diff options
| -rw-r--r-- | list-objects-filter-options.c | 106 | ||||
| -rw-r--r-- | list-objects-filter-options.h | 17 | ||||
| -rw-r--r-- | list-objects-filter.c | 161 | ||||
| -rw-r--r-- | list-objects-filter.h | 13 | ||||
| -rwxr-xr-x | t/t6112-rev-list-filters-objects.sh | 151 | ||||
| -rw-r--r-- | url.c | 6 | ||||
| -rw-r--r-- | url.h | 8 |
7 files changed, 454 insertions, 8 deletions
diff --git a/list-objects-filter-options.c b/list-objects-filter-options.c index 7c3e397d29..75d0236ee2 100644 --- a/list-objects-filter-options.c +++ b/list-objects-filter-options.c @@ -6,6 +6,12 @@ #include "list-objects.h" #include "list-objects-filter.h" #include "list-objects-filter-options.h" +#include "url.h" + +static int parse_combine_filter( + struct list_objects_filter_options *filter_options, + const char *arg, + struct strbuf *errbuf); /* * Parse value of the argument to the "filter" keyword. @@ -35,8 +41,6 @@ static int gently_parse_list_objects_filter( return 1; } - filter_options->filter_spec = strdup(arg); - if (!strcmp(arg, "blob:none")) { filter_options->choice = LOFC_BLOB_NONE; return 0; @@ -77,6 +81,10 @@ static int gently_parse_list_objects_filter( _("sparse:path filters support has been dropped")); } return 1; + + } else if (skip_prefix(arg, "combine:", &v0)) { + return parse_combine_filter(filter_options, v0, errbuf); + } /* * Please update _git_fetch() in git-completion.bash when you @@ -89,10 +97,95 @@ static int gently_parse_list_objects_filter( return 1; } +static const char *RESERVED_NON_WS = "~`!@#$^&*()[]{}\\;'\",<>?"; + +static int has_reserved_character( + struct strbuf *sub_spec, struct strbuf *errbuf) +{ + const char *c = sub_spec->buf; + while (*c) { + if (*c <= ' ' || strchr(RESERVED_NON_WS, *c)) { + strbuf_addf( + errbuf, + _("must escape char in sub-filter-spec: '%c'"), + *c); + return 1; + } + c++; + } + + return 0; +} + +static int parse_combine_subfilter( + struct list_objects_filter_options *filter_options, + struct strbuf *subspec, + struct strbuf *errbuf) +{ + size_t new_index = filter_options->sub_nr++; + char *decoded; + int result; + + ALLOC_GROW(filter_options->sub, filter_options->sub_nr, + filter_options->sub_alloc); + memset(&filter_options->sub[new_index], 0, + sizeof(*filter_options->sub)); + + decoded = url_percent_decode(subspec->buf); + + result = has_reserved_character(subspec, errbuf) || + gently_parse_list_objects_filter( + &filter_options->sub[new_index], decoded, errbuf); + + free(decoded); + return result; +} + +static int parse_combine_filter( + struct list_objects_filter_options *filter_options, + const char *arg, + struct strbuf *errbuf) +{ + struct strbuf **subspecs = strbuf_split_str(arg, '+', 0); + size_t sub; + int result = 0; + + if (!subspecs[0]) { + strbuf_addstr(errbuf, _("expected something after combine:")); + result = 1; + goto cleanup; + } + + for (sub = 0; subspecs[sub] && !result; sub++) { + if (subspecs[sub + 1]) { + /* + * This is not the last subspec. Remove trailing "+" so + * we can parse it. + */ + size_t last = subspecs[sub]->len - 1; + assert(subspecs[sub]->buf[last] == '+'); + strbuf_remove(subspecs[sub], last, 1); + } + result = parse_combine_subfilter( + filter_options, subspecs[sub], errbuf); + } + + filter_options->choice = LOFC_COMBINE; + +cleanup: + strbuf_list_free(subspecs); + if (result) { + list_objects_filter_release(filter_options); + memset(filter_options, 0, sizeof(*filter_options)); + } + return result; +} + int parse_list_objects_filter(struct list_objects_filter_options *filter_options, const char *arg) { struct strbuf buf = STRBUF_INIT; + filter_options->filter_spec = strdup(arg); if (gently_parse_list_objects_filter(filter_options, arg, &buf)) die("%s", buf.buf); return 0; @@ -129,8 +222,15 @@ void expand_list_objects_filter_spec( void list_objects_filter_release( struct list_objects_filter_options *filter_options) { + size_t sub; + + if (!filter_options) + return; free(filter_options->filter_spec); free(filter_options->sparse_oid_value); + for (sub = 0; sub < filter_options->sub_nr; sub++) + list_objects_filter_release(&filter_options->sub[sub]); + free(filter_options->sub); memset(filter_options, 0, sizeof(*filter_options)); } @@ -174,6 +274,8 @@ void partial_clone_get_default_filter_spec( */ if (!core_partial_clone_filter_default) return; + + filter_options->filter_spec = strdup(core_partial_clone_filter_default); gently_parse_list_objects_filter(filter_options, core_partial_clone_filter_default, &errbuf); diff --git a/list-objects-filter-options.h b/list-objects-filter-options.h index c54f0000fb..789faef1e5 100644 --- a/list-objects-filter-options.h +++ b/list-objects-filter-options.h @@ -13,6 +13,7 @@ enum list_objects_filter_choice { LOFC_BLOB_LIMIT, LOFC_TREE_DEPTH, LOFC_SPARSE_OID, + LOFC_COMBINE, LOFC__COUNT /* must be last */ }; @@ -38,13 +39,23 @@ struct list_objects_filter_options { unsigned int no_filter : 1; /* - * Parsed values (fields) from within the filter-spec. These are - * choice-specific; not all values will be defined for any given - * choice. + * BEGIN choice-specific parsed values from within the filter-spec. Only + * some values will be defined for any given choice. */ + struct object_id *sparse_oid_value; unsigned long blob_limit_value; unsigned long tree_exclude_depth; + + /* LOFC_COMBINE values */ + + /* This array contains all the subfilters which this filter combines. */ + size_t sub_nr, sub_alloc; + struct list_objects_filter_options *sub; + + /* + * END choice-specific parsed values. + */ }; /* Normalized command line arguments */ diff --git a/list-objects-filter.c b/list-objects-filter.c index 3b4b6764ca..d664264d65 100644 --- a/list-objects-filter.c +++ b/list-objects-filter.c @@ -26,6 +26,14 @@ */ #define FILTER_SHOWN_BUT_REVISIT (1<<21) +struct subfilter { + struct filter *filter; + struct oidset seen; + struct oidset omits; + struct object_id skip_tree; + unsigned is_skipping_tree : 1; +}; + struct filter { enum list_objects_filter_result (*filter_object_fn)( struct repository *r, @@ -36,6 +44,23 @@ struct filter { struct oidset *omits, void *filter_data); + /* + * Optional. If this function is supplied and the filter needs + * to collect omits, then this function is called once before + * free_fn is called. + * + * This is required because the following two conditions hold: + * + * a. A tree filter can add and remove objects as an object + * graph is traversed. + * b. A combine filter's omit set is the union of all its + * subfilters, which may include tree: filters. + * + * As such, the omits sets must be separate sets, and can only + * be unioned after the traversal is completed. + */ + void (*finalize_omits_fn)(struct oidset *omits, void *filter_data); + void (*free_fn)(void *filter_data); void *filter_data; @@ -471,6 +496,139 @@ static void filter_sparse_oid__init( filter->free_fn = filter_sparse_free; } +/* A filter which only shows objects shown by all sub-filters. */ +struct combine_filter_data { + struct subfilter *sub; + size_t nr; +}; + +static enum list_objects_filter_result process_subfilter( + struct repository *r, + enum list_objects_filter_situation filter_situation, + struct object *obj, + const char *pathname, + const char *filename, + struct subfilter *sub) +{ + enum list_objects_filter_result result; + + /* + * Check and update is_skipping_tree before oidset_contains so + * that is_skipping_tree gets unset even when the object is + * marked as seen. As of this writing, no filter uses + * LOFR_MARK_SEEN on trees that also uses LOFR_SKIP_TREE, so the + * ordering is only theoretically important. Be cautious if you + * change the order of the below checks and more filters have + * been added! + */ + if (sub->is_skipping_tree) { + if (filter_situation == LOFS_END_TREE && + oideq(&obj->oid, &sub->skip_tree)) + sub->is_skipping_tree = 0; + else + return LOFR_ZERO; + } + if (oidset_contains(&sub->seen, &obj->oid)) + return LOFR_ZERO; + + result = list_objects_filter__filter_object( + r, filter_situation, obj, pathname, filename, sub->filter); + + if (result & LOFR_MARK_SEEN) + oidset_insert(&sub->seen, &obj->oid); + + if (result & LOFR_SKIP_TREE) { + sub->is_skipping_tree = 1; + sub->skip_tree = obj->oid; + } + + return result; +} + +static enum list_objects_filter_result filter_combine( + struct repository *r, + enum list_objects_filter_situation filter_situation, + struct object *obj, + const char *pathname, + const char *filename, + struct oidset *omits, + void *filter_data) +{ + struct combine_filter_data *d = filter_data; + enum list_objects_filter_result combined_result = + LOFR_DO_SHOW | LOFR_MARK_SEEN | LOFR_SKIP_TREE; + size_t sub; + + for (sub = 0; sub < d->nr; sub++) { + enum list_objects_filter_result sub_result = process_subfilter( + r, filter_situation, obj, pathname, filename, + &d->sub[sub]); + if (!(sub_result & LOFR_DO_SHOW)) + combined_result &= ~LOFR_DO_SHOW; + if (!(sub_result & LOFR_MARK_SEEN)) + combined_result &= ~LOFR_MARK_SEEN; + if (!d->sub[sub].is_skipping_tree) + combined_result &= ~LOFR_SKIP_TREE; + } + + return combined_result; +} + +static void filter_combine__free(void *filter_data) +{ + struct combine_filter_data *d = filter_data; + size_t sub; + for (sub = 0; sub < d->nr; sub++) { + list_objects_filter__free(d->sub[sub].filter); + oidset_clear(&d->sub[sub].seen); + if (d->sub[sub].omits.set.size) + BUG("expected oidset to be cleared already"); + } + free(d->sub); +} + +static void add_all(struct oidset *dest, struct oidset *src) { + struct oidset_iter iter; + struct object_id *src_oid; + + oidset_iter_init(src, &iter); + while ((src_oid = oidset_iter_next(&iter)) != NULL) + oidset_insert(dest, src_oid); +} + +static void filter_combine__finalize_omits( + struct oidset *omits, + void *filter_data) +{ + struct combine_filter_data *d = filter_data; + size_t sub; + + for (sub = 0; sub < d->nr; sub++) { + add_all(omits, &d->sub[sub].omits); + oidset_clear(&d->sub[sub].omits); + } +} + +static void filter_combine__init( + struct list_objects_filter_options *filter_options, + struct filter* filter) +{ + struct combine_filter_data *d = xcalloc(1, sizeof(*d)); + size_t sub; + + d->nr = filter_options->sub_nr; + d->sub = xcalloc(d->nr, sizeof(*d->sub)); + for (sub = 0; sub < d->nr; sub++) + d->sub[sub].filter = list_objects_filter__init( + filter->omits ? &d->sub[sub].omits : NULL, + &filter_options->sub[sub]); + + filter->filter_data = d; + filter->filter_object_fn = filter_combine; + filter->free_fn = filter_combine__free; + filter->finalize_omits_fn = filter_combine__finalize_omits; +} + typedef void (*filter_init_fn)( struct list_objects_filter_options *filter_options, struct filter *filter); @@ -484,6 +642,7 @@ static filter_init_fn s_filters[] = { filter_blobs_limit__init, filter_trees_depth__init, filter_sparse_oid__init, + filter_combine__init, }; struct filter *list_objects_filter__init( @@ -536,6 +695,8 @@ void list_objects_filter__free(struct filter *filter) { if (!filter) return; + if (filter->finalize_omits_fn && filter->omits) + filter->finalize_omits_fn(filter->omits, filter->filter_data); filter->free_fn(filter->filter_data); free(filter); } diff --git a/list-objects-filter.h b/list-objects-filter.h index 6908954266..cfd784e203 100644 --- a/list-objects-filter.h +++ b/list-objects-filter.h @@ -62,7 +62,13 @@ enum list_objects_filter_situation { struct filter; -/* Constructor for the set of defined list-objects filters. */ +/* + * Constructor for the set of defined list-objects filters. + * The `omitted` set is optional. It is populated with objects that the + * filter excludes. This set should not be considered finalized until + * after list_objects_filter__free is called on the returned `struct + * filter *`. + */ struct filter *list_objects_filter__init( struct oidset *omitted, struct list_objects_filter_options *filter_options); @@ -80,7 +86,10 @@ enum list_objects_filter_result list_objects_filter__filter_object( const char *filename, struct filter *filter); -/* Destroys `filter`. Does nothing if `filter` is null. */ +/* + * Destroys `filter` and finalizes the `omitted` set, if present. Does + * nothing if `filter` is null. + */ void list_objects_filter__free(struct filter *filter); #endif /* LIST_OBJECTS_FILTER_H */ diff --git a/t/t6112-rev-list-filters-objects.sh b/t/t6112-rev-list-filters-objects.sh index acd7f5ab80..05d4f2e9c2 100755 --- a/t/t6112-rev-list-filters-objects.sh +++ b/t/t6112-rev-list-filters-objects.sh @@ -278,7 +278,19 @@ test_expect_success 'verify skipping tree iteration when not collecting omits' ' test_line_count = 2 actual && # Make sure no other trees were considered besides the root. - ! grep "Skipping contents of tree [^.]" filter_trace + ! grep "Skipping contents of tree [^.]" filter_trace && + + # Try this again with "combine:". If both sub-filters are skipping + # trees, the composite filter should also skip trees. This is not + # important unless the user does combine:tree:X+tree:Y or another filter + # besides "tree:" is implemented in the future which can skip trees. + GIT_TRACE=1 git -C r3 rev-list \ + --objects --filter=combine:tree:1+tree:3 HEAD 2>filter_trace && + + # Only skip the dir1/ tree, which is shared between the two commits. + grep "Skipping contents of tree " filter_trace >actual && + test_write_lines "Skipping contents of tree dir1/..." >expected && + test_cmp expected actual ' # Test tree:# filters. @@ -330,6 +342,112 @@ test_expect_success 'verify tree:3 includes everything expected' ' test_line_count = 10 actual ' +test_expect_success 'combine:... for a simple combination' ' + git -C r3 rev-list --objects --filter=combine:tree:2+blob:none HEAD \ + >actual && + + expect_has HEAD "" && + expect_has HEAD~1 "" && + expect_has HEAD dir1 && + + # There are also 2 commit objects + test_line_count = 5 actual +' + +test_expect_success 'combine:... with URL encoding' ' + git -C r3 rev-list --objects \ + --filter=combine:tree%3a2+blob:%6Eon%65 HEAD >actual && + + expect_has HEAD "" && + expect_has HEAD~1 "" && + expect_has HEAD dir1 && + + # There are also 2 commit objects + test_line_count = 5 actual +' + +expect_invalid_filter_spec () { + spec="$1" && + err="$2" && + + test_must_fail git -C r3 rev-list --objects --filter="$spec" HEAD \ + >actual 2>actual_stderr && + test_must_be_empty actual && + test_i18ngrep "$err" actual_stderr +} + +test_expect_success 'combine:... while URL-encoding things that should not be' ' + expect_invalid_filter_spec combine%3Atree:2+blob:none \ + "invalid filter-spec" +' + +test_expect_success 'combine: with nothing after the :' ' + expect_invalid_filter_spec combine: "expected something after combine:" +' + +test_expect_success 'parse error in first sub-filter in combine:' ' + expect_invalid_filter_spec combine:tree:asdf+blob:none \ + "expected .tree:<depth>." +' + +test_expect_success 'combine:... with non-encoded reserved chars' ' + expect_invalid_filter_spec combine:tree:2+sparse:@xyz \ + "must escape char in sub-filter-spec: .@." && + expect_invalid_filter_spec combine:tree:2+sparse:\` \ + "must escape char in sub-filter-spec: .\`." && + expect_invalid_filter_spec combine:tree:2+sparse:~abc \ + "must escape char in sub-filter-spec: .\~." +' + +test_expect_success 'validate err msg for "combine:<valid-filter>+"' ' + expect_invalid_filter_spec combine:tree:2+ "expected .tree:<depth>." +' + +test_expect_success 'combine:... with edge-case hex digits: Ff Aa 0 9' ' + git -C r3 rev-list --objects --filter="combine:tree:2+bl%6Fb:n%6fne" \ + HEAD >actual && + test_line_count = 5 actual && + git -C r3 rev-list --objects --filter="combine:tree%3A2+blob%3anone" \ + HEAD >actual && + test_line_count = 5 actual && + git -C r3 rev-list --objects --filter="combine:tree:%30" HEAD >actual && + test_line_count = 2 actual && + git -C r3 rev-list --objects --filter="combine:tree:%39+blob:none" \ + HEAD >actual && + test_line_count = 5 actual +' + +test_expect_success 'add a sparse pattern blob whose path has reserved chars' ' + cp r3/pattern r3/pattern1+renamed% && + git -C r3 add pattern1+renamed% && + git -C r3 commit -m "add sparse pattern file with reserved chars" +' + +test_expect_success 'combine:... with more than two sub-filters' ' + git -C r3 rev-list --objects \ + --filter=combine:tree:3+blob:limit=40+sparse:oid=master:pattern \ + HEAD >actual && + + expect_has HEAD "" && + expect_has HEAD~1 "" && + expect_has HEAD~2 "" && + expect_has HEAD dir1 && + expect_has HEAD dir1/sparse1 && + expect_has HEAD dir1/sparse2 && + + # Should also have 3 commits + test_line_count = 9 actual && + + # Try again, this time making sure the last sub-filter is only + # URL-decoded once. + cp actual expect && + + git -C r3 rev-list --objects \ + --filter=combine:tree:3+blob:limit=40+sparse:oid=master:pattern1%2brenamed%25 \ + HEAD >actual && + test_cmp expect actual +' + # Test provisional omit collection logic with a repo that has objects appearing # at multiple depths - first deeper than the filter's threshold, then shallow. @@ -373,6 +491,37 @@ test_expect_success 'verify skipping tree iteration when collecting omits' ' test_cmp expect actual ' +test_expect_success 'setup r5' ' + git init r5 && + mkdir -p r5/subdir && + + echo 1 >r5/short-root && + echo 12345 >r5/long-root && + echo a >r5/subdir/short-subdir && + echo abcde >r5/subdir/long-subdir && + + git -C r5 add short-root long-root subdir && + git -C r5 commit -m "commit msg" +' + +test_expect_success 'verify collecting omits in combined: filter' ' + # Note that this test guards against the naive implementation of simply + # giving both filters the same "omits" set and expecting it to + # automatically merge them. + git -C r5 rev-list --objects --quiet --filter-print-omitted \ + --filter=combine:tree:2+blob:limit=3 HEAD >actual && + + # Expect 0 trees/commits, 3 blobs omitted (all blobs except short-root) + omitted_1=$(echo 12345 | git hash-object --stdin) && + omitted_2=$(echo a | git hash-object --stdin) && + omitted_3=$(echo abcde | git hash-object --stdin) && + + grep ~$omitted_1 actual && + grep ~$omitted_2 actual && + grep ~$omitted_3 actual && + test_line_count = 3 actual +' + # Test tree:<depth> where a tree is iterated to twice - once where a subentry is # too deep to be included, and again where the blob inside it is shallow enough # to be included. This makes sure we don't use LOFR_MARK_SEEN incorrectly (we @@ -86,6 +86,12 @@ char *url_decode_mem(const char *url, int len) return url_decode_internal(&url, len, NULL, &out, 0); } +char *url_percent_decode(const char *encoded) +{ + struct strbuf out = STRBUF_INIT; + return url_decode_internal(&encoded, strlen(encoded), NULL, &out, 0); +} + char *url_decode_parameter_name(const char **query) { struct strbuf out = STRBUF_INIT; @@ -7,6 +7,14 @@ int is_url(const char *url); int is_urlschemechar(int first_flag, int ch); char *url_decode(const char *url); char *url_decode_mem(const char *url, int len); + +/* + * Similar to the url_decode_{,mem} methods above, but doesn't assume there + * is a scheme followed by a : at the start of the string. Instead, %-sequences + * before any : are also parsed. + */ +char *url_percent_decode(const char *encoded); + char *url_decode_parameter_name(const char **query); char *url_decode_parameter_value(const char **query); |