From 97be04077f9ed7ef6ca781cc85d5a0ed36530c04 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Fri, 2 Aug 2013 04:59:07 -0700 Subject: cat-file: only split on whitespace when %(rest) is used Commit c334b87b (cat-file: split --batch input lines on whitespace, 2013-07-11) taught `cat-file --batch-check` to split input lines on the first whitespace, and stash everything after the first token into the %(rest) output format element. It claimed: Object names cannot contain spaces, so any input with spaces would have resulted in a "missing" line. But that is not correct. Refs, object sha1s, and various peeling suffixes cannot contain spaces, but some object names can. In particular: 1. Tree paths like "[]:path with whitespace" 2. Reflog specifications like "@{2 days ago}" 3. Commit searches like "rev^{/grep me}" or ":/grep me" To remain backwards compatible, we cannot split on whitespace by default, hence we will ship 1.8.4 with the commit reverted. Resurrect its attempt but in a weaker form; only do the splitting when "%(rest)" is used in the output format. Since that element did not exist at all before c334b87, old scripts cannot be affected. The existence of object names with spaces does mean that you cannot reliably do: echo ":path with space and other data" | git cat-file --batch-check="%(objectname) %(rest)" as it would split the path and feed only ":path" to get_sha1. But that command is nonsensical. If you wanted to see "and other data" in "%(rest)", git cannot possibly know where the filename ends and the "rest" begins. It might be more robust to have something like "-z" to separate the input elements. But this patch is still a reasonable step before having that. It makes the easy cases easy; people who do not care about %(rest) do not have to consider it, and the %(rest) code handles the spaces and newlines of "rev-list --objects" correctly. Hard cases remain hard but possible (if you might get whitespace in your input, you do not get to use %(rest) and must split and join the output yourself using more flexible tools). And most importantly, it does not preclude us from having different splitting rules later if a "-z" (or similar) option is added. So we can make the hard cases easier later, if we choose to. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'builtin') diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 425346048b..41afaa534b 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -119,6 +119,7 @@ struct expand_data { enum object_type type; unsigned long size; unsigned long disk_size; + const char *rest; /* * If mark_query is true, we do not expand anything, but rather @@ -126,6 +127,13 @@ struct expand_data { */ int mark_query; + /* + * Whether to split the input on whitespace before feeding it to + * get_sha1; this is decided during the mark_query phase based on + * whether we have a %(rest) token in our format. + */ + int split_on_whitespace; + /* * After a mark_query run, this object_info is set up to be * passed to sha1_object_info_extended. It will point to the data @@ -163,6 +171,11 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len, data->info.disk_sizep = &data->disk_size; else strbuf_addf(sb, "%lu", data->disk_size); + } else if (is_atom("rest", atom, len)) { + if (data->mark_query) + data->split_on_whitespace = 1; + else if (data->rest) + strbuf_addstr(sb, data->rest); } else die("unknown format element: %.*s", len, atom); } @@ -273,7 +286,23 @@ static int batch_objects(struct batch_options *opt) warn_on_object_refname_ambiguity = 0; while (strbuf_getline(&buf, stdin, '\n') != EOF) { - int error = batch_one_object(buf.buf, opt, &data); + int error; + + if (data.split_on_whitespace) { + /* + * Split at first whitespace, tying off the beginning + * of the string and saving the remainder (or NULL) in + * data.rest. + */ + char *p = strpbrk(buf.buf, " \t"); + if (p) { + while (*p && strchr(" \t", *p)) + *p++ = '\0'; + } + data.rest = p; + } + + error = batch_one_object(buf.buf, opt, &data); if (error) return error; } -- cgit v1.2.3