From a7e6f3f07258e02155f20be4068249b27b837f25 Mon Sep 17 00:00:00 2001
From: Michael Richters <gedankenexperimenter@gmail.com>
Date: Thu, 7 Apr 2022 14:04:10 -0500
Subject: [PATCH] When running IWYU, process source files before headers

Suppose the following:

`foo.cpp` refers to the symbol `Bar`, declared in `bar.h`.
`foo.h` includes `bar.h`.
`foo.cpp` includes `foo.h`, but not `bar.h`.
`foo.h` does not refer to any symbols declared in `bar.h`.

If we process `foo.h` first, `#include "bar.h"` will be removed, causing IWYU to
fail with an error when it tries to process `foo.cpp`, but if we process them in
the other order, `foo.cpp` will get that include before it gets removed from
`foo.h`.  This change sorts the files to be processed, putting all cpp files
first, then all header files, minimizing that problem.

We could do even better by saving the results from `include-what-you-use` for
every file, then going back and calling `fix_includes.py` on each of them, but I
don't think it's worth it.

Signed-off-by: Michael Richters <gedankenexperimenter@gmail.com>
---
 bin/fix-header-includes |  4 +++-
 bin/iwyu.py             | 20 ++++++++++++++++----
 2 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/bin/fix-header-includes b/bin/fix-header-includes
index c25d2706..13c105cb 100755
--- a/bin/fix-header-includes
+++ b/bin/fix-header-includes
@@ -3,4 +3,6 @@
 : "${KALEIDOSCOPE_DIR:=$(pwd)}"
 cd "${KALEIDOSCOPE_DIR}" || exit 1
 
-git ls-files -m | grep -E '\.(h|cpp)$' | xargs "${KALEIDOSCOPE_DIR}"/bin/iwyu.py
+# Process sources first, then headers to minimize errors from removed includes
+git ls-files -m | grep -E '\.(cpp|ino)$' | xargs "${KALEIDOSCOPE_DIR}"/bin/iwyu.py
+git ls-files -m | grep -E '\.h$' | xargs "${KALEIDOSCOPE_DIR}"/bin/iwyu.py
diff --git a/bin/iwyu.py b/bin/iwyu.py
index 15cd81a2..93c6372e 100755
--- a/bin/iwyu.py
+++ b/bin/iwyu.py
@@ -296,12 +296,24 @@ def main():
 
     # ----------------------------------------------------------------------
     regex = re.compile(opts.regex)
+    # Process source files first, then header files, because a source file might have been
+    # relying on a header included by its associated header, but which that header does not
+    # need on its own.  In this case, if we process the header first, IWYU won't be able to
+    # parse the source file, and we'll get an error, but if we do them in the other order,
+    # it'll be fine.
+    source_files = []
+    header_files = []
+    for target_file in (_ for t in targets for _ in build_target_list(t, regex)):
+        if target_file.endswith('.cpp') or target_file.endswith('.ino'):
+            source_files.append(target_file)
+        else:
+            header_files.append(target_file)
     exit_code = 0
-    for src in (_ for t in targets for _ in build_target_list(t, regex)):
-        if src in ignores:
-            logging.info("Skipping ignored file: %s", os.path.relpath(src))
+    for target_file in source_files + header_files:
+        if target_file in ignores:
+            logging.info("Skipping ignored file: %s", os.path.relpath(target_file))
             continue
-        if not run_iwyu(os.path.relpath(src), iwyu_cmd, fix_includes_cmd):
+        if not run_iwyu(os.path.relpath(target_file), iwyu_cmd, fix_includes_cmd):
             exit_code = 1
     return exit_code