split_ident_line(): make best effort when parsing author/committer line

Commits made by ancient version of Git allowed committer without
human readable name, like this (00213b17c in the kernel history):

    tree 6947dba41f8b0e7fe7bccd41a4840d6de6a27079
    parent 352dd1df32e672be4cff71132eb9c06a257872fe
    author Petr Baudis <pasky@ucw.cz> 1135223044 +0100
    committer  <sam@mars.ravnborg.org> 1136151043 +0100

    kconfig: Remove support for lxdialog --checklist

    ...

    Signed-off-by: Petr Baudis <pasky@suse.cz>
    Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
When fed such a commit, --format='%ci' fails to parse it, and gives
back an empty string.  Update the split_ident_line() to be a bit
more lenient when parsing, but make sure the caller that wants to
pick up sane value from its return value does its own validation.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin/commit.c b/builtin/commit.c
index 20cef95d600aeb15b716793beb5fb2534cc2b682..62028e7b44b206e9722eef750be8c067aae31b32 100644 (file)
--- a/builtin/commit.c
+++ b/builtin/commit.c
@@ -478,6 +478,20 @@ static void export_one(const char *var, const char *s, const char *e, int hack)
        strbuf_release(&buf);
 }
 
+static int sane_ident_split(struct ident_split *person)
+{
+       if (!person->name_begin || !person->name_end ||
+           person->name_begin == person->name_end)
+               return 0; /* no human readable name */
+       if (!person->mail_begin || !person->mail_end ||
+           person->mail_begin == person->mail_end)
+               return 0; /* no usable mail */
+       if (!person->date_begin || !person->date_end ||
+           !person->tz_begin || !person->tz_end)
+               return 0;
+       return 1;
+}
+
 static void determine_author_info(struct strbuf *author_ident)
 {
        char *name, *email, *date;
@@ -530,7 +544,8 @@ static void determine_author_info(struct strbuf *author_ident)
        if (force_date)
                date = force_date;
        strbuf_addstr(author_ident, fmt_ident(name, email, date, IDENT_STRICT));
-       if (!split_ident_line(&author, author_ident->buf, author_ident->len)) {
+       if (!split_ident_line(&author, author_ident->buf, author_ident->len) &&
+           sane_ident_split(&author)) {
                export_one("GIT_AUTHOR_NAME", author.name_begin, author.name_end, 0);
                export_one("GIT_AUTHOR_EMAIL", author.mail_begin, author.mail_end, 0);
                export_one("GIT_AUTHOR_DATE", author.date_begin, author.tz_end, '@');

diff --git a/ident.c b/ident.c
index 443c0751bd1f63c059649f9f7f9174349cc1d270..484e0a980308fd2201bf443815a58c41bea17073 100644 (file)
--- a/ident.c
+++ b/ident.c
@@ -210,8 +210,10 @@ int split_ident_line(struct ident_split *split, const char *line, int len)
                        split->name_end = cp + 1;
                        break;
                }
-       if (!split->name_end)
-               return status;
+       if (!split->name_end) {
+               /* no human readable name */
+               split->name_end = split->name_begin;
+       }
 
        for (cp = split->mail_begin; cp < line + len; cp++)
                if (*cp == '>') {