Merge branch 'jc/filter-commit'
* jc/filter-commit:
git log: Unify header_filter and message_filter into one.
Update grep internal for grepping only in head/body
git-log --author and --committer are not left-anchored by default
rev-list: fix segfault with --{author,committer,grep}
revision traversal: --author, --committer, and --grep.
revision traversal: prepare for commit log match.
builtin-grep: make pieces of it available as library.
maint
Junio C Hamano
commit
b0ed9eafb3
|
|
@ -20,6 +20,7 @@ SYNOPSIS
|
||||||
[ \--stdin ]
|
[ \--stdin ]
|
||||||
[ \--topo-order ]
|
[ \--topo-order ]
|
||||||
[ \--parents ]
|
[ \--parents ]
|
||||||
|
[ \--(author|committer|grep)=<pattern> ]
|
||||||
[ [\--objects | \--objects-edge] [ \--unpacked ] ]
|
[ [\--objects | \--objects-edge] [ \--unpacked ] ]
|
||||||
[ \--pretty | \--header ]
|
[ \--pretty | \--header ]
|
||||||
[ \--bisect ]
|
[ \--bisect ]
|
||||||
|
|
@ -154,6 +155,16 @@ limiting may be applied.
|
||||||
|
|
||||||
Limit the commits output to specified time range.
|
Limit the commits output to specified time range.
|
||||||
|
|
||||||
|
--author='pattern', --committer='pattern'::
|
||||||
|
|
||||||
|
Limit the commits output to ones with author/committer
|
||||||
|
header lines that match the specified pattern.
|
||||||
|
|
||||||
|
--grep='pattern'::
|
||||||
|
|
||||||
|
Limit the commits output to ones with log message that
|
||||||
|
matches the specified pattern.
|
||||||
|
|
||||||
--remove-empty::
|
--remove-empty::
|
||||||
|
|
||||||
Stop when a given path disappears from the tree.
|
Stop when a given path disappears from the tree.
|
||||||
|
|
|
||||||
4
Makefile
4
Makefile
|
|
@ -234,7 +234,7 @@ LIB_FILE=libgit.a
|
||||||
XDIFF_LIB=xdiff/lib.a
|
XDIFF_LIB=xdiff/lib.a
|
||||||
|
|
||||||
LIB_H = \
|
LIB_H = \
|
||||||
archive.h blob.h cache.h commit.h csum-file.h delta.h \
|
archive.h blob.h cache.h commit.h csum-file.h delta.h grep.h \
|
||||||
diff.h object.h pack.h pkt-line.h quote.h refs.h list-objects.h sideband.h \
|
diff.h object.h pack.h pkt-line.h quote.h refs.h list-objects.h sideband.h \
|
||||||
run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
|
run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
|
||||||
tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h
|
tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h
|
||||||
|
|
@ -254,7 +254,7 @@ LIB_OBJS = \
|
||||||
server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
|
server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
|
||||||
tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
|
tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
|
||||||
fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
|
fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
|
||||||
write_or_die.o trace.o list-objects.o \
|
write_or_die.o trace.o list-objects.o grep.o \
|
||||||
alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) \
|
alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) \
|
||||||
color.o wt-status.o archive-zip.o
|
color.o wt-status.o archive-zip.o
|
||||||
|
|
||||||
|
|
|
||||||
522
builtin-grep.c
522
builtin-grep.c
|
|
@ -11,6 +11,7 @@
|
||||||
#include "tree-walk.h"
|
#include "tree-walk.h"
|
||||||
#include "builtin.h"
|
#include "builtin.h"
|
||||||
#include <regex.h>
|
#include <regex.h>
|
||||||
|
#include "grep.h"
|
||||||
#include <fnmatch.h>
|
#include <fnmatch.h>
|
||||||
#include <sys/wait.h>
|
#include <sys/wait.h>
|
||||||
|
|
||||||
|
|
@ -82,498 +83,6 @@ static int pathspec_matches(const char **paths, const char *name)
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
enum grep_pat_token {
|
|
||||||
GREP_PATTERN,
|
|
||||||
GREP_AND,
|
|
||||||
GREP_OPEN_PAREN,
|
|
||||||
GREP_CLOSE_PAREN,
|
|
||||||
GREP_NOT,
|
|
||||||
GREP_OR,
|
|
||||||
};
|
|
||||||
|
|
||||||
struct grep_pat {
|
|
||||||
struct grep_pat *next;
|
|
||||||
const char *origin;
|
|
||||||
int no;
|
|
||||||
enum grep_pat_token token;
|
|
||||||
const char *pattern;
|
|
||||||
regex_t regexp;
|
|
||||||
};
|
|
||||||
|
|
||||||
enum grep_expr_node {
|
|
||||||
GREP_NODE_ATOM,
|
|
||||||
GREP_NODE_NOT,
|
|
||||||
GREP_NODE_AND,
|
|
||||||
GREP_NODE_OR,
|
|
||||||
};
|
|
||||||
|
|
||||||
struct grep_expr {
|
|
||||||
enum grep_expr_node node;
|
|
||||||
union {
|
|
||||||
struct grep_pat *atom;
|
|
||||||
struct grep_expr *unary;
|
|
||||||
struct {
|
|
||||||
struct grep_expr *left;
|
|
||||||
struct grep_expr *right;
|
|
||||||
} binary;
|
|
||||||
} u;
|
|
||||||
};
|
|
||||||
|
|
||||||
struct grep_opt {
|
|
||||||
struct grep_pat *pattern_list;
|
|
||||||
struct grep_pat **pattern_tail;
|
|
||||||
struct grep_expr *pattern_expression;
|
|
||||||
int prefix_length;
|
|
||||||
regex_t regexp;
|
|
||||||
unsigned linenum:1;
|
|
||||||
unsigned invert:1;
|
|
||||||
unsigned name_only:1;
|
|
||||||
unsigned unmatch_name_only:1;
|
|
||||||
unsigned count:1;
|
|
||||||
unsigned word_regexp:1;
|
|
||||||
unsigned fixed:1;
|
|
||||||
#define GREP_BINARY_DEFAULT 0
|
|
||||||
#define GREP_BINARY_NOMATCH 1
|
|
||||||
#define GREP_BINARY_TEXT 2
|
|
||||||
unsigned binary:2;
|
|
||||||
unsigned extended:1;
|
|
||||||
unsigned relative:1;
|
|
||||||
unsigned pathname:1;
|
|
||||||
int regflags;
|
|
||||||
unsigned pre_context;
|
|
||||||
unsigned post_context;
|
|
||||||
};
|
|
||||||
|
|
||||||
static void add_pattern(struct grep_opt *opt, const char *pat,
|
|
||||||
const char *origin, int no, enum grep_pat_token t)
|
|
||||||
{
|
|
||||||
struct grep_pat *p = xcalloc(1, sizeof(*p));
|
|
||||||
p->pattern = pat;
|
|
||||||
p->origin = origin;
|
|
||||||
p->no = no;
|
|
||||||
p->token = t;
|
|
||||||
*opt->pattern_tail = p;
|
|
||||||
opt->pattern_tail = &p->next;
|
|
||||||
p->next = NULL;
|
|
||||||
}
|
|
||||||
|
|
||||||
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
|
|
||||||
{
|
|
||||||
int err = regcomp(&p->regexp, p->pattern, opt->regflags);
|
|
||||||
if (err) {
|
|
||||||
char errbuf[1024];
|
|
||||||
char where[1024];
|
|
||||||
if (p->no)
|
|
||||||
sprintf(where, "In '%s' at %d, ",
|
|
||||||
p->origin, p->no);
|
|
||||||
else if (p->origin)
|
|
||||||
sprintf(where, "%s, ", p->origin);
|
|
||||||
else
|
|
||||||
where[0] = 0;
|
|
||||||
regerror(err, &p->regexp, errbuf, 1024);
|
|
||||||
regfree(&p->regexp);
|
|
||||||
die("%s'%s': %s", where, p->pattern, errbuf);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
static struct grep_expr *compile_pattern_expr(struct grep_pat **);
|
|
||||||
static struct grep_expr *compile_pattern_atom(struct grep_pat **list)
|
|
||||||
{
|
|
||||||
struct grep_pat *p;
|
|
||||||
struct grep_expr *x;
|
|
||||||
|
|
||||||
p = *list;
|
|
||||||
switch (p->token) {
|
|
||||||
case GREP_PATTERN: /* atom */
|
|
||||||
x = xcalloc(1, sizeof (struct grep_expr));
|
|
||||||
x->node = GREP_NODE_ATOM;
|
|
||||||
x->u.atom = p;
|
|
||||||
*list = p->next;
|
|
||||||
return x;
|
|
||||||
case GREP_OPEN_PAREN:
|
|
||||||
*list = p->next;
|
|
||||||
x = compile_pattern_expr(list);
|
|
||||||
if (!x)
|
|
||||||
return NULL;
|
|
||||||
if (!*list || (*list)->token != GREP_CLOSE_PAREN)
|
|
||||||
die("unmatched parenthesis");
|
|
||||||
*list = (*list)->next;
|
|
||||||
return x;
|
|
||||||
default:
|
|
||||||
return NULL;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
static struct grep_expr *compile_pattern_not(struct grep_pat **list)
|
|
||||||
{
|
|
||||||
struct grep_pat *p;
|
|
||||||
struct grep_expr *x;
|
|
||||||
|
|
||||||
p = *list;
|
|
||||||
switch (p->token) {
|
|
||||||
case GREP_NOT:
|
|
||||||
if (!p->next)
|
|
||||||
die("--not not followed by pattern expression");
|
|
||||||
*list = p->next;
|
|
||||||
x = xcalloc(1, sizeof (struct grep_expr));
|
|
||||||
x->node = GREP_NODE_NOT;
|
|
||||||
x->u.unary = compile_pattern_not(list);
|
|
||||||
if (!x->u.unary)
|
|
||||||
die("--not followed by non pattern expression");
|
|
||||||
return x;
|
|
||||||
default:
|
|
||||||
return compile_pattern_atom(list);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
static struct grep_expr *compile_pattern_and(struct grep_pat **list)
|
|
||||||
{
|
|
||||||
struct grep_pat *p;
|
|
||||||
struct grep_expr *x, *y, *z;
|
|
||||||
|
|
||||||
x = compile_pattern_not(list);
|
|
||||||
p = *list;
|
|
||||||
if (p && p->token == GREP_AND) {
|
|
||||||
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));
|
|
||||||
z->node = GREP_NODE_AND;
|
|
||||||
z->u.binary.left = x;
|
|
||||||
z->u.binary.right = y;
|
|
||||||
return z;
|
|
||||||
}
|
|
||||||
return x;
|
|
||||||
}
|
|
||||||
|
|
||||||
static struct grep_expr *compile_pattern_or(struct grep_pat **list)
|
|
||||||
{
|
|
||||||
struct grep_pat *p;
|
|
||||||
struct grep_expr *x, *y, *z;
|
|
||||||
|
|
||||||
x = compile_pattern_and(list);
|
|
||||||
p = *list;
|
|
||||||
if (x && p && p->token != GREP_CLOSE_PAREN) {
|
|
||||||
y = compile_pattern_or(list);
|
|
||||||
if (!y)
|
|
||||||
die("not a pattern expression %s", p->pattern);
|
|
||||||
z = xcalloc(1, sizeof (struct grep_expr));
|
|
||||||
z->node = GREP_NODE_OR;
|
|
||||||
z->u.binary.left = x;
|
|
||||||
z->u.binary.right = y;
|
|
||||||
return z;
|
|
||||||
}
|
|
||||||
return x;
|
|
||||||
}
|
|
||||||
|
|
||||||
static struct grep_expr *compile_pattern_expr(struct grep_pat **list)
|
|
||||||
{
|
|
||||||
return compile_pattern_or(list);
|
|
||||||
}
|
|
||||||
|
|
||||||
static void compile_patterns(struct grep_opt *opt)
|
|
||||||
{
|
|
||||||
struct grep_pat *p;
|
|
||||||
|
|
||||||
/* First compile regexps */
|
|
||||||
for (p = opt->pattern_list; p; p = p->next) {
|
|
||||||
if (p->token == GREP_PATTERN)
|
|
||||||
compile_regexp(p, opt);
|
|
||||||
else
|
|
||||||
opt->extended = 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!opt->extended)
|
|
||||||
return;
|
|
||||||
|
|
||||||
/* Then bundle them up in an expression.
|
|
||||||
* A classic recursive descent parser would do.
|
|
||||||
*/
|
|
||||||
p = opt->pattern_list;
|
|
||||||
opt->pattern_expression = compile_pattern_expr(&p);
|
|
||||||
if (p)
|
|
||||||
die("incomplete pattern expression: %s", p->pattern);
|
|
||||||
}
|
|
||||||
|
|
||||||
static char *end_of_line(char *cp, unsigned long *left)
|
|
||||||
{
|
|
||||||
unsigned long l = *left;
|
|
||||||
while (l && *cp != '\n') {
|
|
||||||
l--;
|
|
||||||
cp++;
|
|
||||||
}
|
|
||||||
*left = l;
|
|
||||||
return cp;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int word_char(char ch)
|
|
||||||
{
|
|
||||||
return isalnum(ch) || ch == '_';
|
|
||||||
}
|
|
||||||
|
|
||||||
static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
|
|
||||||
const char *name, unsigned lno, char sign)
|
|
||||||
{
|
|
||||||
if (opt->pathname)
|
|
||||||
printf("%s%c", name, sign);
|
|
||||||
if (opt->linenum)
|
|
||||||
printf("%d%c", lno, sign);
|
|
||||||
printf("%.*s\n", (int)(eol-bol), bol);
|
|
||||||
}
|
|
||||||
|
|
||||||
/*
|
|
||||||
* NEEDSWORK: share code with diff.c
|
|
||||||
*/
|
|
||||||
#define FIRST_FEW_BYTES 8000
|
|
||||||
static int buffer_is_binary(const char *ptr, unsigned long size)
|
|
||||||
{
|
|
||||||
if (FIRST_FEW_BYTES < size)
|
|
||||||
size = FIRST_FEW_BYTES;
|
|
||||||
return !!memchr(ptr, 0, size);
|
|
||||||
}
|
|
||||||
|
|
||||||
static int fixmatch(const char *pattern, char *line, regmatch_t *match)
|
|
||||||
{
|
|
||||||
char *hit = strstr(line, pattern);
|
|
||||||
if (!hit) {
|
|
||||||
match->rm_so = match->rm_eo = -1;
|
|
||||||
return REG_NOMATCH;
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
match->rm_so = hit - line;
|
|
||||||
match->rm_eo = match->rm_so + strlen(pattern);
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol)
|
|
||||||
{
|
|
||||||
int hit = 0;
|
|
||||||
int at_true_bol = 1;
|
|
||||||
regmatch_t pmatch[10];
|
|
||||||
|
|
||||||
again:
|
|
||||||
if (!opt->fixed) {
|
|
||||||
regex_t *exp = &p->regexp;
|
|
||||||
hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
|
|
||||||
pmatch, 0);
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
hit = !fixmatch(p->pattern, bol, pmatch);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (hit && opt->word_regexp) {
|
|
||||||
if ((pmatch[0].rm_so < 0) ||
|
|
||||||
(eol - bol) <= pmatch[0].rm_so ||
|
|
||||||
(pmatch[0].rm_eo < 0) ||
|
|
||||||
(eol - bol) < pmatch[0].rm_eo)
|
|
||||||
die("regexp returned nonsense");
|
|
||||||
|
|
||||||
/* Match beginning must be either beginning of the
|
|
||||||
* line, or at word boundary (i.e. the last char must
|
|
||||||
* not be a word char). Similarly, match end must be
|
|
||||||
* either end of the line, or at word boundary
|
|
||||||
* (i.e. the next char must not be a word char).
|
|
||||||
*/
|
|
||||||
if ( ((pmatch[0].rm_so == 0 && at_true_bol) ||
|
|
||||||
!word_char(bol[pmatch[0].rm_so-1])) &&
|
|
||||||
((pmatch[0].rm_eo == (eol-bol)) ||
|
|
||||||
!word_char(bol[pmatch[0].rm_eo])) )
|
|
||||||
;
|
|
||||||
else
|
|
||||||
hit = 0;
|
|
||||||
|
|
||||||
if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
|
|
||||||
/* There could be more than one match on the
|
|
||||||
* line, and the first match might not be
|
|
||||||
* strict word match. But later ones could be!
|
|
||||||
*/
|
|
||||||
bol = pmatch[0].rm_so + bol + 1;
|
|
||||||
at_true_bol = 0;
|
|
||||||
goto again;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return hit;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int match_expr_eval(struct grep_opt *opt,
|
|
||||||
struct grep_expr *x,
|
|
||||||
char *bol, char *eol)
|
|
||||||
{
|
|
||||||
switch (x->node) {
|
|
||||||
case GREP_NODE_ATOM:
|
|
||||||
return match_one_pattern(opt, x->u.atom, bol, eol);
|
|
||||||
break;
|
|
||||||
case GREP_NODE_NOT:
|
|
||||||
return !match_expr_eval(opt, x->u.unary, bol, eol);
|
|
||||||
case GREP_NODE_AND:
|
|
||||||
return (match_expr_eval(opt, x->u.binary.left, bol, eol) &&
|
|
||||||
match_expr_eval(opt, x->u.binary.right, bol, eol));
|
|
||||||
case GREP_NODE_OR:
|
|
||||||
return (match_expr_eval(opt, x->u.binary.left, bol, eol) ||
|
|
||||||
match_expr_eval(opt, x->u.binary.right, bol, eol));
|
|
||||||
}
|
|
||||||
die("Unexpected node type (internal error) %d\n", x->node);
|
|
||||||
}
|
|
||||||
|
|
||||||
static int match_expr(struct grep_opt *opt, char *bol, char *eol)
|
|
||||||
{
|
|
||||||
struct grep_expr *x = opt->pattern_expression;
|
|
||||||
return match_expr_eval(opt, x, bol, eol);
|
|
||||||
}
|
|
||||||
|
|
||||||
static int match_line(struct grep_opt *opt, char *bol, char *eol)
|
|
||||||
{
|
|
||||||
struct grep_pat *p;
|
|
||||||
if (opt->extended)
|
|
||||||
return match_expr(opt, bol, eol);
|
|
||||||
for (p = opt->pattern_list; p; p = p->next) {
|
|
||||||
if (match_one_pattern(opt, p, bol, eol))
|
|
||||||
return 1;
|
|
||||||
}
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int grep_buffer(struct grep_opt *opt, const char *name,
|
|
||||||
char *buf, unsigned long size)
|
|
||||||
{
|
|
||||||
char *bol = buf;
|
|
||||||
unsigned long left = size;
|
|
||||||
unsigned lno = 1;
|
|
||||||
struct pre_context_line {
|
|
||||||
char *bol;
|
|
||||||
char *eol;
|
|
||||||
} *prev = NULL, *pcl;
|
|
||||||
unsigned last_hit = 0;
|
|
||||||
unsigned last_shown = 0;
|
|
||||||
int binary_match_only = 0;
|
|
||||||
const char *hunk_mark = "";
|
|
||||||
unsigned count = 0;
|
|
||||||
|
|
||||||
if (buffer_is_binary(buf, size)) {
|
|
||||||
switch (opt->binary) {
|
|
||||||
case GREP_BINARY_DEFAULT:
|
|
||||||
binary_match_only = 1;
|
|
||||||
break;
|
|
||||||
case GREP_BINARY_NOMATCH:
|
|
||||||
return 0; /* Assume unmatch */
|
|
||||||
break;
|
|
||||||
default:
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
if (opt->pre_context)
|
|
||||||
prev = xcalloc(opt->pre_context, sizeof(*prev));
|
|
||||||
if (opt->pre_context || opt->post_context)
|
|
||||||
hunk_mark = "--\n";
|
|
||||||
|
|
||||||
while (left) {
|
|
||||||
char *eol, ch;
|
|
||||||
int hit = 0;
|
|
||||||
|
|
||||||
eol = end_of_line(bol, &left);
|
|
||||||
ch = *eol;
|
|
||||||
*eol = 0;
|
|
||||||
|
|
||||||
hit = match_line(opt, bol, eol);
|
|
||||||
|
|
||||||
/* "grep -v -e foo -e bla" should list lines
|
|
||||||
* that do not have either, so inversion should
|
|
||||||
* be done outside.
|
|
||||||
*/
|
|
||||||
if (opt->invert)
|
|
||||||
hit = !hit;
|
|
||||||
if (opt->unmatch_name_only) {
|
|
||||||
if (hit)
|
|
||||||
return 0;
|
|
||||||
goto next_line;
|
|
||||||
}
|
|
||||||
if (hit) {
|
|
||||||
count++;
|
|
||||||
if (binary_match_only) {
|
|
||||||
printf("Binary file %s matches\n", name);
|
|
||||||
return 1;
|
|
||||||
}
|
|
||||||
if (opt->name_only) {
|
|
||||||
printf("%s\n", name);
|
|
||||||
return 1;
|
|
||||||
}
|
|
||||||
/* Hit at this line. If we haven't shown the
|
|
||||||
* pre-context lines, we would need to show them.
|
|
||||||
* When asked to do "count", this still show
|
|
||||||
* the context which is nonsense, but the user
|
|
||||||
* deserves to get that ;-).
|
|
||||||
*/
|
|
||||||
if (opt->pre_context) {
|
|
||||||
unsigned from;
|
|
||||||
if (opt->pre_context < lno)
|
|
||||||
from = lno - opt->pre_context;
|
|
||||||
else
|
|
||||||
from = 1;
|
|
||||||
if (from <= last_shown)
|
|
||||||
from = last_shown + 1;
|
|
||||||
if (last_shown && from != last_shown + 1)
|
|
||||||
printf(hunk_mark);
|
|
||||||
while (from < lno) {
|
|
||||||
pcl = &prev[lno-from-1];
|
|
||||||
show_line(opt, pcl->bol, pcl->eol,
|
|
||||||
name, from, '-');
|
|
||||||
from++;
|
|
||||||
}
|
|
||||||
last_shown = lno-1;
|
|
||||||
}
|
|
||||||
if (last_shown && lno != last_shown + 1)
|
|
||||||
printf(hunk_mark);
|
|
||||||
if (!opt->count)
|
|
||||||
show_line(opt, bol, eol, name, lno, ':');
|
|
||||||
last_shown = last_hit = lno;
|
|
||||||
}
|
|
||||||
else if (last_hit &&
|
|
||||||
lno <= last_hit + opt->post_context) {
|
|
||||||
/* If the last hit is within the post context,
|
|
||||||
* we need to show this line.
|
|
||||||
*/
|
|
||||||
if (last_shown && lno != last_shown + 1)
|
|
||||||
printf(hunk_mark);
|
|
||||||
show_line(opt, bol, eol, name, lno, '-');
|
|
||||||
last_shown = lno;
|
|
||||||
}
|
|
||||||
if (opt->pre_context) {
|
|
||||||
memmove(prev+1, prev,
|
|
||||||
(opt->pre_context-1) * sizeof(*prev));
|
|
||||||
prev->bol = bol;
|
|
||||||
prev->eol = eol;
|
|
||||||
}
|
|
||||||
|
|
||||||
next_line:
|
|
||||||
*eol = ch;
|
|
||||||
bol = eol + 1;
|
|
||||||
if (!left)
|
|
||||||
break;
|
|
||||||
left--;
|
|
||||||
lno++;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (opt->unmatch_name_only) {
|
|
||||||
/* We did not see any hit, so we want to show this */
|
|
||||||
printf("%s\n", name);
|
|
||||||
return 1;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* NEEDSWORK:
|
|
||||||
* The real "grep -c foo *.c" gives many "bar.c:0" lines,
|
|
||||||
* which feels mostly useless but sometimes useful. Maybe
|
|
||||||
* make it another option? For now suppress them.
|
|
||||||
*/
|
|
||||||
if (opt->count && count)
|
|
||||||
printf("%s:%u\n", name, count);
|
|
||||||
return !!last_hit;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name, int tree_name_len)
|
static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name, int tree_name_len)
|
||||||
{
|
{
|
||||||
unsigned long size;
|
unsigned long size;
|
||||||
|
|
@ -1055,8 +564,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
|
||||||
/* ignore empty line like grep does */
|
/* ignore empty line like grep does */
|
||||||
if (!buf[0])
|
if (!buf[0])
|
||||||
continue;
|
continue;
|
||||||
add_pattern(&opt, xstrdup(buf), argv[1], ++lno,
|
append_grep_pattern(&opt, xstrdup(buf),
|
||||||
GREP_PATTERN);
|
argv[1], ++lno,
|
||||||
|
GREP_PATTERN);
|
||||||
}
|
}
|
||||||
fclose(patterns);
|
fclose(patterns);
|
||||||
argv++;
|
argv++;
|
||||||
|
|
@ -1064,27 +574,32 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
if (!strcmp("--not", arg)) {
|
if (!strcmp("--not", arg)) {
|
||||||
add_pattern(&opt, arg, "command line", 0, GREP_NOT);
|
append_grep_pattern(&opt, arg, "command line", 0,
|
||||||
|
GREP_NOT);
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
if (!strcmp("--and", arg)) {
|
if (!strcmp("--and", arg)) {
|
||||||
add_pattern(&opt, arg, "command line", 0, GREP_AND);
|
append_grep_pattern(&opt, arg, "command line", 0,
|
||||||
|
GREP_AND);
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
if (!strcmp("--or", arg))
|
if (!strcmp("--or", arg))
|
||||||
continue; /* no-op */
|
continue; /* no-op */
|
||||||
if (!strcmp("(", arg)) {
|
if (!strcmp("(", arg)) {
|
||||||
add_pattern(&opt, arg, "command line", 0, GREP_OPEN_PAREN);
|
append_grep_pattern(&opt, arg, "command line", 0,
|
||||||
|
GREP_OPEN_PAREN);
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
if (!strcmp(")", arg)) {
|
if (!strcmp(")", arg)) {
|
||||||
add_pattern(&opt, arg, "command line", 0, GREP_CLOSE_PAREN);
|
append_grep_pattern(&opt, arg, "command line", 0,
|
||||||
|
GREP_CLOSE_PAREN);
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
if (!strcmp("-e", arg)) {
|
if (!strcmp("-e", arg)) {
|
||||||
if (1 < argc) {
|
if (1 < argc) {
|
||||||
add_pattern(&opt, argv[1], "-e option", 0,
|
append_grep_pattern(&opt, argv[1],
|
||||||
GREP_PATTERN);
|
"-e option", 0,
|
||||||
|
GREP_PATTERN);
|
||||||
argv++;
|
argv++;
|
||||||
argc--;
|
argc--;
|
||||||
continue;
|
continue;
|
||||||
|
|
@ -1106,8 +621,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
|
||||||
|
|
||||||
/* First unrecognized non-option token */
|
/* First unrecognized non-option token */
|
||||||
if (!opt.pattern_list) {
|
if (!opt.pattern_list) {
|
||||||
add_pattern(&opt, arg, "command line", 0,
|
append_grep_pattern(&opt, arg, "command line", 0,
|
||||||
GREP_PATTERN);
|
GREP_PATTERN);
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
else {
|
else {
|
||||||
|
|
@ -1124,8 +639,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
|
||||||
die("no pattern given.");
|
die("no pattern given.");
|
||||||
if ((opt.regflags != REG_NEWLINE) && opt.fixed)
|
if ((opt.regflags != REG_NEWLINE) && opt.fixed)
|
||||||
die("cannot mix --fixed-strings and regexp");
|
die("cannot mix --fixed-strings and regexp");
|
||||||
if (!opt.fixed)
|
compile_grep_patterns(&opt);
|
||||||
compile_patterns(&opt);
|
|
||||||
|
|
||||||
/* Check revs and then paths */
|
/* Check revs and then paths */
|
||||||
for (i = 1; i < argc; i++) {
|
for (i = 1; i < argc; i++) {
|
||||||
|
|
|
||||||
|
|
@ -269,7 +269,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
|
||||||
revs.diff)
|
revs.diff)
|
||||||
usage(rev_list_usage);
|
usage(rev_list_usage);
|
||||||
|
|
||||||
save_commit_buffer = revs.verbose_header;
|
save_commit_buffer = revs.verbose_header || revs.grep_filter;
|
||||||
track_object_refs = 0;
|
track_object_refs = 0;
|
||||||
if (bisect_list)
|
if (bisect_list)
|
||||||
revs.limited = 1;
|
revs.limited = 1;
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,459 @@
|
||||||
|
#include "cache.h"
|
||||||
|
#include <regex.h>
|
||||||
|
#include "grep.h"
|
||||||
|
|
||||||
|
void append_grep_pattern(struct grep_opt *opt, const char *pat,
|
||||||
|
const char *origin, int no, enum grep_pat_token t)
|
||||||
|
{
|
||||||
|
struct grep_pat *p = xcalloc(1, sizeof(*p));
|
||||||
|
p->pattern = pat;
|
||||||
|
p->origin = origin;
|
||||||
|
p->no = no;
|
||||||
|
p->token = t;
|
||||||
|
*opt->pattern_tail = p;
|
||||||
|
opt->pattern_tail = &p->next;
|
||||||
|
p->next = NULL;
|
||||||
|
}
|
||||||
|
|
||||||
|
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
|
||||||
|
{
|
||||||
|
int err = regcomp(&p->regexp, p->pattern, opt->regflags);
|
||||||
|
if (err) {
|
||||||
|
char errbuf[1024];
|
||||||
|
char where[1024];
|
||||||
|
if (p->no)
|
||||||
|
sprintf(where, "In '%s' at %d, ",
|
||||||
|
p->origin, p->no);
|
||||||
|
else if (p->origin)
|
||||||
|
sprintf(where, "%s, ", p->origin);
|
||||||
|
else
|
||||||
|
where[0] = 0;
|
||||||
|
regerror(err, &p->regexp, errbuf, 1024);
|
||||||
|
regfree(&p->regexp);
|
||||||
|
die("%s'%s': %s", where, p->pattern, errbuf);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static struct grep_expr *compile_pattern_expr(struct grep_pat **);
|
||||||
|
static struct grep_expr *compile_pattern_atom(struct grep_pat **list)
|
||||||
|
{
|
||||||
|
struct grep_pat *p;
|
||||||
|
struct grep_expr *x;
|
||||||
|
|
||||||
|
p = *list;
|
||||||
|
switch (p->token) {
|
||||||
|
case GREP_PATTERN: /* atom */
|
||||||
|
case GREP_PATTERN_HEAD:
|
||||||
|
case GREP_PATTERN_BODY:
|
||||||
|
x = xcalloc(1, sizeof (struct grep_expr));
|
||||||
|
x->node = GREP_NODE_ATOM;
|
||||||
|
x->u.atom = p;
|
||||||
|
*list = p->next;
|
||||||
|
return x;
|
||||||
|
case GREP_OPEN_PAREN:
|
||||||
|
*list = p->next;
|
||||||
|
x = compile_pattern_expr(list);
|
||||||
|
if (!x)
|
||||||
|
return NULL;
|
||||||
|
if (!*list || (*list)->token != GREP_CLOSE_PAREN)
|
||||||
|
die("unmatched parenthesis");
|
||||||
|
*list = (*list)->next;
|
||||||
|
return x;
|
||||||
|
default:
|
||||||
|
return NULL;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static struct grep_expr *compile_pattern_not(struct grep_pat **list)
|
||||||
|
{
|
||||||
|
struct grep_pat *p;
|
||||||
|
struct grep_expr *x;
|
||||||
|
|
||||||
|
p = *list;
|
||||||
|
switch (p->token) {
|
||||||
|
case GREP_NOT:
|
||||||
|
if (!p->next)
|
||||||
|
die("--not not followed by pattern expression");
|
||||||
|
*list = p->next;
|
||||||
|
x = xcalloc(1, sizeof (struct grep_expr));
|
||||||
|
x->node = GREP_NODE_NOT;
|
||||||
|
x->u.unary = compile_pattern_not(list);
|
||||||
|
if (!x->u.unary)
|
||||||
|
die("--not followed by non pattern expression");
|
||||||
|
return x;
|
||||||
|
default:
|
||||||
|
return compile_pattern_atom(list);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static struct grep_expr *compile_pattern_and(struct grep_pat **list)
|
||||||
|
{
|
||||||
|
struct grep_pat *p;
|
||||||
|
struct grep_expr *x, *y, *z;
|
||||||
|
|
||||||
|
x = compile_pattern_not(list);
|
||||||
|
p = *list;
|
||||||
|
if (p && p->token == GREP_AND) {
|
||||||
|
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));
|
||||||
|
z->node = GREP_NODE_AND;
|
||||||
|
z->u.binary.left = x;
|
||||||
|
z->u.binary.right = y;
|
||||||
|
return z;
|
||||||
|
}
|
||||||
|
return x;
|
||||||
|
}
|
||||||
|
|
||||||
|
static struct grep_expr *compile_pattern_or(struct grep_pat **list)
|
||||||
|
{
|
||||||
|
struct grep_pat *p;
|
||||||
|
struct grep_expr *x, *y, *z;
|
||||||
|
|
||||||
|
x = compile_pattern_and(list);
|
||||||
|
p = *list;
|
||||||
|
if (x && p && p->token != GREP_CLOSE_PAREN) {
|
||||||
|
y = compile_pattern_or(list);
|
||||||
|
if (!y)
|
||||||
|
die("not a pattern expression %s", p->pattern);
|
||||||
|
z = xcalloc(1, sizeof (struct grep_expr));
|
||||||
|
z->node = GREP_NODE_OR;
|
||||||
|
z->u.binary.left = x;
|
||||||
|
z->u.binary.right = y;
|
||||||
|
return z;
|
||||||
|
}
|
||||||
|
return x;
|
||||||
|
}
|
||||||
|
|
||||||
|
static struct grep_expr *compile_pattern_expr(struct grep_pat **list)
|
||||||
|
{
|
||||||
|
return compile_pattern_or(list);
|
||||||
|
}
|
||||||
|
|
||||||
|
void compile_grep_patterns(struct grep_opt *opt)
|
||||||
|
{
|
||||||
|
struct grep_pat *p;
|
||||||
|
|
||||||
|
if (opt->fixed)
|
||||||
|
return;
|
||||||
|
|
||||||
|
/* First compile regexps */
|
||||||
|
for (p = opt->pattern_list; p; p = p->next) {
|
||||||
|
switch (p->token) {
|
||||||
|
case GREP_PATTERN: /* atom */
|
||||||
|
case GREP_PATTERN_HEAD:
|
||||||
|
case GREP_PATTERN_BODY:
|
||||||
|
compile_regexp(p, opt);
|
||||||
|
break;
|
||||||
|
default:
|
||||||
|
opt->extended = 1;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if (!opt->extended)
|
||||||
|
return;
|
||||||
|
|
||||||
|
/* Then bundle them up in an expression.
|
||||||
|
* A classic recursive descent parser would do.
|
||||||
|
*/
|
||||||
|
p = opt->pattern_list;
|
||||||
|
opt->pattern_expression = compile_pattern_expr(&p);
|
||||||
|
if (p)
|
||||||
|
die("incomplete pattern expression: %s", p->pattern);
|
||||||
|
}
|
||||||
|
|
||||||
|
static char *end_of_line(char *cp, unsigned long *left)
|
||||||
|
{
|
||||||
|
unsigned long l = *left;
|
||||||
|
while (l && *cp != '\n') {
|
||||||
|
l--;
|
||||||
|
cp++;
|
||||||
|
}
|
||||||
|
*left = l;
|
||||||
|
return cp;
|
||||||
|
}
|
||||||
|
|
||||||
|
static int word_char(char ch)
|
||||||
|
{
|
||||||
|
return isalnum(ch) || ch == '_';
|
||||||
|
}
|
||||||
|
|
||||||
|
static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
|
||||||
|
const char *name, unsigned lno, char sign)
|
||||||
|
{
|
||||||
|
if (opt->pathname)
|
||||||
|
printf("%s%c", name, sign);
|
||||||
|
if (opt->linenum)
|
||||||
|
printf("%d%c", lno, sign);
|
||||||
|
printf("%.*s\n", (int)(eol-bol), bol);
|
||||||
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* NEEDSWORK: share code with diff.c
|
||||||
|
*/
|
||||||
|
#define FIRST_FEW_BYTES 8000
|
||||||
|
static int buffer_is_binary(const char *ptr, unsigned long size)
|
||||||
|
{
|
||||||
|
if (FIRST_FEW_BYTES < size)
|
||||||
|
size = FIRST_FEW_BYTES;
|
||||||
|
return !!memchr(ptr, 0, size);
|
||||||
|
}
|
||||||
|
|
||||||
|
static int fixmatch(const char *pattern, char *line, regmatch_t *match)
|
||||||
|
{
|
||||||
|
char *hit = strstr(line, pattern);
|
||||||
|
if (!hit) {
|
||||||
|
match->rm_so = match->rm_eo = -1;
|
||||||
|
return REG_NOMATCH;
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
match->rm_so = hit - line;
|
||||||
|
match->rm_eo = match->rm_so + strlen(pattern);
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol, enum grep_context ctx)
|
||||||
|
{
|
||||||
|
int hit = 0;
|
||||||
|
int at_true_bol = 1;
|
||||||
|
regmatch_t pmatch[10];
|
||||||
|
|
||||||
|
if ((p->token != GREP_PATTERN) &&
|
||||||
|
((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
|
||||||
|
return 0;
|
||||||
|
|
||||||
|
again:
|
||||||
|
if (!opt->fixed) {
|
||||||
|
regex_t *exp = &p->regexp;
|
||||||
|
hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
|
||||||
|
pmatch, 0);
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
hit = !fixmatch(p->pattern, bol, pmatch);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (hit && opt->word_regexp) {
|
||||||
|
if ((pmatch[0].rm_so < 0) ||
|
||||||
|
(eol - bol) <= pmatch[0].rm_so ||
|
||||||
|
(pmatch[0].rm_eo < 0) ||
|
||||||
|
(eol - bol) < pmatch[0].rm_eo)
|
||||||
|
die("regexp returned nonsense");
|
||||||
|
|
||||||
|
/* Match beginning must be either beginning of the
|
||||||
|
* line, or at word boundary (i.e. the last char must
|
||||||
|
* not be a word char). Similarly, match end must be
|
||||||
|
* either end of the line, or at word boundary
|
||||||
|
* (i.e. the next char must not be a word char).
|
||||||
|
*/
|
||||||
|
if ( ((pmatch[0].rm_so == 0 && at_true_bol) ||
|
||||||
|
!word_char(bol[pmatch[0].rm_so-1])) &&
|
||||||
|
((pmatch[0].rm_eo == (eol-bol)) ||
|
||||||
|
!word_char(bol[pmatch[0].rm_eo])) )
|
||||||
|
;
|
||||||
|
else
|
||||||
|
hit = 0;
|
||||||
|
|
||||||
|
if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
|
||||||
|
/* There could be more than one match on the
|
||||||
|
* line, and the first match might not be
|
||||||
|
* strict word match. But later ones could be!
|
||||||
|
*/
|
||||||
|
bol = pmatch[0].rm_so + bol + 1;
|
||||||
|
at_true_bol = 0;
|
||||||
|
goto again;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return hit;
|
||||||
|
}
|
||||||
|
|
||||||
|
static int match_expr_eval(struct grep_opt *opt,
|
||||||
|
struct grep_expr *x,
|
||||||
|
char *bol, char *eol,
|
||||||
|
enum grep_context ctx)
|
||||||
|
{
|
||||||
|
switch (x->node) {
|
||||||
|
case GREP_NODE_ATOM:
|
||||||
|
return match_one_pattern(opt, x->u.atom, bol, eol, ctx);
|
||||||
|
break;
|
||||||
|
case GREP_NODE_NOT:
|
||||||
|
return !match_expr_eval(opt, x->u.unary, bol, eol, ctx);
|
||||||
|
case GREP_NODE_AND:
|
||||||
|
return (match_expr_eval(opt, x->u.binary.left, bol, eol, ctx) &&
|
||||||
|
match_expr_eval(opt, x->u.binary.right, bol, eol, ctx));
|
||||||
|
case GREP_NODE_OR:
|
||||||
|
return (match_expr_eval(opt, x->u.binary.left, bol, eol, ctx) ||
|
||||||
|
match_expr_eval(opt, x->u.binary.right, bol, eol, ctx));
|
||||||
|
}
|
||||||
|
die("Unexpected node type (internal error) %d\n", x->node);
|
||||||
|
}
|
||||||
|
|
||||||
|
static int match_expr(struct grep_opt *opt, char *bol, char *eol,
|
||||||
|
enum grep_context ctx)
|
||||||
|
{
|
||||||
|
struct grep_expr *x = opt->pattern_expression;
|
||||||
|
return match_expr_eval(opt, x, bol, eol, ctx);
|
||||||
|
}
|
||||||
|
|
||||||
|
static int match_line(struct grep_opt *opt, char *bol, char *eol,
|
||||||
|
enum grep_context ctx)
|
||||||
|
{
|
||||||
|
struct grep_pat *p;
|
||||||
|
if (opt->extended)
|
||||||
|
return match_expr(opt, bol, eol, ctx);
|
||||||
|
for (p = opt->pattern_list; p; p = p->next) {
|
||||||
|
if (match_one_pattern(opt, p, bol, eol, ctx))
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size)
|
||||||
|
{
|
||||||
|
char *bol = buf;
|
||||||
|
unsigned long left = size;
|
||||||
|
unsigned lno = 1;
|
||||||
|
struct pre_context_line {
|
||||||
|
char *bol;
|
||||||
|
char *eol;
|
||||||
|
} *prev = NULL, *pcl;
|
||||||
|
unsigned last_hit = 0;
|
||||||
|
unsigned last_shown = 0;
|
||||||
|
int binary_match_only = 0;
|
||||||
|
const char *hunk_mark = "";
|
||||||
|
unsigned count = 0;
|
||||||
|
enum grep_context ctx = GREP_CONTEXT_HEAD;
|
||||||
|
|
||||||
|
if (buffer_is_binary(buf, size)) {
|
||||||
|
switch (opt->binary) {
|
||||||
|
case GREP_BINARY_DEFAULT:
|
||||||
|
binary_match_only = 1;
|
||||||
|
break;
|
||||||
|
case GREP_BINARY_NOMATCH:
|
||||||
|
return 0; /* Assume unmatch */
|
||||||
|
break;
|
||||||
|
default:
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if (opt->pre_context)
|
||||||
|
prev = xcalloc(opt->pre_context, sizeof(*prev));
|
||||||
|
if (opt->pre_context || opt->post_context)
|
||||||
|
hunk_mark = "--\n";
|
||||||
|
|
||||||
|
while (left) {
|
||||||
|
char *eol, ch;
|
||||||
|
int hit = 0;
|
||||||
|
|
||||||
|
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, ctx);
|
||||||
|
*eol = ch;
|
||||||
|
|
||||||
|
/* "grep -v -e foo -e bla" should list lines
|
||||||
|
* that do not have either, so inversion should
|
||||||
|
* be done outside.
|
||||||
|
*/
|
||||||
|
if (opt->invert)
|
||||||
|
hit = !hit;
|
||||||
|
if (opt->unmatch_name_only) {
|
||||||
|
if (hit)
|
||||||
|
return 0;
|
||||||
|
goto next_line;
|
||||||
|
}
|
||||||
|
if (hit) {
|
||||||
|
count++;
|
||||||
|
if (opt->status_only)
|
||||||
|
return 1;
|
||||||
|
if (binary_match_only) {
|
||||||
|
printf("Binary file %s matches\n", name);
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
if (opt->name_only) {
|
||||||
|
printf("%s\n", name);
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
/* Hit at this line. If we haven't shown the
|
||||||
|
* pre-context lines, we would need to show them.
|
||||||
|
* When asked to do "count", this still show
|
||||||
|
* the context which is nonsense, but the user
|
||||||
|
* deserves to get that ;-).
|
||||||
|
*/
|
||||||
|
if (opt->pre_context) {
|
||||||
|
unsigned from;
|
||||||
|
if (opt->pre_context < lno)
|
||||||
|
from = lno - opt->pre_context;
|
||||||
|
else
|
||||||
|
from = 1;
|
||||||
|
if (from <= last_shown)
|
||||||
|
from = last_shown + 1;
|
||||||
|
if (last_shown && from != last_shown + 1)
|
||||||
|
printf(hunk_mark);
|
||||||
|
while (from < lno) {
|
||||||
|
pcl = &prev[lno-from-1];
|
||||||
|
show_line(opt, pcl->bol, pcl->eol,
|
||||||
|
name, from, '-');
|
||||||
|
from++;
|
||||||
|
}
|
||||||
|
last_shown = lno-1;
|
||||||
|
}
|
||||||
|
if (last_shown && lno != last_shown + 1)
|
||||||
|
printf(hunk_mark);
|
||||||
|
if (!opt->count)
|
||||||
|
show_line(opt, bol, eol, name, lno, ':');
|
||||||
|
last_shown = last_hit = lno;
|
||||||
|
}
|
||||||
|
else if (last_hit &&
|
||||||
|
lno <= last_hit + opt->post_context) {
|
||||||
|
/* If the last hit is within the post context,
|
||||||
|
* we need to show this line.
|
||||||
|
*/
|
||||||
|
if (last_shown && lno != last_shown + 1)
|
||||||
|
printf(hunk_mark);
|
||||||
|
show_line(opt, bol, eol, name, lno, '-');
|
||||||
|
last_shown = lno;
|
||||||
|
}
|
||||||
|
if (opt->pre_context) {
|
||||||
|
memmove(prev+1, prev,
|
||||||
|
(opt->pre_context-1) * sizeof(*prev));
|
||||||
|
prev->bol = bol;
|
||||||
|
prev->eol = eol;
|
||||||
|
}
|
||||||
|
|
||||||
|
next_line:
|
||||||
|
bol = eol + 1;
|
||||||
|
if (!left)
|
||||||
|
break;
|
||||||
|
left--;
|
||||||
|
lno++;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (opt->status_only)
|
||||||
|
return 0;
|
||||||
|
if (opt->unmatch_name_only) {
|
||||||
|
/* We did not see any hit, so we want to show this */
|
||||||
|
printf("%s\n", name);
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* NEEDSWORK:
|
||||||
|
* The real "grep -c foo *.c" gives many "bar.c:0" lines,
|
||||||
|
* which feels mostly useless but sometimes useful. Maybe
|
||||||
|
* make it another option? For now suppress them.
|
||||||
|
*/
|
||||||
|
if (opt->count && count)
|
||||||
|
printf("%s:%u\n", name, count);
|
||||||
|
return !!last_hit;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
@ -0,0 +1,78 @@
|
||||||
|
#ifndef GREP_H
|
||||||
|
#define GREP_H
|
||||||
|
|
||||||
|
enum grep_pat_token {
|
||||||
|
GREP_PATTERN,
|
||||||
|
GREP_PATTERN_HEAD,
|
||||||
|
GREP_PATTERN_BODY,
|
||||||
|
GREP_AND,
|
||||||
|
GREP_OPEN_PAREN,
|
||||||
|
GREP_CLOSE_PAREN,
|
||||||
|
GREP_NOT,
|
||||||
|
GREP_OR,
|
||||||
|
};
|
||||||
|
|
||||||
|
enum grep_context {
|
||||||
|
GREP_CONTEXT_HEAD,
|
||||||
|
GREP_CONTEXT_BODY,
|
||||||
|
};
|
||||||
|
|
||||||
|
struct grep_pat {
|
||||||
|
struct grep_pat *next;
|
||||||
|
const char *origin;
|
||||||
|
int no;
|
||||||
|
enum grep_pat_token token;
|
||||||
|
const char *pattern;
|
||||||
|
regex_t regexp;
|
||||||
|
};
|
||||||
|
|
||||||
|
enum grep_expr_node {
|
||||||
|
GREP_NODE_ATOM,
|
||||||
|
GREP_NODE_NOT,
|
||||||
|
GREP_NODE_AND,
|
||||||
|
GREP_NODE_OR,
|
||||||
|
};
|
||||||
|
|
||||||
|
struct grep_expr {
|
||||||
|
enum grep_expr_node node;
|
||||||
|
union {
|
||||||
|
struct grep_pat *atom;
|
||||||
|
struct grep_expr *unary;
|
||||||
|
struct {
|
||||||
|
struct grep_expr *left;
|
||||||
|
struct grep_expr *right;
|
||||||
|
} binary;
|
||||||
|
} u;
|
||||||
|
};
|
||||||
|
|
||||||
|
struct grep_opt {
|
||||||
|
struct grep_pat *pattern_list;
|
||||||
|
struct grep_pat **pattern_tail;
|
||||||
|
struct grep_expr *pattern_expression;
|
||||||
|
int prefix_length;
|
||||||
|
regex_t regexp;
|
||||||
|
unsigned linenum:1;
|
||||||
|
unsigned invert:1;
|
||||||
|
unsigned status_only:1;
|
||||||
|
unsigned name_only:1;
|
||||||
|
unsigned unmatch_name_only:1;
|
||||||
|
unsigned count:1;
|
||||||
|
unsigned word_regexp:1;
|
||||||
|
unsigned fixed:1;
|
||||||
|
#define GREP_BINARY_DEFAULT 0
|
||||||
|
#define GREP_BINARY_NOMATCH 1
|
||||||
|
#define GREP_BINARY_TEXT 2
|
||||||
|
unsigned binary:2;
|
||||||
|
unsigned extended:1;
|
||||||
|
unsigned relative:1;
|
||||||
|
unsigned pathname:1;
|
||||||
|
int regflags;
|
||||||
|
unsigned pre_context;
|
||||||
|
unsigned post_context;
|
||||||
|
};
|
||||||
|
|
||||||
|
extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
|
||||||
|
extern void compile_grep_patterns(struct grep_opt *opt);
|
||||||
|
extern int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size);
|
||||||
|
|
||||||
|
#endif
|
||||||
69
revision.c
69
revision.c
|
|
@ -6,6 +6,8 @@
|
||||||
#include "diff.h"
|
#include "diff.h"
|
||||||
#include "refs.h"
|
#include "refs.h"
|
||||||
#include "revision.h"
|
#include "revision.h"
|
||||||
|
#include <regex.h>
|
||||||
|
#include "grep.h"
|
||||||
|
|
||||||
static char *path_name(struct name_path *path, const char *name)
|
static char *path_name(struct name_path *path, const char *name)
|
||||||
{
|
{
|
||||||
|
|
@ -672,6 +674,42 @@ int handle_revision_arg(const char *arg, struct rev_info *revs,
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static void add_grep(struct rev_info *revs, const char *ptn, enum grep_pat_token what)
|
||||||
|
{
|
||||||
|
if (!revs->grep_filter) {
|
||||||
|
struct grep_opt *opt = xcalloc(1, sizeof(*opt));
|
||||||
|
opt->status_only = 1;
|
||||||
|
opt->pattern_tail = &(opt->pattern_list);
|
||||||
|
opt->regflags = REG_NEWLINE;
|
||||||
|
revs->grep_filter = opt;
|
||||||
|
}
|
||||||
|
append_grep_pattern(revs->grep_filter, ptn,
|
||||||
|
"command line", 0, what);
|
||||||
|
}
|
||||||
|
|
||||||
|
static void add_header_grep(struct rev_info *revs, const char *field, const char *pattern)
|
||||||
|
{
|
||||||
|
char *pat;
|
||||||
|
const char *prefix;
|
||||||
|
int patlen, fldlen;
|
||||||
|
|
||||||
|
fldlen = strlen(field);
|
||||||
|
patlen = strlen(pattern);
|
||||||
|
pat = xmalloc(patlen + fldlen + 10);
|
||||||
|
prefix = ".*";
|
||||||
|
if (*pattern == '^') {
|
||||||
|
prefix = "";
|
||||||
|
pattern++;
|
||||||
|
}
|
||||||
|
sprintf(pat, "^%s %s%s", field, prefix, pattern);
|
||||||
|
add_grep(revs, pat, GREP_PATTERN_HEAD);
|
||||||
|
}
|
||||||
|
|
||||||
|
static void add_message_grep(struct rev_info *revs, const char *pattern)
|
||||||
|
{
|
||||||
|
add_grep(revs, pattern, GREP_PATTERN_BODY);
|
||||||
|
}
|
||||||
|
|
||||||
static void add_ignore_packed(struct rev_info *revs, const char *name)
|
static void add_ignore_packed(struct rev_info *revs, const char *name)
|
||||||
{
|
{
|
||||||
int num = ++revs->num_ignore_packed;
|
int num = ++revs->num_ignore_packed;
|
||||||
|
|
@ -913,6 +951,23 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
|
||||||
revs->relative_date = 1;
|
revs->relative_date = 1;
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Grepping the commit log
|
||||||
|
*/
|
||||||
|
if (!strncmp(arg, "--author=", 9)) {
|
||||||
|
add_header_grep(revs, "author", arg+9);
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
if (!strncmp(arg, "--committer=", 12)) {
|
||||||
|
add_header_grep(revs, "committer", arg+12);
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
if (!strncmp(arg, "--grep=", 7)) {
|
||||||
|
add_message_grep(revs, arg+7);
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
opts = diff_opt_parse(&revs->diffopt, argv+i, argc-i);
|
opts = diff_opt_parse(&revs->diffopt, argv+i, argc-i);
|
||||||
if (opts > 0) {
|
if (opts > 0) {
|
||||||
revs->diff = 1;
|
revs->diff = 1;
|
||||||
|
|
@ -973,6 +1028,9 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
|
||||||
if (diff_setup_done(&revs->diffopt) < 0)
|
if (diff_setup_done(&revs->diffopt) < 0)
|
||||||
die("diff_setup_done failed");
|
die("diff_setup_done failed");
|
||||||
|
|
||||||
|
if (revs->grep_filter)
|
||||||
|
compile_grep_patterns(revs->grep_filter);
|
||||||
|
|
||||||
return left;
|
return left;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -1045,6 +1103,15 @@ static void mark_boundary_to_show(struct commit *commit)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static int commit_match(struct commit *commit, struct rev_info *opt)
|
||||||
|
{
|
||||||
|
if (!opt->grep_filter)
|
||||||
|
return 1;
|
||||||
|
return grep_buffer(opt->grep_filter,
|
||||||
|
NULL, /* we say nothing, not even filename */
|
||||||
|
commit->buffer, strlen(commit->buffer));
|
||||||
|
}
|
||||||
|
|
||||||
struct commit *get_revision(struct rev_info *revs)
|
struct commit *get_revision(struct rev_info *revs)
|
||||||
{
|
{
|
||||||
struct commit_list *list = revs->commits;
|
struct commit_list *list = revs->commits;
|
||||||
|
|
@ -1105,6 +1172,8 @@ struct commit *get_revision(struct rev_info *revs)
|
||||||
if (revs->no_merges &&
|
if (revs->no_merges &&
|
||||||
commit->parents && commit->parents->next)
|
commit->parents && commit->parents->next)
|
||||||
continue;
|
continue;
|
||||||
|
if (!commit_match(commit, revs))
|
||||||
|
continue;
|
||||||
if (revs->prune_fn && revs->dense) {
|
if (revs->prune_fn && revs->dense) {
|
||||||
/* Commit without changes? */
|
/* Commit without changes? */
|
||||||
if (!(commit->object.flags & TREECHANGE)) {
|
if (!(commit->object.flags & TREECHANGE)) {
|
||||||
|
|
|
||||||
|
|
@ -71,6 +71,9 @@ struct rev_info {
|
||||||
const char *add_signoff;
|
const char *add_signoff;
|
||||||
const char *extra_headers;
|
const char *extra_headers;
|
||||||
|
|
||||||
|
/* Filter by commit log message */
|
||||||
|
struct grep_opt *grep_filter;
|
||||||
|
|
||||||
/* special limits */
|
/* special limits */
|
||||||
int max_count;
|
int max_count;
|
||||||
unsigned long max_age;
|
unsigned long max_age;
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue