From: Phillip Wood Date: Mon, 13 Mar 2023 10:31:44 GMT Subject: Re: [PATCH v2 1/8] for-each-ref: add --stdin option Message-ID: <6badb697-aa74-cc2f-ba43-0bbf54b10973@dunelm.org.uk> In-Reply-To: Hi Stolee On 10/03/2023 17:20, Derrick Stolee via GitGitGadget wrote: > From: Derrick Stolee > > When a user wishes to input a large list of patterns to 'git > for-each-ref' (likely a long list of exact refs) there are frequently > system limits on the number of command-line arguments. > > Add a new --stdin option to instead read the patterns from standard > input. Add tests that check that any unrecognized arguments are > considered an error when --stdin is provided. Also, an empty pattern > list is interpreted as the complete ref set. > > When reading from stdin, we populate the filter.name_patterns array > dynamically as opposed to pointing to the 'argv' array directly. This > requires a careful cast while freeing the individual strings, > conditioned on the --stdin option. I think what you've got here is fine, but if you wanted you could simplify it by using an strvec. Something like struct strvec vec = STRVEC_INIT; ... if (from_stdin) { struct strbuf buf = STRBUF_INIT; if (argv[0]) die(_("unknown arguments supplied with --stdin")); while (strbuf_getline(&line, stdin) != EOF) strvec_push(&vec, buf.buf); filter.name_patters = vec.v; } else { filter.name_patterns = argv; } ... strvec_clear(&vec); gets rid of the manual memory management with ALLOC_GROW() and the need to cast filter.name_patterns when free()ing. It is not immediately obvious from the name but struct strvec keeps the array NULL terminated. Best Wishes Phillip > Signed-off-by: Derrick Stolee > --- > Documentation/git-for-each-ref.txt | 7 +++++- > builtin/for-each-ref.c | 29 ++++++++++++++++++++++- > t/t6300-for-each-ref.sh | 37 ++++++++++++++++++++++++++++++ > 3 files changed, 71 insertions(+), 2 deletions(-) > > diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt > index 6da899c6296..ccdc2911bb9 100644 > --- a/Documentation/git-for-each-ref.txt > +++ b/Documentation/git-for-each-ref.txt > @@ -9,7 +9,8 @@ SYNOPSIS > -------- > [verse] > 'git for-each-ref' [--count=] [--shell|--perl|--python|--tcl] > - [(--sort=)...] [--format=] [...] > + [(--sort=)...] [--format=] > + [ --stdin | ... ] > [--points-at=] > [--merged[=]] [--no-merged[=]] > [--contains[=]] [--no-contains[=]] > @@ -32,6 +33,10 @@ OPTIONS > literally, in the latter case matching completely or from the > beginning up to a slash. > > +--stdin:: > + If `--stdin` is supplied, then the list of patterns is read from > + standard input instead of from the argument list. > + > --count=:: > By default the command shows all refs that match > ``. This option makes it stop after showing > diff --git a/builtin/for-each-ref.c b/builtin/for-each-ref.c > index 6f62f40d126..e005a7ef3ce 100644 > --- a/builtin/for-each-ref.c > +++ b/builtin/for-each-ref.c > @@ -25,6 +25,7 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix) > struct ref_format format = REF_FORMAT_INIT; > struct strbuf output = STRBUF_INIT; > struct strbuf err = STRBUF_INIT; > + int from_stdin = 0; > > struct option opts[] = { > OPT_BIT('s', "shell", &format.quote_style, > @@ -49,6 +50,7 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix) > OPT_CONTAINS(&filter.with_commit, N_("print only refs which contain the commit")), > OPT_NO_CONTAINS(&filter.no_commit, N_("print only refs which don't contain the commit")), > OPT_BOOL(0, "ignore-case", &icase, N_("sorting and filtering are case insensitive")), > + OPT_BOOL(0, "stdin", &from_stdin, N_("read reference patterns from stdin")), > OPT_END(), > }; > > @@ -75,7 +77,27 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix) > ref_sorting_set_sort_flags_all(sorting, REF_SORTING_ICASE, icase); > filter.ignore_case = icase; > > - filter.name_patterns = argv; > + if (from_stdin) { > + struct strbuf line = STRBUF_INIT; > + size_t nr = 0, alloc = 16; > + > + if (argv[0]) > + die(_("unknown arguments supplied with --stdin")); > + > + CALLOC_ARRAY(filter.name_patterns, alloc); > + > + while (strbuf_getline(&line, stdin) != EOF) { > + ALLOC_GROW(filter.name_patterns, nr + 1, alloc); > + filter.name_patterns[nr++] = strbuf_detach(&line, NULL); > + } > + > + /* Add a terminating NULL string. */ > + ALLOC_GROW(filter.name_patterns, nr + 1, alloc); > + filter.name_patterns[nr + 1] = NULL; > + } else { > + filter.name_patterns = argv; > + } > + > filter.match_as_path = 1; > filter_refs(&array, &filter, FILTER_REFS_ALL); > ref_array_sort(sorting, &array); > @@ -97,5 +119,10 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix) > free_commit_list(filter.with_commit); > free_commit_list(filter.no_commit); > ref_sorting_release(sorting); > + if (from_stdin) { > + for (size_t i = 0; filter.name_patterns[i]; i++) > + free((char *)filter.name_patterns[i]); > + free(filter.name_patterns); > + } > return 0; > } > diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh > index c466fd989f1..a58053a54c5 100755 > --- a/t/t6300-for-each-ref.sh > +++ b/t/t6300-for-each-ref.sh > @@ -1464,4 +1464,41 @@ sig_crlf="$(printf "%s" "$sig" | append_cr; echo dummy)" > sig_crlf=${sig_crlf%dummy} > test_atom refs/tags/fake-sig-crlf contents:signature "$sig_crlf" > > +test_expect_success 'git for-each-ref --stdin: empty' ' > + >in && > + git for-each-ref --format="%(refname)" --stdin actual && > + git for-each-ref --format="%(refname)" >expect && > + test_cmp expect actual > +' > + > +test_expect_success 'git for-each-ref --stdin: fails if extra args' ' > + >in && > + test_must_fail git for-each-ref --format="%(refname)" \ > + --stdin refs/heads/extra err && > + grep "unknown arguments supplied with --stdin" err > +' > + > +test_expect_success 'git for-each-ref --stdin: matches' ' > + cat >in <<-EOF && > + refs/tags/multi* > + refs/heads/amb* > + EOF > + > + cat >expect <<-EOF && > + refs/heads/ambiguous > + refs/tags/multi-ref1-100000-user1 > + refs/tags/multi-ref1-100000-user2 > + refs/tags/multi-ref1-200000-user1 > + refs/tags/multi-ref1-200000-user2 > + refs/tags/multi-ref2-100000-user1 > + refs/tags/multi-ref2-100000-user2 > + refs/tags/multi-ref2-200000-user1 > + refs/tags/multi-ref2-200000-user2 > + refs/tags/multiline > + EOF > + > + git for-each-ref --format="%(refname)" --stdin actual && > + test_cmp expect actual > +' > + > test_done