linux-kernel - [PATCH v2 4/6] perf: Add strpbrk_esq() and strdup

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID:  <173099116045.2431889.15772916605719019533.stgit@mhiramat.roam.corp.google.com>
Date: Thu,  7 Nov 2024 23:52:40 +0900
From: "Masami Hiramatsu (Google)" <mhiramat@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>,
	Namhyung Kim <namhyung@...nel.org>
Cc: Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	Masami Hiramatsu <mhiramat@...nel.org>,
	Ian Rogers <irogers@...gle.com>,
	Dima Kogan <dima@...retsauce.net>,
	Alexander Lobakin <aleksander.lobakin@...el.com>,
	Przemek Kitszel <przemyslaw.kitszel@...el.com>,
	linux-perf-users@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH v2 4/6] perf: Add strpbrk_esq() and strdup_esq() for escape and quote

From: Masami Hiramatsu (Google) <mhiramat@...nel.org>

strpbrk_esq() and strdup_esq() are new variants for strpbrk() and
strdup() which handles escaped characters and quoted strings.

- strpbrk_esq() searches specified set of characters but ignores the
  escaped characters and quoted strings.
  e.g. strpbrk_esq("'quote\d' \queue quiz", "qd") returns "quiz".

- strdup_esq() duplicates string but removes backslash and quotes which
  is used for quotation. It also keeps the string (including backslash)
  in the quoted part.
  e.g. strdup_esq("'quote\d' \queue quiz") returns "quote\d queue quiz".

The (single, double) quotes in the quoted part should be escaped by
backslash. In this case, strdup_esq() removes that backslash.
The same quotes must be paired. If you use double quotation, you need
to use the double quotation to close the quoted part.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@...nel.org>
---
 Changes in v2:
  - Added new patch.
---
 tools/perf/util/string.c  |  100 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/string2.h |    2 +
 2 files changed, 102 insertions(+)

diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 116a642ad99d..308fc7ec88cc 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -263,6 +263,34 @@ char *strpbrk_esc(char *str, const char *stopset)
 	return ptr;
 }
 
+/* Like strpbrk_esc(), but not break if it is quoted with single/double quotes */
+char *strpbrk_esq(char *str, const char *stopset)
+{
+	char *_stopset = NULL;
+	char *ptr;
+	const char *squote = "'";
+	const char *dquote = "\"";
+
+	if (asprintf(&_stopset, "%s%c%c", stopset, *squote, *dquote) < 0)
+		return NULL;
+
+	do {
+		ptr = strpbrk_esc(str, _stopset);
+		if (!ptr)
+			break;
+		if (*ptr == *squote)
+			ptr = strpbrk_esc(ptr + 1, squote);
+		else if (*ptr == *dquote)
+			ptr = strpbrk_esc(ptr + 1, dquote);
+		else
+			break;
+		str = ptr + 1;
+	} while (ptr);
+
+	free(_stopset);
+	return ptr;
+}
+
 /* Like strdup, but do not copy a single backslash */
 char *strdup_esc(const char *str)
 {
@@ -293,6 +321,78 @@ char *strdup_esc(const char *str)
 	return ret;
 }
 
+/* Remove backslash right before quote and return next quote address. */
+static char *remove_consumed_esc(char *str, int len, int quote)
+{
+	char *ptr = str, *end = str + len;
+
+	while (*ptr != quote && ptr < end) {
+		if (*ptr == '\\' && *(ptr + 1) == quote) {
+			memmove(ptr, ptr + 1, end - (ptr + 1));
+			/* now *ptr is `quote`. */
+			end--;
+		}
+		ptr++;
+	}
+
+	return *ptr == quote ? ptr : NULL;
+}
+
+/*
+ * Like strdup_esc, but keep quoted string as it is (and single backslash
+ * before quote is removed). If there is no closed quote, return NULL.
+ */
+char *strdup_esq(const char *str)
+{
+	char *d, *ret;
+
+	/* If there is no quote, return normal strdup_esc() */
+	d = strpbrk_esc((char *)str, "\"'");
+	if (!d)
+		return strdup_esc(str);
+
+	ret = strdup(str);
+	if (!ret)
+		return NULL;
+
+	d = ret;
+	do {
+		d = strpbrk(d, "\\\"\'");
+		if (!d)
+			break;
+
+		if (*d == '"' || *d == '\'') {
+			/* This is non-escaped quote */
+			int quote = *d;
+			int len = strlen(d + 1) + 1;
+
+			/*
+			 * Remove the start quote and remove consumed escape (backslash
+			 * before quote) and remove the end quote. If there is no end
+			 * quote, it is the input error.
+			 */
+			memmove(d, d + 1, len);
+			d = remove_consumed_esc(d, len, quote);
+			if (!d)
+				goto error;
+			memmove(d, d + 1, strlen(d + 1) + 1);
+		}
+		if (*d == '\\') {
+			memmove(d, d + 1, strlen(d + 1) + 1);
+			if (*d == '\\') {
+				/* double backslash -- keep the second one. */
+				d++;
+			}
+		}
+	} while (*d != '\0');
+
+	return ret;
+
+error:
+	free(ret);
+	return NULL;
+}
+
 unsigned int hex(char c)
 {
 	if (c >= '0' && c <= '9')
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 52cb8ba057c7..4c8bff47cfd3 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -37,6 +37,8 @@ char *asprintf__tp_filter_pids(size_t npids, pid_t *pids);
 
 char *strpbrk_esc(char *str, const char *stopset);
 char *strdup_esc(const char *str);
+char *strpbrk_esq(char *str, const char *stopset);
+char *strdup_esq(const char *str);
 
 unsigned int hex(char c);
 char *strreplace_chars(char needle, const char *haystack, const char *replace);