);
if(buf->data == NULL) {
fprintf(stderr, "membuf_init: malloc() failed.");
exit(1);
}
}
static void
membuf_fini(struct membuffer* buf)
{
if(buf->data)
free(buf->data);
}
static void
membuf_grow(struct membuffer* buf, MD_SIZE new_asize)
{
buf->data = realloc(buf->data, new_asize);
if(buf->data == NULL) {
fprintf(stderr, "membuf_grow: realloc() failed.");
exit(1);
}
buf->asize = new_asize;
}
static void
membuf_append(struct membuffer* buf, const char* data, MD_SIZE size)
{
if(buf->asize < buf->size + size)
membuf_grow(buf, (buf->size + size) * 2);
memcpy(buf->data + buf->size, data, size);
buf->size += size;
}
#define MEMBUF_APPEND_LITERAL(buf, literal) membuf_append((buf), (literal), strlen(literal))
#define HTML_NEED_ESCAPE(ch) ((ch) == '&' || (ch) == '<' || (ch) == '>' || (ch) == '"')
static void
membuf_append_escaped(struct membuffer* buf, const char* data, MD_SIZE size)
{
MD_OFFSET beg = 0;
MD_OFFSET off = 0;
/* Some characters need to be escaped in normal HTML text. */
while(1) {
while(off < size && !HTML_NEED_ESCAPE(data[off]))
off++;
if(off > beg)
membuf_append(buf, data + beg, off - beg);
if(off < size) {
switch(data[off]) {
case '&': MEMBUF_APPEND_LITERAL(buf, "&"); break;
case '<': MEMBUF_APPEND_LITERAL(buf, "<"); break;
case '>': MEMBUF_APPEND_LITERAL(buf, ">"); break;
case '"': MEMBUF_APPEND_LITERAL(buf, """); break;
}
off++;
} else {
break;
}
beg = off;
}
}
/**************************************
*** HTML renderer implementation ***
**************************************/
static void
open_code_block(struct membuffer* out, const MD_BLOCK_CODE_DETAIL* det)
{
MEMBUF_APPEND_LITERAL(out, "<pre><code");
/* If known, output the HTML 5 attribute class="language-LANGNAME". */
if(det->lang != NULL) {
MEMBUF_APPEND_LITERAL(out, " class=\"language-");
membuf_append_escaped(out, det->lang, det->lang_size);
MEMBUF_APPEND_LITERAL(out, "\"");
}
MEMBUF_APPEND_LITERAL(out, ">");
}
static int
enter_block_callback(MD_BLOCKTYPE type, void* detail, void* userdata)
{
static const char* head[6] = { "<h1>", "<h2>", "<h3>", "<h4>", "<h5>", "<h6>" };
struct membuffer* out = (struct membuffer*) userdata;
switch(type) {
case MD_BLOCK_DOC: /* noop */ break;
case MD_BLOCK_QUOTE: MEMBUF_APPEND_LITERAL(out, "<blockquote>"); break;
case MD_BLOCK_HR: MEMBUF_APPEND_LITERAL(out, "<hr>\n"); break;
case MD_BLOCK_H: MEMBUF_APPEND_LITERAL(out, head[((MD_BLOCK_H_DETAIL*)detail)->level - 1]); break;
case MD_BLOCK_CODE: open_code_block(out, (const MD_BLOCK_CODE_DETAIL*) detail); break;
case MD_BLOCK_HTML: /* noop */ break;
case MD_BLOCK_P: MEMBUF_APPEND_LITERAL(out, "<p>"); break;
}
return 0;
}
static int
leave_block_callback(MD_BLOCKTYPE type, void* detail, void* userdata)
{
static const char* head[6] = { "</h1>\n", "</h2>\n", "</h3>\n", "</h4>\n", "</h5>\n", "</h6>\n" };
struct membuffer* out = (struct membuffer*) userdata;
switch(type) {
case MD_BLOCK_DOC: /*noop*/ break;
case MD_BLOCK_QUOTE: MEMBUF_APPEND_LITERAL(out, "</blockquote>"); break;
case MD_BLOCK_HR: /*noop*/ break;
case MD_BLOCK_H: MEMBUF_APPEND_LITERAL(out, head[((MD_BLOCK_H_DETAIL*)detail)->level - 1]); break;
case MD_BLOCK_CODE: MEMBUF_APPEND_LITERAL(out, "</code></pre>\n"); break;
case MD_BLOCK_HTML: /* noop */ break;
case MD_BLOCK_P: MEMBUF_APPEND_LITERAL(out, "</p>\n"); break;
}
return 0;
}
static int
enter_span_callback(MD_SPANTYPE type, void* detail, void* userdata)
{
return 0;
}
static int
leave_span_callback(MD_SPANTYPE type, void* detail, void* userdata)
{
return 0;
}
static int
text_callback(MD_TEXTTYPE type, const MD_CHAR* text, MD_SIZE size, void* userdata)
{
struct membuffer* out = (struct membuffer*) userdata;
switch(type) {
case MD_TEXT_BR: MEMBUF_APPEND_LITERAL(out, "<br>\n"); break;
case MD_TEXT_SOFTBR: MEMBUF_APPEND_LITERAL(out, "\n"); break;
case MD_TEXT_HTML: membuf_append(out, text, size); break;
default: membuf_append_escaped(out, text, size); break;
}
return 0;
}
static void
debug_log_callback(const char* msg, void* userdata)
{
fprintf(stderr, "Error:%s\n", msg);
}
/**********************
*** Main program ***
**********************/
static int
process_file(FILE* in, FILE* out, unsigned flags, int fullhtml, int print_stat)
{
MD_RENDERER renderer = {
enter_block_callback,
leave_block_callback,
enter_span_callback,
leave_span_callback,
text_callback,
debug_log_callback,
flags
};
MD_SIZE n;
struct membuffer buf_in = {0};
struct membuffer buf_out = {0};
int ret = -1;
clock_t t0, t1;
membuf_init(&buf_in, 32 * 1024);
/* Read the input file into a buffer. */
while(1) {
if(buf_in.size >= buf_in.asize)
membuf_grow(&buf_in, 2 * buf_in.asize);
n = fread(buf_in.data + buf_in.size, 1, buf_in.asize - buf_in.size, in);
if(n == 0)
break;
buf_in.size += n;
}
/* Input size is good estimation of output size. Add some more reserve to
* deal with the HTML header/footer and tags. */
membuf_init(&buf_out, buf_in.size + buf_in.size/8 + 64);
/* Parse the document. This shall call our callbacks provided via the
* md_renderer_t structure. */
t0 = clock();
ret = md_parse(buf_in.data, buf_in.size, &renderer, (void*) &buf_out);
t1 = clock();
if(ret != 0) {
fprintf(stderr, "Parsing failed.\n");
goto out;
}
/* Write down the document in the HTML format. */
if(fullhtml) {
fprintf(out, "<html>\n");
fprintf(out, "<head>\n");
fprintf(out, "<title></title>\n");
fprintf(out, "<meta name=\"generator\" content=\"md2html\">\n");
fprintf(out, "</head>\n");
fprintf(out, "<body>\n");
}
fwrite(buf_out.data, 1, buf_out.size, out);
if(fullhtml) {
fprintf(out, "</body>\n");
fprintf(out, "</html>\n");
}
if(print_stat) {
if(t0 != (clock_t)-1 && t1 != (clock_t)-1) {
double elapsed = (double)(t1 - t0) / CLOCKS_PER_SEC;
if (elapsed < 1)
fprintf(stderr, "Time spent on parsing: %7.2f ms.\n", elapsed*1e3);
else
fprintf(stderr, "Time spent on parsing: %6.3f s.\n", elapsed);
}
}
/* Success if we have reached here. */
ret = 0;
out:
membuf_fini(&buf_in);
membuf_fini(&buf_out);
return ret;
}
#define OPTION_ARG_NONE 0
#define OPTION_ARG_REQUIRED 1
#define OPTION_ARG_OPTIONAL 2
static const option cmdline_options[] = {
{ "output", 'o', 'o', OPTION_ARG_REQUIRED },
{ "full-html", 'f', 'f', OPTION_ARG_NONE },
{ "stat", 's', 's', OPTION_ARG_NONE },
{ "help", 'h', 'h', OPTION_ARG_NONE },
{ "fpermissive-atx-headers", 0, 'A', OPTION_ARG_NONE },
{ "fno-indented-code", 0, 'I', OPTION_ARG_NONE },
{ "fno-html-blocks", 0, 'H', OPTION_ARG_NONE },
{ 0 }
};
static void
usage(void)
{
printf(
"Usage: md2html [OPTION]... [FILE]\n"
"Convert input FILE (or standard input) in Markdown format to HTML.\n"
"\n"
"General options:\n"
" -o --output=FILE output file (default is standard output)\n"
" -f, --full-html generate full HTML document, including header\n"
" -s, --stat measure time of input parsing\n"
" -h, --help display this help and exit\n"
"\n"
"Markdown dialect options:\n"
" --fpermissive-atx-headers allow ATX headers without delimiting space\n"
" --fno-indented-code disable indented code blocks\n"
" --fno-html-blocks disable raw HTML blocks\n"
);
}
static const char* input_path = NULL;
static const char* output_path = NULL;
static unsigned renderer_flags = 0;
static int want_fullhtml = 0;
static int want_stat = 0;
static int
cmdline_callback(int opt, char const* value, void* data)
{
switch(opt) {
case 0:
if(input_path) {
fprintf(stderr, "Too many arguments. Only one input file can be specified.\n");
fprintf(stderr, "Use --help for more info.\n");
exit(1);
}
input_path = value;
break;
case 'o': output_path = value; break;
case 'f': want_fullhtml = 1; break;
case 's': want_stat = 1; break;
case 'h': usage(); exit(0); break;
case 'A': renderer_flags |= MD_FLAG_PERMISSIVEATXHEADERS; break;
case 'I': renderer_flags |= MD_FLAG_NOINDENTEDCODEBLOCKS; break;
case 'H': renderer_flags |= MD_FLAG_NOHTMLBLOCKS; break;
default:
fprintf(stderr, "Illegal option: %s\n", value);
fprintf(stderr, "Use --help for more info.\n");
exit(1);
break;
}
return 0;
}
int
main(int argc, char** argv)
{
FILE* in = stdin;
FILE* out = stdout;
int ret = 0;
if(readoptions(cmdline_options, argc, argv, cmdline_callback, NULL) < 0) {
usage();
exit(1);
}
if(input_path != NULL && strcmp(input_path, "-") != 0) {
in = fopen(input_path, "rb");
if(in == NULL) {
fprintf(stderr, "Cannot open %s.\n", input_path);
exit(1);
}
}
if(output_path != NULL && strcmp(output_path, "-") != 0) {
out = fopen(output_path, "wt");
if(out == NULL) {
fprintf(stderr, "Cannot open %s.\n", input_path);
exit(1);
}
}
ret = process_file(in, out, renderer_flags, want_fullhtml, want_stat);
if(in != stdin)
fclose(in);
if(out != stdout)
fclose(out);
return ret;
}