diff options
author | Philippe Blain <levraiphilippeblain@gmail.com> | 2020-10-29 12:48:28 +0000 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2020-10-29 12:57:45 -0700 |
commit | 9f75ce3d8f2666ea82913a88d7068f28893b23a8 (patch) | |
tree | 8ddd8c9bb432c6f282438169769afb93e9b1e346 /ref-filter.c | |
parent | 69986e19ffcfb9af674ae5180689ab7bbf92ed28 (diff) |
ref-filter: handle CRLF at end-of-line more gracefully
The ref-filter code does not correctly handle commit or tag messages that use CRLF as the line terminator. Such messages can be created with the `--cleanup=verbatim` option of `git commit` and `git tag`, or by using `git commit-tree` directly. The function `find_subpos` in ref-filter.c looks for two consecutive LFs to find the end of the subject line, a sequence which is absent in messages using CRLF. This results in the whole message being parsed as the subject line (`%(contents:subject)`), and the body of the message (`%(contents:body)`) being empty. Moreover, in `copy_subject`, which wants to return the subject as a single line, '\n' is replaced by space, but '\r' is untouched. This impacts the output of `git branch`, `git tag` and `git for-each-ref`. This behaviour is a regression for `git branch --verbose`, which bisects down to 949af0684c (branch: use ref-filter printing APIs, 2017-01-10). Adjust the ref-filter code to be more lenient by hardening the logic in `copy_subject` and `find_subpos` to correctly parse messages containing CRLF. Add a new test script, 't3920-crlf-messages.sh', to test the behaviour of commands using either the ref-filter or the pretty APIs with messages using CRLF line endings. The function `test_crlf_subject_body_and_contents` can be used to test that the `--format` option of `branch`, `tag`, `for-each-ref`, `log` and `show` correctly displays the subject, body and raw content of commit and tag messages using CRLF. Test the output of `branch`, `tag` and `for-each-ref` with such commits. Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Philippe Blain <levraiphilippeblain@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'ref-filter.c')
-rw-r--r-- | ref-filter.c | 36 |
1 files changed, 22 insertions, 14 deletions
diff --git a/ref-filter.c b/ref-filter.c index c62f6b4822..6476686fea 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -1097,14 +1097,19 @@ static const char *copy_email(const char *buf, struct used_atom *atom) static char *copy_subject(const char *buf, unsigned long len) { - char *r = xmemdupz(buf, len); + struct strbuf sb = STRBUF_INIT; int i; - for (i = 0; i < len; i++) - if (r[i] == '\n') - r[i] = ' '; + for (i = 0; i < len; i++) { + if (buf[i] == '\r' && i + 1 < len && buf[i + 1] == '\n') + continue; /* ignore CR in CRLF */ - return r; + if (buf[i] == '\n') + strbuf_addch(&sb, ' '); + else + strbuf_addch(&sb, buf[i]); + } + return strbuf_detach(&sb, NULL); } static void grab_date(const char *buf, struct atom_value *v, const char *atomname) @@ -1228,20 +1233,23 @@ static void find_subpos(const char *buf, /* subject is first non-empty line */ *sub = buf; - /* subject goes to first empty line */ - while (buf < *sig && *buf && *buf != '\n') { - eol = strchrnul(buf, '\n'); - if (*eol) - eol++; - buf = eol; - } + /* subject goes to first empty line before signature begins */ + if ((eol = strstr(*sub, "\n\n"))) { + eol = eol < *sig ? eol : *sig; + /* check if message uses CRLF */ + } else if (! (eol = strstr(*sub, "\r\n\r\n"))) { + /* treat whole message as subject */ + eol = strrchr(*sub, '\0'); + } + buf = eol; *sublen = buf - *sub; /* drop trailing newline, if present */ - if (*sublen && (*sub)[*sublen - 1] == '\n') + while (*sublen && ((*sub)[*sublen - 1] == '\n' || + (*sub)[*sublen - 1] == '\r')) *sublen -= 1; /* skip any empty lines */ - while (*buf == '\n') + while (*buf == '\n' || *buf == '\r') buf++; *body = buf; *bodylen = strlen(buf); |