From ab90ecae992e44e3e8303f143ad858608acabcf5 Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Mon, 16 Mar 2020 18:05:02 +0000 Subject: convert: permit passing additional metadata to filter processes There are a variety of situations where a filter process can make use of some additional metadata. For example, some people find the ident filter too limiting and would like to include the commit or the branch in their smudged files. This information isn't available during checkout as HEAD hasn't been updated at that point, and it wouldn't be available in archives either. Let's add a way to pass this metadata down to the filter. We pass the blob we're operating on, the treeish (preferring the commit over the tree if one exists), and the ref we're operating on. Note that we won't pass this information in all cases, such as when renormalizing or when we're performing diffs, since it doesn't make sense in those cases. The data we currently get from the filter process looks like the following: command=smudge pathname=git.c 0000 With this change, we'll get data more like this: command=smudge pathname=git.c refname=refs/tags/v2.25.1 treeish=c522f061d551c9bb8684a7c3859b2ece4499b56b blob=7be7ad34bd053884ec48923706e70c81719a8660 0000 There are a couple things to note about this approach. For operations like checkout, treeish will always be a commit, since we cannot check out individual trees, but for other operations, like archive, we can end up operating on only a particular tree, so we'll provide only a tree as the treeish. Similar comments apply for refname, since there are a variety of cases in which we won't have a ref. This commit wires up the code to print this information, but doesn't pass any of it at this point. In a future commit, we'll have various code paths pass the actual useful data down. Signed-off-by: brian m. carlson Signed-off-by: Junio C Hamano --- diff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'diff.c') diff --git a/diff.c b/diff.c index f2cfbf2214..12761c8017 100644 --- a/diff.c +++ b/diff.c @@ -4071,7 +4071,7 @@ static void prep_temp_blob(struct index_state *istate, if (!temp->tempfile) die_errno("unable to create temp-file"); if (convert_to_working_tree(istate, path, - (const char *)blob, (size_t)size, &buf)) { + (const char *)blob, (size_t)size, &buf, NULL)) { blob = buf.buf; size = buf.len; } -- cgit 1.2.3-korg From c397aac02f9f97976f675115aa5df6ca01e26d59 Mon Sep 17 00:00:00 2001 From: "brian m. carlson" Date: Mon, 16 Mar 2020 18:05:03 +0000 Subject: convert: provide additional metadata to filters Now that we have the codebase wired up to pass any additional metadata to filters, let's collect the additional metadata that we'd like to pass. The two main places we pass this metadata are checkouts and archives. In these two situations, reading HEAD isn't a valid option, since HEAD isn't updated for checkouts until after the working tree is written and archives can accept an arbitrary tree. In other situations, HEAD will usually reflect the refname of the branch in current use. We pass a smaller amount of data in other cases, such as git cat-file, where we can really only logically know about the blob. This commit updates only the parts of the checkout code where we don't use unpack_trees. That function and callers of it will be handled in a future commit. In the archive code, we leak a small amount of memory, since nothing we pass in the archiver argument structure is freed. Signed-off-by: brian m. carlson Signed-off-by: Junio C Hamano --- archive.c | 13 ++++++++++--- archive.h | 1 + builtin/cat-file.c | 5 ++++- builtin/checkout.c | 13 +++++++++++++ cache.h | 1 + convert.c | 22 ++++++++++++++++++++++ convert.h | 17 +++++++++++++++++ diff.c | 5 ++++- entry.c | 7 +++++-- t/t0021/rot13-filter.pl | 6 ++++++ 10 files changed, 83 insertions(+), 7 deletions(-) (limited to 'diff.c') diff --git a/archive.c b/archive.c index d9e92cce58..fb39706120 100644 --- a/archive.c +++ b/archive.c @@ -77,6 +77,11 @@ void *object_file_to_archive(const struct archiver_args *args, { void *buffer; const struct commit *commit = args->convert ? args->commit : NULL; + struct checkout_metadata meta; + + init_checkout_metadata(&meta, args->refname, + args->commit_oid ? args->commit_oid : + (args->tree ? &args->tree->object.oid : NULL), oid); path += args->baselen; buffer = read_object_file(oid, type, sizep); @@ -85,7 +90,7 @@ void *object_file_to_archive(const struct archiver_args *args, size_t size = 0; strbuf_attach(&buf, buffer, *sizep, *sizep + 1); - convert_to_working_tree(args->repo->index, path, buf.buf, buf.len, &buf, NULL); + convert_to_working_tree(args->repo->index, path, buf.buf, buf.len, &buf, &meta); if (commit) format_subst(commit, buf.buf, buf.len, &buf); buffer = strbuf_detach(&buf, &size); @@ -385,16 +390,17 @@ static void parse_treeish_arg(const char **argv, struct tree *tree; const struct commit *commit; struct object_id oid; + char *ref = NULL; /* Remotes are only allowed to fetch actual refs */ if (remote && !remote_allow_unreachable) { - char *ref = NULL; const char *colon = strchrnul(name, ':'); int refnamelen = colon - name; if (!dwim_ref(name, refnamelen, &oid, &ref)) die(_("no such ref: %.*s"), refnamelen, name); - free(ref); + } else { + dwim_ref(name, strlen(name), &oid, &ref); } if (get_oid(name, &oid)) @@ -427,6 +433,7 @@ static void parse_treeish_arg(const char **argv, tree = parse_tree_indirect(&tree_oid); } + ar_args->refname = ref; ar_args->tree = tree; ar_args->commit_oid = commit_oid; ar_args->commit = commit; diff --git a/archive.h b/archive.h index e60e3dd31c..3bd96bf6bb 100644 --- a/archive.h +++ b/archive.h @@ -8,6 +8,7 @@ struct repository; struct archiver_args { struct repository *repo; + const char *refname; const char *base; size_t baselen; struct tree *tree; diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 545fed4924..6ecc8ee6dc 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -42,7 +42,10 @@ static int filter_object(const char *path, unsigned mode, oid_to_hex(oid), path); if ((type == OBJ_BLOB) && S_ISREG(mode)) { struct strbuf strbuf = STRBUF_INIT; - if (convert_to_working_tree(&the_index, path, *buf, *size, &strbuf, NULL)) { + struct checkout_metadata meta; + + init_checkout_metadata(&meta, NULL, NULL, oid); + if (convert_to_working_tree(&the_index, path, *buf, *size, &strbuf, &meta)) { free(*buf); *size = strbuf.len; *buf = strbuf_detach(&strbuf, NULL); diff --git a/builtin/checkout.c b/builtin/checkout.c index 8a28f48d67..1bdb70d3dd 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -92,6 +92,8 @@ struct branch_info { const char *name; /* The short name used */ const char *path; /* The full name of a real branch */ struct commit *commit; /* The named commit */ + char *refname; /* The full name of the ref being checked out. */ + struct object_id oid; /* The object ID of the commit being checked out. */ /* * if not null the branch is detached because it's already * checked out in this checkout @@ -360,6 +362,10 @@ static int checkout_worktree(const struct checkout_opts *opts, state.refresh_cache = 1; state.istate = &the_index; + init_checkout_metadata(&state.meta, info->refname, + info->commit ? &info->commit->object.oid : &info->oid, + NULL); + enable_delayed_checkout(&state); for (pos = 0; pos < active_nr; pos++) { struct cache_entry *ce = active_cache[pos]; @@ -636,6 +642,13 @@ static void setup_branch_path(struct branch_info *branch) { struct strbuf buf = STRBUF_INIT; + /* + * If this is a ref, resolve it; otherwise, look up the OID for our + * expression. Failure here is okay. + */ + if (!dwim_ref(branch->name, strlen(branch->name), &branch->oid, &branch->refname)) + repo_get_oid_committish(the_repository, branch->name, &branch->oid); + strbuf_branchname(&buf, branch->name, INTERPRET_BRANCH_LOCAL); if (strcmp(buf.buf, branch->name)) branch->name = xstrdup(buf.buf); diff --git a/cache.h b/cache.h index 37c899b53f..9b24e5d61f 100644 --- a/cache.h +++ b/cache.h @@ -1679,6 +1679,7 @@ struct checkout { const char *base_dir; int base_dir_len; struct delayed_checkout *delayed_checkout; + struct checkout_metadata meta; unsigned force:1, quiet:1, not_new:1, diff --git a/convert.c b/convert.c index 6261921cfb..5aa87d45e3 100644 --- a/convert.c +++ b/convert.c @@ -2006,3 +2006,25 @@ int stream_filter(struct stream_filter *filter, { return filter->vtbl->filter(filter, input, isize_p, output, osize_p); } + +void init_checkout_metadata(struct checkout_metadata *meta, const char *refname, + const struct object_id *treeish, + const struct object_id *blob) +{ + memset(meta, 0, sizeof(*meta)); + if (refname) + meta->refname = refname; + if (treeish) + oidcpy(&meta->treeish, treeish); + if (blob) + oidcpy(&meta->blob, blob); +} + +void clone_checkout_metadata(struct checkout_metadata *dst, + const struct checkout_metadata *src, + const struct object_id *blob) +{ + memcpy(dst, src, sizeof(*dst)); + if (blob) + oidcpy(&dst->blob, blob); +} diff --git a/convert.h b/convert.h index 894e01c38b..e29d1026a6 100644 --- a/convert.h +++ b/convert.h @@ -102,6 +102,23 @@ void convert_to_git_filter_fd(const struct index_state *istate, int would_convert_to_git_filter_fd(const struct index_state *istate, const char *path); +/* + * Initialize the checkout metadata with the given values. Any argument may be + * NULL if it is not applicable. The treeish should be a commit if that is + * available, and a tree otherwise. + * + * The refname is not copied and must be valid for the lifetime of the struct. + * THe object IDs are copied. + */ +void init_checkout_metadata(struct checkout_metadata *meta, const char *refname, + const struct object_id *treeish, + const struct object_id *blob); + +/* Copy the metadata from src to dst, updating the blob. */ +void clone_checkout_metadata(struct checkout_metadata *dst, + const struct checkout_metadata *src, + const struct object_id *blob); + /* * Reset the internal list of attributes used by convert_to_git and * convert_to_working_tree. diff --git a/diff.c b/diff.c index 12761c8017..1010d806f5 100644 --- a/diff.c +++ b/diff.c @@ -4062,6 +4062,9 @@ static void prep_temp_blob(struct index_state *istate, struct strbuf tempfile = STRBUF_INIT; char *path_dup = xstrdup(path); const char *base = basename(path_dup); + struct checkout_metadata meta; + + init_checkout_metadata(&meta, NULL, NULL, oid); /* Generate "XXXXXX_basename.ext" */ strbuf_addstr(&tempfile, "XXXXXX_"); @@ -4071,7 +4074,7 @@ static void prep_temp_blob(struct index_state *istate, if (!temp->tempfile) die_errno("unable to create temp-file"); if (convert_to_working_tree(istate, path, - (const char *)blob, (size_t)size, &buf, NULL)) { + (const char *)blob, (size_t)size, &buf, &meta)) { blob = buf.buf; size = buf.len; } diff --git a/entry.c b/entry.c index 4b2d9b2dad..00b4903366 100644 --- a/entry.c +++ b/entry.c @@ -264,6 +264,9 @@ static int write_entry(struct cache_entry *ce, size_t newsize = 0; struct stat st; const struct submodule *sub; + struct checkout_metadata meta; + + clone_checkout_metadata(&meta, &state->meta, &ce->oid); if (ce_mode_s_ifmt == S_IFREG) { struct stream_filter *filter = get_stream_filter(state->istate, ce->name, @@ -315,13 +318,13 @@ static int write_entry(struct cache_entry *ce, */ if (dco && dco->state != CE_NO_DELAY) { ret = async_convert_to_working_tree(state->istate, ce->name, new_blob, - size, &buf, NULL, dco); + size, &buf, &meta, dco); if (ret && string_list_has_string(&dco->paths, ce->name)) { free(new_blob); goto delayed; } } else - ret = convert_to_working_tree(state->istate, ce->name, new_blob, size, &buf, NULL); + ret = convert_to_working_tree(state->istate, ce->name, new_blob, size, &buf, &meta); if (ret) { free(new_blob); diff --git a/t/t0021/rot13-filter.pl b/t/t0021/rot13-filter.pl index 470107248e..c43cf433cf 100644 --- a/t/t0021/rot13-filter.pl +++ b/t/t0021/rot13-filter.pl @@ -135,7 +135,13 @@ sub rot13 { if ( exists $DELAY{$pathname} and $DELAY{$pathname}{"requested"} == 0 ) { $DELAY{$pathname}{"requested"} = 1; } + } elsif ($buffer =~ /^(ref|treeish|blob)=/) { + # Do nothing. } else { + # In general, filters need to be graceful about + # new metadata, since it's documented that we + # can pass any key-value pairs, but for tests, + # let's be a little stricter. die "Unknown message '$buffer'"; } -- cgit 1.2.3-korg