From 3d02b23af5d7ae16d71bcf9823ee63b4fec1d29a Mon Sep 17 00:00:00 2001
From: Andreas Kling <kling@serenityos.org>
Date: Wed, 20 May 2020 14:23:30 +0200
Subject: [PATCH] Revert "Toolchain: Don't pre-build LibC and LibM, nor
 pre-install their headers"

This reverts commit 4e051c6c15f25b58ee67127a9e4bd5e7a8684fea.
---
 Toolchain/BuildIt.sh                 | 14 +++++++
 Toolchain/ComputeDependenciesHash.sh | 60 +++++++++++++++++++++++++++-
 2 files changed, 72 insertions(+), 2 deletions(-)

diff --git a/Toolchain/BuildIt.sh b/Toolchain/BuildIt.sh
index f37704b96e..b50ed23f22 100755
--- a/Toolchain/BuildIt.sh
+++ b/Toolchain/BuildIt.sh
@@ -225,6 +225,20 @@ pushd "$DIR/Build/"
         echo "XXX install gcc and libgcc"
         "$MAKE" install-gcc install-target-libgcc || exit 1
 
+        echo "XXX serenity libc and libm"
+        mkdir -p "$BUILD"
+        pushd "$BUILD"
+            cmake ..
+            "$MAKE" LibC
+            install -D Libraries/LibC/libc.a Libraries/LibM/libm.a Libraries/LibCxx/libstdc++.a Root/usr/lib/
+            SRC_ROOT=$(realpath "$DIR"/..)
+            for header in "$SRC_ROOT"/Libraries/Lib{C,M}/**/*.h; do
+                target=$(echo "$header" | sed -e "s@$SRC_ROOT/Libraries/LibC@@" -e "s@$SRC_ROOT/Libraries/LibM@@")
+                install -D "$header" "Root/usr/include/$target"
+            done
+            unset SRC_ROOT
+        popd
+
         if [ "$(uname -s)" = "OpenBSD" ]; then
             cd "$DIR/Local/libexec/gcc/i686-pc-serenity/$GCC_VERSION" && ln -sf liblto_plugin.so.0.0 liblto_plugin.so
         fi
diff --git a/Toolchain/ComputeDependenciesHash.sh b/Toolchain/ComputeDependenciesHash.sh
index c6cb714e2b..0da2cf2a76 100755
--- a/Toolchain/ComputeDependenciesHash.sh
+++ b/Toolchain/ComputeDependenciesHash.sh
@@ -23,11 +23,67 @@ function finish {
 }
 trap finish EXIT
 
-# Patches and the scripts are the only things that affect the build of the toolchain
-FILE_LIST=$(find Toolchain/Patches -name "*.patch")
+# libstdc++ depends on libc and libm, so we pessimistically assume it depends
+# on *all* of their implementation and recursive dependencies.
+# Scan all files for potential dependencies.
+# Thinking in graphs, this computes the edge list:
+cat <(find AK/ Libraries/ Services/ Kernel/ -name '*.h') \
+    <(find Libraries/LibC/ Libraries/LibM/ -name '*.cpp' ! -name 'Test*.cpp' ) | \
+    xargs grep -F '#include ' | \
+    sed -r \
+        -e 's,^(.*/)([^/]+:)#include "(.*)",\1\2\1\3,' \
+        -e 's^#include <(Kernel/.*)>^\1^' \
+        -e 's^#include <(AK/.*)>^\1^' \
+        -e 's^#include <(Lib[A-Za-z]+/.*)>^Libraries/\1^' \
+        -e 's^#include <((bits|netinet|sys|arpa|net)/.*)>^Libraries/LibC/\1^' \
+        -e 's^#include <fd_set.h>^Libraries/LibC/fd_set.h^' \
+        -e 's^#include <([a-z]{3,10}(_numbers)?\.h)>^Libraries/LibC/\1^' \
+        -e 's^#include <([A-Z][a-z]+Server/.*)>^Services/\1^' \
+        -e 's^#include <(.*)>^UNRESOLVED_I/\1^' \
+        -e 's^#include "(.*)"^UNRESOLVED_L/\1^' > "${DEPLIST_FILE}"
+# Some #include's cannot be resolved, like <chrono>. However, these are only
+# a problem if they turn up as a transitive dependency of libc and libm.
+# We will check for that when the time comes.
+
+# The initial guess is pessimistic: *all* of libc and libm.
+FILE_LIST=$(find Libraries/LibC/ Libraries/LibM/ \( -name '*.cpp' -o -name '*.c' -o -name '*.h' \) ! -name 'Test*')
+echo "$0: Exploring dependencies of libstdc++" >&2
+FILE_LIST_COMPLETE="n"
+# In each iteration, we extend FILE_LIST by the dependencies not listed yet in
+# FILE_LIST.  Note that the results are always semantically the same,
+# but the order depends on the initial `find` runs.
+for _ in $(seq 10) ; do
+    FILE_REGEX=$(echo "${FILE_LIST}" | sed -zr -e 's,\n$,,' -e 's,\.,\\.,g' -e 's,\n,|,g')
+    FURTHER_FILE_LIST=$(grep -P "^(${FILE_REGEX}):" "${DEPLIST_FILE}" | grep -Pv ":(${FILE_REGEX})\$" | sed -re 's,^.*:(.*)$,\1,' | sort -u)
+    if [ -n "${FURTHER_FILE_LIST}" ] ; then
+        # FILE_LIST should grow to a maximum of "number of all .cpp and .c and .h files",
+        # i.e. roughly 700 lines.  This should be managable, even as the project grows.
+        FILE_LIST="${FILE_LIST}
+${FURTHER_FILE_LIST}"
+    else
+        FILE_LIST_COMPLETE="y"
+        break
+    fi
+done
+FURTHER_FILE_LIST=""
+FILE_REGEX=""
+if [ "${FILE_LIST_COMPLETE}" != "y" ] ; then
+    # Dependency chains might grow very long. Also, if for some reason we fail
+    # to filter out the already listed files, the FILE_LIST would grow
+    # exponentially. Both of these unpleasant cases are handled by capping the
+    # iteration count to 10 and giving up:
+    echo "$0: Dependencies don't seem to converge, giving up." >&2
+    exit 1
+fi
 
 # Sort for reproducability,
 FILE_LIST=$(echo "${FILE_LIST}" | LC_ALL=C sort -u)
+if grep -F 'UNRESOLVED' <<EOLIST >&2 ; then
+${FILE_LIST}
+EOLIST
+    echo "$0: Unresolved dependency, giving up."
+    exit 1
+fi
 
 echo "$0: Computing hashes" >&2
 # "$@" is the md5sum invocation. The piping might hide non-zero exit-codes,