git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: git@vger.kernel.org
Cc: "Jeff King" <peff@peff.net>,
	avila.jn@gmail.com, "Junio C Hamano" <gitster@pobox.com>,
	"Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Subject: [PATCH 1/4] wildmatch: do not require "text" to be NUL-terminated
Date: Mon, 25 Mar 2013 13:05:07 +0700	[thread overview]
Message-ID: <1364191510-8900-2-git-send-email-pclouds@gmail.com> (raw)
In-Reply-To: <1364191510-8900-1-git-send-email-pclouds@gmail.com>

This may be helpful when we just want to match a part of "text".
nwildmatch can be used for this purpose.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 wildmatch.c | 43 +++++++++++++++++++++++++------------------
 wildmatch.h | 11 +++++++++--
 2 files changed, 34 insertions(+), 20 deletions(-)

diff --git a/wildmatch.c b/wildmatch.c
index 7192bdc..939bac8 100644
--- a/wildmatch.c
+++ b/wildmatch.c
@@ -52,7 +52,8 @@ typedef unsigned char uchar;
 #define ISXDIGIT(c) (ISASCII(c) && isxdigit(c))
 
 /* Match pattern "p" against "text" */
-static int dowild(const uchar *p, const uchar *text, unsigned int flags)
+static int dowild(const uchar *p, const uchar *text,
+		  const uchar *textend, unsigned int flags)
 {
 	uchar p_ch;
 	const uchar *pattern = p;
@@ -60,8 +61,13 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 	for ( ; (p_ch = *p) != '\0'; text++, p++) {
 		int matched, match_slash, negated;
 		uchar t_ch, prev_ch;
-		if ((t_ch = *text) == '\0' && p_ch != '*')
-			return WM_ABORT_ALL;
+		if (text >= textend) {
+			if (p_ch != '*')
+				return WM_ABORT_ALL;
+			else
+				t_ch = '\0';
+		} else
+			t_ch = *text;
 		if ((flags & WM_CASEFOLD) && ISUPPER(t_ch))
 			t_ch = tolower(t_ch);
 		if ((flags & WM_CASEFOLD) && ISUPPER(p_ch))
@@ -101,7 +107,7 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 					 * both foo/bar and foo/a/bar.
 					 */
 					if (p[0] == '/' &&
-					    dowild(p + 1, text, flags) == WM_MATCH)
+					    dowild(p + 1, text, textend, flags) == WM_MATCH)
 						return WM_MATCH;
 					match_slash = 1;
 				} else
@@ -113,8 +119,9 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 				/* Trailing "**" matches everything.  Trailing "*" matches
 				 * only if there are no more slash characters. */
 				if (!match_slash) {
-					if (strchr((char*)text, '/') != NULL)
-						return WM_NOMATCH;
+					for (;text < textend; text++)
+						if (*text == '/')
+							return WM_NOMATCH;
 				}
 				return WM_MATCH;
 			} else if (!match_slash && *p == '/') {
@@ -123,16 +130,15 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 				 * with WM_PATHNAME matches the next
 				 * directory
 				 */
-				const char *slash = strchr((char*)text, '/');
-				if (!slash)
+				for (;text < textend; text++)
+					if (*text == '/')
+						break;
+				if (text == textend)
 					return WM_NOMATCH;
-				text = (const uchar*)slash;
 				/* the slash is consumed by the top-level for loop */
 				break;
 			}
-			while (1) {
-				if (t_ch == '\0')
-					break;
+			while (text < textend) {
 				/*
 				 * Try to advance faster when an asterisk is
 				 * followed by a literal. We know in this case
@@ -145,18 +151,18 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 					p_ch = *p;
 					if ((flags & WM_CASEFOLD) && ISUPPER(p_ch))
 						p_ch = tolower(p_ch);
-					while ((t_ch = *text) != '\0' &&
+					while (text < textend &&
 					       (match_slash || t_ch != '/')) {
 						if ((flags & WM_CASEFOLD) && ISUPPER(t_ch))
 							t_ch = tolower(t_ch);
 						if (t_ch == p_ch)
 							break;
-						text++;
+						t_ch = ++text < textend ? *text : '\0';
 					}
 					if (t_ch != p_ch)
 						return WM_NOMATCH;
 				}
-				if ((matched = dowild(p, text, flags)) != WM_NOMATCH) {
+				if ((matched = dowild(p, text, textend, flags)) != WM_NOMATCH) {
 					if (!match_slash || matched != WM_ABORT_TO_STARSTAR)
 						return matched;
 				} else if (!match_slash && t_ch == '/')
@@ -261,12 +267,13 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
 		}
 	}
 
-	return *text ? WM_NOMATCH : WM_MATCH;
+	return text < textend ? WM_NOMATCH : WM_MATCH;
 }
 
 /* Match the "pattern" against the "text" string. */
-int wildmatch(const char *pattern, const char *text,
+int nwildmatch(const char *pattern, const char *text, int textlen,
 	      unsigned int flags, struct wildopts *wo)
 {
-	return dowild((const uchar*)pattern, (const uchar*)text, flags);
+	return dowild((const uchar*)pattern, (const uchar*)text,
+		      (const uchar*)text + textlen, flags);
 }
diff --git a/wildmatch.h b/wildmatch.h
index 4090c8f..cdd7544 100644
--- a/wildmatch.h
+++ b/wildmatch.h
@@ -12,7 +12,14 @@
 
 struct wildopts;
 
-int wildmatch(const char *pattern, const char *text,
-	      unsigned int flags,
+int nwildmatch(const char *pattern, const char *text,
+	      int len, unsigned int flags,
 	      struct wildopts *wo);
+
+/* Match the "pattern" against the "text" string. */
+static inline int wildmatch(const char *pattern, const char *text,
+	      unsigned int flags, struct wildopts *wo)
+{
+	return nwildmatch(pattern, text, strlen(text), flags, wo);
+}
 #endif
-- 
1.8.2.82.gc24b958

  reply	other threads:[~2013-03-25  6:06 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-19 17:57 [regression?] trailing slash required in .gitattributes Jeff King
2013-03-19 18:10 ` Junio C Hamano
2013-03-19 18:10 ` Jeff King
2013-03-22 22:24   ` Jeff King
2013-03-22 23:08     ` Junio C Hamano
2013-03-23  8:39       ` Jeff King
2013-03-24  5:25         ` Junio C Hamano
2013-03-26 18:39         ` [PATCH 0/4] attribute regression fix for maint-1.8.1 and upward Junio C Hamano
2013-03-26 18:39           ` [PATCH 1/4] attr.c::path_matches(): the basename is part of the pathname Junio C Hamano
2013-03-26 18:49             ` Jeff King
2013-03-27  1:40               ` Duy Nguyen
2013-03-26 18:39           ` [PATCH 2/4] dir.c::match_basename(): pay attention to the length of string parameters Junio C Hamano
2013-03-26 18:55             ` Jeff King
2013-03-26 20:39               ` Jeff King
2013-03-26 20:49                 ` Junio C Hamano
2013-03-26 21:29                   ` Jeff King
2013-03-26 22:33                     ` Junio C Hamano
2013-03-27  1:04                       ` Jeff King
2013-03-26 18:39           ` [PATCH 3/4] attr.c::path_matches(): special case paths that end with a slash Junio C Hamano
2013-03-26 19:05             ` Jeff King
2013-03-26 21:33               ` Jeff King
2013-03-27  1:30                 ` Duy Nguyen
2013-03-28 19:49               ` Jeff King
2013-03-26 18:39           ` [PATCH 4/4] make sure a pattern without trailing slash matches a directory Junio C Hamano
2013-03-26 19:08             ` Jeff King
2013-03-27  1:13           ` [PATCH 0/4] attribute regression fix for maint-1.8.1 and upward Duy Nguyen
2013-03-27  3:57             ` Junio C Hamano
2013-03-27  4:01               ` Duy Nguyen
2013-03-28 21:43           ` [PATCH v2 0/6] " Jeff King
2013-03-28 21:45             ` [PATCH 1/6] attr.c::path_matches(): the basename is part of the pathname Jeff King
2013-03-28 21:47             ` [PATCH 2/6] dir.c::match_basename(): pay attention to the length of string parameters Jeff King
2013-03-28 22:40               ` Jeff King
2013-03-28 22:49                 ` Jeff King
2013-03-28 23:10                   ` Junio C Hamano
2013-03-28 23:40                   ` Duy Nguyen
2013-03-29  1:25               ` Duy Nguyen
2013-03-29  3:02                 ` Jeff King
2013-03-29  5:57                   ` Junio C Hamano
2013-03-28 21:47             ` [PATCH 3/6] dir.c::match_pathname(): adjust patternlen when shifting pattern Jeff King
2013-03-28 21:48             ` [PATCH 4/6] dir.c::match_pathname(): pay attention to the length of string parameters Jeff King
2013-03-28 22:30               ` Junio C Hamano
2013-03-29  8:45               ` Duy Nguyen
2013-03-29 10:03                 ` Duy Nguyen
2013-03-29 11:32                   ` Torsten Bögershausen
2013-03-29 11:37                     ` Duy Nguyen
2013-03-29 12:05                 ` Jeff King
2013-03-29 13:02                   ` Duy Nguyen
2013-03-29 16:44                     ` Junio C Hamano
2013-03-29 17:04                       ` Jeff King
2013-03-29 17:35                         ` Junio C Hamano
2013-03-29 17:44                           ` Jeff King
2013-03-30  1:40                       ` Duy Nguyen
2013-03-28 21:49             ` [PATCH 5/6] attr.c::path_matches(): special case paths that end with a slash Jeff King
2013-03-28 21:50             ` [PATCH 6/6] t: check that a pattern without trailing slash matches a directory Jeff King
2013-03-28 22:21               ` Eric Sunshine
2013-03-28 22:22                 ` Jeff King
2013-03-23  4:18     ` [regression?] trailing slash required in .gitattributes Duy Nguyen
2013-03-23  4:43       ` Duy Nguyen
2013-03-25  6:05 ` [PATCH 0/4] attr directory matching regression Nguyễn Thái Ngọc Duy
2013-03-25  6:05   ` Nguyễn Thái Ngọc Duy [this message]
2013-03-25  6:05   ` [PATCH 2/4] attr.c: fix pattern{,len} inconsistency in struct match_attr Nguyễn Thái Ngọc Duy
2013-03-25  6:05   ` [PATCH 3/4] dir.c: make match_{base,path}name respect {basename,path}len Nguyễn Thái Ngọc Duy
2013-03-25  6:05   ` [PATCH 4/4] attr.c: fix matching "subdir" without the trailing slash Nguyễn Thái Ngọc Duy
2013-03-25  7:20     ` Duy Nguyen
2013-03-25  9:24       ` Duy Nguyen
2013-03-26 15:10   ` [PATCH 0/4] attr directory matching regression Junio C Hamano

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1364191510-8900-2-git-send-email-pclouds@gmail.com \
    --to=pclouds@gmail.com \
    --cc=avila.jn@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=peff@peff.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).