#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;
+
+/*
+ * 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->regflags = REG_NEWLINE;
+ opt->max_depth = -1;
+ opt->pattern_type_option = GREP_PATTERN_TYPE_UNSPECIFIED;
+ opt->extended_regexp_option = 0;
+ 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;
+}
+
+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")) {
+ if (git_config_bool(var, value))
+ opt->extended_regexp_option = 1;
+ else
+ opt->extended_regexp_option = 0;
+ 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->regflags = def->regflags;
+ opt->relative = def->relative;
+
+ 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)
+{
+ switch (pattern_type) {
+ case GREP_PATTERN_TYPE_UNSPECIFIED:
+ /* fall through */
+
+ case GREP_PATTERN_TYPE_BRE:
+ opt->fixed = 0;
+ opt->pcre = 0;
+ opt->regflags &= ~REG_EXTENDED;
+ break;
+
+ case GREP_PATTERN_TYPE_ERE:
+ opt->fixed = 0;
+ opt->pcre = 0;
+ opt->regflags |= REG_EXTENDED;
+ break;
+
+ case GREP_PATTERN_TYPE_FIXED:
+ opt->fixed = 1;
+ opt->pcre = 0;
+ opt->regflags &= ~REG_EXTENDED;
+ break;
+
+ case GREP_PATTERN_TYPE_PCRE:
+ opt->fixed = 0;
+ opt->pcre = 1;
+ opt->regflags &= ~REG_EXTENDED;
+ 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)
+ 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;
int erroffset;
int options = PCRE_MULTILINE;
- if (opt->ignore_case)
+ if (opt->ignore_case) {
+ if (has_non_ascii(p->pattern))
+ p->pcre_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);
+ p->pcre_tables);
if (!p->pcre_regexp)
compile_regexp_failed(p, error);
{
pcre_free(p->pcre_regexp);
pcre_free(p->pcre_extra_info);
+ pcre_free((void *)p->pcre_tables);
}
#else /* !USE_LIBPCRE */
static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
return 1;
}
+static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
+{
+ struct strbuf sb = STRBUF_INIT;
+ int err;
+ int regflags;
+
+ basic_regex_quote_buf(&sb, p->pattern);
+ regflags = opt->regflags & ~REG_EXTENDED;
+ 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 icase, ascii_only;
int err;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
+ icase = opt->regflags & REG_ICASE || p->ignore_case;
+ ascii_only = !has_non_ascii(p->pattern);
+ /*
+ * 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 || is_fixed(p->pattern, p->patternlen))
- p->fixed = 1;
+ p->fixed = !icase || ascii_only;
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);
+ p->kws = kwsalloc(icase ? 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) {
}
}
-void dump_grep_expression(struct grep_opt *opt)
+static void dump_grep_expression(struct grep_opt *opt)
{
struct grep_expr *x = opt->pattern_expression;
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;
}
+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;
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);
}
}
-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)
{
else if (p->pcre_regexp)
hit = !pcrematch(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)
int ch = *eol;
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 == '-')
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;
fwrite(buf, size, 1, stdout);
}
+static int fill_textconv_grep(struct userdiff_driver *driver,
+ struct grep_source *gs)
+{
+ 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_SHA1:
+ fill_filespec(df, gs->identifier, 1, 0100644);
+ break;
+ case GREP_SOURCE_FILE:
+ fill_filespec(df, null_sha1, 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,
*/
if (opt->count && count) {
char buf[32];
- output_color(opt, gs->name, strlen(gs->name), opt->color_filename);
- output_sep(opt, ':');
+ if (opt->pathname) {
+ 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));
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;
break;
case GREP_SOURCE_SHA1:
gs->identifier = xmalloc(20);
- memcpy(gs->identifier, identifier, 20);
+ hashcpy(gs->identifier, identifier);
break;
case GREP_SOURCE_BUF:
gs->identifier = NULL;
{
free(gs->name);
gs->name = NULL;
+ free(gs->path);
+ gs->path = NULL;
free(gs->identifier);
gs->identifier = NULL;
grep_source_clear_data(gs);
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;
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)