diff options
Diffstat (limited to 'grep.c')
| -rw-r--r-- | grep.c | 200 |
1 files changed, 130 insertions, 70 deletions
@@ -7,6 +7,7 @@ void append_header_grep_pattern(struct grep_opt *opt, enum grep_header_field fie { struct grep_pat *p = xcalloc(1, sizeof(*p)); p->pattern = pat; + p->patternlen = strlen(pat); p->origin = "header"; p->no = 0; p->token = GREP_PATTERN_HEAD; @@ -19,8 +20,15 @@ void append_header_grep_pattern(struct grep_opt *opt, enum grep_header_field fie void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t) { + append_grep_pat(opt, pat, strlen(pat), origin, no, t); +} + +void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, + const char *origin, int no, enum grep_pat_token t) +{ struct grep_pat *p = xcalloc(1, sizeof(*p)); p->pattern = pat; + p->patternlen = patlen; p->origin = origin; p->no = no; p->token = t; @@ -44,8 +52,8 @@ struct grep_opt *grep_opt_dup(const struct grep_opt *opt) append_header_grep_pattern(ret, pat->field, pat->pattern); else - append_grep_pattern(ret, pat->pattern, pat->origin, - pat->no, pat->token); + append_grep_pat(ret, pat->pattern, pat->patternlen, + pat->origin, pat->no, pat->token); } return ret; @@ -181,29 +189,73 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list) return compile_pattern_or(list); } -void compile_grep_patterns(struct grep_opt *opt) +static struct grep_expr *grep_true_expr(void) +{ + struct grep_expr *z = xcalloc(1, sizeof(*z)); + z->node = GREP_NODE_TRUE; + return z; +} + +static struct grep_expr *grep_or_expr(struct grep_expr *left, struct grep_expr *right) +{ + struct grep_expr *z = xcalloc(1, sizeof(*z)); + z->node = GREP_NODE_OR; + z->u.binary.left = left; + z->u.binary.right = right; + return z; +} + +static struct grep_expr *prep_header_patterns(struct grep_opt *opt) { struct grep_pat *p; - struct grep_expr *header_expr = NULL; - - if (opt->header_list) { - p = opt->header_list; - header_expr = compile_pattern_expr(&p); - if (p) - die("incomplete pattern expression: %s", p->pattern); - for (p = opt->header_list; p; p = p->next) { - switch (p->token) { - case GREP_PATTERN: /* atom */ - case GREP_PATTERN_HEAD: - case GREP_PATTERN_BODY: - compile_regexp(p, opt); - break; - default: - opt->extended = 1; - break; - } + struct grep_expr *header_expr; + struct grep_expr *(header_group[GREP_HEADER_FIELD_MAX]); + enum grep_header_field fld; + + if (!opt->header_list) + return NULL; + p = opt->header_list; + for (p = opt->header_list; p; p = p->next) { + if (p->token != GREP_PATTERN_HEAD) + die("bug: a non-header pattern in grep header list."); + if (p->field < 0 || GREP_HEADER_FIELD_MAX <= p->field) + die("bug: unknown header field %d", p->field); + compile_regexp(p, opt); + } + + for (fld = 0; fld < GREP_HEADER_FIELD_MAX; fld++) + header_group[fld] = NULL; + + for (p = opt->header_list; p; p = p->next) { + struct grep_expr *h; + struct grep_pat *pp = p; + + h = compile_pattern_atom(&pp); + if (!h || pp != p->next) + die("bug: malformed header expr"); + if (!header_group[p->field]) { + header_group[p->field] = h; + continue; } + header_group[p->field] = grep_or_expr(h, header_group[p->field]); + } + + header_expr = NULL; + + for (fld = 0; fld < GREP_HEADER_FIELD_MAX; fld++) { + if (!header_group[fld]) + continue; + if (!header_expr) + header_expr = grep_true_expr(); + header_expr = grep_or_expr(header_group[fld], header_expr); } + return header_expr; +} + +void compile_grep_patterns(struct grep_opt *opt) +{ + struct grep_pat *p; + struct grep_expr *header_expr = prep_header_patterns(opt); for (p = opt->pattern_list; p; p = p->next) { switch (p->token) { @@ -223,9 +275,6 @@ void compile_grep_patterns(struct grep_opt *opt) else if (!opt->extended) return; - /* Then bundle them up in an expression. - * A classic recursive descent parser would do. - */ p = opt->pattern_list; if (p) opt->pattern_expression = compile_pattern_expr(&p); @@ -235,22 +284,18 @@ void compile_grep_patterns(struct grep_opt *opt) if (!header_expr) return; - if (opt->pattern_expression) { - struct grep_expr *z; - z = xcalloc(1, sizeof(*z)); - z->node = GREP_NODE_OR; - z->u.binary.left = opt->pattern_expression; - z->u.binary.right = header_expr; - opt->pattern_expression = z; - } else { + if (!opt->pattern_expression) opt->pattern_expression = header_expr; - } + else + opt->pattern_expression = grep_or_expr(opt->pattern_expression, + header_expr); opt->all_match = 1; } static void free_pattern_expr(struct grep_expr *x) { switch (x->node) { + case GREP_NODE_TRUE: case GREP_NODE_ATOM: break; case GREP_NODE_NOT: @@ -329,14 +374,21 @@ static void show_name(struct grep_opt *opt, const char *name) opt->output(opt, opt->null_following_name ? "\0" : "\n", 1); } - -static int fixmatch(const char *pattern, char *line, int ignore_case, regmatch_t *match) +static int fixmatch(struct grep_pat *p, char *line, char *eol, + regmatch_t *match) { char *hit; - if (ignore_case) - hit = strcasestr(line, pattern); - else - hit = strstr(line, pattern); + + if (p->ignore_case) { + char *s = line; + do { + hit = strcasestr(s, p->pattern); + if (hit) + break; + s += strlen(s) + 1; + } while (s < eol); + } else + hit = memmem(line, eol - line, p->pattern, p->patternlen); if (!hit) { match->rm_so = match->rm_eo = -1; @@ -344,11 +396,22 @@ static int fixmatch(const char *pattern, char *line, int ignore_case, regmatch_t } else { match->rm_so = hit - line; - match->rm_eo = match->rm_so + strlen(pattern); + match->rm_eo = match->rm_so + p->patternlen; return 0; } } +static int regmatch(const regex_t *preg, char *line, char *eol, + regmatch_t *match, int eflags) +{ +#ifdef REG_STARTEND + match->rm_so = 0; + match->rm_eo = eol - line; + eflags |= REG_STARTEND; +#endif + return regexec(preg, line, 1, match, eflags); +} + static int strip_timestamp(char *bol, char **eol_p) { char *eol = *eol_p; @@ -399,9 +462,9 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol, again: if (p->fixed) - hit = !fixmatch(p->pattern, bol, p->ignore_case, pmatch); + hit = !fixmatch(p, bol, eol, pmatch); else - hit = !regexec(&p->regexp, bol, 1, pmatch, eflags); + hit = !regmatch(&p->regexp, bol, eol, pmatch, eflags); if (hit && p->word_regexp) { if ((pmatch[0].rm_so < 0) || @@ -461,6 +524,9 @@ static int match_expr_eval(struct grep_expr *x, char *bol, char *eol, if (!x) die("Not a valid grep expression"); switch (x->node) { + case GREP_NODE_TRUE: + h = 1; + break; case GREP_NODE_ATOM: h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0); break; @@ -726,16 +792,9 @@ static int look_ahead(struct grep_opt *opt, regmatch_t m; if (p->fixed) - hit = !fixmatch(p->pattern, bol, p->ignore_case, &m); - else { -#ifdef REG_STARTEND - m.rm_so = 0; - m.rm_eo = *left_p; - hit = !regexec(&p->regexp, bol, 1, &m, REG_STARTEND); -#else - hit = !regexec(&p->regexp, bol, 1, &m, 0); -#endif - } + hit = !fixmatch(p, bol, bol + *left_p, &m); + else + hit = !regmatch(&p->regexp, bol, bol + *left_p, &m, 0); if (!hit || m.rm_so < 0 || m.rm_eo < 0) continue; if (earliest < 0 || m.rm_so < earliest) @@ -800,17 +859,19 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, opt->show_hunk_mark = 1; opt->last_shown = 0; - if (buffer_is_binary(buf, size)) { - switch (opt->binary) { - case GREP_BINARY_DEFAULT: + switch (opt->binary) { + case GREP_BINARY_DEFAULT: + if (buffer_is_binary(buf, size)) binary_match_only = 1; - break; - case GREP_BINARY_NOMATCH: + break; + case GREP_BINARY_NOMATCH: + if (buffer_is_binary(buf, size)) return 0; /* Assume unmatch */ - break; - default: - break; - } + break; + case GREP_BINARY_TEXT: + break; + default: + die("bug: unknown binary handling mode"); } memset(&xecfg, 0, sizeof(xecfg)); @@ -871,6 +932,12 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, count++; if (opt->status_only) return 1; + if (opt->name_only) { + show_name(opt, name); + return 1; + } + if (opt->count) + goto next_line; if (binary_match_only) { opt->output(opt, "Binary file ", 12); output_color(opt, name, strlen(name), @@ -878,22 +945,14 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, opt->output(opt, " matches\n", 9); return 1; } - if (opt->name_only) { - show_name(opt, 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) show_pre_context(opt, name, buf, bol, lno); else if (opt->funcname) show_funcname_line(opt, name, buf, bol, lno); - if (!opt->count) - show_line(opt, bol, eol, name, lno, ':'); + show_line(opt, bol, eol, name, lno, ':'); last_hit = lno; } else if (last_hit && @@ -937,6 +996,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name, output_sep(opt, ':'); snprintf(buf, sizeof(buf), "%u\n", count); opt->output(opt, buf, strlen(buf)); + return 1; } return !!last_hit; } |