#include "cache.h"
#include "config.h"
#include "grep.h"
+#include "object-store.h"
#include "userdiff.h"
#include "xdiff-interface.h"
#include "diff.h"
#include "diffcore.h"
#include "commit.h"
#include "quote.h"
+#include "help.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 const char *color_grep_slots[] = {
+ [GREP_COLOR_CONTEXT] = "context",
+ [GREP_COLOR_FILENAME] = "filename",
+ [GREP_COLOR_FUNCTION] = "function",
+ [GREP_COLOR_LINENO] = "lineNumber",
+ [GREP_COLOR_COLUMNNO] = "column",
+ [GREP_COLOR_MATCH_CONTEXT] = "matchContext",
+ [GREP_COLOR_MATCH_SELECTED] = "matchSelected",
+ [GREP_COLOR_SELECTED] = "selected",
+ [GREP_COLOR_SEP] = "separator",
+};
+
static void std_output(struct grep_opt *opt, const void *buf, size_t size)
{
fwrite(buf, size, 1, stdout);
}
+static void color_set(char *dst, const char *color_bytes)
+{
+ xsnprintf(dst, COLOR_MAXLEN, "%s", color_bytes);
+}
+
/*
* Initialize the grep_defaults template with hardcoded defaults.
* We could let the compiler do this, but without C99 initializers
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);
+ color_set(opt->colors[GREP_COLOR_CONTEXT], "");
+ color_set(opt->colors[GREP_COLOR_FILENAME], "");
+ color_set(opt->colors[GREP_COLOR_FUNCTION], "");
+ color_set(opt->colors[GREP_COLOR_LINENO], "");
+ color_set(opt->colors[GREP_COLOR_COLUMNNO], "");
+ color_set(opt->colors[GREP_COLOR_MATCH_CONTEXT], GIT_COLOR_BOLD_RED);
+ color_set(opt->colors[GREP_COLOR_MATCH_SELECTED], GIT_COLOR_BOLD_RED);
+ color_set(opt->colors[GREP_COLOR_SELECTED], "");
+ color_set(opt->colors[GREP_COLOR_SEP], GIT_COLOR_CYAN);
opt->color = -1;
opt->output = std_output;
}
die("bad %s argument: %s", opt, arg);
}
+define_list_config_array_extra(color_grep_slots, {"match"});
+
/*
* 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;
+ const char *slot;
if (userdiff_config(var, value) < 0)
return -1;
opt->linenum = git_config_bool(var, value);
return 0;
}
+ if (!strcmp(var, "grep.column")) {
+ opt->columnnum = git_config_bool(var, value);
+ return 0;
+ }
if (!strcmp(var, "grep.fullname")) {
opt->relative = !git_config_bool(var, value);
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 (!strcmp(var, "color.grep.match")) {
+ if (grep_config("color.grep.matchcontext", value, cb) < 0)
+ return -1;
+ if (grep_config("color.grep.matchselected", value, cb) < 0)
+ return -1;
+ } else if (skip_prefix(var, "color.grep.", &slot)) {
+ int i = LOOKUP_CONFIG(color_grep_slots, slot);
+ char *color;
+
+ if (i < 0)
+ return -1;
+ color = opt->colors[i];
if (!value)
return config_error_nonbool(var);
return color_parse(value, color);
void grep_init(struct grep_opt *opt, const char *prefix)
{
struct grep_opt *def = &grep_defaults;
+ int i;
memset(opt, 0, sizeof(*opt));
opt->prefix = prefix;
opt->extended_regexp_option = def->extended_regexp_option;
opt->pattern_type_option = def->pattern_type_option;
opt->linenum = def->linenum;
+ opt->columnnum = def->columnnum;
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);
+ for (i = 0; i < NR_GREP_COLORS; i++)
+ color_set(opt->colors[i], def->colors[i]);
}
static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt)
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",
+ BUG("The pcre1_jit_on variable should be 0 or 1, not %d",
p->pcre1_jit_on);
}
#endif
int options = PCRE2_MULTILINE;
const uint8_t *character_tables = NULL;
int jitret;
+ int patinforet;
+ size_t jitsizearg;
assert(opt->pcre2);
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);
+
+ /*
+ * The pcre2_config(PCRE2_CONFIG_JIT, ...) call just
+ * tells us whether the library itself supports JIT,
+ * but to see whether we're going to be actually using
+ * JIT we need to extract PCRE2_INFO_JITSIZE from the
+ * pattern *after* we do pcre2_jit_compile() above.
+ *
+ * This is because if the pattern contains the
+ * (*NO_JIT) verb (see pcre2syntax(3))
+ * pcre2_jit_compile() will exit early with 0. If we
+ * then proceed to call pcre2_jit_match() further down
+ * the line instead of pcre2_match() we'll either
+ * segfault (pre PCRE 10.31) or run into a fatal error
+ * (post PCRE2 10.31)
+ */
+ patinforet = pcre2_pattern_info(p->pcre2_pattern, PCRE2_INFO_JITSIZE, &jitsizearg);
+ if (patinforet)
+ BUG("pcre2_pattern_info() failed: %d", patinforet);
+ if (jitsizearg == 0) {
+ p->pcre2_jit_on = 0;
+ return;
+ }
+
p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL);
if (!p->pcre2_jit_stack)
die("Couldn't allocate PCRE2 JIT stack");
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",
+ BUG("The pcre2_jit_on variable should be 0 or 1, not %d",
p->pcre1_jit_on);
}
}
if (err) {
char errbuf[1024];
regerror(err, &p->regexp, errbuf, sizeof(errbuf));
- regfree(&p->regexp);
compile_regexp_failed(p, errbuf);
}
}
if (err) {
char errbuf[1024];
regerror(err, &p->regexp, errbuf, 1024);
- regfree(&p->regexp);
compile_regexp_failed(p, errbuf);
}
}
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.");
+ 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);
+ 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");
+ BUG("malformed header expr");
if (!header_group[p->field]) {
header_group[p->field] = h;
continue;
if (opt->null_following_name)
opt->output(opt, "\0", 1);
else
- output_color(opt, &sign, 1, opt->color_sep);
+ output_color(opt, &sign, 1, opt->colors[GREP_COLOR_SEP]);
}
static void show_name(struct grep_opt *opt, const char *name)
{
- output_color(opt, name, strlen(name), opt->color_filename);
+ output_color(opt, name, strlen(name), opt->colors[GREP_COLOR_FILENAME]);
opt->output(opt, opt->null_following_name ? "\0" : "\n", 1);
}
return hit;
}
-static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
- enum grep_context ctx, int collect_hits)
+static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, char *bol,
+ char *eol, enum grep_context ctx, ssize_t *col,
+ ssize_t *icol, int collect_hits)
{
int h = 0;
- regmatch_t match;
if (!x)
die("Not a valid grep expression");
h = 1;
break;
case GREP_NODE_ATOM:
- h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0);
+ {
+ regmatch_t tmp;
+ h = match_one_pattern(x->u.atom, bol, eol, ctx,
+ &tmp, 0);
+ if (h && (*col < 0 || tmp.rm_so < *col))
+ *col = tmp.rm_so;
+ }
break;
case GREP_NODE_NOT:
- h = !match_expr_eval(x->u.unary, bol, eol, ctx, 0);
+ /*
+ * Upon visiting a GREP_NODE_NOT, col and icol become swapped.
+ */
+ h = !match_expr_eval(opt, x->u.unary, bol, eol, ctx, icol, col,
+ 0);
break;
case GREP_NODE_AND:
- if (!match_expr_eval(x->u.binary.left, bol, eol, ctx, 0))
- return 0;
- h = match_expr_eval(x->u.binary.right, bol, eol, ctx, 0);
+ h = match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col,
+ icol, 0);
+ if (h || opt->columnnum) {
+ /*
+ * Don't short-circuit AND when given --column, since a
+ * NOT earlier in the tree may turn this into an OR. In
+ * this case, see the below comment.
+ */
+ h &= match_expr_eval(opt, x->u.binary.right, bol, eol,
+ ctx, col, icol, 0);
+ }
break;
case GREP_NODE_OR:
- if (!collect_hits)
- return (match_expr_eval(x->u.binary.left,
- bol, eol, ctx, 0) ||
- match_expr_eval(x->u.binary.right,
- bol, eol, ctx, 0));
- h = match_expr_eval(x->u.binary.left, bol, eol, ctx, 0);
- x->u.binary.left->hit |= h;
- h |= match_expr_eval(x->u.binary.right, bol, eol, ctx, 1);
+ if (!(collect_hits || opt->columnnum)) {
+ /*
+ * Don't short-circuit OR when given --column (or
+ * collecting hits) to ensure we don't skip a later
+ * child that would produce an earlier match.
+ */
+ return (match_expr_eval(opt, x->u.binary.left, bol, eol,
+ ctx, col, icol, 0) ||
+ match_expr_eval(opt, x->u.binary.right, bol,
+ eol, ctx, col, icol, 0));
+ }
+ h = match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col,
+ icol, 0);
+ if (collect_hits)
+ x->u.binary.left->hit |= h;
+ h |= match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col,
+ icol, collect_hits);
break;
default:
die("Unexpected node type (internal error) %d", x->node);
}
static int match_expr(struct grep_opt *opt, char *bol, char *eol,
- enum grep_context ctx, int collect_hits)
+ enum grep_context ctx, ssize_t *col,
+ ssize_t *icol, int collect_hits)
{
struct grep_expr *x = opt->pattern_expression;
- return match_expr_eval(x, bol, eol, ctx, collect_hits);
+ 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,
+ ssize_t *col, ssize_t *icol,
enum grep_context ctx, int collect_hits)
{
struct grep_pat *p;
- regmatch_t match;
+ int hit = 0;
if (opt->extended)
- return match_expr(opt, bol, eol, ctx, collect_hits);
+ return match_expr(opt, bol, eol, ctx, col, icol,
+ collect_hits);
/* we do not call with collect_hits without being extended */
for (p = opt->pattern_list; p; p = p->next) {
- if (match_one_pattern(p, bol, eol, ctx, &match, 0))
- return 1;
+ regmatch_t tmp;
+ if (match_one_pattern(p, bol, eol, ctx, &tmp, 0)) {
+ hit |= 1;
+ if (!opt->columnnum) {
+ /*
+ * Without --column, any single match on a line
+ * is enough to know that it needs to be
+ * printed. With --column, scan _all_ patterns
+ * to find the earliest.
+ */
+ break;
+ }
+ if (*col < 0 || tmp.rm_so < *col)
+ *col = tmp.rm_so;
+ }
}
- return 0;
+ return hit;
}
static int match_next_pattern(struct grep_pat *p, char *bol, char *eol,
}
static void show_line(struct grep_opt *opt, char *bol, char *eol,
- const char *name, unsigned lno, char sign)
+ const char *name, unsigned lno, ssize_t cno, char sign)
{
int rest = eol - bol;
const char *match_color, *line_color = NULL;
} 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);
+ output_color(opt, "--", 2, opt->colors[GREP_COLOR_SEP]);
opt->output(opt, "\n", 1);
}
} else if (lno > opt->last_shown + 1) {
- output_color(opt, "--", 2, opt->color_sep);
+ output_color(opt, "--", 2, opt->colors[GREP_COLOR_SEP]);
opt->output(opt, "\n", 1);
}
}
if (opt->heading && opt->last_shown == 0) {
- output_color(opt, name, strlen(name), opt->color_filename);
+ output_color(opt, name, strlen(name), opt->colors[GREP_COLOR_FILENAME]);
opt->output(opt, "\n", 1);
}
opt->last_shown = lno;
if (!opt->heading && opt->pathname) {
- output_color(opt, name, strlen(name), opt->color_filename);
+ output_color(opt, name, strlen(name), opt->colors[GREP_COLOR_FILENAME]);
output_sep(opt, sign);
}
if (opt->linenum) {
char buf[32];
xsnprintf(buf, sizeof(buf), "%d", lno);
- output_color(opt, buf, strlen(buf), opt->color_lineno);
+ output_color(opt, buf, strlen(buf), opt->colors[GREP_COLOR_LINENO]);
+ output_sep(opt, sign);
+ }
+ /*
+ * Treat 'cno' as the 1-indexed offset from the start of a non-context
+ * line to its first match. Otherwise, 'cno' is 0 indicating that we are
+ * being called with a context line.
+ */
+ if (opt->columnnum && cno) {
+ char buf[32];
+ xsnprintf(buf, sizeof(buf), "%"PRIuMAX, (uintmax_t)cno);
+ output_color(opt, buf, strlen(buf), opt->colors[GREP_COLOR_COLUMNNO]);
output_sep(opt, sign);
}
if (opt->color) {
int eflags = 0;
if (sign == ':')
- match_color = opt->color_match_selected;
+ match_color = opt->colors[GREP_COLOR_MATCH_SELECTED];
else
- match_color = opt->color_match_context;
+ match_color = opt->colors[GREP_COLOR_MATCH_CONTEXT];
if (sign == ':')
- line_color = opt->color_selected;
+ line_color = opt->colors[GREP_COLOR_SELECTED];
else if (sign == '-')
- line_color = opt->color_context;
+ line_color = opt->colors[GREP_COLOR_CONTEXT];
else if (sign == '=')
- line_color = opt->color_function;
+ line_color = opt->colors[GREP_COLOR_FUNCTION];
*eol = '\0';
while (next_match(opt, bol, eol, ctx, &match, eflags)) {
if (match.rm_so == match.rm_eo)
break;
if (match_funcname(opt, gs, bol, eol)) {
- show_line(opt, bol, eol, gs->name, lno, '=');
+ show_line(opt, bol, eol, gs->name, lno, 0, '=');
break;
}
}
}
+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)
{
- unsigned cur = lno, from = 1, funcname_lno = 0;
- int funcname_needed = !!opt->funcname;
-
- if (opt->funcbody && !match_funcname(opt, gs, bol, end))
- funcname_needed = 2;
+ unsigned cur = lno, from = 1, funcname_lno = 0, orig_from;
+ int funcname_needed = !!opt->funcname, comment_needed = 0;
if (opt->pre_context < lno)
from = lno - opt->pre_context;
if (from <= opt->last_shown)
from = opt->last_shown + 1;
+ orig_from = from;
+ if (opt->funcbody) {
+ if (match_funcname(opt, gs, bol, end))
+ comment_needed = 1;
+ else
+ funcname_needed = 1;
+ from = opt->last_shown + 1;
+ }
/* Rewind. */
- while (bol > gs->buf &&
- cur > (funcname_needed == 2 ? opt->last_shown + 1 : from)) {
+ while (bol > gs->buf && cur > from) {
+ char *next_bol = bol;
char *eol = --bol;
while (bol > gs->buf && bol[-1] != '\n')
bol--;
cur--;
+ if (comment_needed && (is_empty_line(bol, eol) ||
+ match_funcname(opt, gs, bol, eol))) {
+ comment_needed = 0;
+ from = orig_from;
+ if (cur < from) {
+ cur++;
+ bol = next_bol;
+ break;
+ }
+ }
if (funcname_needed && match_funcname(opt, gs, bol, eol)) {
funcname_lno = cur;
funcname_needed = 0;
+ if (opt->funcbody)
+ comment_needed = 1;
+ else
+ from = orig_from;
}
}
while (*eol != '\n')
eol++;
- show_line(opt, bol, eol, gs->name, cur, sign);
+ show_line(opt, bol, eol, gs->name, cur, 0, sign);
bol = eol + 1;
cur++;
}
fill_filespec(df, &null_oid, 0, 0100644);
break;
default:
- die("BUG: attempt to textconv something without a path?");
+ BUG("attempt to textconv something without a path?");
}
/*
case GREP_BINARY_TEXT:
break;
default:
- die("BUG: unknown binary handling mode");
+ BUG("unknown binary handling mode");
}
}
while (left) {
char *eol, ch;
int hit;
+ ssize_t cno;
+ ssize_t col = -1, icol = -1;
/*
* look_ahead() skips quickly to the line that possibly
if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol))
ctx = GREP_CONTEXT_BODY;
- hit = match_line(opt, bol, eol, ctx, collect_hits);
+ hit = match_line(opt, bol, eol, &col, &icol, ctx, collect_hits);
*eol = ch;
if (collect_hits)
if (binary_match_only) {
opt->output(opt, "Binary file ", 12);
output_color(opt, gs->name, strlen(gs->name),
- opt->color_filename);
+ opt->colors[GREP_COLOR_FILENAME]);
opt->output(opt, " matches\n", 9);
return 1;
}
show_pre_context(opt, gs, bol, eol, lno);
else if (opt->funcname)
show_funcname_line(opt, gs, bol, lno);
- show_line(opt, bol, eol, gs->name, lno, ':');
+ cno = opt->invert ? icol : col;
+ if (cno < 0) {
+ /*
+ * A negative cno indicates that there was no
+ * match on the line. We are thus inverted and
+ * being asked to show all lines that _don't_
+ * match a given expression. Therefore, set cno
+ * to 0 to suggest the whole line matches.
+ */
+ cno = 0;
+ }
+ show_line(opt, bol, eol, gs->name, lno, cno + 1, ':');
last_hit = lno;
if (opt->funcbody)
show_function = 1;
/* If the last hit is within the post context,
* we need to show this line.
*/
- show_line(opt, bol, eol, gs->name, lno, '-');
+ show_line(opt, bol, eol, gs->name, lno, col + 1, '-');
}
next_line:
char buf[32];
if (opt->pathname) {
output_color(opt, gs->name, strlen(gs->name),
- opt->color_filename);
+ opt->colors[GREP_COLOR_FILENAME]);
output_sep(opt, ':');
}
xsnprintf(buf, sizeof(buf), "%u\n", count);
enum object_type type;
grep_read_lock();
- gs->buf = read_sha1_file(gs->identifier, &type, &gs->size);
+ gs->buf = read_object_file(gs->identifier, &type, &gs->size);
grep_read_unlock();
if (!gs->buf)
case GREP_SOURCE_BUF:
return gs->buf ? 0 : -1;
}
- die("BUG: invalid grep_source type to load");
+ BUG("invalid grep_source type to load");
}
void grep_source_load_driver(struct grep_source *gs)