[OE-core] [PATCHv4] scripts/sstate-sysroot-cruft.sh: add simple script to find files in sysroots not tracked by sstate

[Martin Jansa]

* it's not very universal, but works with default oe-core setup and
  shows basic HOW-TO. It can be improved later.

Signed-off-by: Martin Jansa <Martin.Jansa at gmail.com>
---
 V2: added .pyo to WHITELIST
     shorter filenames
     TMPDIR
     added duplicates but not shown

 V3: use also populate-sysroot.MACHINE, manifest name for populate-sysroot
     was changed in febeaf3d1b8917b660c7279b008d8b03337568e9

 V4: dropped eglibc-initial work around, it was fixed in oe-core
                                                                                                                                                              
 scripts/sstate-sysroot-cruft.sh | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100755 scripts/sstate-sysroot-cruft.sh

diff --git a/scripts/sstate-sysroot-cruft.sh b/scripts/sstate-sysroot-cruft.sh
new file mode 100755
index 0000000..ca23dcf
--- /dev/null
+++ b/scripts/sstate-sysroot-cruft.sh
@@ -0,0 +1,34 @@
+#!/bin/sh
+
+# Used to find files installed in sysroot which are not tracked by sstate manifest
+# Update BASE
+
+BASE="/OE/oe-core"
+TMPDIR="${BASE}/tmp-eglibc"
+
+OUTPUT=${BASE}/sysroot.cruft.`date "+%s"`
+WHITELIST="\/var\/pseudo\/*[^\/]*$ \/shlibs$ \.pyc$ \.pyo$"
+
+mkdir ${OUTPUT}
+find ${TMPDIR}/sstate-control -name \*.populate-sysroot\* -o -name \*.package\* | xargs cat | grep sysroots | \
+  sed 's#/$##g; s#///*#/#g' | \
+  # work around for paths ending with / for directories and multiplied // (e.g. paths to native sysroot)
+  sort > ${OUTPUT}/master.list.all
+sort -u ${OUTPUT}/master.list.all > ${OUTPUT}/master.list # -u because some directories are listed for more recipes
+find ${TMPDIR}/sysroots/ | \
+  sort > ${OUTPUT}/sysroot.list
+
+diff ${OUTPUT}/master.list.all ${OUTPUT}/master.list > ${OUTPUT}/duplicates
+diff ${OUTPUT}/master.list ${OUTPUT}/sysroot.list > ${OUTPUT}/diff.all
+
+cp ${OUTPUT}/diff.all ${OUTPUT}/diff
+for item in ${WHITELIST}; do 
+  sed -i "/${item}/d" ${OUTPUT}/diff;
+done
+
+# too many false positives for directories
+# echo "Following files are installed in sysroot at least twice"
+# cat ${OUTPUT}/duplicates
+
+echo "Following files are installed in sysroot, but not tracked by sstate"
+cat ${OUTPUT}/diff
-- 
1.8.0