X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=builtin-grep.c;h=ad7dc00cde4e8e08ef35b313525781c135357df3;hb=747fa12cef73b6ca04fffaddaad7326cf546cdea;hp=743ca8c692094a2089de1fbf45cfe65f8acef729;hpb=4f12d529abbf233e1df93e7ffa5f2719005a2258;p=git.git diff --git a/builtin-grep.c b/builtin-grep.c index 743ca8c69..ad7dc00cd 100644 --- a/builtin-grep.c +++ b/builtin-grep.c @@ -11,6 +11,7 @@ #include "tree-walk.h" #include "builtin.h" #include +#include "grep.h" #include #include @@ -82,554 +83,40 @@ static int pathspec_matches(const char **paths, const char *name) return 0; } -enum grep_pat_token { - GREP_PATTERN, - GREP_AND, - GREP_OPEN_PAREN, - GREP_CLOSE_PAREN, - GREP_NOT, - GREP_OR, -}; - -struct grep_pat { - struct grep_pat *next; - const char *origin; - int no; - enum grep_pat_token token; - const char *pattern; - regex_t regexp; -}; - -enum grep_expr_node { - GREP_NODE_ATOM, - GREP_NODE_NOT, - GREP_NODE_AND, - GREP_NODE_OR, -}; - -struct grep_expr { - enum grep_expr_node node; - union { - struct grep_pat *atom; - struct grep_expr *unary; - struct { - struct grep_expr *left; - struct grep_expr *right; - } binary; - } u; -}; - -struct grep_opt { - struct grep_pat *pattern_list; - struct grep_pat **pattern_tail; - struct grep_expr *pattern_expression; - regex_t regexp; - unsigned linenum:1; - unsigned invert:1; - unsigned name_only:1; - unsigned unmatch_name_only:1; - unsigned count:1; - unsigned word_regexp:1; - unsigned fixed:1; -#define GREP_BINARY_DEFAULT 0 -#define GREP_BINARY_NOMATCH 1 -#define GREP_BINARY_TEXT 2 - unsigned binary:2; - unsigned extended:1; - int regflags; - unsigned pre_context; - unsigned post_context; -}; - -static void add_pattern(struct grep_opt *opt, const char *pat, - const char *origin, int no, enum grep_pat_token t) -{ - struct grep_pat *p = xcalloc(1, sizeof(*p)); - p->pattern = pat; - p->origin = origin; - p->no = no; - p->token = t; - *opt->pattern_tail = p; - opt->pattern_tail = &p->next; - p->next = NULL; -} - -static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) -{ - int err = regcomp(&p->regexp, p->pattern, opt->regflags); - if (err) { - char errbuf[1024]; - char where[1024]; - if (p->no) - sprintf(where, "In '%s' at %d, ", - p->origin, p->no); - else if (p->origin) - sprintf(where, "%s, ", p->origin); - else - where[0] = 0; - regerror(err, &p->regexp, errbuf, 1024); - regfree(&p->regexp); - die("%s'%s': %s", where, p->pattern, errbuf); - } -} - -#if DEBUG -static inline void indent(int in) -{ - int i; - for (i = 0; i < in; i++) putchar(' '); -} - -static void dump_pattern_exp(struct grep_expr *x, int in) -{ - switch (x->node) { - case GREP_NODE_ATOM: - indent(in); - puts(x->u.atom->pattern); - break; - case GREP_NODE_NOT: - indent(in); - puts("--not"); - dump_pattern_exp(x->u.unary, in+1); - break; - case GREP_NODE_AND: - dump_pattern_exp(x->u.binary.left, in+1); - indent(in); - puts("--and"); - dump_pattern_exp(x->u.binary.right, in+1); - break; - case GREP_NODE_OR: - dump_pattern_exp(x->u.binary.left, in+1); - indent(in); - puts("--or"); - dump_pattern_exp(x->u.binary.right, in+1); - break; - } -} - -static void looking_at(const char *msg, struct grep_pat **list) -{ - struct grep_pat *p = *list; - fprintf(stderr, "%s: looking at ", msg); - if (!p) - fprintf(stderr, "empty\n"); - else - fprintf(stderr, "<%s>\n", p->pattern); -} -#else -#define looking_at(a,b) do {} while(0) -#endif - -static struct grep_expr *compile_pattern_expr(struct grep_pat **); -static struct grep_expr *compile_pattern_atom(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x; - - looking_at("atom", list); - - p = *list; - switch (p->token) { - case GREP_PATTERN: /* atom */ - x = xcalloc(1, sizeof (struct grep_expr)); - x->node = GREP_NODE_ATOM; - x->u.atom = p; - *list = p->next; - return x; - case GREP_OPEN_PAREN: - *list = p->next; - x = compile_pattern_expr(list); - if (!x) - return NULL; - if (!*list || (*list)->token != GREP_CLOSE_PAREN) - die("unmatched parenthesis"); - *list = (*list)->next; - return x; - default: - return NULL; - } -} - -static struct grep_expr *compile_pattern_not(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x; - - looking_at("not", list); - - p = *list; - switch (p->token) { - case GREP_NOT: - if (!p->next) - die("--not not followed by pattern expression"); - *list = p->next; - x = xcalloc(1, sizeof (struct grep_expr)); - x->node = GREP_NODE_NOT; - x->u.unary = compile_pattern_not(list); - if (!x->u.unary) - die("--not followed by non pattern expression"); - return x; - default: - return compile_pattern_atom(list); - } -} - -static struct grep_expr *compile_pattern_and(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x, *y, *z; - - looking_at("and", list); - - x = compile_pattern_not(list); - p = *list; - if (p && p->token == GREP_AND) { - if (!p->next) - die("--and not followed by pattern expression"); - *list = p->next; - y = compile_pattern_and(list); - if (!y) - die("--and not followed by pattern expression"); - z = xcalloc(1, sizeof (struct grep_expr)); - z->node = GREP_NODE_AND; - z->u.binary.left = x; - z->u.binary.right = y; - return z; - } - return x; -} - -static struct grep_expr *compile_pattern_or(struct grep_pat **list) -{ - struct grep_pat *p; - struct grep_expr *x, *y, *z; - - looking_at("or", list); - - x = compile_pattern_and(list); - p = *list; - if (x && p && p->token != GREP_CLOSE_PAREN) { - y = compile_pattern_or(list); - if (!y) - die("not a pattern expression %s", p->pattern); - z = xcalloc(1, sizeof (struct grep_expr)); - z->node = GREP_NODE_OR; - z->u.binary.left = x; - z->u.binary.right = y; - return z; - } - return x; -} - -static struct grep_expr *compile_pattern_expr(struct grep_pat **list) -{ - looking_at("expr", list); - - return compile_pattern_or(list); -} - -static void compile_patterns(struct grep_opt *opt) -{ - struct grep_pat *p; - - /* First compile regexps */ - for (p = opt->pattern_list; p; p = p->next) { - if (p->token == GREP_PATTERN) - compile_regexp(p, opt); - else - opt->extended = 1; - } - - if (!opt->extended) - return; - - /* Then bundle them up in an expression. - * A classic recursive descent parser would do. - */ - p = opt->pattern_list; - opt->pattern_expression = compile_pattern_expr(&p); -#if DEBUG - dump_pattern_exp(opt->pattern_expression, 0); -#endif - if (p) - die("incomplete pattern expression: %s", p->pattern); -} - -static char *end_of_line(char *cp, unsigned long *left) -{ - unsigned long l = *left; - while (l && *cp != '\n') { - l--; - cp++; - } - *left = l; - return cp; -} - -static int word_char(char ch) -{ - return isalnum(ch) || ch == '_'; -} - -static void show_line(struct grep_opt *opt, const char *bol, const char *eol, - const char *name, unsigned lno, char sign) -{ - printf("%s%c", name, sign); - if (opt->linenum) - printf("%d%c", lno, sign); - printf("%.*s\n", (int)(eol-bol), bol); -} - -/* - * NEEDSWORK: share code with diff.c - */ -#define FIRST_FEW_BYTES 8000 -static int buffer_is_binary(const char *ptr, unsigned long size) -{ - if (FIRST_FEW_BYTES < size) - size = FIRST_FEW_BYTES; - if (memchr(ptr, 0, size)) - return 1; - return 0; -} - -static int fixmatch(const char *pattern, char *line, regmatch_t *match) -{ - char *hit = strstr(line, pattern); - if (!hit) { - match->rm_so = match->rm_eo = -1; - return REG_NOMATCH; - } - else { - match->rm_so = hit - line; - match->rm_eo = match->rm_so + strlen(pattern); - return 0; - } -} - -static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol) -{ - int hit = 0; - regmatch_t pmatch[10]; - - if (!opt->fixed) { - regex_t *exp = &p->regexp; - hit = !regexec(exp, bol, ARRAY_SIZE(pmatch), - pmatch, 0); - } - else { - hit = !fixmatch(p->pattern, bol, pmatch); - } - - if (hit && opt->word_regexp) { - /* Match beginning must be either - * beginning of the line, or at word - * boundary (i.e. the last char must - * not be alnum or underscore). - */ - if ((pmatch[0].rm_so < 0) || - (eol - bol) <= pmatch[0].rm_so || - (pmatch[0].rm_eo < 0) || - (eol - bol) < pmatch[0].rm_eo) - die("regexp returned nonsense"); - if (pmatch[0].rm_so != 0 && - word_char(bol[pmatch[0].rm_so-1])) - hit = 0; - if (pmatch[0].rm_eo != (eol-bol) && - word_char(bol[pmatch[0].rm_eo])) - hit = 0; - } - return hit; -} - -static int match_expr_eval(struct grep_opt *opt, - struct grep_expr *x, - char *bol, char *eol) -{ - switch (x->node) { - case GREP_NODE_ATOM: - return match_one_pattern(opt, x->u.atom, bol, eol); - break; - case GREP_NODE_NOT: - return !match_expr_eval(opt, x->u.unary, bol, eol); - case GREP_NODE_AND: - return (match_expr_eval(opt, x->u.binary.left, bol, eol) && - match_expr_eval(opt, x->u.binary.right, bol, eol)); - case GREP_NODE_OR: - return (match_expr_eval(opt, x->u.binary.left, bol, eol) || - match_expr_eval(opt, x->u.binary.right, bol, eol)); - } - die("Unexpected node type (internal error) %d\n", x->node); -} - -static int match_expr(struct grep_opt *opt, char *bol, char *eol) -{ - struct grep_expr *x = opt->pattern_expression; - return match_expr_eval(opt, x, bol, eol); -} - -static int match_line(struct grep_opt *opt, char *bol, char *eol) -{ - struct grep_pat *p; - if (opt->extended) - return match_expr(opt, bol, eol); - for (p = opt->pattern_list; p; p = p->next) { - if (match_one_pattern(opt, p, bol, eol)) - return 1; - } - return 0; -} - -static int grep_buffer(struct grep_opt *opt, const char *name, - char *buf, unsigned long size) -{ - char *bol = buf; - unsigned long left = size; - unsigned lno = 1; - struct pre_context_line { - char *bol; - char *eol; - } *prev = NULL, *pcl; - unsigned last_hit = 0; - unsigned last_shown = 0; - int binary_match_only = 0; - const char *hunk_mark = ""; - unsigned count = 0; - - if (buffer_is_binary(buf, size)) { - switch (opt->binary) { - case GREP_BINARY_DEFAULT: - binary_match_only = 1; - break; - case GREP_BINARY_NOMATCH: - return 0; /* Assume unmatch */ - break; - default: - break; - } - } - - if (opt->pre_context) - prev = xcalloc(opt->pre_context, sizeof(*prev)); - if (opt->pre_context || opt->post_context) - hunk_mark = "--\n"; - - while (left) { - char *eol, ch; - int hit = 0; - - eol = end_of_line(bol, &left); - ch = *eol; - *eol = 0; - - hit = match_line(opt, bol, eol); - - /* "grep -v -e foo -e bla" should list lines - * that do not have either, so inversion should - * be done outside. - */ - if (opt->invert) - hit = !hit; - if (opt->unmatch_name_only) { - if (hit) - return 0; - goto next_line; - } - if (hit) { - count++; - if (binary_match_only) { - printf("Binary file %s matches\n", name); - return 1; - } - if (opt->name_only) { - printf("%s\n", name); - return 1; - } - /* Hit at this line. If we haven't shown the - * pre-context lines, we would need to show them. - * When asked to do "count", this still show - * the context which is nonsense, but the user - * deserves to get that ;-). - */ - if (opt->pre_context) { - unsigned from; - if (opt->pre_context < lno) - from = lno - opt->pre_context; - else - from = 1; - if (from <= last_shown) - from = last_shown + 1; - if (last_shown && from != last_shown + 1) - printf(hunk_mark); - while (from < lno) { - pcl = &prev[lno-from-1]; - show_line(opt, pcl->bol, pcl->eol, - name, from, '-'); - from++; - } - last_shown = lno-1; - } - if (last_shown && lno != last_shown + 1) - printf(hunk_mark); - if (!opt->count) - show_line(opt, bol, eol, name, lno, ':'); - last_shown = last_hit = lno; - } - else if (last_hit && - lno <= last_hit + opt->post_context) { - /* If the last hit is within the post context, - * we need to show this line. - */ - if (last_shown && lno != last_shown + 1) - printf(hunk_mark); - show_line(opt, bol, eol, name, lno, '-'); - last_shown = lno; - } - if (opt->pre_context) { - memmove(prev+1, prev, - (opt->pre_context-1) * sizeof(*prev)); - prev->bol = bol; - prev->eol = eol; - } - - next_line: - *eol = ch; - bol = eol + 1; - if (!left) - break; - left--; - lno++; - } - - if (opt->unmatch_name_only) { - /* We did not see any hit, so we want to show this */ - printf("%s\n", name); - return 1; - } - - /* NEEDSWORK: - * The real "grep -c foo *.c" gives many "bar.c:0" lines, - * which feels mostly useless but sometimes useful. Maybe - * make it another option? For now suppress them. - */ - if (opt->count && count) - printf("%s:%u\n", name, count); - return !!last_hit; -} - -static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name) +static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name, int tree_name_len) { unsigned long size; char *data; char type[20]; + char *to_free = NULL; int hit; + data = read_sha1_file(sha1, type, &size); if (!data) { error("'%s': unable to read %s", name, sha1_to_hex(sha1)); return 0; } + if (opt->relative && opt->prefix_length) { + static char name_buf[PATH_MAX]; + char *cp; + int name_len = strlen(name) - opt->prefix_length + 1; + + if (!tree_name_len) + name += opt->prefix_length; + else { + if (ARRAY_SIZE(name_buf) <= name_len) + cp = to_free = xmalloc(name_len); + else + cp = name_buf; + memcpy(cp, name, tree_name_len); + strcpy(cp + tree_name_len, + name + tree_name_len + opt->prefix_length); + name = cp; + } + } hit = grep_buffer(opt, name, data, size); free(data); + free(to_free); return hit; } @@ -659,6 +146,8 @@ static int grep_file(struct grep_opt *opt, const char *filename) return 0; } close(i); + if (opt->relative && opt->prefix_length) + filename += opt->prefix_length; i = grep_buffer(opt, filename, data, st.st_size); free(data); return i; @@ -705,7 +194,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached) char *argptr = randarg; struct grep_pat *p; - if (opt->extended) + if (opt->extended || (opt->relative && opt->prefix_length)) return -1; len = nr = 0; push_arg("grep"); @@ -713,6 +202,8 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached) push_arg("-F"); if (opt->linenum) push_arg("-n"); + if (!opt->pathname) + push_arg("-h"); if (opt->regflags & REG_EXTENDED) push_arg("-E"); if (opt->regflags & REG_ICASE) @@ -830,10 +321,11 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached) if (!pathspec_matches(paths, ce->name)) continue; if (cached) - hit |= grep_sha1(opt, ce->sha1, ce->name); + hit |= grep_sha1(opt, ce->sha1, ce->name, 0); else hit |= grep_file(opt, ce->name); } + free_grep_patterns(opt); return hit; } @@ -845,11 +337,12 @@ static int grep_tree(struct grep_opt *opt, const char **paths, int hit = 0; struct name_entry entry; char *down; - char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100); + int tn_len = strlen(tree_name); + char *path_buf = xmalloc(PATH_MAX + tn_len + 100); - if (tree_name[0]) { - int offset = sprintf(path_buf, "%s:", tree_name); - down = path_buf + offset; + if (tn_len) { + tn_len = sprintf(path_buf, "%s:", tree_name); + down = path_buf + tn_len; strcat(down, base); } else { @@ -871,7 +364,7 @@ static int grep_tree(struct grep_opt *opt, const char **paths, if (!pathspec_matches(paths, down)) ; else if (S_ISREG(entry.mode)) - hit |= grep_sha1(opt, entry.sha1, path_buf); + hit |= grep_sha1(opt, entry.sha1, path_buf, tn_len); else if (S_ISDIR(entry.mode)) { char type[20]; struct tree_desc sub; @@ -891,9 +384,9 @@ static int grep_tree(struct grep_opt *opt, const char **paths, static int grep_object(struct grep_opt *opt, const char **paths, struct object *obj, const char *name) { - if (obj->type == TYPE_BLOB) - return grep_sha1(opt, obj->sha1, name); - if (obj->type == TYPE_COMMIT || obj->type == TYPE_TREE) { + if (obj->type == OBJ_BLOB) + return grep_sha1(opt, obj->sha1, name, 0); + if (obj->type == OBJ_COMMIT || obj->type == OBJ_TREE) { struct tree_desc tree; void *data; int hit; @@ -919,18 +412,20 @@ static const char emsg_missing_context_len[] = static const char emsg_missing_argument[] = "option requires an argument -%s"; -int cmd_grep(int argc, const char **argv, char **envp) +int cmd_grep(int argc, const char **argv, const char *prefix) { int hit = 0; int cached = 0; int seen_dashdash = 0; struct grep_opt opt; struct object_array list = { 0, 0, NULL }; - const char *prefix = setup_git_directory(); const char **paths = NULL; int i; memset(&opt, 0, sizeof(opt)); + opt.prefix_length = (prefix && *prefix) ? strlen(prefix) : 0; + opt.relative = 1; + opt.pathname = 1; opt.pattern_tail = &opt.pattern_list; opt.regflags = REG_NEWLINE; @@ -941,7 +436,7 @@ int cmd_grep(int argc, const char **argv, char **envp) * pattern, but then what follows it must be zero or more * valid refs up to the -- (if exists), and then existing * paths. If there is an explicit pattern, then the first - * unrecocnized non option is the beginning of the refs list + * unrecognized non option is the beginning of the refs list * that continues up to the -- (if exists), and then paths. */ @@ -990,10 +485,12 @@ int cmd_grep(int argc, const char **argv, char **envp) opt.linenum = 1; continue; } + if (!strcmp("-h", arg)) { + opt.pathname = 0; + continue; + } if (!strcmp("-H", arg)) { - /* We always show the pathname, so this - * is a noop. - */ + opt.pathname = 1; continue; } if (!strcmp("-l", arg) || @@ -1068,8 +565,9 @@ int cmd_grep(int argc, const char **argv, char **envp) /* ignore empty line like grep does */ if (!buf[0]) continue; - add_pattern(&opt, strdup(buf), argv[1], ++lno, - GREP_PATTERN); + append_grep_pattern(&opt, xstrdup(buf), + argv[1], ++lno, + GREP_PATTERN); } fclose(patterns); argv++; @@ -1077,33 +575,46 @@ int cmd_grep(int argc, const char **argv, char **envp) continue; } if (!strcmp("--not", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_NOT); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_NOT); continue; } if (!strcmp("--and", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_AND); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_AND); continue; } if (!strcmp("--or", arg)) continue; /* no-op */ if (!strcmp("(", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_OPEN_PAREN); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_OPEN_PAREN); continue; } if (!strcmp(")", arg)) { - add_pattern(&opt, arg, "command line", 0, GREP_CLOSE_PAREN); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_CLOSE_PAREN); + continue; + } + if (!strcmp("--all-match", arg)) { + opt.all_match = 1; continue; } if (!strcmp("-e", arg)) { if (1 < argc) { - add_pattern(&opt, argv[1], "-e option", 0, - GREP_PATTERN); + append_grep_pattern(&opt, argv[1], + "-e option", 0, + GREP_PATTERN); argv++; argc--; continue; } die(emsg_missing_argument, arg); } + if (!strcmp("--full-name", arg)) { + opt.relative = 0; + continue; + } if (!strcmp("--", arg)) { /* later processing wants to have this at argv[1] */ argv--; @@ -1115,8 +626,8 @@ int cmd_grep(int argc, const char **argv, char **envp) /* First unrecognized non-option token */ if (!opt.pattern_list) { - add_pattern(&opt, arg, "command line", 0, - GREP_PATTERN); + append_grep_pattern(&opt, arg, "command line", 0, + GREP_PATTERN); break; } else { @@ -1133,8 +644,7 @@ int cmd_grep(int argc, const char **argv, char **envp) die("no pattern given."); if ((opt.regflags != REG_NEWLINE) && opt.fixed) die("cannot mix --fixed-strings and regexp"); - if (!opt.fixed) - compile_patterns(&opt); + compile_grep_patterns(&opt); /* Check revs and then paths */ for (i = 1; i < argc; i++) { @@ -1162,8 +672,15 @@ int cmd_grep(int argc, const char **argv, char **envp) verify_filename(prefix, argv[j]); } - if (i < argc) + if (i < argc) { paths = get_pathspec(prefix, argv + i); + if (opt.prefix_length && opt.relative) { + /* Make sure we do not get outside of paths */ + for (i = 0; paths[i]; i++) + if (strncmp(prefix, paths[i], opt.prefix_length)) + die("git-grep: cannot generate relative filenames containing '..'"); + } + } else if (prefix) { paths = xcalloc(2, sizeof(const char *)); paths[0] = prefix; @@ -1182,5 +699,6 @@ int cmd_grep(int argc, const char **argv, char **envp) if (grep_object(&opt, paths, real_obj, list.objects[i].name)) hit = 1; } + free_grep_patterns(&opt); return !hit; }