New code to scan for patterns (used only for url pattern matching atm, but

2002-12-09  Jeffrey Stedfast  <fejj@ximian.com>

	* camel-url-scanner.c: New code to scan for patterns (used only
	for url pattern matching atm, but we may find other uses for this
	and thus rename it? I dunno). Uses ETrie.

svn path=/trunk/; revision=19075

1 files changed, 396 insertions, 0 deletions

diff --git a/camel/camel-url-scanner.c b/camel/camel-url-scanner.c
new file mode 100644
index 0000000000..8ff6a14156
--- /dev/null
+++ b/camel/camel-url-scanner.c
@@ -0,0 +1,396 @@
+/* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
+/*
+ *  Authors: Jeffrey Stedfast <fejj@ximian.com>
+ *
+ *  Copyright 2002 Ximian, Inc. (www.ximian.com)
+ *
+ *  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 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  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, write to the Free Software
+ *  Foundation, Inc., 59 Temple Street #330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+
+#ifdef HAVE_CONFIG_H
+#include <config.h>
+#endif
+
+#include <string.h>
+
+#include "e-util/e-trie.h"
+#include "camel-url-scanner.h"
+
+
+struct _CamelUrlScanner {
+	GPtrArray *patterns;
+	ETrie *trie;
+};
+
+
+CamelUrlScanner *
+camel_url_scanner_new (void)
+{
+	CamelUrlScanner *scanner;
+	
+	scanner = g_new (CamelUrlScanner, 1);
+	scanner->patterns = g_ptr_array_new ();
+	scanner->trie = e_trie_new (TRUE);
+	
+	return scanner;
+}
+
+
+void
+camel_url_scanner_free (CamelUrlScanner *scanner)
+{
+	g_return_if_fail (scanner != NULL);
+	
+	g_ptr_array_free (scanner->patterns, TRUE);
+	e_trie_free (scanner->trie);
+	g_free (scanner);
+}
+
+
+void
+camel_url_scanner_add (CamelUrlScanner *scanner, urlpattern_t *pattern)
+{
+	g_return_if_fail (scanner != NULL);
+	
+	e_trie_add (scanner->trie, pattern->pattern, scanner->patterns->len);
+	g_ptr_array_add (scanner->patterns, pattern);
+}
+
+
+gboolean
+camel_url_scanner_scan (CamelUrlScanner *scanner, const char *in, size_t inlen, urlmatch_t *match)
+{
+	const char *pos, *inend;
+	urlpattern_t *pat;
+	int pattern;
+	
+	g_return_val_if_fail (scanner != NULL, FALSE);
+	g_return_val_if_fail (in != NULL, FALSE);
+	
+	if (!(pos = e_trie_search (scanner->trie, in, inlen, &pattern)))
+		return FALSE;
+	
+	pat = g_ptr_array_index (scanner->patterns, pattern);
+	
+	inend = in + inlen;
+	if (!pat->start (in, pos, inend, match))
+		return FALSE;
+	
+	if (!pat->end (in, pos, inend, match))
+		return FALSE;
+	
+	match->pattern = pat->pattern;
+	match->prefix = pat->prefix;
+	
+	return TRUE;
+}
+
+
+static unsigned char url_scanner_table[256] = {
+	  1,  1,  1,  1,  1,  1,  1,  1,  1,  9,  9,  1,  1,  9,  1,  1,
+	  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,
+	 24, 64, 96, 64, 64, 64, 64, 64, 96, 96, 64, 64, 96, 64, 96, 96,
+	  4,  4,  4,  4,  4,  4,  4,  4,  4,  4, 96, 96, 32, 64, 32, 64,
+	 96,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,
+	  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2, 96, 96, 96, 64, 64,
+	 64,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,
+	  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2, 64, 64, 64, 64,  1,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+	  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0
+};
+
+enum {
+	IS_CTRL		= (1 << 0),
+	IS_ALPHA        = (1 << 1),
+	IS_DIGIT        = (1 << 2),
+	IS_LWSP		= (1 << 3),
+	IS_SPACE	= (1 << 4),
+	IS_SPECIAL	= (1 << 5),
+	IS_URLSAFE      = (1 << 6),
+};
+
+#define is_ctrl(x) ((url_scanner_table[(unsigned char)(x)] & IS_CTRL) != 0)
+#define is_lwsp(x) ((url_scanner_table[(unsigned char)(x)] & IS_LWSP) != 0)
+#define is_atom(x) ((url_scanner_table[(unsigned char)(x)] & (IS_SPECIAL|IS_SPACE|IS_CTRL)) == 0)
+#define is_alpha(x) ((url_scanner_table[(unsigned char)(x)] & IS_ALPHA) != 0)
+#define is_digit(x) ((url_scanner_table[(unsigned char)(x)] & IS_DIGIT) != 0)
+#define is_domain(x) ((url_scanner_table[(unsigned char)(x)] & (IS_ALPHA|IS_DIGIT)) != 0 || (x) == '-')
+#define is_urlsafe(x) ((url_scanner_table[(unsigned char)(x)] & (IS_ALPHA|IS_DIGIT|IS_URLSAFE)) != 0)
+
+
+gboolean
+camel_url_addrspec_start (const char *in, const char *pos, const char *inend, urlmatch_t *match)
+{
+	register const char *inptr = pos;
+	
+	g_assert (*inptr == '@');
+	
+	inptr--;
+	
+	while (inptr > in) {
+		if (is_atom (*inptr))
+			inptr--;
+		else
+			break;
+		
+		while (inptr > in && is_atom (*inptr))
+			inptr--;
+		
+		if (inptr > in && *inptr == '.')
+			inptr--;
+	}
+	
+	if (!is_atom (*inptr))
+		inptr++;
+	
+	if (inptr == pos)
+		return FALSE;
+	
+	match->um_so = (inptr - in);
+	
+	return TRUE;
+}
+
+gboolean
+camel_url_addrspec_end (const char *in, const char *pos, const char *inend, urlmatch_t *match)
+{
+	const char *inptr = pos;
+	int parts = 0, digits;
+	
+	g_assert (*inptr == '@');
+	
+	inptr++;
+	
+	if (*inptr == '[') {
+		/* domain literal */
+		do {
+			inptr++;
+			
+			digits = 0;
+			while (inptr < inend && is_digit (*inptr) && digits < 3) {
+				inptr++;
+				digits++;
+			}
+			
+			parts++;
+			
+			if (*inptr != '.' && parts != 4)
+				return FALSE;
+		} while (parts < 4);
+		
+		if (*inptr == ']')
+			inptr++;
+		else
+			return FALSE;
+	} else {
+		while (inptr < inend) {
+			if (is_domain (*inptr))
+				inptr++;
+			else
+				break;
+			
+			while (inptr < inend && is_domain (*inptr))
+				inptr++;
+			
+			if (inptr < inend && *inptr == '.')
+				inptr++;
+		}
+	}
+	
+	if (inptr == pos)
+		return FALSE;
+	
+	match->um_eo = (inptr - in);
+	
+	return TRUE;
+}
+
+gboolean
+camel_url_file_start (const char *in, const char *pos, const char *inend, urlmatch_t *match)
+{
+	match->um_so = (pos - in);
+	
+	return TRUE;
+}
+
+gboolean
+camel_url_file_end (const char *in, const char *pos, const char *inend, urlmatch_t *match)
+{
+	register const char *inptr = pos;
+	
+	inptr += strlen (match->pattern);
+	
+	if (*inptr == '/')
+		inptr++;
+	
+	while (inptr < inend && is_urlsafe (*inptr))
+		inptr++;
+	
+	if (inptr == pos)
+		return FALSE;
+	
+	match->um_eo = (inptr - in);
+	
+	return TRUE;
+}
+
+gboolean
+camel_url_web_start (const char *in, const char *pos, const char *inend, urlmatch_t *match)
+{
+	match->um_so = (pos - in);
+	
+	return TRUE;
+}
+
+gboolean
+camel_url_web_end (const char *in, const char *pos, const char *inend, urlmatch_t *match)
+{
+	register const char *inptr = pos;
+	int parts = 0, digits, port;
+	
+	inptr += strlen (match->pattern);
+	
+	/* find the end of the domain */
+	if (is_digit (*inptr)) {
+		/* domain-literal */
+		do {
+			digits = 0;
+			while (inptr < inend && is_digit (*inptr) && digits < 3) {
+				inptr++;
+				digits++;
+			}
+			
+			parts++;
+			
+			if (*inptr != '.' && parts != 4)
+				return FALSE;
+			else if (*inptr == '.')
+				inptr++;
+			
+		} while (parts < 4);
+	} else if (is_domain (*inptr)) {
+		do {
+			while (inptr < inend && is_domain (*inptr))
+				inptr++;
+			
+			if (inptr < inend && *inptr == '.')
+				inptr++;
+			else
+				break;
+			
+		} while (inptr < inend);
+	} else {
+		return FALSE;
+	}
+	
+	if (inptr < inend && *inptr == ':') {
+		/* skip past the port */
+		inptr++;
+		port = 0;
+		
+		while (inptr < inend && is_digit (*inptr) && port < 65536)
+			port = (port * 10) + (*inptr++ - '0');
+	}
+	
+	if (inptr < inend && *inptr == '/') {
+		/* skip past our url path */
+		inptr++;
+		
+		while (inptr < inend && is_urlsafe (*inptr))
+			inptr++;
+	}
+	
+	match->um_eo = (inptr - in);
+	
+	return TRUE;
+}
+
+
+
+#ifdef BUILD_TABLE
+
+#include <stdio.h>
+
+/* got these from rfc1738 */
+#define CHARS_LWSP " \t\n\r"               /* linear whitespace chars */
+#define CHARS_SPECIAL "()<>@,;:\\\".[]"
+
+/* got these from rfc1738 */
+#define CHARS_URLSAFE "$-_.+!*'(),{}|\\^~[]`#%\";/?:@&="
+
+
+static void
+table_init_bits (unsigned int mask, const unsigned char *vals)
+{
+	int i;
+	
+	for (i = 0; vals[i] != '\0'; i++)
+		url_scanner_table[vals[i]] |= mask;
+}
+
+static void
+url_scanner_table_init (void)
+{
+	int i;
+	
+	for (i = 0; i < 256; i++) {
+		url_scanner_table[i] = 0;
+		if (i < 32)
+			url_scanner_table[i] |= IS_CTRL;
+		if ((i >= '0' && i <= '9'))
+			url_scanner_table[i] |= IS_DIGIT;
+		if ((i >= 'a' && i <= 'z') || (i >= 'A' && i <= 'Z'))
+			url_scanner_table[i] |= IS_ALPHA;
+	}
+	
+	url_scanner_table[127] |= IS_CTRL;
+	url_scanner_table[' '] |= IS_SPACE;
+	
+	/* not defined to be special in rfc0822, but when scanning
+           backwards to find the beginning of the email address we do
+           not want to incldue this char if we come accross it - so
+           this is kind of a hack */
+	url_scanner_table['/'] |= IS_SPECIAL;
+	
+	table_init_bits (IS_LWSP, CHARS_LWSP);
+	table_init_bits (IS_SPECIAL, CHARS_SPECIAL);
+	table_init_bits (IS_URLSAFE, CHARS_URLSAFE);
+}
+
+int main (int argc, char **argv)
+{
+	int i;
+	
+	url_scanner_table_init ();
+	
+	printf ("static unsigned char url_scanner_table[256] = {");
+	for (i = 0; i < 256; i++) {
+		printf ("%s%3d%s", (i % 16) ? "" : "\n\t",
+			url_scanner_table[i], i != 255 ? "," : "\n");
+	}
+	printf ("};\n\n");
+	
+	return 0;
+}
+
+#endif /* BUILD_TABLE */