From: Junio C Hamano Date: Wed, 23 Oct 2013 20:21:30 +0000 (-0700) Subject: Merge branch 'mg/more-textconv' X-Git-Tag: v1.8.5-rc0~32 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/4197361e39a304df30cc492122dbdfe90ae8af0e?ds=inline;hp=-c Merge branch 'mg/more-textconv' Make "git grep" and "git show" pay attention to --textconv when dealing with blob objects. * mg/more-textconv: grep: honor --textconv for the case rev:path grep: allow to use textconv filters t7008: demonstrate behavior of grep with textconv cat-file: do not die on --textconv without textconv filters show: honor --textconv for blobs diff_opt: track whether flags have been set explicitly t4030: demonstrate behavior of show with textconv --- 4197361e39a304df30cc492122dbdfe90ae8af0e diff --combined Documentation/git-grep.txt index 8497aa4494,a5c5a27da4..f83733490f --- a/Documentation/git-grep.txt +++ b/Documentation/git-grep.txt @@@ -9,7 -9,7 +9,7 @@@ git-grep - Print lines matching a patte SYNOPSIS -------- [verse] - 'git grep' [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp] + 'git grep' [-a | --text] [-I] [--textconv] [-i | --ignore-case] [-w | --word-regexp] [-v | --invert-match] [-h|-H] [--full-name] [-E | --extended-regexp] [-G | --basic-regexp] [-P | --perl-regexp] @@@ -25,7 -25,7 +25,7 @@@ [-W | --function-context] [-f ] [-e] [--and|--or|--not|(|)|-e ...] - [ [--exclude-standard] [--cached | --no-index | --untracked] | ...] + [ [--[no-]exclude-standard] [--cached | --no-index | --untracked] | ...] [--] [...] DESCRIPTION @@@ -80,6 -80,13 +80,13 @@@ OPTION --text:: Process binary files as if they were text. + --textconv:: + Honor textconv filter settings. + + --no-textconv:: + Do not honor textconv filter settings. + This is the default. + -i:: --ignore-case:: Ignore case differences between the patterns and the diff --combined builtin/cat-file.c index 41afaa534b,fbaa1213f1..b2ca775a80 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@@ -13,6 -13,76 +13,6 @@@ #include "userdiff.h" #include "streaming.h" -#define BATCH 1 -#define BATCH_CHECK 2 - -static void pprint_tag(const unsigned char *sha1, const char *buf, unsigned long size) -{ - /* the parser in tag.c is useless here. */ - const char *endp = buf + size; - const char *cp = buf; - - while (cp < endp) { - char c = *cp++; - if (c != '\n') - continue; - if (7 <= endp - cp && !memcmp("tagger ", cp, 7)) { - const char *tagger = cp; - - /* Found the tagger line. Copy out the contents - * of the buffer so far. - */ - write_or_die(1, buf, cp - buf); - - /* - * Do something intelligent, like pretty-printing - * the date. - */ - while (cp < endp) { - if (*cp++ == '\n') { - /* tagger to cp is a line - * that has ident and time. - */ - const char *sp = tagger; - char *ep; - unsigned long date; - long tz; - while (sp < cp && *sp != '>') - sp++; - if (sp == cp) { - /* give up */ - write_or_die(1, tagger, - cp - tagger); - break; - } - while (sp < cp && - !('0' <= *sp && *sp <= '9')) - sp++; - write_or_die(1, tagger, sp - tagger); - date = strtoul(sp, &ep, 10); - tz = strtol(ep, NULL, 10); - sp = show_date(date, tz, 0); - write_or_die(1, sp, strlen(sp)); - xwrite(1, "\n", 1); - break; - } - } - break; - } - if (cp < endp && *cp == '\n') - /* end of header */ - break; - } - /* At this point, we have copied out the header up to the end of - * the tagger line and cp points at one past \n. It could be the - * next header line after the tagger line, or it could be another - * \n that marks the end of the headers. We need to copy out the - * remainder as is. - */ - if (cp < endp) - write_or_die(1, cp, endp - cp); -} - static int cat_one_file(int opt, const char *exp_type, const char *obj_name) { unsigned char sha1[20]; @@@ -45,6 -115,14 +45,14 @@@ case 'e': return !has_sha1_file(sha1); + case 'c': + if (!obj_context.path[0]) + die("git cat-file --textconv %s: must be ", + obj_name); + + if (textconv_object(obj_context.path, obj_context.mode, sha1, 1, &buf, &size)) + break; + case 'p': type = sha1_object_info(sha1, NULL); if (type < 0) @@@ -63,20 -141,14 +71,10 @@@ buf = read_sha1_file(sha1, &type, &size); if (!buf) die("Cannot read object %s", obj_name); - if (type == OBJ_TAG) { - pprint_tag(sha1, buf, size); - return 0; - } /* otherwise just spit out the data */ break; - case 'c': - if (!obj_context.path[0]) - die("git cat-file --textconv %s: must be ", - obj_name); - - if (!textconv_object(obj_context.path, obj_context.mode, sha1, 1, &buf, &size)) - die("git cat-file --textconv: unable to run textconv on %s", - obj_name); - break; - case 0: if (type_from_string(exp_type) == OBJ_BLOB) { unsigned char blob_sha1[20]; @@@ -114,195 -186,54 +112,195 @@@ return 0; } -static int batch_one_object(const char *obj_name, int print_contents) -{ +struct expand_data { unsigned char sha1[20]; - enum object_type type = 0; + enum object_type type; unsigned long size; - void *contents = NULL; + unsigned long disk_size; + const char *rest; + + /* + * If mark_query is true, we do not expand anything, but rather + * just mark the object_info with items we wish to query. + */ + int mark_query; + + /* + * Whether to split the input on whitespace before feeding it to + * get_sha1; this is decided during the mark_query phase based on + * whether we have a %(rest) token in our format. + */ + int split_on_whitespace; + + /* + * After a mark_query run, this object_info is set up to be + * passed to sha1_object_info_extended. It will point to the data + * elements above, so you can retrieve the response from there. + */ + struct object_info info; +}; + +static int is_atom(const char *atom, const char *s, int slen) +{ + int alen = strlen(atom); + return alen == slen && !memcmp(atom, s, alen); +} + +static void expand_atom(struct strbuf *sb, const char *atom, int len, + void *vdata) +{ + struct expand_data *data = vdata; + + if (is_atom("objectname", atom, len)) { + if (!data->mark_query) + strbuf_addstr(sb, sha1_to_hex(data->sha1)); + } else if (is_atom("objecttype", atom, len)) { + if (data->mark_query) + data->info.typep = &data->type; + else + strbuf_addstr(sb, typename(data->type)); + } else if (is_atom("objectsize", atom, len)) { + if (data->mark_query) + data->info.sizep = &data->size; + else + strbuf_addf(sb, "%lu", data->size); + } else if (is_atom("objectsize:disk", atom, len)) { + if (data->mark_query) + data->info.disk_sizep = &data->disk_size; + else + strbuf_addf(sb, "%lu", data->disk_size); + } else if (is_atom("rest", atom, len)) { + if (data->mark_query) + data->split_on_whitespace = 1; + else if (data->rest) + strbuf_addstr(sb, data->rest); + } else + die("unknown format element: %.*s", len, atom); +} + +static size_t expand_format(struct strbuf *sb, const char *start, void *data) +{ + const char *end; + + if (*start != '(') + return 0; + end = strchr(start + 1, ')'); + if (!end) + die("format element '%s' does not end in ')'", start); + + expand_atom(sb, start + 1, end - start - 1, data); + + return end - start + 1; +} + +static void print_object_or_die(int fd, const unsigned char *sha1, + enum object_type type, unsigned long size) +{ + if (type == OBJ_BLOB) { + if (stream_blob_to_fd(fd, sha1, NULL, 0) < 0) + die("unable to stream %s to stdout", sha1_to_hex(sha1)); + } + else { + enum object_type rtype; + unsigned long rsize; + void *contents; + + contents = read_sha1_file(sha1, &rtype, &rsize); + if (!contents) + die("object %s disappeared", sha1_to_hex(sha1)); + if (rtype != type) + die("object %s changed type!?", sha1_to_hex(sha1)); + if (rsize != size) + die("object %s change size!?", sha1_to_hex(sha1)); + + write_or_die(fd, contents, size); + free(contents); + } +} + +struct batch_options { + int enabled; + int print_contents; + const char *format; +}; + +static int batch_one_object(const char *obj_name, struct batch_options *opt, + struct expand_data *data) +{ + struct strbuf buf = STRBUF_INIT; if (!obj_name) return 1; - if (get_sha1(obj_name, sha1)) { + if (get_sha1(obj_name, data->sha1)) { printf("%s missing\n", obj_name); fflush(stdout); return 0; } - if (print_contents == BATCH) - contents = read_sha1_file(sha1, &type, &size); - else - type = sha1_object_info(sha1, &size); - - if (type <= 0) { + if (sha1_object_info_extended(data->sha1, &data->info) < 0) { printf("%s missing\n", obj_name); fflush(stdout); - if (print_contents == BATCH) - free(contents); return 0; } - printf("%s %s %lu\n", sha1_to_hex(sha1), typename(type), size); - fflush(stdout); + strbuf_expand(&buf, opt->format, expand_format, data); + strbuf_addch(&buf, '\n'); + write_or_die(1, buf.buf, buf.len); + strbuf_release(&buf); - if (print_contents == BATCH) { - write_or_die(1, contents, size); - printf("\n"); - fflush(stdout); - free(contents); + if (opt->print_contents) { + print_object_or_die(1, data->sha1, data->type, data->size); + write_or_die(1, "\n", 1); } - return 0; } -static int batch_objects(int print_contents) +static int batch_objects(struct batch_options *opt) { struct strbuf buf = STRBUF_INIT; + struct expand_data data; + + if (!opt->format) + opt->format = "%(objectname) %(objecttype) %(objectsize)"; + + /* + * Expand once with our special mark_query flag, which will prime the + * object_info to be handed to sha1_object_info_extended for each + * object. + */ + memset(&data, 0, sizeof(data)); + data.mark_query = 1; + strbuf_expand(&buf, opt->format, expand_format, &data); + data.mark_query = 0; + + /* + * We are going to call get_sha1 on a potentially very large number of + * objects. In most large cases, these will be actual object sha1s. The + * cost to double-check that each one is not also a ref (just so we can + * warn) ends up dwarfing the actual cost of the object lookups + * themselves. We can work around it by just turning off the warning. + */ + warn_on_object_refname_ambiguity = 0; while (strbuf_getline(&buf, stdin, '\n') != EOF) { - int error = batch_one_object(buf.buf, print_contents); + int error; + + if (data.split_on_whitespace) { + /* + * Split at first whitespace, tying off the beginning + * of the string and saving the remainder (or NULL) in + * data.rest. + */ + char *p = strpbrk(buf.buf, " \t"); + if (p) { + while (*p && strchr(" \t", *p)) + *p++ = '\0'; + } + data.rest = p; + } + + error = batch_one_object(buf.buf, opt, &data); if (error) return error; } @@@ -324,29 -255,10 +322,29 @@@ static int git_cat_file_config(const ch return git_default_config(var, value, cb); } +static int batch_option_callback(const struct option *opt, + const char *arg, + int unset) +{ + struct batch_options *bo = opt->value; + + if (unset) { + memset(bo, 0, sizeof(*bo)); + return 0; + } + + bo->enabled = 1; + bo->print_contents = !strcmp(opt->long_name, "batch"); + bo->format = arg; + + return 0; +} + int cmd_cat_file(int argc, const char **argv, const char *prefix) { - int opt = 0, batch = 0; + int opt = 0; const char *exp_type = NULL, *obj_name = NULL; + struct batch_options batch = {0}; const struct option options[] = { OPT_GROUP(N_(" can be one of: blob, tree, commit, tag")), @@@ -357,12 -269,12 +355,12 @@@ OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'), OPT_SET_INT(0, "textconv", &opt, N_("for blob objects, run textconv on object's content"), 'c'), - OPT_SET_INT(0, "batch", &batch, - N_("show info and content of objects fed from the standard input"), - BATCH), - OPT_SET_INT(0, "batch-check", &batch, - N_("show info about objects fed from the standard input"), - BATCH_CHECK), + { OPTION_CALLBACK, 0, "batch", &batch, "format", + N_("show info and content of objects fed from the standard input"), + PARSE_OPT_OPTARG, batch_option_callback }, + { OPTION_CALLBACK, 0, "batch-check", &batch, "format", + N_("show info about objects fed from the standard input"), + PARSE_OPT_OPTARG, batch_option_callback }, OPT_END() }; @@@ -379,19 -291,19 +377,19 @@@ else usage_with_options(cat_file_usage, options); } - if (!opt && !batch) { + if (!opt && !batch.enabled) { if (argc == 2) { exp_type = argv[0]; obj_name = argv[1]; } else usage_with_options(cat_file_usage, options); } - if (batch && (opt || argc)) { + if (batch.enabled && (opt || argc)) { usage_with_options(cat_file_usage, options); } - if (batch) - return batch_objects(batch); + if (batch.enabled) + return batch_objects(&batch); return cat_one_file(opt, exp_type, obj_name); } diff --combined builtin/grep.c index 03bc442e3f,bb7f970ca0..63f86032d9 --- a/builtin/grep.c +++ b/builtin/grep.c @@@ -17,7 -17,6 +17,7 @@@ #include "grep.h" #include "quote.h" #include "dir.h" +#include "pathspec.h" static char const * const grep_usage[] = { N_("git grep [options] [-e] [...] [[--] ...]"), @@@ -287,7 -286,8 +287,7 @@@ static int grep_sha1(struct grep_opt *o struct strbuf pathbuf = STRBUF_INIT; if (opt->relative && opt->prefix_length) { - quote_path_relative(filename + tree_name_len, -1, &pathbuf, - opt->prefix); + quote_path_relative(filename + tree_name_len, opt->prefix, &pathbuf); strbuf_insert(&pathbuf, 0, filename, tree_name_len); } else { strbuf_addstr(&pathbuf, filename); @@@ -318,7 -318,7 +318,7 @@@ static int grep_file(struct grep_opt *o struct strbuf buf = STRBUF_INIT; if (opt->relative && opt->prefix_length) - quote_path_relative(filename, -1, &buf, opt->prefix); + quote_path_relative(filename, opt->prefix, &buf); else strbuf_addstr(&buf, filename); @@@ -376,7 -376,7 +376,7 @@@ static int grep_cache(struct grep_opt * read_cache(); for (nr = 0; nr < active_nr; nr++) { - struct cache_entry *ce = active_cache[nr]; + const struct cache_entry *ce = active_cache[nr]; if (!S_ISREG(ce->ce_mode)) continue; if (!match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL)) @@@ -458,10 -458,10 +458,10 @@@ static int grep_tree(struct grep_opt *o } static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, - struct object *obj, const char *name) + struct object *obj, const char *name, struct object_context *oc) { if (obj->type == OBJ_BLOB) - return grep_sha1(opt, obj->sha1, name, 0, NULL); + return grep_sha1(opt, obj->sha1, name, 0, oc ? oc->path : NULL); if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) { struct tree_desc tree; void *data; @@@ -503,7 -503,7 +503,7 @@@ static int grep_objects(struct grep_op for (i = 0; i < nr; i++) { struct object *real_obj; real_obj = deref_tag(list->objects[i].item, NULL, 0); - if (grep_object(opt, pathspec, real_obj, list->objects[i].name)) { + if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].context)) { hit = 1; if (opt->status_only) break; @@@ -522,7 -522,7 +522,7 @@@ static int grep_directory(struct grep_o if (exc_std) setup_standard_excludes(&dir); - fill_directory(&dir, pathspec->raw); + fill_directory(&dir, pathspec); for (i = 0; i < dir.nr; i++) { const char *name = dir.entries[i]->name; int namelen = strlen(name); @@@ -630,6 -630,7 +630,6 @@@ int cmd_grep(int argc, const char **arg const char *show_in_pager = NULL, *default_pager = "dummy"; struct grep_opt opt; struct object_array list = OBJECT_ARRAY_INIT; - const char **paths = NULL; struct pathspec pathspec; struct string_list path_list = STRING_LIST_INIT_NODUP; int i; @@@ -638,26 -639,28 +638,28 @@@ int pattern_type_arg = GREP_PATTERN_TYPE_UNSPECIFIED; struct option options[] = { - OPT_BOOLEAN(0, "cached", &cached, + OPT_BOOL(0, "cached", &cached, N_("search in index instead of in the work tree")), OPT_NEGBIT(0, "no-index", &use_index, N_("find in contents not managed by git"), 1), - OPT_BOOLEAN(0, "untracked", &untracked, + OPT_BOOL(0, "untracked", &untracked, N_("search in both tracked and untracked files")), OPT_SET_INT(0, "exclude-standard", &opt_exclude, N_("search also in ignored files"), 1), OPT_GROUP(""), - OPT_BOOLEAN('v', "invert-match", &opt.invert, + OPT_BOOL('v', "invert-match", &opt.invert, N_("show non-matching lines")), - OPT_BOOLEAN('i', "ignore-case", &opt.ignore_case, + OPT_BOOL('i', "ignore-case", &opt.ignore_case, N_("case insensitive matching")), - OPT_BOOLEAN('w', "word-regexp", &opt.word_regexp, + OPT_BOOL('w', "word-regexp", &opt.word_regexp, N_("match patterns only at word boundaries")), OPT_SET_INT('a', "text", &opt.binary, N_("process binary files as text"), GREP_BINARY_TEXT), OPT_SET_INT('I', NULL, &opt.binary, N_("don't match patterns in binary files"), GREP_BINARY_NOMATCH), + OPT_BOOL(0, "textconv", &opt.allow_textconv, + N_("process binary files with textconv filters")), { OPTION_INTEGER, 0, "max-depth", &opt.max_depth, N_("depth"), N_("descend at most levels"), PARSE_OPT_NONEG, NULL, 1 }, @@@ -675,26 -678,26 +677,26 @@@ N_("use Perl-compatible regular expressions"), GREP_PATTERN_TYPE_PCRE), OPT_GROUP(""), - OPT_BOOLEAN('n', "line-number", &opt.linenum, N_("show line numbers")), + OPT_BOOL('n', "line-number", &opt.linenum, N_("show line numbers")), OPT_NEGBIT('h', NULL, &opt.pathname, N_("don't show filenames"), 1), OPT_BIT('H', NULL, &opt.pathname, N_("show filenames"), 1), OPT_NEGBIT(0, "full-name", &opt.relative, N_("show filenames relative to top directory"), 1), - OPT_BOOLEAN('l', "files-with-matches", &opt.name_only, + OPT_BOOL('l', "files-with-matches", &opt.name_only, N_("show only filenames instead of matching lines")), - OPT_BOOLEAN(0, "name-only", &opt.name_only, + OPT_BOOL(0, "name-only", &opt.name_only, N_("synonym for --files-with-matches")), - OPT_BOOLEAN('L', "files-without-match", + OPT_BOOL('L', "files-without-match", &opt.unmatch_name_only, N_("show only the names of files without match")), - OPT_BOOLEAN('z', "null", &opt.null_following_name, + OPT_BOOL('z', "null", &opt.null_following_name, N_("print NUL after filenames")), - OPT_BOOLEAN('c', "count", &opt.count, + OPT_BOOL('c', "count", &opt.count, N_("show the number of matches instead of matching lines")), OPT__COLOR(&opt.color, N_("highlight matches")), - OPT_BOOLEAN(0, "break", &opt.file_break, + OPT_BOOL(0, "break", &opt.file_break, N_("print empty line between matches from different files")), - OPT_BOOLEAN(0, "heading", &opt.heading, + OPT_BOOL(0, "heading", &opt.heading, N_("show filename only once above matches from same file")), OPT_GROUP(""), OPT_CALLBACK('C', "context", &opt, N_("n"), @@@ -706,9 -709,9 +708,9 @@@ N_("show context lines after matches")), OPT_NUMBER_CALLBACK(&opt, N_("shortcut for -C NUM"), context_callback), - OPT_BOOLEAN('p', "show-function", &opt.funcname, + OPT_BOOL('p', "show-function", &opt.funcname, N_("show a line with the function name before matches")), - OPT_BOOLEAN('W', "function-context", &opt.funcbody, + OPT_BOOL('W', "function-context", &opt.funcbody, N_("show the surrounding function")), OPT_GROUP(""), OPT_CALLBACK('f', NULL, &opt, N_("file"), @@@ -718,7 -721,7 +720,7 @@@ { OPTION_CALLBACK, 0, "and", &opt, NULL, N_("combine patterns specified with -e"), PARSE_OPT_NOARG | PARSE_OPT_NONEG, and_callback }, - OPT_BOOLEAN(0, "or", &dummy, ""), + OPT_BOOL(0, "or", &dummy, ""), { OPTION_CALLBACK, 0, "not", &opt, NULL, "", PARSE_OPT_NOARG | PARSE_OPT_NONEG, not_callback }, { OPTION_CALLBACK, '(', NULL, &opt, NULL, "", @@@ -729,7 -732,7 +731,7 @@@ close_callback }, OPT__QUIET(&opt.status_only, N_("indicate hit with exit status without output")), - OPT_BOOLEAN(0, "all-match", &opt.all_match, + OPT_BOOL(0, "all-match", &opt.all_match, N_("show only matches from files that match all patterns")), { OPTION_SET_INT, 0, "debug", &opt.debug, NULL, N_("show parse tree for grep expression"), @@@ -738,8 -741,8 +740,8 @@@ { OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager, N_("pager"), N_("show matching files in the pager"), PARSE_OPT_OPTARG, NULL, (intptr_t)default_pager }, - OPT_BOOLEAN(0, "ext-grep", &external_grep_allowed__ignored, - N_("allow calling of grep(1) (ignored by this build)")), + OPT_BOOL(0, "ext-grep", &external_grep_allowed__ignored, + N_("allow calling of grep(1) (ignored by this build)")), { OPTION_CALLBACK, 0, "help-all", &options, NULL, N_("show usage"), PARSE_OPT_HIDDEN | PARSE_OPT_NOARG, help_callback }, OPT_END() @@@ -817,12 -820,13 +819,13 @@@ for (i = 0; i < argc; i++) { const char *arg = argv[i]; unsigned char sha1[20]; + struct object_context oc; /* Is it a rev? */ - if (!get_sha1(arg, sha1)) { + if (!get_sha1_with_context(arg, 0, sha1, &oc)) { struct object *object = parse_object_or_die(sha1, arg); if (!seen_dashdash) verify_non_filename(prefix, arg); - add_object_array(object, arg, &list); + add_object_array_with_context(object, arg, &list, xmemdupz(&oc, sizeof(struct object_context))); continue; } if (!strcmp(arg, "--")) { @@@ -856,10 -860,8 +859,10 @@@ verify_filename(prefix, argv[j], j == i); } - paths = get_pathspec(prefix, argv + i); - init_pathspec(&pathspec, paths); + parse_pathspec(&pathspec, 0, + PATHSPEC_PREFER_CWD | + (opt.max_depth != -1 ? PATHSPEC_MAXDEPTH_VALID : 0), + prefix, argv + i); pathspec.max_depth = opt.max_depth; pathspec.recursive = 1; diff --combined builtin/log.c index 77d0f5f3fd,815c5b84ed..b708517a35 --- a/builtin/log.c +++ b/builtin/log.c @@@ -19,7 -19,6 +19,7 @@@ #include "remote.h" #include "string-list.h" #include "parse-options.h" +#include "line-log.h" #include "branch.h" #include "streaming.h" #include "version.h" @@@ -38,17 -37,11 +38,17 @@@ static const char *fmt_patch_subject_pr static const char *fmt_pretty; static const char * const builtin_log_usage[] = { - N_("git log [] [..] [[--] ...]\n") + N_("git log [] [] [[--] ...]\n") N_(" or: git show [options] ..."), NULL }; +struct line_opt_callback_data { + struct rev_info *rev; + const char *prefix; + struct string_list args; +}; + static int parse_decoration_style(const char *var, const char *value) { switch (git_config_maybe_bool(var, value)) { @@@ -83,19 -76,6 +83,19 @@@ static int decorate_callback(const stru return 0; } +static int log_line_range_callback(const struct option *option, const char *arg, int unset) +{ + struct line_opt_callback_data *data = option->value; + + if (!arg) + return -1; + + data->rev->line_level_traverse = 1; + string_list_append(&data->args, arg); + + return 0; +} + static void cmd_log_init_defaults(struct rev_info *rev) { if (fmt_pretty) @@@ -111,6 -91,7 +111,7 @@@ if (default_date_mode) rev->date_mode = parse_date_format(default_date_mode); + rev->diffopt.touched_flags = 0; } static void cmd_log_init_finish(int argc, const char **argv, const char *prefix, @@@ -118,23 -99,16 +119,23 @@@ { struct userformat_want w; int quiet = 0, source = 0, mailmap = 0; + static struct line_opt_callback_data line_cb = {NULL, NULL, STRING_LIST_INIT_DUP}; const struct option builtin_log_options[] = { - OPT_BOOL(0, "quiet", &quiet, N_("suppress diff output")), + OPT__QUIET(&quiet, N_("suppress diff output")), OPT_BOOL(0, "source", &source, N_("show source")), OPT_BOOL(0, "use-mailmap", &mailmap, N_("Use mail map file")), { OPTION_CALLBACK, 0, "decorate", NULL, NULL, N_("decorate options"), PARSE_OPT_OPTARG, decorate_callback}, + OPT_CALLBACK('L', NULL, &line_cb, "n,m:file", + "Process line range n,m in file, counting from 1", + log_line_range_callback), OPT_END() }; + line_cb.rev = rev; + line_cb.prefix = prefix; + mailmap = use_mailmap_config; argc = parse_options(argc, argv, prefix, builtin_log_options, builtin_log_usage, @@@ -188,10 -162,6 +189,10 @@@ rev->show_decorations = 1; load_ref_decorations(decoration_style); } + + if (rev->line_level_traverse) + line_log_init(rev, line_cb.prefix, &line_cb.args); + setup_pager(); } @@@ -237,7 -207,7 +238,7 @@@ static void log_show_early(struct rev_i int i = revs->early_output; int show_header = 1; - sort_in_topological_order(&list, revs->lifo); + sort_in_topological_order(&list, revs->sort_order); while (list && i) { struct commit *commit = list->item; switch (simplify_commit(revs, commit)) { @@@ -436,10 -406,29 +437,29 @@@ static void show_tagger(char *buf, int strbuf_release(&out); } - static int show_blob_object(const unsigned char *sha1, struct rev_info *rev) + static int show_blob_object(const unsigned char *sha1, struct rev_info *rev, const char *obj_name) { + unsigned char sha1c[20]; + struct object_context obj_context; + char *buf; + unsigned long size; + fflush(stdout); - return stream_blob_to_fd(1, sha1, NULL, 0); + if (!DIFF_OPT_TOUCHED(&rev->diffopt, ALLOW_TEXTCONV) || + !DIFF_OPT_TST(&rev->diffopt, ALLOW_TEXTCONV)) + return stream_blob_to_fd(1, sha1, NULL, 0); + + if (get_sha1_with_context(obj_name, 0, sha1c, &obj_context)) + die("Not a valid object name %s", obj_name); + if (!obj_context.path[0] || + !textconv_object(obj_context.path, obj_context.mode, sha1c, 1, &buf, &size)) + return stream_blob_to_fd(1, sha1, NULL, 0); + + if (!buf) + die("git show %s: bad file", obj_name); + + write_or_die(1, buf, size); + return 0; } static int show_tag_object(const unsigned char *sha1, struct rev_info *rev) @@@ -503,7 -492,7 +523,7 @@@ int cmd_show(int argc, const char **arg init_grep_defaults(); git_config(git_log_config, NULL); - init_pathspec(&match_all, NULL); + memset(&match_all, 0, sizeof(match_all)); init_revisions(&rev, prefix); rev.diff = 1; rev.always_show_header = 1; @@@ -525,7 -514,7 +545,7 @@@ const char *name = objects[i].name; switch (o->type) { case OBJ_BLOB: - ret = show_blob_object(o->sha1, NULL); + ret = show_blob_object(o->sha1, &rev, name); break; case OBJ_TAG: { struct tag *t = (struct tag *)o; @@@ -1112,21 -1101,6 +1132,21 @@@ static int cc_callback(const struct opt return 0; } +static int from_callback(const struct option *opt, const char *arg, int unset) +{ + char **from = opt->value; + + free(*from); + + if (unset) + *from = NULL; + else if (arg) + *from = xstrdup(arg); + else + *from = xstrdup(git_committer_info(IDENT_NO_DATE)); + return 0; +} + int cmd_format_patch(int argc, const char **argv, const char *prefix) { struct commit *commit; @@@ -1149,7 -1123,6 +1169,7 @@@ int quiet = 0; int reroll_count = -1; char *branch_name = NULL; + char *from = NULL; const struct option builtin_format_patch_options[] = { { OPTION_CALLBACK, 'n', "numbered", &numbered, NULL, N_("use [PATCH n/m] even with a single patch"), @@@ -1179,13 -1152,13 +1199,13 @@@ { OPTION_CALLBACK, 'k', "keep-subject", &rev, NULL, N_("don't strip/add [PATCH]"), PARSE_OPT_NOARG | PARSE_OPT_NONEG, keep_callback }, - OPT_BOOLEAN(0, "no-binary", &no_binary_diff, - N_("don't output binary diffs")), - OPT_BOOLEAN(0, "ignore-if-in-upstream", &ignore_if_in_upstream, - N_("don't include a patch matching a commit upstream")), - { OPTION_BOOLEAN, 'p', "no-stat", &use_patch_format, NULL, + OPT_BOOL(0, "no-binary", &no_binary_diff, + N_("don't output binary diffs")), + OPT_BOOL(0, "ignore-if-in-upstream", &ignore_if_in_upstream, + N_("don't include a patch matching a commit upstream")), + { OPTION_SET_INT, 'p', "no-stat", &use_patch_format, NULL, N_("show patch format instead of default (patch + stat)"), - PARSE_OPT_NONEG | PARSE_OPT_NOARG }, + PARSE_OPT_NONEG | PARSE_OPT_NOARG, NULL, 1}, OPT_GROUP(N_("Messaging")), { OPTION_CALLBACK, 0, "add-header", NULL, N_("header"), N_("add email header"), 0, header_callback }, @@@ -1193,9 -1166,6 +1213,9 @@@ 0, to_callback }, { OPTION_CALLBACK, 0, "cc", NULL, N_("email"), N_("add Cc: header"), 0, cc_callback }, + { OPTION_CALLBACK, 0, "from", &from, N_("ident"), + N_("set From address to (or committer ident if absent)"), + PARSE_OPT_OPTARG, from_callback }, OPT_STRING(0, "in-reply-to", &in_reply_to, N_("message-id"), N_("make first mail a reply to ")), { OPTION_CALLBACK, 0, "attach", &rev, N_("boundary"), @@@ -1210,7 -1180,8 +1230,7 @@@ PARSE_OPT_OPTARG, thread_callback }, OPT_STRING(0, "signature", &signature, N_("signature"), N_("add a signature")), - OPT_BOOLEAN(0, "quiet", &quiet, - N_("don't print the patch filenames")), + OPT__QUIET(&quiet, N_("don't print the patch filenames")), OPT_END() }; @@@ -1282,11 -1253,6 +1302,11 @@@ rev.extra_headers = strbuf_detach(&buf, NULL); + if (from) { + if (split_ident_line(&rev.from_ident, from, strlen(from))) + die(_("invalid ident line: %s"), from); + } + if (start_number < 0) start_number = 1; diff --combined diff.c index a04a34d048,7c248726ad..e34bf97120 --- a/diff.c +++ b/diff.c @@@ -669,7 -669,7 +669,7 @@@ static void emit_rewrite_diff(const cha memset(&ecbdata, 0, sizeof(ecbdata)); ecbdata.color_diff = want_color(o->use_color); ecbdata.found_changesp = &o->found_changes; - ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a); + ecbdata.ws_rule = whitespace_rule(name_b); ecbdata.opt = o; if (ecbdata.ws_rule & WS_BLANK_AT_EOF) { mmfile_t mf1, mf2; @@@ -1683,7 -1683,9 +1683,7 @@@ static void show_stats(struct diffstat_ del = deleted; if (graph_width <= max_change) { - int total = add + del; - - total = scale_linear(add + del, graph_width, max_change); + int total = scale_linear(add + del, graph_width, max_change); if (total < 2 && add && del) /* width >= 2 due to the sanity check */ total = 2; @@@ -2252,7 -2254,7 +2252,7 @@@ static void builtin_diff(const char *na (!two->mode || S_ISGITLINK(two->mode))) { const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); - show_submodule_summary(o->file, one ? one->path : two->path, + show_submodule_summary(o->file, one->path ? one->path : two->path, line_prefix, one->sha1, two->sha1, two->dirty_submodule, meta, del, add, reset); @@@ -2372,7 -2374,7 +2372,7 @@@ ecbdata.label_path = lbl; ecbdata.color_diff = want_color(o->use_color); ecbdata.found_changesp = &o->found_changes; - ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a); + ecbdata.ws_rule = whitespace_rule(name_b); if (ecbdata.ws_rule & WS_BLANK_AT_EOF) check_blank_at_eof(&mf1, &mf2, &ecbdata); ecbdata.opt = o; @@@ -2584,7 -2586,7 +2584,7 @@@ void fill_filespec(struct diff_filespe */ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int want_file) { - struct cache_entry *ce; + const struct cache_entry *ce; struct stat st; int pos, len; @@@ -2675,14 -2677,6 +2675,14 @@@ static int diff_populate_gitlink(struc int diff_populate_filespec(struct diff_filespec *s, int size_only) { int err = 0; + /* + * demote FAIL to WARN to allow inspecting the situation + * instead of refusing. + */ + enum safe_crlf crlf_warn = (safe_crlf == SAFE_CRLF_FAIL + ? SAFE_CRLF_WARN + : safe_crlf); + if (!DIFF_FILE_VALID(s)) die("internal error: asking to populate invalid file."); if (S_ISDIR(s->mode)) @@@ -2738,7 -2732,7 +2738,7 @@@ /* * Convert from working tree format to canonical git format */ - if (convert_to_git(s->path, s->data, s->size, &buf, safe_crlf)) { + if (convert_to_git(s->path, s->data, s->size, &buf, crlf_warn)) { size_t size = 0; munmap(s->data, s->size); s->should_munmap = 0; @@@ -3219,6 -3213,9 +3219,9 @@@ void diff_setup_done(struct diff_option { int count = 0; + if (options->set_default) + options->set_default(options); + if (options->output_format & DIFF_FORMAT_NAME) count++; if (options->output_format & DIFF_FORMAT_NAME_STATUS) @@@ -3503,93 -3500,6 +3506,93 @@@ static int parse_submodule_opt(struct d return 1; } +static const char diff_status_letters[] = { + DIFF_STATUS_ADDED, + DIFF_STATUS_COPIED, + DIFF_STATUS_DELETED, + DIFF_STATUS_MODIFIED, + DIFF_STATUS_RENAMED, + DIFF_STATUS_TYPE_CHANGED, + DIFF_STATUS_UNKNOWN, + DIFF_STATUS_UNMERGED, + DIFF_STATUS_FILTER_AON, + DIFF_STATUS_FILTER_BROKEN, + '\0', +}; + +static unsigned int filter_bit['Z' + 1]; + +static void prepare_filter_bits(void) +{ + int i; + + if (!filter_bit[DIFF_STATUS_ADDED]) { + for (i = 0; diff_status_letters[i]; i++) + filter_bit[(int) diff_status_letters[i]] = (1 << i); + } +} + +static unsigned filter_bit_tst(char status, const struct diff_options *opt) +{ + return opt->filter & filter_bit[(int) status]; +} + +static int parse_diff_filter_opt(const char *optarg, struct diff_options *opt) +{ + int i, optch; + + prepare_filter_bits(); + + /* + * If there is a negation e.g. 'd' in the input, and we haven't + * initialized the filter field with another --diff-filter, start + * from full set of bits, except for AON. + */ + if (!opt->filter) { + for (i = 0; (optch = optarg[i]) != '\0'; i++) { + if (optch < 'a' || 'z' < optch) + continue; + opt->filter = (1 << (ARRAY_SIZE(diff_status_letters) - 1)) - 1; + opt->filter &= ~filter_bit[DIFF_STATUS_FILTER_AON]; + break; + } + } + + for (i = 0; (optch = optarg[i]) != '\0'; i++) { + unsigned int bit; + int negate; + + if ('a' <= optch && optch <= 'z') { + negate = 1; + optch = toupper(optch); + } else { + negate = 0; + } + + bit = (0 <= optch && optch <= 'Z') ? filter_bit[optch] : 0; + if (!bit) + return optarg[i]; + if (negate) + opt->filter &= ~bit; + else + opt->filter |= bit; + } + return 0; +} + +/* Used only by "diff-files" and "diff --no-index" */ +void handle_deprecated_show_diff_q(struct diff_options *opt) +{ + warning("'diff -q' and 'diff-files -q' are deprecated."); + warning("Use 'diff --diff-filter=d' instead to ignore deleted filepairs."); + parse_diff_filter_opt("d", opt); +} + +static void enable_patch_output(int *fmt) { + *fmt &= ~DIFF_FORMAT_NO_OUTPUT; + *fmt |= DIFF_FORMAT_PATCH; +} + int diff_opt_parse(struct diff_options *options, const char **av, int ac) { const char *arg = av[0]; @@@ -3597,15 -3507,15 +3600,15 @@@ int argcount; /* Output format options */ - if (!strcmp(arg, "-p") || !strcmp(arg, "-u") || !strcmp(arg, "--patch")) - options->output_format |= DIFF_FORMAT_PATCH; - else if (opt_arg(arg, 'U', "unified", &options->context)) - options->output_format |= DIFF_FORMAT_PATCH; + if (!strcmp(arg, "-p") || !strcmp(arg, "-u") || !strcmp(arg, "--patch") + || opt_arg(arg, 'U', "unified", &options->context)) + enable_patch_output(&options->output_format); else if (!strcmp(arg, "--raw")) options->output_format |= DIFF_FORMAT_RAW; - else if (!strcmp(arg, "--patch-with-raw")) - options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_RAW; - else if (!strcmp(arg, "--numstat")) + else if (!strcmp(arg, "--patch-with-raw")) { + enable_patch_output(&options->output_format); + options->output_format |= DIFF_FORMAT_RAW; + } else if (!strcmp(arg, "--numstat")) options->output_format |= DIFF_FORMAT_NUMSTAT; else if (!strcmp(arg, "--shortstat")) options->output_format |= DIFF_FORMAT_SHORTSTAT; @@@ -3627,14 -3537,13 +3630,14 @@@ options->output_format |= DIFF_FORMAT_CHECKDIFF; else if (!strcmp(arg, "--summary")) options->output_format |= DIFF_FORMAT_SUMMARY; - else if (!strcmp(arg, "--patch-with-stat")) - options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_DIFFSTAT; - else if (!strcmp(arg, "--name-only")) + else if (!strcmp(arg, "--patch-with-stat")) { + enable_patch_output(&options->output_format); + options->output_format |= DIFF_FORMAT_DIFFSTAT; + } else if (!strcmp(arg, "--name-only")) options->output_format |= DIFF_FORMAT_NAME; else if (!strcmp(arg, "--name-status")) options->output_format |= DIFF_FORMAT_NAME_STATUS; - else if (!strcmp(arg, "-s")) + else if (!strcmp(arg, "-s") || !strcmp(arg, "--no-patch")) options->output_format |= DIFF_FORMAT_NO_OUTPUT; else if (!prefixcmp(arg, "--stat")) /* --stat, --stat-width, --stat-name-width, or --stat-count */ @@@ -3687,8 -3596,6 +3690,8 @@@ DIFF_XDL_SET(options, IGNORE_WHITESPACE_CHANGE); else if (!strcmp(arg, "--ignore-space-at-eol")) DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL); + else if (!strcmp(arg, "--ignore-blank-lines")) + DIFF_XDL_SET(options, IGNORE_BLANK_LINES); else if (!strcmp(arg, "--patience")) options->xdl_opts = DIFF_WITH_ALG(options, PATIENCE_DIFF); else if (!strcmp(arg, "--histogram")) @@@ -3707,7 -3614,7 +3710,7 @@@ /* flags options */ else if (!strcmp(arg, "--binary")) { - options->output_format |= DIFF_FORMAT_PATCH; + enable_patch_output(&options->output_format); DIFF_OPT_SET(options, BINARY); } else if (!strcmp(arg, "--full-index")) @@@ -3814,10 -3721,7 +3817,10 @@@ return argcount; } else if ((argcount = parse_long_opt("diff-filter", av, &optarg))) { - options->filter = optarg; + int offending = parse_diff_filter_opt(optarg, options); + if (offending) + die("unknown change class '%c' in --diff-filter=%s", + offending, optarg); return argcount; } else if (!strcmp(arg, "--abbrev")) @@@ -4549,7 -4453,7 +4552,7 @@@ void diff_flush(struct diff_options *op DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) { /* * run diff_flush_patch for the exit status. setting - * options->file to /dev/null should be safe, becaue we + * options->file to /dev/null should be safe, because we * aren't supposed to produce any output anyway. */ if (options->close_file) @@@ -4609,32 -4513,27 +4612,32 @@@ free_queue } } -static void diffcore_apply_filter(const char *filter) +static int match_filter(const struct diff_options *options, const struct diff_filepair *p) +{ + return (((p->status == DIFF_STATUS_MODIFIED) && + ((p->score && + filter_bit_tst(DIFF_STATUS_FILTER_BROKEN, options)) || + (!p->score && + filter_bit_tst(DIFF_STATUS_MODIFIED, options)))) || + ((p->status != DIFF_STATUS_MODIFIED) && + filter_bit_tst(p->status, options))); +} + +static void diffcore_apply_filter(struct diff_options *options) { int i; struct diff_queue_struct *q = &diff_queued_diff; struct diff_queue_struct outq; + DIFF_QUEUE_CLEAR(&outq); - if (!filter) + if (!options->filter) return; - if (strchr(filter, DIFF_STATUS_FILTER_AON)) { + if (filter_bit_tst(DIFF_STATUS_FILTER_AON, options)) { int found; for (i = found = 0; !found && i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - if (((p->status == DIFF_STATUS_MODIFIED) && - ((p->score && - strchr(filter, DIFF_STATUS_FILTER_BROKEN)) || - (!p->score && - strchr(filter, DIFF_STATUS_MODIFIED)))) || - ((p->status != DIFF_STATUS_MODIFIED) && - strchr(filter, p->status))) + if (match_filter(options, q->queue[i])) found++; } if (found) @@@ -4652,7 -4551,14 +4655,7 @@@ /* Only the matching ones */ for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; - - if (((p->status == DIFF_STATUS_MODIFIED) && - ((p->score && - strchr(filter, DIFF_STATUS_FILTER_BROKEN)) || - (!p->score && - strchr(filter, DIFF_STATUS_MODIFIED)))) || - ((p->status != DIFF_STATUS_MODIFIED) && - strchr(filter, p->status))) + if (match_filter(options, p)) diff_q(&outq, p); else diff_free_filepair(p); @@@ -4759,7 -4665,7 +4762,7 @@@ void diffcore_std(struct diff_options * if (!options->found_follow) /* See try_to_follow_renames() in tree-diff.c */ diff_resolve_rename_copy(); - diffcore_apply_filter(options->filter); + diffcore_apply_filter(options); if (diff_queued_diff.nr && !DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) DIFF_OPT_SET(options, HAS_CHANGES); diff --combined diff.h index 44092c2176,e995ae12fe..e34232501e --- a/diff.h +++ b/diff.h @@@ -5,7 -5,6 +5,7 @@@ #define DIFF_H #include "tree-walk.h" +#include "pathspec.h" struct rev_info; struct diff_options; @@@ -88,8 -87,9 +88,9 @@@ typedef struct strbuf *(*diff_prefix_fn #define DIFF_OPT_PICKAXE_IGNORE_CASE (1 << 30) #define DIFF_OPT_TST(opts, flag) ((opts)->flags & DIFF_OPT_##flag) - #define DIFF_OPT_SET(opts, flag) ((opts)->flags |= DIFF_OPT_##flag) - #define DIFF_OPT_CLR(opts, flag) ((opts)->flags &= ~DIFF_OPT_##flag) + #define DIFF_OPT_TOUCHED(opts, flag) ((opts)->touched_flags & DIFF_OPT_##flag) + #define DIFF_OPT_SET(opts, flag) (((opts)->flags |= DIFF_OPT_##flag),((opts)->touched_flags |= DIFF_OPT_##flag)) + #define DIFF_OPT_CLR(opts, flag) (((opts)->flags &= ~DIFF_OPT_##flag),((opts)->touched_flags |= DIFF_OPT_##flag)) #define DIFF_XDL_TST(opts, flag) ((opts)->xdl_opts & XDF_##flag) #define DIFF_XDL_SET(opts, flag) ((opts)->xdl_opts |= XDF_##flag) #define DIFF_XDL_CLR(opts, flag) ((opts)->xdl_opts &= ~XDF_##flag) @@@ -104,15 -104,13 +105,16 @@@ enum diff_words_type }; struct diff_options { - const char *filter; const char *orderfile; const char *pickaxe; const char *single_follow; const char *a_prefix, *b_prefix; unsigned flags; + unsigned touched_flags; + + /* diff-filter bits */ + unsigned int filter; + int use_color; int context; int interhunkcontext; @@@ -149,6 -147,8 +151,8 @@@ /* to support internal diff recursion by --follow hack*/ int found_follow; + void (*set_default)(struct diff_options *); + FILE *file; int close_file; @@@ -183,6 -183,8 +187,6 @@@ const char *diff_line_prefix(struct dif extern const char mime_boundary_leader[]; -extern void diff_tree_setup_paths(const char **paths, struct diff_options *); -extern void diff_tree_release_paths(struct diff_options *); extern int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt); extern int diff_tree_sha1(const unsigned char *old, const unsigned char *new, @@@ -340,8 -342,6 +344,8 @@@ extern int parse_rename_score(const cha extern long parse_algorithm_value(const char *value); +extern void handle_deprecated_show_diff_q(struct diff_options *); + extern int print_stat_summary(FILE *fp, int files, int insertions, int deletions); extern void setup_diff_pager(struct diff_options *); diff --combined object.c index 5f792cbfd3,c8ffc9e006..584f7acb36 --- a/object.c +++ b/object.c @@@ -43,17 -43,16 +43,17 @@@ int type_from_string(const char *str die("invalid object type \"%s\"", str); } -static unsigned int hash_obj(struct object *obj, unsigned int n) +static unsigned int hash_obj(const unsigned char *sha1, unsigned int n) { unsigned int hash; - memcpy(&hash, obj->sha1, sizeof(unsigned int)); - return hash % n; + memcpy(&hash, sha1, sizeof(unsigned int)); + /* Assumes power-of-2 hash sizes in grow_object_hash */ + return hash & (n - 1); } static void insert_obj_hash(struct object *obj, struct object **hash, unsigned int size) { - unsigned int j = hash_obj(obj, size); + unsigned int j = hash_obj(obj->sha1, size); while (hash[j]) { j++; @@@ -63,15 -62,22 +63,15 @@@ hash[j] = obj; } -static unsigned int hashtable_index(const unsigned char *sha1) -{ - unsigned int i; - memcpy(&i, sha1, sizeof(unsigned int)); - return i % obj_hash_size; -} - struct object *lookup_object(const unsigned char *sha1) { - unsigned int i; + unsigned int i, first; struct object *obj; if (!obj_hash) return NULL; - i = hashtable_index(sha1); + first = i = hash_obj(sha1, obj_hash_size); while ((obj = obj_hash[i]) != NULL) { if (!hashcmp(sha1, obj->sha1)) break; @@@ -79,26 -85,12 +79,26 @@@ if (i == obj_hash_size) i = 0; } + if (obj && i != first) { + /* + * Move object to where we started to look for it so + * that we do not need to walk the hash table the next + * time we look for it. + */ + struct object *tmp = obj_hash[i]; + obj_hash[i] = obj_hash[first]; + obj_hash[first] = tmp; + } return obj; } static void grow_object_hash(void) { int i; + /* + * Note that this size must always be power-of-2 to match hash_obj + * above. + */ int new_hash_size = obj_hash_size < 32 ? 32 : 2 * obj_hash_size; struct object **new_hash; @@@ -143,7 -135,7 +143,7 @@@ struct object *lookup_unknown_object(co struct object *parse_object_buffer(const unsigned char *sha1, enum object_type type, unsigned long size, void *buffer, int *eaten_p) { struct object *obj; - int eaten = 0; + *eaten_p = 0; obj = NULL; if (type == OBJ_BLOB) { @@@ -162,7 -154,7 +162,7 @@@ if (!tree->object.parsed) { if (parse_tree_buffer(tree, buffer, size)) return NULL; - eaten = 1; + *eaten_p = 1; } } } else if (type == OBJ_COMMIT) { @@@ -172,7 -164,7 +172,7 @@@ return NULL; if (!commit->buffer) { commit->buffer = buffer; - eaten = 1; + *eaten_p = 1; } obj = &commit->object; } @@@ -189,6 -181,7 +189,6 @@@ } if (obj && obj->type == OBJ_NONE) obj->type = type; - *eaten_p = eaten; return obj; } @@@ -262,23 -255,11 +262,21 @@@ int object_list_contains(struct object_ return 0; } - void add_object_array(struct object *obj, const char *name, struct object_array *array) - { - add_object_array_with_mode(obj, name, array, S_IFINVALID); - } - -static void add_object_array_with_mode_context(struct object *obj, const char *name, struct object_array *array, unsigned mode, struct object_context *context) +/* + * A zero-length string to which object_array_entry::name can be + * initialized without requiring a malloc/free. + */ +static char object_array_slopbuf[1]; + - void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode) ++static void add_object_array_with_mode_context(struct object *obj, const char *name, ++ struct object_array *array, ++ unsigned mode, ++ struct object_context *context) { unsigned nr = array->nr; unsigned alloc = array->alloc; struct object_array_entry *objects = array->objects; + struct object_array_entry *entry; if (nr >= alloc) { alloc = (alloc + 32) * 2; @@@ -286,67 -267,47 +284,86 @@@ array->alloc = alloc; array->objects = objects; } - objects[nr].item = obj; - objects[nr].name = name; - objects[nr].mode = mode; - objects[nr].context = context; + entry = &objects[nr]; + entry->item = obj; + if (!name) + entry->name = NULL; + else if (!*name) + /* Use our own empty string instead of allocating one: */ + entry->name = object_array_slopbuf; + else + entry->name = xstrdup(name); + entry->mode = mode; ++ entry->context = context; array->nr = ++nr; } + void add_object_array(struct object *obj, const char *name, struct object_array *array) + { + add_object_array_with_mode(obj, name, array, S_IFINVALID); + } + + void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode) + { + add_object_array_with_mode_context(obj, name, array, mode, NULL); + } + + void add_object_array_with_context(struct object *obj, const char *name, struct object_array *array, struct object_context *context) + { + if (context) + add_object_array_with_mode_context(obj, name, array, context->mode, context); + else + add_object_array_with_mode_context(obj, name, array, S_IFINVALID, context); + } + -void object_array_remove_duplicates(struct object_array *array) +void object_array_filter(struct object_array *array, + object_array_each_func_t want, void *cb_data) { - unsigned int ref, src, dst; + unsigned nr = array->nr, src, dst; struct object_array_entry *objects = array->objects; - for (ref = 0; ref + 1 < array->nr; ref++) { - for (src = ref + 1, dst = src; - src < array->nr; - src++) { - if (!strcmp(objects[ref].name, objects[src].name)) - continue; + for (src = dst = 0; src < nr; src++) { + if (want(&objects[src], cb_data)) { if (src != dst) objects[dst] = objects[src]; dst++; + } else { + if (objects[src].name != object_array_slopbuf) + free(objects[src].name); + } + } + array->nr = dst; +} + +/* + * Return true iff array already contains an entry with name. + */ +static int contains_name(struct object_array *array, const char *name) +{ + unsigned nr = array->nr, i; + struct object_array_entry *object = array->objects; + + for (i = 0; i < nr; i++, object++) + if (!strcmp(object->name, name)) + return 1; + return 0; +} + +void object_array_remove_duplicates(struct object_array *array) +{ + unsigned nr = array->nr, src; + struct object_array_entry *objects = array->objects; + + array->nr = 0; + for (src = 0; src < nr; src++) { + if (!contains_name(array, objects[src].name)) { + if (src != array->nr) + objects[array->nr] = objects[src]; + array->nr++; + } else { + if (objects[src].name != object_array_slopbuf) + free(objects[src].name); } - array->nr = dst; } } diff --combined object.h index 2ff68c52dd,695847dfd4..dc5df8ce1d --- a/object.h +++ b/object.h @@@ -11,14 -11,9 +11,15 @@@ struct object_array unsigned int alloc; struct object_array_entry { struct object *item; - const char *name; + /* + * name or NULL. If non-NULL, the memory pointed to + * is owned by this object *except* if it points at + * object_array_slopbuf, which is a static copy of the + * empty string. + */ + char *name; unsigned mode; + struct object_context *context; } *objects; }; @@@ -91,22 -86,8 +92,23 @@@ int object_list_contains(struct object_ /* Object array handling .. */ void add_object_array(struct object *obj, const char *name, struct object_array *array); void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode); + void add_object_array_with_context(struct object *obj, const char *name, struct object_array *array, struct object_context *context); -void object_array_remove_duplicates(struct object_array *); + +typedef int (*object_array_each_func_t)(struct object_array_entry *, void *); + +/* + * Apply want to each entry in array, retaining only the entries for + * which the function returns true. Preserve the order of the entries + * that are retained. + */ +void object_array_filter(struct object_array *array, + object_array_each_func_t want, void *cb_data); + +/* + * Remove from array all but the first entry with a given name. + * Warning: this function uses an O(N^2) algorithm. + */ +void object_array_remove_duplicates(struct object_array *array); void clear_object_flags(unsigned flags); diff --combined t/t4030-diff-textconv.sh index f75f46f92d,0ebb028ccc..aad6c7f78d --- a/t/t4030-diff-textconv.sh +++ b/t/t4030-diff-textconv.sh @@@ -58,6 -58,12 +58,12 @@@ test_expect_success 'diff produces text test_cmp expect.text actual ' + test_expect_success 'show commit produces text' ' + git show HEAD >diff && + find_diff actual && + test_cmp expect.text actual + ' + test_expect_success 'diff-tree produces binary' ' git diff-tree -p HEAD^ HEAD >diff && find_diff actual && @@@ -84,6 -90,24 +90,24 @@@ test_expect_success 'status -v produce git reset --soft HEAD@{1} ' + test_expect_success 'show blob produces binary' ' + git show HEAD:file >actual && + printf "\\0\\n\\01\\n" >expect && + test_cmp expect actual + ' + + test_expect_success 'show --textconv blob produces text' ' + git show --textconv HEAD:file >actual && + printf "0\\n1\\n" >expect && + test_cmp expect actual + ' + + test_expect_success 'show --no-textconv blob produces binary' ' + git show --no-textconv HEAD:file >actual && + printf "\\0\\n\\01\\n" >expect && + test_cmp expect actual + ' + test_expect_success 'grep-diff (-G) operates on textconv data (add)' ' echo one >expect && git log --root --format=%s -G0 >actual && @@@ -139,10 -163,12 +163,10 @@@ index 0000000..67be42 +frotz \ No newline at end of file EOF -# make a symlink the hard way that works on symlink-challenged file systems + test_expect_success 'textconv does not act on symlinks' ' - printf frotz > file && - git add file && - git ls-files -s | sed -e s/100644/120000/ | - git update-index --index-info && + rm -f file && + test_ln_s_add frotz file && git commit -m typechange && git show >diff && find_diff actual && diff --combined t/t8007-cat-file-textconv.sh index b95e102891,83c663678f..eacd49ade6 --- a/t/t8007-cat-file-textconv.sh +++ b/t/t8007-cat-file-textconv.sh @@@ -12,7 -12,9 +12,7 @@@ chmod +x helpe test_expect_success 'setup ' ' echo "bin: test" >one.bin && - if test_have_prereq SYMLINKS; then - ln -s one.bin symlink.bin - fi && + test_ln_s_add one.bin symlink.bin && git add . && GIT_AUTHOR_NAME=Number1 git commit -a -m First --date="2010-01-01 18:00:00" && echo "bin: test version 2" >one.bin && @@@ -20,11 -22,11 +20,11 @@@ ' cat >expected <result + git cat-file --textconv :one.bin >result && test_cmp expected result ' @@@ -34,10 -36,6 +34,6 @@@ test_expect_success 'setup textconv fil git config diff.test.cachetextconv false ' - cat >expected <result && test_cmp expected result @@@ -70,26 -68,20 +66,20 @@@ test_expect_success 'cat-file --textcon test_cmp expected result ' -test_expect_success SYMLINKS 'cat-file without --textconv (symlink)' ' +test_expect_success 'cat-file without --textconv (symlink)' ' + printf "%s" "one.bin" >expected && git cat-file blob :symlink.bin >result && - printf "%s" "one.bin" >expected test_cmp expected result ' -test_expect_success SYMLINKS 'cat-file --textconv on index (symlink)' ' +test_expect_success 'cat-file --textconv on index (symlink)' ' - ! git cat-file --textconv :symlink.bin 2>result && - cat >expected <<\EOF && - fatal: git cat-file --textconv: unable to run textconv on :symlink.bin - EOF + git cat-file --textconv :symlink.bin >result && test_cmp expected result ' -test_expect_success SYMLINKS 'cat-file --textconv on HEAD (symlink)' ' +test_expect_success 'cat-file --textconv on HEAD (symlink)' ' - ! git cat-file --textconv HEAD:symlink.bin 2>result && - cat >expected <result && test_cmp expected result '