X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=6e69001c4c4d78fa2e52fc851525c30bfd8f7a59;hb=6e6f7999361925e4c944f308df4bc32a1842cd69;hp=a2c2a4a6ff2944359ad2a5012c8f2f915279183e;hpb=956abe9ad5f13a0d1755262be412d6a54fda72e9;p=public-inbox.git

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index a2c2a4a6..6e69001c 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -6,6 +6,7 @@
 # We focus on the lowest common denominators here:
 # - targeted at text-only console browsers (w3m, links, etc..)
 # - Only basic HTML, CSS only for line-wrapping <pre> text content for GUIs
+#   and diff/syntax-highlighting (optional)
 # - No JavaScript, graphics or icons allowed.
 # - Must not rely on static content
 # - UTF-8 is only for user-content, 7-bit US-ASCII for us
@@ -13,16 +14,22 @@ package PublicInbox::WWW;
 use 5.008;
 use strict;
 use warnings;
+use bytes (); # only for bytes::length
+use Plack::Util;
 use PublicInbox::Config;
 use PublicInbox::Hval;
 use URI::Escape qw(uri_unescape);
 use PublicInbox::MID qw(mid_escape);
 require PublicInbox::Git;
 use PublicInbox::GitHTTPBackend;
-our $INBOX_RE = qr!\A/([\w\.\-]+)!;
+use PublicInbox::UserContent;
+
+# TODO: consider a routing tree now that we have more endpoints:
+our $INBOX_RE = qr!\A/([\w\-][\w\.\-]*)!;
 our $MID_RE = qr!([^/]+)!;
 our $END_RE = qr!(T/|t/|t\.mbox(?:\.gz)?|t\.atom|raw|)!;
 our $ATTACH_RE = qr!(\d[\.\d]*)-([[:alnum:]][\w\.-]+[[:alnum:]])!i;
+our $OID_RE = qr![a-f0-9]{7,40}!;
 
 sub new {
 	my ($class, $pi_config) = @_;
@@ -36,6 +43,17 @@ sub run {
 	PublicInbox::WWW->new->call($req->env);
 }
 
+my %path_re_cache;
+
+sub path_re ($) {
+	my $sn = $_[0]->{SCRIPT_NAME};
+	$path_re_cache{$sn} ||= do {
+		$sn = '/'.$sn unless index($sn, '/') == 0;
+		$sn =~ s!/\z!!;
+		qr!\A(?:https?://[^/]+)?\Q$sn\E(/[^\?\#]+)!;
+	};
+}
+
 sub call {
 	my ($self, $env) = @_;
 	my $ctx = { env => $env, www => $self };
@@ -50,14 +68,15 @@ sub call {
 	} split(/[&;]+/, $env->{QUERY_STRING});
 	$ctx->{qp} = \%qp;
 
-	my $path_info = $env->{PATH_INFO};
+	# not using $env->{PATH_INFO} here since that's already decoded
+	my ($path_info) = ($env->{REQUEST_URI} =~ path_re($env));
 	my $method = $env->{REQUEST_METHOD};
 
 	if ($method eq 'POST') {
-		if ($path_info =~ m!$INBOX_RE/(git-upload-pack)\z!) {
-			my $path = $2;
+		if ($path_info =~ m!$INBOX_RE/(?:(\d+)/)?(git-upload-pack)\z!) {
+			my ($part, $path) = ($2, $3);
 			return invalid_inbox($ctx, $1) ||
-				serve_git($ctx, $path);
+				serve_git($ctx, $part, $path);
 		} elsif ($path_info =~ m!$INBOX_RE/!o) {
 			return invalid_inbox($ctx, $1) || mbox_results($ctx);
 		}
@@ -77,10 +96,10 @@ sub call {
 		invalid_inbox($ctx, $1) || get_atom($ctx);
 	} elsif ($path_info =~ m!$INBOX_RE/new\.html\z!o) {
 		invalid_inbox($ctx, $1) || get_new($ctx);
-	} elsif ($path_info =~ m!$INBOX_RE/
+	} elsif ($path_info =~ m!$INBOX_RE/(?:(\d+)/)?
 				($PublicInbox::GitHTTPBackend::ANY)\z!ox) {
-		my $path = $2;
-		invalid_inbox($ctx, $1) || serve_git($ctx, $path);
+		my ($part, $path) = ($2, $3);
+		invalid_inbox($ctx, $1) || serve_git($ctx, $part, $path);
 	} elsif ($path_info =~ m!$INBOX_RE/([\w-]+).mbox\.gz\z!o) {
 		serve_mbox_range($ctx, $1, $2);
 	} elsif ($path_info =~ m!$INBOX_RE/$MID_RE/$END_RE\z!o) {
@@ -91,19 +110,26 @@ sub call {
 		invalid_inbox_mid($ctx, $1, $2) || get_attach($ctx, $idx, $fn);
 	# in case people leave off the trailing slash:
 	} elsif ($path_info =~ m!$INBOX_RE/$MID_RE/(T|t)\z!o) {
-		my ($inbox, $mid, $suffix) = ($1, $2, $3);
+		my ($inbox, $mid_ue, $suffix) = ($1, $2, $3);
 		$suffix .= $suffix =~ /\A[tT]\z/ ? '/#u' : '/';
-		r301($ctx, $inbox, $mid, $suffix);
+		r301($ctx, $inbox, $mid_ue, $suffix);
 
 	} elsif ($path_info =~ m!$INBOX_RE/$MID_RE/R/?\z!o) {
-		my ($inbox, $mid) = ($1, $2);
-		r301($ctx, $inbox, $mid, '#R');
+		my ($inbox, $mid_ue) = ($1, $2);
+		r301($ctx, $inbox, $mid_ue, '#R');
 
 	} elsif ($path_info =~ m!$INBOX_RE/$MID_RE/f/?\z!o) {
 		r301($ctx, $1, $2);
 	} elsif ($path_info =~ m!$INBOX_RE/_/text(?:/(.*))?\z!o) {
 		get_text($ctx, $1, $2);
-
+	} elsif ($path_info =~ m!$INBOX_RE/([\w\-\.]+)\.css\z!o) {
+		get_css($ctx, $1, $2);
+	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s/\z!o) {
+		get_vcs_object($ctx, $1, $2);
+	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s/([\w\.\-]+)\z!o) {
+		get_vcs_object($ctx, $1, $2, $3);
+	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s\z!o) {
+		r301($ctx, $1, $2, 's/');
 	# convenience redirects order matters
 	} elsif ($path_info =~ m!$INBOX_RE/([^/]{2,})\z!o) {
 		r301($ctx, $1, $2);
@@ -115,6 +141,7 @@ sub call {
 
 # for CoW-friendliness, MOOOOO!
 sub preload {
+	my ($self) = @_;
 	require PublicInbox::Feed;
 	require PublicInbox::View;
 	require PublicInbox::SearchThread;
@@ -127,6 +154,10 @@ sub preload {
 			PublicInbox::NewsWWW)) {
 		eval "require $_;";
 	}
+	if (ref($self)) {
+		$self->cgit;
+		$self->stylesheets_prepare($_) for ('', '../', '../../');
+	}
 }
 
 # private functions below
@@ -144,14 +175,20 @@ sub r404 {
 # simple response for errors
 sub r { [ $_[0], ['Content-Type' => 'text/plain'], [ join(' ', @_, "\n") ] ] }
 
+sub news_cgit_fallback ($) {
+	my ($ctx) = @_;
+	my $www = $ctx->{www};
+	my $env = $ctx->{env};
+	my $res = $www->news_www->call($env);
+	$res->[0] == 404 ? $www->cgit->call($env) : $res;
+}
+
 # returns undef if valid, array ref response if invalid
 sub invalid_inbox ($$) {
 	my ($ctx, $inbox) = @_;
-	my $www = $ctx->{www};
-	my $obj = $www->{pi_config}->lookup_name($inbox);
-	if (defined $obj) {
-		$ctx->{git} = $obj->git;
-		$ctx->{-inbox} = $obj;
+	my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox);
+	if (defined $ibx) {
+		$ctx->{-inbox} = $ibx;
 		return;
 	}
 
@@ -159,24 +196,25 @@ sub invalid_inbox ($$) {
 	# generation and link things intended for nntp:// to https?://,
 	# so try to infer links and redirect them to the appropriate
 	# list URL.
-	$www->news_www->call($ctx->{env});
+	news_cgit_fallback($ctx);
 }
 
 # returns undef if valid, array ref response if invalid
 sub invalid_inbox_mid {
-	my ($ctx, $inbox, $mid) = @_;
+	my ($ctx, $inbox, $mid_ue) = @_;
 	my $ret = invalid_inbox($ctx, $inbox);
 	return $ret if $ret;
 
-	$ctx->{mid} = $mid;
-	if ($mid =~ /\A[a-f0-9]{40}\z/) {
-		# this is horiffically wasteful for legacy URLs:
-		if ($mid = mid2blob($ctx)) {
-			require Email::Simple;
-			use PublicInbox::MID qw/mid_clean/;
-			my $s = Email::Simple->new($mid);
-			$ctx->{mid} = mid_clean($s->header('Message-ID'));
-		}
+	my $mid = $ctx->{mid} = uri_unescape($mid_ue);
+	my $ibx = $ctx->{-inbox};
+	if ($mid =~ m!\A([a-f0-9]{2})([a-f0-9]{38})\z!) {
+		my ($x2, $x38) = ($1, $2);
+		# this is horrifically wasteful for legacy URLs:
+		my $str = $ctx->{-inbox}->msg_by_path("$x2/$x38") or return;
+		require Email::Simple;
+		my $s = Email::Simple->new($str);
+		$mid = PublicInbox::MID::mid_clean($s->header('Message-ID'));
+		return r301($ctx, $inbox, mid_escape($mid));
 	}
 	undef;
 }
@@ -208,12 +246,6 @@ sub get_index {
 	}
 }
 
-# just returns a string ref for the blob in the current ctx
-sub mid2blob {
-	my ($ctx) = @_;
-	$ctx->{-inbox}->msg_by_mid($ctx->{mid});
-}
-
 # /$INBOX/$MESSAGE_ID/raw                    -> raw mbox
 sub get_mid_txt {
 	my ($ctx) = @_;
@@ -250,6 +282,18 @@ sub get_text {
 	PublicInbox::WwwText::get_text($ctx, $key);
 }
 
+# show git objects (blobs and commits)
+# /$INBOX/_/$OBJECT_ID/show
+# /$INBOX/_/${OBJECT_ID}_${FILENAME}
+# KEY may contain slashes
+sub get_vcs_object ($$$;$) {
+	my ($ctx, $inbox, $oid, $filename) = @_;
+	my $r404 = invalid_inbox($ctx, $inbox);
+	return $r404 if $r404;
+	require PublicInbox::ViewVCS;
+	PublicInbox::ViewVCS::show($ctx, $oid, $filename);
+}
+
 sub ctx_get {
 	my ($ctx, $key) = @_;
 	my $val = $ctx->{$key};
@@ -352,21 +396,25 @@ sub legacy_redirects {
 	} elsif ($path_info =~ m!$INBOX_RE/(\S+/\S+)/f\z!o) {
 		r301($ctx, $1, $2);
 	} else {
-		$ctx->{www}->news_www->call($ctx->{env});
+		news_cgit_fallback($ctx);
 	}
 }
 
 sub r301 {
-	my ($ctx, $inbox, $mid, $suffix) = @_;
-	my $obj = $ctx->{-inbox};
-	unless ($obj) {
+	my ($ctx, $inbox, $mid_ue, $suffix) = @_;
+	my $ibx = $ctx->{-inbox};
+	unless ($ibx) {
 		my $r404 = invalid_inbox($ctx, $inbox);
 		return $r404 if $r404;
-		$obj = $ctx->{-inbox};
+		$ibx = $ctx->{-inbox};
 	}
-	my $url = $obj->base_url($ctx->{env});
+	my $url = $ibx->base_url($ctx->{env});
 	my $qs = $ctx->{env}->{QUERY_STRING};
-	$url .= (mid_escape($mid) . '/') if (defined $mid);
+	if (defined $mid_ue) {
+		# common, and much nicer as '@' than '%40':
+		$mid_ue =~ s/%40/@/g;
+		$url .= $mid_ue . '/';
+	}
 	$url .= $suffix if (defined $suffix);
 	$url .= "?$qs" if $qs ne '';
 
@@ -376,9 +424,9 @@ sub r301 {
 }
 
 sub msg_page {
-	my ($ctx, $inbox, $mid, $e) = @_;
+	my ($ctx, $inbox, $mid_ue, $e) = @_;
 	my $ret;
-	$ret = invalid_inbox_mid($ctx, $inbox, $mid) and return $ret;
+	$ret = invalid_inbox_mid($ctx, $inbox, $mid_ue) and return $ret;
 	'' eq $e and return get_mid_html($ctx);
 	'T/' eq $e and return get_thread($ctx, 1);
 	't/' eq $e and return get_thread($ctx);
@@ -393,8 +441,11 @@ sub msg_page {
 }
 
 sub serve_git {
-	my ($ctx, $path) = @_;
-	PublicInbox::GitHTTPBackend::serve($ctx->{env}, $ctx->{git}, $path);
+	my ($ctx, $part, $path) = @_;
+	my $env = $ctx->{env};
+	my $ibx = $ctx->{-inbox};
+	my $git = defined $part ? $ibx->git_part($part) : $ibx->git;
+	$git ? PublicInbox::GitHTTPBackend::serve($env, $git, $path) : r404();
 }
 
 sub mbox_results {
@@ -424,10 +475,156 @@ sub news_www {
 	}
 }
 
+sub cgit {
+	my ($self) = @_;
+	$self->{cgit} ||= do {
+		my $pi_config = $self->{pi_config};
+
+		if (defined($pi_config->{'publicinbox.cgitrc'})) {
+			require PublicInbox::Cgit;
+			PublicInbox::Cgit->new($pi_config);
+		} else {
+			Plack::Util::inline_object(call => sub { r404() });
+		}
+	}
+}
+
 sub get_attach {
 	my ($ctx, $idx, $fn) = @_;
 	require PublicInbox::WwwAttach;
 	PublicInbox::WwwAttach::get_attach($ctx, $idx, $fn);
 }
 
+# User-generated content (UGC) may have excessively long lines
+# and screw up rendering on some browsers, so we use pre-wrap.
+#
+# We also force everything to the same scaled font-size because GUI
+# browsers (tested both Firefox and surf (webkit)) uses a larger font
+# for the Search <form> element than the rest of the page.  Font size
+# uniformity is important to people who rely on gigantic fonts.
+# Finally, we use monospace to ensure the Search field and button
+# has the same size and spacing as everything else which is
+# <pre>-formatted anyways.
+our $STYLE = 'pre{white-space:pre-wrap}*{font-size:100%;font-family:monospace}';
+
+sub stylesheets_prepare ($$) {
+	my ($self, $upfx) = @_;
+	my $mini = eval {
+		require CSS::Minifier;
+		sub { CSS::Minifier::minify(input => $_[0]) };
+	} || eval {
+		require CSS::Minifier::XS;
+		sub { CSS::Minifier::XS::minify($_[0]) };
+	} || sub { $_[0] };
+
+	my $css_map = {};
+	my $stylesheets = $self->{pi_config}->{css} || [];
+	my $links = [];
+	my $inline_ok = 1;
+
+	foreach my $s (@$stylesheets) {
+		my $attr = {};
+		local $_ = $s;
+		foreach my $k (qw(media title href)) {
+			if (s/\s*$k='([^']+)'// || s/\s*$k=(\S+)//) {
+				$attr->{$k} = $1;
+			}
+		}
+
+		if (defined $attr->{href}) {
+			$inline_ok = 0;
+		} else {
+			my $fn = $_;
+			open(my $fh, '<', $fn) or do {
+				warn "failed to open $fn: $!\n";
+				next;
+			};
+			my ($key) = (m!([^/]+?)(?:\.css)?\z!i);
+			my $ctime = 0;
+			my $local = do { local $/; <$fh> };
+			if ($local =~ /\S/) {
+				$ctime = sprintf('%x',(stat($fh))[10]);
+				$local = $mini->($local);
+			}
+
+			# do not let BOFHs override userContent.css:
+			if ($local =~ /!\s*important\b/i) {
+				warn "ignoring $fn since it uses `!important'\n";
+				next;
+			}
+
+			$css_map->{$key} = $local;
+			$attr->{href} = "$upfx$key.css?$ctime";
+			if (defined($attr->{title})) {
+				$inline_ok = 0;
+			} elsif (($attr->{media}||'screen') eq 'screen') {
+				$attr->{-inline} = $local;
+			}
+		}
+		push @$links, $attr;
+	}
+
+	my $buf = "<style>$STYLE";
+	if ($inline_ok) {
+		my @ext; # for media=print and whatnot
+		foreach my $attr (@$links) {
+			if (defined(my $str = delete $attr->{-inline})) {
+				$buf .= $str;
+			} else {
+				push @ext, $attr;
+			}
+		}
+		$links = \@ext;
+	}
+	$buf .= '</style>';
+
+	if (@$links) {
+		foreach my $attr (@$links) {
+			delete $attr->{-inline};
+			$buf .= "<link\ntype=text/css\nrel=stylesheet";
+			while (my ($k, $v) = each %$attr) {
+				$v = qq{"$v"} if $v =~ /[\s=]/;
+				$buf .= qq{\n$k=$v};
+			}
+			$buf .= ' />';
+		}
+		$self->{"-style-$upfx"} = $buf;
+	} else {
+		$self->{-style_inline} = $buf;
+	}
+	$self->{-css_map} = $css_map;
+}
+
+# returns an HTML fragment with <style> or <link> tags in them
+# Called by WwwStream by nearly every HTML page
+sub style {
+	my ($self, $upfx) = @_;
+	$self->{-style_inline} || $self->{"-style-$upfx"} || do {
+		stylesheets_prepare($self, $upfx);
+		$self->{-style_inline} || $self->{"-style-$upfx"}
+	};
+}
+
+# /$INBOX/$KEY.css endpoint
+# CSS is configured globally for all inboxes, but we access them on
+# a per-inbox basis.  This allows administrators to setup per-inbox
+# static routes to intercept the request before it hits PSGI
+sub get_css ($$$) {
+	my ($ctx, $inbox, $key) = @_;
+	my $r404 = invalid_inbox($ctx, $inbox);
+	return $r404 if $r404;
+	my $self = $ctx->{www};
+	my $css_map = $self->{-css_map} || stylesheets_prepare($self, '');
+	my $css = $css_map->{$key};
+	if (!defined($css) && $key eq 'userContent') {
+		my $env = $ctx->{env};
+		$css = PublicInbox::UserContent::sample($ctx->{-inbox}, $env);
+	}
+	defined $css or return r404();
+	my $h = [ 'Content-Length', bytes::length($css),
+		'Content-Type', 'text/css' ];
+	PublicInbox::GitHTTPBackend::cache_one_year($h);
+	[ 200, $h, [ $css ] ];
+}
+
 1;