#include "cache.h"
+#include "config.h"
#include "grep.h"
#include "userdiff.h"
#include "xdiff-interface.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "commit.h"
+#include "quote.h"
+
+static int grep_source_load(struct grep_source *gs);
+static int grep_source_is_binary(struct grep_source *gs);
+
+static struct grep_opt grep_defaults;
+
+static void std_output(struct grep_opt *opt, const void *buf, size_t size)
+{
+ fwrite(buf, size, 1, stdout);
+}
+
+/*
+ * Initialize the grep_defaults template with hardcoded defaults.
+ * We could let the compiler do this, but without C99 initializers
+ * the code gets unwieldy and unreadable, so...
+ */
+void init_grep_defaults(void)
+{
+ struct grep_opt *opt = &grep_defaults;
+ static int run_once;
+
+ if (run_once)
+ return;
+ run_once++;
+
+ memset(opt, 0, sizeof(*opt));
+ opt->relative = 1;
+ opt->pathname = 1;
+ opt->max_depth = -1;
+ opt->pattern_type_option = GREP_PATTERN_TYPE_UNSPECIFIED;
+ color_set(opt->color_context, "");
+ color_set(opt->color_filename, "");
+ color_set(opt->color_function, "");
+ color_set(opt->color_lineno, "");
+ color_set(opt->color_match_context, GIT_COLOR_BOLD_RED);
+ color_set(opt->color_match_selected, GIT_COLOR_BOLD_RED);
+ color_set(opt->color_selected, "");
+ color_set(opt->color_sep, GIT_COLOR_CYAN);
+ opt->color = -1;
+ opt->output = std_output;
+}
+
+static int parse_pattern_type_arg(const char *opt, const char *arg)
+{
+ if (!strcmp(arg, "default"))
+ return GREP_PATTERN_TYPE_UNSPECIFIED;
+ else if (!strcmp(arg, "basic"))
+ return GREP_PATTERN_TYPE_BRE;
+ else if (!strcmp(arg, "extended"))
+ return GREP_PATTERN_TYPE_ERE;
+ else if (!strcmp(arg, "fixed"))
+ return GREP_PATTERN_TYPE_FIXED;
+ else if (!strcmp(arg, "perl"))
+ return GREP_PATTERN_TYPE_PCRE;
+ die("bad %s argument: %s", opt, arg);
+}
+
+/*
+ * Read the configuration file once and store it in
+ * the grep_defaults template.
+ */
+int grep_config(const char *var, const char *value, void *cb)
+{
+ struct grep_opt *opt = &grep_defaults;
+ char *color = NULL;
+
+ if (userdiff_config(var, value) < 0)
+ return -1;
+
+ if (!strcmp(var, "grep.extendedregexp")) {
+ opt->extended_regexp_option = git_config_bool(var, value);
+ return 0;
+ }
+
+ if (!strcmp(var, "grep.patterntype")) {
+ opt->pattern_type_option = parse_pattern_type_arg(var, value);
+ return 0;
+ }
+
+ if (!strcmp(var, "grep.linenumber")) {
+ opt->linenum = git_config_bool(var, value);
+ return 0;
+ }
+
+ if (!strcmp(var, "grep.fullname")) {
+ opt->relative = !git_config_bool(var, value);
+ return 0;
+ }
+
+ if (!strcmp(var, "color.grep"))
+ opt->color = git_config_colorbool(var, value);
+ else if (!strcmp(var, "color.grep.context"))
+ color = opt->color_context;
+ else if (!strcmp(var, "color.grep.filename"))
+ color = opt->color_filename;
+ else if (!strcmp(var, "color.grep.function"))
+ color = opt->color_function;
+ else if (!strcmp(var, "color.grep.linenumber"))
+ color = opt->color_lineno;
+ else if (!strcmp(var, "color.grep.matchcontext"))
+ color = opt->color_match_context;
+ else if (!strcmp(var, "color.grep.matchselected"))
+ color = opt->color_match_selected;
+ else if (!strcmp(var, "color.grep.selected"))
+ color = opt->color_selected;
+ else if (!strcmp(var, "color.grep.separator"))
+ color = opt->color_sep;
+ else if (!strcmp(var, "color.grep.match")) {
+ int rc = 0;
+ if (!value)
+ return config_error_nonbool(var);
+ rc |= color_parse(value, opt->color_match_context);
+ rc |= color_parse(value, opt->color_match_selected);
+ return rc;
+ }
+
+ if (color) {
+ if (!value)
+ return config_error_nonbool(var);
+ return color_parse(value, color);
+ }
+ return 0;
+}
+
+/*
+ * 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).
+ */
+void grep_init(struct grep_opt *opt, const char *prefix)
+{
+ struct grep_opt *def = &grep_defaults;
+
+ memset(opt, 0, sizeof(*opt));
+ opt->prefix = prefix;
+ opt->prefix_length = (prefix && *prefix) ? strlen(prefix) : 0;
+ opt->pattern_tail = &opt->pattern_list;
+ opt->header_tail = &opt->header_list;
+
+ opt->color = def->color;
+ opt->extended_regexp_option = def->extended_regexp_option;
+ opt->pattern_type_option = def->pattern_type_option;
+ opt->linenum = def->linenum;
+ opt->max_depth = def->max_depth;
+ opt->pathname = def->pathname;
+ opt->relative = def->relative;
+ opt->output = def->output;
+
+ color_set(opt->color_context, def->color_context);
+ color_set(opt->color_filename, def->color_filename);
+ color_set(opt->color_function, def->color_function);
+ color_set(opt->color_lineno, def->color_lineno);
+ color_set(opt->color_match_context, def->color_match_context);
+ color_set(opt->color_match_selected, def->color_match_selected);
+ color_set(opt->color_selected, def->color_selected);
+ color_set(opt->color_sep, def->color_sep);
+}
+
+static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt)
+{
+ /*
+ * When committing to the pattern type by setting the relevant
+ * fields in grep_opt it's generally not necessary to zero out
+ * the fields we're not choosing, since they won't have been
+ * set by anything. The extended_regexp_option field is the
+ * only exception to this.
+ *
+ * This is because in the process of parsing grep.patternType
+ * & grep.extendedRegexp we set opt->pattern_type_option and
+ * opt->extended_regexp_option, respectively. We then
+ * internally use opt->extended_regexp_option to see if we're
+ * compiling an ERE. It must be unset if that's not actually
+ * the case.
+ */
+ if (pattern_type != GREP_PATTERN_TYPE_ERE &&
+ opt->extended_regexp_option)
+ opt->extended_regexp_option = 0;
+
+ switch (pattern_type) {
+ case GREP_PATTERN_TYPE_UNSPECIFIED:
+ /* fall through */
+
+ case GREP_PATTERN_TYPE_BRE:
+ break;
+
+ case GREP_PATTERN_TYPE_ERE:
+ opt->extended_regexp_option = 1;
+ break;
+
+ case GREP_PATTERN_TYPE_FIXED:
+ opt->fixed = 1;
+ 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;
+ }
+}
+
+void grep_commit_pattern_type(enum grep_pattern_type pattern_type, struct grep_opt *opt)
+{
+ if (pattern_type != GREP_PATTERN_TYPE_UNSPECIFIED)
+ grep_set_pattern_type_option(pattern_type, opt);
+ else if (opt->pattern_type_option != GREP_PATTERN_TYPE_UNSPECIFIED)
+ grep_set_pattern_type_option(opt->pattern_type_option, opt);
+ else if (opt->extended_regexp_option)
+ /*
+ * This branch *must* happen after setting from the
+ * opt->pattern_type_option above, we don't want
+ * grep.extendedRegexp to override grep.patternType!
+ */
+ grep_set_pattern_type_option(GREP_PATTERN_TYPE_ERE, opt);
+}
static struct grep_pat *create_grep_pat(const char *pat, size_t patlen,
const char *origin, int no,
{
struct grep_pat *p = create_grep_pat(pat, strlen(pat), "header", 0,
GREP_PATTERN_HEAD, field);
+ if (field == GREP_HEADER_REFLOG)
+ opt->use_reflog_filter = 1;
do_append_grep_pat(&opt->header_tail, p);
}
char where[1024];
if (p->no)
- sprintf(where, "In '%s' at %d, ", p->origin, p->no);
+ xsnprintf(where, sizeof(where), "In '%s' at %d, ", p->origin, p->no);
else if (p->origin)
- sprintf(where, "%s, ", p->origin);
+ xsnprintf(where, sizeof(where), "%s, ", p->origin);
else
where[0] = 0;
die("%s'%s': %s", where, p->pattern, error);
}
-#ifdef USE_LIBPCRE
-static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+static int is_fixed(const char *s, size_t len)
+{
+ size_t i;
+
+ for (i = 0; i < len; i++) {
+ if (is_regex_special(s[i]))
+ return 0;
+ }
+
+ return 1;
+}
+
+static int has_null(const char *s, size_t len)
+{
+ /*
+ * regcomp cannot accept patterns with NULs so when using it
+ * we consider any pattern containing a NUL fixed.
+ */
+ if (memchr(s, 0, len))
+ return 1;
+
+ return 0;
+}
+
+#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;
- if (opt->ignore_case)
+ if (opt->ignore_case) {
+ if (has_non_ascii(p->pattern))
+ p->pcre1_tables = pcre_maketables();
options |= PCRE_CASELESS;
+ }
+ if (is_utf8_locale() && has_non_ascii(p->pattern))
+ options |= PCRE_UTF8;
- p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
- NULL);
- if (!p->pcre_regexp)
+ p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
+ p->pcre1_tables);
+ if (!p->pcre1_regexp)
compile_regexp_failed(p, error);
- p->pcre_extra_info = pcre_study(p->pcre_regexp, 0, &error);
- if (!p->pcre_extra_info && error)
+ p->pcre1_extra_info = pcre_study(p->pcre1_regexp, PCRE_STUDY_JIT_COMPILE, &error);
+ if (!p->pcre1_extra_info && error)
die("%s", error);
+
+#ifdef GIT_PCRE1_USE_JIT
+ pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on);
+ if (p->pcre1_jit_on == 1) {
+ p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024);
+ if (!p->pcre1_jit_stack)
+ die("Couldn't allocate PCRE JIT stack");
+ pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack);
+ } else if (p->pcre1_jit_on != 0) {
+ die("BUG: The pcre1_jit_on variable should be 0 or 1, not %d",
+ p->pcre1_jit_on);
+ }
+#endif
}
-static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
regmatch_t *match, int eflags)
{
int ovector[30], ret, flags = 0;
if (eflags & REG_NOTBOL)
flags |= PCRE_NOTBOL;
- ret = pcre_exec(p->pcre_regexp, p->pcre_extra_info, line, eol - line,
- 0, flags, ovector, ARRAY_SIZE(ovector));
+#ifdef GIT_PCRE1_USE_JIT
+ if (p->pcre1_jit_on) {
+ ret = pcre_jit_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
+ eol - line, 0, flags, ovector,
+ ARRAY_SIZE(ovector), p->pcre1_jit_stack);
+ } else
+#endif
+ {
+ 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) {
return ret;
}
-static void free_pcre_regexp(struct grep_pat *p)
+static void free_pcre1_regexp(struct grep_pat *p)
{
- pcre_free(p->pcre_regexp);
- pcre_free(p->pcre_extra_info);
+ pcre_free(p->pcre1_regexp);
+#ifdef GIT_PCRE1_USE_JIT
+ if (p->pcre1_jit_on) {
+ pcre_free_study(p->pcre1_extra_info);
+ pcre_jit_stack_free(p->pcre1_jit_stack);
+ } else
+#endif
+ {
+ pcre_free(p->pcre1_extra_info);
+ }
+ pcre_free((void *)p->pcre1_tables);
}
-#else /* !USE_LIBPCRE */
-static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+#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");
}
-static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
regmatch_t *match, int eflags)
{
return 1;
}
-static void free_pcre_regexp(struct grep_pat *p)
+static void free_pcre1_regexp(struct grep_pat *p)
{
}
-#endif /* !USE_LIBPCRE */
+#endif /* !USE_LIBPCRE1 */
-static int is_fixed(const char *s, size_t len)
+#ifdef USE_LIBPCRE2
+static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
{
- size_t i;
+ int error;
+ PCRE2_UCHAR errbuf[256];
+ PCRE2_SIZE erroffset;
+ int options = PCRE2_MULTILINE;
+ const uint8_t *character_tables = NULL;
+ int jitret;
+
+ assert(opt->pcre2);
+
+ p->pcre2_compile_context = NULL;
+
+ if (opt->ignore_case) {
+ if (has_non_ascii(p->pattern)) {
+ character_tables = pcre2_maketables(NULL);
+ p->pcre2_compile_context = pcre2_compile_context_create(NULL);
+ pcre2_set_character_tables(p->pcre2_compile_context, character_tables);
+ }
+ options |= PCRE2_CASELESS;
+ }
+ if (is_utf8_locale() && has_non_ascii(p->pattern))
+ options |= PCRE2_UTF;
- /* regcomp cannot accept patterns with NULs so we
- * consider any pattern containing a NUL fixed.
- */
- if (memchr(s, 0, len))
- return 1;
+ p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
+ p->patternlen, options, &error, &erroffset,
+ p->pcre2_compile_context);
- for (i = 0; i < len; i++) {
- if (is_regex_special(s[i]))
- return 0;
+ if (p->pcre2_pattern) {
+ p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, NULL);
+ if (!p->pcre2_match_data)
+ die("Couldn't allocate PCRE2 match data");
+ } else {
+ pcre2_get_error_message(error, errbuf, sizeof(errbuf));
+ compile_regexp_failed(p, (const char *)&errbuf);
+ }
+
+ pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on);
+ if (p->pcre2_jit_on == 1) {
+ jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE);
+ if (jitret)
+ die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret);
+ p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL);
+ if (!p->pcre2_jit_stack)
+ die("Couldn't allocate PCRE2 JIT stack");
+ p->pcre2_match_context = pcre2_match_context_create(NULL);
+ if (!p->pcre2_match_context)
+ die("Couldn't allocate PCRE2 match context");
+ pcre2_jit_stack_assign(p->pcre2_match_context, NULL, p->pcre2_jit_stack);
+ } else if (p->pcre2_jit_on != 0) {
+ die("BUG: The pcre2_jit_on variable should be 0 or 1, not %d",
+ p->pcre1_jit_on);
}
+}
+
+static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
+ regmatch_t *match, int eflags)
+{
+ int ret, flags = 0;
+ PCRE2_SIZE *ovector;
+ PCRE2_UCHAR errbuf[256];
+
+ if (eflags & REG_NOTBOL)
+ flags |= PCRE2_NOTBOL;
+
+ if (p->pcre2_jit_on)
+ ret = pcre2_jit_match(p->pcre2_pattern, (unsigned char *)line,
+ eol - line, 0, flags, p->pcre2_match_data,
+ NULL);
+ else
+ ret = pcre2_match(p->pcre2_pattern, (unsigned char *)line,
+ eol - line, 0, flags, p->pcre2_match_data,
+ NULL);
+
+ if (ret < 0 && ret != PCRE2_ERROR_NOMATCH) {
+ pcre2_get_error_message(ret, errbuf, sizeof(errbuf));
+ die("%s failed with error code %d: %s",
+ (p->pcre2_jit_on ? "pcre2_jit_match" : "pcre2_match"), ret,
+ errbuf);
+ }
+ if (ret > 0) {
+ ovector = pcre2_get_ovector_pointer(p->pcre2_match_data);
+ ret = 0;
+ match->rm_so = (int)ovector[0];
+ match->rm_eo = (int)ovector[1];
+ }
+
+ return ret;
+}
+
+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);
+ pcre2_jit_stack_free(p->pcre2_jit_stack);
+ pcre2_match_context_free(p->pcre2_match_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");
+}
+static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
+ regmatch_t *match, int eflags)
+{
return 1;
}
+static void free_pcre2_pattern(struct grep_pat *p)
+{
+}
+#endif /* !USE_LIBPCRE2 */
+
+static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
+{
+ struct strbuf sb = STRBUF_INIT;
+ int err;
+ int regflags = 0;
+
+ basic_regex_quote_buf(&sb, p->pattern);
+ 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];
+ regerror(err, &p->regexp, errbuf, sizeof(errbuf));
+ regfree(&p->regexp);
+ compile_regexp_failed(p, errbuf);
+ }
+}
+
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
+ int ascii_only;
int err;
+ int regflags = REG_NEWLINE;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
+ ascii_only = !has_non_ascii(p->pattern);
- if (opt->fixed || is_fixed(p->pattern, p->patternlen))
- p->fixed = 1;
- else
- p->fixed = 0;
+ /*
+ * Even when -F (fixed) asks us to do a non-regexp search, we
+ * may not be able to correctly case-fold when -i
+ * (ignore-case) is asked (in which case, we'll synthesize a
+ * regexp to match the pattern that matches regexp special
+ * characters literally, while ignoring case differences). On
+ * the other hand, even without -F, if the pattern does not
+ * have any regexp special characters and there is no need for
+ * case-folding search, we can internally turn it into a
+ * simple string match using kws. p->fixed tells us if we
+ * want to use kws.
+ */
+ if (opt->fixed ||
+ has_null(p->pattern, p->patternlen) ||
+ is_fixed(p->pattern, p->patternlen))
+ p->fixed = !p->ignore_case || ascii_only;
if (p->fixed) {
- if (opt->regflags & REG_ICASE || p->ignore_case)
- p->kws = kwsalloc(tolower_trans_tbl);
- else
- p->kws = kwsalloc(NULL);
+ p->kws = kwsalloc(p->ignore_case ? tolower_trans_tbl : NULL);
kwsincr(p->kws, p->pattern, p->patternlen);
kwsprep(p->kws);
return;
+ } else if (opt->fixed) {
+ /*
+ * We come here when the pattern has the non-ascii
+ * characters we cannot case-fold, and asked to
+ * ignore-case.
+ */
+ compile_fixed_regexp(p, opt);
+ return;
}
- if (opt->pcre) {
- compile_pcre_regexp(p, opt);
+ if (opt->pcre2) {
+ compile_pcre2_pattern(p, opt);
return;
}
- err = regcomp(&p->regexp, p->pattern, opt->regflags);
+ if (opt->pcre1) {
+ compile_pcre1_regexp(p, opt);
+ return;
+ }
+
+ if (p->ignore_case)
+ regflags |= REG_ICASE;
+ if (opt->extended_regexp_option)
+ regflags |= REG_EXTENDED;
+ err = regcomp(&p->regexp, p->pattern, regflags);
if (err) {
char errbuf[1024];
regerror(err, &p->regexp, errbuf, 1024);
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));
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);
+ die("BUG: a non-header pattern in grep header list.");
+ if (p->field < GREP_HEADER_FIELD_MIN ||
+ GREP_HEADER_FIELD_MAX <= p->field)
+ die("BUG: unknown header field %d", p->field);
compile_regexp(p, opt);
}
h = compile_pattern_atom(&pp);
if (!h || pp != p->next)
- die("bug: malformed header expr");
+ die("BUG: malformed header expr");
if (!header_group[p->field]) {
header_group[p->field] = h;
continue;
return header_expr;
}
-void compile_grep_patterns(struct grep_opt *opt)
+static struct grep_expr *grep_splice_or(struct grep_expr *x, struct grep_expr *y)
+{
+ struct grep_expr *z = x;
+
+ while (x) {
+ assert(x->node == GREP_NODE_OR);
+ if (x->u.binary.right &&
+ x->u.binary.right->node == GREP_NODE_TRUE) {
+ x->u.binary.right = y;
+ break;
+ }
+ x = x->u.binary.right;
+ }
+ return z;
+}
+
+static void compile_grep_patterns_real(struct grep_opt *opt)
{
struct grep_pat *p;
struct grep_expr *header_expr = prep_header_patterns(opt);
if (opt->all_match || header_expr)
opt->extended = 1;
- else if (!opt->extended)
+ else if (!opt->extended && !opt->debug)
return;
p = opt->pattern_list;
if (!opt->pattern_expression)
opt->pattern_expression = header_expr;
+ else if (opt->all_match)
+ opt->pattern_expression = grep_splice_or(header_expr,
+ opt->pattern_expression);
else
opt->pattern_expression = grep_or_expr(opt->pattern_expression,
header_expr);
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) {
case GREP_PATTERN_BODY:
if (p->kws)
kwsfree(p->kws);
- else if (p->pcre_regexp)
- free_pcre_regexp(p);
+ else if (p->pcre1_regexp)
+ free_pcre1_regexp(p);
+ else if (p->pcre2_pattern)
+ free_pcre2_pattern(p);
else
regfree(&p->regexp);
free(p->pattern);
}
}
-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 patmatch(struct grep_pat *p, char *line, char *eol,
regmatch_t *match, int eflags)
{
if (p->fixed)
hit = !fixmatch(p, line, eol, match);
- else if (p->pcre_regexp)
- hit = !pcrematch(p, line, eol, match, eflags);
+ else if (p->pcre1_regexp)
+ hit = !pcre1match(p, line, eol, match, eflags);
+ else if (p->pcre2_pattern)
+ hit = !pcre2match(p, line, eol, match, eflags);
else
- hit = !regmatch(&p->regexp, line, eol, match, eflags);
+ hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,
+ eflags);
return hit;
}
} header_field[] = {
{ "author ", 7 },
{ "committer ", 10 },
+ { "reflog ", 7 },
};
static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
if (strncmp(bol, field, len))
return 0;
bol += len;
- saved_ch = strip_timestamp(bol, &eol);
+ switch (p->field) {
+ case GREP_HEADER_AUTHOR:
+ case GREP_HEADER_COMMITTER:
+ saved_ch = strip_timestamp(bol, &eol);
+ break;
+ default:
+ break;
+ }
}
again:
const char *name, unsigned lno, char sign)
{
int rest = eol - bol;
- char *line_color = NULL;
+ const char *match_color, *line_color = NULL;
if (opt->file_break && opt->last_shown == 0) {
if (opt->show_hunk_mark)
}
if (opt->linenum) {
char buf[32];
- snprintf(buf, sizeof(buf), "%d", lno);
+ xsnprintf(buf, sizeof(buf), "%d", lno);
output_color(opt, buf, strlen(buf), opt->color_lineno);
output_sep(opt, sign);
}
int eflags = 0;
if (sign == ':')
+ match_color = opt->color_match_selected;
+ else
+ match_color = opt->color_match_context;
+ if (sign == ':')
line_color = opt->color_selected;
else if (sign == '-')
line_color = opt->color_context;
output_color(opt, bol, match.rm_so, line_color);
output_color(opt, bol + match.rm_so,
- match.rm_eo - match.rm_so,
- opt->color_match);
+ match.rm_eo - match.rm_so, match_color);
bol += match.rm_eo;
rest -= match.rm_eo;
eflags = REG_NOTBOL;
return 0;
}
-static void std_output(struct grep_opt *opt, const void *buf, size_t size)
+static int fill_textconv_grep(struct userdiff_driver *driver,
+ struct grep_source *gs)
{
- fwrite(buf, size, 1, stdout);
+ struct diff_filespec *df;
+ char *buf;
+ size_t size;
+
+ if (!driver || !driver->textconv)
+ return grep_source_load(gs);
+
+ /*
+ * The textconv interface is intimately tied to diff_filespecs, so we
+ * have to pretend to be one. If we could unify the grep_source
+ * and diff_filespec structs, this mess could just go away.
+ */
+ df = alloc_filespec(gs->path);
+ switch (gs->type) {
+ case GREP_SOURCE_OID:
+ fill_filespec(df, gs->identifier, 1, 0100644);
+ break;
+ case GREP_SOURCE_FILE:
+ fill_filespec(df, &null_oid, 0, 0100644);
+ break;
+ default:
+ die("BUG: attempt to textconv something without a path?");
+ }
+
+ /*
+ * fill_textconv is not remotely thread-safe; it may load objects
+ * behind the scenes, and it modifies the global diff tempfile
+ * structure.
+ */
+ grep_read_lock();
+ size = fill_textconv(driver, df, &buf);
+ grep_read_unlock();
+ free_filespec(df);
+
+ /*
+ * The normal fill_textconv usage by the diff machinery would just keep
+ * the textconv'd buf separate from the diff_filespec. But much of the
+ * grep code passes around a grep_source and assumes that its "buf"
+ * pointer is the beginning of the thing we are searching. So let's
+ * install our textconv'd version into the grep_source, taking care not
+ * to leak any existing buffer.
+ */
+ grep_source_clear_data(gs);
+ gs->buf = buf;
+ gs->size = size;
+
+ return 0;
+}
+
+static int is_empty_line(const char *bol, const char *eol)
+{
+ while (bol < eol && isspace(*bol))
+ bol++;
+ return bol == eol;
}
static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
{
char *bol;
+ char *peek_bol = NULL;
unsigned long left;
unsigned lno = 1;
unsigned last_hit = 0;
unsigned count = 0;
int try_lookahead = 0;
int show_function = 0;
+ struct userdiff_driver *textconv = NULL;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
}
opt->last_shown = 0;
- switch (opt->binary) {
- case GREP_BINARY_DEFAULT:
- if (grep_source_is_binary(gs))
- binary_match_only = 1;
- break;
- case GREP_BINARY_NOMATCH:
- if (grep_source_is_binary(gs))
- return 0; /* Assume unmatch */
- break;
- case GREP_BINARY_TEXT:
- break;
- default:
- die("bug: unknown binary handling mode");
+ if (opt->allow_textconv) {
+ grep_source_load_driver(gs);
+ /*
+ * We might set up the shared textconv cache data here, which
+ * is not thread-safe.
+ */
+ grep_attr_lock();
+ textconv = userdiff_get_textconv(gs->driver);
+ grep_attr_unlock();
+ }
+
+ /*
+ * We know the result of a textconv is text, so we only have to care
+ * about binary handling if we are not using it.
+ */
+ if (!textconv) {
+ switch (opt->binary) {
+ case GREP_BINARY_DEFAULT:
+ if (grep_source_is_binary(gs))
+ binary_match_only = 1;
+ break;
+ case GREP_BINARY_NOMATCH:
+ if (grep_source_is_binary(gs))
+ return 0; /* Assume unmatch */
+ break;
+ case GREP_BINARY_TEXT:
+ break;
+ default:
+ die("BUG: unknown binary handling mode");
+ }
}
memset(&xecfg, 0, sizeof(xecfg));
try_lookahead = should_lookahead(opt);
- if (grep_source_load(gs) < 0)
+ if (fill_textconv_grep(textconv, gs) < 0)
return 0;
bol = gs->buf;
show_function = 1;
goto next_line;
}
- if (show_function && match_funcname(opt, gs, bol, eol))
- show_function = 0;
+ if (show_function && (!peek_bol || peek_bol < bol)) {
+ unsigned long peek_left = left;
+ char *peek_eol = eol;
+
+ /*
+ * Trailing empty lines are not interesting.
+ * Peek past them to see if they belong to the
+ * body of the current function.
+ */
+ peek_bol = bol;
+ while (is_empty_line(peek_bol, peek_eol)) {
+ peek_bol = peek_eol + 1;
+ peek_eol = end_of_line(peek_bol, &peek_left);
+ }
+
+ if (match_funcname(opt, gs, peek_bol, peek_eol))
+ show_function = 0;
+ }
if (show_function ||
(last_hit && lno <= last_hit + opt->post_context)) {
/* If the last hit is within the post context,
return 0;
if (opt->status_only)
- return 0;
+ return opt->unmatch_name_only;
if (opt->unmatch_name_only) {
/* We did not see any hit, so we want to show this */
show_name(opt, gs->name);
*/
if (opt->count && count) {
char buf[32];
- output_color(opt, gs->name, strlen(gs->name), opt->color_filename);
- output_sep(opt, ':');
- snprintf(buf, sizeof(buf), "%u\n", count);
+ if (opt->pathname) {
+ output_color(opt, gs->name, strlen(gs->name),
+ opt->color_filename);
+ output_sep(opt, ':');
+ }
+ xsnprintf(buf, sizeof(buf), "%u\n", count);
opt->output(opt, buf, strlen(buf));
return 1;
}
struct grep_source gs;
int r;
- grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL);
+ grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL, NULL);
gs.buf = buf;
gs.size = size;
}
void grep_source_init(struct grep_source *gs, enum grep_source_type type,
- const char *name, const void *identifier)
+ const char *name, const char *path,
+ const void *identifier)
{
gs->type = type;
- gs->name = name ? xstrdup(name) : NULL;
+ gs->name = xstrdup_or_null(name);
+ gs->path = xstrdup_or_null(path);
gs->buf = NULL;
gs->size = 0;
gs->driver = NULL;
case GREP_SOURCE_FILE:
gs->identifier = xstrdup(identifier);
break;
- case GREP_SOURCE_SHA1:
- gs->identifier = xmalloc(20);
- memcpy(gs->identifier, identifier, 20);
+ case GREP_SOURCE_OID:
+ gs->identifier = oiddup(identifier);
break;
case GREP_SOURCE_BUF:
gs->identifier = NULL;
+ break;
}
}
void grep_source_clear(struct grep_source *gs)
{
- free(gs->name);
- gs->name = NULL;
- free(gs->identifier);
- gs->identifier = NULL;
+ FREE_AND_NULL(gs->name);
+ FREE_AND_NULL(gs->path);
+ FREE_AND_NULL(gs->identifier);
grep_source_clear_data(gs);
}
{
switch (gs->type) {
case GREP_SOURCE_FILE:
- case GREP_SOURCE_SHA1:
- free(gs->buf);
- gs->buf = NULL;
+ case GREP_SOURCE_OID:
+ FREE_AND_NULL(gs->buf);
gs->size = 0;
break;
case GREP_SOURCE_BUF:
}
}
-static int grep_source_load_sha1(struct grep_source *gs)
+static int grep_source_load_oid(struct grep_source *gs)
{
enum object_type type;
if (!gs->buf)
return error(_("'%s': unable to read %s"),
gs->name,
- sha1_to_hex(gs->identifier));
+ oid_to_hex(gs->identifier));
return 0;
}
if (lstat(filename, &st) < 0) {
err_ret:
if (errno != ENOENT)
- error(_("'%s': %s"), filename, strerror(errno));
+ error_errno(_("failed to stat '%s'"), filename);
return -1;
}
if (!S_ISREG(st.st_mode))
i = open(filename, O_RDONLY);
if (i < 0)
goto err_ret;
- data = xmalloc(size + 1);
+ data = xmallocz(size);
if (st.st_size != read_in_full(i, data, size)) {
- error(_("'%s': short read %s"), filename, strerror(errno));
+ error_errno(_("'%s': short read"), filename);
close(i);
free(data);
return -1;
}
close(i);
- data[size] = 0;
gs->buf = data;
gs->size = size;
return 0;
}
-int grep_source_load(struct grep_source *gs)
+static int grep_source_load(struct grep_source *gs)
{
if (gs->buf)
return 0;
switch (gs->type) {
case GREP_SOURCE_FILE:
return grep_source_load_file(gs);
- case GREP_SOURCE_SHA1:
- return grep_source_load_sha1(gs);
+ case GREP_SOURCE_OID:
+ return grep_source_load_oid(gs);
case GREP_SOURCE_BUF:
return gs->buf ? 0 : -1;
}
- die("BUG: invalid grep_source type");
+ die("BUG: invalid grep_source type to load");
}
void grep_source_load_driver(struct grep_source *gs)
return;
grep_attr_lock();
- gs->driver = userdiff_find_by_path(gs->name);
+ if (gs->path)
+ gs->driver = userdiff_find_by_path(gs->path);
if (!gs->driver)
gs->driver = userdiff_find_by_name("default");
grep_attr_unlock();
}
-int grep_source_is_binary(struct grep_source *gs)
+static int grep_source_is_binary(struct grep_source *gs)
{
grep_source_load_driver(gs);
if (gs->driver->binary != -1)