Small tweaks to our whitespace handling

This is still not (and likely will never be) intended to just be blindly
run and mechanically applied to all files. It tries to implement our rules
but it is not perfect and more importantly, we have parts of the code
where we intentionally break our rules for various reasons of readability
in that particular situation.

But running this against the sources files you touch often will point out
things that are wrong and should be fixed.

This fixes the indentation for continuation lines and the handling of the
for each style loops (clang 3.5 should have this built in - I'll play with
the current development version of this later).

Signed-off-by: Dirk Hohndel <dirk@hohndel.org>

.clang-format

@@ -10,6 +10,7 @@ ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ColumnLimit: 0
 IndentFunctionDeclarationAfterType: false #personal taste, good for long methods
 IndentWidth: 8
+ContinuationIndentWidth: 8
 MaxEmptyLinesToKeep: 2
 NamespaceIndentation: All
 SpaceBeforeAssignmentOperators: true
@@ -18,3 +19,4 @@ SpacesInParentheses: false
 SpacesBeforeTrailingComments: 1
 UseTab: Always
 PointerBindsToType: false
+# doesn't work, yet -> ForEachMacros: "Q_FOREACH"

scripts/whitespace.pl

@@ -3,17 +3,23 @@
 my $input = $ARGV[0];
 my $source = `clang-format $input`;
 # for_each_dive (...) and Q_FOREACH and friends...
-$source =~ s/^(.*each.*\(.*\).*)\n\s*{\s*$/$1 {/img;
+$source =~ s/(?:\G|^)(.*each.*\(.*) \* (\S.*\))$/$1 *$2/img; # if a variable is declared in the argument, '*' is an indicator for a pointer, not arithmatic
+$source =~ s/(?:\G|^)(.*each.*\(.*) \& (\S.*\))$/$1 &$2/img; # if a variable is declared in the argument, '&' is an indicator for a reference, not bit logic
+$source =~ s/(?:\G|^)(.*each[^\s(]*)\s*(\(.*)$/$1 $2/img;    # we want exactly one space between keyword and opening parenthesis '('
+$source =~ s/(?:\G|^)(.*each.*\(.*\).*)\n\s*{\s*$/$1 {/img;  # we want the opening curly brace on the same line, separated by a space
 $source =~ s/(?:\G|^)(\s+[^#\/*].*each.*\(.*\))\n(\s*)([^{}\s])/$1\n\t$2$3/img;
 
+# don't have '{' in the next line when declaring data types
 $source =~ s/^(\s*struct[^()\n]*)\n\s*{\s*$/$1 {/img;
 $source =~ s/^(\s*static\s+struct[^()\n]*)\n\s*{\s*$/$1 {/img;
 $source =~ s/^(\s*union[^()\n]*)\n\s*{\s*$/$1 {/img;
 $source =~ s/^(\s*static\s+union[^()\n]*)\n\s*{\s*$/$1 {/img;
 $source =~ s/^(\s*class.*)\n\s*{\s*$/$1 {/img;
+# a namespace shouldn't look like a function
+$source =~ s/(?:\G|^)(namespace.*)\n{/$1 {/img;
 # colon goes at the end of a line
 $source =~ s/^(\S*::\S*.*)\n\s*: /$1 : /img;
-# odd indentations from flang-format:
+# odd indentations from clang-format:
 # six spaces or four spaces after tabs (for continuation strings)
 $source =~ s/(?:\G|^)[ ]{6}/\t/mg;
 $source =~ s/(?:\G|^)(\t*)[ ]{4}"/$1\t"/mg;
@@ -23,15 +29,16 @@ $source =~ s/(?:\G|^)(\t*)[ ]{4}"/$1\t"/mg;
 # from?
 # I couldn't figure out how to make it apply to an arbitrary number of
 # intermediate lines, so I hardcoded 0 through 5 lines between the #define
-# or #id defined statements and the end of the multi line statement
+# or #if defined statements and the end of the multi line statement
 $source =~ s/^(#(?:if |)define.*)\n +([^*].*)$/$1\n\t$2/mg;
 $source =~ s/^(#(?:if |)define.*)((?:\\\n.*){1})\n +([^*].*)$/$1$2\n\t$3/mg;
 $source =~ s/^(#(?:if |)define.*)((?:\\\n.*){2})\n +([^*].*)$/$1$2\n\t$3/mg;
 $source =~ s/^(#(?:if |)define.*)((?:\\\n.*){3})\n +([^*].*)$/$1$2\n\t$3/mg;
 $source =~ s/^(#(?:if |)define.*)((?:\\\n.*){4})\n +([^*].*)$/$1$2\n\t$3/mg;
 $source =~ s/^(#(?:if |)define.*)((?:\\\n.*){5})\n +([^*].*)$/$1$2\n\t$3/mg;
-# don't put line break before the last single term argument of a
+# don't put line break before the last single term argument of a calculation
-# calculation
 $source =~ s/(?:\G|^)(.*[+-])\n\s*(\S*\;)$/$1 $2/mg;
-open (DIFF, "| diff -u $input -");
+$quotedinput = $input;
+$quotedinput =~ s|/|\\/|g;
+open (DIFF, "| diff -u $input - | sed -e 's/--- $quotedinput/--- $quotedinput.old/' | sed -e 's/+++ -/+++ $quotedinput/'");
 print DIFF $source ;