123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417 |
- /*
- * 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_toc = 0;
- static int want_stat = 0;
- MD_TOC_OPTIONS toc_options = { 0, NULL};
- /*********************************
- *** 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, &toc_options);
- 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 },
- { 't', "table-of-content", 't', CMDLINE_OPTFLAG_OPTIONALARG },
- { 0, "toc", 't', CMDLINE_OPTFLAG_OPTIONALARG },
- { 0, "toc-depth", 'd', CMDLINE_OPTFLAG_REQUIREDARG },
- { '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, "fheading-auto-id", '#', 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"
- " -t, --table-of-content=MARK, --toc=MARK\n"
- " Generate a table of content in place of MARK line\n"
- " If no MARK is given, the toc is generated at start\n"
- " --toc-depth=D Set the maximum level of heading in the table\n"
- " of content. 1 to 6. Default is 3\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"
- " --fheading-auto-id\n"
- " Enable heading auto identifier\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 parse_toc_depth(char const* value){
- toc_options.depth = -1;
- toc_options.depth = *value - '0';
- return (toc_options.depth>0 && toc_options.depth <= 6);
- }
- 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 't':
- want_toc = 1;
- parser_flags |= MD_FLAG_HEADINGAUTOID;
- toc_options.toc_placeholder = value;
- if(toc_options.depth == 0)
- toc_options.depth = 3;
- break;
- case 'd':
- if(!parse_toc_depth(value)){
- fprintf(stderr, "Invalid toc-depth: %s\n", value);
- fprintf(stderr, "Must be a number in the range 1-6\n");
- exit(1);
- }
- 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;
- case '#': parser_flags |= MD_FLAG_HEADINGAUTOID; 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;
- }
|