чување 2ac06532ee52ee9986d19addbb4d9d96491e50e0
родитељ 0bfc85afbb6942543638118c36f25c0f36d7a919
Аутор: Страхиња Радић <contact@strahinja.org>
Датум: Fri, 11 Dec 2020 16:14:16 +0100
Continued WIP migration to C
Signed-off-by: Страхиња Радић <contact@strahinja.org>
Diffstat:
| M | README | | | 30 | ++---------------------------- |
| M | defs.h | | | 19 | +++++++++++++++++++ |
| M | index.html | | | 72 | +++++++++++++++++++++++++++++++++--------------------------------------- |
| M | index.slw | | | 3 | ++- |
| M | slweb.c | | | 358 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---- |
измењених датотека: 5, додавања: 399(+), брисања: 83(-)
diff --git a/README b/README
@@ -1,35 +1,9 @@
- **IMPORTANT NOTE**
- ==================
-
-Version v0.2.8-beta is the last version of slweb using sed. I decided to switch
-to C because of the limitation of sed(1) when used to parse the entire file as a
-single string (the -z option), as listed in
-
- https://www.gnu.org/software/sed/manual/sed.html#Limitations
-
- > For those who want to write portable sed scripts, be aware that some
- > implementations have been known to limit line lengths (for the pattern
- > and hold spaces) to be no more than 4000 bytes. The POSIX standard
- > specifies that conforming sed implementations shall support at least
- > 8192 byte line lengths. GNU sed has no built-in limit on line length;
- > as long as it can malloc() more (virtual) memory, you can feed or
- > construct lines as long as you like.
-
-When processed through slweb, some of the test pages using the cyrillic text in
-UTF-8 would be rendered incorrectly, even when using GNU sed. I suspect this is
-the result of the mentioned limitation.
-
- The next version of slweb is going to be written in C from scratch and
-labeled v0.3.0.
-
- -- Strahinya
-
slweb
=====
-Slweb is a static website generator which aims at being simplistic. It uses
-sed(1) to transform a custom Markdown-like syntax into HTML.
+Slweb is a static website generator which aims at being simplistic. It
+transforms custom Markdown-like syntax into HTML.
Install
diff --git a/defs.h b/defs.h
@@ -40,6 +40,9 @@ typedef enum
TRUE = 1
} BOOL;
+typedef unsigned char UBYTE;
+typedef unsigned short USHORT;
+
typedef enum
{
CMD_NONE,
@@ -49,5 +52,21 @@ typedef enum
CMD_VERSION
} Command;
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-const-variable"
+const UBYTE MAX_HEADING_LEVEL = 4;
+
+const USHORT ST_NONE = 0;
+const USHORT ST_YAML = 1;
+const USHORT ST_YAML_VAR = 1 << 1;
+const USHORT ST_YAML_VAL = 1 << 2;
+const USHORT ST_PARA_OPEN = 1 << 3;
+const USHORT ST_TAG = 1 << 4;
+const USHORT ST_HEADING = 1 << 5;
+const USHORT ST_PRE = 1 << 6;
+const USHORT ST_CODE = 1 << 7;
+const USHORT ST_BLOCKQUOTE = 1 << 8;
+#pragma GCC diagnostic pop
+
#endif /* __DEFS_H */
diff --git a/index.html b/index.html
@@ -1,28 +1,23 @@
-site-name: slweb - Simple static website generator.
-site-desc: Simple static website generator
-stylesheet: index.css
----
-{main}
-# slweb
+<main>
-**Slweb** is a static website generator which aims at being simplistic. It uses
-**sed**(1) to transform a custom Markdown-like syntax into HTML.
+<h1>slweb</h1>
-## Install
+<p>**Slweb** is a static website generator which aims at being simplistic. It uses
+**sed**(1) to transform a custom Markdown-like syntax into HTML.</p>
-```
+<h2>Install</h2>
+<pre>
$ git clone https://github.com/Strahinja/slweb.git
$ cd slweb
$ make && sudo make install
-```
-
-## Examples
+</pre>
-See the `[examples/](https://github.com/Strahinja/slweb/tree/master/examples)` directory in this repository.
+<h2>Examples</h2>
-Given the file `index.slw` in the current directory:
+<p>See the [<code>examples/</code>](https://github.com/Strahinja/slweb/tree/master/examples) directory in this repository.</p>
-```
+<p>Given the file <code>index.slw</code> in the current directory:</p>
+<pre>
site-name: Test website
site-desc: My first website in slweb
---
@@ -33,17 +28,15 @@ site-desc: My first website in slweb
This is an \_example_ of a statically generated HTML.
\
\{/main}
-```
-
-after using the command:
+</pre>
-```
+<p>after using the command:</p>
+<pre>
$ slweb index.slw > index.html
-```
+</pre>
-file `index.html` contains:
-
-```
+<p>file <code>index.html</code> contains:</p>
+<pre>
<!DOCTYPE html>
<html lang="en">
<head>
@@ -63,27 +56,28 @@ file `index.html` contains:
</main>
</body>
</html>
-```
+</pre>
-## License
+<h2>License</h2>
-slweb - Simple static website generator.
-Copyright (C) 2020 Страхиња Радић
+<p>slweb - Simple static website generator.<br />
+Copyright (C) 2020 Страхиња Радић</p>
-This program is free software: you can redistribute it and/or modify it under
+<p>This program is free software: you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free Software
Foundation, either version 3 of the License, or (at your option) any later
-version.
+version. </p>
-This program is distributed in the hope that it will be useful, but WITHOUT ANY
+<p>This program is distributed in the hope that it will be useful, but WITHOUT ANY
WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A
-PARTICULAR PURPOSE. See the GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License along with
-this program. If not, see <https://www.gnu.org/licenses/>.
-
-{git-log}
+PARTICULAR PURPOSE. See the GNU General Public License for more details. </p>
-{made-by}
-{/main}
+<p>You should have received a copy of the GNU General Public License along with
+this program. If not, see <https://www.gnu.org/licenses/>. </p>
+<git-log>
+<div id="made-by">
+Generated by <a href="https://github.com/Strahinja/slweb">slweb</a>
+© 2020 Strahinya Radich.
+</div><!--made-by-->
+</main>
diff --git a/index.slw b/index.slw
@@ -1,3 +1,4 @@
+---
site-name: slweb - Simple static website generator.
site-desc: Simple static website generator
stylesheet: index.css
@@ -18,7 +19,7 @@ $ make && sudo make install
## Examples
-See the `[examples/](https://github.com/Strahinja/slweb/tree/master/examples)` directory in this repository.
+See the [`examples/`](https://github.com/Strahinja/slweb/tree/master/examples) directory in this repository.
Given the file `index.slw` in the current directory:
diff --git a/slweb.c b/slweb.c
@@ -18,7 +18,13 @@
*/
#include "defs.h"
+#include <asm-generic/errno-base.h>
+#include <stdio.h>
#include <stdlib.h>
+#include <unistr.h>
+
+static size_t lineno = 0;
+static size_t colno = 1;
int
version()
@@ -47,6 +53,18 @@ error(int code, uint8_t* fmt, ...)
return code;
}
+int
+warning(int code, uint8_t* fmt, ...)
+{
+ uint8_t buf[BUFSIZE];
+ va_list args;
+ va_start(args, fmt);
+ u8_vsnprintf(buf, sizeof(buf), (const char*)fmt, args);
+ va_end(args);
+ fprintf(stderr, "Warning: %s", buf);
+ return code;
+}
+
char*
substr(char* src, int start, int finish)
{
@@ -57,6 +75,8 @@ substr(char* src, int start, int finish)
if (substr_len < 0)
substr_len = 0;
char* result = (char*) calloc(substr_len+1, sizeof(char));
+ if (!result)
+ exit(error(ENOMEM, (uint8_t*)"Memory allocation failed (out of memory?)\n"));
char* presult = result;
for (int i = start; i < finish && *(src+i) != '\0'; i++)
@@ -82,13 +102,70 @@ set_basedir(char* arg, char** basedir)
*basedir = (char*) calloc(strlen(arg)+1, sizeof(char));
if (!*basedir)
- return 1;
+ return error(ENOMEM, (uint8_t*)"Memory allocation failed (out of memory?)\n");
strcpy(*basedir, arg);
return 0;
}
+uint8_t*
+init_string(uint8_t** str)
+{
+ if (!str || !*str)
+ return NULL;
+
+ *str[0] = '\0';
+
+ return *str;
+}
+
+int
+finish_and_print_token(uint8_t** token, uint8_t** ptoken, FILE* output)
+{
+ if (!token || !*token || !ptoken || !*ptoken)
+ return 1;
+
+ *ptoken[0] = '\0';
+ fprintf(output, "%s", *token);
+}
+
+int
+process_heading(uint8_t* token, FILE* output, UBYTE heading_level)
+{
+ if (!token || u8_strlen(token) < 1)
+ warning(1, (uint8_t*)"Empty heading\n");
+
+ fprintf(output, "<h%d>%s</h%d>",
+ heading_level,
+ token ? (char*)token : "",
+ heading_level);
+
+ return 0;
+}
+
+int
+process_tag(uint8_t* token, FILE* output, BOOL end_tag)
+{
+ if (!token || u8_strlen(token) < 1)
+ return warning(1, (uint8_t*)"No tag\n");
+
+ if (!strcmp(token, "made-by"))
+ {
+ fprintf(output, "<div id=\"made-by\">\n"
+ "Generated by <a href=\"https://github.com/Strahinja/slweb\">"
+ "slweb</a>\n"
+ "© 2020 Strahinya Radich.\n"
+ "</div><!--made-by-->\n");
+ }
+ else
+ fprintf(output, "<%s%s>",
+ end_tag ? (const char*)"/" : (const char*)"",
+ token);
+
+ return 0;
+}
+
int
main(int argc, char** argv)
{
@@ -99,6 +176,8 @@ main(int argc, char** argv)
char* basedir = NULL;
basedir = (char*) calloc(2, sizeof(char));
+ if (!basedir)
+ return error(ENOMEM, (uint8_t*)"Memory allocation failed (out of memory?)\n");
basedir[0] = '.';
while ((arg = *++argv))
@@ -133,7 +212,7 @@ main(int argc, char** argv)
}
else
{
- error(1, (uint8_t*)"Invalid argument: --%s\n", arg);
+ error(EINVAL, (uint8_t*)"Invalid argument: --%s\n", arg);
return usage();
}
}
@@ -154,7 +233,7 @@ main(int argc, char** argv)
cmd = CMD_VERSION;
break;
default:
- error(1, (uint8_t*)"Invalid argument: -%c\n", c);
+ error(EINVAL, (uint8_t*)"Invalid argument: -%c\n", c);
return usage();
}
}
@@ -183,42 +262,291 @@ main(int argc, char** argv)
if (cmd == CMD_VERSION)
return version();
- /*
- *printf("debug: basedir=%s, filename=%s, body_only=%s\n",
- * basedir, filename ? filename : "(NULL)", body_only ? "TRUE" : "FALSE");
- */
-
FILE* input = NULL;
if (filename)
{
input = fopen(filename, "r");
if (!input)
{
- return error(ENOENT, (uint8_t*)"File not found: %s\n", filename);
+ return error(ENOENT, (uint8_t*)"No such file: %s\n", filename);
}
}
else
input = stdin;
uint8_t* line = (uint8_t*) calloc(BUFSIZE, sizeof(uint8_t));
+ uint8_t* pline = NULL;
size_t line_len = 0;
+ uint8_t* token = (uint8_t*) calloc(BUFSIZE, sizeof(uint8_t));
+ uint8_t* ptoken = NULL;
+ size_t token_len = 0;
+ USHORT state = ST_NONE;
+ UBYTE heading_level = 0;
+ BOOL end_tag = FALSE;
+ BOOL first_line_in_doc = TRUE;
+ BOOL previous_line_blank = FALSE;
+ BOOL print_newline = FALSE;
+
+ if (!line)
+ return error(ENOMEM, (uint8_t*)"Memory allocation failed (out of memory?)\n");
do
{
- fgets((char*)line, sizeof(uint8_t) * BUFSIZE, input);
+ if (!fgets((char*)line, sizeof(char) * BUFSIZE, input))
+ continue;
+
+ uint8_t* eol = u8_strchr(line, (ucs4_t)'\n');
+ if (eol)
+ *eol = (uint8_t)'\0';
+
+ lineno++;
+ colno = 1;
+
+ /*
+ *fprintf(stderr, "=D: s:0x%X, hl:%d, et:%s, flid:%s, plb:%s \n",
+ * state,
+ * heading_level,
+ * end_tag ? "T" : "F",
+ * first_line_in_doc ? "T" : "F",
+ * previous_line_blank ? "T" : "F");
+ */
+
line_len = u8_strlen(line);
+ pline = line;
+ ptoken = init_string(&token);
+
+ do
+ {
+ switch (*pline)
+ {
+ case '-':
+ if (colno == 1
+ && !(state & ST_PRE)
+ && u8_strlen(pline) > 2
+ && !strcmp(substr((char*)pline, 0, 3), "---"))
+ {
+ state ^= ST_YAML;
+
+ if (state & ST_YAML)
+ first_line_in_doc = FALSE;
+ else
+ first_line_in_doc = TRUE;
+
+ pline += 3;
+ colno += 3;
+ }
+ else
+ {
+ *ptoken++ = *pline++;
+ colno++;
+ }
+ break;
+ case '`':
+ if (colno == 1
+ && u8_strlen(pline) > 2
+ && !strcmp(substr((char*)pline, 0, 3), "```"))
+ {
+ state ^= ST_PRE;
+
+ if (state & ST_PRE)
+ printf("<pre>");
+ else
+ printf("</pre>");
+ print_newline = TRUE;
- if (!feof(input))
+ pline += 3;
+ colno += 3;
+ }
+ else if (!(state & (ST_HEADING | ST_YAML | ST_PRE)))
+ {
+ state ^= ST_CODE;
+
+ if (state & ST_CODE)
+ {
+ *ptoken = '\0';
+ u8_strncat(ptoken, (uint8_t*)"<code>", strlen("<code>"));
+ ptoken += strlen("<code>");
+ }
+ else
+ {
+ *ptoken = '\0';
+ u8_strncat(ptoken, (uint8_t*)"</code>", strlen("</code>"));
+ ptoken += strlen("</code>");
+ }
+
+ pline++;
+ colno++;
+ }
+ else
+ {
+ *ptoken++ = *pline++;
+ colno++;
+ }
+ break;
+ case '#':
+ if (colno == 1
+ && !(state & (ST_PRE | ST_YAML)))
+ {
+ state |= ST_HEADING;
+ heading_level = 1;
+ pline++;
+ colno++;
+ }
+ else if (state & ST_HEADING && *(pline-1) == '#')
+ {
+ if (heading_level < MAX_HEADING_LEVEL)
+ heading_level++;
+ pline++;
+ colno++;
+ }
+ else {
+ *ptoken++ = *pline++;
+ colno++;
+ }
+ break;
+ case ' ':
+ if (u8_strlen(pline) == 2)
+ {
+ if (*(pline+1) == ' ')
+ {
+ *ptoken = '\0';
+ u8_strncat(ptoken, (uint8_t*)"<br />", strlen("<br />"));
+ ptoken += strlen("<br />");
+ pline++;
+ colno++;
+ }
+ else
+ *ptoken++ = *pline;
+ }
+ else if (!(state & ST_HEADING
+ && *(pline-1) == '#'))
+ *ptoken++ = *pline;
+ pline++;
+ colno++;
+ break;
+ case '{':
+ if (state & (ST_PRE | ST_YAML | ST_HEADING))
+ {
+ *ptoken++ = *pline++;
+ colno++;
+ break;
+ }
+
+ state |= ST_TAG;
+ if (token[0])
+ finish_and_print_token(&token, &ptoken, stdout);
+ ptoken = init_string(&token);
+ pline++;
+ colno++;
+ break;
+
+ case '/':
+ if (state & (ST_PRE | ST_YAML | ST_HEADING))
+ {
+ *ptoken++ = *pline++;
+ colno++;
+ break;
+ }
+
+ if (state & ST_TAG)
+ {
+ if (*(pline-1) != '{')
+ return error(1, (uint8_t*)"Character '/' not allowed here");
+
+ end_tag = TRUE;
+ }
+ else
+ *ptoken++ = *pline;
+
+ pline++;
+ colno++;
+ break;
+
+ case '}':
+ if (state & (ST_PRE | ST_YAML | ST_HEADING))
+ {
+ *ptoken++ = *pline++;
+ colno++;
+ break;
+ }
+
+ state &= ~ST_TAG;
+ *ptoken = '\0';
+ process_tag(token, stdout, end_tag);
+ first_line_in_doc = FALSE;
+ print_newline = TRUE;
+ ptoken = init_string(&token);
+ end_tag = FALSE;
+
+ pline++;
+ colno++;
+ break;
+
+ default:
+ *ptoken++ = *pline++;
+ colno++;
+ }
+ }
+ while (pline && *pline);
+
+ if (!(state & ST_YAML))
{
- uint8_t* eol = u8_strchr(line, (ucs4_t)'\n');
- if (eol)
- *eol = (uint8_t)'\0';
+ if (token[0])
+ {
+ if (colno != 2 && !(state & ST_PRE))
+ printf("\n");
+
+ if (state & ST_HEADING)
+ {
+ state &= ~ST_HEADING;
+ *ptoken = '\0';
+ process_heading(token, stdout, heading_level);
+ first_line_in_doc = FALSE;
+ ptoken = init_string(&token);
+ heading_level = 0;
+ print_newline = TRUE;
+ }
+ else {
+
+ if (first_line_in_doc || previous_line_blank)
+ {
+ printf("<p>");
+ first_line_in_doc = FALSE;
+ state |= ST_PARA_OPEN;
+ }
+ finish_and_print_token(&token, &ptoken, stdout);
+ print_newline = state & (ST_PRE | ST_CODE);
+ }
+ previous_line_blank = FALSE;
+ }
+ else if (colno == 2)
+ {
+ if (!previous_line_blank && (state & ST_PARA_OPEN))
+ {
+ printf("</p>\n");
+ print_newline = FALSE;
+ state &= ~ST_PARA_OPEN;
+ }
+ previous_line_blank = TRUE;
+ }
+ else
+ previous_line_blank = FALSE;
+
+ if (print_newline)
+ {
+ printf("\n");
+ print_newline = FALSE;
+ }
- printf("%s\n", line);
}
+
+ ptoken = init_string(&token);
+
}
while (!feof(input));
+ free(line);
+
return 0;
}
