[PATCH -v2] scipts/tags.sh: Add custom sort order

[peterz@infradead.org]

One long standing annoyance I have with using vim-tags is that our tags
file is not properly sorted. That is, the sorting exhuberant Ctags does
is only on the tag itself.

The problem with that is that, for example, the tag 'mutex' appears a
mere 505 times, 492 of those are structure members. However it is _far_
more likely that someone wants the struct definition when looking for
the mutex tag than any of those members. However, due to the nature of
the sorting, the struct definition will not be first.

So add a script that does a custom sort of the tags file, taking the tag
kind into account.

The kind ordering is roughly: 'type', 'function', 'macro', 'enum', rest.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
Changes since v1:
 - removed the need for tags.unsorted by using a pipe

Due to this change 'make tags' is now actually faster than it was before
due to less sorting.

 scripts/sort-tags.awk | 79 +++++++++++++++++++++++++++++++++++++++++++++++++++
 scripts/tags.sh       | 11 +++++--
 2 files changed, 87 insertions(+), 3 deletions(-)

diff --git a/scripts/sort-tags.awk b/scripts/sort-tags.awk
new file mode 100755
index 000000000000..1eb50406c9d3
--- /dev/null
+++ b/scripts/sort-tags.awk
@@ -0,0 +1,79 @@
+#!/usr/bin/awk -f
+
+# $ ctags --list-kinds
+# C
+#   c  classes
+#   s  structure names
+#   t  typedefs
+#   g  enumeration names
+#   u  union names
+#   n  namespaces
+
+#   f  function definitions
+#   p  function prototypes [off]
+#   d  macro definitions
+
+#   e  enumerators (values inside an enumeration)
+#   m  class, struct, and union members
+#   v  variable definitions
+
+#   l  local variables [off]
+#   x  external and forward variable declarations [off]
+
+BEGIN {
+	FS = "\t"
+
+	sort = "LC_ALL=C sort"
+
+	# our sort order for C kinds:
+	order["c"] = "A"
+	order["s"] = "B"
+	order["t"] = "C"
+	order["g"] = "D"
+	order["u"] = "E"
+	order["n"] = "F"
+	order["f"] = "G"
+	order["p"] = "H"
+	order["d"] = "I"
+	order["e"] = "J"
+	order["m"] = "K"
+	order["v"] = "L"
+	order["l"] = "M"
+	order["x"] = "N"
+}
+
+# pass through header
+/^!_TAG/ {
+	print $0
+	next
+}
+
+{
+	# find 'kinds'
+	for (i = 1; i <= NF; i++) {
+		if ($i ~ /;"$/) {
+			kind = $(i+1)
+			break;
+		}
+	}
+
+	# create sort key
+	if (order[kind])
+		key = $1 order[kind];
+	else
+		key = $1 "Z";
+
+	# get it sorted
+	print key "\t" $0 |& sort
+}
+
+END {
+	close(sort, "to")
+	while ((sort |& getline) > 0) {
+		# strip key
+		sub(/[^[:space:]]*[[:space:]]*/, "")
+		print $0
+	}
+	close(sort)
+}
+
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 4e18ae5282a6..51087c3d8b1e 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -251,8 +251,10 @@ setup_regex()
 
 exuberant()
 {
+	(
+
 	setup_regex exuberant asm c
-	all_target_sources | xargs $1 -a                        \
+	all_target_sources | xargs $1				\
 	-I __initdata,__exitdata,__initconst,__ro_after_init	\
 	-I __initdata_memblock					\
 	-I __refdata,__attribute,__maybe_unused,__always_unused \
@@ -266,12 +268,15 @@ exuberant()
 	-I DEFINE_TRACE,EXPORT_TRACEPOINT_SYMBOL,EXPORT_TRACEPOINT_SYMBOL_GPL \
 	-I static,const						\
 	--extra=+fq --c-kinds=+px --fields=+iaS --langmap=c:+.h \
+	--sort=no -o -						\
 	"${regex[@]}"
 
 	setup_regex exuberant kconfig
-	all_kconfigs | xargs $1 -a                              \
-	--langdef=kconfig --language-force=kconfig "${regex[@]}"
+	all_kconfigs | xargs $1					\
+	--langdef=kconfig --language-force=kconfig --sort=no	\
+	-o - "${regex[@]}"
 
+	) | scripts/sort-tags.awk > tags
 }
 
 emacs()