From: Lennart Poettering <lennart@poettering.net>
Date: Wed, 14 Jun 2023 08:09:22 +0000 (+0200)
Subject: time-util,socket: accept both kinds of unicode µ symbols
X-Git-Tag: v254-rc1~210^2~1
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=d0a6d7c4d1285d6af2be299a466c964f0c5991a2;p=thirdparty%2Fsystemd.git

time-util,socket: accept both kinds of unicode µ symbols

Apparently there are two µ symbols, accept both when parsing.

One is the greek small letter mu (μ) the other is the micro sign (µ).
Unicode recommendation considers both equivalent, and says use of greek
small letter mu is preferred. See:

https://www.unicode.org/reports/tr25

Hence accept both when parsing.

Inspired by: #28029
---

diff --git a/src/basic/time-util.c b/src/basic/time-util.c
index f124e6f0162..0ab2a81059a 100644
--- a/src/basic/time-util.c
+++ b/src/basic/time-util.c
@@ -1046,7 +1046,8 @@ static const char* extract_multiplier(const char *p, usec_t *ret) {
                 { "y",       USEC_PER_YEAR   },
                 { "usec",    1ULL            },
                 { "us",      1ULL            },
-                { "µs",      1ULL            },
+                { "μs",      1ULL            }, /* U+03bc (aka GREEK SMALL LETTER MU) */
+                { "µs",      1ULL            }, /* U+b5 (aka MICRO SIGN) */
         };
 
         assert(p);
@@ -1224,7 +1225,8 @@ static const char* extract_nsec_multiplier(const char *p, nsec_t *ret) {
                 { "y",       NSEC_PER_YEAR   },
                 { "usec",    NSEC_PER_USEC   },
                 { "us",      NSEC_PER_USEC   },
-                { "µs",      NSEC_PER_USEC   },
+                { "μs",      NSEC_PER_USEC   }, /* U+03bc (aka GREEK LETTER MU) */
+                { "µs",      NSEC_PER_USEC   }, /* U+b5 (aka MICRO SIGN) */
                 { "nsec",    1ULL            },
                 { "ns",      1ULL            },
                 { "",        1ULL            }, /* default is nsec */
@@ -1701,9 +1703,9 @@ TimestampStyle timestamp_style_from_string(const char *s) {
         t = (TimestampStyle) string_table_lookup(timestamp_style_table, ELEMENTSOF(timestamp_style_table), s);
         if (t >= 0)
                 return t;
-        if (streq_ptr(s, "µs"))
+        if (STRPTR_IN_SET(s, "µs", "μs")) /* acccept both µ symbols in unicode, i.e. micro symbol + greek small letter mu. */
                 return TIMESTAMP_US;
-        if (streq_ptr(s, "µs+utc"))
+        if (STRPTR_IN_SET(s, "µs+utc", "μs+utc"))
                 return TIMESTAMP_US_UTC;
         return t;
 }
diff --git a/src/core/socket.c b/src/core/socket.c
index 8e7797139bf..e4c1f5a793f 100644
--- a/src/core/socket.c
+++ b/src/core/socket.c
@@ -3519,7 +3519,7 @@ SocketTimestamping socket_timestamping_from_string_harder(const char *p) {
          * too. */
         if (streq(p, "nsec"))
                 return SOCKET_TIMESTAMPING_NS;
-        if (STR_IN_SET(p, "usec", "µs"))
+        if (STR_IN_SET(p, "usec", "µs", "μs")) /* Accept both small greek letter mu + micro sign unicode codepoints */
                 return SOCKET_TIMESTAMPING_US;
 
         r = parse_boolean(p);
diff --git a/src/test/test-time-util.c b/src/test/test-time-util.c
index 235c6cf1642..a67bfc87342 100644
--- a/src/test/test-time-util.c
+++ b/src/test/test-time-util.c
@@ -35,7 +35,9 @@ TEST(parse_sec) {
         assert_se(u == 700 * USEC_PER_MSEC);
         assert_se(parse_sec("23us", &u) >= 0);
         assert_se(u == 23);
-        assert_se(parse_sec("23µs", &u) >= 0);
+        assert_se(parse_sec("23μs", &u) >= 0); /* greek small letter mu */
+        assert_se(u == 23);
+        assert_se(parse_sec("23µs", &u) >= 0); /* micro symbol */
         assert_se(u == 23);
         assert_se(parse_sec("infinity", &u) >= 0);
         assert_se(u == USEC_INFINITY);