summaryrefslogtreecommitdiffstats
path: root/tdemarkdown/md4c/md2html/md2html.c
blob: 06b2b74b1c5aeb87fa109e04984b7a52c3cf7c44 (plain)
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
/*
 * MD4C: Markdown parser for C
 * (http://github.com/mity/md4c)
 *
 * Copyright (c) 2016-2020 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 <stdlib.h>
#include <string.h>
#include <time.h>

#include "md4c-html.h"
#include "cmdline.h"



/* Global options. */
static unsigned parser_flags = 0;
#ifndef MD4C_USE_ASCII
    static unsigned renderer_flags = MD_HTML_FLAG_DEBUG | MD_HTML_FLAG_SKIP_UTF8_BOM;
#else
    static unsigned renderer_flags = MD_HTML_FLAG_DEBUG;
#endif
static int want_fullhtml = 0;
static int want_xhtml = 0;
static int want_stat = 0;


/*********************************
 ***  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;
    size_t asize;
    size_t 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.\n");
        exit(1);
    }
}

static void
membuf_fini(struct membuffer* buf)
{
    if(buf->data)
        free(buf->data);
}

static void
membuf_grow(struct membuffer* buf, size_t new_asize)
{
    buf->data = realloc(buf->data, new_asize);
    if(buf->data == NULL) {
        fprintf(stderr, "membuf_grow: realloc() failed.\n");
        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 + buf->size / 2 + size);
    memcpy(buf->data + buf->size, data, size);
    buf->size += size;
}


/**********************
 ***  Main program  ***
 **********************/

static void
process_output(const MD_CHAR* text, MD_SIZE size, void* userdata)
{
    membuf_append((struct membuffer*) userdata, text, size);
}

static int
process_file(FILE* in, FILE* out)
{
    size_t 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, buf_in.asize + buf_in.asize / 2);

        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, (MD_SIZE)(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_html(buf_in.data, (MD_SIZE)buf_in.size, process_output, (void*) &buf_out,
                    parser_flags, renderer_flags);

    t1 = clock();
    if(ret != 0) {
        fprintf(stderr, "Parsing failed.\n");
        goto out;
    }

    /* Write down the document in the HTML format. */
    if(want_fullhtml) {
        if(want_xhtml) {
            fprintf(out, "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n");
            fprintf(out, "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\" "
                            "\"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n");
            fprintf(out, "<html xmlns=\"http://www.w3.org/1999/xhtml\">\n");
        } else {
            fprintf(out, "<!DOCTYPE html>\n");
            fprintf(out, "<html>\n");
        }
        fprintf(out, "<head>\n");
        fprintf(out, "<title></title>\n");
        fprintf(out, "<meta name=\"generator\" content=\"md2html\"%s>\n", want_xhtml ? " /" : "");
        fprintf(out, "</head>\n");
        fprintf(out, "<body>\n");
    }

    fwrite(buf_out.data, 1, buf_out.size, out);

    if(want_fullhtml) {
        fprintf(out, "</body>\n");
        fprintf(out, "</html>\n");
    }

    if(want_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;
}


static const CMDLINE_OPTION cmdline_options[] = {
    { 'o', "output",                        'o', CMDLINE_OPTFLAG_REQUIREDARG },
    { 'f', "full-html",                     'f', 0 },
    { 'x', "xhtml",                         'x', 0 },
    { 's', "stat",                          's', 0 },
    { 'h', "help",                          'h', 0 },
    { 'v', "version",                       'v', 0 },

    {  0,  "commonmark",                    'c', 0 },
    {  0,  "github",                        'g', 0 },

    {  0,  "fcollapse-whitespace",          'W', 0 },
    {  0,  "flatex-math",                   'L', 0 },
    {  0,  "fpermissive-atx-headers",       'A', 0 },
    {  0,  "fpermissive-autolinks",         'V', 0 },
    {  0,  "fpermissive-email-autolinks",   '@', 0 },
    {  0,  "fpermissive-url-autolinks",     'U', 0 },
    {  0,  "fpermissive-www-autolinks",     '.', 0 },
    {  0,  "fstrikethrough",                'S', 0 },
    {  0,  "ftables",                       'T', 0 },
    {  0,  "ftasklists",                    'X', 0 },
    {  0,  "funderline",                    '_', 0 },
    {  0,  "fverbatim-entities",            'E', 0 },
    {  0,  "fwiki-links",                   'K', 0 },

    {  0,  "fno-html-blocks",               'F', 0 },
    {  0,  "fno-html-spans",                'G', 0 },
    {  0,  "fno-html",                      'H', 0 },
    {  0,  "fno-indented-code",             'I', 0 },

    {  0,  NULL,                             0,  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"
        "  -x, --xhtml          Generate XHTML instead of HTML\n"
        "  -s, --stat           Measure time of input parsing\n"
        "  -h, --help           Display this help and exit\n"
        "  -v, --version        Display version and exit\n"
        "\n"
        "Markdown dialect options:\n"
        "(note these are equivalent to some combinations of the flags below)\n"
        "      --commonmark     CommonMark (this is default)\n"
        "      --github         Github Flavored Markdown\n"
        "\n"
        "Markdown extension options:\n"
        "      --fcollapse-whitespace\n"
        "                       Collapse non-trivial whitespace\n"
        "      --flatex-math    Enable LaTeX style mathematics spans\n"
        "      --fpermissive-atx-headers\n"
        "                       Allow ATX headers without delimiting space\n"
        "      --fpermissive-url-autolinks\n"
        "                       Allow URL autolinks without '<', '>'\n"
        "      --fpermissive-www-autolinks\n"
        "                       Allow WWW autolinks without any scheme (e.g. 'www.example.com')\n"
        "      --fpermissive-email-autolinks  \n"
        "                       Allow e-mail autolinks without '<', '>' and 'mailto:'\n"
        "      --fpermissive-autolinks\n"
        "                       Same as --fpermissive-url-autolinks --fpermissive-www-autolinks\n"
        "                       --fpermissive-email-autolinks\n"
        "      --fstrikethrough Enable strike-through spans\n"
        "      --ftables        Enable tables\n"
        "      --ftasklists     Enable task lists\n"
        "      --funderline     Enable underline spans\n"
        "      --fwiki-links    Enable wiki links\n"
        "\n"
        "Markdown suppression options:\n"
        "      --fno-html-blocks\n"
        "                       Disable raw HTML blocks\n"
        "      --fno-html-spans\n"
        "                       Disable raw HTML spans\n"
        "      --fno-html       Same as --fno-html-blocks --fno-html-spans\n"
        "      --fno-indented-code\n"
        "                       Disable indented code blocks\n"
        "\n"
        "HTML generator options:\n"
        "      --fverbatim-entities\n"
        "                       Do not translate entities\n"
        "\n"
    );
}

static void
version(void)
{
    printf("%d.%d.%d\n", MD_VERSION_MAJOR, MD_VERSION_MINOR, MD_VERSION_RELEASE);
}

static const char* input_path = NULL;
static const char* output_path = NULL;

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 'x':   want_xhtml = 1; renderer_flags |= MD_HTML_FLAG_XHTML; break;
        case 's':   want_stat = 1; break;
        case 'h':   usage(); exit(0); break;
        case 'v':   version(); exit(0); break;

        case 'c':   parser_flags |= MD_DIALECT_COMMONMARK; break;
        case 'g':   parser_flags |= MD_DIALECT_GITHUB; break;

        case 'E':   renderer_flags |= MD_HTML_FLAG_VERBATIM_ENTITIES; break;
        case 'A':   parser_flags |= MD_FLAG_PERMISSIVEATXHEADERS; break;
        case 'I':   parser_flags |= MD_FLAG_NOINDENTEDCODEBLOCKS; break;
        case 'F':   parser_flags |= MD_FLAG_NOHTMLBLOCKS; break;
        case 'G':   parser_flags |= MD_FLAG_NOHTMLSPANS; break;
        case 'H':   parser_flags |= MD_FLAG_NOHTML; break;
        case 'W':   parser_flags |= MD_FLAG_COLLAPSEWHITESPACE; break;
        case 'U':   parser_flags |= MD_FLAG_PERMISSIVEURLAUTOLINKS; break;
        case '.':   parser_flags |= MD_FLAG_PERMISSIVEWWWAUTOLINKS; break;
        case '@':   parser_flags |= MD_FLAG_PERMISSIVEEMAILAUTOLINKS; break;
        case 'V':   parser_flags |= MD_FLAG_PERMISSIVEAUTOLINKS; break;
        case 'T':   parser_flags |= MD_FLAG_TABLES; break;
        case 'S':   parser_flags |= MD_FLAG_STRIKETHROUGH; break;
        case 'L':   parser_flags |= MD_FLAG_LATEXMATHSPANS; break;
        case 'K':   parser_flags |= MD_FLAG_WIKILINKS; break;
        case 'X':   parser_flags |= MD_FLAG_TASKLISTS; break;
        case '_':   parser_flags |= MD_FLAG_UNDERLINE; 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(cmdline_read(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", output_path);
            exit(1);
        }
    }

    ret = process_file(in, out);
    if(in != stdin)
        fclose(in);
    if(out != stdout)
        fclose(out);

    return ret;
}