Add a couple of helper tools to prepare git commits by removing all trailing blank lines, and replacing tabs with indents. These tools default to looking only at modified files, but can also be used to scan the entire directory tree via the --all option.

Signed-off-by: Ralph Castain <rhc@open-mpi.org>

contrib/fix_indent.pl

@@ -10,6 +10,7 @@
 #                         University of Stuttgart.  All rights reserved.
 # Copyright (c) 2004-2005 The Regents of the University of California.
 #                         All rights reserved.
+# Copyright (c) 2016      Intel, Inc.  All rights reserved.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
@@ -18,6 +19,8 @@
 #
 #To keep brian happy
 
+use Text::Tabs;
+
 if (scalar(@ARGV) != 1) {
     print "We need a source tree path\n";
     exit(3);
@@ -31,12 +34,11 @@ while(<HEADERS>) {
     $file_name = $_;
     print $file_name;
     open(FILE, "$file_name");
-    while(<FILE>) {
-        s/^(#)([\s|\t]*)(\w)/$1$3/;
-        print TEMP;
-    }
-    close(TEMP);
+    my @lines_with_tabs = <FILE>;
     close(FILE);
+    my @expanded_lines = expand(@lines_with_tabs);
+    print TEMP join("\n",@expanded_lines),"\n";
+    close(TEMP);
     system("mv temp.txt $file_name");
 }
 close(HEADERS);
@@ -47,12 +49,11 @@ while(<SOURCES>) {
     $file_name = $_;
     print $file_name;
     open(FILE, "$file_name");
-    while(<FILE>) {
-        s/^(#)([\s|\t]*)(\w)/$1$3/;
-        print TEMP;
-    }
-    close(TEMP);
+    my @lines_with_tabs = <FILE>;
     close(FILE);
+    my @expanded_lines = expand(@lines_with_tabs);
+    print TEMP join("\n",@expanded_lines),"\n";
+    close(TEMP);
     system("mv temp.txt $file_name");
 }
 close(SOURCES);

contrib/purge-tab-indents.pl

@@ -0,0 +1,168 @@
+#!/usr/bin/perl -w
+
+use strict;
+use Cwd;
+use File::Basename;
+use Text::Tabs;
+use Getopt::Long;
+
+# Set to true if the script should merely check for up-to-date copyrights.
+# Will exit with status 111 if there are out of date copyrights which this
+# script can correct.
+my $CHECK_ONLY = 0;
+# used by $CHECK_ONLY logic for bookeeping
+my $would_replace = 0;
+
+# Set to true to suppress most informational messages.  Only out of date files
+# will be printed.
+my $QUIET = 0;
+
+# Set to true if we just want to see the help message
+my $HELP = 0;
+
+# Set to true if we want to strip blank lines from all files
+my $ALL = 0;
+
+GetOptions(
+    "help" => \$HELP,
+    "quiet" => \$QUIET,
+    "check-only" => \$CHECK_ONLY,
+    "all" => \$ALL,
+) or die "unable to parse options, stopped";
+
+if ($HELP) {
+    print <<EOT;
+$0 [options]
+
+--help | -h          This help message
+--quiet | -q         Only output critical messages to stdout
+--check-only         exit(111) if there are modified files with trailing blank lines
+--all                Strip trailing blank lines from all fines, even those not modified
+EOT
+    exit(0);
+}
+
+#-------------------------------------------------------------------------------
+# predeclare sub for print-like syntax
+sub quiet_print {
+    unless ($QUIET) {
+        print @_;
+    }
+}
+
+#-------------------------------------------------------------------------------
+
+my @exts = qw(.h .c);
+
+# Find the top-level OMPI source tree dir
+my $start = cwd();
+my $top = $start;
+while (! -f "$top/AUTHORS") {
+    chdir("..");
+    $top = cwd();
+    die "Can't find top-level directory"
+        if ($top eq "/");
+}
+chdir($start);
+
+my @files = find_modified_files();
+
+if ($#files < 0) {
+    exit(0);
+}
+
+my $fh;
+
+# Examine each of the files and purge any tabs
+foreach my $f (@files) {
+    my ($name, $dir, $ext) = fileparse($f, @exts);
+
+    if ($ext !~ /h/ && $ext !~ /c/) {
+        next;
+    }
+
+    print "FILE: ", $f, "\n";
+
+    open(FILE, "$f");
+    my @lines_with_tabs = <FILE>;
+    close(FILE);
+
+    my @expanded_lines = expand(@lines_with_tabs);
+    open(TEMP, ">temp.txt");
+    print TEMP join("\n",@expanded_lines),"\n";
+    close(TEMP);
+    system("mv temp.txt $f");
+}
+
+# Returns a list of file names (relative to pwd) which the VCS considers to be modified.
+sub find_modified_files {
+    my @files = ();
+
+    # Number of path entries to remove from ${top}-relative paths.
+    # (--show-cdup either returns the empty string or sequence of "../"
+    # entries, always ending in a "/")
+    my $n_strip = scalar(split(m!/!, scalar(`git rev-parse --show-cdup`))) - 1;
+
+    # "." restricts scope, but does not get us relative path names
+    my $cmd = "git status -z --porcelain --untracked-files=no .";
+    my $lines = `$cmd`;
+
+    # From git-status(1):
+    # X          Y     Meaning
+    # -------------------------------------------------
+    #           [MD]   not updated
+    # M        [ MD]   updated in index
+    # A        [ MD]   added to index
+    # D         [ M]   deleted from index
+    # R        [ MD]   renamed in index
+    # C        [ MD]   copied in index
+    # [MARC]           index and work tree matches
+    # [ MARC]     M    work tree changed since index
+    # [ MARC]     D    deleted in work tree
+    # -------------------------------------------------
+    # D           D    unmerged, both deleted
+    # A           U    unmerged, added by us
+    # U           D    unmerged, deleted by them
+    # U           A    unmerged, added by them
+    # D           U    unmerged, deleted by us
+    # A           A    unmerged, both added
+    # U           U    unmerged, both modified
+    # -------------------------------------------------
+    # ?           ?    untracked
+    # -------------------------------------------------
+    my $s1 = "";
+    my $s2 = "";
+    my $fullname = "";
+    foreach my $line (split /\x{00}/, $lines) {
+        my $keep = 0;
+        unless (($s1, $s2, $fullname) = $line =~ m/^(.)(.) (.*)$/) {
+            next;
+        }
+
+        if ($ALL) {
+            $keep = 1;
+        } else {
+            # ignore all merge cases
+            next if ($s1 eq "D" and $s2 eq "D");
+            next if ($s1 eq "A" and $s2 eq "A");
+            next if ($s1 eq "U" or $s2 eq "U");
+
+            # only update for actually added/modified cases, no copies,
+            # renames, etc.
+            $keep = 1 if ($s1 eq "M" or $s2 eq "M");
+            $keep = 1 if ($s1 eq "A");
+        }
+
+        if ($keep) {
+            my $relname = $fullname;
+            $relname =~ s!^([^/]*/){$n_strip}!!g;
+
+            print "RELNAME", $relname, "\n";
+            push @files, $relname
+                if (-f $relname);
+        }
+    }
+    return @files;
+}
+
+exit 0;

contrib/purge-trailing-blank-lines.pl

@@ -0,0 +1,172 @@
+#!/usr/bin/perl -w
+
+use strict;
+use Cwd;
+use Getopt::Long;
+
+# Set to true if the script should merely check for up-to-date copyrights.
+# Will exit with status 111 if there are out of date copyrights which this
+# script can correct.
+my $CHECK_ONLY = 0;
+# used by $CHECK_ONLY logic for bookeeping
+my $would_replace = 0;
+
+# Set to true to suppress most informational messages.  Only out of date files
+# will be printed.
+my $QUIET = 0;
+
+# Set to true if we just want to see the help message
+my $HELP = 0;
+
+# Set to true if we want to strip blank lines from all files
+my $ALL = 0;
+
+GetOptions(
+    "help" => \$HELP,
+    "quiet" => \$QUIET,
+    "check-only" => \$CHECK_ONLY,
+    "all" => \$ALL,
+) or die "unable to parse options, stopped";
+
+if ($HELP) {
+    print <<EOT;
+$0 [options]
+
+--help | -h          This help message
+--quiet | -q         Only output critical messages to stdout
+--check-only         exit(111) if there are modified files with trailing blank lines
+--all                Strip trailing blank lines from all fines, even those not modified
+EOT
+    exit(0);
+}
+
+#-------------------------------------------------------------------------------
+# predeclare sub for print-like syntax
+sub quiet_print {
+    unless ($QUIET) {
+        print @_;
+    }
+}
+
+#-------------------------------------------------------------------------------
+
+# Find the top-level source tree dir
+my $start = cwd();
+my $top = $start;
+while (! -f "$top/AUTHORS") {
+    chdir("..");
+    $top = cwd();
+    die "Can't find top-level directory"
+        if ($top eq "/");
+}
+chdir($start);
+
+my @files = find_modified_files();
+
+if ($#files < 0) {
+    exit(0);
+}
+
+my $fh;
+
+# Examine each of the files and remove trailing blank lines
+foreach my $f (@files) {
+    quiet_print "==> Working file: $f\n";
+    open $fh, "+<$f" or die "$!";
+
+    binmode $fh; # Just in case
+
+    my $size = 4096;
+
+    my ($cur_pos, $buf);
+    seek $fh, -$size, 2;
+    while (1) {
+        $cur_pos = tell $fh;
+        read $fh, $buf, $size;
+        last if $buf =~ m/\S/s;
+        seek $fh, -$size*2, 1;
+    }
+
+    $buf =~ m/(\s+)$/s;
+    $cur_pos += $-[0] || 0;
+
+    truncate $fh, ++$cur_pos if $cur_pos;
+
+    close $fh;
+}
+
+# Returns a list of file names (relative to pwd) which the VCS considers to be modified.
+sub find_modified_files {
+    my @files = ();
+
+    # Number of path entries to remove from ${top}-relative paths.
+    # (--show-cdup either returns the empty string or sequence of "../"
+    # entries, always ending in a "/")
+    my $n_strip = scalar(split(m!/!, scalar(`git rev-parse --show-cdup`))) - 1;
+
+    # "." restricts scope, but does not get us relative path names
+    my $cmd = "git status -z --porcelain --untracked-files=no .";
+    my $lines = `$cmd`;
+
+    # From git-status(1):
+    # X          Y     Meaning
+    # -------------------------------------------------
+    #           [MD]   not updated
+    # M        [ MD]   updated in index
+    # A        [ MD]   added to index
+    # D         [ M]   deleted from index
+    # R        [ MD]   renamed in index
+    # C        [ MD]   copied in index
+    # [MARC]           index and work tree matches
+    # [ MARC]     M    work tree changed since index
+    # [ MARC]     D    deleted in work tree
+    # -------------------------------------------------
+    # D           D    unmerged, both deleted
+    # A           U    unmerged, added by us
+    # U           D    unmerged, deleted by them
+    # U           A    unmerged, added by them
+    # D           U    unmerged, deleted by us
+    # A           A    unmerged, both added
+    # U           U    unmerged, both modified
+    # -------------------------------------------------
+    # ?           ?    untracked
+    # -------------------------------------------------
+    my $s1 = "";
+    my $s2 = "";
+    my $fullname = "";
+
+    foreach my $line (split /\x{00}/, $lines) {
+        my $keep = 0;
+        unless (($s1, $s2, $fullname) = $line =~ m/^(.)(.) (.*)$/) {
+            next;
+        }
+
+        # skip opal_ignore files
+        next if ($fullname =~ "opal_ignore");
+
+        if ($ALL) {
+            $keep = 1;
+        } else {
+            # ignore all merge cases
+            next if ($s1 eq "D" and $s2 eq "D");
+            next if ($s1 eq "A" and $s2 eq "A");
+            next if ($s1 eq "U" or $s2 eq "U");
+
+            # only update for actually added/modified cases, no copies,
+            # renames, etc.
+            $keep = 1 if ($s1 eq "M" or $s2 eq "M");
+            $keep = 1 if ($s1 eq "A");
+        }
+
+        if ($keep) {
+            my $relname = $fullname;
+            $relname =~ s!^([^/]*/){$n_strip}!!g;
+
+            push @files, $relname
+                if (-f $relname);
+        }
+    }
+    return @files;
+}
+
+exit 0;

contrib/whitespace-purge.sh

@@ -1,9 +1,9 @@
 #!/bin/bash
 #
-# Copyright (c) 2015      Intel, Inc. All rights reserved.
+# Copyright (c) 2015-2016 Intel, Inc.  All rights reserved.
 # Copyright (c) 2015      Los Alamos National Security, LLC. All rights
 #                         reserved
-# Copyright (c) 2015 Cisco Systems, Inc.
+# Copyright (c) 2015      Cisco Systems, Inc.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow