rfc patch PR32760: find-debuginfo for static libraries

[Frank Ch. Eigler]

Hi -

This patch appears to make unstripped static libraries work, in the
sense of PR32760, as mentioned in RHBZ1395280.  I'm trying to figure
out how to test it automatically; there are no current tests for the
script in the debugedit testsuite.


Author: Frank Ch. Eigler <fche@redhat.com>
Date:   Thu Mar 6 14:45:36 2025 -0500

    PR32760: find-debuginfo: handle static libraries
    
    Formerly, static .a libraries with debuginfo were ignored by
    find-debuginfo.  If unstripped, then the raw build-directory paths in
    them would leak into the downstream package.  New code in
    find-debuginfo looks for archive ".a" files in the build tree, and
    runs debugedit only to enumerate and rewrite source paths.  This
    allows ultimate users of the .a files to receive debuginfo, with
    usable (and debuginfod-resolvable) source file paths.
    
    This works by having find-debuginfo find .a files, extracting all
    the .o files, individually running debugedit, then repacking the
    files back into the .a.  do_file() delegates to do_ar_file(),
    doing rather less work than for .so/exec files.
    
    Signed-off-by: Frank Ch. Eigler <fche@redhat.com>

diff --git a/scripts/find-debuginfo.in b/scripts/find-debuginfo.in
index 4cc49f2f8cd0..494d68e05797 100755
--- a/scripts/find-debuginfo.in
+++ b/scripts/find-debuginfo.in
@@ -4,7 +4,7 @@
 # find-debuginfo - automagically generate debug info and file list
 # for inclusion in package file lists.
 
-# Copyright (C) 2002-2021 rpm and debugedit contributors
+# Copyright (C) 2002-2025 rpm and debugedit contributors
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -28,7 +28,7 @@ automagically generates debug info and file lists
 Options:
 [--strict-build-id] [-g] [-r] [-m] [-i] [-n] [-q] [-v]
 [--keep-section SECTION] [--remove-section SECTION]
-[--g-libs]
+[--g-libs] [-a]
 [-j N] [--jobs N]
 [-o debugfiles.list]
 [-S debugsourcefiles.list]
@@ -95,6 +95,11 @@ will be called /usr/debug/src/<BASE>.  This makes sure the debug source
 dirs are unique between package version, release and achitecture (Use
 --unique-debug-src-base "%{name}-%{VERSION}-%{RELEASE}.%{_arch}")
 
+If -a is given, then static libraries will be ignored.  Otherwise,
+they receive only with source-path rewriting and collection.  They are
+not stripped, since they have no persistent build-ids to accommodate
+eventual reunification.
+
 The -q or --quiet flag silences all non-error output from the script.
 The -v or --verbose flag add more output for all files processed.
 When neither -q or -v is given then only output for each pass is given.
@@ -167,6 +172,9 @@ quiet=false
 # add more non-error output
 verbose=false
 
+# process static libraries
+process_ar=true
+
 BUILDDIR=.
 out=debugfiles.list
 srcout=
@@ -260,6 +268,9 @@ while [ $# -gt 0 ]; do
     srcout=$2
     shift
     ;;
+  -a)
+    process_ar=false
+    ;;
   -q|--quiet)
     quiet=true
     verbose=false
@@ -443,10 +454,14 @@ trap 'rm -rf "$temp"' EXIT
 # Build a list of unstripped ELF files and their hardlinks
 touch "$temp/primary"
 touch "$temp/linked"
-find "$RPM_BUILD_ROOT" ! -path "${debugdir}/*.debug" -type f \
-     		     \( -perm -0100 -or -perm -0010 -or -perm -0001 \) \
-		     -print | LC_ALL=C sort |
-file -N -f - | sed -n -e 's/^\(.*\):[ 	]*.*ELF.*, not stripped.*/\1/p' |
+(find "$RPM_BUILD_ROOT" ! -path "${debugdir}/*.debug" -type f \
+      \( -perm -0100 -or -perm -0010 -or -perm -0001 \) \
+      -print | 
+     file -N -f - | sed -n -e 's/^\(.*\):[     ]*.*ELF.*, not stripped.*/\1/p';
+ # plus static libraries
+ $process_ar && find "$RPM_BUILD_ROOT" -type f -name '*.a' -print |
+         file -N -f - | sed -n -e 's/^\(.*\):[         ]*current ar archive.*/\1/p'
+) | LC_ALL=C sort |
 xargs --no-run-if-empty stat -c '%h %D_%i %n' |
 while read nlinks inum f; do
   if [ $nlinks -gt 1 ]; then
@@ -461,11 +476,54 @@ while read nlinks inum f; do
   echo "$nlinks $inum $f" >>"$temp/primary"
 done
 
+
+# Handle ELF archives
+do_ar_file()
+{
+  local nlinks=$1 inum=$2 f=$3 id link linked
+
+  artemp="$temp/ar.$inum"
+  mkdir -p "$artemp"
+  (cd "$artemp"; ar x "$f")
+
+  # See also cpio SOURCEFILE copy. Directories must match up.
+  debug_base_name="$RPM_BUILD_DIR"
+  debug_dest_name="/usr/src/debug"
+  if [ ! -z "$unique_debug_src_base" ]; then
+    debug_base_name="$BUILDDIR"
+    debug_dest_name="/usr/src/debug/${unique_debug_src_base}"
+  fi
+
+  find "$artemp" -type f -type f -print | file -N -f - |
+      sed -n -e 's/^\(.*\):[ 	]*.*ELF.*, not stripped.*/\1/p' |
+      while read objfile; do
+          $verbose && echo "processing ${f#$RPM_BUILD_DIR/} ${objfile#$artemp/}"
+          # nb: debugedit -l writes to $SOURCEFILES in O_APPEND mode, so can be reused.
+          debugedit -b "$debug_base_name" -d "$debug_dest_name" \
+		    -l "$SOURCEFILE" "$objfile"
+          # replace old object with new in archive, nb: relative path names
+          (cd "$artemp"; ar r "$f" ${objfile#$artemp/}) 
+      done
+
+  $verbose && echo found $(tr -dc '\0' < "$SOURCEFILE" | wc -c) source files
+
+  # NB: no need to strip or dwz-compress or gdbindex or
+  # ELFBINSFILE-collect objects / archives.  These operations only
+  # make sense on the final binaries that the static archives are
+  # linked into.
+}
+
+
 # Strip ELF binaries
 do_file()
 {
   local nlinks=$1 inum=$2 f=$3 id link linked
 
+  if expr "$f" : "^.*\.a$" >/dev/null; then # treat as static archive
+      do_ar_file "$1" "$2" "$3"
+      return
+  fi
+
   get_debugfn "$f"
   [ -f "${debugfn}" ] && return 0