diff options
Diffstat (limited to 't')
48 files changed, 4134 insertions, 109 deletions
@@ -319,6 +319,10 @@ GIT_TEST_OE_DELTA_SIZE=<n> exercises the uncomon pack-objects code path where deltas larger than this limit require extra memory allocation for bookkeeping. +GIT_TEST_VALIDATE_INDEX_CACHE_ENTRIES=<boolean> checks that cache-tree +records are valid when the index is written out or after a merge. This +is mostly to catch missing invalidation. Default is true. + GIT_TEST_COMMIT_GRAPH=<boolean>, when true, forces the commit-graph to be written after every 'git commit' command, and overrides the 'core.commitGraph' setting to true. diff --git a/t/chainlint.sed b/t/chainlint.sed index 8544df38df..70df40e34b 100644 --- a/t/chainlint.sed +++ b/t/chainlint.sed @@ -94,14 +94,14 @@ # here-doc -- swallow it to avoid false hits within its body (but keep the # command to which it was attached) -/<<[ ]*[-\\']*[A-Za-z0-9_]/ { - s/^\(.*\)<<[ ]*[-\\']*\([A-Za-z0-9_][A-Za-z0-9_]*\)'*/<\2>\1<</ +/<<[ ]*[-\\'"]*[A-Za-z0-9_]/ { + s/^\(.*\)<<[ ]*[-\\'"]*\([A-Za-z0-9_][A-Za-z0-9_]*\)['"]*/<\2>\1<</ s/[ ]*<<// - :hereslurp + :hered N /^<\([^>]*\)>.*\n[ ]*\1[ ]*$/!{ s/\n.*$// - bhereslurp + bhered } s/^<[^>]*>// s/\n.*$// @@ -131,9 +131,8 @@ b b :subshell -# bare "(" line? +# bare "(" line? -- stash for later printing /^[ ]*([ ]*$/ { - # stash for later printing h bnextline } @@ -150,7 +149,7 @@ s/.*\n// :slurp # incomplete line "...\" -/\\$/bincomplete +/\\$/bicmplte # multi-line quoted string "...\n..."? /"/bdqstring # multi-line quoted string '...\n...'? (but not contraction in string "it's") @@ -159,7 +158,7 @@ s/.*\n// } :folded # here-doc -- swallow it -/<<[ ]*[-\\']*[A-Za-z0-9_]/bheredoc +/<<[ ]*[-\\'"]*[A-Za-z0-9_]/bheredoc # comment or empty line -- discard since final non-comment, non-empty line # before closing ")", "done", "elsif", "else", or "fi" will need to be # re-visited to drop "suspect" marking since final line of those constructs @@ -172,7 +171,7 @@ s/.*\n// /"[^"]*#[^"]*"/!s/[ ]#.*$// } # one-liner "case ... esac" -/^[ ]*case[ ]*..*esac/bcheckchain +/^[ ]*case[ ]*..*esac/bchkchn # multi-line "case ... esac" /^[ ]*case[ ]..*[ ]in/bcase # multi-line "for ... done" or "while ... done" @@ -201,32 +200,32 @@ s/.*\n// /^[ ]*fi[ ]*[<>|]/bdone /^[ ]*fi[ ]*)/bdone # nested one-liner "(...) &&" -/^[ ]*(.*)[ ]*&&[ ]*$/bcheckchain +/^[ ]*(.*)[ ]*&&[ ]*$/bchkchn # nested one-liner "(...)" -/^[ ]*(.*)[ ]*$/bcheckchain +/^[ ]*(.*)[ ]*$/bchkchn # nested one-liner "(...) >x" (or "2>x" or "<x" or "|x") -/^[ ]*(.*)[ ]*[0-9]*[<>|]/bcheckchain +/^[ ]*(.*)[ ]*[0-9]*[<>|]/bchkchn # nested multi-line "(...\n...)" /^[ ]*(/bnest # multi-line "{...\n...}" /^[ ]*{/bblock # closing ")" on own line -- exit subshell -/^[ ]*)/bclosesolo +/^[ ]*)/bclssolo # "$((...))" -- arithmetic expansion; not closing ")" -/\$(([^)][^)]*))[^)]*$/bcheckchain +/\$(([^)][^)]*))[^)]*$/bchkchn # "$(...)" -- command substitution; not closing ")" -/\$([^)][^)]*)[^)]*$/bcheckchain +/\$([^)][^)]*)[^)]*$/bchkchn # multi-line "$(...\n...)" -- command substitution; treat as nested subshell /\$([^)]*$/bnest # "=(...)" -- Bash array assignment; not closing ")" -/=(/bcheckchain +/=(/bchkchn # closing "...) &&" /)[ ]*&&[ ]*$/bclose # closing "...)" /)[ ]*$/bclose # closing "...) >x" (or "2>x" or "<x" or "|x") /)[ ]*[<>|]/bclose -:checkchain +:chkchn # mark suspect if line uses ";" internally rather than "&&" (but not ";" in a # string and not ";;" in one-liner "case...esac") /;/{ @@ -245,7 +244,7 @@ n bslurp # found incomplete line "...\" -- slurp up next line -:incomplete +:icmplte N s/\\\n// bslurp @@ -281,13 +280,13 @@ bfolded # found here-doc -- swallow it to avoid false hits within its body (but keep # the command to which it was attached) :heredoc -s/^\(.*\)<<[ ]*[-\\']*\([A-Za-z0-9_][A-Za-z0-9_]*\)'*/<\2>\1<</ +s/^\(.*\)<<[ ]*[-\\'"]*\([A-Za-z0-9_][A-Za-z0-9_]*\)['"]*/<\2>\1<</ s/[ ]*<<// -:hereslurpsub +:heredsub N /^<\([^>]*\)>.*\n[ ]*\1[ ]*$/!{ s/\n.*$// - bhereslurpsub + bheredsub } s/^<[^>]*>// s/\n.*$// @@ -317,43 +316,43 @@ x # is 'done' or 'fi' cuddled with ")" to close subshell? /done.*)/bclose /fi.*)/bclose -bcheckchain +bchkchn # found nested multi-line "(...\n...)" -- pass through untouched :nest x -:nestslurp +:nstslurp n # closing ")" on own line -- stop nested slurp -/^[ ]*)/bnestclose +/^[ ]*)/bnstclose # comment -- not closing ")" if in comment -/^[ ]*#/bnestcontinue +/^[ ]*#/bnstcnt # "$((...))" -- arithmetic expansion; not closing ")" -/\$(([^)][^)]*))[^)]*$/bnestcontinue +/\$(([^)][^)]*))[^)]*$/bnstcnt # "$(...)" -- command substitution; not closing ")" -/\$([^)][^)]*)[^)]*$/bnestcontinue +/\$([^)][^)]*)[^)]*$/bnstcnt # closing "...)" -- stop nested slurp -/)/bnestclose -:nestcontinue +/)/bnstclose +:nstcnt x -bnestslurp -:nestclose +bnstslurp +:nstclose s/^/>>/ # is it "))" which closes nested and parent subshells? /)[ ]*)/bslurp -bcheckchain +bchkchn # found multi-line "{...\n...}" block -- pass through untouched :block x n # closing "}" -- stop block slurp -/}/bcheckchain +/}/bchkchn bblock # found closing ")" on own line -- drop "suspect" from final line of subshell # since that line legitimately lacks "&&" and exit subshell loop -:closesolo +:clssolo x s/?!AMP?!// p diff --git a/t/chainlint/here-doc.expect b/t/chainlint/here-doc.expect index aff6568716..534b065e38 100644 --- a/t/chainlint/here-doc.expect +++ b/t/chainlint/here-doc.expect @@ -4,4 +4,6 @@ cat >foo && cat >bar && +cat >boo && + horticulture diff --git a/t/chainlint/here-doc.test b/t/chainlint/here-doc.test index f2bb14b693..ad4ce8afd9 100644 --- a/t/chainlint/here-doc.test +++ b/t/chainlint/here-doc.test @@ -21,6 +21,13 @@ boz woz FUMP +# LINT: swallow "quoted" here-doc +cat <<"zump" >boo && +snoz +boz +woz +zump + # LINT: swallow here-doc (EOF is last line of test) horticulture <<\EOF gomez diff --git a/t/chainlint/subshell-here-doc.expect b/t/chainlint/subshell-here-doc.expect index 7663ea7fc4..74723e7340 100644 --- a/t/chainlint/subshell-here-doc.expect +++ b/t/chainlint/subshell-here-doc.expect @@ -6,5 +6,6 @@ ( cat >bup && cat >bup2 && + cat >bup3 && meep >) diff --git a/t/chainlint/subshell-here-doc.test b/t/chainlint/subshell-here-doc.test index b6b5a9b33a..f6b3ba4214 100644 --- a/t/chainlint/subshell-here-doc.test +++ b/t/chainlint/subshell-here-doc.test @@ -31,5 +31,9 @@ glink FIZZ ARBITRARY2 + cat <<-"ARBITRARY3" >bup3 && + glink + FIZZ + ARBITRARY3 meep ) diff --git a/t/check-non-portable-shell.pl b/t/check-non-portable-shell.pl index d5823f71d8..b45bdac688 100755 --- a/t/check-non-portable-shell.pl +++ b/t/check-non-portable-shell.pl @@ -41,6 +41,9 @@ while (<>) { /^\s*[^#]\s*which\s/ and err 'which is not portable (use type)'; /\btest\s+[^=]*==/ and err '"test a == b" is not portable (use =)'; /\bwc -l.*"\s*=/ and err '`"$(wc -l)"` is not portable (use test_line_count)'; + /\bhead\s+-c\b/ and err 'head -c is not portable (use test_copy_bytes BYTES <file >out)'; + /(?:\$\(seq|^\s*seq\b)/ and err 'seq is not portable (use test_seq)'; + /\bgrep\b.*--file\b/ and err 'grep --file FILE is not portable (use grep -f FILE)'; /\bexport\s+[A-Za-z0-9_]*=/ and err '"export FOO=bar" is not portable (use FOO=bar && export FOO)'; /^\s*([A-Z0-9_]+=(\w+|(["']).*?\3)\s+)+(\w+)/ and exists($func{$4}) and err '"FOO=bar shell_func" assignment extends beyond "shell_func"'; diff --git a/t/helper/test-dump-cache-tree.c b/t/helper/test-dump-cache-tree.c index 98a4891f1d..6a3f88f5f5 100644 --- a/t/helper/test-dump-cache-tree.c +++ b/t/helper/test-dump-cache-tree.c @@ -33,7 +33,7 @@ static int dump_cache_tree(struct cache_tree *it, } else { dump_one(it, pfx, ""); - if (oidcmp(&it->oid, &ref->oid) || + if (!oideq(&it->oid, &ref->oid) || ref->entry_count != it->entry_count || ref->subtree_nr != it->subtree_nr) { /* claims to be valid but is lying */ diff --git a/t/helper/test-reach.c b/t/helper/test-reach.c new file mode 100644 index 0000000000..eb21103998 --- /dev/null +++ b/t/helper/test-reach.c @@ -0,0 +1,130 @@ +#include "test-tool.h" +#include "cache.h" +#include "commit.h" +#include "commit-reach.h" +#include "config.h" +#include "parse-options.h" +#include "ref-filter.h" +#include "string-list.h" +#include "tag.h" + +static void print_sorted_commit_ids(struct commit_list *list) +{ + int i; + struct string_list s = STRING_LIST_INIT_DUP; + + while (list) { + string_list_append(&s, oid_to_hex(&list->item->object.oid)); + list = list->next; + } + + string_list_sort(&s); + + for (i = 0; i < s.nr; i++) + printf("%s\n", s.items[i].string); + + string_list_clear(&s, 0); +} + +int cmd__reach(int ac, const char **av) +{ + struct object_id oid_A, oid_B; + struct commit *A, *B; + struct commit_list *X, *Y; + struct commit **X_array; + int X_nr, X_alloc; + struct strbuf buf = STRBUF_INIT; + struct repository *r = the_repository; + + setup_git_directory(); + + if (ac < 2) + exit(1); + + A = B = NULL; + X = Y = NULL; + X_nr = 0; + X_alloc = 16; + ALLOC_ARRAY(X_array, X_alloc); + + while (strbuf_getline(&buf, stdin) != EOF) { + struct object_id oid; + struct object *o; + struct commit *c; + if (buf.len < 3) + continue; + + if (get_oid_committish(buf.buf + 2, &oid)) + die("failed to resolve %s", buf.buf + 2); + + o = parse_object(r, &oid); + o = deref_tag_noverify(o); + + if (!o) + die("failed to load commit for input %s resulting in oid %s\n", + buf.buf, oid_to_hex(&oid)); + + c = object_as_type(r, o, OBJ_COMMIT, 0); + + if (!c) + die("failed to load commit for input %s resulting in oid %s\n", + buf.buf, oid_to_hex(&oid)); + + switch (buf.buf[0]) { + case 'A': + oidcpy(&oid_A, &oid); + A = c; + break; + + case 'B': + oidcpy(&oid_B, &oid); + B = c; + break; + + case 'X': + commit_list_insert(c, &X); + ALLOC_GROW(X_array, X_nr + 1, X_alloc); + X_array[X_nr++] = c; + break; + + case 'Y': + commit_list_insert(c, &Y); + break; + + default: + die("unexpected start of line: %c", buf.buf[0]); + } + } + strbuf_release(&buf); + + if (!strcmp(av[1], "ref_newer")) + printf("%s(A,B):%d\n", av[1], ref_newer(&oid_A, &oid_B)); + else if (!strcmp(av[1], "in_merge_bases")) + printf("%s(A,B):%d\n", av[1], in_merge_bases(A, B)); + else if (!strcmp(av[1], "is_descendant_of")) + printf("%s(A,X):%d\n", av[1], is_descendant_of(A, X)); + else if (!strcmp(av[1], "get_merge_bases_many")) { + struct commit_list *list = get_merge_bases_many(A, X_nr, X_array); + printf("%s(A,X):\n", av[1]); + print_sorted_commit_ids(list); + } else if (!strcmp(av[1], "reduce_heads")) { + struct commit_list *list = reduce_heads(X); + printf("%s(X):\n", av[1]); + print_sorted_commit_ids(list); + } else if (!strcmp(av[1], "can_all_from_reach")) { + printf("%s(X,Y):%d\n", av[1], can_all_from_reach(X, Y, 1)); + } else if (!strcmp(av[1], "commit_contains")) { + struct ref_filter filter; + struct contains_cache cache; + init_contains_cache(&cache); + + if (ac > 2 && !strcmp(av[2], "--tag")) + filter.with_commit_tag_algo = 1; + else + filter.with_commit_tag_algo = 0; + + printf("%s(_,A,X,_):%d\n", av[1], commit_contains(&filter, A, X, &cache)); + } + + exit(0); +} diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c new file mode 100644 index 0000000000..831b586d02 --- /dev/null +++ b/t/helper/test-read-midx.c @@ -0,0 +1,51 @@ +#include "test-tool.h" +#include "cache.h" +#include "midx.h" +#include "repository.h" +#include "object-store.h" + +static int read_midx_file(const char *object_dir) +{ + uint32_t i; + struct multi_pack_index *m = load_multi_pack_index(object_dir, 1); + + if (!m) + return 1; + + printf("header: %08x %d %d %d\n", + m->signature, + m->version, + m->num_chunks, + m->num_packs); + + printf("chunks:"); + + if (m->chunk_pack_names) + printf(" pack-names"); + if (m->chunk_oid_fanout) + printf(" oid-fanout"); + if (m->chunk_oid_lookup) + printf(" oid-lookup"); + if (m->chunk_object_offsets) + printf(" object-offsets"); + if (m->chunk_large_offsets) + printf(" large-offsets"); + + printf("\nnum_objects: %d\n", m->num_objects); + + printf("packs:\n"); + for (i = 0; i < m->num_packs; i++) + printf("%s\n", m->pack_names[i]); + + printf("object-dir: %s\n", m->object_dir); + + return 0; +} + +int cmd__read_midx(int argc, const char **argv) +{ + if (argc != 2) + usage("read-midx <object-dir>"); + + return read_midx_file(argv[1]); +} diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c index 0edafcfd65..bef50c4dcc 100644 --- a/t/helper/test-tool.c +++ b/t/helper/test-tool.c @@ -27,7 +27,9 @@ static struct test_cmd cmds[] = { { "online-cpus", cmd__online_cpus }, { "path-utils", cmd__path_utils }, { "prio-queue", cmd__prio_queue }, + { "reach", cmd__reach }, { "read-cache", cmd__read_cache }, + { "read-midx", cmd__read_midx }, { "ref-store", cmd__ref_store }, { "regex", cmd__regex }, { "repository", cmd__repository }, diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h index e954e8c522..321982e4bc 100644 --- a/t/helper/test-tool.h +++ b/t/helper/test-tool.h @@ -23,7 +23,9 @@ int cmd__mktemp(int argc, const char **argv); int cmd__online_cpus(int argc, const char **argv); int cmd__path_utils(int argc, const char **argv); int cmd__prio_queue(int argc, const char **argv); +int cmd__reach(int argc, const char **argv); int cmd__read_cache(int argc, const char **argv); +int cmd__read_midx(int argc, const char **argv); int cmd__ref_store(int argc, const char **argv); int cmd__regex(int argc, const char **argv); int cmd__repository(int argc, const char **argv); diff --git a/t/lib-submodule-update.sh b/t/lib-submodule-update.sh index 5b56b23166..016391723c 100755 --- a/t/lib-submodule-update.sh +++ b/t/lib-submodule-update.sh @@ -235,7 +235,7 @@ reset_work_tree_to_interested () { then mkdir -p submodule_update/.git/modules/sub1/modules && cp -r submodule_update_repo/.git/modules/sub1/modules/sub2 submodule_update/.git/modules/sub1/modules/sub2 - # core.worktree is unset for sub2 as it is not checked out + GIT_WORK_TREE=. git -C submodule_update/.git/modules/sub1/modules/sub2 config --unset core.worktree fi && # indicate we are interested in the submodule: git -C submodule_update config submodule.sub1.url "bogus" && @@ -709,8 +709,7 @@ test_submodule_recursing_with_args_common() { git branch -t remove_sub1 origin/remove_sub1 && $command remove_sub1 && test_superproject_content origin/remove_sub1 && - ! test -e sub1 && - test_must_fail git config -f .git/modules/sub1/config core.worktree + ! test -e sub1 ) ' # ... absorbing a .git directory along the way. diff --git a/t/perf/README b/t/perf/README index 21321a0f36..be12090c38 100644 --- a/t/perf/README +++ b/t/perf/README @@ -168,3 +168,28 @@ that While we have tried to make sure that it can cope with embedded whitespace and other special characters, it will not work with multi-line data. + +Rather than tracking the performance by run-time as `test_perf` does, you +may also track output size by using `test_size`. The stdout of the +function should be a single numeric value, which will be captured and +shown in the aggregated output. For example: + + test_perf 'time foo' ' + ./foo >foo.out + ' + + test_size 'output size' + wc -c <foo.out + ' + +might produce output like: + + Test origin HEAD + ------------------------------------------------------------- + 1234.1 time foo 0.37(0.79+0.02) 0.26(0.51+0.02) -29.7% + 1234.2 output size 4.3M 3.6M -14.7% + +The item being measured (and its units) is up to the test; the context +and the test title should make it clear to the user whether bigger or +smaller numbers are better. Unlike test_perf, the test code will only be +run once, since output sizes tend to be more deterministic than timings. diff --git a/t/perf/aggregate.perl b/t/perf/aggregate.perl index bc865160e7..494907a892 100755 --- a/t/perf/aggregate.perl +++ b/t/perf/aggregate.perl @@ -13,27 +13,42 @@ sub get_times { my $line = <$fh>; return undef if not defined $line; close $fh or die "cannot close $name: $!"; - $line =~ /^(?:(\d+):)?(\d+):(\d+(?:\.\d+)?) (\d+(?:\.\d+)?) (\d+(?:\.\d+)?)$/ - or die "bad input line: $line"; - my $rt = ((defined $1 ? $1 : 0.0)*60+$2)*60+$3; - return ($rt, $4, $5); + # times + if ($line =~ /^(?:(\d+):)?(\d+):(\d+(?:\.\d+)?) (\d+(?:\.\d+)?) (\d+(?:\.\d+)?)$/) { + my $rt = ((defined $1 ? $1 : 0.0)*60+$2)*60+$3; + return ($rt, $4, $5); + # size + } elsif ($line =~ /^\d+$/) { + return $&; + } else { + die "bad input line: $line"; + } +} + +sub relative_change { + my ($r, $firstr) = @_; + if ($firstr > 0) { + return sprintf "%+.1f%%", 100.0*($r-$firstr)/$firstr; + } elsif ($r == 0) { + return "="; + } else { + return "+inf"; + } } sub format_times { my ($r, $u, $s, $firstr) = @_; + # no value means we did not finish the test if (!defined $r) { return "<missing>"; } - my $out = sprintf "%.2f(%.2f+%.2f)", $r, $u, $s; - if (defined $firstr) { - if ($firstr > 0) { - $out .= sprintf " %+.1f%%", 100.0*($r-$firstr)/$firstr; - } elsif ($r == 0) { - $out .= " ="; - } else { - $out .= " +inf"; - } + # a single value means we have a size, not times + if (!defined $u) { + return format_size($r, $firstr); } + # otherwise, we have real/user/system times + my $out = sprintf "%.2f(%.2f+%.2f)", $r, $u, $s; + $out .= ' ' . relative_change($r, $firstr) if defined $firstr; return $out; } @@ -51,6 +66,25 @@ EOT exit(1); } +sub human_size { + my $n = shift; + my @units = ('', qw(K M G)); + while ($n > 900 && @units > 1) { + $n /= 1000; + shift @units; + } + return $n unless length $units[0]; + return sprintf '%.1f%s', $n, $units[0]; +} + +sub format_size { + my ($size, $first) = @_; + # match the width of a time: 0.00(0.00+0.00) + my $out = sprintf '%15s', human_size($size); + $out .= ' ' . relative_change($size, $first) if defined $first; + return $out; +} + my (@dirs, %dirnames, %dirabbrevs, %prefixes, @tests, $codespeed, $sortby, $subsection, $reponame); @@ -181,7 +215,14 @@ sub print_default_results { my $firstr; for my $i (0..$#dirs) { my $d = $dirs[$i]; - $times{$prefixes{$d}.$t} = [get_times("$resultsdir/$prefixes{$d}$t.times")]; + my $base = "$resultsdir/$prefixes{$d}$t"; + $times{$prefixes{$d}.$t} = []; + foreach my $type (qw(times size)) { + if (-e "$base.$type") { + $times{$prefixes{$d}.$t} = [get_times("$base.$type")]; + last; + } + } my ($r,$u,$s) = @{$times{$prefixes{$d}.$t}}; my $w = length format_times($r,$u,$s,$firstr); $colwidth[$i] = $w if $w > $colwidth[$i]; diff --git a/t/perf/p5311-pack-bitmaps-fetch.sh b/t/perf/p5311-pack-bitmaps-fetch.sh new file mode 100755 index 0000000000..b04575951f --- /dev/null +++ b/t/perf/p5311-pack-bitmaps-fetch.sh @@ -0,0 +1,45 @@ +#!/bin/sh + +test_description='performance of fetches from bitmapped packs' +. ./perf-lib.sh + +test_perf_default_repo + +test_expect_success 'create bitmapped server repo' ' + git config pack.writebitmaps true && + git config pack.writebitmaphashcache true && + git repack -ad +' + +# simulate a fetch from a repository that last fetched N days ago, for +# various values of N. We do so by following the first-parent chain, +# and assume the first entry in the chain that is N days older than the current +# HEAD is where the HEAD would have been then. +for days in 1 2 4 8 16 32 64 128; do + title=$(printf '%10s' "($days days)") + test_expect_success "setup revs from $days days ago" ' + now=$(git log -1 --format=%ct HEAD) && + then=$(($now - ($days * 86400))) && + tip=$(git rev-list -1 --first-parent --until=$then HEAD) && + { + echo HEAD && + echo ^$tip + } >revs + ' + + test_perf "server $title" ' + git pack-objects --stdout --revs \ + --thin --delta-base-offset \ + <revs >tmp.pack + ' + + test_size "size $title" ' + wc -c <tmp.pack + ' + + test_perf "client $title" ' + git index-pack --stdin --fix-thin <tmp.pack + ' +done + +test_done diff --git a/t/perf/perf-lib.sh b/t/perf/perf-lib.sh index e4c343a6b7..11d1922cf5 100644 --- a/t/perf/perf-lib.sh +++ b/t/perf/perf-lib.sh @@ -179,8 +179,8 @@ exit $ret' >&3 2>&4 return "$eval_ret" } - -test_perf () { +test_wrapper_ () { + test_wrapper_func_=$1; shift test_start_ test "$#" = 3 && { test_prereq=$1; shift; } || test_prereq= test "$#" = 2 || @@ -191,35 +191,57 @@ test_perf () { base=$(basename "$0" .sh) echo "$test_count" >>"$perf_results_dir"/$base.subtests echo "$1" >"$perf_results_dir"/$base.$test_count.descr - if test -z "$verbose"; then - printf "%s" "perf $test_count - $1:" - else - echo "perf $test_count - $1:" - fi - for i in $(test_seq 1 $GIT_PERF_REPEAT_COUNT); do - say >&3 "running: $2" - if test_run_perf_ "$2" - then - if test -z "$verbose"; then - printf " %s" "$i" - else - echo "* timing run $i/$GIT_PERF_REPEAT_COUNT:" - fi + base="$perf_results_dir"/"$perf_results_prefix$(basename "$0" .sh)"."$test_count" + "$test_wrapper_func_" "$@" + fi + + test_finish_ +} + +test_perf_ () { + if test -z "$verbose"; then + printf "%s" "perf $test_count - $1:" + else + echo "perf $test_count - $1:" + fi + for i in $(test_seq 1 $GIT_PERF_REPEAT_COUNT); do + say >&3 "running: $2" + if test_run_perf_ "$2" + then + if test -z "$verbose"; then + printf " %s" "$i" else - test -z "$verbose" && echo - test_failure_ "$@" - break + echo "* timing run $i/$GIT_PERF_REPEAT_COUNT:" fi - done - if test -z "$verbose"; then - echo " ok" else - test_ok_ "$1" + test -z "$verbose" && echo + test_failure_ "$@" + break fi - base="$perf_results_dir"/"$perf_results_prefix$(basename "$0" .sh)"."$test_count" - "$TEST_DIRECTORY"/perf/min_time.perl test_time.* >"$base".times + done + if test -z "$verbose"; then + echo " ok" + else + test_ok_ "$1" fi - test_finish_ + "$TEST_DIRECTORY"/perf/min_time.perl test_time.* >"$base".times +} + +test_perf () { + test_wrapper_ test_perf_ "$@" +} + +test_size_ () { + say >&3 "running: $2" + if test_eval_ "$2" 3>"$base".size; then + test_ok_ "$1" + else + test_failure_ "$@" + fi +} + +test_size () { + test_wrapper_ test_size_ "$@" } # We extend test_done to print timings at the end (./run disables this diff --git a/t/t0019/parse_json.perl b/t/t0019/parse_json.perl index ca4e5bfa78..fea87fb81b 100644 --- a/t/t0019/parse_json.perl +++ b/t/t0019/parse_json.perl @@ -34,6 +34,9 @@ sub dump_item { } elsif (ref($value) eq 'HASH') { print "$label_in hash\n"; dump_hash($label_in, $value); + } elsif (ref $value) { + my $bool = $value ? 1 : 0; + print "$label_in $bool\n"; } elsif (defined $value) { print "$label_in $value\n"; } else { diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh index 12b8eb963a..7e87b5a200 100755 --- a/t/t0028-working-tree-encoding.sh +++ b/t/t0028-working-tree-encoding.sh @@ -203,7 +203,11 @@ test_expect_success 'error if encoding garbage is already in Git' ' test_i18ngrep "error: BOM is required" err.out ' -test_expect_success 'check roundtrip encoding' ' +test_lazy_prereq ICONV_SHIFT_JIS ' + iconv -f UTF-8 -t SHIFT-JIS </dev/null +' + +test_expect_success ICONV_SHIFT_JIS 'check roundtrip encoding' ' test_when_finished "rm -f roundtrip.shift roundtrip.utf16" && test_when_finished "git reset --hard HEAD" && diff --git a/t/t1090-sparse-checkout-scope.sh b/t/t1090-sparse-checkout-scope.sh index 1f61eb3e88..25d7c700f6 100755 --- a/t/t1090-sparse-checkout-scope.sh +++ b/t/t1090-sparse-checkout-scope.sh @@ -31,6 +31,20 @@ test_expect_success 'perform sparse checkout of master' ' test_path_is_file c ' +test_expect_success 'checkout -b checkout.optimizeNewBranch interaction' ' + cp .git/info/sparse-checkout .git/info/sparse-checkout.bak && + test_when_finished " + mv -f .git/info/sparse-checkout.bak .git/info/sparse-checkout + git checkout master + " && + echo "/b" >>.git/info/sparse-checkout && + test "$(git ls-files -t b)" = "S b" && + git -c checkout.optimizeNewBranch=true checkout -b fast && + test "$(git ls-files -t b)" = "S b" && + git checkout -b slow && + test "$(git ls-files -t b)" = "H b" +' + test_expect_success 'merge feature branch into sparse checkout of master' ' git merge feature && test_path_is_file a && diff --git a/t/t1404-update-ref-errors.sh b/t/t1404-update-ref-errors.sh index 2a42a589a4..51a4f4c0ac 100755 --- a/t/t1404-update-ref-errors.sh +++ b/t/t1404-update-ref-errors.sh @@ -559,9 +559,9 @@ test_expect_success 'no bogus intermediate values during delete' ' { # Note: the following command is intentionally run in the # background. We increase the timeout so that `update-ref` - # attempts to acquire the `packed-refs` lock for longer than - # it takes for us to do the check then delete it: - git -c core.packedrefstimeout=3000 update-ref -d $prefix/foo & + # attempts to acquire the `packed-refs` lock for much longer + # than it takes for us to do the check then delete it: + git -c core.packedrefstimeout=30000 update-ref -d $prefix/foo & } && pid2=$! && # Give update-ref plenty of time to get to the point where it tries diff --git a/t/t3206-range-diff.sh b/t/t3206-range-diff.sh index 2237c7f4af..88ebed1dfa 100755 --- a/t/t3206-range-diff.sh +++ b/t/t3206-range-diff.sh @@ -133,13 +133,64 @@ test_expect_success 'changed message' ' Z + Also a silly comment here! + - Zdiff --git a/file b/file - Z--- a/file - Z+++ b/file + Z diff --git a/file b/file + Z --- a/file + Z +++ b/file 3: 147e64e = 3: b9cb956 s/11/B/ 4: a63e992 = 4: 8add5f1 s/12/B/ EOF test_cmp expected actual ' +test_expect_success 'dual-coloring' ' + sed -e "s|^:||" >expect <<-\EOF && + :<YELLOW>1: a4b3333 = 1: f686024 s/5/A/<RESET> + :<RED>2: f51d370 <RESET><YELLOW>!<RESET><GREEN> 2: 4ab067d<RESET><YELLOW> s/4/A/<RESET> + : <REVERSE><CYAN>@@ -2,6 +2,8 @@<RESET> + : <RESET> + : s/4/A/<RESET> + : <RESET> + : <REVERSE><GREEN>+<RESET><BOLD> Also a silly comment here!<RESET> + : <REVERSE><GREEN>+<RESET> + : diff --git a/file b/file<RESET> + : --- a/file<RESET> + : +++ b/file<RESET> + :<RED>3: 0559556 <RESET><YELLOW>!<RESET><GREEN> 3: b9cb956<RESET><YELLOW> s/11/B/<RESET> + : <REVERSE><CYAN>@@ -10,7 +10,7 @@<RESET> + : 9<RESET> + : 10<RESET> + : <RED> -11<RESET> + : <REVERSE><RED>-<RESET><FAINT;GREEN>+BB<RESET> + : <REVERSE><GREEN>+<RESET><BOLD;GREEN>+B<RESET> + : 12<RESET> + : 13<RESET> + : 14<RESET> + :<RED>4: d966c5c <RESET><YELLOW>!<RESET><GREEN> 4: 8add5f1<RESET><YELLOW> s/12/B/<RESET> + : <REVERSE><CYAN>@@ -8,7 +8,7 @@<RESET> + : <CYAN> @@<RESET> + : 9<RESET> + : 10<RESET> + : <REVERSE><RED>-<RESET><FAINT> BB<RESET> + : <REVERSE><GREEN>+<RESET><BOLD> B<RESET> + : <RED> -12<RESET> + : <GREEN> +B<RESET> + : 13<RESET> + EOF + git range-diff changed...changed-message --color --dual-color >actual.raw && + test_decode_color >actual <actual.raw && + test_cmp expect actual +' + +for prev in topic master..topic +do + test_expect_success "format-patch --range-diff=$prev" ' + git format-patch --stdout --cover-letter --range-diff=$prev \ + master..unmodified >actual && + grep "= 1: .* s/5/A" actual && + grep "= 2: .* s/4/A" actual && + grep "= 3: .* s/11/B" actual && + grep "= 4: .* s/12/B" actual + ' +done + test_done diff --git a/t/t3401-rebase-and-am-rename.sh b/t/t3401-rebase-and-am-rename.sh index 8f832957fc..e0b5111993 100755 --- a/t/t3401-rebase-and-am-rename.sh +++ b/t/t3401-rebase-and-am-rename.sh @@ -5,7 +5,7 @@ test_description='git rebase + directory rename tests' . ./test-lib.sh . "$TEST_DIRECTORY"/lib-rebase.sh -test_expect_success 'setup testcase' ' +test_expect_success 'setup testcase where directory rename should be detected' ' test_create_repo dir-rename && ( cd dir-rename && @@ -102,4 +102,112 @@ test_expect_failure 'am: directory rename detected' ' ) ' +test_expect_success 'setup testcase where directory rename should NOT be detected' ' + test_create_repo no-dir-rename && + ( + cd no-dir-rename && + + mkdir x && + test_seq 1 10 >x/a && + test_seq 11 20 >x/b && + test_seq 21 30 >x/c && + echo original >project_info && + git add x project_info && + git commit -m "Initial" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo v2 >project_info && + git add project_info && + git commit -m "Modify project_info" && + + git checkout B && + mkdir y && + git mv x/c y/c && + echo v1 >project_info && + git add project_info && + git commit -m "Rename x/c to y/c, modify project_info" + ) +' + +test_expect_success 'rebase --interactive: NO directory rename' ' + test_when_finished "git -C no-dir-rename rebase --abort" && + ( + cd no-dir-rename && + + git checkout B^0 && + + set_fake_editor && + test_must_fail env FAKE_LINES="1" git rebase --interactive A && + + git ls-files -s >out && + test_line_count = 6 out && + + test_path_is_file x/a && + test_path_is_file x/b && + test_path_is_missing x/c + ) +' + +test_expect_success 'rebase (am): NO directory rename' ' + test_when_finished "git -C no-dir-rename rebase --abort" && + ( + cd no-dir-rename && + + git checkout B^0 && + + set_fake_editor && + test_must_fail git rebase A && + + git ls-files -s >out && + test_line_count = 6 out && + + test_path_is_file x/a && + test_path_is_file x/b && + test_path_is_missing x/c + ) +' + +test_expect_success 'rebase --merge: NO directory rename' ' + test_when_finished "git -C no-dir-rename rebase --abort" && + ( + cd no-dir-rename && + + git checkout B^0 && + + set_fake_editor && + test_must_fail git rebase --merge A && + + git ls-files -s >out && + test_line_count = 6 out && + + test_path_is_file x/a && + test_path_is_file x/b && + test_path_is_missing x/c + ) +' + +test_expect_success 'am: NO directory rename' ' + test_when_finished "git -C no-dir-rename am --abort" && + ( + cd no-dir-rename && + + git checkout A^0 && + + git format-patch -1 B && + + test_must_fail git am --3way 0001*.patch && + + git ls-files -s >out && + test_line_count = 6 out && + + test_path_is_file x/a && + test_path_is_file x/b && + test_path_is_missing x/c + ) +' + test_done diff --git a/t/t3404-rebase-interactive.sh b/t/t3404-rebase-interactive.sh index 259c27233d..86bba5ed7c 100755 --- a/t/t3404-rebase-interactive.sh +++ b/t/t3404-rebase-interactive.sh @@ -1426,9 +1426,21 @@ test_expect_success 'rebase -i --gpg-sign=<key-id> overrides commit.gpgSign' ' test_expect_success 'valid author header after --root swap' ' rebase_setup_and_clean author-header no-conflict-branch && set_fake_editor && - FAKE_LINES="2 1" git rebase -i --root && - git cat-file commit HEAD^ >out && - grep "^author ..*> [0-9][0-9]* [-+][0-9][0-9][0-9][0-9]$" out + git commit --amend --author="Au ${SQ}thor <author@example.com>" --no-edit && + git cat-file commit HEAD | grep ^author >expected && + FAKE_LINES="5 1" git rebase -i --root && + git cat-file commit HEAD^ | grep ^author >actual && + test_cmp expected actual +' + +test_expect_success 'valid author header when author contains single quote' ' + rebase_setup_and_clean author-header no-conflict-branch && + set_fake_editor && + git commit --amend --author="Au ${SQ}thor <author@example.com>" --no-edit && + git cat-file commit HEAD | grep ^author >expected && + FAKE_LINES="2" git rebase -i HEAD~2 && + git cat-file commit HEAD | grep ^author >actual && + test_cmp expected actual ' test_done diff --git a/t/t4013-diff-various.sh b/t/t4013-diff-various.sh index f8d853595b..73f7038253 100755 --- a/t/t4013-diff-various.sh +++ b/t/t4013-diff-various.sh @@ -140,7 +140,7 @@ do expect="$TEST_DIRECTORY/t4013/diff.$test" actual="$pfx-diff.$test" - test_expect_success "git $cmd # magic is ${magic:-"(not used)"}" ' + test_expect_success "git $cmd # magic is ${magic:-(not used)}" ' { echo "$ git $cmd" case "$magic" in diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index 53880da7bb..909c743c13 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -1717,4 +1717,38 @@ test_expect_success 'format-patch --pretty=mboxrd' ' test_cmp expect actual ' +test_expect_success 'interdiff: setup' ' + git checkout -b boop master && + test_commit fnorp blorp && + test_commit fleep blorp +' + +test_expect_success 'interdiff: cover-letter' ' + sed "y/q/ /" >expect <<-\EOF && + +fleep + --q + EOF + git format-patch --cover-letter --interdiff=boop~2 -1 boop && + test_i18ngrep "^Interdiff:$" 0000-cover-letter.patch && + test_i18ngrep ! "^Interdiff:$" 0001-fleep.patch && + sed "1,/^@@ /d; /^-- $/q" <0000-cover-letter.patch >actual && + test_cmp expect actual +' + +test_expect_success 'interdiff: reroll-count' ' + git format-patch --cover-letter --interdiff=boop~2 -v2 -1 boop && + test_i18ngrep "^Interdiff ..* v1:$" v2-0000-cover-letter.patch +' + +test_expect_success 'interdiff: solo-patch' ' + cat >expect <<-\EOF && + +fleep + + EOF + git format-patch --interdiff=boop~2 -1 boop && + test_i18ngrep "^Interdiff:$" 0001-fleep.patch && + sed "1,/^ @@ /d; /^$/q" <0001-fleep.patch >actual && + test_cmp expect actual +' + test_done diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh index 65da74c766..428b3c1e9e 100755 --- a/t/t4200-rerere.sh +++ b/t/t4200-rerere.sh @@ -577,4 +577,69 @@ test_expect_success 'multiple identical conflicts' ' count_pre_post 0 0 ' +test_expect_success 'rerere with unexpected conflict markers does not crash' ' + git reset --hard && + + git checkout -b branch-1 master && + echo "bar" >test && + git add test && + git commit -q -m two && + + git reset --hard && + git checkout -b branch-2 master && + echo "foo" >test && + git add test && + git commit -q -a -m one && + + test_must_fail git merge branch-1 && + echo "<<<<<<< a" >test && + git rerere && + + git rerere clear +' + +test_expect_success 'rerere with inner conflict markers' ' + git reset --hard && + + git checkout -b A master && + echo "bar" >test && + git add test && + git commit -q -m two && + echo "baz" >test && + git add test && + git commit -q -m three && + + git reset --hard && + git checkout -b B master && + echo "foo" >test && + git add test && + git commit -q -a -m one && + + test_must_fail git merge A~ && + git add test && + git commit -q -m "will solve conflicts later" && + test_must_fail git merge A && + + echo "resolved" >test && + git add test && + git commit -q -m "solved conflict" && + + echo "resolved" >expect && + + git reset --hard HEAD~~ && + test_must_fail git merge A~ && + git add test && + git commit -q -m "will solve conflicts later" && + test_must_fail git merge A && + cat test >actual && + test_cmp expect actual && + + git add test && + git commit -m "rerere solved conflict" && + git reset --hard HEAD~ && + test_must_fail git merge A && + cat test >actual && + test_cmp expect actual +' + test_done diff --git a/t/t4205-log-pretty-formats.sh b/t/t4205-log-pretty-formats.sh index 2052cadb11..978a8a66ff 100755 --- a/t/t4205-log-pretty-formats.sh +++ b/t/t4205-log-pretty-formats.sh @@ -598,4 +598,27 @@ test_expect_success ':only and :unfold work together' ' test_cmp expect actual ' +test_expect_success 'trailer parsing not fooled by --- line' ' + git commit --allow-empty -F - <<-\EOF && + this is the subject + + This is the body. The message has a "---" line which would confuse a + message+patch parser. But here we know we have only a commit message, + so we get it right. + + trailer: wrong + --- + This is more body. + + trailer: right + EOF + + { + echo "trailer: right" && + echo + } >expect && + git log --no-walk --format="%(trailers)" >actual && + test_cmp expect actual +' + test_done diff --git a/t/t4256-am-format-flowed.sh b/t/t4256-am-format-flowed.sh new file mode 100755 index 0000000000..6340310e9a --- /dev/null +++ b/t/t4256-am-format-flowed.sh @@ -0,0 +1,19 @@ +#!/bin/sh + +test_description='test format=flowed support of git am' + +. ./test-lib.sh + +test_expect_success 'setup' ' + cp "$TEST_DIRECTORY/t4256/1/mailinfo.c.orig" mailinfo.c && + git add mailinfo.c && + git commit -m initial +' + +test_expect_success 'am with format=flowed' ' + git am <"$TEST_DIRECTORY/t4256/1/patch" >stdout 2>stderr && + test_i18ngrep "warning: Patch sent with format=flowed" stderr && + test_cmp "$TEST_DIRECTORY/t4256/1/mailinfo.c" mailinfo.c +' + +test_done diff --git a/t/t4256/1/mailinfo.c b/t/t4256/1/mailinfo.c new file mode 100644 index 0000000000..b395adbdf2 --- /dev/null +++ b/t/t4256/1/mailinfo.c @@ -0,0 +1,1245 @@ +#include "cache.h" +#include "config.h" +#include "utf8.h" +#include "strbuf.h" +#include "mailinfo.h" + +static void cleanup_space(struct strbuf *sb) +{ + size_t pos, cnt; + for (pos = 0; pos < sb->len; pos++) { + if (isspace(sb->buf[pos])) { + sb->buf[pos] = ' '; + for (cnt = 0; isspace(sb->buf[pos + cnt + 1]); cnt++); + strbuf_remove(sb, pos + 1, cnt); + } + } +} + +static void get_sane_name(struct strbuf *out, struct strbuf *name, struct strbuf *email) +{ + struct strbuf *src = name; + if (name->len < 3 || 60 < name->len || strchr(name->buf, '@') || + strchr(name->buf, '<') || strchr(name->buf, '>')) + src = email; + else if (name == out) + return; + strbuf_reset(out); + strbuf_addbuf(out, src); +} + +static void parse_bogus_from(struct mailinfo *mi, const struct strbuf *line) +{ + /* John Doe <johndoe> */ + + char *bra, *ket; + /* This is fallback, so do not bother if we already have an + * e-mail address. + */ + if (mi->email.len) + return; + + bra = strchr(line->buf, '<'); + if (!bra) + return; + ket = strchr(bra, '>'); + if (!ket) + return; + + strbuf_reset(&mi->email); + strbuf_add(&mi->email, bra + 1, ket - bra - 1); + + strbuf_reset(&mi->name); + strbuf_add(&mi->name, line->buf, bra - line->buf); + strbuf_trim(&mi->name); + get_sane_name(&mi->name, &mi->name, &mi->email); +} + +static const char *unquote_comment(struct strbuf *outbuf, const char *in) +{ + int c; + int take_next_literally = 0; + + strbuf_addch(outbuf, '('); + + while ((c = *in++) != 0) { + if (take_next_literally == 1) { + take_next_literally = 0; + } else { + switch (c) { + case '\\': + take_next_literally = 1; + continue; + case '(': + in = unquote_comment(outbuf, in); + continue; + case ')': + strbuf_addch(outbuf, ')'); + return in; + } + } + + strbuf_addch(outbuf, c); + } + + return in; +} + +static const char *unquote_quoted_string(struct strbuf *outbuf, const char *in) +{ + int c; + int take_next_literally = 0; + + while ((c = *in++) != 0) { + if (take_next_literally == 1) { + take_next_literally = 0; + } else { + switch (c) { + case '\\': + take_next_literally = 1; + continue; + case '"': + return in; + } + } + + strbuf_addch(outbuf, c); + } + + return in; +} + +static void unquote_quoted_pair(struct strbuf *line) +{ + struct strbuf outbuf; + const char *in = line->buf; + int c; + + strbuf_init(&outbuf, line->len); + + while ((c = *in++) != 0) { + switch (c) { + case '"': + in = unquote_quoted_string(&outbuf, in); + continue; + case '(': + in = unquote_comment(&outbuf, in); + continue; + } + + strbuf_addch(&outbuf, c); + } + + strbuf_swap(&outbuf, line); + strbuf_release(&outbuf); + +} + +static void handle_from(struct mailinfo *mi, const struct strbuf *from) +{ + char *at; + size_t el; + struct strbuf f; + + strbuf_init(&f, from->len); + strbuf_addbuf(&f, from); + + unquote_quoted_pair(&f); + + at = strchr(f.buf, '@'); + if (!at) { + parse_bogus_from(mi, from); + goto out; + } + + /* + * If we already have one email, don't take any confusing lines + */ + if (mi->email.len && strchr(at + 1, '@')) + goto out; + + /* Pick up the string around '@', possibly delimited with <> + * pair; that is the email part. + */ + while (at > f.buf) { + char c = at[-1]; + if (isspace(c)) + break; + if (c == '<') { + at[-1] = ' '; + break; + } + at--; + } + el = strcspn(at, " \n\t\r\v\f>"); + strbuf_reset(&mi->email); + strbuf_add(&mi->email, at, el); + strbuf_remove(&f, at - f.buf, el + (at[el] ? 1 : 0)); + + /* The remainder is name. It could be + * + * - "John Doe <john.doe@xz>" (a), or + * - "john.doe@xz (John Doe)" (b), or + * - "John (zzz) Doe <john.doe@xz> (Comment)" (c) + * + * but we have removed the email part, so + * + * - remove extra spaces which could stay after email (case 'c'), and + * - trim from both ends, possibly removing the () pair at the end + * (cases 'a' and 'b'). + */ + cleanup_space(&f); + strbuf_trim(&f); + if (f.buf[0] == '(' && f.len && f.buf[f.len - 1] == ')') { + strbuf_remove(&f, 0, 1); + strbuf_setlen(&f, f.len - 1); + } + + get_sane_name(&mi->name, &f, &mi->email); +out: + strbuf_release(&f); +} + +static void handle_header(struct strbuf **out, const struct strbuf *line) +{ + if (!*out) { + *out = xmalloc(sizeof(struct strbuf)); + strbuf_init(*out, line->len); + } else + strbuf_reset(*out); + + strbuf_addbuf(*out, line); +} + +/* NOTE NOTE NOTE. We do not claim we do full MIME. We just attempt + * to have enough heuristics to grok MIME encoded patches often found + * on our mailing lists. For example, we do not even treat header lines + * case insensitively. + */ + +static int slurp_attr(const char *line, const char *name, struct strbuf *attr) +{ + const char *ends, *ap = strcasestr(line, name); + size_t sz; + + strbuf_setlen(attr, 0); + if (!ap) + return 0; + ap += strlen(name); + if (*ap == '"') { + ap++; + ends = "\""; + } + else + ends = "; \t"; + sz = strcspn(ap, ends); + strbuf_add(attr, ap, sz); + return 1; +} + +static int has_attr_value(const char *line, const char *name, const char *value) +{ + struct strbuf sb = STRBUF_INIT; + int rc = slurp_attr(line, name, &sb) && !strcasecmp(sb.buf, value); + strbuf_release(&sb); + return rc; +} + +static void handle_content_type(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf *boundary = xmalloc(sizeof(struct strbuf)); + strbuf_init(boundary, line->len); + + mi->format_flowed = has_attr_value(line->buf, "format=", "flowed"); + mi->delsp = has_attr_value(line->buf, "delsp=", "yes"); + + if (slurp_attr(line->buf, "boundary=", boundary)) { + strbuf_insert(boundary, 0, "--", 2); + if (++mi->content_top >= &mi->content[MAX_BOUNDARIES]) { + error("Too many boundaries to handle"); + mi->input_error = -1; + mi->content_top = &mi->content[MAX_BOUNDARIES] - 1; + return; + } + *(mi->content_top) = boundary; + boundary = NULL; + } + slurp_attr(line->buf, "charset=", &mi->charset); + + if (boundary) { + strbuf_release(boundary); + free(boundary); + } +} + +static void handle_content_transfer_encoding(struct mailinfo *mi, + const struct strbuf *line) +{ + if (strcasestr(line->buf, "base64")) + mi->transfer_encoding = TE_BASE64; + else if (strcasestr(line->buf, "quoted-printable")) + mi->transfer_encoding = TE_QP; + else + mi->transfer_encoding = TE_DONTCARE; +} + +static int is_multipart_boundary(struct mailinfo *mi, const struct strbuf *line) +{ + struct strbuf *content_top = *(mi->content_top); + + return ((content_top->len <= line->len) && + !memcmp(line->buf, content_top->buf, content_top->len)); +} + +static void cleanup_subject(struct mailinfo *mi, struct strbuf *subject) +{ + size_t at = 0; + + while (at < subject->len) { + char *pos; + size_t remove; + + switch (subject->buf[at]) { + case 'r': case 'R': + if (subject->len <= at + 3) + break; + if ((subject->buf[at + 1] == 'e' || + subject->buf[at + 1] == 'E') && + subject->buf[at + 2] == ':') { + strbuf_remove(subject, at, 3); + continue; + } + at++; + break; + case ' ': case '\t': case ':': + strbuf_remove(subject, at, 1); + continue; + case '[': + pos = strchr(subject->buf + at, ']'); + if (!pos) + break; + remove = pos - subject->buf + at + 1; + if (!mi->keep_non_patch_brackets_in_subject || + (7 <= remove && + memmem(subject->buf + at, remove, "PATCH", 5))) + strbuf_remove(subject, at, remove); + else { + at += remove; + /* + * If the input had a space after the ], keep + * it. We don't bother with finding the end of + * the space, since we later normalize it + * anyway. + */ + if (isspace(subject->buf[at])) + at += 1; + } + continue; + } + break; + } + strbuf_trim(subject); +} + +#define MAX_HDR_PARSED 10 +static const char *header[MAX_HDR_PARSED] = { + "From","Subject","Date", +}; + +static inline int cmp_header(const struct strbuf *line, const char *hdr) +{ + int len = strlen(hdr); + return !strncasecmp(line->buf, hdr, len) && line->len > len && + line->buf[len] == ':' && isspace(line->buf[len + 1]); +} + +static int is_format_patch_separator(const char *line, int len) +{ + static const char SAMPLE[] = + "From e6807f3efca28b30decfecb1732a56c7db1137ee Mon Sep 17 00:00:00 2001\n"; + const char *cp; + + if (len != strlen(SAMPLE)) + return 0; + if (!skip_prefix(line, "From ", &cp)) + return 0; + if (strspn(cp, "0123456789abcdef") != 40) + return 0; + cp += 40; + return !memcmp(SAMPLE + (cp - line), cp, strlen(SAMPLE) - (cp - line)); +} + +static struct strbuf *decode_q_segment(const struct strbuf *q_seg, int rfc2047) +{ + const char *in = q_seg->buf; + int c; + struct strbuf *out = xmalloc(sizeof(struct strbuf)); + strbuf_init(out, q_seg->len); + + while ((c = *in++) != 0) { + if (c == '=') { + int ch, d = *in; + if (d == '\n' || !d) + break; /* drop trailing newline */ + ch = hex2chr(in); + if (ch >= 0) { + strbuf_addch(out, ch); + in += 2; + continue; + } + /* garbage -- fall through */ + } + if (rfc2047 && c == '_') /* rfc2047 4.2 (2) */ + c = 0x20; + strbuf_addch(out, c); + } + return out; +} + +static struct strbuf *decode_b_segment(const struct strbuf *b_seg) +{ + /* Decode in..ep, possibly in-place to ot */ + int c, pos = 0, acc = 0; + const char *in = b_seg->buf; + struct strbuf *out = xmalloc(sizeof(struct strbuf)); + strbuf_init(out, b_seg->len); + + while ((c = *in++) != 0) { + if (c == '+') + c = 62; + else if (c == '/') + c = 63; + else if ('A' <= c && c <= 'Z') + c -= 'A'; + else if ('a' <= c && c <= 'z') + c -= 'a' - 26; + else if ('0' <= c && c <= '9') + c -= '0' - 52; + else + continue; /* garbage */ + switch (pos++) { + case 0: + acc = (c << 2); + break; + case 1: + strbuf_addch(out, (acc | (c >> 4))); + acc = (c & 15) << 4; + break; + case 2: + strbuf_addch(out, (acc | (c >> 2))); + acc = (c & 3) << 6; + break; + case 3: + strbuf_addch(out, (acc | c)); + acc = pos = 0; + break; + } + } + return out; +} + +static int convert_to_utf8(struct mailinfo *mi, + struct strbuf *line, const char *charset) +{ + char *out; + + if (!mi->metainfo_charset || !charset || !*charset) + return 0; + + if (same_encoding(mi->metainfo_charset, charset)) + return 0; + out = reencode_string(line->buf, mi->metainfo_charset, charset); + if (!out) { + mi->input_error = -1; + return error("cannot convert from %s to %s", + charset, mi->metainfo_charset); + } + strbuf_attach(line, out, strlen(out), strlen(out)); + return 0; +} + +static void decode_header(struct mailinfo *mi, struct strbuf *it) +{ + char *in, *ep, *cp; + struct strbuf outbuf = STRBUF_INIT, *dec; + struct strbuf charset_q = STRBUF_INIT, piecebuf = STRBUF_INIT; + int found_error = 1; /* pessimism */ + + in = it->buf; + while (in - it->buf <= it->len && (ep = strstr(in, "=?")) != NULL) { + int encoding; + strbuf_reset(&charset_q); + strbuf_reset(&piecebuf); + + if (in != ep) { + /* + * We are about to process an encoded-word + * that begins at ep, but there is something + * before the encoded word. + */ + char *scan; + for (scan = in; scan < ep; scan++) + if (!isspace(*scan)) + break; + + if (scan != ep || in == it->buf) { + /* + * We should not lose that "something", + * unless we have just processed an + * encoded-word, and there is only LWS + * before the one we are about to process. + */ + strbuf_add(&outbuf, in, ep - in); + } + } + /* E.g. + * ep : "=?iso-2022-jp?B?GyR...?= foo" + * ep : "=?ISO-8859-1?Q?Foo=FCbar?= baz" + */ + ep += 2; + + if (ep - it->buf >= it->len || !(cp = strchr(ep, '?'))) + goto release_return; + + if (cp + 3 - it->buf > it->len) + goto release_return; + strbuf_add(&charset_q, ep, cp - ep); + + encoding = cp[1]; + if (!encoding || cp[2] != '?') + goto release_return; + ep = strstr(cp + 3, "?="); + if (!ep) + goto release_return; + strbuf_add(&piecebuf, cp + 3, ep - cp - 3); + switch (tolower(encoding)) { + default: + goto release_return; + case 'b': + dec = decode_b_segment(&piecebuf); + break; + case 'q': + dec = decode_q_segment(&piecebuf, 1); + break; + } + if (convert_to_utf8(mi, dec, charset_q.buf)) + goto release_return; + + strbuf_addbuf(&outbuf, dec); + strbuf_release(dec); + free(dec); + in = ep + 2; + } + strbuf_addstr(&outbuf, in); + strbuf_reset(it); + strbuf_addbuf(it, &outbuf); + found_error = 0; +release_return: + strbuf_release(&outbuf); + strbuf_release(&charset_q); + strbuf_release(&piecebuf); + + if (found_error) + mi->input_error = -1; +} + +static int check_header(struct mailinfo *mi, + const struct strbuf *line, + struct strbuf *hdr_data[], int overwrite) +{ + int i, ret = 0, len; + struct strbuf sb = STRBUF_INIT; + + /* search for the interesting parts */ + for (i = 0; header[i]; i++) { + int len = strlen(header[i]); + if ((!hdr_data[i] || overwrite) && cmp_header(line, header[i])) { + /* Unwrap inline B and Q encoding, and optionally + * normalize the meta information to utf8. + */ + strbuf_add(&sb, line->buf + len + 2, line->len - len - 2); + decode_header(mi, &sb); + handle_header(&hdr_data[i], &sb); + ret = 1; + goto check_header_out; + } + } + + /* Content stuff */ + if (cmp_header(line, "Content-Type")) { + len = strlen("Content-Type: "); + strbuf_add(&sb, line->buf + len, line->len - len); + decode_header(mi, &sb); + strbuf_insert(&sb, 0, "Content-Type: ", len); + handle_content_type(mi, &sb); + ret = 1; + goto check_header_out; + } + if (cmp_header(line, "Content-Transfer-Encoding")) { + len = strlen("Content-Transfer-Encoding: "); + strbuf_add(&sb, line->buf + len, line->len - len); + decode_header(mi, &sb); + handle_content_transfer_encoding(mi, &sb); + ret = 1; + goto check_header_out; + } + if (cmp_header(line, "Message-Id")) { + len = strlen("Message-Id: "); + strbuf_add(&sb, line->buf + len, line->len - len); + decode_header(mi, &sb); + if (mi->add_message_id) + mi->message_id = strbuf_detach(&sb, NULL); + ret = 1; + goto check_header_out; + } + +check_header_out: + strbuf_release(&sb); + return ret; +} + +/* + * Returns 1 if the given line or any line beginning with the given line is an + * in-body header (that is, check_header will succeed when passed + * mi->s_hdr_data). + */ +static int is_inbody_header(const struct mailinfo *mi, + const struct strbuf *line) +{ + int i; + for (i = 0; header[i]; i++) + if (!mi->s_hdr_data[i] && cmp_header(line, header[i])) + return 1; + return 0; +} + +static void decode_transfer_encoding(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf *ret; + + switch (mi->transfer_encoding) { + case TE_QP: + ret = decode_q_segment(line, 0); + break; + case TE_BASE64: + ret = decode_b_segment(line); + break; + case TE_DONTCARE: + default: + return; + } + strbuf_reset(line); + strbuf_addbuf(line, ret); + strbuf_release(ret); + free(ret); +} + +static inline int patchbreak(const struct strbuf *line) +{ + size_t i; + + /* Beginning of a "diff -" header? */ + if (starts_with(line->buf, "diff -")) + return 1; + + /* CVS "Index: " line? */ + if (starts_with(line->buf, "Index: ")) + return 1; + + /* + * "--- <filename>" starts patches without headers + * "---<sp>*" is a manual separator + */ + if (line->len < 4) + return 0; + + if (starts_with(line->buf, "---")) { + /* space followed by a filename? */ + if (line->buf[3] == ' ' && !isspace(line->buf[4])) + return 1; + /* Just whitespace? */ + for (i = 3; i < line->len; i++) { + unsigned char c = line->buf[i]; + if (c == '\n') + return 1; + if (!isspace(c)) + break; + } + return 0; + } + return 0; +} + +static int is_scissors_line(const char *line) +{ + const char *c; + int scissors = 0, gap = 0; + const char *first_nonblank = NULL, *last_nonblank = NULL; + int visible, perforation = 0, in_perforation = 0; + + for (c = line; *c; c++) { + if (isspace(*c)) { + if (in_perforation) { + perforation++; + gap++; + } + continue; + } + last_nonblank = c; + if (first_nonblank == NULL) + first_nonblank = c; + if (*c == '-') { + in_perforation = 1; + perforation++; + continue; + } + if ((!memcmp(c, ">8", 2) || !memcmp(c, "8<", 2) || + !memcmp(c, ">%", 2) || !memcmp(c, "%<", 2))) { + in_perforation = 1; + perforation += 2; + scissors += 2; + c++; + continue; + } + in_perforation = 0; + } + + /* + * The mark must be at least 8 bytes long (e.g. "-- >8 --"). + * Even though there can be arbitrary cruft on the same line + * (e.g. "cut here"), in order to avoid misidentification, the + * perforation must occupy more than a third of the visible + * width of the line, and dashes and scissors must occupy more + * than half of the perforation. + */ + + if (first_nonblank && last_nonblank) + visible = last_nonblank - first_nonblank + 1; + else + visible = 0; + return (scissors && 8 <= visible && + visible < perforation * 3 && + gap * 2 < perforation); +} + +static void flush_inbody_header_accum(struct mailinfo *mi) +{ + if (!mi->inbody_header_accum.len) + return; + if (!check_header(mi, &mi->inbody_header_accum, mi->s_hdr_data, 0)) + BUG("inbody_header_accum, if not empty, must always contain a valid in-body header"); + strbuf_reset(&mi->inbody_header_accum); +} + +static int check_inbody_header(struct mailinfo *mi, const struct strbuf *line) +{ + if (mi->inbody_header_accum.len && + (line->buf[0] == ' ' || line->buf[0] == '\t')) { + if (mi->use_scissors && is_scissors_line(line->buf)) { + /* + * This is a scissors line; do not consider this line + * as a header continuation line. + */ + flush_inbody_header_accum(mi); + return 0; + } + strbuf_strip_suffix(&mi->inbody_header_accum, "\n"); + strbuf_addbuf(&mi->inbody_header_accum, line); + return 1; + } + + flush_inbody_header_accum(mi); + + if (starts_with(line->buf, ">From") && isspace(line->buf[5])) + return is_format_patch_separator(line->buf + 1, line->len - 1); + if (starts_with(line->buf, "[PATCH]") && isspace(line->buf[7])) { + int i; + for (i = 0; header[i]; i++) + if (!strcmp("Subject", header[i])) { + handle_header(&mi->s_hdr_data[i], line); + return 1; + } + return 0; + } + if (is_inbody_header(mi, line)) { + strbuf_addbuf(&mi->inbody_header_accum, line); + return 1; + } + return 0; +} + +static int handle_commit_msg(struct mailinfo *mi, struct strbuf *line) +{ + assert(!mi->filter_stage); + + if (mi->header_stage) { + if (!line->len || (line->len == 1 && line->buf[0] == '\n')) { + if (mi->inbody_header_accum.len) { + flush_inbody_header_accum(mi); + mi->header_stage = 0; + } + return 0; + } + } + + if (mi->use_inbody_headers && mi->header_stage) { + mi->header_stage = check_inbody_header(mi, line); + if (mi->header_stage) + return 0; + } else + /* Only trim the first (blank) line of the commit message + * when ignoring in-body headers. + */ + mi->header_stage = 0; + + /* normalize the log message to UTF-8. */ + if (convert_to_utf8(mi, line, mi->charset.buf)) + return 0; /* mi->input_error already set */ + + if (mi->use_scissors && is_scissors_line(line->buf)) { + int i; + + strbuf_setlen(&mi->log_message, 0); + mi->header_stage = 1; + + /* + * We may have already read "secondary headers"; purge + * them to give ourselves a clean restart. + */ + for (i = 0; header[i]; i++) { + if (mi->s_hdr_data[i]) + strbuf_release(mi->s_hdr_data[i]); + mi->s_hdr_data[i] = NULL; + } + return 0; + } + + if (patchbreak(line)) { + if (mi->message_id) + strbuf_addf(&mi->log_message, + "Message-Id: %s\n", mi->message_id); + return 1; + } + + strbuf_addbuf(&mi->log_message, line); + return 0; +} + +static void handle_patch(struct mailinfo *mi, const struct strbuf *line) +{ + fwrite(line->buf, 1, line->len, mi->patchfile); + mi->patch_lines++; +} + +static void handle_filter(struct mailinfo *mi, struct strbuf *line) +{ + switch (mi->filter_stage) { + case 0: + if (!handle_commit_msg(mi, line)) + break; + mi->filter_stage++; + /* fallthrough */ + case 1: + handle_patch(mi, line); + break; + } +} + +static int is_rfc2822_header(const struct strbuf *line) +{ + /* + * The section that defines the loosest possible + * field name is "3.6.8 Optional fields". + * + * optional-field = field-name ":" unstructured CRLF + * field-name = 1*ftext + * ftext = %d33-57 / %59-126 + */ + int ch; + char *cp = line->buf; + + /* Count mbox From headers as headers */ + if (starts_with(cp, "From ") || starts_with(cp, ">From ")) + return 1; + + while ((ch = *cp++)) { + if (ch == ':') + return 1; + if ((33 <= ch && ch <= 57) || + (59 <= ch && ch <= 126)) + continue; + break; + } + return 0; +} + +static int read_one_header_line(struct strbuf *line, FILE *in) +{ + struct strbuf continuation = STRBUF_INIT; + + /* Get the first part of the line. */ + if (strbuf_getline_lf(line, in)) + return 0; + + /* + * Is it an empty line or not a valid rfc2822 header? + * If so, stop here, and return false ("not a header") + */ + strbuf_rtrim(line); + if (!line->len || !is_rfc2822_header(line)) { + /* Re-add the newline */ + strbuf_addch(line, '\n'); + return 0; + } + + /* + * Now we need to eat all the continuation lines.. + * Yuck, 2822 header "folding" + */ + for (;;) { + int peek; + + peek = fgetc(in); + if (peek == EOF) + break; + ungetc(peek, in); + if (peek != ' ' && peek != '\t') + break; + if (strbuf_getline_lf(&continuation, in)) + break; + continuation.buf[0] = ' '; + strbuf_rtrim(&continuation); + strbuf_addbuf(line, &continuation); + } + strbuf_release(&continuation); + + return 1; +} + +static int find_boundary(struct mailinfo *mi, struct strbuf *line) +{ + while (!strbuf_getline_lf(line, mi->input)) { + if (*(mi->content_top) && is_multipart_boundary(mi, line)) + return 1; + } + return 0; +} + +static int handle_boundary(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf newline = STRBUF_INIT; + + strbuf_addch(&newline, '\n'); +again: + if (line->len >= (*(mi->content_top))->len + 2 && + !memcmp(line->buf + (*(mi->content_top))->len, "--", 2)) { + /* we hit an end boundary */ + /* pop the current boundary off the stack */ + strbuf_release(*(mi->content_top)); + FREE_AND_NULL(*(mi->content_top)); + + /* technically won't happen as is_multipart_boundary() + will fail first. But just in case.. + */ + if (--mi->content_top < mi->content) { + error("Detected mismatched boundaries, can't recover"); + mi->input_error = -1; + mi->content_top = mi->content; + strbuf_release(&newline); + return 0; + } + handle_filter(mi, &newline); + strbuf_release(&newline); + if (mi->input_error) + return 0; + + /* skip to the next boundary */ + if (!find_boundary(mi, line)) + return 0; + goto again; + } + + /* set some defaults */ + mi->transfer_encoding = TE_DONTCARE; + strbuf_reset(&mi->charset); + + /* slurp in this section's info */ + while (read_one_header_line(line, mi->input)) + check_header(mi, line, mi->p_hdr_data, 0); + + strbuf_release(&newline); + /* replenish line */ + if (strbuf_getline_lf(line, mi->input)) + return 0; + strbuf_addch(line, '\n'); + return 1; +} + +static void handle_filter_flowed(struct mailinfo *mi, struct strbuf *line, + struct strbuf *prev) +{ + size_t len = line->len; + const char *rest; + + if (!mi->format_flowed) { + handle_filter(mi, line); + return; + } + + if (line->buf[len - 1] == '\n') { + len--; + if (len && line->buf[len - 1] == '\r') + len--; + } + + /* Keep signature separator as-is. */ + if (skip_prefix(line->buf, "-- ", &rest) && rest - line->buf == len) { + if (prev->len) { + handle_filter(mi, prev); + strbuf_reset(prev); + } + handle_filter(mi, line); + return; + } + + /* Unstuff space-stuffed line. */ + if (len && line->buf[0] == ' ') { + strbuf_remove(line, 0, 1); + len--; + } + + /* Save flowed line for later, but without the soft line break. */ + if (len && line->buf[len - 1] == ' ') { + strbuf_add(prev, line->buf, len - !!mi->delsp); + return; + } + + /* Prepend any previous partial lines */ + strbuf_insert(line, 0, prev->buf, prev->len); + strbuf_reset(prev); + + handle_filter(mi, line); +} + +static void handle_body(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf prev = STRBUF_INIT; + + /* Skip up to the first boundary */ + if (*(mi->content_top)) { + if (!find_boundary(mi, line)) + goto handle_body_out; + } + + do { + /* process any boundary lines */ + if (*(mi->content_top) && is_multipart_boundary(mi, line)) { + /* flush any leftover */ + if (prev.len) { + handle_filter(mi, &prev); + strbuf_reset(&prev); + } + if (!handle_boundary(mi, line)) + goto handle_body_out; + } + + /* Unwrap transfer encoding */ + decode_transfer_encoding(mi, line); + + switch (mi->transfer_encoding) { + case TE_BASE64: + case TE_QP: + { + struct strbuf **lines, **it, *sb; + + /* Prepend any previous partial lines */ + strbuf_insert(line, 0, prev.buf, prev.len); + strbuf_reset(&prev); + + /* + * This is a decoded line that may contain + * multiple new lines. Pass only one chunk + * at a time to handle_filter() + */ + lines = strbuf_split(line, '\n'); + for (it = lines; (sb = *it); it++) { + if (*(it + 1) == NULL) /* The last line */ + if (sb->buf[sb->len - 1] != '\n') { + /* Partial line, save it for later. */ + strbuf_addbuf(&prev, sb); + break; + } + handle_filter_flowed(mi, sb, &prev); + } + /* + * The partial chunk is saved in "prev" and will be + * appended by the next iteration of read_line_with_nul(). + */ + strbuf_list_free(lines); + break; + } + default: + handle_filter_flowed(mi, line, &prev); + } + + if (mi->input_error) + break; + } while (!strbuf_getwholeline(line, mi->input, '\n')); + + if (prev.len) + handle_filter(mi, &prev); + + flush_inbody_header_accum(mi); + +handle_body_out: + strbuf_release(&prev); +} + +static void output_header_lines(FILE *fout, const char *hdr, const struct strbuf *data) +{ + const char *sp = data->buf; + while (1) { + char *ep = strchr(sp, '\n'); + int len; + if (!ep) + len = strlen(sp); + else + len = ep - sp; + fprintf(fout, "%s: %.*s\n", hdr, len, sp); + if (!ep) + break; + sp = ep + 1; + } +} + +static void handle_info(struct mailinfo *mi) +{ + struct strbuf *hdr; + int i; + + for (i = 0; header[i]; i++) { + /* only print inbody headers if we output a patch file */ + if (mi->patch_lines && mi->s_hdr_data[i]) + hdr = mi->s_hdr_data[i]; + else if (mi->p_hdr_data[i]) + hdr = mi->p_hdr_data[i]; + else + continue; + + if (!strcmp(header[i], "Subject")) { + if (!mi->keep_subject) { + cleanup_subject(mi, hdr); + cleanup_space(hdr); + } + output_header_lines(mi->output, "Subject", hdr); + } else if (!strcmp(header[i], "From")) { + cleanup_space(hdr); + handle_from(mi, hdr); + fprintf(mi->output, "Author: %s\n", mi->name.buf); + fprintf(mi->output, "Email: %s\n", mi->email.buf); + } else { + cleanup_space(hdr); + fprintf(mi->output, "%s: %s\n", header[i], hdr->buf); + } + } + fprintf(mi->output, "\n"); +} + +int mailinfo(struct mailinfo *mi, const char *msg, const char *patch) +{ + FILE *cmitmsg; + int peek; + struct strbuf line = STRBUF_INIT; + + cmitmsg = fopen(msg, "w"); + if (!cmitmsg) { + perror(msg); + return -1; + } + mi->patchfile = fopen(patch, "w"); + if (!mi->patchfile) { + perror(patch); + fclose(cmitmsg); + return -1; + } + + mi->p_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*(mi->p_hdr_data))); + mi->s_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*(mi->s_hdr_data))); + + do { + peek = fgetc(mi->input); + if (peek == EOF) { + fclose(cmitmsg); + return error("empty patch: '%s'", patch); + } + } while (isspace(peek)); + ungetc(peek, mi->input); + + /* process the email header */ + while (read_one_header_line(&line, mi->input)) + check_header(mi, &line, mi->p_hdr_data, 1); + + handle_body(mi, &line); + fwrite(mi->log_message.buf, 1, mi->log_message.len, cmitmsg); + fclose(cmitmsg); + fclose(mi->patchfile); + + handle_info(mi); + strbuf_release(&line); + return mi->input_error; +} + +static int git_mailinfo_config(const char *var, const char *value, void *mi_) +{ + struct mailinfo *mi = mi_; + + if (!starts_with(var, "mailinfo.")) + return git_default_config(var, value, NULL); + if (!strcmp(var, "mailinfo.scissors")) { + mi->use_scissors = git_config_bool(var, value); + return 0; + } + /* perhaps others here */ + return 0; +} + +void setup_mailinfo(struct mailinfo *mi) +{ + memset(mi, 0, sizeof(*mi)); + strbuf_init(&mi->name, 0); + strbuf_init(&mi->email, 0); + strbuf_init(&mi->charset, 0); + strbuf_init(&mi->log_message, 0); + strbuf_init(&mi->inbody_header_accum, 0); + mi->header_stage = 1; + mi->use_inbody_headers = 1; + mi->content_top = mi->content; + git_config(git_mailinfo_config, mi); +} + +void clear_mailinfo(struct mailinfo *mi) +{ + int i; + + strbuf_release(&mi->name); + strbuf_release(&mi->email); + strbuf_release(&mi->charset); + strbuf_release(&mi->inbody_header_accum); + free(mi->message_id); + + if (mi->p_hdr_data) + for (i = 0; mi->p_hdr_data[i]; i++) + strbuf_release(mi->p_hdr_data[i]); + free(mi->p_hdr_data); + if (mi->s_hdr_data) + for (i = 0; mi->s_hdr_data[i]; i++) + strbuf_release(mi->s_hdr_data[i]); + free(mi->s_hdr_data); + + while (mi->content < mi->content_top) { + free(*(mi->content_top)); + mi->content_top--; + } + + strbuf_release(&mi->log_message); +} diff --git a/t/t4256/1/mailinfo.c.orig b/t/t4256/1/mailinfo.c.orig new file mode 100644 index 0000000000..3281a37d51 --- /dev/null +++ b/t/t4256/1/mailinfo.c.orig @@ -0,0 +1,1185 @@ +#include "cache.h" +#include "config.h" +#include "utf8.h" +#include "strbuf.h" +#include "mailinfo.h" + +static void cleanup_space(struct strbuf *sb) +{ + size_t pos, cnt; + for (pos = 0; pos < sb->len; pos++) { + if (isspace(sb->buf[pos])) { + sb->buf[pos] = ' '; + for (cnt = 0; isspace(sb->buf[pos + cnt + 1]); cnt++); + strbuf_remove(sb, pos + 1, cnt); + } + } +} + +static void get_sane_name(struct strbuf *out, struct strbuf *name, struct strbuf *email) +{ + struct strbuf *src = name; + if (name->len < 3 || 60 < name->len || strchr(name->buf, '@') || + strchr(name->buf, '<') || strchr(name->buf, '>')) + src = email; + else if (name == out) + return; + strbuf_reset(out); + strbuf_addbuf(out, src); +} + +static void parse_bogus_from(struct mailinfo *mi, const struct strbuf *line) +{ + /* John Doe <johndoe> */ + + char *bra, *ket; + /* This is fallback, so do not bother if we already have an + * e-mail address. + */ + if (mi->email.len) + return; + + bra = strchr(line->buf, '<'); + if (!bra) + return; + ket = strchr(bra, '>'); + if (!ket) + return; + + strbuf_reset(&mi->email); + strbuf_add(&mi->email, bra + 1, ket - bra - 1); + + strbuf_reset(&mi->name); + strbuf_add(&mi->name, line->buf, bra - line->buf); + strbuf_trim(&mi->name); + get_sane_name(&mi->name, &mi->name, &mi->email); +} + +static const char *unquote_comment(struct strbuf *outbuf, const char *in) +{ + int c; + int take_next_literally = 0; + + strbuf_addch(outbuf, '('); + + while ((c = *in++) != 0) { + if (take_next_literally == 1) { + take_next_literally = 0; + } else { + switch (c) { + case '\\': + take_next_literally = 1; + continue; + case '(': + in = unquote_comment(outbuf, in); + continue; + case ')': + strbuf_addch(outbuf, ')'); + return in; + } + } + + strbuf_addch(outbuf, c); + } + + return in; +} + +static const char *unquote_quoted_string(struct strbuf *outbuf, const char *in) +{ + int c; + int take_next_literally = 0; + + while ((c = *in++) != 0) { + if (take_next_literally == 1) { + take_next_literally = 0; + } else { + switch (c) { + case '\\': + take_next_literally = 1; + continue; + case '"': + return in; + } + } + + strbuf_addch(outbuf, c); + } + + return in; +} + +static void unquote_quoted_pair(struct strbuf *line) +{ + struct strbuf outbuf; + const char *in = line->buf; + int c; + + strbuf_init(&outbuf, line->len); + + while ((c = *in++) != 0) { + switch (c) { + case '"': + in = unquote_quoted_string(&outbuf, in); + continue; + case '(': + in = unquote_comment(&outbuf, in); + continue; + } + + strbuf_addch(&outbuf, c); + } + + strbuf_swap(&outbuf, line); + strbuf_release(&outbuf); + +} + +static void handle_from(struct mailinfo *mi, const struct strbuf *from) +{ + char *at; + size_t el; + struct strbuf f; + + strbuf_init(&f, from->len); + strbuf_addbuf(&f, from); + + unquote_quoted_pair(&f); + + at = strchr(f.buf, '@'); + if (!at) { + parse_bogus_from(mi, from); + goto out; + } + + /* + * If we already have one email, don't take any confusing lines + */ + if (mi->email.len && strchr(at + 1, '@')) + goto out; + + /* Pick up the string around '@', possibly delimited with <> + * pair; that is the email part. + */ + while (at > f.buf) { + char c = at[-1]; + if (isspace(c)) + break; + if (c == '<') { + at[-1] = ' '; + break; + } + at--; + } + el = strcspn(at, " \n\t\r\v\f>"); + strbuf_reset(&mi->email); + strbuf_add(&mi->email, at, el); + strbuf_remove(&f, at - f.buf, el + (at[el] ? 1 : 0)); + + /* The remainder is name. It could be + * + * - "John Doe <john.doe@xz>" (a), or + * - "john.doe@xz (John Doe)" (b), or + * - "John (zzz) Doe <john.doe@xz> (Comment)" (c) + * + * but we have removed the email part, so + * + * - remove extra spaces which could stay after email (case 'c'), and + * - trim from both ends, possibly removing the () pair at the end + * (cases 'a' and 'b'). + */ + cleanup_space(&f); + strbuf_trim(&f); + if (f.buf[0] == '(' && f.len && f.buf[f.len - 1] == ')') { + strbuf_remove(&f, 0, 1); + strbuf_setlen(&f, f.len - 1); + } + + get_sane_name(&mi->name, &f, &mi->email); +out: + strbuf_release(&f); +} + +static void handle_header(struct strbuf **out, const struct strbuf *line) +{ + if (!*out) { + *out = xmalloc(sizeof(struct strbuf)); + strbuf_init(*out, line->len); + } else + strbuf_reset(*out); + + strbuf_addbuf(*out, line); +} + +/* NOTE NOTE NOTE. We do not claim we do full MIME. We just attempt + * to have enough heuristics to grok MIME encoded patches often found + * on our mailing lists. For example, we do not even treat header lines + * case insensitively. + */ + +static int slurp_attr(const char *line, const char *name, struct strbuf *attr) +{ + const char *ends, *ap = strcasestr(line, name); + size_t sz; + + strbuf_setlen(attr, 0); + if (!ap) + return 0; + ap += strlen(name); + if (*ap == '"') { + ap++; + ends = "\""; + } + else + ends = "; \t"; + sz = strcspn(ap, ends); + strbuf_add(attr, ap, sz); + return 1; +} + +static void handle_content_type(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf *boundary = xmalloc(sizeof(struct strbuf)); + strbuf_init(boundary, line->len); + + if (slurp_attr(line->buf, "boundary=", boundary)) { + strbuf_insert(boundary, 0, "--", 2); + if (++mi->content_top >= &mi->content[MAX_BOUNDARIES]) { + error("Too many boundaries to handle"); + mi->input_error = -1; + mi->content_top = &mi->content[MAX_BOUNDARIES] - 1; + return; + } + *(mi->content_top) = boundary; + boundary = NULL; + } + slurp_attr(line->buf, "charset=", &mi->charset); + + if (boundary) { + strbuf_release(boundary); + free(boundary); + } +} + +static void handle_content_transfer_encoding(struct mailinfo *mi, + const struct strbuf *line) +{ + if (strcasestr(line->buf, "base64")) + mi->transfer_encoding = TE_BASE64; + else if (strcasestr(line->buf, "quoted-printable")) + mi->transfer_encoding = TE_QP; + else + mi->transfer_encoding = TE_DONTCARE; +} + +static int is_multipart_boundary(struct mailinfo *mi, const struct strbuf *line) +{ + struct strbuf *content_top = *(mi->content_top); + + return ((content_top->len <= line->len) && + !memcmp(line->buf, content_top->buf, content_top->len)); +} + +static void cleanup_subject(struct mailinfo *mi, struct strbuf *subject) +{ + size_t at = 0; + + while (at < subject->len) { + char *pos; + size_t remove; + + switch (subject->buf[at]) { + case 'r': case 'R': + if (subject->len <= at + 3) + break; + if ((subject->buf[at + 1] == 'e' || + subject->buf[at + 1] == 'E') && + subject->buf[at + 2] == ':') { + strbuf_remove(subject, at, 3); + continue; + } + at++; + break; + case ' ': case '\t': case ':': + strbuf_remove(subject, at, 1); + continue; + case '[': + pos = strchr(subject->buf + at, ']'); + if (!pos) + break; + remove = pos - subject->buf + at + 1; + if (!mi->keep_non_patch_brackets_in_subject || + (7 <= remove && + memmem(subject->buf + at, remove, "PATCH", 5))) + strbuf_remove(subject, at, remove); + else { + at += remove; + /* + * If the input had a space after the ], keep + * it. We don't bother with finding the end of + * the space, since we later normalize it + * anyway. + */ + if (isspace(subject->buf[at])) + at += 1; + } + continue; + } + break; + } + strbuf_trim(subject); +} + +#define MAX_HDR_PARSED 10 +static const char *header[MAX_HDR_PARSED] = { + "From","Subject","Date", +}; + +static inline int cmp_header(const struct strbuf *line, const char *hdr) +{ + int len = strlen(hdr); + return !strncasecmp(line->buf, hdr, len) && line->len > len && + line->buf[len] == ':' && isspace(line->buf[len + 1]); +} + +static int is_format_patch_separator(const char *line, int len) +{ + static const char SAMPLE[] = + "From e6807f3efca28b30decfecb1732a56c7db1137ee Mon Sep 17 00:00:00 2001\n"; + const char *cp; + + if (len != strlen(SAMPLE)) + return 0; + if (!skip_prefix(line, "From ", &cp)) + return 0; + if (strspn(cp, "0123456789abcdef") != 40) + return 0; + cp += 40; + return !memcmp(SAMPLE + (cp - line), cp, strlen(SAMPLE) - (cp - line)); +} + +static struct strbuf *decode_q_segment(const struct strbuf *q_seg, int rfc2047) +{ + const char *in = q_seg->buf; + int c; + struct strbuf *out = xmalloc(sizeof(struct strbuf)); + strbuf_init(out, q_seg->len); + + while ((c = *in++) != 0) { + if (c == '=') { + int ch, d = *in; + if (d == '\n' || !d) + break; /* drop trailing newline */ + ch = hex2chr(in); + if (ch >= 0) { + strbuf_addch(out, ch); + in += 2; + continue; + } + /* garbage -- fall through */ + } + if (rfc2047 && c == '_') /* rfc2047 4.2 (2) */ + c = 0x20; + strbuf_addch(out, c); + } + return out; +} + +static struct strbuf *decode_b_segment(const struct strbuf *b_seg) +{ + /* Decode in..ep, possibly in-place to ot */ + int c, pos = 0, acc = 0; + const char *in = b_seg->buf; + struct strbuf *out = xmalloc(sizeof(struct strbuf)); + strbuf_init(out, b_seg->len); + + while ((c = *in++) != 0) { + if (c == '+') + c = 62; + else if (c == '/') + c = 63; + else if ('A' <= c && c <= 'Z') + c -= 'A'; + else if ('a' <= c && c <= 'z') + c -= 'a' - 26; + else if ('0' <= c && c <= '9') + c -= '0' - 52; + else + continue; /* garbage */ + switch (pos++) { + case 0: + acc = (c << 2); + break; + case 1: + strbuf_addch(out, (acc | (c >> 4))); + acc = (c & 15) << 4; + break; + case 2: + strbuf_addch(out, (acc | (c >> 2))); + acc = (c & 3) << 6; + break; + case 3: + strbuf_addch(out, (acc | c)); + acc = pos = 0; + break; + } + } + return out; +} + +static int convert_to_utf8(struct mailinfo *mi, + struct strbuf *line, const char *charset) +{ + char *out; + + if (!mi->metainfo_charset || !charset || !*charset) + return 0; + + if (same_encoding(mi->metainfo_charset, charset)) + return 0; + out = reencode_string(line->buf, mi->metainfo_charset, charset); + if (!out) { + mi->input_error = -1; + return error("cannot convert from %s to %s", + charset, mi->metainfo_charset); + } + strbuf_attach(line, out, strlen(out), strlen(out)); + return 0; +} + +static void decode_header(struct mailinfo *mi, struct strbuf *it) +{ + char *in, *ep, *cp; + struct strbuf outbuf = STRBUF_INIT, *dec; + struct strbuf charset_q = STRBUF_INIT, piecebuf = STRBUF_INIT; + int found_error = 1; /* pessimism */ + + in = it->buf; + while (in - it->buf <= it->len && (ep = strstr(in, "=?")) != NULL) { + int encoding; + strbuf_reset(&charset_q); + strbuf_reset(&piecebuf); + + if (in != ep) { + /* + * We are about to process an encoded-word + * that begins at ep, but there is something + * before the encoded word. + */ + char *scan; + for (scan = in; scan < ep; scan++) + if (!isspace(*scan)) + break; + + if (scan != ep || in == it->buf) { + /* + * We should not lose that "something", + * unless we have just processed an + * encoded-word, and there is only LWS + * before the one we are about to process. + */ + strbuf_add(&outbuf, in, ep - in); + } + } + /* E.g. + * ep : "=?iso-2022-jp?B?GyR...?= foo" + * ep : "=?ISO-8859-1?Q?Foo=FCbar?= baz" + */ + ep += 2; + + if (ep - it->buf >= it->len || !(cp = strchr(ep, '?'))) + goto release_return; + + if (cp + 3 - it->buf > it->len) + goto release_return; + strbuf_add(&charset_q, ep, cp - ep); + + encoding = cp[1]; + if (!encoding || cp[2] != '?') + goto release_return; + ep = strstr(cp + 3, "?="); + if (!ep) + goto release_return; + strbuf_add(&piecebuf, cp + 3, ep - cp - 3); + switch (tolower(encoding)) { + default: + goto release_return; + case 'b': + dec = decode_b_segment(&piecebuf); + break; + case 'q': + dec = decode_q_segment(&piecebuf, 1); + break; + } + if (convert_to_utf8(mi, dec, charset_q.buf)) + goto release_return; + + strbuf_addbuf(&outbuf, dec); + strbuf_release(dec); + free(dec); + in = ep + 2; + } + strbuf_addstr(&outbuf, in); + strbuf_reset(it); + strbuf_addbuf(it, &outbuf); + found_error = 0; +release_return: + strbuf_release(&outbuf); + strbuf_release(&charset_q); + strbuf_release(&piecebuf); + + if (found_error) + mi->input_error = -1; +} + +static int check_header(struct mailinfo *mi, + const struct strbuf *line, + struct strbuf *hdr_data[], int overwrite) +{ + int i, ret = 0, len; + struct strbuf sb = STRBUF_INIT; + + /* search for the interesting parts */ + for (i = 0; header[i]; i++) { + int len = strlen(header[i]); + if ((!hdr_data[i] || overwrite) && cmp_header(line, header[i])) { + /* Unwrap inline B and Q encoding, and optionally + * normalize the meta information to utf8. + */ + strbuf_add(&sb, line->buf + len + 2, line->len - len - 2); + decode_header(mi, &sb); + handle_header(&hdr_data[i], &sb); + ret = 1; + goto check_header_out; + } + } + + /* Content stuff */ + if (cmp_header(line, "Content-Type")) { + len = strlen("Content-Type: "); + strbuf_add(&sb, line->buf + len, line->len - len); + decode_header(mi, &sb); + strbuf_insert(&sb, 0, "Content-Type: ", len); + handle_content_type(mi, &sb); + ret = 1; + goto check_header_out; + } + if (cmp_header(line, "Content-Transfer-Encoding")) { + len = strlen("Content-Transfer-Encoding: "); + strbuf_add(&sb, line->buf + len, line->len - len); + decode_header(mi, &sb); + handle_content_transfer_encoding(mi, &sb); + ret = 1; + goto check_header_out; + } + if (cmp_header(line, "Message-Id")) { + len = strlen("Message-Id: "); + strbuf_add(&sb, line->buf + len, line->len - len); + decode_header(mi, &sb); + if (mi->add_message_id) + mi->message_id = strbuf_detach(&sb, NULL); + ret = 1; + goto check_header_out; + } + +check_header_out: + strbuf_release(&sb); + return ret; +} + +/* + * Returns 1 if the given line or any line beginning with the given line is an + * in-body header (that is, check_header will succeed when passed + * mi->s_hdr_data). + */ +static int is_inbody_header(const struct mailinfo *mi, + const struct strbuf *line) +{ + int i; + for (i = 0; header[i]; i++) + if (!mi->s_hdr_data[i] && cmp_header(line, header[i])) + return 1; + return 0; +} + +static void decode_transfer_encoding(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf *ret; + + switch (mi->transfer_encoding) { + case TE_QP: + ret = decode_q_segment(line, 0); + break; + case TE_BASE64: + ret = decode_b_segment(line); + break; + case TE_DONTCARE: + default: + return; + } + strbuf_reset(line); + strbuf_addbuf(line, ret); + strbuf_release(ret); + free(ret); +} + +static inline int patchbreak(const struct strbuf *line) +{ + size_t i; + + /* Beginning of a "diff -" header? */ + if (starts_with(line->buf, "diff -")) + return 1; + + /* CVS "Index: " line? */ + if (starts_with(line->buf, "Index: ")) + return 1; + + /* + * "--- <filename>" starts patches without headers + * "---<sp>*" is a manual separator + */ + if (line->len < 4) + return 0; + + if (starts_with(line->buf, "---")) { + /* space followed by a filename? */ + if (line->buf[3] == ' ' && !isspace(line->buf[4])) + return 1; + /* Just whitespace? */ + for (i = 3; i < line->len; i++) { + unsigned char c = line->buf[i]; + if (c == '\n') + return 1; + if (!isspace(c)) + break; + } + return 0; + } + return 0; +} + +static int is_scissors_line(const char *line) +{ + const char *c; + int scissors = 0, gap = 0; + const char *first_nonblank = NULL, *last_nonblank = NULL; + int visible, perforation = 0, in_perforation = 0; + + for (c = line; *c; c++) { + if (isspace(*c)) { + if (in_perforation) { + perforation++; + gap++; + } + continue; + } + last_nonblank = c; + if (first_nonblank == NULL) + first_nonblank = c; + if (*c == '-') { + in_perforation = 1; + perforation++; + continue; + } + if ((!memcmp(c, ">8", 2) || !memcmp(c, "8<", 2) || + !memcmp(c, ">%", 2) || !memcmp(c, "%<", 2))) { + in_perforation = 1; + perforation += 2; + scissors += 2; + c++; + continue; + } + in_perforation = 0; + } + + /* + * The mark must be at least 8 bytes long (e.g. "-- >8 --"). + * Even though there can be arbitrary cruft on the same line + * (e.g. "cut here"), in order to avoid misidentification, the + * perforation must occupy more than a third of the visible + * width of the line, and dashes and scissors must occupy more + * than half of the perforation. + */ + + if (first_nonblank && last_nonblank) + visible = last_nonblank - first_nonblank + 1; + else + visible = 0; + return (scissors && 8 <= visible && + visible < perforation * 3 && + gap * 2 < perforation); +} + +static void flush_inbody_header_accum(struct mailinfo *mi) +{ + if (!mi->inbody_header_accum.len) + return; + if (!check_header(mi, &mi->inbody_header_accum, mi->s_hdr_data, 0)) + BUG("inbody_header_accum, if not empty, must always contain a valid in-body header"); + strbuf_reset(&mi->inbody_header_accum); +} + +static int check_inbody_header(struct mailinfo *mi, const struct strbuf *line) +{ + if (mi->inbody_header_accum.len && + (line->buf[0] == ' ' || line->buf[0] == '\t')) { + if (mi->use_scissors && is_scissors_line(line->buf)) { + /* + * This is a scissors line; do not consider this line + * as a header continuation line. + */ + flush_inbody_header_accum(mi); + return 0; + } + strbuf_strip_suffix(&mi->inbody_header_accum, "\n"); + strbuf_addbuf(&mi->inbody_header_accum, line); + return 1; + } + + flush_inbody_header_accum(mi); + + if (starts_with(line->buf, ">From") && isspace(line->buf[5])) + return is_format_patch_separator(line->buf + 1, line->len - 1); + if (starts_with(line->buf, "[PATCH]") && isspace(line->buf[7])) { + int i; + for (i = 0; header[i]; i++) + if (!strcmp("Subject", header[i])) { + handle_header(&mi->s_hdr_data[i], line); + return 1; + } + return 0; + } + if (is_inbody_header(mi, line)) { + strbuf_addbuf(&mi->inbody_header_accum, line); + return 1; + } + return 0; +} + +static int handle_commit_msg(struct mailinfo *mi, struct strbuf *line) +{ + assert(!mi->filter_stage); + + if (mi->header_stage) { + if (!line->len || (line->len == 1 && line->buf[0] == '\n')) { + if (mi->inbody_header_accum.len) { + flush_inbody_header_accum(mi); + mi->header_stage = 0; + } + return 0; + } + } + + if (mi->use_inbody_headers && mi->header_stage) { + mi->header_stage = check_inbody_header(mi, line); + if (mi->header_stage) + return 0; + } else + /* Only trim the first (blank) line of the commit message + * when ignoring in-body headers. + */ + mi->header_stage = 0; + + /* normalize the log message to UTF-8. */ + if (convert_to_utf8(mi, line, mi->charset.buf)) + return 0; /* mi->input_error already set */ + + if (mi->use_scissors && is_scissors_line(line->buf)) { + int i; + + strbuf_setlen(&mi->log_message, 0); + mi->header_stage = 1; + + /* + * We may have already read "secondary headers"; purge + * them to give ourselves a clean restart. + */ + for (i = 0; header[i]; i++) { + if (mi->s_hdr_data[i]) + strbuf_release(mi->s_hdr_data[i]); + mi->s_hdr_data[i] = NULL; + } + return 0; + } + + if (patchbreak(line)) { + if (mi->message_id) + strbuf_addf(&mi->log_message, + "Message-Id: %s\n", mi->message_id); + return 1; + } + + strbuf_addbuf(&mi->log_message, line); + return 0; +} + +static void handle_patch(struct mailinfo *mi, const struct strbuf *line) +{ + fwrite(line->buf, 1, line->len, mi->patchfile); + mi->patch_lines++; +} + +static void handle_filter(struct mailinfo *mi, struct strbuf *line) +{ + switch (mi->filter_stage) { + case 0: + if (!handle_commit_msg(mi, line)) + break; + mi->filter_stage++; + /* fallthrough */ + case 1: + handle_patch(mi, line); + break; + } +} + +static int is_rfc2822_header(const struct strbuf *line) +{ + /* + * The section that defines the loosest possible + * field name is "3.6.8 Optional fields". + * + * optional-field = field-name ":" unstructured CRLF + * field-name = 1*ftext + * ftext = %d33-57 / %59-126 + */ + int ch; + char *cp = line->buf; + + /* Count mbox From headers as headers */ + if (starts_with(cp, "From ") || starts_with(cp, ">From ")) + return 1; + + while ((ch = *cp++)) { + if (ch == ':') + return 1; + if ((33 <= ch && ch <= 57) || + (59 <= ch && ch <= 126)) + continue; + break; + } + return 0; +} + +static int read_one_header_line(struct strbuf *line, FILE *in) +{ + struct strbuf continuation = STRBUF_INIT; + + /* Get the first part of the line. */ + if (strbuf_getline_lf(line, in)) + return 0; + + /* + * Is it an empty line or not a valid rfc2822 header? + * If so, stop here, and return false ("not a header") + */ + strbuf_rtrim(line); + if (!line->len || !is_rfc2822_header(line)) { + /* Re-add the newline */ + strbuf_addch(line, '\n'); + return 0; + } + + /* + * Now we need to eat all the continuation lines.. + * Yuck, 2822 header "folding" + */ + for (;;) { + int peek; + + peek = fgetc(in); + if (peek == EOF) + break; + ungetc(peek, in); + if (peek != ' ' && peek != '\t') + break; + if (strbuf_getline_lf(&continuation, in)) + break; + continuation.buf[0] = ' '; + strbuf_rtrim(&continuation); + strbuf_addbuf(line, &continuation); + } + strbuf_release(&continuation); + + return 1; +} + +static int find_boundary(struct mailinfo *mi, struct strbuf *line) +{ + while (!strbuf_getline_lf(line, mi->input)) { + if (*(mi->content_top) && is_multipart_boundary(mi, line)) + return 1; + } + return 0; +} + +static int handle_boundary(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf newline = STRBUF_INIT; + + strbuf_addch(&newline, '\n'); +again: + if (line->len >= (*(mi->content_top))->len + 2 && + !memcmp(line->buf + (*(mi->content_top))->len, "--", 2)) { + /* we hit an end boundary */ + /* pop the current boundary off the stack */ + strbuf_release(*(mi->content_top)); + FREE_AND_NULL(*(mi->content_top)); + + /* technically won't happen as is_multipart_boundary() + will fail first. But just in case.. + */ + if (--mi->content_top < mi->content) { + error("Detected mismatched boundaries, can't recover"); + mi->input_error = -1; + mi->content_top = mi->content; + strbuf_release(&newline); + return 0; + } + handle_filter(mi, &newline); + strbuf_release(&newline); + if (mi->input_error) + return 0; + + /* skip to the next boundary */ + if (!find_boundary(mi, line)) + return 0; + goto again; + } + + /* set some defaults */ + mi->transfer_encoding = TE_DONTCARE; + strbuf_reset(&mi->charset); + + /* slurp in this section's info */ + while (read_one_header_line(line, mi->input)) + check_header(mi, line, mi->p_hdr_data, 0); + + strbuf_release(&newline); + /* replenish line */ + if (strbuf_getline_lf(line, mi->input)) + return 0; + strbuf_addch(line, '\n'); + return 1; +} + +static void handle_body(struct mailinfo *mi, struct strbuf *line) +{ + struct strbuf prev = STRBUF_INIT; + + /* Skip up to the first boundary */ + if (*(mi->content_top)) { + if (!find_boundary(mi, line)) + goto handle_body_out; + } + + do { + /* process any boundary lines */ + if (*(mi->content_top) && is_multipart_boundary(mi, line)) { + /* flush any leftover */ + if (prev.len) { + handle_filter(mi, &prev); + strbuf_reset(&prev); + } + if (!handle_boundary(mi, line)) + goto handle_body_out; + } + + /* Unwrap transfer encoding */ + decode_transfer_encoding(mi, line); + + switch (mi->transfer_encoding) { + case TE_BASE64: + case TE_QP: + { + struct strbuf **lines, **it, *sb; + + /* Prepend any previous partial lines */ + strbuf_insert(line, 0, prev.buf, prev.len); + strbuf_reset(&prev); + + /* + * This is a decoded line that may contain + * multiple new lines. Pass only one chunk + * at a time to handle_filter() + */ + lines = strbuf_split(line, '\n'); + for (it = lines; (sb = *it); it++) { + if (*(it + 1) == NULL) /* The last line */ + if (sb->buf[sb->len - 1] != '\n') { + /* Partial line, save it for later. */ + strbuf_addbuf(&prev, sb); + break; + } + handle_filter(mi, sb); + } + /* + * The partial chunk is saved in "prev" and will be + * appended by the next iteration of read_line_with_nul(). + */ + strbuf_list_free(lines); + break; + } + default: + handle_filter(mi, line); + } + + if (mi->input_error) + break; + } while (!strbuf_getwholeline(line, mi->input, '\n')); + + flush_inbody_header_accum(mi); + +handle_body_out: + strbuf_release(&prev); +} + +static void output_header_lines(FILE *fout, const char *hdr, const struct strbuf *data) +{ + const char *sp = data->buf; + while (1) { + char *ep = strchr(sp, '\n'); + int len; + if (!ep) + len = strlen(sp); + else + len = ep - sp; + fprintf(fout, "%s: %.*s\n", hdr, len, sp); + if (!ep) + break; + sp = ep + 1; + } +} + +static void handle_info(struct mailinfo *mi) +{ + struct strbuf *hdr; + int i; + + for (i = 0; header[i]; i++) { + /* only print inbody headers if we output a patch file */ + if (mi->patch_lines && mi->s_hdr_data[i]) + hdr = mi->s_hdr_data[i]; + else if (mi->p_hdr_data[i]) + hdr = mi->p_hdr_data[i]; + else + continue; + + if (!strcmp(header[i], "Subject")) { + if (!mi->keep_subject) { + cleanup_subject(mi, hdr); + cleanup_space(hdr); + } + output_header_lines(mi->output, "Subject", hdr); + } else if (!strcmp(header[i], "From")) { + cleanup_space(hdr); + handle_from(mi, hdr); + fprintf(mi->output, "Author: %s\n", mi->name.buf); + fprintf(mi->output, "Email: %s\n", mi->email.buf); + } else { + cleanup_space(hdr); + fprintf(mi->output, "%s: %s\n", header[i], hdr->buf); + } + } + fprintf(mi->output, "\n"); +} + +int mailinfo(struct mailinfo *mi, const char *msg, const char *patch) +{ + FILE *cmitmsg; + int peek; + struct strbuf line = STRBUF_INIT; + + cmitmsg = fopen(msg, "w"); + if (!cmitmsg) { + perror(msg); + return -1; + } + mi->patchfile = fopen(patch, "w"); + if (!mi->patchfile) { + perror(patch); + fclose(cmitmsg); + return -1; + } + + mi->p_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*(mi->p_hdr_data))); + mi->s_hdr_data = xcalloc(MAX_HDR_PARSED, sizeof(*(mi->s_hdr_data))); + + do { + peek = fgetc(mi->input); + if (peek == EOF) { + fclose(cmitmsg); + return error("empty patch: '%s'", patch); + } + } while (isspace(peek)); + ungetc(peek, mi->input); + + /* process the email header */ + while (read_one_header_line(&line, mi->input)) + check_header(mi, &line, mi->p_hdr_data, 1); + + handle_body(mi, &line); + fwrite(mi->log_message.buf, 1, mi->log_message.len, cmitmsg); + fclose(cmitmsg); + fclose(mi->patchfile); + + handle_info(mi); + strbuf_release(&line); + return mi->input_error; +} + +static int git_mailinfo_config(const char *var, const char *value, void *mi_) +{ + struct mailinfo *mi = mi_; + + if (!starts_with(var, "mailinfo.")) + return git_default_config(var, value, NULL); + if (!strcmp(var, "mailinfo.scissors")) { + mi->use_scissors = git_config_bool(var, value); + return 0; + } + /* perhaps others here */ + return 0; +} + +void setup_mailinfo(struct mailinfo *mi) +{ + memset(mi, 0, sizeof(*mi)); + strbuf_init(&mi->name, 0); + strbuf_init(&mi->email, 0); + strbuf_init(&mi->charset, 0); + strbuf_init(&mi->log_message, 0); + strbuf_init(&mi->inbody_header_accum, 0); + mi->header_stage = 1; + mi->use_inbody_headers = 1; + mi->content_top = mi->content; + git_config(git_mailinfo_config, mi); +} + +void clear_mailinfo(struct mailinfo *mi) +{ + int i; + + strbuf_release(&mi->name); + strbuf_release(&mi->email); + strbuf_release(&mi->charset); + strbuf_release(&mi->inbody_header_accum); + free(mi->message_id); + + if (mi->p_hdr_data) + for (i = 0; mi->p_hdr_data[i]; i++) + strbuf_release(mi->p_hdr_data[i]); + free(mi->p_hdr_data); + if (mi->s_hdr_data) + for (i = 0; mi->s_hdr_data[i]; i++) + strbuf_release(mi->s_hdr_data[i]); + free(mi->s_hdr_data); + + while (mi->content < mi->content_top) { + free(*(mi->content_top)); + mi->content_top--; + } + + strbuf_release(&mi->log_message); +} diff --git a/t/t4256/1/patch b/t/t4256/1/patch new file mode 100644 index 0000000000..bd0d8b0251 --- /dev/null +++ b/t/t4256/1/patch @@ -0,0 +1,129 @@ +From: A <author@example.com> +Subject: [PATCH] mailinfo: support format=flowed +Message-ID: <aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa@example.com> +Date: Sat, 25 Aug 2018 22:04:50 +0200 +User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:60.0) Gecko/20100101 + Thunderbird/60.0 +MIME-Version: 1.0 +Content-Type: text/plain; charset=utf-8; format=flowed +Content-Language: en-US +Content-Transfer-Encoding: 7bit + +--- + mailinfo.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- + 1 file changed, 62 insertions(+), 2 deletions(-) + +diff --git a/mailinfo.c b/mailinfo.c +index 3281a37d51..b395adbdf2 100644 +--- a/mailinfo.c ++++ b/mailinfo.c +@@ -237,11 +237,22 @@ static int slurp_attr(const char *line, const char +*name, struct strbuf *attr) + return 1; + } + ++static int has_attr_value(const char *line, const char *name, const +char *value) ++{ ++ struct strbuf sb = STRBUF_INIT; ++ int rc = slurp_attr(line, name, &sb) && !strcasecmp(sb.buf, value); ++ strbuf_release(&sb); ++ return rc; ++} ++ + static void handle_content_type(struct mailinfo *mi, struct strbuf *line) + { + struct strbuf *boundary = xmalloc(sizeof(struct strbuf)); + strbuf_init(boundary, line->len); + ++ mi->format_flowed = has_attr_value(line->buf, "format=", "flowed"); ++ mi->delsp = has_attr_value(line->buf, "delsp=", "yes"); ++ + if (slurp_attr(line->buf, "boundary=", boundary)) { + strbuf_insert(boundary, 0, "--", 2); + if (++mi->content_top >= &mi->content[MAX_BOUNDARIES]) { +@@ -964,6 +975,52 @@ static int handle_boundary(struct mailinfo *mi, +struct strbuf *line) + return 1; + } + ++static void handle_filter_flowed(struct mailinfo *mi, struct strbuf *line, ++ struct strbuf *prev) ++{ ++ size_t len = line->len; ++ const char *rest; ++ ++ if (!mi->format_flowed) { ++ handle_filter(mi, line); ++ return; ++ } ++ ++ if (line->buf[len - 1] == '\n') { ++ len--; ++ if (len && line->buf[len - 1] == '\r') ++ len--; ++ } ++ ++ /* Keep signature separator as-is. */ ++ if (skip_prefix(line->buf, "-- ", &rest) && rest - line->buf == len) { ++ if (prev->len) { ++ handle_filter(mi, prev); ++ strbuf_reset(prev); ++ } ++ handle_filter(mi, line); ++ return; ++ } ++ ++ /* Unstuff space-stuffed line. */ ++ if (len && line->buf[0] == ' ') { ++ strbuf_remove(line, 0, 1); ++ len--; ++ } ++ ++ /* Save flowed line for later, but without the soft line break. */ ++ if (len && line->buf[len - 1] == ' ') { ++ strbuf_add(prev, line->buf, len - !!mi->delsp); ++ return; ++ } ++ ++ /* Prepend any previous partial lines */ ++ strbuf_insert(line, 0, prev->buf, prev->len); ++ strbuf_reset(prev); ++ ++ handle_filter(mi, line); ++} ++ + static void handle_body(struct mailinfo *mi, struct strbuf *line) + { + struct strbuf prev = STRBUF_INIT; +@@ -1012,7 +1069,7 @@ static void handle_body(struct mailinfo *mi, +struct strbuf *line) + strbuf_addbuf(&prev, sb); + break; + } +- handle_filter(mi, sb); ++ handle_filter_flowed(mi, sb, &prev); + } + /* + * The partial chunk is saved in "prev" and will be +@@ -1022,13 +1079,16 @@ static void handle_body(struct mailinfo *mi, +struct strbuf *line) + break; + } + default: +- handle_filter(mi, line); ++ handle_filter_flowed(mi, line, &prev); + } + + if (mi->input_error) + break; + } while (!strbuf_getwholeline(line, mi->input, '\n')); + ++ if (prev.len) ++ handle_filter(mi, &prev); ++ + flush_inbody_header_accum(mi); + + handle_body_out: +-- +2.18.0 diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh index 557bd0d0c0..1be3459c5b 100755 --- a/t/t5310-pack-bitmaps.sh +++ b/t/t5310-pack-bitmaps.sh @@ -335,11 +335,104 @@ test_expect_success 'truncated bitmap fails gracefully' ' git rev-list --use-bitmap-index --count --all >expect && bitmap=$(ls .git/objects/pack/*.bitmap) && test_when_finished "rm -f $bitmap" && - head -c 512 <$bitmap >$bitmap.tmp && + test_copy_bytes 512 <$bitmap >$bitmap.tmp && mv -f $bitmap.tmp $bitmap && git rev-list --use-bitmap-index --count --all >actual 2>stderr && test_cmp expect actual && test_i18ngrep corrupt stderr ' +# have_delta <obj> <expected_base> +# +# Note that because this relies on cat-file, it might find _any_ copy of an +# object in the repository. The caller is responsible for making sure +# there's only one (e.g., via "repack -ad", or having just fetched a copy). +have_delta () { + echo $2 >expect && + echo $1 | git cat-file --batch-check="%(deltabase)" >actual && + test_cmp expect actual +} + +# Create a state of history with these properties: +# +# - refs that allow a client to fetch some new history, while sharing some old +# history with the server; we use branches delta-reuse-old and +# delta-reuse-new here +# +# - the new history contains an object that is stored on the server as a delta +# against a base that is in the old history +# +# - the base object is not immediately reachable from the tip of the old +# history; finding it would involve digging down through history we know the +# other side has +# +# This should result in a state where fetching from old->new would not +# traditionally reuse the on-disk delta (because we'd have to dig to realize +# that the client has it), but we will do so if bitmaps can tell us cheaply +# that the other side has it. +test_expect_success 'set up thin delta-reuse parent' ' + # This first commit contains the buried base object. + test-tool genrandom delta 16384 >file && + git add file && + git commit -m "delta base" && + base=$(git rev-parse --verify HEAD:file) && + + # These intermediate commits bury the base back in history. + # This becomes the "old" state. + for i in 1 2 3 4 5 + do + echo $i >file && + git commit -am "intermediate $i" || return 1 + done && + git branch delta-reuse-old && + + # And now our new history has a delta against the buried base. Note + # that this must be smaller than the original file, since pack-objects + # prefers to create deltas from smaller objects to larger. + test-tool genrandom delta 16300 >file && + git commit -am "delta result" && + delta=$(git rev-parse --verify HEAD:file) && + git branch delta-reuse-new && + + # Repack with bitmaps and double check that we have the expected delta + # relationship. + git repack -adb && + have_delta $delta $base +' + +# Now we can sanity-check the non-bitmap behavior (that the server is not able +# to reuse the delta). This isn't strictly something we care about, so this +# test could be scrapped in the future. But it makes sure that the next test is +# actually triggering the feature we want. +# +# Note that our tools for working with on-the-wire "thin" packs are limited. So +# we actually perform the fetch, retain the resulting pack, and inspect the +# result. +test_expect_success 'fetch without bitmaps ignores delta against old base' ' + test_config pack.usebitmaps false && + test_when_finished "rm -rf client.git" && + git init --bare client.git && + ( + cd client.git && + git config transfer.unpackLimit 1 && + git fetch .. delta-reuse-old:delta-reuse-old && + git fetch .. delta-reuse-new:delta-reuse-new && + have_delta $delta $ZERO_OID + ) +' + +# And do the same for the bitmap case, where we do expect to find the delta. +test_expect_success 'fetch with bitmaps can reuse old base' ' + test_config pack.usebitmaps true && + test_when_finished "rm -rf client.git" && + git init --bare client.git && + ( + cd client.git && + git config transfer.unpackLimit 1 && + git fetch .. delta-reuse-old:delta-reuse-old && + git fetch .. delta-reuse-new:delta-reuse-new && + have_delta $delta $base + ) +' + test_done diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 3c1ffad491..0c500f7ca2 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -134,7 +134,7 @@ test_expect_success 'Add one more commit' ' git branch commits/8 && ls $objdir/pack | grep idx >existing-idx && git repack && - ls $objdir/pack| grep idx | grep -v --file=existing-idx >new-idx + ls $objdir/pack| grep idx | grep -v -f existing-idx >new-idx ' # Current graph structure: diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh new file mode 100755 index 0000000000..6f56b38674 --- /dev/null +++ b/t/t5319-multi-pack-index.sh @@ -0,0 +1,217 @@ +#!/bin/sh + +test_description='multi-pack-indexes' +. ./test-lib.sh + +objdir=.git/objects + +midx_read_expect () { + NUM_PACKS=$1 + NUM_OBJECTS=$2 + NUM_CHUNKS=$3 + OBJECT_DIR=$4 + EXTRA_CHUNKS="$5" + { + cat <<-EOF && + header: 4d494458 1 $NUM_CHUNKS $NUM_PACKS + chunks: pack-names oid-fanout oid-lookup object-offsets$EXTRA_CHUNKS + num_objects: $NUM_OBJECTS + packs: + EOF + if test $NUM_PACKS -ge 1 + then + ls $OBJECT_DIR/pack/ | grep idx | sort + fi && + printf "object-dir: $OBJECT_DIR\n" + } >expect && + test-tool read-midx $OBJECT_DIR >actual && + test_cmp expect actual +} + +test_expect_success 'write midx with no packs' ' + test_when_finished rm -f pack/multi-pack-index && + git multi-pack-index --object-dir=. write && + midx_read_expect 0 0 4 . +' + +generate_objects () { + i=$1 + iii=$(printf '%03i' $i) + { + test-tool genrandom "bar" 200 && + test-tool genrandom "baz $iii" 50 + } >wide_delta_$iii && + { + test-tool genrandom "foo"$i 100 && + test-tool genrandom "foo"$(( $i + 1 )) 100 && + test-tool genrandom "foo"$(( $i + 2 )) 100 + } >deep_delta_$iii && + { + echo $iii && + test-tool genrandom "$iii" 8192 + } >file_$iii && + git update-index --add file_$iii deep_delta_$iii wide_delta_$iii +} + +commit_and_list_objects () { + { + echo 101 && + test-tool genrandom 100 8192; + } >file_101 && + git update-index --add file_101 && + tree=$(git write-tree) && + commit=$(git commit-tree $tree -p HEAD</dev/null) && + { + echo $tree && + git ls-tree $tree | sed -e "s/.* \\([0-9a-f]*\\) .*/\\1/" + } >obj-list && + git reset --hard $commit +} + +test_expect_success 'create objects' ' + test_commit initial && + for i in $(test_seq 1 5) + do + generate_objects $i + done && + commit_and_list_objects +' + +test_expect_success 'write midx with one v1 pack' ' + pack=$(git pack-objects --index-version=1 $objdir/pack/test <obj-list) && + test_when_finished rm $objdir/pack/test-$pack.pack \ + $objdir/pack/test-$pack.idx $objdir/pack/multi-pack-index && + git multi-pack-index --object-dir=$objdir write && + midx_read_expect 1 18 4 $objdir +' + +midx_git_two_modes () { + if [ "$2" = "sorted" ] + then + git -c core.multiPackIndex=false $1 | sort >expect && + git -c core.multiPackIndex=true $1 | sort >actual + else + git -c core.multiPackIndex=false $1 >expect && + git -c core.multiPackIndex=true $1 >actual + fi && + test_cmp expect actual +} + +compare_results_with_midx () { + MSG=$1 + test_expect_success "check normal git operations: $MSG" ' + midx_git_two_modes "rev-list --objects --all" && + midx_git_two_modes "log --raw" && + midx_git_two_modes "count-objects --verbose" && + midx_git_two_modes "cat-file --batch-all-objects --buffer --batch-check" && + midx_git_two_modes "cat-file --batch-all-objects --buffer --batch-check --unsorted" sorted + ' +} + +test_expect_success 'write midx with one v2 pack' ' + git pack-objects --index-version=2,0x40 $objdir/pack/test <obj-list && + git multi-pack-index --object-dir=$objdir write && + midx_read_expect 1 18 4 $objdir +' + +compare_results_with_midx "one v2 pack" + +test_expect_success 'add more objects' ' + for i in $(test_seq 6 10) + do + generate_objects $i + done && + commit_and_list_objects +' + +test_expect_success 'write midx with two packs' ' + git pack-objects --index-version=1 $objdir/pack/test-2 <obj-list && + git multi-pack-index --object-dir=$objdir write && + midx_read_expect 2 34 4 $objdir +' + +compare_results_with_midx "two packs" + +test_expect_success 'add more packs' ' + for j in $(test_seq 11 20) + do + generate_objects $j && + commit_and_list_objects && + git pack-objects --index-version=2 $objdir/pack/test-pack <obj-list + done +' + +compare_results_with_midx "mixed mode (two packs + extra)" + +test_expect_success 'write midx with twelve packs' ' + git multi-pack-index --object-dir=$objdir write && + midx_read_expect 12 74 4 $objdir +' + +compare_results_with_midx "twelve packs" + +test_expect_success 'repack removes multi-pack-index' ' + test_path_is_file $objdir/pack/multi-pack-index && + git repack -adf && + test_path_is_missing $objdir/pack/multi-pack-index +' + +compare_results_with_midx "after repack" + +test_expect_success 'multi-pack-index and pack-bitmap' ' + git -c repack.writeBitmaps=true repack -ad && + git multi-pack-index write && + git rev-list --test-bitmap HEAD +' + +test_expect_success 'multi-pack-index and alternates' ' + git init --bare alt.git && + echo $(pwd)/alt.git/objects >.git/objects/info/alternates && + echo content1 >file1 && + altblob=$(GIT_DIR=alt.git git hash-object -w file1) && + git cat-file blob $altblob && + git rev-list --all +' + +compare_results_with_midx "with alternate (local midx)" + +test_expect_success 'multi-pack-index in an alternate' ' + mv .git/objects/pack/* alt.git/objects/pack && + test_commit add_local_objects && + git repack --local && + git multi-pack-index write && + midx_read_expect 1 3 4 $objdir && + git reset --hard HEAD~1 && + rm -f .git/objects/pack/* +' + +compare_results_with_midx "with alternate (remote midx)" + + +# usage: corrupt_data <file> <pos> [<data>] +corrupt_data () { + file=$1 + pos=$2 + data="${3:-\0}" + printf "$data" | dd of="$file" bs=1 seek="$pos" conv=notrunc +} + +# Force 64-bit offsets by manipulating the idx file. +# This makes the IDX file _incorrect_ so be careful to clean up after! +test_expect_success 'force some 64-bit offsets with pack-objects' ' + mkdir objects64 && + mkdir objects64/pack && + for i in $(test_seq 1 11) + do + generate_objects 11 + done && + commit_and_list_objects && + pack64=$(git pack-objects --index-version=2,0x40 objects64/pack/test-64 <obj-list) && + idx64=objects64/pack/test-64-$pack64.idx && + chmod u+w $idx64 && + corrupt_data $idx64 2999 "\02" && + midx64=$(git multi-pack-index --object-dir=objects64 write) && + midx_read_expect 1 63 5 objects64 " large-offsets" +' + +test_done diff --git a/t/t5320-delta-islands.sh b/t/t5320-delta-islands.sh new file mode 100755 index 0000000000..fea92a5777 --- /dev/null +++ b/t/t5320-delta-islands.sh @@ -0,0 +1,143 @@ +#!/bin/sh + +test_description='exercise delta islands' +. ./test-lib.sh + +# returns true iff $1 is a delta based on $2 +is_delta_base () { + delta_base=$(echo "$1" | git cat-file --batch-check='%(deltabase)') && + echo >&2 "$1 has base $delta_base" && + test "$delta_base" = "$2" +} + +# generate a commit on branch $1 with a single file, "file", whose +# content is mostly based on the seed $2, but with a unique bit +# of content $3 appended. This should allow us to see whether +# blobs of different refs delta against each other. +commit() { + blob=$({ test-tool genrandom "$2" 10240 && echo "$3"; } | + git hash-object -w --stdin) && + tree=$(printf '100644 blob %s\tfile\n' "$blob" | git mktree) && + commit=$(echo "$2-$3" | git commit-tree "$tree" ${4:+-p "$4"}) && + git update-ref "refs/heads/$1" "$commit" && + eval "$1"'=$(git rev-parse $1:file)' && + eval "echo >&2 $1=\$$1" +} + +test_expect_success 'setup commits' ' + commit one seed 1 && + commit two seed 12 +' + +# Note: This is heavily dependent on the "prefer larger objects as base" +# heuristic. +test_expect_success 'vanilla repack deltas one against two' ' + git repack -adf && + is_delta_base $one $two +' + +test_expect_success 'island repack with no island definition is vanilla' ' + git repack -adfi && + is_delta_base $one $two +' + +test_expect_success 'island repack with no matches is vanilla' ' + git -c "pack.island=refs/foo" repack -adfi && + is_delta_base $one $two +' + +test_expect_success 'separate islands disallows delta' ' + git -c "pack.island=refs/heads/(.*)" repack -adfi && + ! is_delta_base $one $two && + ! is_delta_base $two $one +' + +test_expect_success 'same island allows delta' ' + git -c "pack.island=refs/heads" repack -adfi && + is_delta_base $one $two +' + +test_expect_success 'coalesce same-named islands' ' + git \ + -c "pack.island=refs/(.*)/one" \ + -c "pack.island=refs/(.*)/two" \ + repack -adfi && + is_delta_base $one $two +' + +test_expect_success 'island restrictions drop reused deltas' ' + git repack -adfi && + is_delta_base $one $two && + git -c "pack.island=refs/heads/(.*)" repack -adi && + ! is_delta_base $one $two && + ! is_delta_base $two $one +' + +test_expect_success 'island regexes are left-anchored' ' + git -c "pack.island=heads/(.*)" repack -adfi && + is_delta_base $one $two +' + +test_expect_success 'island regexes follow last-one-wins scheme' ' + git \ + -c "pack.island=refs/heads/(.*)" \ + -c "pack.island=refs/heads/" \ + repack -adfi && + is_delta_base $one $two +' + +test_expect_success 'setup shared history' ' + commit root shared root && + commit one shared 1 root && + commit two shared 12-long root +' + +# We know that $two will be preferred as a base from $one, +# because we can transform it with a pure deletion. +# +# We also expect $root as a delta against $two by the "longest is base" rule. +test_expect_success 'vanilla delta goes between branches' ' + git repack -adf && + is_delta_base $one $two && + is_delta_base $root $two +' + +# Here we should allow $one to base itself on $root; even though +# they are in different islands, the objects in $root are in a superset +# of islands compared to those in $one. +# +# Similarly, $two can delta against $root by our rules. And unlike $one, +# in which we are just allowing it, the island rules actually put $root +# as a possible base for $two, which it would not otherwise be (due to the size +# sorting). +test_expect_success 'deltas allowed against superset islands' ' + git -c "pack.island=refs/heads/(.*)" repack -adfi && + is_delta_base $one $root && + is_delta_base $two $root +' + +# We are going to test the packfile order here, so we again have to make some +# assumptions. We assume that "$root", as part of our core "one", must come +# before "$two". This should be guaranteed by the island code. However, for +# this test to fail without islands, we are also assuming that it would not +# otherwise do so. This is true by the current write order, which will put +# commits (and their contents) before their parents. +test_expect_success 'island core places core objects first' ' + cat >expect <<-EOF && + $root + $two + EOF + git -c "pack.island=refs/heads/(.*)" \ + -c "pack.islandcore=one" \ + repack -adfi && + git verify-pack -v .git/objects/pack/*.pack | + cut -d" " -f1 | + egrep "$root|$two" >actual && + test_cmp expect actual +' + +test_expect_success 'unmatched island core is not fatal' ' + git -c "pack.islandcore=one" repack -adfi +' + +test_done diff --git a/t/t5552-skipping-fetch-negotiator.sh b/t/t5552-skipping-fetch-negotiator.sh index 5ad5bece55..30857b84a8 100755 --- a/t/t5552-skipping-fetch-negotiator.sh +++ b/t/t5552-skipping-fetch-negotiator.sh @@ -46,7 +46,7 @@ test_expect_success 'commits with no parents are sent regardless of skip distanc test_commit -C server to_fetch && git init client && - for i in $(seq 7) + for i in $(test_seq 7) do test_commit -C client c$i done && @@ -89,7 +89,7 @@ test_expect_success 'when two skips collide, favor the larger one' ' test_commit -C server to_fetch && git init client && - for i in $(seq 11) + for i in $(test_seq 11) do test_commit -C client c$i done && @@ -168,14 +168,14 @@ test_expect_success 'do not send "have" with ancestors of commits that server AC test_commit -C server to_fetch && git init client && - for i in $(seq 8) + for i in $(test_seq 8) do git -C client checkout --orphan b$i && test_commit -C client b$i.c0 done && - for j in $(seq 19) + for j in $(test_seq 19) do - for i in $(seq 8) + for i in $(test_seq 8) do git -C client checkout b$i && test_commit -C client b$i.c$j @@ -205,7 +205,7 @@ test_expect_success 'do not send "have" with ancestors of commits that server AC # fetch-pack should thus not send any more commits in the b1 branch, but # should still send the others (in this test, just check b2). - for i in $(seq 0 8) + for i in $(test_seq 0 8) do have_not_sent b1.c$i done && diff --git a/t/t5562-http-backend-content-length.sh b/t/t5562-http-backend-content-length.sh index 43570ce120..b24d8b05a4 100755 --- a/t/t5562-http-backend-content-length.sh +++ b/t/t5562-http-backend-content-length.sh @@ -153,4 +153,15 @@ test_expect_success 'CONTENT_LENGTH overflow ssite_t' ' grep "fatal:.*CONTENT_LENGTH" err ' +test_expect_success 'empty CONTENT_LENGTH' ' + env \ + QUERY_STRING="service=git-receive-pack" \ + PATH_TRANSLATED="$PWD"/.git/info/refs \ + GIT_HTTP_EXPORT_ALL=TRUE \ + REQUEST_METHOD=GET \ + CONTENT_LENGTH="" \ + git http-backend <empty_body >act.out 2>act.err && + verify_http_result "200 OK" +' + test_done diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh index ddaa96ac4f..f1a49e94f5 100755 --- a/t/t5601-clone.sh +++ b/t/t5601-clone.sh @@ -624,10 +624,16 @@ test_expect_success 'clone on case-insensitive fs' ' git hash-object -w -t tree --stdin) && c=$(git commit-tree -m bogus $t) && git update-ref refs/heads/bogus $c && - git clone -b bogus . bogus + git clone -b bogus . bogus 2>warning ) ' +test_expect_success !MINGW,!CYGWIN,CASE_INSENSITIVE_FS 'colliding file detection' ' + grep X icasefs/warning && + grep x icasefs/warning && + test_i18ngrep "the following paths have collided" icasefs/warning +' + partial_clone () { SERVER="$1" && URL="$2" && diff --git a/t/t5703-upload-pack-ref-in-want.sh b/t/t5703-upload-pack-ref-in-want.sh index a73c55a47e..d1ccc22331 100755 --- a/t/t5703-upload-pack-ref-in-want.sh +++ b/t/t5703-upload-pack-ref-in-want.sh @@ -176,7 +176,7 @@ test_expect_success 'setup repos for change-while-negotiating test' ' git clone "http://127.0.0.1:$LIB_HTTPD_PORT/smart/repo" "$LOCAL_PRISTINE" && cd "$LOCAL_PRISTINE" && git checkout -b side && - for i in $(seq 1 33); do test_commit s$i; done && + for i in $(test_seq 1 33); do test_commit s$i; done && # Add novel commits to upstream git checkout master && @@ -289,7 +289,7 @@ test_expect_success 'setup repos for fetching with ref-in-want tests' ' git clone "file://$REPO" "$LOCAL_PRISTINE" && cd "$LOCAL_PRISTINE" && git checkout -b side && - for i in $(seq 1 33); do test_commit s$i; done && + for i in $(test_seq 1 33); do test_commit s$i; done && # Add novel commits to upstream git checkout master && diff --git a/t/t6018-rev-list-glob.sh b/t/t6018-rev-list-glob.sh index 0bf10d0686..db8a7834d8 100755 --- a/t/t6018-rev-list-glob.sh +++ b/t/t6018-rev-list-glob.sh @@ -255,7 +255,7 @@ test_expect_success 'rev-list accumulates multiple --exclude' ' compare rev-list "--exclude=refs/remotes/* --exclude=refs/tags/* --all" --branches ' -test_expect_failure 'rev-list should succeed with empty output on empty stdin' ' +test_expect_success 'rev-list should succeed with empty output on empty stdin' ' git rev-list --stdin </dev/null >actual && test_must_be_empty actual ' diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh index 024f8c06f7..97bfbee6e8 100755 --- a/t/t6300-for-each-ref.sh +++ b/t/t6300-for-each-ref.sh @@ -715,6 +715,29 @@ test_expect_success 'basic atom: head contents:trailers' ' test_cmp expect actual.clean ' +test_expect_success 'trailer parsing not fooled by --- line' ' + git commit --allow-empty -F - <<-\EOF && + this is the subject + + This is the body. The message has a "---" line which would confuse a + message+patch parser. But here we know we have only a commit message, + so we get it right. + + trailer: wrong + --- + This is more body. + + trailer: right + EOF + + { + echo "trailer: right" && + echo + } >expect && + git for-each-ref --format="%(trailers)" refs/heads/master >actual && + test_cmp expect actual +' + test_expect_success 'Add symbolic ref for the following tests' ' git symbolic-ref refs/heads/sym refs/heads/master ' diff --git a/t/t6600-test-reach.sh b/t/t6600-test-reach.sh new file mode 100755 index 0000000000..d139a00d1d --- /dev/null +++ b/t/t6600-test-reach.sh @@ -0,0 +1,242 @@ +#!/bin/sh + +test_description='basic commit reachability tests' + +. ./test-lib.sh + +# Construct a grid-like commit graph with points (x,y) +# with 1 <= x <= 10, 1 <= y <= 10, where (x,y) has +# parents (x-1, y) and (x, y-1), keeping in mind that +# we drop a parent if a coordinate is nonpositive. +# +# (10,10) +# / \ +# (10,9) (9,10) +# / \ / \ +# (10,8) (9,9) (8,10) +# / \ / \ / \ +# ( continued...) +# \ / \ / \ / +# (3,1) (2,2) (1,3) +# \ / \ / +# (2,1) (2,1) +# \ / +# (1,1) +# +# We use branch 'commit-x-y' to refer to (x,y). +# This grid allows interesting reachability and +# non-reachability queries: (x,y) can reach (x',y') +# if and only if x' <= x and y' <= y. +test_expect_success 'setup' ' + for i in $(test_seq 1 10) + do + test_commit "1-$i" && + git branch -f commit-1-$i + done && + for j in $(test_seq 1 9) + do + git reset --hard commit-$j-1 && + x=$(($j + 1)) && + test_commit "$x-1" && + git branch -f commit-$x-1 && + + for i in $(test_seq 2 10) + do + git merge commit-$j-$i -m "$x-$i" && + git branch -f commit-$x-$i + done + done && + git commit-graph write --reachable && + mv .git/objects/info/commit-graph commit-graph-full && + git show-ref -s commit-5-5 | git commit-graph write --stdin-commits && + mv .git/objects/info/commit-graph commit-graph-half && + git config core.commitGraph true +' + +test_three_modes () { + test_when_finished rm -rf .git/objects/info/commit-graph && + test-tool reach $1 <input >actual && + test_cmp expect actual && + cp commit-graph-full .git/objects/info/commit-graph && + test-tool reach $1 <input >actual && + test_cmp expect actual && + cp commit-graph-half .git/objects/info/commit-graph && + test-tool reach $1 <input >actual && + test_cmp expect actual +} + +test_expect_success 'ref_newer:miss' ' + cat >input <<-\EOF && + A:commit-5-7 + B:commit-4-9 + EOF + echo "ref_newer(A,B):0" >expect && + test_three_modes ref_newer +' + +test_expect_success 'ref_newer:hit' ' + cat >input <<-\EOF && + A:commit-5-7 + B:commit-2-3 + EOF + echo "ref_newer(A,B):1" >expect && + test_three_modes ref_newer +' + +test_expect_success 'in_merge_bases:hit' ' + cat >input <<-\EOF && + A:commit-5-7 + B:commit-8-8 + EOF + echo "in_merge_bases(A,B):1" >expect && + test_three_modes in_merge_bases +' + +test_expect_success 'in_merge_bases:miss' ' + cat >input <<-\EOF && + A:commit-6-8 + B:commit-5-9 + EOF + echo "in_merge_bases(A,B):0" >expect && + test_three_modes in_merge_bases +' + +test_expect_success 'is_descendant_of:hit' ' + cat >input <<-\EOF && + A:commit-5-7 + X:commit-4-8 + X:commit-6-6 + X:commit-1-1 + EOF + echo "is_descendant_of(A,X):1" >expect && + test_three_modes is_descendant_of +' + +test_expect_success 'is_descendant_of:miss' ' + cat >input <<-\EOF && + A:commit-6-8 + X:commit-5-9 + X:commit-4-10 + X:commit-7-6 + EOF + echo "is_descendant_of(A,X):0" >expect && + test_three_modes is_descendant_of +' + +test_expect_success 'get_merge_bases_many' ' + cat >input <<-\EOF && + A:commit-5-7 + X:commit-4-8 + X:commit-6-6 + X:commit-8-3 + EOF + { + echo "get_merge_bases_many(A,X):" && + git rev-parse commit-5-6 \ + commit-4-7 | sort + } >expect && + test_three_modes get_merge_bases_many +' + +test_expect_success 'reduce_heads' ' + cat >input <<-\EOF && + X:commit-1-10 + X:commit-2-8 + X:commit-3-6 + X:commit-4-4 + X:commit-1-7 + X:commit-2-5 + X:commit-3-3 + X:commit-5-1 + EOF + { + echo "reduce_heads(X):" && + git rev-parse commit-5-1 \ + commit-4-4 \ + commit-3-6 \ + commit-2-8 \ + commit-1-10 | sort + } >expect && + test_three_modes reduce_heads +' + +test_expect_success 'can_all_from_reach:hit' ' + cat >input <<-\EOF && + X:commit-2-10 + X:commit-3-9 + X:commit-4-8 + X:commit-5-7 + X:commit-6-6 + X:commit-7-5 + X:commit-8-4 + X:commit-9-3 + Y:commit-1-9 + Y:commit-2-8 + Y:commit-3-7 + Y:commit-4-6 + Y:commit-5-5 + Y:commit-6-4 + Y:commit-7-3 + Y:commit-8-1 + EOF + echo "can_all_from_reach(X,Y):1" >expect && + test_three_modes can_all_from_reach +' + +test_expect_success 'can_all_from_reach:miss' ' + cat >input <<-\EOF && + X:commit-2-10 + X:commit-3-9 + X:commit-4-8 + X:commit-5-7 + X:commit-6-6 + X:commit-7-5 + X:commit-8-4 + X:commit-9-3 + Y:commit-1-9 + Y:commit-2-8 + Y:commit-3-7 + Y:commit-4-6 + Y:commit-5-5 + Y:commit-6-4 + Y:commit-8-5 + EOF + echo "can_all_from_reach(X,Y):0" >expect && + test_three_modes can_all_from_reach +' + +test_expect_success 'commit_contains:hit' ' + cat >input <<-\EOF && + A:commit-7-7 + X:commit-2-10 + X:commit-3-9 + X:commit-4-8 + X:commit-5-7 + X:commit-6-6 + X:commit-7-5 + X:commit-8-4 + X:commit-9-3 + EOF + echo "commit_contains(_,A,X,_):1" >expect && + test_three_modes commit_contains && + test_three_modes commit_contains --tag +' + +test_expect_success 'commit_contains:miss' ' + cat >input <<-\EOF && + A:commit-6-5 + X:commit-2-10 + X:commit-3-9 + X:commit-4-8 + X:commit-5-7 + X:commit-6-6 + X:commit-7-5 + X:commit-8-4 + X:commit-9-3 + EOF + echo "commit_contains(_,A,X,_):0" >expect && + test_three_modes commit_contains && + test_three_modes commit_contains --tag +' + +test_done diff --git a/t/t7400-submodule-basic.sh b/t/t7400-submodule-basic.sh index 7d3d984210..c0ffc1022a 100755 --- a/t/t7400-submodule-basic.sh +++ b/t/t7400-submodule-basic.sh @@ -984,11 +984,6 @@ test_expect_success 'submodule deinit should remove the whole submodule section rmdir init ' -test_expect_success 'submodule deinit should unset core.worktree' ' - test_path_is_file .git/modules/example/config && - test_must_fail git config -f .git/modules/example/config core.worktree -' - test_expect_success 'submodule deinit from subdirectory' ' git submodule update --init && git config submodule.example.foo bar && diff --git a/t/t7501-commit.sh b/t/t7501-commit.sh index 4cae92804d..1a6773ee68 100755 --- a/t/t7501-commit.sh +++ b/t/t7501-commit.sh @@ -517,6 +517,22 @@ Myfooter: x" && test_cmp expected actual ' +test_expect_success 'signoff not confused by ---' ' + cat >expected <<-EOF && + subject + + body + --- + these dashes confuse the parser! + + Signed-off-by: $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> + EOF + # should be a noop, since we already signed + git commit --allow-empty --signoff -F expected && + git log -1 --pretty=format:%B >actual && + test_cmp expected actual +' + test_expect_success 'multiple -m' ' >negative && diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh index 164719d1c9..c441861331 100755 --- a/t/t7513-interpret-trailers.sh +++ b/t/t7513-interpret-trailers.sh @@ -1417,4 +1417,46 @@ test_expect_success 'unfold' ' test_cmp expected actual ' +test_expect_success 'handling of --- lines in input' ' + echo "real-trailer: just right" >expected && + + git interpret-trailers --parse >actual <<-\EOF && + subject + + body + + not-a-trailer: too soon + ------ this is just a line in the commit message with a bunch of + ------ dashes; it does not have any syntactic meaning. + + real-trailer: just right + --- + below the dashed line may be a patch, etc. + + not-a-trailer: too late + EOF + + test_cmp expected actual +' + +test_expect_success 'suppress --- handling' ' + echo "real-trailer: just right" >expected && + + git interpret-trailers --parse --no-divider >actual <<-\EOF && + subject + + This commit message has a "---" in it, but because we tell + interpret-trailers not to respect that, it has no effect. + + not-a-trailer: too soon + --- + + This is still the commit message body. + + real-trailer: just right + EOF + + test_cmp expected actual +' + test_done diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh index 4207af4077..d82fac9d79 100644 --- a/t/test-lib-functions.sh +++ b/t/test-lib-functions.sh @@ -42,6 +42,8 @@ test_decode_color () { function name(n) { if (n == 0) return "RESET"; if (n == 1) return "BOLD"; + if (n == 2) return "FAINT"; + if (n == 3) return "ITALIC"; if (n == 7) return "REVERSE"; if (n == 30) return "BLACK"; if (n == 31) return "RED"; diff --git a/t/test-lib.sh b/t/test-lib.sh index 8bb0f4348e..3f95bfda60 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -867,7 +867,7 @@ then # handle only executables, unless they are shell libraries that # need to be in the exec-path. test -x "$1" || - test "# " = "$(head -c 2 <"$1")" || + test "# " = "$(test_copy_bytes 2 <"$1")" || return; base=$(basename "$1") @@ -882,7 +882,7 @@ then # do not override scripts if test -x "$symlink_target" && test ! -d "$symlink_target" && - test "#!" != "$(head -c 2 < "$symlink_target")" + test "#!" != "$(test_copy_bytes 2 <"$symlink_target")" then symlink_target=../valgrind.sh fi @@ -1083,6 +1083,12 @@ else test_set_prereq C_LOCALE_OUTPUT fi +if test -z "$GIT_TEST_CHECK_CACHE_TREE" +then + GIT_TEST_CHECK_CACHE_TREE=true + export GIT_TEST_CHECK_CACHE_TREE +fi + test_lazy_prereq PIPE ' # test whether the filesystem supports FIFOs test_have_prereq !MINGW,!CYGWIN && |