#!/usr/bin/env tclsh

#
# \brief  Generate ABI symbol list for a shared library
# \author Norman Feske
# \date   2016-12-07
#
# The tool takes the shared library as argument and writes the output to
# standard output. Each line of the resulting output contains the symbol name,
# type, and size
#

# normalize sort order across platforms
set env(LC_COLLATE) C

# obtain symbol information via 'nm'
set symbols [exec nm --format posix --dynamic $argv | sort]

# obtain demangled input via c++filt
set demangled [exec c++filt << $symbols]

set demangled_lines [split $demangled "\n"]

# obtail list of blacklisted symbols
set fd [open "[file dirname $argv0]/internal_abi.list"]
set symbol_blacklist [split [read $fd] "\n"]
close $fd

# add notice that the symbols file hasn't undergone any manual inspection
puts "# Please review the symbols and remove this line."

set i 0
set output_lines {}
foreach line [split $symbols "\n"] {

	set size_hex 0
	set type "U"

	# match undefined symbol
	if {![regexp {^(\w+) U\s*$} $line dummy name]} {

		# match defined symbol, which does not always feature a value or size
		if {![regexp {^([\w.]+) (\w) *\w* ?(\w*)$} $line dummy name type size_hex]} {
			puts stderr "Error: unexpected format of line: $line"
			exit -1
		}
	}

	# decimal symbol size
	set size_dec [expr 0x0$size_hex]

	set demangled_name $name
	regexp {^(.+) \w \w+( \w+)?$} [lindex $demangled_lines $i] dummy demangled_name

	set keep 1

	#
	# Ignore undefined symbols
	#
	if {$type == "U"} { set keep 0 }

	#
	# Check if the unmangled line contains a template-argument delimiter ('<')
	# prior the first opening parenthesis. This way, template methods match but
	# signatures of non-template functions/methods that take templated
	# arguments won't. We can discard symbols for the former but not the
	# latter.
	#
	if {[regexp {^[^(]+<} $demangled_name dummy]} { set keep 0 }

	#
	# Drop weak vtable and typeinfo symbols
	#
	# Those symbols are solely used to merge vtables between the executable and
	# shared library. When linking object files that use the same types, the
	# merging saves a lot space. However, the benefit at the coarse granularity
	# of shared libraries is rather small compared to the huge inflation of the
	# ABI size caused by such symbols.
	#
	if {($type == "V") && ([regexp {^(typeinfo |vtable )} $demangled_name dummy])} {
		set keep 0 }

	#
	# Drop weak C++ symbols
	#
	# In contrast to weak C symbols, which are rarely and always deliberately
	# created, weak C++ symbols are implicitly created by the compiler for
	# inline functions.
	#
	if {[regexp {W|V} $type] && ($name != $demangled_name)} {
		set keep 0 }

	#
	# Drop weak local symbols
	#
	if {[regexp {w|v} $type]} {
		set keep 0 }

	#
	# Drop blacklisted symbols
	#
	foreach blacklisted_symbol $symbol_blacklist {
		if {$name == $blacklisted_symbol} { set keep 0 } }

	# write result
	if {$keep} {

		#
		# Annotate the size for global data symbols where the size is needed to
		# create copy relations (ARM EABI) in the binary that is linked against
		# the shared library. For each global read-only data symbol found in
		# the shared object, the linker reserves space (according to the
		# symbol's size) in the binary's BSS segment. At runtime, the dynamic
		# linker copies the data from the shared library's symbol into the
		# binary's BSS.
		#
		if {($type == "D") || ($type == "B") || ($type == "R")} {
			puts "$name $type $size_dec"
		} else {
			puts "$name $type"
		}
	}
	incr i
}