Change from last version: * Remove the atom_type member from valid_atom at the suggestion of Christian and Junio, and use ATOM_* as the coordinates of valid_atom. * Add ATOM_INVALID and ATOM_UNKNOWN under Christian's suggestion, we can traverse valid_atom through them. * Add a note about enum atom_type to remind readers of its role. ZheNing Hu (2): [GSOC] ref-filter: add objectsize to used_atom [GSOC] ref-filter: introduce enum atom_type ref-filter.c | 231 ++++++++++++++++++++++++++++++++++----------------- 1 file changed, 155 insertions(+), 76 deletions(-) base-commit: 7e391989789db82983665667013a46eabc6fc570 Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-951%2Fadlternative%2Fref-filter-atom-type-v2 Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-951/adlternative/ref-filter-atom-type-v2 Pull-Request: https://github.com/gitgitgadget/git/pull/951 Range-diff vs v1: 1: 91ca57c9d04a = 1: 91ca57c9d04a [GSOC] ref-filter: add objectsize to used_atom 2: 3770df182983 ! 2: a1f70b39b7ef [GSOC][RFC] ref-filter: introduce enum atom_type @@ Metadata Author: ZheNing Hu <adlternative@xxxxxxxxx> ## Commit message ## - [GSOC][RFC] ref-filter: introduce enum atom_type + [GSOC] ref-filter: introduce enum atom_type In the original ref-filter design, it will copy the parsed atom's name and attributes to `used_atom[i].name` in the @@ Commit message in the later specific ref attributes filling step. It use a lot of string matching to determine which atom we need. - Introduce the enum member `valid_atom.atom_type` which - record type of each valid_atom, in the first step of the - atom parsing, `used_atom.atom_type` will record corresponding - enum value from `valid_atom.atom_type`, and then in specific - reference attribute filling step, only need to compare the - value of the `used_atom.atom_type` to judge the atom type. + Introduce the enum "atom_type", each enum value is named + as `ATOM_*`, which is the index of each corresponding + valid_atom entry. In the first step of the atom parsing, + `used_atom.atom_type` will record corresponding enum value + from valid_atom entry index, and then in specific reference + attribute filling step, only need to compare the value of + the `used_atom.atom_type` to judge the atom type. - At the same time, The value of an atom_type is the coordinate - of its corresponding valid_atom entry, we can quickly index - to the corresponding valid_atom entry by the atom_type value. + the enum value of `ATOM_UNKNOWN` is equals to zero, which + could ensure that we can easily distinguish such a struct + where the atom_type is known from such a struct where it + is unknown yet. + + the enum value of `ATOM_INVALID` is equals to the size of + valid_atom array, which could help us iterate over + valid_atom array using something like: + + for (i = ATOM_UNKNOWN + 1; i < ATOM_INVALID; i++) + /* do something with valid_atom[i] */; Signed-off-by: ZheNing Hu <adlternative@xxxxxxxxx> @@ ref-filter.c: static struct ref_to_worktree_map { struct worktree **worktrees; } ref_to_worktree_map; ++/* ++ * The enum atom_type is used as the coordinates of valid_atom entry. ++ * In the atom parsing stage, it will be passed to used_atom.atom_type ++ * as the identifier of the atom type. We can judge the type of used_atom ++ * entry by `if (used_atom[i].atom_type == ATOM_*)`. ++ * ++ * ATOM_UNKNOWN equals to 0, used as an enumeration value of uninitialized ++ * atom_type. ++ * ATOM_INVALID equals to the size of valid_atom array, which could help us ++ * iterate over valid_atom array like this: ++ * ++ * for (i = ATOM_UNKNOWN + 1; i < ATOM_INVALID; i++) { ++ * int len = strlen(valid_atom[i].name); ++ * if (len == atom_len && !memcmp(valid_atom[i].name, sp, len)) ++ * break; ++ * } ++ */ +enum atom_type { ++ATOM_UNKNOWN, +ATOM_REFNAME, +ATOM_OBJECTTYPE, +ATOM_OBJECTSIZE, @@ ref-filter.c: static struct ref_to_worktree_map { +ATOM_IF, +ATOM_THEN, +ATOM_ELSE, ++ATOM_INVALID, +}; + /* * An atom is a valid field atom listed below, possibly prefixed with * a "*" to denote deref_tag(). -@@ ref-filter.c: static struct used_atom { - const char *name; - cmp_type type; - info_source source; -+ enum atom_type atom_type; - union { - char color[COLOR_MAXLEN]; - struct align align; -@@ ref-filter.c: static int head_atom_parser(const struct ref_format *format, struct used_atom *a - } - - static struct { +@@ ref-filter.c: static struct ref_to_worktree_map { + * array. + */ + static struct used_atom { + enum atom_type atom_type; const char *name; + cmp_type type; info_source source; - cmp_type cmp_type; +@@ ref-filter.c: static struct { int (*parser)(const struct ref_format *format, struct used_atom *atom, const char *arg, struct strbuf *err); } valid_atom[] = { @@ ref-filter.c: static int head_atom_parser(const struct ref_format *format, struc - { "if", SOURCE_NONE, FIELD_STR, if_atom_parser }, - { "then", SOURCE_NONE }, - { "else", SOURCE_NONE }, -+ { ATOM_REFNAME, "refname", SOURCE_NONE, FIELD_STR, refname_atom_parser }, -+ { ATOM_OBJECTTYPE, "objecttype", SOURCE_OTHER, FIELD_STR, objecttype_atom_parser }, -+ { ATOM_OBJECTSIZE, "objectsize", SOURCE_OTHER, FIELD_ULONG, objectsize_atom_parser }, -+ { ATOM_OBJECTNAME, "objectname", SOURCE_OTHER, FIELD_STR, oid_atom_parser }, -+ { ATOM_DELTABASE, "deltabase", SOURCE_OTHER, FIELD_STR, deltabase_atom_parser }, -+ { ATOM_TREE, "tree", SOURCE_OBJ, FIELD_STR, oid_atom_parser }, -+ { ATOM_PARENT, "parent", SOURCE_OBJ, FIELD_STR, oid_atom_parser }, -+ { ATOM_NUMPARENT, "numparent", SOURCE_OBJ, FIELD_ULONG }, -+ { ATOM_OBJECT, "object", SOURCE_OBJ }, -+ { ATOM_TYPE, "type", SOURCE_OBJ }, -+ { ATOM_TAG, "tag", SOURCE_OBJ }, -+ { ATOM_AUTHOR, "author", SOURCE_OBJ }, -+ { ATOM_AUTHORNAME, "authorname", SOURCE_OBJ }, -+ { ATOM_AUTHOREMAIL, "authoremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser }, -+ { ATOM_AUTHORDATE, "authordate", SOURCE_OBJ, FIELD_TIME }, -+ { ATOM_COMMITTER, "committer", SOURCE_OBJ }, -+ { ATOM_COMMITTERNAME, "committername", SOURCE_OBJ }, -+ { ATOM_COMMITTEREMAIL, "committeremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser }, -+ { ATOM_COMMITTERDATE, "committerdate", SOURCE_OBJ, FIELD_TIME }, -+ { ATOM_TAGGER, "tagger", SOURCE_OBJ }, -+ { ATOM_TAGGERNAME, "taggername", SOURCE_OBJ }, -+ { ATOM_TAGGEREMAIL, "taggeremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser }, -+ { ATOM_TAGGERDATE, "taggerdate", SOURCE_OBJ, FIELD_TIME }, -+ { ATOM_CREATOR, "creator", SOURCE_OBJ }, -+ { ATOM_CREATORDATE, "creatordate", SOURCE_OBJ, FIELD_TIME }, -+ { ATOM_SUBJECT, "subject", SOURCE_OBJ, FIELD_STR, subject_atom_parser }, -+ { ATOM_BODY, "body", SOURCE_OBJ, FIELD_STR, body_atom_parser }, -+ { ATOM_TRAILERS, "trailers", SOURCE_OBJ, FIELD_STR, trailers_atom_parser }, -+ { ATOM_CONTENTS, "contents", SOURCE_OBJ, FIELD_STR, contents_atom_parser }, -+ { ATOM_UPSTREAM, "upstream", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser }, -+ { ATOM_PUSH, "push", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser }, -+ { ATOM_SYMREF, "symref", SOURCE_NONE, FIELD_STR, refname_atom_parser }, -+ { ATOM_FLAG, "flag", SOURCE_NONE }, -+ { ATOM_HEAD, "HEAD", SOURCE_NONE, FIELD_STR, head_atom_parser }, -+ { ATOM_COLOR, "color", SOURCE_NONE, FIELD_STR, color_atom_parser }, -+ { ATOM_WORKTREEPATH, "worktreepath", SOURCE_NONE }, -+ { ATOM_ALIGN, "align", SOURCE_NONE, FIELD_STR, align_atom_parser }, -+ { ATOM_END, "end", SOURCE_NONE }, -+ { ATOM_IF, "if", SOURCE_NONE, FIELD_STR, if_atom_parser }, -+ { ATOM_THEN, "then", SOURCE_NONE }, -+ { ATOM_ELSE, "else", SOURCE_NONE }, ++ [ATOM_REFNAME] = { "refname", SOURCE_NONE, FIELD_STR, refname_atom_parser }, ++ [ATOM_OBJECTTYPE] = { "objecttype", SOURCE_OTHER, FIELD_STR, objecttype_atom_parser }, ++ [ATOM_OBJECTSIZE] = { "objectsize", SOURCE_OTHER, FIELD_ULONG, objectsize_atom_parser }, ++ [ATOM_OBJECTNAME] = { "objectname", SOURCE_OTHER, FIELD_STR, oid_atom_parser }, ++ [ATOM_DELTABASE] = { "deltabase", SOURCE_OTHER, FIELD_STR, deltabase_atom_parser }, ++ [ATOM_TREE] = { "tree", SOURCE_OBJ, FIELD_STR, oid_atom_parser }, ++ [ATOM_PARENT] = { "parent", SOURCE_OBJ, FIELD_STR, oid_atom_parser }, ++ [ATOM_NUMPARENT] = { "numparent", SOURCE_OBJ, FIELD_ULONG }, ++ [ATOM_OBJECT] = { "object", SOURCE_OBJ }, ++ [ATOM_TYPE] = { "type", SOURCE_OBJ }, ++ [ATOM_TAG] = { "tag", SOURCE_OBJ }, ++ [ATOM_AUTHOR] = { "author", SOURCE_OBJ }, ++ [ATOM_AUTHORNAME] = { "authorname", SOURCE_OBJ }, ++ [ATOM_AUTHOREMAIL] = { "authoremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser }, ++ [ATOM_AUTHORDATE] = { "authordate", SOURCE_OBJ, FIELD_TIME }, ++ [ATOM_COMMITTER] = { "committer", SOURCE_OBJ }, ++ [ATOM_COMMITTERNAME] = { "committername", SOURCE_OBJ }, ++ [ATOM_COMMITTEREMAIL] = { "committeremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser }, ++ [ATOM_COMMITTERDATE] = { "committerdate", SOURCE_OBJ, FIELD_TIME }, ++ [ATOM_TAGGER] = { "tagger", SOURCE_OBJ }, ++ [ATOM_TAGGERNAME] = { "taggername", SOURCE_OBJ }, ++ [ATOM_TAGGEREMAIL] = { "taggeremail", SOURCE_OBJ, FIELD_STR, person_email_atom_parser }, ++ [ATOM_TAGGERDATE] = { "taggerdate", SOURCE_OBJ, FIELD_TIME }, ++ [ATOM_CREATOR] = { "creator", SOURCE_OBJ }, ++ [ATOM_CREATORDATE] = { "creatordate", SOURCE_OBJ, FIELD_TIME }, ++ [ATOM_SUBJECT] = { "subject", SOURCE_OBJ, FIELD_STR, subject_atom_parser }, ++ [ATOM_BODY] = { "body", SOURCE_OBJ, FIELD_STR, body_atom_parser }, ++ [ATOM_TRAILERS] = { "trailers", SOURCE_OBJ, FIELD_STR, trailers_atom_parser }, ++ [ATOM_CONTENTS] = { "contents", SOURCE_OBJ, FIELD_STR, contents_atom_parser }, ++ [ATOM_UPSTREAM] = { "upstream", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser }, ++ [ATOM_PUSH] = { "push", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser }, ++ [ATOM_SYMREF] = { "symref", SOURCE_NONE, FIELD_STR, refname_atom_parser }, ++ [ATOM_FLAG] = { "flag", SOURCE_NONE }, ++ [ATOM_HEAD] = { "HEAD", SOURCE_NONE, FIELD_STR, head_atom_parser }, ++ [ATOM_COLOR] = { "color", SOURCE_NONE, FIELD_STR, color_atom_parser }, ++ [ATOM_WORKTREEPATH] = { "worktreepath", SOURCE_NONE }, ++ [ATOM_ALIGN] = { "align", SOURCE_NONE, FIELD_STR, align_atom_parser }, ++ [ATOM_END] = { "end", SOURCE_NONE }, ++ [ATOM_IF] = { "if", SOURCE_NONE, FIELD_STR, if_atom_parser }, ++ [ATOM_THEN] = { "then", SOURCE_NONE }, ++ [ATOM_ELSE] = { "else", SOURCE_NONE }, /* * Please update $__git_ref_fieldlist in git-completion.bash * when you add new atoms +@@ ref-filter.c: static int parse_ref_filter_atom(const struct ref_format *format, + atom_len = (arg ? arg : ep) - sp; + + /* Is the atom a valid one? */ +- for (i = 0; i < ARRAY_SIZE(valid_atom); i++) { ++ for (i = ATOM_UNKNOWN + 1; i < ATOM_INVALID; i++) { + int len = strlen(valid_atom[i].name); + if (len == atom_len && !memcmp(valid_atom[i].name, sp, len)) + break; + } + +- if (ARRAY_SIZE(valid_atom) <= i) ++ if (i == ATOM_INVALID) + return strbuf_addf_ret(err, -1, _("unknown field name: %.*s"), + (int)(ep-atom), atom); + if (valid_atom[i].source != SOURCE_NONE && !have_git_dir()) @@ ref-filter.c: static int parse_ref_filter_atom(const struct ref_format *format, at = used_atom_cnt; used_atom_cnt++; REALLOC_ARRAY(used_atom, used_atom_cnt); -+ used_atom[at].atom_type = valid_atom[i].atom_type; ++ used_atom[at].atom_type = i; used_atom[at].name = xmemdupz(atom, ep - atom); used_atom[at].type = valid_atom[i].cmp_type; used_atom[at].source = valid_atom[i].source; @@ ref-filter.c: static int parse_ref_filter_atom(const struct ref_format *format, if (*atom == '*') need_tagged = 1; - if (!strcmp(valid_atom[i].name, "symref")) -+ if (valid_atom[i].atom_type == ATOM_SYMREF) ++ if (i == ATOM_SYMREF) need_symref = 1; return at; } -- gitgitgadget
