user/dev discussion of public-inbox itself
 help / color / Atom feed
d22c80b97b4871a00dba47f3e8b055bd1659ab06 blob 7028 bytes (raw)

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
 
# Copyright (C) 2019-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# used by PublicInbox::View
# This adds CSS spans for diff highlighting.
# It also generates links for ViewVCS + SolverGit to show
# (or reconstruct) blobs.

package PublicInbox::ViewDiff;
use 5.010_001;
use strict;
use warnings;
use base qw(Exporter);
our @EXPORT_OK = qw(flush_diff);
use URI::Escape qw(uri_escape_utf8);
use PublicInbox::Hval qw(ascii_html to_attr);
use PublicInbox::Git qw(git_unquote);

sub UNSAFE () { "^A-Za-z0-9\-\._~/" }

my $OID_NULL = '0{7,40}';
my $OID_BLOB = '[a-f0-9]{7,40}';
my $LF = qr!\n!;
my $ANY = qr![^\n]!;
my $FN = qr!(?:"?[^/\n]+/[^\n]+|/dev/null)!;

# cf. git diff.c :: get_compact_summary
my $DIFFSTAT_COMMENT =
	qr/(?: *\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\))? *\z/s;
my $NULL_TO_BLOB = qr/^(index $OID_NULL\.\.)($OID_BLOB)\b/ms;
my $BLOB_TO_NULL = qr/^index ($OID_BLOB)(\.\.$OID_NULL)\b/ms;
my $BLOB_TO_BLOB = qr/^index ($OID_BLOB)\.\.($OID_BLOB)/ms;
my $EXTRACT_DIFFS = qr/(
		(?:	# begin header stuff, don't capture filenames, here,
			# but instead wait for the --- and +++ lines.
			(?:^diff\x20--git\x20$FN\x20$FN$LF)

			# old mode || new mode || copy|rename|deleted|...
			(?:^[a-z]$ANY+$LF)*
		)? # end of optional stuff, everything below is required
		^index\x20($OID_BLOB)\.\.($OID_BLOB)$ANY*$LF
		^---\x20($FN)$LF
		^\+{3}\x20($FN)$LF)/msx;
my $IS_OID = qr/\A$OID_BLOB\z/s;

# link to line numbers in blobs
sub diff_hunk ($$$$) {
	my ($dst, $dctx, $ca, $cb) = @_;
	my ($oid_a, $oid_b, $spfx) = @$dctx{qw(oid_a oid_b spfx)};

	if (defined($spfx) && defined($oid_a) && defined($oid_b)) {
		my ($n) = ($ca =~ /^-([0-9]+)/);
		$n = defined($n) ? do { ++$n; "#n$n" } : '';

		$$dst .= qq(@@ <a\nhref="$spfx$oid_a/s/$dctx->{Q}$n">$ca</a>);

		($n) = ($cb =~ /^\+([0-9]+)/);
		$n = defined($n) ? do { ++$n; "#n$n" } : '';
		$$dst .= qq( <a\nhref="$spfx$oid_b/s/$dctx->{Q}$n">$cb</a> @@);
	} else {
		$$dst .= "@@ $ca $cb @@";
	}
}

sub oid ($$$) {
	my ($dctx, $spfx, $oid) = @_;
	defined($spfx) ? qq(<a\nhref="$spfx$oid/s/$dctx->{Q}">$oid</a>) : $oid;
}

# returns true if diffstat anchor written, false otherwise
sub anchor0 ($$$$) {
	my ($dst, $ctx, $fn, $rest) = @_;

	my $orig = $fn;

	# normal git diffstat output is impossible to parse reliably
	# without --numstat, and that isn't the default for format-patch.
	# So only do best-effort handling of renames for common cases;
	# which works well in practice. If projects put "=>", or trailing
	# spaces in filenames, oh well :P
	$fn =~ s/$DIFFSTAT_COMMENT//;
	$fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/;
	$fn = git_unquote($fn);

	# long filenames will require us to walk backwards in anchor1
	if ($fn =~ s!\A\.\.\./?!!) {
		$ctx->{-long_path}->{$fn} = qr/\Q$fn\E\z/s;
	}

	if (my $attr = to_attr($ctx->{-apfx}.$fn)) {
		$ctx->{-anchors}->{$attr} = 1;
		my $spaces = ($orig =~ s/( +)\z//) ? $1 : '';
		$$dst .= " <a\nid=i$attr\nhref=#$attr>" .
			ascii_html($orig) . '</a>' . $spaces .
			$ctx->{-linkify}->to_html($rest);
		return 1;
	}
	undef;
}

# returns "diff --git" anchor destination, undef otherwise
sub anchor1 ($$) {
	my ($ctx, $pb) = @_;
	my $attr = to_attr($ctx->{-apfx}.$pb) or return;

	my $ok = delete $ctx->{-anchors}->{$attr};

	# unlikely, check the end of all long path names we captured:
	unless ($ok) {
		my $lp = $ctx->{-long_path} or return;
		foreach my $fn (keys %$lp) {
			$pb =~ $lp->{$fn} or next;

			delete $lp->{$fn};
			$attr = to_attr($ctx->{-apfx}.$fn) or return;
			$ok = delete $ctx->{-anchors}->{$attr} or return;
			last;
		}
	}
	$ok ? "<a\nhref=#i$attr\nid=$attr>diff</a> --git" : undef
}

sub diff_header ($$$$) {
	my ($dst, $x, $ctx, $top) = @_;
	my (undef, undef, $pa, $pb) = splice(@$top, 0, 4); # ignore oid_{a,b}
	my $spfx = $ctx->{-spfx};
	my $dctx = { spfx => $spfx };

	# get rid of leading "a/" or "b/" (or whatever --{src,dst}-prefix are)
	$pa = (split('/', git_unquote($pa), 2))[1] if $pa ne '/dev/null';
	$pb = (split('/', git_unquote($pb), 2))[1] if $pb ne '/dev/null';
	if ($pa eq $pb && $pb ne '/dev/null') {
		$dctx->{Q} = "?b=".uri_escape_utf8($pb, UNSAFE);
	} else {
		my @q;
		if ($pb ne '/dev/null') {
			push @q, 'b='.uri_escape_utf8($pb, UNSAFE);
		}
		if ($pa ne '/dev/null') {
			push @q, 'a='.uri_escape_utf8($pa, UNSAFE);
		}
		$dctx->{Q} = '?'.join('&amp;', @q);
	}

	# linkify early and all at once, since we know the following
	# subst ops on $$x won't need further escaping:
	$$x = $ctx->{-linkify}->to_html($$x);

	# no need to capture oid_a and oid_b on add/delete,
	# we just linkify OIDs directly via s///e in conditional
	if (($$x =~ s/$NULL_TO_BLOB/$1 . oid($dctx, $spfx, $2)/e) ||
		($$x =~ s/$BLOB_TO_NULL/
			'index ' . oid($dctx, $spfx, $1) . $2/e)) {
	} elsif ($$x =~ $BLOB_TO_BLOB) {
		# modification-only, not add/delete:
		# linkify hunk headers later using oid_a and oid_b
		@$dctx{qw(oid_a oid_b)} = ($1, $2);
	} else {
		warn "BUG? <$$x> had no ^index line";
	}
	$$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!ems;
	$$dst .= qq(<span\nclass="head">);
	$$dst .= $$x;
	$$dst .= '</span>';
	$dctx;
}

sub diff_before_or_after ($$$) {
	my ($dst, $ctx, $x) = @_;
	my $linkify = $ctx->{-linkify};
	for my $y (split(/(^---\n)/sm, $$x)) {
		if ($y =~ /\A---\n\z/s) {
			$$dst .= "---\n"; # all HTML is "\r\n" => "\n"
		} elsif ($y =~ /^ [0-9]+ files? changed, /sm) {
			# ok, looks like a diffstat, go line-by-line:
			for my $l (split(/^/m, $y)) {
				if ($l =~ /^ (.+)( +\| .*\z)/s) {
					anchor0($dst, $ctx, $1, $2) and next;
				}
				$$dst .= $linkify->to_html($l);
			}
		} else { # commit message, notes, etc
			$$dst .= $linkify->to_html($y);
		}
	}
}

# callers must do CRLF => LF conversion before calling this
sub flush_diff ($$$) {
	my ($dst, $ctx, $cur) = @_;

	my @top = split($EXTRACT_DIFFS, $$cur);
	$$cur = undef;

	my $linkify = $ctx->{-linkify};
	my $dctx; # {}, keys: Q, oid_a, oid_b

	while (defined(my $x = shift @top)) {
		if (scalar(@top) >= 4 &&
				$top[1] =~ $IS_OID &&
				$top[0] =~ $IS_OID) {
			$dctx = diff_header($dst, \$x, $ctx, \@top);
		} elsif ($dctx) {
			my $after = '';
			for my $s (split(/((?:(?:^\+[^\n]*\n)+)|
					(?:(?:^-[^\n]*\n)+)|
					(?:^@@ [^\n]+\n))/xsm, $x)) {
				if (!defined($dctx)) {
					$after .= $s;
				} elsif ($s =~ s/\A@@ (\S+) (\S+) @@//) {
					$$dst .= qq(<span\nclass="hunk">);
					diff_hunk($dst, $dctx, $1, $2);
					$$dst .= $linkify->to_html($s);
					$$dst .= '</span>';
				} elsif ($s =~ /\A\+/) {
					$$dst .= qq(<span\nclass="add">);
					$$dst .= $linkify->to_html($s);
					$$dst .= '</span>';
				} elsif ($s =~ /\A-- $/sm) { # email sig starts
					$dctx = undef;
					$after .= $s;
				} elsif ($s =~ /\A-/) {
					$$dst .= qq(<span\nclass="del">);
					$$dst .= $linkify->to_html($s);
					$$dst .= '</span>';
				} else {
					$$dst .= $linkify->to_html($s);
				}
			}
			diff_before_or_after($dst, $ctx, \$after) unless $dctx;
		} else {
			diff_before_or_after($dst, $ctx, \$x);
		}
	}
}

1;
debug log:

solving d22c80b9 ...
found d22c80b9 in https://80x24.org/public-inbox.git

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Example config snippet for mirrors

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.io/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git