[PATCH] Munge ChangeLog-style commit messages, and grab author name and email.

[Carl Worth <cworth@cworth.org>]

The cairo project has been using ChangeLog-style commit messages, such as:

	2006-01-18  Carl Worth  <cworth@cworth.org>

		* src/cairo-pdf-surface.c: (cairo_pdf_surface_create_for_stream),
		(cairo_pdf_surface_create): Fix compilation-breaking typo.

This patch recognizes that style and munges it up into:

	Fix compilation-breaking typo.

which results in a much more useful headline within git.

It also grabs the name and email address from the first line and
commits with those as GIT_AUTHOR_NAME and GIT_AUTHOR_MAIL.

It would probably make sense to hide all this munging behind an
appropriate command-line parameter, but I'm offering this up as is in
case it's useful for anyone with similar commit messages.

Signed-off-by: Carl Worth <cworth@cworth.org>
Signed-off-by: Keith Packard <keithp@keithp.com>

---

 git-cvsimport.perl |   71 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 71 insertions(+), 0 deletions(-)

2f2002fe619c45cb1be1c0f063416ede242f3552
diff --git a/git-cvsimport.perl b/git-cvsimport.perl
index 00fc3ba..6b63aa2 100755
--- a/git-cvsimport.perl
+++ b/git-cvsimport.perl
@@ -658,6 +658,12 @@ my $commit = sub {
 			}
 		}
 
+		# Look for name and email from ChangeLog-style commit message
+		if ($logmsg =~ /^\s*\d\d\d\d-\d\d-\d\d\s*(.*)\s*<(.*)>/) {
+		    $author_name = $1;
+		    $author_email = $2;
+		}
+
 		exec("env",
 			"GIT_AUTHOR_NAME=$author_name",
 			"GIT_AUTHOR_EMAIL=$author_email",
@@ -673,8 +679,73 @@ my $commit = sub {
 
 	# compatibility with git2cvs
 	substr($logmsg,32767) = "" if length($logmsg) > 32767;
+
+	# We do a bunch of munging on the log message here,
+	# particularly for logs that are formatted in a ChangeLog
+	# style.
+
+	my $origlog = $logmsg;
+
+	# Kill initial date/name stamp: YYYY-MM-DD First Last <email@example.com>
+
+	$logmsg =~ s|^\s*\d\d*-\d\d*-\d\d*\s*[^<\n]*<[^>\n]*>\s*$|* \n|mg;
+
+	# Strip out nickle version numbers
+	$logmsg =~ s|^(version )?2.\d\d*$||mg;
+
+	# Remove initial space for each line
+	$logmsg =~ s|^[ \t]+||mg;
+
+	# Collapse space sequences
+	$logmsg =~ s|[ \t]+| |g;
+
+	# Un-fold paragraphs
+	$logmsg =~ s|([^\n])\n([^*+\-\n])|$1 $2|g;
+
+	my @lines = split (/\n/, $logmsg);
+	
+	$logmsg = "";
+
+	my $reviews = "";
+
+	foreach my $line (@lines) {
+		# Pull out any reviewed-by name
+		if ($line =~ /^reviewed by:\s*/i) {
+			if ($line !~ /<delete if not using/) {
+				$reviews = $reviews . "\n" . $line;
+			}
+		} else { 
+		        # find lines begining with '*'
+			if ($line =~ s/^\*\s\s*//) {
+				# strip off filenames
+			        while ($line =~ s/^[^ :,]*([,:]| (?=\())\s*// ) {
+				}
+				# strip off function names
+				while ($line =~ s/^\([^)]*\)[,:]*\s*// ) {
+				}
+			}
+			$logmsg = $logmsg . $line . "\n";
+		}
+	}
+	$logmsg = $logmsg . $reviews;
+
+	# Trim initial newlines
+	$logmsg =~ s|^\n+||;
+
+	# Remove initial space for each line
+	$logmsg =~ s|^[ \t]+||mg;
+
+	# Collapse space sequences
+	$logmsg =~ s|[ \t]+| |g;
+
+	# collapse sequences of newlines
+	$logmsg =~ s/\n\n*/\n/g;
+
+	# Remove trailing whitespace
 	$logmsg =~ s/[\s\n]+\z//;
 
+#	print "<<<< Original\n$origlog\n---- Rewritten\n$logmsg\n<<<<\n";
+	
 	if (@skipped) {
 	    $logmsg .= "\n\n\nSKIPPED:\n\t";
 	    $logmsg .= join("\n\t", @skipped) . "\n";
-- 
1.1.6.g9da5