From 9cfa5126a0bdb47bc9c6d5feb76bb0fbfd40785b Mon Sep 17 00:00:00 2001 From: Jeff King Date: Wed, 17 Apr 2013 17:00:48 -0400 Subject: [PATCH 1/3] cat-file: print tags raw for "cat-file -p" When "cat-file -p" prints commits, it shows them in their raw format, since git's format is already human-readable. For tags, however, we print the whole thing raw except for one thing: we convert the timestamp on the tagger line into a human-readable date. This dates all the way back to a0f15fa (Pretty-print tagger dates, 2006-03-01). At that time there was no other way to pretty-print a tag. These days, however, neither of those matters much. The normal way to pretty-print a tag is with "git show", which is much more flexible than "cat-file -p". Commit a0f15fa also built "verify-tag --verbose" (and subsequently "tag -v") around the "cat-file -p" output. However, that behavior was lost in commit 62e09ce (Make git tag a builtin, 2007-07-20), and we went back to printing the raw tag contents. Nobody seems to have noticed the bug since then (and it is arguably a saner behavior anyway, as it shows the actual bytes for which we verified the signature). Let's drop the tagger-date formatting for "cat-file -p". It makes us more consistent with cat-file's commit pretty-printer, and as a bonus, we can drop the hand-rolled tag parsing code in cat-file (which happened to behave inconsistently with the tag pretty-printing code elsewhere). This is a change of output format, so it's possible that some callers could considered this a regression. However, the original behavior was arguably a bug (due to the inconsistency with commits), likely nobody was relying on it (even we do not use it ourselves these days), and anyone relying on the "-p" pretty-printer should be able to expect a change in the output format (i.e., while "cat-file" is plumbing, the output format of "-p" was never guaranteed to be stable). Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 71 --------------------------------------------- t/t1006-cat-file.sh | 5 +--- 2 files changed, 1 insertion(+), 75 deletions(-) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 40f87b4649..045cee7bce 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -16,73 +16,6 @@ #define BATCH 1 #define BATCH_CHECK 2 -static void pprint_tag(const unsigned char *sha1, const char *buf, unsigned long size) -{ - /* the parser in tag.c is useless here. */ - const char *endp = buf + size; - const char *cp = buf; - - while (cp < endp) { - char c = *cp++; - if (c != '\n') - continue; - if (7 <= endp - cp && !memcmp("tagger ", cp, 7)) { - const char *tagger = cp; - - /* Found the tagger line. Copy out the contents - * of the buffer so far. - */ - write_or_die(1, buf, cp - buf); - - /* - * Do something intelligent, like pretty-printing - * the date. - */ - while (cp < endp) { - if (*cp++ == '\n') { - /* tagger to cp is a line - * that has ident and time. - */ - const char *sp = tagger; - char *ep; - unsigned long date; - long tz; - while (sp < cp && *sp != '>') - sp++; - if (sp == cp) { - /* give up */ - write_or_die(1, tagger, - cp - tagger); - break; - } - while (sp < cp && - !('0' <= *sp && *sp <= '9')) - sp++; - write_or_die(1, tagger, sp - tagger); - date = strtoul(sp, &ep, 10); - tz = strtol(ep, NULL, 10); - sp = show_date(date, tz, 0); - write_or_die(1, sp, strlen(sp)); - xwrite(1, "\n", 1); - break; - } - } - break; - } - if (cp < endp && *cp == '\n') - /* end of header */ - break; - } - /* At this point, we have copied out the header up to the end of - * the tagger line and cp points at one past \n. It could be the - * next header line after the tagger line, or it could be another - * \n that marks the end of the headers. We need to copy out the - * remainder as is. - */ - if (cp < endp) - write_or_die(1, cp, endp - cp); -} - static int cat_one_file(int opt, const char *exp_type, const char *obj_name) { unsigned char sha1[20]; @@ -133,10 +66,6 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name) buf = read_sha1_file(sha1, &type, &size); if (!buf) die("Cannot read object %s", obj_name); - if (type == OBJ_TAG) { - pprint_tag(sha1, buf, size); - return 0; - } /* otherwise just spit out the data */ break; diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index 9820f70c84..9cc5c6bf4d 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -134,15 +134,12 @@ tagger $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>" tag_description="This is a tag" tag_content="$tag_header_without_timestamp 0000000000 +0000 -$tag_description" -tag_pretty_content="$tag_header_without_timestamp Thu Jan 1 00:00:00 1970 +0000 - $tag_description" tag_sha1=$(echo_without_newline "$tag_content" | git mktag) tag_size=$(strlen "$tag_content") -run_tests 'tag' $tag_sha1 $tag_size "$tag_content" "$tag_pretty_content" 1 +run_tests 'tag' $tag_sha1 $tag_size "$tag_content" "$tag_content" 1 test_expect_success \ "Reach a blob from a tag pointing to it" \ From 9dbe7c3d7f4424cf0c27c2d4efabf72e58fa76b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Scharfe?= Date: Wed, 17 Apr 2013 20:33:35 +0200 Subject: [PATCH 2/3] pretty: handle broken commit headers gracefully Centralize the parsing of the date and time zone strings in the new helper function show_ident_date() and make sure it checks the pointers provided by split_ident_line() for NULL before use. Reported-by: Ivan Lyapunov Signed-off-by: Rene Scharfe Signed-off-by: Junio C Hamano --- pretty.c | 45 ++++++++++++++++++++++-------------------- t/t4212-log-corrupt.sh | 42 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+), 21 deletions(-) create mode 100755 t/t4212-log-corrupt.sh diff --git a/pretty.c b/pretty.c index 41f04e669d..acbfceb5fe 100644 --- a/pretty.c +++ b/pretty.c @@ -393,6 +393,19 @@ static void add_rfc2047(struct strbuf *sb, const char *line, size_t len, strbuf_addstr(sb, "?="); } +static const char *show_ident_date(const struct ident_split *ident, + enum date_mode mode) +{ + unsigned long date = 0; + int tz = 0; + + if (ident->date_begin && ident->date_end) + date = strtoul(ident->date_begin, NULL, 10); + if (ident->tz_begin && ident->tz_end) + tz = strtol(ident->tz_begin, NULL, 10); + return show_date(date, tz, mode); +} + void pp_user_info(const struct pretty_print_context *pp, const char *what, struct strbuf *sb, const char *line, const char *encoding) @@ -401,12 +414,10 @@ void pp_user_info(const struct pretty_print_context *pp, struct strbuf mail; struct ident_split ident; int linelen; - char *line_end, *date; + char *line_end; const char *mailbuf, *namebuf; size_t namelen, maillen; int max_length = 78; /* per rfc2822 */ - unsigned long time; - int tz; if (pp->fmt == CMIT_FMT_ONELINE) return; @@ -438,8 +449,6 @@ void pp_user_info(const struct pretty_print_context *pp, strbuf_add(&name, namebuf, namelen); namelen = name.len + mail.len + 3; /* ' ' + '<' + '>' */ - time = strtoul(ident.date_begin, &date, 10); - tz = strtol(date, NULL, 10); if (pp->fmt == CMIT_FMT_EMAIL) { strbuf_addstr(sb, "From: "); @@ -472,13 +481,16 @@ void pp_user_info(const struct pretty_print_context *pp, switch (pp->fmt) { case CMIT_FMT_MEDIUM: - strbuf_addf(sb, "Date: %s\n", show_date(time, tz, pp->date_mode)); + strbuf_addf(sb, "Date: %s\n", + show_ident_date(&ident, pp->date_mode)); break; case CMIT_FMT_EMAIL: - strbuf_addf(sb, "Date: %s\n", show_date(time, tz, DATE_RFC2822)); + strbuf_addf(sb, "Date: %s\n", + show_ident_date(&ident, DATE_RFC2822)); break; case CMIT_FMT_FULLER: - strbuf_addf(sb, "%sDate: %s\n", what, show_date(time, tz, pp->date_mode)); + strbuf_addf(sb, "%sDate: %s\n", what, + show_ident_date(&ident, pp->date_mode)); break; default: /* notin' */ @@ -688,8 +700,6 @@ static size_t format_person_part(struct strbuf *sb, char part, { /* currently all placeholders have same length */ const int placeholder_len = 2; - int tz; - unsigned long date = 0; struct ident_split s; const char *name, *mail; size_t maillen, namelen; @@ -716,30 +726,23 @@ static size_t format_person_part(struct strbuf *sb, char part, if (!s.date_begin) goto skip; - date = strtoul(s.date_begin, NULL, 10); - if (part == 't') { /* date, UNIX timestamp */ strbuf_add(sb, s.date_begin, s.date_end - s.date_begin); return placeholder_len; } - /* parse tz */ - tz = strtoul(s.tz_begin + 1, NULL, 10); - if (*s.tz_begin == '-') - tz = -tz; - switch (part) { case 'd': /* date */ - strbuf_addstr(sb, show_date(date, tz, dmode)); + strbuf_addstr(sb, show_ident_date(&s, dmode)); return placeholder_len; case 'D': /* date, RFC2822 style */ - strbuf_addstr(sb, show_date(date, tz, DATE_RFC2822)); + strbuf_addstr(sb, show_ident_date(&s, DATE_RFC2822)); return placeholder_len; case 'r': /* date, relative */ - strbuf_addstr(sb, show_date(date, tz, DATE_RELATIVE)); + strbuf_addstr(sb, show_ident_date(&s, DATE_RELATIVE)); return placeholder_len; case 'i': /* date, ISO 8601 */ - strbuf_addstr(sb, show_date(date, tz, DATE_ISO8601)); + strbuf_addstr(sb, show_ident_date(&s, DATE_ISO8601)); return placeholder_len; } diff --git a/t/t4212-log-corrupt.sh b/t/t4212-log-corrupt.sh new file mode 100755 index 0000000000..ec5099b83d --- /dev/null +++ b/t/t4212-log-corrupt.sh @@ -0,0 +1,42 @@ +#!/bin/sh + +test_description='git log with invalid commit headers' + +. ./test-lib.sh + +test_expect_success 'setup' ' + test_commit foo && + + git cat-file commit HEAD | + sed "/^author /s/>/>-<>/" >broken_email.commit && + git hash-object -w -t commit broken_email.commit >broken_email.hash && + git update-ref refs/heads/broken_email $(cat broken_email.hash) +' + +test_expect_success 'git log with broken author email' ' + { + echo commit $(cat broken_email.hash) + echo "Author: A U Thor " + echo "Date: Thu Jan 1 00:00:00 1970 +0000" + echo + echo " foo" + } >expect.out && + : >expect.err && + + git log broken_email >actual.out 2>actual.err && + + test_cmp expect.out actual.out && + test_cmp expect.err actual.err +' + +test_expect_success 'git log --format with broken author email' ' + echo "A U Thor+author@example.com+" >expect.out && + : >expect.err && + + git log --format="%an+%ae+%ad" broken_email >actual.out 2>actual.err && + + test_cmp expect.out actual.out && + test_cmp expect.err actual.err +' + +test_done From de5abe9fe91a496d019d62abefe23df9d72fad30 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Scharfe?= Date: Wed, 17 Apr 2013 20:33:54 +0200 Subject: [PATCH 3/3] blame: handle broken commit headers gracefully split_ident_line() can leave us with the pointers date_begin, date_end, tz_begin and tz_end all set to NULL. Check them before use and supply the same fallback values as in the case of a negative return code from split_ident_line(). The "(unknown)" is not actually shown in the output, though, because it will be converted to a number (zero) eventually. Signed-off-by: Rene Scharfe Signed-off-by: Junio C Hamano --- builtin/blame.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/builtin/blame.c b/builtin/blame.c index 86100e9662..77707819af 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -1375,10 +1375,15 @@ static void get_ac_line(const char *inbuf, const char *what, maillen = ident.mail_end - ident.mail_begin; mailbuf = ident.mail_begin; - *time = strtoul(ident.date_begin, NULL, 10); + if (ident.date_begin && ident.date_end) + *time = strtoul(ident.date_begin, NULL, 10); + else + *time = 0; - len = ident.tz_end - ident.tz_begin; - strbuf_add(tz, ident.tz_begin, len); + if (ident.tz_begin && ident.tz_end) + strbuf_add(tz, ident.tz_begin, ident.tz_end - ident.tz_begin); + else + strbuf_addstr(tz, "(unknown)"); /* * Now, convert both name and e-mail using mailmap