diff options
author | Junio C Hamano <gitster@pobox.com> | 2017-08-11 13:27:00 -0700 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2017-08-11 13:27:00 -0700 |
commit | 51b8aecabed1363f13c990320a50e1fb2aa3f696 (patch) | |
tree | 989a4699cd5d3e9a8a645ac67092e66ba62094d7 | |
parent | Merge branch 'st/lib-gpg-kill-stray-agent' (diff) | |
parent | convert: add "status=delayed" to filter process protocol (diff) | |
download | tgif-51b8aecabed1363f13c990320a50e1fb2aa3f696.tar.xz |
Merge branch 'ls/filter-process-delayed'
The filter-process interface learned to allow a process with long
latency give a "delayed" response.
* ls/filter-process-delayed:
convert: add "status=delayed" to filter process protocol
convert: refactor capabilities negotiation
convert: move multiple file filter error handling to separate function
convert: put the flags field before the flag itself for consistent style
t0021: write "OUT <size>" only on success
t0021: make debug log file name configurable
t0021: keep filter log files on comparison
-rw-r--r-- | Documentation/gitattributes.txt | 69 | ||||
-rw-r--r-- | builtin/checkout.c | 3 | ||||
-rw-r--r-- | cache.h | 3 | ||||
-rw-r--r-- | convert.c | 202 | ||||
-rw-r--r-- | convert.h | 26 | ||||
-rw-r--r-- | entry.c | 132 | ||||
-rwxr-xr-x | t/t0021-conversion.sh | 178 | ||||
-rw-r--r-- | t/t0021/rot13-filter.pl | 214 | ||||
-rw-r--r-- | unpack-trees.c | 2 |
9 files changed, 668 insertions, 161 deletions
diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt index 2a2d7e2a4d..c4f2be2542 100644 --- a/Documentation/gitattributes.txt +++ b/Documentation/gitattributes.txt @@ -425,8 +425,8 @@ packet: git< capability=clean packet: git< capability=smudge packet: git< 0000 ------------------------ -Supported filter capabilities in version 2 are "clean" and -"smudge". +Supported filter capabilities in version 2 are "clean", "smudge", +and "delay". Afterwards Git sends a list of "key=value" pairs terminated with a flush packet. The list will contain at least the filter command @@ -512,12 +512,73 @@ the protocol then Git will stop the filter process and restart it with the next file that needs to be processed. Depending on the `filter.<driver>.required` flag Git will interpret that as error. -After the filter has processed a blob it is expected to wait for -the next "key=value" list containing a command. Git will close +After the filter has processed a command it is expected to wait for +a "key=value" list containing the next command. Git will close the command pipe on exit. The filter is expected to detect EOF and exit gracefully on its own. Git will wait until the filter process has stopped. +Delay +^^^^^ + +If the filter supports the "delay" capability, then Git can send the +flag "can-delay" after the filter command and pathname. This flag +denotes that the filter can delay filtering the current blob (e.g. to +compensate network latencies) by responding with no content but with +the status "delayed" and a flush packet. +------------------------ +packet: git> command=smudge +packet: git> pathname=path/testfile.dat +packet: git> can-delay=1 +packet: git> 0000 +packet: git> CONTENT +packet: git> 0000 +packet: git< status=delayed +packet: git< 0000 +------------------------ + +If the filter supports the "delay" capability then it must support the +"list_available_blobs" command. If Git sends this command, then the +filter is expected to return a list of pathnames representing blobs +that have been delayed earlier and are now available. +The list must be terminated with a flush packet followed +by a "success" status that is also terminated with a flush packet. If +no blobs for the delayed paths are available, yet, then the filter is +expected to block the response until at least one blob becomes +available. The filter can tell Git that it has no more delayed blobs +by sending an empty list. As soon as the filter responds with an empty +list, Git stops asking. All blobs that Git has not received at this +point are considered missing and will result in an error. + +------------------------ +packet: git> command=list_available_blobs +packet: git> 0000 +packet: git< pathname=path/testfile.dat +packet: git< pathname=path/otherfile.dat +packet: git< 0000 +packet: git< status=success +packet: git< 0000 +------------------------ + +After Git received the pathnames, it will request the corresponding +blobs again. These requests contain a pathname and an empty content +section. The filter is expected to respond with the smudged content +in the usual way as explained above. +------------------------ +packet: git> command=smudge +packet: git> pathname=path/testfile.dat +packet: git> 0000 +packet: git> 0000 # empty content! +packet: git< status=success +packet: git< 0000 +packet: git< SMUDGED_CONTENT +packet: git< 0000 +packet: git< 0000 # empty list, keep "status=success" unchanged! +------------------------ + +Example +^^^^^^^ + A long running filter demo implementation can be found in `contrib/long-running-filter/example.pl` located in the Git core repository. If you develop your own long running filter diff --git a/builtin/checkout.c b/builtin/checkout.c index 9661e1bcba..2d75ac66c7 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -358,6 +358,8 @@ static int checkout_paths(const struct checkout_opts *opts, state.force = 1; state.refresh_cache = 1; state.istate = &the_index; + + enable_delayed_checkout(&state); for (pos = 0; pos < active_nr; pos++) { struct cache_entry *ce = active_cache[pos]; if (ce->ce_flags & CE_MATCHED) { @@ -372,6 +374,7 @@ static int checkout_paths(const struct checkout_opts *opts, pos = skip_same_name(ce, pos) - 1; } } + errs |= finish_delayed_checkout(&state); if (write_locked_index(&the_index, lock_file, COMMIT_LOCK)) die(_("unable to write new index file")); @@ -1499,6 +1499,7 @@ struct checkout { struct index_state *istate; const char *base_dir; int base_dir_len; + struct delayed_checkout *delayed_checkout; unsigned force:1, quiet:1, not_new:1, @@ -1508,6 +1509,8 @@ struct checkout { #define TEMPORARY_FILENAME_LENGTH 25 extern int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath); +extern void enable_delayed_checkout(struct checkout *state); +extern int finish_delayed_checkout(struct checkout *state); struct cache_def { struct strbuf path; @@ -501,6 +501,7 @@ static int apply_single_file_filter(const char *path, const char *src, size_t le #define CAP_CLEAN (1u<<0) #define CAP_SMUDGE (1u<<1) +#define CAP_DELAY (1u<<2) struct cmd2process { struct subprocess_entry subprocess; /* must be the first member! */ @@ -512,7 +513,7 @@ static struct hashmap subprocess_map; static int start_multi_file_filter_fn(struct subprocess_entry *subprocess) { - int err; + int err, i; struct cmd2process *entry = (struct cmd2process *)subprocess; struct string_list cap_list = STRING_LIST_INIT_NODUP; char *cap_buf; @@ -520,6 +521,15 @@ static int start_multi_file_filter_fn(struct subprocess_entry *subprocess) struct child_process *process = &subprocess->process; const char *cmd = subprocess->cmd; + static const struct { + const char *name; + unsigned int cap; + } known_caps[] = { + { "clean", CAP_CLEAN }, + { "smudge", CAP_SMUDGE }, + { "delay", CAP_DELAY }, + }; + sigchain_push(SIGPIPE, SIG_IGN); err = packet_writel(process->in, "git-filter-client", "version=2", NULL); @@ -538,7 +548,15 @@ static int start_multi_file_filter_fn(struct subprocess_entry *subprocess) if (err) goto done; - err = packet_writel(process->in, "capability=clean", "capability=smudge", NULL); + for (i = 0; i < ARRAY_SIZE(known_caps); ++i) { + err = packet_write_fmt_gently( + process->in, "capability=%s\n", known_caps[i].name); + if (err) + goto done; + } + err = packet_flush_gently(process->in); + if (err) + goto done; for (;;) { cap_buf = packet_read_line(process->out, NULL); @@ -550,16 +568,15 @@ static int start_multi_file_filter_fn(struct subprocess_entry *subprocess) continue; cap_name = cap_list.items[1].string; - if (!strcmp(cap_name, "clean")) { - entry->supported_capabilities |= CAP_CLEAN; - } else if (!strcmp(cap_name, "smudge")) { - entry->supported_capabilities |= CAP_SMUDGE; - } else { - warning( - "external filter '%s' requested unsupported filter capability '%s'", - cmd, cap_name - ); - } + i = ARRAY_SIZE(known_caps) - 1; + while (i >= 0 && strcmp(cap_name, known_caps[i].name)) + i--; + + if (i >= 0) + entry->supported_capabilities |= known_caps[i].cap; + else + warning("external filter '%s' requested unsupported filter capability '%s'", + cmd, cap_name); string_list_clear(&cap_list, 0); } @@ -570,11 +587,36 @@ done: return err; } +static void handle_filter_error(const struct strbuf *filter_status, + struct cmd2process *entry, + const unsigned int wanted_capability) { + if (!strcmp(filter_status->buf, "error")) + ; /* The filter signaled a problem with the file. */ + else if (!strcmp(filter_status->buf, "abort") && wanted_capability) { + /* + * The filter signaled a permanent problem. Don't try to filter + * files with the same command for the lifetime of the current + * Git process. + */ + entry->supported_capabilities &= ~wanted_capability; + } else { + /* + * Something went wrong with the protocol filter. + * Force shutdown and restart if another blob requires filtering. + */ + error("external filter '%s' failed", entry->subprocess.cmd); + subprocess_stop(&subprocess_map, &entry->subprocess); + free(entry); + } +} + static int apply_multi_file_filter(const char *path, const char *src, size_t len, int fd, struct strbuf *dst, const char *cmd, - const unsigned int wanted_capability) + const unsigned int wanted_capability, + struct delayed_checkout *dco) { int err; + int can_delay = 0; struct cmd2process *entry; struct child_process *process; struct strbuf nbuf = STRBUF_INIT; @@ -603,12 +645,12 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len } process = &entry->subprocess.process; - if (!(wanted_capability & entry->supported_capabilities)) + if (!(entry->supported_capabilities & wanted_capability)) return 0; - if (CAP_CLEAN & wanted_capability) + if (wanted_capability & CAP_CLEAN) filter_type = "clean"; - else if (CAP_SMUDGE & wanted_capability) + else if (wanted_capability & CAP_SMUDGE) filter_type = "smudge"; else die("unexpected filter type"); @@ -630,6 +672,14 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len if (err) goto done; + if ((entry->supported_capabilities & CAP_DELAY) && + dco && dco->state == CE_CAN_DELAY) { + can_delay = 1; + err = packet_write_fmt_gently(process->in, "can-delay=1\n"); + if (err) + goto done; + } + err = packet_flush_gently(process->in); if (err) goto done; @@ -645,14 +695,73 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len if (err) goto done; - err = strcmp(filter_status.buf, "success"); + if (can_delay && !strcmp(filter_status.buf, "delayed")) { + string_list_insert(&dco->filters, cmd); + string_list_insert(&dco->paths, path); + } else { + /* The filter got the blob and wants to send us a response. */ + err = strcmp(filter_status.buf, "success"); + if (err) + goto done; + + err = read_packetized_to_strbuf(process->out, &nbuf) < 0; + if (err) + goto done; + + err = subprocess_read_status(process->out, &filter_status); + if (err) + goto done; + + err = strcmp(filter_status.buf, "success"); + } + +done: + sigchain_pop(SIGPIPE); + + if (err) + handle_filter_error(&filter_status, entry, wanted_capability); + else + strbuf_swap(dst, &nbuf); + strbuf_release(&nbuf); + return !err; +} + + +int async_query_available_blobs(const char *cmd, struct string_list *available_paths) +{ + int err; + char *line; + struct cmd2process *entry; + struct child_process *process; + struct strbuf filter_status = STRBUF_INIT; + + assert(subprocess_map_initialized); + entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd); + if (!entry) { + error("external filter '%s' is not available anymore although " + "not all paths have been filtered", cmd); + return 0; + } + process = &entry->subprocess.process; + sigchain_push(SIGPIPE, SIG_IGN); + + err = packet_write_fmt_gently( + process->in, "command=list_available_blobs\n"); if (err) goto done; - err = read_packetized_to_strbuf(process->out, &nbuf) < 0; + err = packet_flush_gently(process->in); if (err) goto done; + while ((line = packet_read_line(process->out, NULL))) { + const char *path; + if (skip_prefix(line, "pathname=", &path)) + string_list_insert(available_paths, xstrdup(path)); + else + ; /* ignore unknown keys */ + } + err = subprocess_read_status(process->out, &filter_status); if (err) goto done; @@ -662,29 +771,8 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len done: sigchain_pop(SIGPIPE); - if (err) { - if (!strcmp(filter_status.buf, "error")) { - /* The filter signaled a problem with the file. */ - } else if (!strcmp(filter_status.buf, "abort")) { - /* - * The filter signaled a permanent problem. Don't try to filter - * files with the same command for the lifetime of the current - * Git process. - */ - entry->supported_capabilities &= ~wanted_capability; - } else { - /* - * Something went wrong with the protocol filter. - * Force shutdown and restart if another blob requires filtering. - */ - error("external filter '%s' failed", cmd); - subprocess_stop(&subprocess_map, &entry->subprocess); - free(entry); - } - } else { - strbuf_swap(dst, &nbuf); - } - strbuf_release(&nbuf); + if (err) + handle_filter_error(&filter_status, entry, 0); return !err; } @@ -699,7 +787,8 @@ static struct convert_driver { static int apply_filter(const char *path, const char *src, size_t len, int fd, struct strbuf *dst, struct convert_driver *drv, - const unsigned int wanted_capability) + const unsigned int wanted_capability, + struct delayed_checkout *dco) { const char *cmd = NULL; @@ -709,15 +798,16 @@ static int apply_filter(const char *path, const char *src, size_t len, if (!dst) return 1; - if ((CAP_CLEAN & wanted_capability) && !drv->process && drv->clean) + if ((wanted_capability & CAP_CLEAN) && !drv->process && drv->clean) cmd = drv->clean; - else if ((CAP_SMUDGE & wanted_capability) && !drv->process && drv->smudge) + else if ((wanted_capability & CAP_SMUDGE) && !drv->process && drv->smudge) cmd = drv->smudge; if (cmd && *cmd) return apply_single_file_filter(path, src, len, fd, dst, cmd); else if (drv->process && *drv->process) - return apply_multi_file_filter(path, src, len, fd, dst, drv->process, wanted_capability); + return apply_multi_file_filter(path, src, len, fd, dst, + drv->process, wanted_capability, dco); return 0; } @@ -1058,7 +1148,7 @@ int would_convert_to_git_filter_fd(const char *path) if (!ca.drv->required) return 0; - return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN); + return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN, NULL); } const char *get_convert_attr_ascii(const char *path) @@ -1096,7 +1186,7 @@ int convert_to_git(const struct index_state *istate, convert_attrs(&ca, path); - ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN); + ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN, NULL); if (!ret && ca.drv && ca.drv->required) die("%s: clean filter '%s' failed", path, ca.drv->name); @@ -1122,7 +1212,7 @@ void convert_to_git_filter_fd(const struct index_state *istate, assert(ca.drv); assert(ca.drv->clean || ca.drv->process); - if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN)) + if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL)) die("%s: clean filter '%s' failed", path, ca.drv->name); crlf_to_git(istate, path, dst->buf, dst->len, dst, ca.crlf_action, checksafe); @@ -1131,7 +1221,7 @@ void convert_to_git_filter_fd(const struct index_state *istate, static int convert_to_working_tree_internal(const char *path, const char *src, size_t len, struct strbuf *dst, - int normalizing) + int normalizing, struct delayed_checkout *dco) { int ret = 0, ret_filter = 0; struct conv_attrs ca; @@ -1156,22 +1246,30 @@ static int convert_to_working_tree_internal(const char *path, const char *src, } } - ret_filter = apply_filter(path, src, len, -1, dst, ca.drv, CAP_SMUDGE); + ret_filter = apply_filter( + path, src, len, -1, dst, ca.drv, CAP_SMUDGE, dco); if (!ret_filter && ca.drv && ca.drv->required) die("%s: smudge filter %s failed", path, ca.drv->name); return ret | ret_filter; } +int async_convert_to_working_tree(const char *path, const char *src, + size_t len, struct strbuf *dst, + void *dco) +{ + return convert_to_working_tree_internal(path, src, len, dst, 0, dco); +} + int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst) { - return convert_to_working_tree_internal(path, src, len, dst, 0); + return convert_to_working_tree_internal(path, src, len, dst, 0, NULL); } int renormalize_buffer(const struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst) { - int ret = convert_to_working_tree_internal(path, src, len, dst, 1); + int ret = convert_to_working_tree_internal(path, src, len, dst, 1, NULL); if (ret) { src = dst->buf; len = dst->len; @@ -4,6 +4,8 @@ #ifndef CONVERT_H #define CONVERT_H +#include "string-list.h" + struct index_state; enum safe_crlf { @@ -34,6 +36,26 @@ enum eol { #endif }; +enum ce_delay_state { + CE_NO_DELAY = 0, + CE_CAN_DELAY = 1, + CE_RETRY = 2 +}; + +struct delayed_checkout { + /* + * State of the currently processed cache entry. If the state is + * CE_CAN_DELAY, then the filter can delay the current cache entry. + * If the state is CE_RETRY, then this signals the filter that the + * cache entry was requested before. + */ + enum ce_delay_state state; + /* List of filter drivers that signaled delayed blobs. */ + struct string_list filters; + /* List of delayed blobs identified by their path. */ + struct string_list paths; +}; + extern enum eol core_eol; extern const char *get_cached_convert_stats_ascii(const struct index_state *istate, const char *path); @@ -46,6 +68,10 @@ extern int convert_to_git(const struct index_state *istate, struct strbuf *dst, enum safe_crlf checksafe); extern int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst); +extern int async_convert_to_working_tree(const char *path, const char *src, + size_t len, struct strbuf *dst, + void *dco); +extern int async_query_available_blobs(const char *cmd, struct string_list *available_paths); extern int renormalize_buffer(const struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst); @@ -137,6 +137,105 @@ static int streaming_write_entry(const struct cache_entry *ce, char *path, return result; } +void enable_delayed_checkout(struct checkout *state) +{ + if (!state->delayed_checkout) { + state->delayed_checkout = xmalloc(sizeof(*state->delayed_checkout)); + state->delayed_checkout->state = CE_CAN_DELAY; + string_list_init(&state->delayed_checkout->filters, 0); + string_list_init(&state->delayed_checkout->paths, 0); + } +} + +static int remove_available_paths(struct string_list_item *item, void *cb_data) +{ + struct string_list *available_paths = cb_data; + struct string_list_item *available; + + available = string_list_lookup(available_paths, item->string); + if (available) + available->util = (void *)item->string; + return !available; +} + +int finish_delayed_checkout(struct checkout *state) +{ + int errs = 0; + struct string_list_item *filter, *path; + struct delayed_checkout *dco = state->delayed_checkout; + + if (!state->delayed_checkout) + return errs; + + dco->state = CE_RETRY; + while (dco->filters.nr > 0) { + for_each_string_list_item(filter, &dco->filters) { + struct string_list available_paths = STRING_LIST_INIT_NODUP; + + if (!async_query_available_blobs(filter->string, &available_paths)) { + /* Filter reported an error */ + errs = 1; + filter->string = ""; + continue; + } + if (available_paths.nr <= 0) { + /* + * Filter responded with no entries. That means + * the filter is done and we can remove the + * filter from the list (see + * "string_list_remove_empty_items" call below). + */ + filter->string = ""; + continue; + } + + /* + * In dco->paths we store a list of all delayed paths. + * The filter just send us a list of available paths. + * Remove them from the list. + */ + filter_string_list(&dco->paths, 0, + &remove_available_paths, &available_paths); + + for_each_string_list_item(path, &available_paths) { + struct cache_entry* ce; + + if (!path->util) { + error("external filter '%s' signaled that '%s' " + "is now available although it has not been " + "delayed earlier", + filter->string, path->string); + errs |= 1; + + /* + * Do not ask the filter for available blobs, + * again, as the filter is likely buggy. + */ + filter->string = ""; + continue; + } + ce = index_file_exists(state->istate, path->string, + strlen(path->string), 0); + errs |= (ce ? checkout_entry(ce, state, NULL) : 1); + } + } + string_list_remove_empty_items(&dco->filters, 0); + } + string_list_clear(&dco->filters, 0); + + /* At this point we should not have any delayed paths anymore. */ + errs |= dco->paths.nr; + for_each_string_list_item(path, &dco->paths) { + error("'%s' was not filtered properly", path->string); + } + string_list_clear(&dco->paths, 0); + + free(dco); + state->delayed_checkout = NULL; + + return errs; +} + static int write_entry(struct cache_entry *ce, char *path, const struct checkout *state, int to_tempfile) { @@ -179,11 +278,34 @@ static int write_entry(struct cache_entry *ce, /* * Convert from git internal format to working tree format */ - if (ce_mode_s_ifmt == S_IFREG && - convert_to_working_tree(ce->name, new, size, &buf)) { - free(new); - new = strbuf_detach(&buf, &newsize); - size = newsize; + if (ce_mode_s_ifmt == S_IFREG) { + struct delayed_checkout *dco = state->delayed_checkout; + if (dco && dco->state != CE_NO_DELAY) { + /* Do not send the blob in case of a retry. */ + if (dco->state == CE_RETRY) { + new = NULL; + size = 0; + } + ret = async_convert_to_working_tree( + ce->name, new, size, &buf, dco); + if (ret && string_list_has_string(&dco->paths, ce->name)) { + free(new); + goto finish; + } + } else + ret = convert_to_working_tree( + ce->name, new, size, &buf); + + if (ret) { + free(new); + new = strbuf_detach(&buf, &newsize); + size = newsize; + } + /* + * No "else" here as errors from convert are OK at this + * point. If the error would have been fatal (e.g. + * filter is required), then we would have died already. + */ } fd = open_output_fd(path, ce, to_tempfile); diff --git a/t/t0021-conversion.sh b/t/t0021-conversion.sh index 161f560446..eb3d83744a 100755 --- a/t/t0021-conversion.sh +++ b/t/t0021-conversion.sh @@ -28,7 +28,7 @@ file_size () { } filter_git () { - rm -f rot13-filter.log && + rm -f *.log && git "$@" } @@ -42,10 +42,10 @@ test_cmp_count () { for FILE in "$expect" "$actual" do sort "$FILE" | uniq -c | - sed -e "s/^ *[0-9][0-9]*[ ]*IN: /x IN: /" >"$FILE.tmp" && - mv "$FILE.tmp" "$FILE" || return + sed -e "s/^ *[0-9][0-9]*[ ]*IN: /x IN: /" >"$FILE.tmp" done && - test_cmp "$expect" "$actual" + test_cmp "$expect.tmp" "$actual.tmp" && + rm "$expect.tmp" "$actual.tmp" } # Compare two files but exclude all `clean` invocations because Git can @@ -56,10 +56,10 @@ test_cmp_exclude_clean () { actual=$2 for FILE in "$expect" "$actual" do - grep -v "IN: clean" "$FILE" >"$FILE.tmp" && - mv "$FILE.tmp" "$FILE" + grep -v "IN: clean" "$FILE" >"$FILE.tmp" done && - test_cmp "$expect" "$actual" + test_cmp "$expect.tmp" "$actual.tmp" && + rm "$expect.tmp" "$actual.tmp" } # Check that the contents of two files are equal and that their rot13 version @@ -342,7 +342,7 @@ test_expect_success 'diff does not reuse worktree files that need cleaning' ' ' test_expect_success PERL 'required process filter should filter data' ' - test_config_global filter.protocol.process "rot13-filter.pl clean smudge" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean smudge" && test_config_global filter.protocol.required true && rm -rf repo && mkdir repo && @@ -375,7 +375,7 @@ test_expect_success PERL 'required process filter should filter data' ' IN: clean testsubdir/test3 '\''sq'\'',\$x=.r $S3 [OK] -- OUT: $S3 . [OK] STOP EOF - test_cmp_count expected.log rot13-filter.log && + test_cmp_count expected.log debug.log && git commit -m "test commit 2" && rm -f test2.r "testsubdir/test3 '\''sq'\'',\$x=.r" && @@ -388,7 +388,7 @@ test_expect_success PERL 'required process filter should filter data' ' IN: smudge testsubdir/test3 '\''sq'\'',\$x=.r $S3 [OK] -- OUT: $S3 . [OK] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && filter_git checkout --quiet --no-progress empty-branch && cat >expected.log <<-EOF && @@ -397,7 +397,7 @@ test_expect_success PERL 'required process filter should filter data' ' IN: clean test.r $S [OK] -- OUT: $S . [OK] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && filter_git checkout --quiet --no-progress master && cat >expected.log <<-EOF && @@ -409,7 +409,7 @@ test_expect_success PERL 'required process filter should filter data' ' IN: smudge testsubdir/test3 '\''sq'\'',\$x=.r $S3 [OK] -- OUT: $S3 . [OK] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.r && test_cmp_committed_rot13 "$TEST_ROOT/test2.o" test2.r && @@ -419,7 +419,7 @@ test_expect_success PERL 'required process filter should filter data' ' test_expect_success PERL 'required process filter takes precedence' ' test_config_global filter.protocol.clean false && - test_config_global filter.protocol.process "rot13-filter.pl clean" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean" && test_config_global filter.protocol.required true && rm -rf repo && mkdir repo && @@ -439,12 +439,12 @@ test_expect_success PERL 'required process filter takes precedence' ' IN: clean test.r $S [OK] -- OUT: $S . [OK] STOP EOF - test_cmp_count expected.log rot13-filter.log + test_cmp_count expected.log debug.log ) ' test_expect_success PERL 'required process filter should be used only for "clean" operation only' ' - test_config_global filter.protocol.process "rot13-filter.pl clean" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean" && rm -rf repo && mkdir repo && ( @@ -462,7 +462,7 @@ test_expect_success PERL 'required process filter should be used only for "clean IN: clean test.r $S [OK] -- OUT: $S . [OK] STOP EOF - test_cmp_count expected.log rot13-filter.log && + test_cmp_count expected.log debug.log && rm test.r && @@ -474,12 +474,12 @@ test_expect_success PERL 'required process filter should be used only for "clean init handshake complete STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log + test_cmp_exclude_clean expected.log debug.log ) ' test_expect_success PERL 'required process filter should process multiple packets' ' - test_config_global filter.protocol.process "rot13-filter.pl clean smudge" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean smudge" && test_config_global filter.protocol.required true && rm -rf repo && @@ -514,7 +514,7 @@ test_expect_success PERL 'required process filter should process multiple packet IN: clean 3pkt_2+1.file $(($S*2+1)) [OK] -- OUT: $(($S*2+1)) ... [OK] STOP EOF - test_cmp_count expected.log rot13-filter.log && + test_cmp_count expected.log debug.log && rm -f *.file && @@ -529,7 +529,7 @@ test_expect_success PERL 'required process filter should process multiple packet IN: smudge 3pkt_2+1.file $(($S*2+1)) [OK] -- OUT: $(($S*2+1)) ... [OK] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && for FILE in *.file do @@ -539,7 +539,7 @@ test_expect_success PERL 'required process filter should process multiple packet ' test_expect_success PERL 'required process filter with clean error should fail' ' - test_config_global filter.protocol.process "rot13-filter.pl clean smudge" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean smudge" && test_config_global filter.protocol.required true && rm -rf repo && mkdir repo && @@ -558,7 +558,7 @@ test_expect_success PERL 'required process filter with clean error should fail' ' test_expect_success PERL 'process filter should restart after unexpected write failure' ' - test_config_global filter.protocol.process "rot13-filter.pl clean smudge" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean smudge" && rm -rf repo && mkdir repo && ( @@ -579,7 +579,7 @@ test_expect_success PERL 'process filter should restart after unexpected write f git add . && rm -f *.r && - rm -f rot13-filter.log && + rm -f debug.log && git checkout --quiet --no-progress . 2>git-stderr.log && grep "smudge write error at" git-stderr.log && @@ -588,14 +588,14 @@ test_expect_success PERL 'process filter should restart after unexpected write f cat >expected.log <<-EOF && START init handshake complete - IN: smudge smudge-write-fail.r $SF [OK] -- OUT: $SF [WRITE FAIL] + IN: smudge smudge-write-fail.r $SF [OK] -- [WRITE FAIL] START init handshake complete IN: smudge test.r $S [OK] -- OUT: $S . [OK] IN: smudge test2.r $S2 [OK] -- OUT: $S2 . [OK] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.r && test_cmp_committed_rot13 "$TEST_ROOT/test2.o" test2.r && @@ -609,7 +609,7 @@ test_expect_success PERL 'process filter should restart after unexpected write f ' test_expect_success PERL 'process filter should not be restarted if it signals an error' ' - test_config_global filter.protocol.process "rot13-filter.pl clean smudge" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean smudge" && rm -rf repo && mkdir repo && ( @@ -634,12 +634,12 @@ test_expect_success PERL 'process filter should not be restarted if it signals a cat >expected.log <<-EOF && START init handshake complete - IN: smudge error.r $SE [OK] -- OUT: 0 [ERROR] + IN: smudge error.r $SE [OK] -- [ERROR] IN: smudge test.r $S [OK] -- OUT: $S . [OK] IN: smudge test2.r $S2 [OK] -- OUT: $S2 . [OK] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.r && test_cmp_committed_rot13 "$TEST_ROOT/test2.o" test2.r && @@ -648,7 +648,7 @@ test_expect_success PERL 'process filter should not be restarted if it signals a ' test_expect_success PERL 'process filter abort stops processing of all further files' ' - test_config_global filter.protocol.process "rot13-filter.pl clean smudge" && + test_config_global filter.protocol.process "rot13-filter.pl debug.log clean smudge" && rm -rf repo && mkdir repo && ( @@ -673,10 +673,10 @@ test_expect_success PERL 'process filter abort stops processing of all further f cat >expected.log <<-EOF && START init handshake complete - IN: smudge abort.r $SA [OK] -- OUT: 0 [ABORT] + IN: smudge abort.r $SA [OK] -- [ABORT] STOP EOF - test_cmp_exclude_clean expected.log rot13-filter.log && + test_cmp_exclude_clean expected.log debug.log && test_cmp "$TEST_ROOT/test.o" test.r && test_cmp "$TEST_ROOT/test2.o" test2.r && @@ -701,4 +701,120 @@ test_expect_success PERL 'invalid process filter must fail (and not hang!)' ' ) ' +test_expect_success PERL 'delayed checkout in process filter' ' + test_config_global filter.a.process "rot13-filter.pl a.log clean smudge delay" && + test_config_global filter.a.required true && + test_config_global filter.b.process "rot13-filter.pl b.log clean smudge delay" && + test_config_global filter.b.required true && + + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + echo "*.a filter=a" >.gitattributes && + echo "*.b filter=b" >>.gitattributes && + cp "$TEST_ROOT/test.o" test.a && + cp "$TEST_ROOT/test.o" test-delay10.a && + cp "$TEST_ROOT/test.o" test-delay11.a && + cp "$TEST_ROOT/test.o" test-delay20.a && + cp "$TEST_ROOT/test.o" test-delay10.b && + git add . && + git commit -m "test commit" + ) && + + S=$(file_size "$TEST_ROOT/test.o") && + cat >a.exp <<-EOF && + START + init handshake complete + IN: smudge test.a $S [OK] -- OUT: $S . [OK] + IN: smudge test-delay10.a $S [OK] -- [DELAYED] + IN: smudge test-delay11.a $S [OK] -- [DELAYED] + IN: smudge test-delay20.a $S [OK] -- [DELAYED] + IN: list_available_blobs test-delay10.a test-delay11.a [OK] + IN: smudge test-delay10.a 0 [OK] -- OUT: $S . [OK] + IN: smudge test-delay11.a 0 [OK] -- OUT: $S . [OK] + IN: list_available_blobs test-delay20.a [OK] + IN: smudge test-delay20.a 0 [OK] -- OUT: $S . [OK] + IN: list_available_blobs [OK] + STOP + EOF + cat >b.exp <<-EOF && + START + init handshake complete + IN: smudge test-delay10.b $S [OK] -- [DELAYED] + IN: list_available_blobs test-delay10.b [OK] + IN: smudge test-delay10.b 0 [OK] -- OUT: $S . [OK] + IN: list_available_blobs [OK] + STOP + EOF + + rm -rf repo-cloned && + filter_git clone repo repo-cloned && + test_cmp_count a.exp repo-cloned/a.log && + test_cmp_count b.exp repo-cloned/b.log && + + ( + cd repo-cloned && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay11.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay20.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.b && + + rm *.a *.b && + filter_git checkout . && + test_cmp_count ../a.exp a.log && + test_cmp_count ../b.exp b.log && + + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay11.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay20.a && + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.b + ) +' + +test_expect_success PERL 'missing file in delayed checkout' ' + test_config_global filter.bug.process "rot13-filter.pl bug.log clean smudge delay" && + test_config_global filter.bug.required true && + + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + echo "*.a filter=bug" >.gitattributes && + cp "$TEST_ROOT/test.o" missing-delay.a + git add . && + git commit -m "test commit" + ) && + + rm -rf repo-cloned && + test_must_fail git clone repo repo-cloned 2>git-stderr.log && + cat git-stderr.log && + grep "error: .missing-delay\.a. was not filtered properly" git-stderr.log +' + +test_expect_success PERL 'invalid file in delayed checkout' ' + test_config_global filter.bug.process "rot13-filter.pl bug.log clean smudge delay" && + test_config_global filter.bug.required true && + + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + echo "*.a filter=bug" >.gitattributes && + cp "$TEST_ROOT/test.o" invalid-delay.a && + cp "$TEST_ROOT/test.o" unfiltered + git add . && + git commit -m "test commit" + ) && + + rm -rf repo-cloned && + test_must_fail git clone repo repo-cloned 2>git-stderr.log && + grep "error: external filter .* signaled that .unfiltered. is now available although it has not been delayed earlier" git-stderr.log +' + test_done diff --git a/t/t0021/rot13-filter.pl b/t/t0021/rot13-filter.pl index 617f581e56..ad685d92f8 100644 --- a/t/t0021/rot13-filter.pl +++ b/t/t0021/rot13-filter.pl @@ -2,8 +2,9 @@ # Example implementation for the Git filter protocol version 2 # See Documentation/gitattributes.txt, section "Filter Protocol" # -# The script takes the list of supported protocol capabilities as -# arguments ("clean", "smudge", etc). +# The first argument defines a debug log file that the script write to. +# All remaining arguments define a list of supported protocol +# capabilities ("clean", "smudge", etc). # # This implementation supports special test cases: # (1) If data with the pathname "clean-write-fail.r" is processed with @@ -17,6 +18,16 @@ # operation then the filter signals that it cannot or does not want # to process the file and any file after that is processed with the # same command. +# (5) If data with a pathname that is a key in the DELAY hash is +# requested (e.g. "test-delay10.a") then the filter responds with +# a "delay" status and sets the "requested" field in the DELAY hash. +# The filter will signal the availability of this object after +# "count" (field in DELAY hash) "list_available_blobs" commands. +# (6) If data with the pathname "missing-delay.a" is processed that the +# filter will drop the path from the "list_available_blobs" response. +# (7) If data with the pathname "invalid-delay.a" is processed that the +# filter will add the path "unfiltered" which was not delayed before +# to the "list_available_blobs" response. # use strict; @@ -24,9 +35,19 @@ use warnings; use IO::File; my $MAX_PACKET_CONTENT_SIZE = 65516; +my $log_file = shift @ARGV; my @capabilities = @ARGV; -open my $debug, ">>", "rot13-filter.log" or die "cannot open log file: $!"; +open my $debug, ">>", $log_file or die "cannot open log file: $!"; + +my %DELAY = ( + 'test-delay10.a' => { "requested" => 0, "count" => 1 }, + 'test-delay11.a' => { "requested" => 0, "count" => 1 }, + 'test-delay20.a' => { "requested" => 0, "count" => 2 }, + 'test-delay10.b' => { "requested" => 0, "count" => 1 }, + 'missing-delay.a' => { "requested" => 0, "count" => 1 }, + 'invalid-delay.a' => { "requested" => 0, "count" => 1 }, +); sub rot13 { my $str = shift; @@ -64,7 +85,7 @@ sub packet_bin_read { sub packet_txt_read { my ( $res, $buf ) = packet_bin_read(); - unless ( $buf =~ s/\n$// ) { + unless ( $buf eq '' or $buf =~ s/\n$// ) { die "A non-binary line MUST be terminated by an LF."; } return ( $res, $buf ); @@ -99,6 +120,7 @@ packet_flush(); ( packet_txt_read() eq ( 0, "capability=clean" ) ) || die "bad capability"; ( packet_txt_read() eq ( 0, "capability=smudge" ) ) || die "bad capability"; +( packet_txt_read() eq ( 0, "capability=delay" ) ) || die "bad capability"; ( packet_bin_read() eq ( 1, "" ) ) || die "bad capability end"; foreach (@capabilities) { @@ -109,88 +131,142 @@ print $debug "init handshake complete\n"; $debug->flush(); while (1) { - my ($command) = packet_txt_read() =~ /^command=(.+)$/; + my ( $command ) = packet_txt_read() =~ /^command=(.+)$/; print $debug "IN: $command"; $debug->flush(); - my ($pathname) = packet_txt_read() =~ /^pathname=(.+)$/; - print $debug " $pathname"; - $debug->flush(); - - if ( $pathname eq "" ) { - die "bad pathname '$pathname'"; - } + if ( $command eq "list_available_blobs" ) { + # Flush + packet_bin_read(); - # Flush - packet_bin_read(); - - my $input = ""; - { - binmode(STDIN); - my $buffer; - my $done = 0; - while ( !$done ) { - ( $done, $buffer ) = packet_bin_read(); - $input .= $buffer; + foreach my $pathname ( sort keys %DELAY ) { + if ( $DELAY{$pathname}{"requested"} >= 1 ) { + $DELAY{$pathname}{"count"} = $DELAY{$pathname}{"count"} - 1; + if ( $pathname eq "invalid-delay.a" ) { + # Send Git a pathname that was not delayed earlier + packet_txt_write("pathname=unfiltered"); + } + if ( $pathname eq "missing-delay.a" ) { + # Do not signal Git that this file is available + } elsif ( $DELAY{$pathname}{"count"} == 0 ) { + print $debug " $pathname"; + packet_txt_write("pathname=$pathname"); + } + } } - print $debug " " . length($input) . " [OK] -- "; - $debug->flush(); - } - - my $output; - if ( $pathname eq "error.r" or $pathname eq "abort.r" ) { - $output = ""; - } - elsif ( $command eq "clean" and grep( /^clean$/, @capabilities ) ) { - $output = rot13($input); - } - elsif ( $command eq "smudge" and grep( /^smudge$/, @capabilities ) ) { - $output = rot13($input); - } - else { - die "bad command '$command'"; - } - print $debug "OUT: " . length($output) . " "; - $debug->flush(); - - if ( $pathname eq "error.r" ) { - print $debug "[ERROR]\n"; - $debug->flush(); - packet_txt_write("status=error"); packet_flush(); - } - elsif ( $pathname eq "abort.r" ) { - print $debug "[ABORT]\n"; + + print $debug " [OK]\n"; $debug->flush(); - packet_txt_write("status=abort"); + packet_txt_write("status=success"); packet_flush(); } else { - packet_txt_write("status=success"); - packet_flush(); + my ( $pathname ) = packet_txt_read() =~ /^pathname=(.+)$/; + print $debug " $pathname"; + $debug->flush(); - if ( $pathname eq "${command}-write-fail.r" ) { - print $debug "[WRITE FAIL]\n"; + if ( $pathname eq "" ) { + die "bad pathname '$pathname'"; + } + + # Read until flush + my ( $done, $buffer ) = packet_txt_read(); + while ( $buffer ne '' ) { + if ( $buffer eq "can-delay=1" ) { + if ( exists $DELAY{$pathname} and $DELAY{$pathname}{"requested"} == 0 ) { + $DELAY{$pathname}{"requested"} = 1; + } + } else { + die "Unknown message '$buffer'"; + } + + ( $done, $buffer ) = packet_txt_read(); + } + + my $input = ""; + { + binmode(STDIN); + my $buffer; + my $done = 0; + while ( !$done ) { + ( $done, $buffer ) = packet_bin_read(); + $input .= $buffer; + } + print $debug " " . length($input) . " [OK] -- "; $debug->flush(); - die "${command} write error"; } - while ( length($output) > 0 ) { - my $packet = substr( $output, 0, $MAX_PACKET_CONTENT_SIZE ); - packet_bin_write($packet); - # dots represent the number of packets - print $debug "."; - if ( length($output) > $MAX_PACKET_CONTENT_SIZE ) { - $output = substr( $output, $MAX_PACKET_CONTENT_SIZE ); + my $output; + if ( exists $DELAY{$pathname} and exists $DELAY{$pathname}{"output"} ) { + $output = $DELAY{$pathname}{"output"} + } + elsif ( $pathname eq "error.r" or $pathname eq "abort.r" ) { + $output = ""; + } + elsif ( $command eq "clean" and grep( /^clean$/, @capabilities ) ) { + $output = rot13($input); + } + elsif ( $command eq "smudge" and grep( /^smudge$/, @capabilities ) ) { + $output = rot13($input); + } + else { + die "bad command '$command'"; + } + + if ( $pathname eq "error.r" ) { + print $debug "[ERROR]\n"; + $debug->flush(); + packet_txt_write("status=error"); + packet_flush(); + } + elsif ( $pathname eq "abort.r" ) { + print $debug "[ABORT]\n"; + $debug->flush(); + packet_txt_write("status=abort"); + packet_flush(); + } + elsif ( $command eq "smudge" and + exists $DELAY{$pathname} and + $DELAY{$pathname}{"requested"} == 1 + ) { + print $debug "[DELAYED]\n"; + $debug->flush(); + packet_txt_write("status=delayed"); + packet_flush(); + $DELAY{$pathname}{"requested"} = 2; + $DELAY{$pathname}{"output"} = $output; + } + else { + packet_txt_write("status=success"); + packet_flush(); + + if ( $pathname eq "${command}-write-fail.r" ) { + print $debug "[WRITE FAIL]\n"; + $debug->flush(); + die "${command} write error"; } - else { - $output = ""; + + print $debug "OUT: " . length($output) . " "; + $debug->flush(); + + while ( length($output) > 0 ) { + my $packet = substr( $output, 0, $MAX_PACKET_CONTENT_SIZE ); + packet_bin_write($packet); + # dots represent the number of packets + print $debug "."; + if ( length($output) > $MAX_PACKET_CONTENT_SIZE ) { + $output = substr( $output, $MAX_PACKET_CONTENT_SIZE ); + } + else { + $output = ""; + } } + packet_flush(); + print $debug " [OK]\n"; + $debug->flush(); + packet_flush(); } - packet_flush(); - print $debug " [OK]\n"; - $debug->flush(); - packet_flush(); } } diff --git a/unpack-trees.c b/unpack-trees.c index dd535bc849..862cfce661 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -380,6 +380,7 @@ static int check_updates(struct unpack_trees_options *o) if (should_update_submodules() && o->update && !o->dry_run) reload_gitmodules_file(index, &state); + enable_delayed_checkout(&state); for (i = 0; i < index->cache_nr; i++) { struct cache_entry *ce = index->cache[i]; @@ -394,6 +395,7 @@ static int check_updates(struct unpack_trees_options *o) } } } + errs |= finish_delayed_checkout(&state); stop_progress(&progress); if (o->update) git_attr_set_direction(GIT_ATTR_CHECKIN, NULL); |