Browse files

Import a mass of changes from boobook

1. Add the new method mkd_string(), which assembles a list from a string.
2. Add a tests directory and three test files.
3. Move the smartypants code out into a separate function, so I can
   (eventually) pass a /don't_be_clever/ flag in to the markdown()
   function.
4. Redo the mail address mangler so I can mangle the
   mailto: as well as the address.
5. Fix a bug in the DELETE() macro in cstring.h
6. Fix dependencies in the Makefile so that a reconfigure forces a
   complete recompile.
7. Code tweaks to make gcc stfu
8. Tweak the build dependencies again.
  • Loading branch information...
1 parent c61e67f commit c27ea14dd669ccc984883802dfbe13f10087ff77 david parsons committed Dec 21, 2007
Showing with 1,093 additions and 117 deletions.
  1. +7 −5 Makefile.in
  2. +1 −1 cstring.h
  3. +1 −0 main.c
  4. +119 −102 markdown.c
  5. +0 −2 markdown.h
  6. +39 −6 mkdio.c
  7. +2 −1 mkdio.h
  8. +13 −0 tests/chrome.text
  9. +14 −0 tests/links.text
  10. +897 −0 tests/syntax.text
View
12 Makefile.in
@@ -22,12 +22,15 @@ install: $(PGM)
# @INSTALL_DIR@ $(MANDIR)/man3
# @INSTALL_DATA@ markdown.3 mkdio.3 $(MANDIR)/man3
-version.o: VERSION
+version.o: VERSION config.h
echo 'char version[] = VERSION;' > version.c && \
$(CC) -DVERSION=\"`cat VERSION`\" -c version.c
-$(PGM): main.c version.o $(MKDLIB)
- $(CC) -L. -I. -o $(PGM) main.c version.o -lmarkdown @LIBS@
+$(PGM): main.o version.o $(MKDLIB)
+ $(CC) -L. -o $(PGM) main.o version.o -lmarkdown @LIBS@
+
+main.o: main.c mkdio.h config.h
+ $(CC) -I. -c main.c
$(MKDLIB): $(OBJS)
$(AR) crv $(MKDLIB) $(OBJS)
@@ -41,5 +44,4 @@ distclean spotless: clean
markdown.o: markdown.c config.h cstring.h
-mkdio.o: mkdio.c mkdio.h cstring.h
-$(PGM): mkdio.h config.h
+mkdio.o: mkdio.c mkdio.h cstring.h config.h
View
2 cstring.h
@@ -20,7 +20,7 @@
: !((x).text = realloc((x).text, sizeof T(x)[0] * ((x).alloc += 100)))), \
(x).size++]
-#define DELETE(x) (x).alloc ? (free(T(x)), S(x) x.alloc = 0) \
+#define DELETE(x) (x).alloc ? (free(T(x)), S(x) = (x).alloc = 0) \
: ( S(x) = 0 )
#define CLIP(t,i,sz) \
( ((i) >= 0) && ((sz) > 0) && (((i)+(sz)) <= S(t)) ) ? \
View
1 main.c
@@ -2,6 +2,7 @@
#include <stdlib.h>
#include <mkdio.h>
+float
main(int argc, char **argv)
{
View
221 markdown.c
@@ -1,10 +1,16 @@
/* markdown: a C implementation of John Gruber's Markdown markup language.
+ *
+ * Copyright (C) 2007 David L Parsons.
+ * The redistribution terms are provided in the COPYRIGHT file that must
+ * be distributed with this source code.
*/
#include <stdio.h>
#include <string.h>
#include <stdarg.h>
#include <stdlib.h>
#include <time.h>
+#include <ctype.h>
+
#include "cstring.h"
#include "markdown.h"
@@ -20,8 +26,12 @@ static char *blocktags[] = { "ADDRESS", "BDO", "BLOCKQUOTE", "CENTER",
"H5", "H6", "LISTING", "NOBR", "UL",
"P", "OL", "DL", "PLAINTEXT", "PRE",
"WBR", "XMP" };
-#define SZBLOCKTAGS (sizeof blocktags / sizeof blocktags[0])
+#define SZTAGS (sizeof blocktags / sizeof blocktags[0])
+
+static STRING(Footnote) footnotes;
+
+typedef int (*stfu)(const void*,const void*);
/* case insensitive string sort (for qsort() and bsearch() of block tags)
*/
@@ -47,7 +57,7 @@ footsort(Footnote *a, Footnote *b)
static char *
isblocktag(char *tag)
{
- char **r=bsearch(&tag, blocktags, SZBLOCKTAGS, sizeof blocktags[0], casort);
+ char **r=bsearch(&tag, blocktags, SZTAGS, sizeof blocktags[0], (stfu)casort);
return r ? (*r) : 0;
}
@@ -87,7 +97,7 @@ mkd_firstnonblank(Line *p)
static Cstring output;
static unsigned int csp = 0;
-static int
+static void
push(char *t, int s)
{
int i;
@@ -183,7 +193,6 @@ linkylinky(int image, FILE *out)
skipblankc();
if ( image && (peek(1) == '=') ) {
- char *dim;
int width, height;
pull();
@@ -227,7 +236,8 @@ linkylinky(int image, FILE *out)
}
T(key.tag) = tag;
- ret = bsearch(&key, T(footnotes), S(footnotes), sizeof key, footsort);
+ ret = bsearch(&key, T(footnotes), S(footnotes),
+ sizeof key, (stfu)footsort);
if ( ret ) {
if ( S(ret->link) )
@@ -245,19 +255,26 @@ linkylinky(int image, FILE *out)
}
-static char*
-hexfmt()
+static void
+mangle(unsigned char *s, int len, FILE *out)
{
- return (random()&1) ? "&#x%02x;" : "&#%02d;";
+ while ( len-- > 0 )
+ fprintf(out, (random()&1) ? "&#x%02x;" : "&#%02d;", *s++);
}
+/* a < may be just a regular character, the start of an embedded html
+ * tag, or the start of an <automatic link>. If it's an automatic
+ * link, we also need to know if it's an email address because if it
+ * is we need to mangle it in our futile attempt to cut down on the
+ * spaminess of the rendered page.
+ */
static int
-handle_less_than(FILE *out)
+maybe_tag_or_link(FILE *out)
{
char *text;
int c, size, i;
- int maybetag=1, maybelink=0, maybeaddress=0;
+ int maybetag=1, maybeaddress=0;
for ( size=0; ((c = peek(size+1)) != '>') && !isspace(c); size++ ) {
if ( ! (c == '/' || isalnum(c) || c == '~') )
@@ -285,20 +302,18 @@ handle_less_than(FILE *out)
return 1;
}
if ( maybeaddress ) {
- fprintf(out, "&lt;<a href=\"mailto:");
- for ( i=0; i < size; i++ )
- fprintf(out, hexfmt(), (unsigned char)text[i]);
+ fprintf(out, "&lt;<a href=\"");
+ mangle("mailto:", 7, out);
+ mangle(text, size, out);
fprintf(out,"\">");
- for ( i=0; i < size; i++ )
- fprintf(out,hexfmt(), (unsigned char)text[i]);
+ mangle(text, size, out);
fprintf(out,"</a>");
return 1;
}
- fprintf(out,"&lt;");
shift(-size);
- return 1;
-}
+ return 0;
+} /* maybe_tag_or_link */
static int
@@ -310,18 +325,80 @@ isthisblank(i)
}
+/* Smarty-pants-style chrome for quotes, -, ellipses, and (r)(c)(tm)
+ */
+static int
+smartypants(int c, int *flags, FILE *out)
+{
+ int squo, dquo;
+
+ switch (c) {
+ case '"': dquo = 0x01 & (*flags);
+ if ( isthisblank ( dquo ? 1 : -1 ) ) {
+ fprintf(out, "&%cdquo;", dquo ? 'r' : 'l' );
+ (*flags) ^= 0x01;
+ return 1;
+ }
+ break;
+
+ case '\'': squo = 0x02 & (*flags);
+ if ( isthisblank( squo ? 1 : -1 ) ) {
+ fprintf(out, "&%csquo;", squo ? 'r' : 'l' );
+ (*flags) ^= 0x02;
+ return 1;
+ }
+ break;
+
+ case '.': if ( peek(1) == '.' && peek(2) == '.' ) {
+ fprintf(out,"&hellip;");
+ shift(2);
+ return 1;
+ }
+ break;
+
+ case '-': if ( peek(1) == '-' ) {
+ fprintf(out, "&mdash;");
+ pull();
+ return 1;
+ }
+ else if ( isspace(peek(-1)) && isspace(peek(1)) ) {
+ fprintf(out, "&ndash;");
+ return 1;
+ }
+ break;
+
+ case '(': c = toupper(peek(1));
+ if ( (c == 'C' || c == 'R') && (peek(2) == ')') ) {
+ fprintf(out, "&%s;", (c=='C') ? "copy" : "reg" );
+ shift(2);
+ return 1;
+ }
+ else if ( (c == 'T') && (toupper(peek(2)) == 'M')
+ && (peek(3) == ')') ) {
+ fprintf(out, "&trade;");
+ shift(3);
+ return 1;
+ }
+ break;
+ }
+ return 0;
+} /* smartypants */
+
+
static void code(int, FILE*);
+
static void
text(FILE *out)
{
int c, j;
int em = 0;
int strong = 0;
- int dquo = 0;
- int squo = 0;
+ int smartyflags = 0;
while ( (c = pull()) != EOF ) {
+ if (smartypants(c, &smartyflags, out))
+ continue;
switch (c) {
case 0: break;
@@ -374,6 +451,7 @@ text(FILE *out)
}
else
code(1, out);
+ fprintf(out, "</code>");
break;
case '\\': if ( (c = pull()) == '&' )
@@ -384,8 +462,7 @@ text(FILE *out)
fputc( c ? c : '\\', out);
break;
- case '<': if ( !handle_less_than(out) )
- fprintf(out, "&lt;");
+ case '<': maybe_tag_or_link(out) || fprintf(out, "&lt;");
break;
case '&': j = (peek(1) == '#' ) ? 2 : 1;
@@ -400,86 +477,35 @@ text(FILE *out)
default: fputc(c, out);
break;
-
-/* Smarty-pants-style chrome for quotes, -, ellipses, and (r)(c)(tm)
- */
- case '"': fprintf(out, "&%cdquo;", dquo ? 'r' : 'l' );
- dquo = !dquo;
- break;
-
- case '\'': if ( isthisblank( squo ? 1 : -1 ) ) {
- fprintf(out, "&%csquo;", squo ? 'r' : 'l' );
- squo = !squo;
- }
- else
- fputc(c,out);
- break;
- break;
-
- case '.': if ( peek(1) == '.' && peek(2) == '.' ) {
- fprintf(out,"&hellip;");
- pull();pull();
- }
- else
- fputc(c, out);
- break;
-
- case '-': if ( peek(1) == '-' ) {
- fprintf(out, "&mdash;");
- pull();
- }
- else if ( isspace(peek(-1)) && isspace(peek(1)) )
- fprintf(out, "&ndash;");
- else
- fputc(c, out);
- break;
-
- case '(': if ( (j = toupper(peek(1))) == 'R' || j == 'C' ) {
- if ( peek(2) == ')' ) {
- fprintf(out, "&%s;", (j=='C') ? "copy" : "reg" );
- pull();pull();
- break;
- }
- }
- else if ( j == 'T' && toupper(peek(2)) == 'M'
- && peek(3) == ')' ) {
- fprintf(out, "&trade;");
- pull();pull();pull();
- break;
- }
- fputc(c, out);
- break;
}
}
if ( em ) fputs("</em>", out);
if ( strong ) fputs("</strong>", out);
-}
+} /* text */
+/* the only characters that have special meaning in a code block are
+ * `<' and `&' , which are /always/ expanded to &lt; and &amp;
+ */
static void
code(int escape, FILE *out)
{
- int c, j;
+ int c;
while ( (c = pull()) != EOF ) {
switch (c) {
+ case '&': fprintf(out, "&amp;"); break;
+ case '<': fprintf(out, "&lt;"); break;
case '`': switch (escape) {
case 2: if ( peek(1) == '`' ) {
- pull();
- case 1: fprintf(out, "</code>");
- return;
+ shift(1);
+ case 1: return;
}
}
- fputc(c, out);
- break;
-
- case '&': fprintf(out, "&amp;"); break;
- case '<': fprintf(out, "&lt;"); break;
default: fputc(c, out); break;
}
}
- fprintf(out, "</code>");
-}
+} /* code */
/* setext header; 2 lines, second is ==== or -----
@@ -609,9 +635,9 @@ static Paragraph *display(Paragraph*, FILE*, int);
static void
emit(Paragraph *p, FILE *out)
{
- int multiple = p->next;
+ int multiple = ( p->next != 0 );
- while ( p = display(p, out, multiple) )
+ while (( p = display(p, out, multiple) ))
;
}
@@ -636,13 +662,6 @@ listdisplay(Paragraph *p, FILE* out)
}
-static int
-nextislist(Paragraph *p)
-{
- return p && (p->typ == UL || p->typ == OL);
-}
-
-
/* dump out a Paragraph in the desired manner
*/
static Paragraph*
@@ -982,7 +1001,7 @@ static Line *
listblock(Paragraph *p, int trim)
{
Line *t = p->text;
- Line *first = t, *blank, *last = 0;
+ Line *last = 0;
do {
if ( last ) {
@@ -1112,7 +1131,7 @@ compile(Line *ptr, int toplevel)
char *key;
int list_type, indent;
- while ( ptr = skipempty(ptr) ) {
+ while (( ptr = skipempty(ptr) )) {
if ( toplevel && (key = isopentag(ptr)) ) {
p = Pp(&d, ptr, HTML, 0);
ptr = htmlblock(p, key);
@@ -1125,7 +1144,7 @@ compile(Line *ptr, int toplevel)
p = Pp(&d, 0, HR, 0);
ptr = ptr->next;
}
- else if ( list_type = islist(ptr, &indent) ) {
+ else if (( list_type = islist(ptr, &indent) )) {
p = Pp(&d, ptr, list_type, 0);
ptr = listblock(p, indent);
@@ -1161,8 +1180,6 @@ freeLine(Line *p)
static void
freeParagraph(Paragraph *p)
{
- Line *t;
-
if (p->next) freeParagraph(p->next);
if (p->down) freeParagraph(p->down);
else if (p->text) freeLine(p->text);
@@ -1176,9 +1193,9 @@ freefootnotes()
int i;
for (i=0; i < S(footnotes); i++) {
- free(T(T(footnotes)[i].tag));
- free(T(T(footnotes)[i].link));
- free(T(T(footnotes)[i].title));
+ DELETE(T(footnotes)[i].tag);
+ DELETE(T(footnotes)[i].link);
+ DELETE(T(footnotes)[i].title);
}
S(footnotes) = 0;
}
@@ -1192,7 +1209,7 @@ initmarkdown()
if ( init ) return;
srandom((unsigned int)time(0));
- qsort(blocktags, SZBLOCKTAGS, sizeof blocktags[0], casort);
+ qsort(blocktags, SZTAGS, sizeof blocktags[0], (stfu)casort);
CREATE(footnotes);
CREATE(output);
init = 1;
@@ -1206,7 +1223,7 @@ markdown(Line *text, FILE *out, int flags)
initmarkdown();
paragraph = compile(text, 1);
- qsort(T(footnotes), S(footnotes), sizeof T(footnotes)[0], footsort);
+ qsort(T(footnotes), S(footnotes), sizeof T(footnotes)[0], (stfu)footsort);
emit(paragraph, out);
View
2 markdown.h
@@ -13,8 +13,6 @@ typedef struct footnote {
int height, width; /* dimensions (for image link) */
} Footnote;
-static STRING(Footnote) footnotes;
-
/* each input line is read into a Line, which contains the line,
* the offset of the first non-space character [this assumes
* that all tabs will be expanded to spaces!], and a pointer to
View
45 mkdio.c
@@ -1,3 +1,10 @@
+/*
+ * mkdio -- markdown front end input functions
+ *
+ * Copyright (C) 2007 David L Parsons.
+ * The redistribution terms are provided in the COPYRIGHT file that must
+ * be distributed with this source code.
+ */
#include "config.h"
#include <stdio.h>
#include <stdlib.h>
@@ -73,26 +80,52 @@ mkd_close(LineAnchor *p)
Line *
mkd_in(FILE *input)
{
- int i, c, xp;
- Line *p;
- static Cstring line = { 0, 0 };
+ int c;
+ Cstring line;
LineAnchor *a = mkd_open();
if ( !a ) return 0;
+ CREATE(line);
for (; (c = getc(input)) != EOF; ) {
if (c == '\n') {
- xp = 0;
mkd_write(a, T(line), S(line));
S(line) = 0;
}
else {
EXPAND(line) = c;
- xp++;
}
}
- if ( xp )
+ if ( S(line) )
+ mkd_write(a, T(line), S(line));
+
+ DELETE(line);
+ return mkd_close(a);
+}
+
+
+/* convert a block of text into a linked list
+ */
+Line *
+mkd_string(char *buf, int len)
+{
+ Cstring line;
+ LineAnchor *a = mkd_open();
+
+ if ( !a ) return 0;
+
+ CREATE(line);
+ for ( ; len-- > 0; ++buf ) {
+ if ( *buf == '\n' ) {
+ mkd_write(a, T(line), S(line));
+ S(line) = 0;
+ }
+ else
+ EXPAND(line) = *buf;
+ }
+ if ( S(line) )
mkd_write(a, T(line), S(line));
+ DELETE(line);
return mkd_close(a);
}
View
3 mkdio.h
@@ -7,7 +7,8 @@ void *mkd_open(); /* open a mkdio input assembler */
int mkd_write(void*, char*, int); /* write text into the assembler */
void *mkd_close(void*); /* get the assembled input */
-void *mkd_in(FILE*); /* get assembled input from a file */
+void *mkd_in(FILE*); /* assemble input from a file */
+void *mkd_string(char*,int); /* assemble input from a buffer */
void markdown(void*, FILE*, int); /* mark it on down */
View
13 tests/chrome.text
@@ -0,0 +1,13 @@
+->###chrome with my markdown###<-
+
+1. `(c)` -> `&copy;` (c)
+2. `(r)` -> `&reg;` (r)
+3. `(tm)` -> `&trade;` (tm)
+4. `...` -> `&hellip;` ...
+5. `--` -> `&emdash;` --
+6. `-` -> `&ndash;` - (but not if it's between-words)
+7. "fancy quoting"
+8. 'fancy quoting (#2)'
+9. don't do it unless it's a real quote.
+10. `` (`) ``
+
View
14 tests/links.text
@@ -0,0 +1,14 @@
+ 1. <http://automatic>
+ 2. [automatic] (http://automatic "automatic link")
+ 3. [automatic](http://automatic "automatic link")
+ 4. [automatic](http://automatic)
+ 5. [automatic] (http://automatic)
+ 6. [automatic] []
+ 7. [automatic][]
+ 8. [my][automatic]
+ 9. [my] [automatic]
+
+ [automatic]: http://automatic "footnote"
+
+
+ [automatic] [
View
897 tests/syntax.text
@@ -0,0 +1,897 @@
+Markdown: Syntax
+================
+
+<ul id="ProjectSubmenu">
+ <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li>
+ <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li>
+ <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li>
+ <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li>
+ <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li>
+</ul>
+
+
+* [Overview](#overview)
+ * [Philosophy](#philosophy)
+ * [Inline HTML](#html)
+ * [Automatic Escaping for Special Characters](#autoescape)
+* [Block Elements](#block)
+ * [Paragraphs and Line Breaks](#p)
+ * [Headers](#header)
+ * [Blockquotes](#blockquote)
+ * [Lists](#list)
+ * [Code Blocks](#precode)
+ * [Horizontal Rules](#hr)
+* [Span Elements](#span)
+ * [Links](#link)
+ * [Emphasis](#em)
+ * [Code](#code)
+ * [Images](#img)
+* [Miscellaneous](#misc)
+ * [Backslash Escapes](#backslash)
+ * [Automatic Links](#autolink)
+
+
+**Note:** This document is itself written using Markdown; you
+can [see the source for it by adding '.text' to the URL][src].
+
+ [src]: /projects/markdown/syntax.text
+
+* * *
+
+<h2 id="overview">Overview</h2>
+
+<h3 id="philosophy">Philosophy</h3>
+
+Markdown is intended to be as easy-to-read and easy-to-write as is feasible.
+
+Readability, however, is emphasized above all else. A Markdown-formatted
+document should be publishable as-is, as plain text, without looking
+like it's been marked up with tags or formatting instructions. While
+Markdown's syntax has been influenced by several existing text-to-HTML
+filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4],
+[Grutatext] [5], and [EtText] [6] -- the single biggest source of
+inspiration for Markdown's syntax is the format of plain text email.
+
+ [1]: http://docutils.sourceforge.net/mirror/setext.html
+ [2]: http://www.aaronsw.com/2002/atx/
+ [3]: http://textism.com/tools/textile/
+ [4]: http://docutils.sourceforge.net/rst.html
+ [5]: http://www.triptico.com/software/grutatxt.html
+ [6]: http://ettext.taint.org/doc/
+
+To this end, Markdown's syntax is comprised entirely of punctuation
+characters, which punctuation characters have been carefully chosen so
+as to look like what they mean. E.g., asterisks around a word actually
+look like \*emphasis\*. Markdown lists look like, well, lists. Even
+blockquotes look like quoted passages of text, assuming you've ever
+used email.
+
+
+
+<h3 id="html">Inline HTML</h3>
+
+Markdown's syntax is intended for one purpose: to be used as a
+format for *writing* for the web.
+
+Markdown is not a replacement for HTML, or even close to it. Its
+syntax is very small, corresponding only to a very small subset of
+HTML tags. The idea is *not* to create a syntax that makes it easier
+to insert HTML tags. In my opinion, HTML tags are already easy to
+insert. The idea for Markdown is to make it easy to read, write, and
+edit prose. HTML is a *publishing* format; Markdown is a *writing*
+format. Thus, Markdown's formatting syntax only addresses issues that
+can be conveyed in plain text.
+
+For any markup that is not covered by Markdown's syntax, you simply
+use HTML itself. There's no need to preface it or delimit it to
+indicate that you're switching from Markdown to HTML; you just use
+the tags.
+
+The only restrictions are that block-level HTML elements -- e.g. `<div>`,
+`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding
+content by blank lines, and the start and end tags of the block should
+not be indented with tabs or spaces. Markdown is smart enough not
+to add extra (unwanted) `<p>` tags around HTML block-level tags.
+
+For example, to add an HTML table to a Markdown article:
+
+ This is a regular paragraph.
+
+ <table>
+ <tr>
+ <td>Foo</td>
+ </tr>
+ </table>
+
+ This is another regular paragraph.
+
+Note that Markdown formatting syntax is not processed within block-level
+HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an
+HTML block.
+
+Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be
+used anywhere in a Markdown paragraph, list item, or header. If you
+want, you can even use HTML tags instead of Markdown formatting; e.g. if
+you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's
+link or image syntax, go right ahead.
+
+Unlike block-level HTML tags, Markdown syntax *is* processed within
+span-level tags.
+
+
+<h3 id="autoescape">Automatic Escaping for Special Characters</h3>
+
+In HTML, there are two characters that demand special treatment: `<`
+and `&`. Left angle brackets are used to start tags; ampersands are
+used to denote HTML entities. If you want to use them as literal
+characters, you must escape them as entities, e.g. `&lt;`, and
+`&amp;`.
+
+Ampersands in particular are bedeviling for web writers. If you want to
+write about 'AT&T', you need to write '`AT&amp;T`'. You even need to
+escape ampersands within URLs. Thus, if you want to link to:
+
+ http://images.google.com/images?num=30&q=larry+bird
+
+you need to encode the URL as:
+
+ http://images.google.com/images?num=30&amp;q=larry+bird
+
+in your anchor tag `href` attribute. Needless to say, this is easy to
+forget, and is probably the single most common source of HTML validation
+errors in otherwise well-marked-up web sites.
+
+Markdown allows you to use these characters naturally, taking care of
+all the necessary escaping for you. If you use an ampersand as part of
+an HTML entity, it remains unchanged; otherwise it will be translated
+into `&amp;`.
+
+So, if you want to include a copyright symbol in your article, you can write:
+
+ &copy;
+
+and Markdown will leave it alone. But if you write:
+
+ AT&T
+
+Markdown will translate it to:
+
+ AT&amp;T
+
+Similarly, because Markdown supports [inline HTML](#html), if you use
+angle brackets as delimiters for HTML tags, Markdown will treat them as
+such. But if you write:
+
+ 4 < 5
+
+Markdown will translate it to:
+
+ 4 &lt; 5
+
+However, inside Markdown code spans and blocks, angle brackets and
+ampersands are *always* encoded automatically. This makes it easy to use
+Markdown to write about HTML code. (As opposed to raw HTML, which is a
+terrible format for writing about HTML syntax, because every single `<`
+and `&` in your example code needs to be escaped.)
+
+
+* * *
+
+
+<h2 id="block">Block Elements</h2>
+
+
+<h3 id="p">Paragraphs and Line Breaks</h3>
+
+A paragraph is simply one or more consecutive lines of text, separated
+by one or more blank lines. (A blank line is any line that looks like a
+blank line -- a line containing nothing but spaces or tabs is considered
+blank.) Normal paragraphs should not be indented with spaces or tabs.
+
+The implication of the "one or more consecutive lines of text" rule is
+that Markdown supports "hard-wrapped" text paragraphs. This differs
+significantly from most other text-to-HTML formatters (including Movable
+Type's "Convert Line Breaks" option) which translate every line break
+character in a paragraph into a `<br />` tag.
+
+When you *do* want to insert a `<br />` break tag using Markdown, you
+end a line with two or more spaces, then type return.
+
+Yes, this takes a tad more effort to create a `<br />`, but a simplistic
+"every line break is a `<br />`" rule wouldn't work for Markdown.
+Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l]
+work best -- and look better -- when you format them with hard breaks.
+
+ [bq]: #blockquote
+ [l]: #list
+
+
+
+<h3 id="header">Headers</h3>
+
+Markdown supports two styles of headers, [Setext] [1] and [atx] [2].
+
+Setext-style headers are "underlined" using equal signs (for first-level
+headers) and dashes (for second-level headers). For example:
+
+ This is an H1
+ =============
+
+ This is an H2
+ -------------
+
+Any number of underlining `=`'s or `-`'s will work.
+
+Atx-style headers use 1-6 hash characters at the start of the line,
+corresponding to header levels 1-6. For example:
+
+ # This is an H1
+
+ ## This is an H2
+
+ ###### This is an H6
+
+Optionally, you may "close" atx-style headers. This is purely
+cosmetic -- you can use this if you think it looks better. The
+closing hashes don't even need to match the number of hashes
+used to open the header. (The number of opening hashes
+determines the header level.) :
+
+ # This is an H1 #
+
+ ## This is an H2 ##
+
+ ### This is an H3 ######
+
+
+<h3 id="blockquote">Blockquotes</h3>
+
+Markdown uses email-style `>` characters for blockquoting. If you're
+familiar with quoting passages of text in an email message, then you
+know how to create a blockquote in Markdown. It looks best if you hard
+wrap the text and put a `>` before every line:
+
+ > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
+ > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
+ > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
+ >
+ > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
+ > id sem consectetuer libero luctus adipiscing.
+
+Markdown allows you to be lazy and only put the `>` before the first
+line of a hard-wrapped paragraph:
+
+ > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
+ consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
+ Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
+
+ > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
+ id sem consectetuer libero luctus adipiscing.
+
+Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by
+adding additional levels of `>`:
+
+ > This is the first level of quoting.
+ >
+ > > This is nested blockquote.
+ >
+ > Back to the first level.
+
+Blockquotes can contain other Markdown elements, including headers, lists,
+and code blocks:
+
+ > ## This is a header.
+ >
+ > 1. This is the first list item.
+ > 2. This is the second list item.
+ >
+ > Here's some example code:
+ >
+ > return shell_exec("echo $input | $markdown_script");
+
+Any decent text editor should make email-style quoting easy. For
+example, with BBEdit, you can make a selection and choose Increase
+Quote Level from the Text menu.
+
+
+<h3 id="list">Lists</h3>
+
+Markdown supports ordered (numbered) and unordered (bulleted) lists.
+
+Unordered lists use asterisks, pluses, and hyphens -- interchangably
+-- as list markers:
+
+ * Red
+ * Green
+ * Blue
+
+is equivalent to:
+
+ + Red
+ + Green
+ + Blue
+
+and:
+
+ - Red
+ - Green
+ - Blue
+
+Ordered lists use numbers followed by periods:
+
+ 1. Bird
+ 2. McHale
+ 3. Parish
+
+It's important to note that the actual numbers you use to mark the
+list have no effect on the HTML output Markdown produces. The HTML
+Markdown produces from the above list is:
+
+ <ol>
+ <li>Bird</li>
+ <li>McHale</li>
+ <li>Parish</li>
+ </ol>
+
+If you instead wrote the list in Markdown like this:
+
+ 1. Bird
+ 1. McHale
+ 1. Parish
+
+or even:
+
+ 3. Bird
+ 1. McHale
+ 8. Parish
+
+you'd get the exact same HTML output. The point is, if you want to,
+you can use ordinal numbers in your ordered Markdown lists, so that
+the numbers in your source match the numbers in your published HTML.
+But if you want to be lazy, you don't have to.
+
+If you do use lazy list numbering, however, you should still start the
+list with the number 1. At some point in the future, Markdown may support
+starting ordered lists at an arbitrary number.
+
+List markers typically start at the left margin, but may be indented by
+up to three spaces. List markers must be followed by one or more spaces
+or a tab.
+
+To make lists look nice, you can wrap items with hanging indents:
+
+ * Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
+ Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
+ viverra nec, fringilla in, laoreet vitae, risus.
+ * Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
+ Suspendisse id sem consectetuer libero luctus adipiscing.
+
+But if you want to be lazy, you don't have to:
+
+ * Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
+ Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
+ viverra nec, fringilla in, laoreet vitae, risus.
+ * Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
+ Suspendisse id sem consectetuer libero luctus adipiscing.
+
+If list items are separated by blank lines, Markdown will wrap the
+items in `<p>` tags in the HTML output. For example, this input:
+
+ * Bird
+ * Magic
+
+will turn into:
+
+ <ul>
+ <li>Bird</li>
+ <li>Magic</li>
+ </ul>
+
+But this:
+
+ * Bird
+
+ * Magic
+
+will turn into:
+
+ <ul>
+ <li><p>Bird</p></li>
+ <li><p>Magic</p></li>
+ </ul>
+
+List items may consist of multiple paragraphs. Each subsequent
+paragraph in a list item must be intended by either 4 spaces
+or one tab:
+
+ 1. This is a list item with two paragraphs. Lorem ipsum dolor
+ sit amet, consectetuer adipiscing elit. Aliquam hendrerit
+ mi posuere lectus.
+
+ Vestibulum enim wisi, viverra nec, fringilla in, laoreet
+ vitae, risus. Donec sit amet nisl. Aliquam semper ipsum
+ sit amet velit.
+
+ 2. Suspendisse id sem consectetuer libero luctus adipiscing.
+
+It looks nice if you indent every line of the subsequent
+paragraphs, but here again, Markdown will allow you to be
+lazy:
+
+ * This is a list item with two paragraphs.
+
+ This is the second paragraph in the list item. You're
+ only required to indent the first line. Lorem ipsum dolor
+ sit amet, consectetuer adipiscing elit.
+
+ * Another item in the same list.
+
+To put a blockquote within a list item, the blockquote's `>`
+delimiters need to be indented:
+
+ * A list item with a blockquote:
+
+ > This is a blockquote
+ > inside a list item.
+
+To put a code block within a list item, the code block needs
+to be indented *twice* -- 8 spaces or two tabs:
+
+ * A list item with a code block:
+
+ <code goes here>
+
+
+It's worth noting that it's possible to trigger an ordered list by
+accident, by writing something like this:
+
+ 1986. What a great season.
+
+In other words, a *number-period-space* sequence at the beginning of a
+line. To avoid this, you can backslash-escape the period:
+
+ 1986\. What a great season.
+
+
+
+<h3 id="precode">Code Blocks</h3>
+
+Pre-formatted code blocks are used for writing about programming or
+markup source code. Rather than forming normal paragraphs, the lines
+of a code block are interpreted literally. Markdown wraps a code block
+in both `<pre>` and `<code>` tags.
+
+To produce a code block in Markdown, simply indent every line of the
+block by at least 4 spaces or 1 tab. For example, given this input:
+
+ This is a normal paragraph:
+
+ This is a code block.
+
+Markdown will generate:
+
+ <p>This is a normal paragraph:</p>
+
+ <pre><code>This is a code block.
+ </code></pre>
+
+One level of indentation -- 4 spaces or 1 tab -- is removed from each
+line of the code block. For example, this:
+
+ Here is an example of AppleScript:
+
+ tell application "Foo"
+ beep
+ end tell
+
+will turn into:
+
+ <p>Here is an example of AppleScript:</p>
+
+ <pre><code>tell application "Foo"
+ beep
+ end tell
+ </code></pre>
+
+A code block continues until it reaches a line that is not indented
+(or the end of the article).
+
+Within a code block, ampersands (`&`) and angle brackets (`<` and `>`)
+are automatically converted into HTML entities. This makes it very
+easy to include example HTML source code using Markdown -- just paste
+it and indent it, and Markdown will handle the hassle of encoding the
+ampersands and angle brackets. For example, this:
+
+ <div class="footer">
+ &copy; 2004 Foo Corporation
+ </div>
+
+will turn into:
+
+ <pre><code>&lt;div class="footer"&gt;
+ &amp;copy; 2004 Foo Corporation
+ &lt;/div&gt;
+ </code></pre>
+
+Regular Markdown syntax is not processed within code blocks. E.g.,
+asterisks are just literal asterisks within a code block. This means
+it's also easy to use Markdown to write about Markdown's own syntax.
+
+
+
+<h3 id="hr">Horizontal Rules</h3>
+
+You can produce a horizontal rule tag (`<hr />`) by placing three or
+more hyphens, asterisks, or underscores on a line by themselves. If you
+wish, you may use spaces between the hyphens or asterisks. Each of the
+following lines will produce a horizontal rule:
+
+ * * *
+
+ ***
+
+ *****
+
+ - - -
+
+ ---------------------------------------
+
+
+* * *
+
+<h2 id="span">Span Elements</h2>
+
+<h3 id="link">Links</h3>
+
+Markdown supports two style of links: *inline* and *reference*.
+
+In both styles, the link text is delimited by [square brackets].
+
+To create an inline link, use a set of regular parentheses immediately
+after the link text's closing square bracket. Inside the parentheses,
+put the URL where you want the link to point, along with an *optional*
+title for the link, surrounded in quotes. For example:
+
+ This is [an example](http://example.com/ "Title") inline link.
+
+ [This link](http://example.net/) has no title attribute.
+
+Will produce:
+
+ <p>This is <a href="http://example.com/" title="Title">
+ an example</a> inline link.</p>
+
+ <p><a href="http://example.net/">This link</a> has no
+ title attribute.</p>
+
+If you're referring to a local resource on the same server, you can
+use relative paths:
+
+ See my [About](/about/) page for details.
+
+Reference-style links use a second set of square brackets, inside
+which you place a label of your choosing to identify the link:
+
+ This is [an example][id] reference-style link.
+
+You can optionally use a space to separate the sets of brackets:
+
+ This is [an example] [id] reference-style link.
+
+Then, anywhere in the document, you define your link label like this,
+on a line by itself:
+
+ [id]: http://example.com/ "Optional Title Here"
+
+That is:
+
+* Square brackets containing the link identifier (optionally
+ indented from the left margin using up to three spaces);
+* followed by a colon;
+* followed by one or more spaces (or tabs);
+* followed by the URL for the link;
+* optionally followed by a title attribute for the link, enclosed
+ in double or single quotes, or enclosed in parentheses.
+
+The following three link definitions are equivalent:
+
+ [foo]: http://example.com/ "Optional Title Here"
+ [foo]: http://example.com/ 'Optional Title Here'
+ [foo]: http://example.com/ (Optional Title Here)
+
+**Note:** There is a known bug in Markdown.pl 1.0.1 which prevents
+single quotes from being used to delimit link titles.
+
+The link URL may, optionally, be surrounded by angle brackets:
+
+ [id]: <http://example.com/> "Optional Title Here"
+
+You can put the title attribute on the next line and use extra spaces
+or tabs for padding, which tends to look better with longer URLs:
+
+ [id]: http://example.com/longish/path/to/resource/here
+ "Optional Title Here"
+
+Link definitions are only used for creating links during Markdown
+processing, and are stripped from your document in the HTML output.
+
+Link definition names may constist of letters, numbers, spaces, and
+punctuation -- but they are *not* case sensitive. E.g. these two
+links:
+
+ [link text][a]
+ [link text][A]
+
+are equivalent.
+
+The *implicit link name* shortcut allows you to omit the name of the
+link, in which case the link text itself is used as the name.
+Just use an empty set of square brackets -- e.g., to link the word
+"Google" to the google.com web site, you could simply write:
+
+ [Google][]
+
+And then define the link:
+
+ [Google]: http://google.com/
+
+Because link names may contain spaces, this shortcut even works for
+multiple words in the link text:
+
+ Visit [Daring Fireball][] for more information.
+
+And then define the link:
+
+ [Daring Fireball]: http://daringfireball.net/
+
+Link definitions can be placed anywhere in your Markdown document. I
+tend to put them immediately after each paragraph in which they're
+used, but if you want, you can put them all at the end of your
+document, sort of like footnotes.
+
+Here's an example of reference links in action:
+
+ I get 10 times more traffic from [Google] [1] than from
+ [Yahoo] [2] or [MSN] [3].
+
+ [1]: http://google.com/ "Google"
+ [2]: http://search.yahoo.com/ "Yahoo Search"
+ [3]: http://search.msn.com/ "MSN Search"
+
+Using the implicit link name shortcut, you could instead write:
+
+ I get 10 times more traffic from [Google][] than from
+ [Yahoo][] or [MSN][].
+
+ [google]: http://google.com/ "Google"
+ [yahoo]: http://search.yahoo.com/ "Yahoo Search"
+ [msn]: http://search.msn.com/ "MSN Search"
+
+Both of the above examples will produce the following HTML output:
+
+ <p>I get 10 times more traffic from <a href="http://google.com/"
+ title="Google">Google</a> than from
+ <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a>
+ or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p>
+
+For comparison, here is the same paragraph written using
+Markdown's inline link style:
+
+ I get 10 times more traffic from [Google](http://google.com/ "Google")
+ than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or
+ [MSN](http://search.msn.com/ "MSN Search").
+
+The point of reference-style links is not that they're easier to
+write. The point is that with reference-style links, your document
+source is vastly more readable. Compare the above examples: using
+reference-style links, the paragraph itself is only 81 characters
+long; with inline-style links, it's 176 characters; and as raw HTML,
+it's 234 characters. In the raw HTML, there's more markup than there
+is text.
+
+With Markdown's reference-style links, a source document much more
+closely resembles the final output, as rendered in a browser. By
+allowing you to move the markup-related metadata out of the paragraph,
+you can add links without interrupting the narrative flow of your
+prose.
+
+
+<h3 id="em">Emphasis</h3>
+
+Markdown treats asterisks (`*`) and underscores (`_`) as indicators of
+emphasis. Text wrapped with one `*` or `_` will be wrapped with an
+HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML
+`<strong>` tag. E.g., this input:
+
+ *single asterisks*
+
+ _single underscores_
+
+ **double asterisks**
+
+ __double underscores__
+
+will produce:
+
+ <em>single asterisks</em>
+
+ <em>single underscores</em>
+
+ <strong>double asterisks</strong>
+
+ <strong>double underscores</strong>
+
+You can use whichever style you prefer; the lone restriction is that
+the same character must be used to open and close an emphasis span.
+
+Emphasis can be used in the middle of a word:
+
+ un*fucking*believable
+
+But if you surround an `*` or `_` with spaces, it'll be treated as a
+literal asterisk or underscore.
+
+To produce a literal asterisk or underscore at a position where it
+would otherwise be used as an emphasis delimiter, you can backslash
+escape it:
+
+ \*this text is surrounded by literal asterisks\*
+
+
+
+<h3 id="code">Code</h3>
+
+To indicate a span of code, wrap it with backtick quotes (`` ` ``).
+Unlike a pre-formatted code block, a code span indicates code within a
+normal paragraph. For example:
+
+ Use the `printf()` function.
+
+will produce:
+
+ <p>Use the <code>printf()</code> function.</p>
+
+To include a literal backtick character within a code span, you can use
+multiple backticks as the opening and closing delimiters:
+
+ ``There is a literal backtick (`) here.``
+
+which will produce this:
+
+ <p><code>There is a literal backtick (`) here.</code></p>
+
+The backtick delimiters surrounding a code span may include spaces --
+one after the opening, one before the closing. This allows you to place
+literal backtick characters at the beginning or end of a code span:
+
+ A single backtick in a code span: `` ` ``
+
+ A backtick-delimited string in a code span: `` `foo` ``
+
+will produce:
+
+ <p>A single backtick in a code span: <code>`</code></p>
+
+ <p>A backtick-delimited string in a code span: <code>`foo`</code></p>
+
+With a code span, ampersands and angle brackets are encoded as HTML
+entities automatically, which makes it easy to include example HTML
+tags. Markdown will turn this:
+
+ Please don't use any `<blink>` tags.
+
+into:
+
+ <p>Please don't use any <code>&lt;blink&gt;</code> tags.</p>
+
+You can write this:
+
+ `&#8212;` is the decimal-encoded equivalent of `&mdash;`.
+
+to produce:
+
+ <p><code>&amp;#8212;</code> is the decimal-encoded
+ equivalent of <code>&amp;mdash;</code>.</p>
+
+
+
+<h3 id="img">Images</h3>
+
+Admittedly, it's fairly difficult to devise a "natural" syntax for
+placing images into a plain text document format.
+
+Markdown uses an image syntax that is intended to resemble the syntax
+for links, allowing for two styles: *inline* and *reference*.
+
+Inline image syntax looks like this:
+
+ ![Alt text](/path/to/img.jpg)
+
+ ![Alt text](/path/to/img.jpg "Optional title")
+
+That is:
+
+* An exclamation mark: `!`;
+* followed by a set of square brackets, containing the `alt`
+ attribute text for the image;
+* followed by a set of parentheses, containing the URL or path to
+ the image, and an optional `title` attribute enclosed in double
+ or single quotes.
+
+Reference-style image syntax looks like this:
+
+ ![Alt text][id]
+
+Where "id" is the name of a defined image reference. Image references
+are defined using syntax identical to link references:
+
+ [id]: url/to/image "Optional title attribute"
+
+As of this writing, Markdown has no syntax for specifying the
+dimensions of an image; if this is important to you, you can simply
+use regular HTML `<img>` tags.
+
+
+* * *
+
+
+<h2 id="misc">Miscellaneous</h2>
+
+<h3 id="autolink">Automatic Links</h3>
+
+Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:
+
+ <http://example.com/>
+
+Markdown will turn this into:
+
+ <a href="http://example.com/">http://example.com/</a>
+
+Automatic links for email addresses work similarly, except that
+Markdown will also perform a bit of randomized decimal and hex
+entity-encoding to help obscure your address from address-harvesting
+spambots. For example, Markdown will turn this:
+
+ <address@example.com>
+
+into something like this:
+
+ <a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65;
+ &#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;
+ &#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61;
+ &#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a>
+
+which will render in a browser as a clickable link to "address@example.com".
+
+(This sort of entity-encoding trick will indeed fool many, if not
+most, address-harvesting bots, but it definitely won't fool all of
+them. It's better than nothing, but an address published in this way
+will probably eventually start receiving spam.)
+
+
+
+<h3 id="backslash">Backslash Escapes</h3>
+
+Markdown allows you to use backslash escapes to generate literal
+characters which would otherwise have special meaning in Markdown's
+formatting syntax. For example, if you wanted to surround a word with
+literal asterisks (instead of an HTML `<em>` tag), you can backslashes
+before the asterisks, like this:
+
+ \*literal asterisks\*
+
+Markdown provides backslash escapes for the following characters:
+
+ \ backslash
+ ` backtick
+ * asterisk
+ _ underscore
+ {} curly braces
+ [] square brackets
+ () parentheses
+ # hash mark
+ + plus sign
+ - minus sign (hyphen)
+ . dot
+ ! exclamation mark
+

0 comments on commit c27ea14

Please sign in to comment.