From 9fcc9caf368aa1fb9ecc68c64b8918d82a637cdb Mon Sep 17 00:00:00 2001 From: Christian Couder Date: Fri, 10 Jul 2020 18:47:37 +0200 Subject: [PATCH 1/3] Documentation: clarify %(contents:XXXX) doc Let's avoid a big dense paragraph by using an unordered list for the %(contents:XXXX) format specifiers. While at it let's also make the following improvements: - Let's not describe %(contents) using "complete message" as it's not clear what an incomplete message is. - Let's improve how the "subject" and "body" are described. - Let's state that "signature" is only available for tag objects. Suggested-by: Jeff King Signed-off-by: Christian Couder Signed-off-by: Junio C Hamano --- Documentation/git-for-each-ref.txt | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt index 6dcd39f6f6..b739412c30 100644 --- a/Documentation/git-for-each-ref.txt +++ b/Documentation/git-for-each-ref.txt @@ -232,12 +232,24 @@ Fields that have name-email-date tuple as its value (`author`, `committer`, and `tagger`) can be suffixed with `name`, `email`, and `date` to extract the named component. -The complete message in a commit and tag object is `contents`. -Its first line is `contents:subject`, where subject is the concatenation -of all lines of the commit message up to the first blank line. The next -line is `contents:body`, where body is all of the lines after the first -blank line. The optional GPG signature is `contents:signature`. The -first `N` lines of the message is obtained using `contents:lines=N`. +The message in a commit or a tag object is `contents`, from which +`contents:` can be used to extract various parts out of: + +contents:subject:: + The first paragraph of the message, which typically is a + single line, is taken as the "subject" of the commit or the + tag message. + +contents:body:: + The remainder of the commit or the tag message that follows + the "subject". + +contents:signature:: + The optional GPG signature of the tag. + +contents:lines=N:: + The first `N` lines of the message. + Additionally, the trailers as interpreted by linkgit:git-interpret-trailers[1] are obtained as `trailers` (or by using the historical alias `contents:trailers`). Non-trailer lines from the trailer block can be omitted From 6e2ef8eb06456e288a0a3cc451134479173cebc5 Mon Sep 17 00:00:00 2001 From: Christian Couder Date: Fri, 10 Jul 2020 18:47:38 +0200 Subject: [PATCH 2/3] t6300: test refs pointing to tree and blob Adding tests for refs pointing to tree and blob shows that we care about testing both positive ("see, my shiny new toy does work") and negative ("and it won't do nonsensical things when given an input it is not designed to work with") cases. Signed-off-by: Christian Couder Signed-off-by: Junio C Hamano --- t/t6300-for-each-ref.sh | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh index da59fadc5d..e9f468d360 100755 --- a/t/t6300-for-each-ref.sh +++ b/t/t6300-for-each-ref.sh @@ -650,6 +650,25 @@ test_atom refs/tags/signed-long contents "subject line body contents $sig" +test_expect_success 'set up refs pointing to tree and blob' ' + git update-ref refs/mytrees/first refs/heads/master^{tree} && + git update-ref refs/myblobs/first refs/heads/master:one +' + +test_atom refs/mytrees/first subject "" +test_atom refs/mytrees/first contents:subject "" +test_atom refs/mytrees/first body "" +test_atom refs/mytrees/first contents:body "" +test_atom refs/mytrees/first contents:signature "" +test_atom refs/mytrees/first contents "" + +test_atom refs/myblobs/first subject "" +test_atom refs/myblobs/first contents:subject "" +test_atom refs/myblobs/first body "" +test_atom refs/myblobs/first contents:body "" +test_atom refs/myblobs/first contents:signature "" +test_atom refs/myblobs/first contents "" + test_expect_success 'set up multiple-sort tags' ' for when in 100000 200000 do From b6839fda6809b1de8d528837dfc99d0837f77c9d Mon Sep 17 00:00:00 2001 From: Christian Couder Date: Thu, 16 Jul 2020 14:19:40 +0200 Subject: [PATCH 3/3] ref-filter: add support for %(contents:size) It's useful and efficient to be able to get the size of the contents directly without having to pipe through `wc -c`. Also the result of the following: `git for-each-ref --format='%(contents)' refs/heads/my-branch | wc -c` is off by one as `git for-each-ref` appends a newline character after the contents, which can be seen by comparing its output with the output from `git cat-file`. As with %(contents), %(contents:size) is silently ignored, if a ref points to something other than a commit or a tag: ``` $ git update-ref refs/mytrees/first HEAD^{tree} $ git for-each-ref --format='%(contents)' refs/mytrees/first $ git for-each-ref --format='%(contents:size)' refs/mytrees/first ``` Signed-off-by: Christian Couder Signed-off-by: Junio C Hamano --- Documentation/git-for-each-ref.txt | 3 +++ ref-filter.c | 7 ++++++- t/t6300-for-each-ref.sh | 19 +++++++++++++++++++ 3 files changed, 28 insertions(+), 1 deletion(-) diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt index b739412c30..2ea71c5f6c 100644 --- a/Documentation/git-for-each-ref.txt +++ b/Documentation/git-for-each-ref.txt @@ -235,6 +235,9 @@ and `date` to extract the named component. The message in a commit or a tag object is `contents`, from which `contents:` can be used to extract various parts out of: +contents:size:: + The size in bytes of the commit or tag message. + contents:subject:: The first paragraph of the message, which typically is a single line, is taken as the "subject" of the commit or the diff --git a/ref-filter.c b/ref-filter.c index 8447cb09be..73d8bfa86d 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -127,7 +127,8 @@ static struct used_atom { unsigned int nobracket : 1, push : 1, push_remote : 1; } remote_ref; struct { - enum { C_BARE, C_BODY, C_BODY_DEP, C_LINES, C_SIG, C_SUB, C_TRAILERS } option; + enum { C_BARE, C_BODY, C_BODY_DEP, C_LENGTH, + C_LINES, C_SIG, C_SUB, C_TRAILERS } option; struct process_trailer_options trailer_opts; unsigned int nlines; } contents; @@ -338,6 +339,8 @@ static int contents_atom_parser(const struct ref_format *format, struct used_ato atom->u.contents.option = C_BARE; else if (!strcmp(arg, "body")) atom->u.contents.option = C_BODY; + else if (!strcmp(arg, "size")) + atom->u.contents.option = C_LENGTH; else if (!strcmp(arg, "signature")) atom->u.contents.option = C_SIG; else if (!strcmp(arg, "subject")) @@ -1253,6 +1256,8 @@ static void grab_sub_body_contents(struct atom_value *val, int deref, void *buf) v->s = copy_subject(subpos, sublen); else if (atom->u.contents.option == C_BODY_DEP) v->s = xmemdupz(bodypos, bodylen); + else if (atom->u.contents.option == C_LENGTH) + v->s = xstrfmt("%"PRIuMAX, (uintmax_t)strlen(subpos)); else if (atom->u.contents.option == C_BODY) v->s = xmemdupz(bodypos, nonsiglen); else if (atom->u.contents.option == C_SIG) diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh index e9f468d360..ea9bb6dade 100755 --- a/t/t6300-for-each-ref.sh +++ b/t/t6300-for-each-ref.sh @@ -52,6 +52,25 @@ test_atom() { sanitize_pgp actual.clean && test_cmp expected actual.clean " + # Automatically test "contents:size" atom after testing "contents" + if test "$2" = "contents" + then + case $(git cat-file -t "$ref") in + tag) + # We cannot use $3 as it expects sanitize_pgp to run + expect=$(git cat-file tag $ref | tail -n +6 | wc -c) ;; + tree | blob) + expect='' ;; + commit) + expect=$(printf '%s' "$3" | wc -c) ;; + esac + # Leave $expect unquoted to lose possible leading whitespaces + echo $expect >expected + test_expect_${4:-sucess} $PREREQ "basic atom: $1 contents:size" ' + git for-each-ref --format="%(contents:size)" "$ref" >actual && + test_cmp expect actual + ' + fi } hexlen=$(test_oid hexsz)