commit 3ca74bd94fd1d1034dd02d6076b117d48cefa157 (patch)
parent daf51240a0e3d3328842a7314eb375b29d0ae8a8
Author: Alex Karle <alex@alexkarle.com>
Date: Tue, 28 Dec 2021 00:17:43 -0500
Change link syntax to [desc](url) style
This is one of those things that I think is just much better looking
from the plaintext-source perspective. It's a shame that it's a bit more
complex / inefficient (repeatedly strcat-ing instead of printing/saving
the characters as they come), but IMHO, it's cleaner:
read about [my link](https://alexkarle.com) mid-sentence
vs
read about [https://alexkarle.com my link] mid-sentence
Time to go update my whole site with this syntax. Regex to the rescue!
Diffstat:
6 files changed, 108 insertions(+), 31 deletions(-)
diff --git a/README b/README
@@ -40,7 +40,7 @@ is enforced via pledge(2)). Common usage is:
- TAB code blocks
- Inline `code`, _italics_, and *bold*
- Escaping via \\
-- Links: [https://alexkarle.com my site] or [https://alexkarle.com]
+- Links: [my site](https://alexkarle.com) or [https://alexkarle.com]
## TODO
diff --git a/nihdoc.1 b/nihdoc.1
@@ -29,7 +29,7 @@ Inline *bold*, _italics_, `code` (bold/italics disabled in code)
.It
backslash to escape
.It
-[alexkarle.com] bare links and [alexkarle.com description]
+[alexkarle.com] bare links and [description](alexkarle.com)
.It
# headers (each # adds a level)
.It
diff --git a/nihdoc.c b/nihdoc.c
@@ -7,6 +7,7 @@
#include <stdio.h>
#include <unistd.h>
#include <stdbool.h>
+#include <string.h>
/* Global Constants and Enums */
@@ -30,6 +31,7 @@ enum Link {
NOL,
URL_PARSE,
DESC_PARSE,
+ OPT_URL,
};
@@ -40,8 +42,7 @@ enum Link in_link = NOL;
int hlvl = 0;
bool fmts[256] = {false}; /* indexed by _ * ` */
bool escape = false;
-char lnkbuf[2048] = {0};
-int lnkidx = 0;
+char lnkdes[2048] = {0};
int indent = 0;
int previndent = 0;
int listdepth = 0;
@@ -93,10 +94,10 @@ void handle_lf() {
printf("</h%d>\n", hlvl);
}
- /* terminate url parsing in links */
- if (in_link == URL_PARSE) {
- in_link = DESC_PARSE;
- printf("\">");
+ /* Check for [url] style links */
+ if (in_link == OPT_URL) {
+ in_link = NOL;
+ printf("<a href=\"%s\">%s</a>", lnkdes, lnkdes);
}
/* multi-line types (two lf to close) */
@@ -139,10 +140,34 @@ void toggle_format() {
}
}
+void pushbuf() {
+ /* push description onto lnkdes, with formatting! */
+ char buf[12] = {0};
+ if (escape) {
+ buf[0] = c;
+ escape = false;
+ } else if (c == '`' || c == '_' || c == '*') {
+ snprintf(buf, 12, "<%s%s>", fmts[c] ? "/" : "", FMT_STRS[c]);
+ fmts[c] ^= true;
+ } else if (c == '\\') {
+ escape = true;
+ } else {
+ buf[0] = c;
+ }
+ strcat(lnkdes, buf);
+}
+
int parse() {
/* Mini state machine (home grown spaghetti code) */
while ((c = getchar()) != EOF) {
- /* Handle Escapes before all else */
+ /* Store links as we go, before the main loop */
+ if (in_link == DESC_PARSE && c != ']') {
+ pushbuf();
+ /* skip the regular loop -- pushbuf handles formatting */
+ continue;
+ }
+
+ /* Handle Escapes before any other bit of the main loop */
if (escape) {
maybe_startp();
putesc(c);
@@ -150,11 +175,6 @@ int parse() {
continue;
}
- /* Store links as we go */
- if (in_link == URL_PARSE && c != ']') {
- lnkbuf[lnkidx++] = c;
- }
-
/* Store the indentation */
if (!linestarted && c == ' ') {
indent++;
@@ -181,9 +201,10 @@ int parse() {
if (in == HEADER_PARSE) {
printf("<h%d>", hlvl);
in = HEADER;
- } else if (in_link == URL_PARSE) {
- in_link = DESC_PARSE;
- printf("\">");
+ } else if (in_link == OPT_URL) {
+ /* [url] style links */
+ in_link = NOL;
+ printf("<a href=\"%s\">%s</a> ", lnkdes, lnkdes);
} else if (in == LIST_PARSE) {
if (!listdepth) {
newlist();
@@ -232,22 +253,32 @@ int parse() {
case '[':
if (in_link == NOL && !fmt_disabled()) {
maybe_startp();
+ in_link = DESC_PARSE;
+ lnkdes[0] = '\0';
+ } else {
+ putesc(c);
+ }
+ break;
+ case ']':
+ if (in_link == DESC_PARSE) {
+ in_link = OPT_URL;
+ } else {
+ putesc(c);
+ }
+ break;
+ case '(':
+ if (in_link == OPT_URL) {
+ /* don't print it, start parsing */
in_link = URL_PARSE;
- lnkidx = 0;
printf("<a href=\"");
} else {
putesc(c);
}
break;
- case ']':
+ case ')':
if (in_link == URL_PARSE) {
- /* no description */
- in_link = NOL;
- lnkbuf[lnkidx] = '\0';
- printf("\">%s</a>", lnkbuf);
- } else if (in_link == DESC_PARSE) {
in_link = NOL;
- printf("</a>");
+ printf("\">%s</a>", lnkdes);
} else {
putesc(c);
}
diff --git a/test/big.txt b/test/big.txt
@@ -27,7 +27,7 @@ that wraps nicely
This is a _paragraph_ *dangit* with
links to [https://alexkarle.com] and
-my [gopher://alexkarle.com gopherhole].
+my [gopherhole](gopher://alexkarle.com).
> this is a block quote
> that wraps!
@@ -41,14 +41,14 @@ my [gopher://alexkarle.com gopherhole].
cheers!
-[gopher://alexkarle.com use `sacc(1)`]
+[use `sacc(1)`](gopher://alexkarle.com)
-[https://example.com this is a link
-with a newline!]
+[this is a link
+with a newline!](https://example.com)
-[https://example.com
+[
this is another link
-with a newline!]
+with a newline!](https://example.com)
> This is a block quote
>
diff --git a/test/link.html b/test/link.html
@@ -0,0 +1,27 @@
+<p>
+<a href="https://alexkarle.com">https://alexkarle.com</a>
+</p>
+<p>
+<a href="https://alexkarle.com">link <code>with code</code> <strong>and bold</strong></a>
+</p>
+<p>
+<a href="https://alexkarle.com">link with *escape</a>
+</p>
+<p>
+this is a paragraph about
+<a href="https://alexkarle.com">https://alexkarle.com</a>
+yo!
+</p>
+<p>
+this is a paragraph about
+<a href="https://alexkarle.com">my site</a>
+yo!
+</p>
+<p>
+this is a paragraph about
+<a href="https://alexkarle.com">https://alexkarle.com</a> yo!
+</p>
+<p>
+this is a paragraph about
+<a href="https://alexkarle.com">my site</a> yo!
+</p>
diff --git a/test/link.txt b/test/link.txt
@@ -0,0 +1,19 @@
+[https://alexkarle.com]
+
+[link `with code` *and bold*](https://alexkarle.com)
+
+[link with \*escape](https://alexkarle.com)
+
+this is a paragraph about
+[https://alexkarle.com]
+yo!
+
+this is a paragraph about
+[my site](https://alexkarle.com)
+yo!
+
+this is a paragraph about
+[https://alexkarle.com] yo!
+
+this is a paragraph about
+[my site](https://alexkarle.com) yo!
