* [PATCH 0/3] viewvcs odds and ends
@ 2019-02-01 7:50 7% Eric Wong
2019-02-01 7:50 6% ` [PATCH 3/3] viewdiff: support renames and long paths in diffstat anchors Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2019-02-01 7:50 UTC (permalink / raw)
To: meta
Some corner-case fixes around some odd filenames,
long paths and renames.
Eric Wong (3):
viewvcs: allow '0' as a valid filename for blob downloads
viewdiff: escape HTML ampersand for renames
viewdiff: support renames and long paths in diffstat anchors
lib/PublicInbox/View.pm | 1 +
lib/PublicInbox/ViewDiff.pm | 62 ++++++++++++++++++++++++++++---------
lib/PublicInbox/ViewVCS.pm | 2 +-
3 files changed, 49 insertions(+), 16 deletions(-)
--
EW
^ permalink raw reply [relevance 7%]
* [PATCH 3/3] viewdiff: support renames and long paths in diffstat anchors
2019-02-01 7:50 7% [PATCH 0/3] viewvcs odds and ends Eric Wong
@ 2019-02-01 7:50 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-02-01 7:50 UTC (permalink / raw)
To: meta
This is best-effort, but works well-enough in practice for
projects which use shell-friendly filenames as well as the
long path names for some Linux kernel selftests.
---
lib/PublicInbox/View.pm | 1 +
lib/PublicInbox/ViewDiff.pm | 62 ++++++++++++++++++++++++++++---------
2 files changed, 48 insertions(+), 15 deletions(-)
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 69aca3d..e64c965 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -571,6 +571,7 @@ sub add_text_body {
$ctx->{-apfx} = join('/', @idx);
$ctx->{-anchors} = {}; # attr => filename
$ctx->{-diff} = $diff = [];
+ delete $ctx->{-long_path};
my $spfx;
if ($ibx->{-repo_objs}) {
if (index($upfx, '//') >= 0) { # absolute URL (Atom feeds)
diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index fbdc5b9..c818203 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -77,10 +77,28 @@ sub to_state ($$$) {
sub anchor0 ($$$$$) {
my ($dst, $ctx, $linkify, $fn, $rest) = @_;
+
+ my $orig = $fn;
+
+ # normal git diffstat output is impossible to parse reliably
+ # without --numstat, and that isn't the default for format-patch.
+ # So only do best-effort handling of renames for common cases;
+ # which works well in practice. If projects put "=>", or trailing
+ # spaces in filenames, oh well :P
+ $fn =~ s/ +\z//s;
+ $fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/;
+ $fn = git_unquote($fn);
+
+ # long filenames will require us to walk backwards in anchor1
+ if ($fn =~ s!\A\.\.\./?!!) {
+ my $lp = $ctx->{-long_path} ||= {};
+ $lp->{$fn} = qr/\Q$fn\E\z/s;
+ }
+
if (my $attr = to_attr($ctx->{-apfx}.$fn)) {
$ctx->{-anchors}->{$attr} = 1;
$$dst .= " <a\nid=i$attr\nhref=#$attr>" .
- ascii_html($fn) . '</a>'.
+ ascii_html($orig) . '</a>'.
to_html($linkify, $rest);
return 1;
}
@@ -92,7 +110,21 @@ sub anchor1 ($$$$$) {
my $attr = to_attr($ctx->{-apfx}.$pb) or return;
my $line = to_html($linkify, $s);
- if (delete $ctx->{-anchors}->{$attr} && $line =~ s/^diff //) {
+ my $ok = delete $ctx->{-anchors}->{$attr};
+
+ # unlikely, check the end of all long path names we captured:
+ unless ($ok) {
+ my $lp = $ctx->{-long_path} or return;
+ foreach my $fn (keys %$lp) {
+ $pb =~ $lp->{$fn} or next;
+
+ delete $lp->{$fn};
+ $attr = to_attr($ctx->{-apfx}.$fn) or return;
+ $ok = delete $ctx->{-anchors}->{$attr} or return;
+ last;
+ }
+ }
+ if ($ok && $line =~ s/^diff //) {
$$dst .= "<a\nhref=#i$attr\nid=$attr>diff</a> ".$line;
return 1;
}
@@ -113,7 +145,7 @@ sub flush_diff ($$$) {
} elsif ($s =~ /^ /) {
# works for common cases, but not weird/long filenames
if ($state == DSTATE_STAT &&
- $s =~ /^ (\S+)(\s+\|.*\z)/s) {
+ $s =~ /^ (.+)( +\| .*\z)/s) {
anchor0($dst, $ctx, $linkify, $1, $2) and next;
} elsif ($state2class[$state]) {
to_state($dst, $state, DSTATE_CTX);
@@ -124,20 +156,20 @@ sub flush_diff ($$$) {
to_state($dst, $state, DSTATE_INIT);
$$dst .= $s;
} elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!) {
+ my ($pa, $pb) = ($1, $2);
if ($state != DSTATE_HEAD) {
- my ($pa, $pb) = ($1, $2);
to_state($dst, $state, DSTATE_HEAD);
- $pa = (split('/', git_unquote($pa), 2))[1];
- $pb = (split('/', git_unquote($pb), 2))[1];
- $dctx = {
- Q => "?b=".uri_escape_utf8($pb, UNSAFE),
- };
- if ($pa ne $pb) {
- $dctx->{Q} .= '&a='.
- uri_escape_utf8($pa, UNSAFE);
- }
- anchor1($dst, $ctx, $linkify, $pb, $s) and next;
}
+ $pa = (split('/', git_unquote($pa), 2))[1];
+ $pb = (split('/', git_unquote($pb), 2))[1];
+ $dctx = {
+ Q => "?b=".uri_escape_utf8($pb, UNSAFE),
+ };
+ if ($pa ne $pb) {
+ $dctx->{Q} .= '&a='.
+ uri_escape_utf8($pa, UNSAFE);
+ }
+ anchor1($dst, $ctx, $linkify, $pb, $s) and next;
$$dst .= to_html($linkify, $s);
} elsif ($s =~ s/^(index $OID_NULL\.\.)($OID_BLOB)\b//o) {
$$dst .= $1 . oid($dctx, $spfx, $2);
@@ -160,7 +192,7 @@ sub flush_diff ($$$) {
$$dst .= to_html($linkify, $s);
} elsif ($s =~ m!^--- $PATH_A! ||
$s =~ m!^\+{3} $PATH_B!) {
- # color only (no oid link)
+ # color only (no oid link) if missing dctx->{oid_*}
$state <= DSTATE_STAT and
to_state($dst, $state, DSTATE_HEAD);
$$dst .= to_html($linkify, $s);
--
EW
^ permalink raw reply related [relevance 6%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2019-02-01 7:50 7% [PATCH 0/3] viewvcs odds and ends Eric Wong
2019-02-01 7:50 6% ` [PATCH 3/3] viewdiff: support renames and long paths in diffstat anchors Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).