[PATCH] gitweb: redacted e-mail addresses feature.

["Georgios Kontaxis via GitGitGadget" <gitgitgadget@xxxxxxxxx>]

From: Georgios Kontaxis <geko1702+commits@xxxxxxxxx>

Gitweb extracts content from the Git log and makes it accessible
over HTTP. As a result, e-mail addresses found in commits are
exposed to web crawlers. This may result in unsolicited messages.
This is a feature for redacting e-mail addresses from the generated
HTML content.

This feature does not prevent someone from downloading the
unredacted commit log and extracting information from it.
It aims to hinder the low-effort bulk collection of e-mail
addresses by web crawlers.

Signed-off-by: Georgios Kontaxis <geko1702+commits@xxxxxxxxx>
---
    gitweb: Redacted e-mail addresses feature.
    
    Gitweb extracts content from the Git log and makes it accessible over
    HTTP. As a result, e-mail addresses found in commits are exposed to web
    crawlers. This may result in unsolicited messages. This is a feature for
    redacting e-mail addresses from the generated HTML content.
    
    This feature does not prevent someone from downloading the unredacted
    commit log and extracting information from it. It aims to hinder the
    low-effort bulk collection of e-mail addresses by web crawlers.
    
    Signed-off-by: Georgios Kontaxis geko1702+commits@xxxxxxxxx

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-910%2Fkontaxis%2Fkontaxis%2Femail_privacy-v1
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-910/kontaxis/kontaxis/email_privacy-v1
Pull-Request: https://github.com/gitgitgadget/git/pull/910

 Documentation/gitweb.conf.txt | 12 ++++++++++++
 gitweb/gitweb.perl            | 36 ++++++++++++++++++++++++++++++++---
 2 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/Documentation/gitweb.conf.txt b/Documentation/gitweb.conf.txt
index 7963a79ba98b..10653d8670a8 100644
--- a/Documentation/gitweb.conf.txt
+++ b/Documentation/gitweb.conf.txt
@@ -896,6 +896,18 @@ same as of the snippet above:
 It is an error to specify a ref that does not pass "git check-ref-format"
 scrutiny. Duplicated values are filtered.
 
+email_privacy::
+    Redact e-mail addresses from the generated HTML, etc. content.
+    This hides e-mail addresses found in the commit log from web crawlers.
+    Enabled by default.
++
+It is highly recommended to keep this feature enabled unless web crawlers
+are hindered in some other way. You can disable this feature as shown below:
++
+---------------------------------------------------------------------------
+$feature{'email_privacy'}{'default'} = [0];
+---------------------------------------------------------------------------
+
 
 EXAMPLES
 --------
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 0959a782eccb..9d21c2583e18 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -569,6 +569,15 @@ sub evaluate_uri {
 		'sub' => \&feature_extra_branch_refs,
 		'override' => 0,
 		'default' => []},
+
+    # Redact e-mail addresses.
+
+    # To disable system wide have in $GITWEB_CONFIG
+    # $feature{'email_privacy'}{'default'} = [0];
+	'email_privacy' => {
+		'sub' => sub { feature_bool('email_privacy', @_) },
+		'override' => 0,
+		'default' => [1]},
 );
 
 sub gitweb_get_feature {
@@ -3471,6 +3480,10 @@ sub parse_tag {
 			if ($tag{'author'} =~ m/^([^<]+) <([^>]*)>/) {
 				$tag{'author_name'}  = $1;
 				$tag{'author_email'} = $2;
+				if (gitweb_check_feature('email_privacy')) {
+					$tag{'author_email'} = "private";
+					$tag{'author'} =~ s/<([^>]+)>/<private>/;
+				}
 			} else {
 				$tag{'author_name'} = $tag{'author'};
 			}
@@ -3519,6 +3532,10 @@ sub parse_commit_text {
 			if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) {
 				$co{'author_name'}  = $1;
 				$co{'author_email'} = $2;
+				if (gitweb_check_feature('email_privacy')) {
+					$co{'author_email'} = "private";
+					$co{'author'} =~ s/<([^>]+)>/<private>/;
+				}
 			} else {
 				$co{'author_name'} = $co{'author'};
 			}
@@ -3529,6 +3546,10 @@ sub parse_commit_text {
 			if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) {
 				$co{'committer_name'}  = $1;
 				$co{'committer_email'} = $2;
+				if (gitweb_check_feature('email_privacy')) {
+					$co{'committer_email'} = "private";
+					$co{'committer'} =~ s/<([^>]+)>/<private>/;
+				}
 			} else {
 				$co{'committer_name'} = $co{'committer'};
 			}
@@ -3568,9 +3589,13 @@ sub parse_commit_text {
 	if (! defined $co{'title'} || $co{'title'} eq "") {
 		$co{'title'} = $co{'title_short'} = '(no commit message)';
 	}
-	# remove added spaces
+	# remove added spaces, redact e-mail addresses if applicable.
 	foreach my $line (@commit_lines) {
 		$line =~ s/^    //;
+		if (gitweb_check_feature('email_privacy') &&
+			$line =~ m/^([^<]+) <([^>]*)>/) {
+			$line =~ s/<([^>]+)>/<private>/;
+		}
 	}
 	$co{'comment'} = \@commit_lines;
 
@@ -8060,8 +8085,13 @@ sub git_commitdiff {
 		close $fd
 			or print "Reading git-diff-tree failed\n";
 	} elsif ($format eq 'patch') {
-		local $/ = undef;
-		print <$fd>;
+		while (my $line = <$fd>) {
+			if (gitweb_check_feature('email_privacy') &&
+				$line =~ m/^([^<]+) <([^>]*)>/) {
+				$line =~ s/<([^>]+)>/<private>/;
+			}
+			print $line;
+		}
 		close $fd
 			or print "Reading git-format-patch failed\n";
 	}

base-commit: a5828ae6b52137b913b978e16cd2334482eb4c1f
-- 
gitgitgadget