diff options
Diffstat (limited to 'grep.c')
| -rw-r--r-- | grep.c | 516 |
1 files changed, 172 insertions, 344 deletions
@@ -40,20 +40,6 @@ static struct grep_opt grep_defaults = { .output = std_output, }; -#ifdef USE_LIBPCRE2 -static pcre2_general_context *pcre2_global_context; - -static void *pcre2_malloc(PCRE2_SIZE size, MAYBE_UNUSED void *memory_data) -{ - return malloc(size); -} - -static void pcre2_free(void *pointer, MAYBE_UNUSED void *memory_data) -{ - free(pointer); -} -#endif - static const char *color_grep_slots[] = { [GREP_COLOR_CONTEXT] = "context", [GREP_COLOR_FILENAME] = "filename", @@ -152,25 +138,9 @@ int grep_config(const char *var, const char *value, void *cb) * Initialize one instance of grep_opt and copy the * default values from the template we read the configuration * information in an earlier call to git_config(grep_config). - * - * If using PCRE, make sure that the library is configured - * to use the same allocator as Git (e.g. nedmalloc on Windows). - * - * Any allocated memory needs to be released in grep_destroy(). */ void grep_init(struct grep_opt *opt, struct repository *repo, const char *prefix) { -#if defined(USE_LIBPCRE2) - if (!pcre2_global_context) - pcre2_global_context = pcre2_general_context_create( - pcre2_malloc, pcre2_free, NULL); -#endif - -#ifdef USE_LIBPCRE1 - pcre_malloc = malloc; - pcre_free = free; -#endif - *opt = grep_defaults; opt->repo = repo; @@ -180,13 +150,6 @@ void grep_init(struct grep_opt *opt, struct repository *repo, const char *prefix opt->header_tail = &opt->header_list; } -void grep_destroy(void) -{ -#ifdef USE_LIBPCRE2 - pcre2_general_context_free(pcre2_global_context); -#endif -} - static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt) { /* @@ -223,17 +186,7 @@ static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, st break; case GREP_PATTERN_TYPE_PCRE: -#ifdef USE_LIBPCRE2 opt->pcre2 = 1; -#else - /* - * It's important that pcre1 always be assigned to - * even when there's no USE_LIBPCRE* defined. We still - * call the PCRE stub function, it just dies with - * "cannot use Perl-compatible regexes[...]". - */ - opt->pcre1 = 1; -#endif break; } } @@ -377,93 +330,29 @@ static int is_fixed(const char *s, size_t len) return 1; } -#ifdef USE_LIBPCRE1 -static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) -{ - const char *error; - int erroffset; - int options = PCRE_MULTILINE; - int study_options = 0; - - if (opt->ignore_case) { - if (!opt->ignore_locale && has_non_ascii(p->pattern)) - p->pcre1_tables = pcre_maketables(); - options |= PCRE_CASELESS; - } - if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern)) - options |= PCRE_UTF8; - - p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset, - p->pcre1_tables); - if (!p->pcre1_regexp) - compile_regexp_failed(p, error); - -#if defined(PCRE_CONFIG_JIT) && !defined(NO_LIBPCRE1_JIT) - pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on); - if (opt->debug) - fprintf(stderr, "pcre1_jit_on=%d\n", p->pcre1_jit_on); - - if (p->pcre1_jit_on) - study_options = PCRE_STUDY_JIT_COMPILE; -#endif - - p->pcre1_extra_info = pcre_study(p->pcre1_regexp, study_options, &error); - if (!p->pcre1_extra_info && error) - die("%s", error); -} - -static int pcre1match(struct grep_pat *p, const char *line, const char *eol, - regmatch_t *match, int eflags) -{ - int ovector[30], ret, flags = PCRE_NO_UTF8_CHECK; - - if (eflags & REG_NOTBOL) - flags |= PCRE_NOTBOL; - - ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, - eol - line, 0, flags, ovector, - ARRAY_SIZE(ovector)); - - if (ret < 0 && ret != PCRE_ERROR_NOMATCH) - die("pcre_exec failed with error code %d", ret); - if (ret > 0) { - ret = 0; - match->rm_so = ovector[0]; - match->rm_eo = ovector[1]; - } - - return ret; -} +#ifdef USE_LIBPCRE2 +#define GREP_PCRE2_DEBUG_MALLOC 0 -static void free_pcre1_regexp(struct grep_pat *p) +static void *pcre2_malloc(PCRE2_SIZE size, MAYBE_UNUSED void *memory_data) { - pcre_free(p->pcre1_regexp); -#ifdef PCRE_CONFIG_JIT - if (p->pcre1_jit_on) - pcre_free_study(p->pcre1_extra_info); - else + void *pointer = malloc(size); +#if GREP_PCRE2_DEBUG_MALLOC + static int count = 1; + fprintf(stderr, "PCRE2:%p -> #%02d: alloc(%lu)\n", pointer, count++, size); #endif - pcre_free(p->pcre1_extra_info); - pcre_free((void *)p->pcre1_tables); -} -#else /* !USE_LIBPCRE1 */ -static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt) -{ - die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); + return pointer; } -static int pcre1match(struct grep_pat *p, const char *line, const char *eol, - regmatch_t *match, int eflags) -{ - return 1; -} - -static void free_pcre1_regexp(struct grep_pat *p) +static void pcre2_free(void *pointer, MAYBE_UNUSED void *memory_data) { +#if GREP_PCRE2_DEBUG_MALLOC + static int count = 1; + if (pointer) + fprintf(stderr, "PCRE2:%p -> #%02d: free()\n", pointer, count++); +#endif + free(pointer); } -#endif /* !USE_LIBPCRE1 */ -#ifdef USE_LIBPCRE2 static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) { int error; @@ -474,32 +363,43 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt int patinforet; size_t jitsizearg; - assert(opt->pcre2); - - p->pcre2_compile_context = NULL; + /* + * Call pcre2_general_context_create() before calling any + * other pcre2_*(). It sets up our malloc()/free() functions + * with which everything else is allocated. + */ + p->pcre2_general_context = pcre2_general_context_create( + pcre2_malloc, pcre2_free, NULL); + if (!p->pcre2_general_context) + die("Couldn't allocate PCRE2 general context"); - /* pcre2_global_context is initialized in append_grep_pattern */ if (opt->ignore_case) { if (!opt->ignore_locale && has_non_ascii(p->pattern)) { - if (!pcre2_global_context) - BUG("pcre2_global_context uninitialized"); - p->pcre2_tables = pcre2_maketables(pcre2_global_context); - p->pcre2_compile_context = pcre2_compile_context_create(NULL); + p->pcre2_tables = pcre2_maketables(p->pcre2_general_context); + p->pcre2_compile_context = pcre2_compile_context_create(p->pcre2_general_context); pcre2_set_character_tables(p->pcre2_compile_context, p->pcre2_tables); } options |= PCRE2_CASELESS; } - if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) && - !(!opt->ignore_case && (p->fixed || p->is_fixed))) - options |= PCRE2_UTF; + if ((!opt->ignore_locale && !has_non_ascii(p->pattern)) || + (!opt->ignore_locale && is_utf8_locale() && + has_non_ascii(p->pattern) && !(!opt->ignore_case && + (p->fixed || p->is_fixed)))) + options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF); + +#ifdef GIT_PCRE2_VERSION_10_36_OR_HIGHER + /* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */ + if (PCRE2_MATCH_INVALID_UTF && options & (PCRE2_UTF | PCRE2_CASELESS)) + options |= PCRE2_NO_START_OPTIMIZE; +#endif p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern, p->patternlen, options, &error, &erroffset, p->pcre2_compile_context); if (p->pcre2_pattern) { - p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, NULL); + p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, p->pcre2_general_context); if (!p->pcre2_match_data) die("Couldn't allocate PCRE2 match data"); } else { @@ -508,8 +408,6 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt } pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on); - if (opt->debug) - fprintf(stderr, "pcre2_jit_on=%d\n", p->pcre2_jit_on); if (p->pcre2_jit_on) { jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE); if (jitret) @@ -535,9 +433,6 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt BUG("pcre2_pattern_info() failed: %d", patinforet); if (jitsizearg == 0) { p->pcre2_jit_on = 0; - if (opt->debug) - fprintf(stderr, "pcre2_jit_on=%d: (*NO_JIT) in regex\n", - p->pcre2_jit_on); return; } } @@ -583,16 +478,16 @@ static void free_pcre2_pattern(struct grep_pat *p) pcre2_compile_context_free(p->pcre2_compile_context); pcre2_code_free(p->pcre2_pattern); pcre2_match_data_free(p->pcre2_match_data); +#ifdef GIT_PCRE2_VERSION_10_34_OR_HIGHER + pcre2_maketables_free(p->pcre2_general_context, p->pcre2_tables); +#else free((void *)p->pcre2_tables); +#endif + pcre2_general_context_free(p->pcre2_general_context); } #else /* !USE_LIBPCRE2 */ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt) { - /* - * Unreachable until USE_LIBPCRE2 becomes synonymous with - * USE_LIBPCRE. See the sibling comment in - * grep_set_pattern_type_option(). - */ die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE"); } @@ -616,8 +511,6 @@ static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt) if (opt->ignore_case) regflags |= REG_ICASE; err = regcomp(&p->regexp, sb.buf, regflags); - if (opt->debug) - fprintf(stderr, "fixed %s\n", sb.buf); strbuf_release(&sb); if (err) { char errbuf[1024]; @@ -652,7 +545,6 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) #endif if (p->fixed || p->is_fixed) { #ifdef USE_LIBPCRE2 - opt->pcre2 = 1; if (p->is_fixed) { compile_pcre2_pattern(p, opt); } else { @@ -693,11 +585,6 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt) return; } - if (opt->pcre1) { - compile_pcre1_regexp(p, opt); - return; - } - if (p->ignore_case) regflags |= REG_ICASE; if (opt->extended_regexp_option) @@ -723,7 +610,7 @@ static struct grep_expr *compile_pattern_atom(struct grep_pat **list) case GREP_PATTERN: /* atom */ case GREP_PATTERN_HEAD: case GREP_PATTERN_BODY: - x = xcalloc(1, sizeof (struct grep_expr)); + CALLOC_ARRAY(x, 1); x->node = GREP_NODE_ATOM; x->u.atom = p; *list = p->next; @@ -753,7 +640,7 @@ static struct grep_expr *compile_pattern_not(struct grep_pat **list) if (!p->next) die("--not not followed by pattern expression"); *list = p->next; - x = xcalloc(1, sizeof (struct grep_expr)); + CALLOC_ARRAY(x, 1); x->node = GREP_NODE_NOT; x->u.unary = compile_pattern_not(list); if (!x->u.unary) @@ -772,13 +659,15 @@ static struct grep_expr *compile_pattern_and(struct grep_pat **list) x = compile_pattern_not(list); p = *list; if (p && p->token == GREP_AND) { + if (!x) + die("--and not preceded by pattern expression"); 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)); + CALLOC_ARRAY(z, 1); z->node = GREP_NODE_AND; z->u.binary.left = x; z->u.binary.right = y; @@ -798,7 +687,7 @@ static struct grep_expr *compile_pattern_or(struct grep_pat **list) y = compile_pattern_or(list); if (!y) die("not a pattern expression %s", p->pattern); - z = xcalloc(1, sizeof (struct grep_expr)); + CALLOC_ARRAY(z, 1); z->node = GREP_NODE_OR; z->u.binary.left = x; z->u.binary.right = y; @@ -812,87 +701,6 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list) return compile_pattern_or(list); } -static void indent(int in) -{ - while (in-- > 0) - fputc(' ', stderr); -} - -static void dump_grep_pat(struct grep_pat *p) -{ - switch (p->token) { - case GREP_AND: fprintf(stderr, "*and*"); break; - case GREP_OPEN_PAREN: fprintf(stderr, "*(*"); break; - case GREP_CLOSE_PAREN: fprintf(stderr, "*)*"); break; - case GREP_NOT: fprintf(stderr, "*not*"); break; - case GREP_OR: fprintf(stderr, "*or*"); break; - - case GREP_PATTERN: fprintf(stderr, "pattern"); break; - case GREP_PATTERN_HEAD: fprintf(stderr, "pattern_head"); break; - case GREP_PATTERN_BODY: fprintf(stderr, "pattern_body"); break; - } - - switch (p->token) { - default: break; - case GREP_PATTERN_HEAD: - fprintf(stderr, "<head %d>", p->field); break; - case GREP_PATTERN_BODY: - fprintf(stderr, "<body>"); break; - } - switch (p->token) { - default: break; - case GREP_PATTERN_HEAD: - case GREP_PATTERN_BODY: - case GREP_PATTERN: - fprintf(stderr, "%.*s", (int)p->patternlen, p->pattern); - break; - } - fputc('\n', stderr); -} - -static void dump_grep_expression_1(struct grep_expr *x, int in) -{ - indent(in); - switch (x->node) { - case GREP_NODE_TRUE: - fprintf(stderr, "true\n"); - break; - case GREP_NODE_ATOM: - dump_grep_pat(x->u.atom); - break; - case GREP_NODE_NOT: - fprintf(stderr, "(not\n"); - dump_grep_expression_1(x->u.unary, in+1); - indent(in); - fprintf(stderr, ")\n"); - break; - case GREP_NODE_AND: - fprintf(stderr, "(and\n"); - dump_grep_expression_1(x->u.binary.left, in+1); - dump_grep_expression_1(x->u.binary.right, in+1); - indent(in); - fprintf(stderr, ")\n"); - break; - case GREP_NODE_OR: - fprintf(stderr, "(or\n"); - dump_grep_expression_1(x->u.binary.left, in+1); - dump_grep_expression_1(x->u.binary.right, in+1); - indent(in); - fprintf(stderr, ")\n"); - break; - } -} - -static void dump_grep_expression(struct grep_opt *opt) -{ - struct grep_expr *x = opt->pattern_expression; - - if (opt->all_match) - fprintf(stderr, "[all-match]\n"); - dump_grep_expression_1(x, 0); - fflush(NULL); -} - static struct grep_expr *grep_true_expr(void) { struct grep_expr *z = xcalloc(1, sizeof(*z)); @@ -973,7 +781,7 @@ static struct grep_expr *grep_splice_or(struct grep_expr *x, struct grep_expr *y return z; } -static void compile_grep_patterns_real(struct grep_opt *opt) +void compile_grep_patterns(struct grep_opt *opt) { struct grep_pat *p; struct grep_expr *header_expr = prep_header_patterns(opt); @@ -993,7 +801,7 @@ static void compile_grep_patterns_real(struct grep_opt *opt) if (opt->all_match || header_expr) opt->extended = 1; - else if (!opt->extended && !opt->debug) + else if (!opt->extended) return; p = opt->pattern_list; @@ -1016,13 +824,6 @@ static void compile_grep_patterns_real(struct grep_opt *opt) opt->all_match = 1; } -void compile_grep_patterns(struct grep_opt *opt) -{ - compile_grep_patterns_real(opt); - if (opt->debug) - dump_grep_expression(opt); -} - static void free_pattern_expr(struct grep_expr *x) { switch (x->node) { @@ -1051,9 +852,7 @@ void free_grep_patterns(struct grep_opt *opt) case GREP_PATTERN: /* atom */ case GREP_PATTERN_HEAD: case GREP_PATTERN_BODY: - if (p->pcre1_regexp) - free_pcre1_regexp(p); - else if (p->pcre2_pattern) + if (p->pcre2_pattern) free_pcre2_pattern(p); else regfree(&p->regexp); @@ -1070,7 +869,7 @@ void free_grep_patterns(struct grep_opt *opt) free_pattern_expr(opt->pattern_expression); } -static char *end_of_line(char *cp, unsigned long *left) +static const char *end_of_line(const char *cp, unsigned long *left) { unsigned long l = *left; while (l && *cp != '\n') { @@ -1111,14 +910,13 @@ static void show_name(struct grep_opt *opt, const char *name) opt->output(opt, opt->null_following_name ? "\0" : "\n", 1); } -static int patmatch(struct grep_pat *p, char *line, char *eol, +static int patmatch(struct grep_pat *p, + const char *line, const char *eol, regmatch_t *match, int eflags) { int hit; - if (p->pcre1_regexp) - hit = !pcre1match(p, line, eol, match, eflags); - else if (p->pcre2_pattern) + if (p->pcre2_pattern) hit = !pcre2match(p, line, eol, match, eflags); else hit = !regexec_buf(&p->regexp, line, eol - line, 1, match, @@ -1127,20 +925,16 @@ static int patmatch(struct grep_pat *p, char *line, char *eol, return hit; } -static int strip_timestamp(char *bol, char **eol_p) +static void strip_timestamp(const char *bol, const char **eol_p) { - char *eol = *eol_p; - int ch; + const char *eol = *eol_p; while (bol < --eol) { if (*eol != '>') continue; *eol_p = ++eol; - ch = *eol; - *eol = '\0'; - return ch; + break; } - return 0; } static struct { @@ -1152,37 +946,18 @@ static struct { { "reflog ", 7 }, }; -static int match_one_pattern(struct grep_pat *p, char *bol, char *eol, - enum grep_context ctx, - regmatch_t *pmatch, int eflags) +static int headerless_match_one_pattern(struct grep_pat *p, + const char *bol, const char *eol, + enum grep_context ctx, + regmatch_t *pmatch, int eflags) { int hit = 0; - int saved_ch = 0; const char *start = bol; if ((p->token != GREP_PATTERN) && ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD))) return 0; - if (p->token == GREP_PATTERN_HEAD) { - const char *field; - size_t len; - assert(p->field < ARRAY_SIZE(header_field)); - field = header_field[p->field].field; - len = header_field[p->field].len; - if (strncmp(bol, field, len)) - return 0; - bol += len; - switch (p->field) { - case GREP_HEADER_AUTHOR: - case GREP_HEADER_COMMITTER: - saved_ch = strip_timestamp(bol, &eol); - break; - default: - break; - } - } - again: hit = patmatch(p, bol, eol, pmatch, eflags); @@ -1226,8 +1001,6 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol, goto again; } } - if (p->token == GREP_PATTERN_HEAD && saved_ch) - *eol = saved_ch; if (hit) { pmatch[0].rm_so += bol - start; pmatch[0].rm_eo += bol - start; @@ -1235,8 +1008,39 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol, return hit; } -static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, char *bol, - char *eol, enum grep_context ctx, ssize_t *col, +static int match_one_pattern(struct grep_pat *p, + const char *bol, const char *eol, + enum grep_context ctx, regmatch_t *pmatch, + int eflags) +{ + const char *field; + size_t len; + + if (p->token == GREP_PATTERN_HEAD) { + assert(p->field < ARRAY_SIZE(header_field)); + field = header_field[p->field].field; + len = header_field[p->field].len; + if (strncmp(bol, field, len)) + return 0; + bol += len; + + switch (p->field) { + case GREP_HEADER_AUTHOR: + case GREP_HEADER_COMMITTER: + strip_timestamp(bol, &eol); + break; + default: + break; + } + } + + return headerless_match_one_pattern(p, bol, eol, ctx, pmatch, eflags); +} + + +static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, + const char *bol, const char *eol, + enum grep_context ctx, ssize_t *col, ssize_t *icol, int collect_hits) { int h = 0; @@ -1303,7 +1107,8 @@ static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, char *bol, return h; } -static int match_expr(struct grep_opt *opt, char *bol, char *eol, +static int match_expr(struct grep_opt *opt, + const char *bol, const char *eol, enum grep_context ctx, ssize_t *col, ssize_t *icol, int collect_hits) { @@ -1311,7 +1116,8 @@ static int match_expr(struct grep_opt *opt, char *bol, char *eol, return match_expr_eval(opt, x, bol, eol, ctx, col, icol, collect_hits); } -static int match_line(struct grep_opt *opt, char *bol, char *eol, +static int match_line(struct grep_opt *opt, + const char *bol, const char *eol, ssize_t *col, ssize_t *icol, enum grep_context ctx, int collect_hits) { @@ -1343,13 +1149,14 @@ static int match_line(struct grep_opt *opt, char *bol, char *eol, return hit; } -static int match_next_pattern(struct grep_pat *p, char *bol, char *eol, +static int match_next_pattern(struct grep_pat *p, + const char *bol, const char *eol, enum grep_context ctx, regmatch_t *pmatch, int eflags) { regmatch_t match; - if (!match_one_pattern(p, bol, eol, ctx, &match, eflags)) + if (!headerless_match_one_pattern(p, bol, eol, ctx, &match, eflags)) return 0; if (match.rm_so < 0 || match.rm_eo < 0) return 0; @@ -1364,18 +1171,26 @@ static int match_next_pattern(struct grep_pat *p, char *bol, char *eol, return 1; } -static int next_match(struct grep_opt *opt, char *bol, char *eol, - enum grep_context ctx, regmatch_t *pmatch, int eflags) +int grep_next_match(struct grep_opt *opt, + const char *bol, const char *eol, + enum grep_context ctx, regmatch_t *pmatch, + enum grep_header_field field, int eflags) { struct grep_pat *p; int hit = 0; pmatch->rm_so = pmatch->rm_eo = -1; if (bol < eol) { - for (p = opt->pattern_list; p; p = p->next) { + for (p = ((ctx == GREP_CONTEXT_HEAD) + ? opt->header_list : opt->pattern_list); + p; p = p->next) { switch (p->token) { - case GREP_PATTERN: /* atom */ case GREP_PATTERN_HEAD: + if ((field != GREP_HEADER_FIELD_MAX) && + (p->field != field)) + continue; + /* fall thru */ + case GREP_PATTERN: /* atom */ case GREP_PATTERN_BODY: hit |= match_next_pattern(p, bol, eol, ctx, pmatch, eflags); @@ -1420,7 +1235,8 @@ static void show_line_header(struct grep_opt *opt, const char *name, } } -static void show_line(struct grep_opt *opt, char *bol, char *eol, +static void show_line(struct grep_opt *opt, + const char *bol, const char *eol, const char *name, unsigned lno, ssize_t cno, char sign) { int rest = eol - bol; @@ -1451,7 +1267,6 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol, if (opt->color || opt->only_matching) { regmatch_t match; enum grep_context ctx = GREP_CONTEXT_BODY; - int ch = *eol; int eflags = 0; if (opt->color) { @@ -1466,8 +1281,8 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol, else if (sign == '=') line_color = opt->colors[GREP_COLOR_FUNCTION]; } - *eol = '\0'; - while (next_match(opt, bol, eol, ctx, &match, eflags)) { + while (grep_next_match(opt, bol, eol, ctx, &match, + GREP_HEADER_FIELD_MAX, eflags)) { if (match.rm_so == match.rm_eo) break; @@ -1484,7 +1299,6 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol, rest -= match.rm_eo; eflags = REG_NOTBOL; } - *eol = ch; } if (!opt->only_matching) { output_color(opt, bol, rest, line_color); @@ -1512,7 +1326,8 @@ static inline void grep_attr_unlock(void) pthread_mutex_unlock(&grep_attr_mutex); } -static int match_funcname(struct grep_opt *opt, struct grep_source *gs, char *bol, char *eol) +static int match_funcname(struct grep_opt *opt, struct grep_source *gs, + const char *bol, const char *eol) { xdemitconf_t *xecfg = opt->priv; if (xecfg && !xecfg->find_func) { @@ -1539,10 +1354,10 @@ static int match_funcname(struct grep_opt *opt, struct grep_source *gs, char *bo } static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs, - char *bol, unsigned lno) + const char *bol, unsigned lno) { while (bol > gs->buf) { - char *eol = --bol; + const char *eol = --bol; while (bol > gs->buf && bol[-1] != '\n') bol--; @@ -1561,7 +1376,7 @@ static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs, static int is_empty_line(const char *bol, const char *eol); static void show_pre_context(struct grep_opt *opt, struct grep_source *gs, - char *bol, char *end, unsigned lno) + const char *bol, const char *end, unsigned lno) { unsigned cur = lno, from = 1, funcname_lno = 0, orig_from; int funcname_needed = !!opt->funcname, comment_needed = 0; @@ -1581,8 +1396,8 @@ static void show_pre_context(struct grep_opt *opt, struct grep_source *gs, /* Rewind. */ while (bol > gs->buf && cur > from) { - char *next_bol = bol; - char *eol = --bol; + const char *next_bol = bol; + const char *eol = --bol; while (bol > gs->buf && bol[-1] != '\n') bol--; @@ -1613,7 +1428,7 @@ static void show_pre_context(struct grep_opt *opt, struct grep_source *gs, /* Back forward. */ while (cur < lno) { - char *eol = bol, sign = (cur == funcname_lno) ? '=' : '-'; + const char *eol = bol, sign = (cur == funcname_lno) ? '=' : '-'; while (*eol != '\n') eol++; @@ -1641,12 +1456,12 @@ static int should_lookahead(struct grep_opt *opt) static int look_ahead(struct grep_opt *opt, unsigned long *left_p, unsigned *lno_p, - char **bol_p) + const char **bol_p) { unsigned lno = *lno_p; - char *bol = *bol_p; + const char *bol = *bol_p; struct grep_pat *p; - char *sp, *last_bol; + const char *sp, *last_bol; regoff_t earliest = -1; for (p = opt->pattern_list; p; p = p->next) { @@ -1701,7 +1516,7 @@ static int fill_textconv_grep(struct repository *r, fill_filespec(df, gs->identifier, 1, 0100644); break; case GREP_SOURCE_FILE: - fill_filespec(df, &null_oid, 0, 0100644); + fill_filespec(df, null_oid(), 0, 0100644); break; default: BUG("attempt to textconv something without a path?"); @@ -1748,8 +1563,8 @@ static int is_empty_line(const char *bol, const char *eol) static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits) { - char *bol; - char *peek_bol = NULL; + const char *bol; + const char *peek_bol = NULL; unsigned long left; unsigned lno = 1; unsigned last_hit = 0; @@ -1831,7 +1646,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle bol = gs->buf; left = gs->size; while (left) { - char *eol, ch; + const char *eol; int hit; ssize_t cno; ssize_t col = -1, icol = -1; @@ -1852,14 +1667,11 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle && look_ahead(opt, &left, &lno, &bol)) break; eol = end_of_line(bol, &left); - ch = *eol; - *eol = 0; if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol)) ctx = GREP_CONTEXT_BODY; hit = match_line(opt, bol, eol, &col, &icol, ctx, collect_hits); - *eol = ch; if (collect_hits) goto next_line; @@ -1918,7 +1730,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle } if (show_function && (!peek_bol || peek_bol < bol)) { unsigned long peek_left = left; - char *peek_eol = eol; + const char *peek_eol = eol; /* * Trailing empty lines are not interesting. @@ -2030,14 +1842,25 @@ int grep_source(struct grep_opt *opt, struct grep_source *gs) return grep_source_1(opt, gs, 0); } -int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size) +static void grep_source_init_buf(struct grep_source *gs, + const char *buf, + unsigned long size) +{ + gs->type = GREP_SOURCE_BUF; + gs->name = NULL; + gs->path = NULL; + gs->buf = buf; + gs->size = size; + gs->driver = NULL; + gs->identifier = NULL; +} + +int grep_buffer(struct grep_opt *opt, const char *buf, unsigned long size) { struct grep_source gs; int r; - grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL, NULL); - gs.buf = buf; - gs.size = size; + grep_source_init_buf(&gs, buf, size); r = grep_source(opt, &gs); @@ -2045,28 +1868,30 @@ int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size) return r; } -void grep_source_init(struct grep_source *gs, enum grep_source_type type, - const char *name, const char *path, - const void *identifier) +void grep_source_init_file(struct grep_source *gs, const char *name, + const char *path) { - gs->type = type; + gs->type = GREP_SOURCE_FILE; gs->name = xstrdup_or_null(name); gs->path = xstrdup_or_null(path); gs->buf = NULL; gs->size = 0; gs->driver = NULL; + gs->identifier = xstrdup(path); +} - switch (type) { - case GREP_SOURCE_FILE: - gs->identifier = xstrdup(identifier); - break; - case GREP_SOURCE_OID: - gs->identifier = oiddup(identifier); - break; - case GREP_SOURCE_BUF: - gs->identifier = NULL; - break; - } +void grep_source_init_oid(struct grep_source *gs, const char *name, + const char *path, const struct object_id *oid, + struct repository *repo) +{ + gs->type = GREP_SOURCE_OID; + gs->name = xstrdup_or_null(name); + gs->path = xstrdup_or_null(path); + gs->buf = NULL; + gs->size = 0; + gs->driver = NULL; + gs->identifier = oiddup(oid); + gs->repo = repo; } void grep_source_clear(struct grep_source *gs) @@ -2082,7 +1907,9 @@ void grep_source_clear_data(struct grep_source *gs) switch (gs->type) { case GREP_SOURCE_FILE: case GREP_SOURCE_OID: - FREE_AND_NULL(gs->buf); + /* these types own the buffer */ + free((char *)gs->buf); + gs->buf = NULL; gs->size = 0; break; case GREP_SOURCE_BUF: @@ -2095,7 +1922,8 @@ static int grep_source_load_oid(struct grep_source *gs) { enum object_type type; - gs->buf = read_object_file(gs->identifier, &type, &gs->size); + gs->buf = repo_read_object_file(gs->repo, gs->identifier, &type, + &gs->size); if (!gs->buf) return error(_("'%s': unable to read %s"), gs->name, |