strbuf: split out logic to humanise byte values

In a subsequent commit, byte size values displayed in table output for
the git-repo(1) "structure" subcommand will be shown in a more
human-readable format with the appropriate unit prefixes. For this
usecase, the downscaled values and unit strings must be handled
separately to ensure proper column alignment.

Split out logic from strbuf_humanise() to downscale byte values and
determine the corresponding unit prefix into a separate humanise_bytes()
function that provides seperate value and unit strings.

Note that the "byte" string in "t/helper/test-simple-ipc.c" is unmarked
for translation here so that it doesn't conflict with the newly defined
plural "byte/bytes" translation and instead uses it.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: jltobler

strbuf.c

@@ -836,55 +836,61 @@ void strbuf_addstr_urlencode(struct strbuf *sb, const char *s,
 	strbuf_add_urlencode(sb, s, strlen(s), allow_unencoded_fn);
 }
 
-static void strbuf_humanise(struct strbuf *buf, off_t bytes,
-				 int humanise_rate)
+void humanise_bytes(off_t bytes, char **value, const char **unit,
+		    unsigned flags)
 {
+	int humanise_rate = flags & HUMANISE_RATE;
+
 	if (bytes > 1 << 30) {
-		strbuf_addf(buf,
-				humanise_rate == 0 ?
-					/* TRANSLATORS: IEC 80000-13:2008 gibibyte */
-					_("%u.%2.2u GiB") :
-					/* TRANSLATORS: IEC 80000-13:2008 gibibyte/second */
-					_("%u.%2.2u GiB/s"),
-			    (unsigned)(bytes >> 30),
-			    (unsigned)(bytes & ((1 << 30) - 1)) / 10737419);
+		*value = xstrfmt(_("%u.%2.2u"), (unsigned)(bytes >> 30),
+				 (unsigned)(bytes & ((1 << 30) - 1)) / 10737419);
+		/* TRANSLATORS: IEC 80000-13:2008 gibibyte/second and gibibyte */
+		*unit = humanise_rate ? _("GiB/s") : _("GiB");
 	} else if (bytes > 1 << 20) {
-		unsigned x = bytes + 5243;  /* for rounding */
-		strbuf_addf(buf,
-				humanise_rate == 0 ?
-					/* TRANSLATORS: IEC 80000-13:2008 mebibyte */
-					_("%u.%2.2u MiB") :
-					/* TRANSLATORS: IEC 80000-13:2008 mebibyte/second */
-					_("%u.%2.2u MiB/s"),
-			    x >> 20, ((x & ((1 << 20) - 1)) * 100) >> 20);
+		unsigned x = bytes + 5243; /* for rounding */
+		*value = xstrfmt(_("%u.%2.2u"), x >> 20,
+				 ((x & ((1 << 20) - 1)) * 100) >> 20);
+		/* TRANSLATORS: IEC 80000-13:2008 mebibyte/second and mebibyte */
+		*unit = humanise_rate ? _("MiB/s") : _("MiB");
 	} else if (bytes > 1 << 10) {
-		unsigned x = bytes + 5;  /* for rounding */
-		strbuf_addf(buf,
-				humanise_rate == 0 ?
-					/* TRANSLATORS: IEC 80000-13:2008 kibibyte */
-					_("%u.%2.2u KiB") :
-					/* TRANSLATORS: IEC 80000-13:2008 kibibyte/second */
-					_("%u.%2.2u KiB/s"),
-			    x >> 10, ((x & ((1 << 10) - 1)) * 100) >> 10);
+		unsigned x = bytes + 5; /* for rounding */
+		*value = xstrfmt(_("%u.%2.2u"), x >> 10,
+				 ((x & ((1 << 10) - 1)) * 100) >> 10);
+		/* TRANSLATORS: IEC 80000-13:2008 kibibyte/second and kibibyte */
+		*unit = humanise_rate ? _("KiB/s") : _("KiB");
 	} else {
-		strbuf_addf(buf,
-				humanise_rate == 0 ?
-					/* TRANSLATORS: IEC 80000-13:2008 byte */
-					Q_("%u byte", "%u bytes", bytes) :
-					/* TRANSLATORS: IEC 80000-13:2008 byte/second */
-					Q_("%u byte/s", "%u bytes/s", bytes),
-				(unsigned)bytes);
+		*value = xstrfmt("%u", (unsigned)bytes);
+		*unit = humanise_rate ?
+			       /* TRANSLATORS: IEC 80000-13:2008 byte/second */
+			       Q_("byte/s", "bytes/s", bytes) :
+			       /* TRANSLATORS: IEC 80000-13:2008 byte */
+			       Q_("byte", "bytes", bytes);
 	}
 }
 
+static void strbuf_humanise(struct strbuf *buf, off_t bytes, unsigned flags)
+{
+	char *value;
+	const char *unit;
+
+	humanise_bytes(bytes, &value, &unit, flags);
+
+	/*
+	 * TRANSLATORS: The first argument is the number string. The second
+	 * argument is the unit string (i.e. "12.34 MiB/s").
+	 */
+	strbuf_addf(buf, _("%s %s"), value, unit);
+	free(value);
+}
+
 void strbuf_humanise_bytes(struct strbuf *buf, off_t bytes)
 {
 	strbuf_humanise(buf, bytes, 0);
 }
 
 void strbuf_humanise_rate(struct strbuf *buf, off_t bytes)
 {
-	strbuf_humanise(buf, bytes, 1);
+	strbuf_humanise(buf, bytes, HUMANISE_RATE);
 }
 
 int printf_ln(const char *fmt, ...)

strbuf.h

@@ -367,6 +367,20 @@ void strbuf_addbuf_percentquote(struct strbuf *dst, const struct strbuf *src);
  */
 void strbuf_add_percentencode(struct strbuf *dst, const char *src, int flags);
 
+enum humanise_flags {
+	/*
+	 * Use rate based units for humanised values.
+	 */
+	HUMANISE_RATE = (1 << 0),
+};
+
+/**
+ * Converts the given byte size into a downscaled human-readable value and
+ * corresponding unit as two separate strings.
+ */
+void humanise_bytes(off_t bytes, char **value, const char **unit,
+		    unsigned flags);
+
 /**
  * Append the given byte size as a human-readable string (i.e. 12.23 KiB,
  * 3.50 MiB).

t/helper/test-simple-ipc.c

@@ -603,7 +603,12 @@ int cmd__simple_ipc(int argc, const char **argv)
 		OPT_INTEGER(0, "bytecount", &cl_args.bytecount, N_("number of bytes")),
 		OPT_INTEGER(0, "batchsize", &cl_args.batchsize, N_("number of requests per thread")),
 
-		OPT_STRING(0, "byte", &bytevalue, N_("byte"), N_("ballast character")),
+		/*
+		 * The "byte" string here is not marked for translation and
+		 * instead relies on translation in strbuf.c:humanise_bytes() to
+		 * avoid conflict with the plural form.
+		 */
+		OPT_STRING(0, "byte", &bytevalue, "byte", N_("ballast character")),
 		OPT_STRING(0, "token", &cl_args.token, N_("token"), N_("command token to send to the server")),
 
 		OPT_END()