#include "userdiff.h"
#include "xdiff-interface.h"
+static int grep_source_load(struct grep_source *gs);
+static int grep_source_is_binary(struct grep_source *gs);
+
+
static struct grep_pat *create_grep_pat(const char *pat, size_t patlen,
const char *origin, int no,
enum grep_pat_token t,
enum grep_header_field field)
{
struct grep_pat *p = xcalloc(1, sizeof(*p));
- p->pattern = pat;
+ p->pattern = xmemdupz(pat, patlen);
p->patternlen = patlen;
p->origin = origin;
p->no = no;
**tail = p;
*tail = &p->next;
p->next = NULL;
+
+ switch (p->token) {
+ case GREP_PATTERN: /* atom */
+ case GREP_PATTERN_HEAD:
+ case GREP_PATTERN_BODY:
+ for (;;) {
+ struct grep_pat *new_pat;
+ size_t len = 0;
+ char *cp = p->pattern + p->patternlen, *nl = NULL;
+ while (++len <= p->patternlen) {
+ if (*(--cp) == '\n') {
+ nl = cp;
+ break;
+ }
+ }
+ if (!nl)
+ break;
+ new_pat = create_grep_pat(nl + 1, len - 1, p->origin,
+ p->no, p->token, p->field);
+ new_pat->next = p->next;
+ if (!p->next)
+ *tail = &new_pat->next;
+ p->next = new_pat;
+ *nl = '\0';
+ p->patternlen -= len;
+ }
+ break;
+ default:
+ break;
+ }
}
void append_header_grep_pattern(struct grep_opt *opt,
{
const char *error;
int erroffset;
- int options = 0;
+ int options = PCRE_MULTILINE;
if (opt->ignore_case)
options |= PCRE_CASELESS;
}
#endif /* !USE_LIBPCRE */
+static int is_fixed(const char *s, size_t len)
+{
+ size_t i;
+
+ /* regcomp cannot accept patterns with NULs so we
+ * consider any pattern containing a NUL fixed.
+ */
+ if (memchr(s, 0, len))
+ return 1;
+
+ for (i = 0; i < len; i++) {
+ if (is_regex_special(s[i]))
+ return 0;
+ }
+
+ return 1;
+}
+
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
int err;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
- p->fixed = opt->fixed;
- if (p->fixed)
+ if (opt->fixed || is_fixed(p->pattern, p->patternlen))
+ p->fixed = 1;
+ else
+ p->fixed = 0;
+
+ if (p->fixed) {
+ if (opt->regflags & REG_ICASE || p->ignore_case)
+ p->kws = kwsalloc(tolower_trans_tbl);
+ else
+ p->kws = kwsalloc(NULL);
+ kwsincr(p->kws, p->pattern, p->patternlen);
+ kwsprep(p->kws);
return;
+ }
if (opt->pcre) {
compile_pcre_regexp(p, opt);
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));
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.");
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: /* atom */
case GREP_PATTERN_HEAD:
case GREP_PATTERN_BODY:
- if (p->pcre_regexp)
+ if (p->kws)
+ kwsfree(p->kws);
+ else if (p->pcre_regexp)
free_pcre_regexp(p);
else
regfree(&p->regexp);
+ free(p->pattern);
break;
default:
break;
static void output_color(struct grep_opt *opt, const void *data, size_t size,
const char *color)
{
- if (opt->color && color && color[0]) {
+ if (want_color(opt->color) && color && color[0]) {
opt->output(opt, color, strlen(color));
opt->output(opt, data, size);
opt->output(opt, GIT_COLOR_RESET, strlen(GIT_COLOR_RESET));
static int fixmatch(struct grep_pat *p, char *line, char *eol,
regmatch_t *match)
{
- char *hit;
-
- 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) {
+ struct kwsmatch kwsm;
+ size_t offset = kwsexec(p->kws, line, eol - line, &kwsm);
+ if (offset == -1) {
match->rm_so = match->rm_eo = -1;
return REG_NOMATCH;
- }
- else {
- match->rm_so = hit - line;
- match->rm_eo = match->rm_so + p->patternlen;
+ } else {
+ match->rm_so = offset;
+ match->rm_eo = match->rm_so + kwsm.size[0];
return 0;
}
}
int rest = eol - bol;
char *line_color = NULL;
- if (opt->pre_context || opt->post_context) {
+ if (opt->file_break && opt->last_shown == 0) {
+ if (opt->show_hunk_mark)
+ opt->output(opt, "\n", 1);
+ } else if (opt->pre_context || opt->post_context || opt->funcbody) {
if (opt->last_shown == 0) {
if (opt->show_hunk_mark) {
output_color(opt, "--", 2, opt->color_sep);
opt->output(opt, "\n", 1);
}
}
+ if (opt->heading && opt->last_shown == 0) {
+ output_color(opt, name, strlen(name), opt->color_filename);
+ opt->output(opt, "\n", 1);
+ }
opt->last_shown = lno;
- if (opt->pathname) {
+ if (!opt->heading && opt->pathname) {
output_color(opt, name, strlen(name), opt->color_filename);
output_sep(opt, sign);
}
opt->output(opt, "\n", 1);
}
-static int match_funcname(struct grep_opt *opt, char *bol, char *eol)
+#ifndef NO_PTHREADS
+int grep_use_locks;
+
+/*
+ * This lock protects access to the gitattributes machinery, which is
+ * not thread-safe.
+ */
+pthread_mutex_t grep_attr_mutex;
+
+static inline void grep_attr_lock(void)
+{
+ if (grep_use_locks)
+ pthread_mutex_lock(&grep_attr_mutex);
+}
+
+static inline void grep_attr_unlock(void)
+{
+ if (grep_use_locks)
+ pthread_mutex_unlock(&grep_attr_mutex);
+}
+
+/*
+ * Same as git_attr_mutex, but protecting the thread-unsafe object db access.
+ */
+pthread_mutex_t grep_read_mutex;
+
+#else
+#define grep_attr_lock()
+#define grep_attr_unlock()
+#endif
+
+static int match_funcname(struct grep_opt *opt, struct grep_source *gs, char *bol, char *eol)
{
xdemitconf_t *xecfg = opt->priv;
- if (xecfg && xecfg->find_func) {
+ if (xecfg && !xecfg->find_func) {
+ grep_source_load_driver(gs);
+ if (gs->driver->funcname.pattern) {
+ const struct userdiff_funcname *pe = &gs->driver->funcname;
+ xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
+ } else {
+ xecfg = opt->priv = NULL;
+ }
+ }
+
+ if (xecfg) {
char buf[1];
return xecfg->find_func(bol, eol - bol, buf, 1,
xecfg->find_func_priv) >= 0;
return 0;
}
-static void show_funcname_line(struct grep_opt *opt, const char *name,
- char *buf, char *bol, unsigned lno)
+static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs,
+ char *bol, unsigned lno)
{
- while (bol > buf) {
+ while (bol > gs->buf) {
char *eol = --bol;
- while (bol > buf && bol[-1] != '\n')
+ while (bol > gs->buf && bol[-1] != '\n')
bol--;
lno--;
if (lno <= opt->last_shown)
break;
- if (match_funcname(opt, bol, eol)) {
- show_line(opt, bol, eol, name, lno, '=');
+ if (match_funcname(opt, gs, bol, eol)) {
+ show_line(opt, bol, eol, gs->name, lno, '=');
break;
}
}
}
-static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
- char *bol, unsigned lno)
+static void show_pre_context(struct grep_opt *opt, struct grep_source *gs,
+ char *bol, char *end, unsigned lno)
{
unsigned cur = lno, from = 1, funcname_lno = 0;
- int funcname_needed = opt->funcname;
+ int funcname_needed = !!opt->funcname;
+
+ if (opt->funcbody && !match_funcname(opt, gs, bol, end))
+ funcname_needed = 2;
if (opt->pre_context < lno)
from = lno - opt->pre_context;
from = opt->last_shown + 1;
/* Rewind. */
- while (bol > buf && cur > from) {
+ while (bol > gs->buf &&
+ cur > (funcname_needed == 2 ? opt->last_shown + 1 : from)) {
char *eol = --bol;
- while (bol > buf && bol[-1] != '\n')
+ while (bol > gs->buf && bol[-1] != '\n')
bol--;
cur--;
- if (funcname_needed && match_funcname(opt, bol, eol)) {
+ if (funcname_needed && match_funcname(opt, gs, bol, eol)) {
funcname_lno = cur;
funcname_needed = 0;
}
/* We need to look even further back to find a function signature. */
if (opt->funcname && funcname_needed)
- show_funcname_line(opt, name, buf, bol, cur);
+ show_funcname_line(opt, gs, bol, cur);
/* Back forward. */
while (cur < lno) {
while (*eol != '\n')
eol++;
- show_line(opt, bol, eol, name, cur, sign);
+ show_line(opt, bol, eol, gs->name, cur, sign);
bol = eol + 1;
cur++;
}
return 0;
}
-int grep_threads_ok(const struct grep_opt *opt)
-{
- /* If this condition is true, then we may use the attribute
- * machinery in grep_buffer_1. The attribute code is not
- * thread safe, so we disable the use of threads.
- */
- if (opt->funcname && !opt->unmatch_name_only && !opt->status_only &&
- !opt->name_only)
- return 0;
-
- return 1;
-}
-
static void std_output(struct grep_opt *opt, const void *buf, size_t size)
{
fwrite(buf, size, 1, stdout);
}
-static int grep_buffer_1(struct grep_opt *opt, const char *name,
- char *buf, unsigned long size, int collect_hits)
+static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
{
- char *bol = buf;
- unsigned long left = size;
+ char *bol;
+ unsigned long left;
unsigned lno = 1;
unsigned last_hit = 0;
int binary_match_only = 0;
unsigned count = 0;
int try_lookahead = 0;
+ int show_function = 0;
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
if (!opt->output)
opt->output = std_output;
- if (opt->last_shown && (opt->pre_context || opt->post_context) &&
- opt->output == std_output)
- opt->show_hunk_mark = 1;
+ if (opt->pre_context || opt->post_context || opt->file_break ||
+ opt->funcbody) {
+ /* Show hunk marks, except for the first file. */
+ if (opt->last_shown)
+ opt->show_hunk_mark = 1;
+ /*
+ * If we're using threads then we can't easily identify
+ * the first file. Always put hunk marks in that case
+ * and skip the very first one later in work_done().
+ */
+ if (opt->output != std_output)
+ opt->show_hunk_mark = 1;
+ }
opt->last_shown = 0;
switch (opt->binary) {
case GREP_BINARY_DEFAULT:
- if (buffer_is_binary(buf, size))
+ if (grep_source_is_binary(gs))
binary_match_only = 1;
break;
case GREP_BINARY_NOMATCH:
- if (buffer_is_binary(buf, size))
+ if (grep_source_is_binary(gs))
return 0; /* Assume unmatch */
break;
case GREP_BINARY_TEXT:
}
memset(&xecfg, 0, sizeof(xecfg));
- if (opt->funcname && !opt->unmatch_name_only && !opt->status_only &&
- !opt->name_only && !binary_match_only && !collect_hits) {
- struct userdiff_driver *drv = userdiff_find_by_path(name);
- if (drv && drv->funcname.pattern) {
- const struct userdiff_funcname *pe = &drv->funcname;
- xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
- opt->priv = &xecfg;
- }
- }
+ opt->priv = &xecfg;
+
try_lookahead = should_lookahead(opt);
+ if (grep_source_load(gs) < 0)
+ return 0;
+
+ bol = gs->buf;
+ left = gs->size;
while (left) {
char *eol, ch;
int hit;
*/
if (try_lookahead
&& !(last_hit
- && lno <= last_hit + opt->post_context)
+ && (show_function ||
+ lno <= last_hit + opt->post_context))
&& look_ahead(opt, &left, &lno, &bol))
break;
eol = end_of_line(bol, &left);
if (opt->status_only)
return 1;
if (opt->name_only) {
- show_name(opt, name);
+ show_name(opt, gs->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),
+ output_color(opt, gs->name, strlen(gs->name),
opt->color_filename);
opt->output(opt, " matches\n", 9);
return 1;
/* Hit at this line. If we haven't shown the
* pre-context lines, we would need to show them.
*/
- if (opt->pre_context)
- show_pre_context(opt, name, buf, bol, lno);
+ if (opt->pre_context || opt->funcbody)
+ show_pre_context(opt, gs, bol, eol, lno);
else if (opt->funcname)
- show_funcname_line(opt, name, buf, bol, lno);
- show_line(opt, bol, eol, name, lno, ':');
+ show_funcname_line(opt, gs, bol, lno);
+ show_line(opt, bol, eol, gs->name, lno, ':');
last_hit = lno;
+ if (opt->funcbody)
+ show_function = 1;
+ goto next_line;
}
- else if (last_hit &&
- lno <= last_hit + opt->post_context) {
+ if (show_function && match_funcname(opt, gs, bol, eol))
+ show_function = 0;
+ if (show_function ||
+ (last_hit && lno <= last_hit + opt->post_context)) {
/* If the last hit is within the post context,
* we need to show this line.
*/
- show_line(opt, bol, eol, name, lno, '-');
+ show_line(opt, bol, eol, gs->name, lno, '-');
}
next_line:
return 0;
if (opt->unmatch_name_only) {
/* We did not see any hit, so we want to show this */
- show_name(opt, name);
+ show_name(opt, gs->name);
return 1;
}
*/
if (opt->count && count) {
char buf[32];
- output_color(opt, name, strlen(name), opt->color_filename);
+ output_color(opt, gs->name, strlen(gs->name), opt->color_filename);
output_sep(opt, ':');
snprintf(buf, sizeof(buf), "%u\n", count);
opt->output(opt, buf, strlen(buf));
}
}
-int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size)
+int grep_source(struct grep_opt *opt, struct grep_source *gs)
{
/*
* we do not have to do the two-pass grep when we do not check
* buffer-wide "all-match".
*/
if (!opt->all_match)
- return grep_buffer_1(opt, name, buf, size, 0);
+ return grep_source_1(opt, gs, 0);
/* Otherwise the toplevel "or" terms hit a bit differently.
* We first clear hit markers from them.
*/
clr_hit_marker(opt->pattern_expression);
- grep_buffer_1(opt, name, buf, size, 1);
+ grep_source_1(opt, gs, 1);
if (!chk_hit_marker(opt->pattern_expression))
return 0;
- return grep_buffer_1(opt, name, buf, size, 0);
+ return grep_source_1(opt, gs, 0);
+}
+
+int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size)
+{
+ struct grep_source gs;
+ int r;
+
+ grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL);
+ gs.buf = buf;
+ gs.size = size;
+
+ r = grep_source(opt, &gs);
+
+ grep_source_clear(&gs);
+ return r;
+}
+
+void grep_source_init(struct grep_source *gs, enum grep_source_type type,
+ const char *name, const void *identifier)
+{
+ gs->type = type;
+ gs->name = name ? xstrdup(name) : NULL;
+ gs->buf = NULL;
+ gs->size = 0;
+ gs->driver = NULL;
+
+ switch (type) {
+ case GREP_SOURCE_FILE:
+ gs->identifier = xstrdup(identifier);
+ break;
+ case GREP_SOURCE_SHA1:
+ gs->identifier = xmalloc(20);
+ memcpy(gs->identifier, identifier, 20);
+ break;
+ case GREP_SOURCE_BUF:
+ gs->identifier = NULL;
+ }
+}
+
+void grep_source_clear(struct grep_source *gs)
+{
+ free(gs->name);
+ gs->name = NULL;
+ free(gs->identifier);
+ gs->identifier = NULL;
+ grep_source_clear_data(gs);
+}
+
+void grep_source_clear_data(struct grep_source *gs)
+{
+ switch (gs->type) {
+ case GREP_SOURCE_FILE:
+ case GREP_SOURCE_SHA1:
+ free(gs->buf);
+ gs->buf = NULL;
+ gs->size = 0;
+ break;
+ case GREP_SOURCE_BUF:
+ /* leave user-provided buf intact */
+ break;
+ }
+}
+
+static int grep_source_load_sha1(struct grep_source *gs)
+{
+ enum object_type type;
+
+ grep_read_lock();
+ gs->buf = read_sha1_file(gs->identifier, &type, &gs->size);
+ grep_read_unlock();
+
+ if (!gs->buf)
+ return error(_("'%s': unable to read %s"),
+ gs->name,
+ sha1_to_hex(gs->identifier));
+ return 0;
+}
+
+static int grep_source_load_file(struct grep_source *gs)
+{
+ const char *filename = gs->identifier;
+ struct stat st;
+ char *data;
+ size_t size;
+ int i;
+
+ if (lstat(filename, &st) < 0) {
+ err_ret:
+ if (errno != ENOENT)
+ error(_("'%s': %s"), filename, strerror(errno));
+ return -1;
+ }
+ if (!S_ISREG(st.st_mode))
+ return -1;
+ size = xsize_t(st.st_size);
+ i = open(filename, O_RDONLY);
+ if (i < 0)
+ goto err_ret;
+ data = xmalloc(size + 1);
+ if (st.st_size != read_in_full(i, data, size)) {
+ error(_("'%s': short read %s"), filename, strerror(errno));
+ close(i);
+ free(data);
+ return -1;
+ }
+ close(i);
+ data[size] = 0;
+
+ gs->buf = data;
+ gs->size = size;
+ return 0;
+}
+
+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_BUF:
+ return gs->buf ? 0 : -1;
+ }
+ die("BUG: invalid grep_source type");
+}
+
+void grep_source_load_driver(struct grep_source *gs)
+{
+ if (gs->driver)
+ return;
+
+ grep_attr_lock();
+ gs->driver = userdiff_find_by_path(gs->name);
+ if (!gs->driver)
+ gs->driver = userdiff_find_by_name("default");
+ grep_attr_unlock();
+}
+
+static int grep_source_is_binary(struct grep_source *gs)
+{
+ grep_source_load_driver(gs);
+ if (gs->driver->binary != -1)
+ return gs->driver->binary;
+
+ if (!grep_source_load(gs))
+ return buffer_is_binary(gs->buf, gs->size);
+
+ return 0;
}