*
* MAINTAINER: Rob Landley <rob@landley.net>
*
- * Licensed under GPL version 2, see file LICENSE in this tarball for details.
+ * Licensed under GPLv2, see file LICENSE in this source tree.
*/
/* Code overview.
#include "libbb.h"
#include "xregex.h"
+enum {
+ OPT_in_place = 1 << 0,
+};
+
/* Each sed command turns into one of these structures. */
typedef struct sed_cmd_s {
/* Ordered by alignment requirements: currently 36 bytes on x86 */
int idx; /* Space used */
int len; /* Space allocated */
} pipeline;
-};
+} FIX_ALIASING;
#define G (*(struct globals*)&bb_common_bufsiz1)
-void BUG_sed_globals_too_big(void);
+struct BUG_G_too_big {
+ char BUG_G_too_big[sizeof(G) <= COMMON_BUFSIZE ? 1 : -1];
+};
#define INIT_G() do { \
- if (sizeof(struct globals) > COMMON_BUFSIZE) \
- BUG_sed_globals_too_big(); \
G.sed_cmd_tail = &G.sed_cmd_head; \
} while (0)
continue;
}
/* Skip spaces */
- if (isspace(substr[idx])) continue;
+ if (isspace(substr[idx]))
+ continue;
switch (substr[idx]) {
/* Replace all occurrences */
break;
/* Comment */
case '#':
- while (substr[++idx]) /*skip all*/;
+ // while (substr[++idx]) continue;
+ idx += strlen(substr + idx); // same
/* Fall through */
/* End of command */
case ';':
bb_error_msg_and_die("bad option in substitution expression");
}
}
-out:
+ out:
/* compile the match string into a regex */
if (*match != '\0') {
/* If match is empty, we use last regex used at runtime */
/* handle edit cmds: (a)ppend, (i)nsert, and (c)hange */
else if (strchr("aic", sed_cmd->cmd)) {
if ((sed_cmd->end_line || sed_cmd->end_match) && sed_cmd->cmd != 'c')
- bb_error_msg_and_die
- ("only a beginning address can be specified for edit commands");
+ bb_error_msg_and_die("only a beginning address can be specified for edit commands");
for (;;) {
if (*cmdstr == '\n' || *cmdstr == '\\') {
cmdstr++;
break;
- } else if (isspace(*cmdstr))
- cmdstr++;
- else
+ }
+ if (!isspace(*cmdstr))
break;
+ cmdstr++;
}
sed_cmd->string = xstrdup(cmdstr);
/* "\anychar" -> "anychar" */
static void add_cmd(const char *cmdstr)
{
sed_cmd_t *sed_cmd;
- int temp;
+ unsigned len, n;
/* Append this line to any unfinished line from last time. */
if (G.add_cmd_line) {
cmdstr = G.add_cmd_line = tp;
}
- /* If this line ends with backslash, request next line. */
- temp = strlen(cmdstr);
- if (temp && cmdstr[--temp] == '\\') {
+ /* If this line ends with unescaped backslash, request next line. */
+ n = len = strlen(cmdstr);
+ while (n && cmdstr[n-1] == '\\')
+ n--;
+ if ((len - n) & 1) { /* if odd number of trailing backslashes */
if (!G.add_cmd_line)
G.add_cmd_line = xstrdup(cmdstr);
- G.add_cmd_line[temp] = '\0';
+ G.add_cmd_line[len-1] = '\0';
return;
}
/* last part (mandatory) will be a command */
if (!*cmdstr)
bb_error_msg_and_die("missing command");
- sed_cmd->cmd = *(cmdstr++);
+ sed_cmd->cmd = *cmdstr++;
cmdstr = parse_cmd_args(sed_cmd, cmdstr);
/* Add the command to the command array */
static void do_subst_w_backrefs(char *line, char *replace)
{
- int i,j;
+ int i, j;
/* go through the replacement string */
for (i = 0; replace[i]; i++) {
}
}
-static int do_subst_command(sed_cmd_t *sed_cmd, char **line)
+static int do_subst_command(sed_cmd_t *sed_cmd, char **line_p)
{
- char *oldline = *line;
+ char *line = *line_p;
int altered = 0;
unsigned match_count = 0;
regex_t *current_regex;
+ current_regex = sed_cmd->sub_match;
/* Handle empty regex. */
- if (sed_cmd->sub_match == NULL) {
+ if (!current_regex) {
current_regex = G.previous_regex_ptr;
if (!current_regex)
bb_error_msg_and_die("no previous regexp");
- } else
- G.previous_regex_ptr = current_regex = sed_cmd->sub_match;
+ }
+ G.previous_regex_ptr = current_regex;
/* Find the first match */
- if (REG_NOMATCH == regexec(current_regex, oldline, 10, G.regmatch, 0))
+ if (REG_NOMATCH == regexec(current_regex, line, 10, G.regmatch, 0))
return 0;
/* Initialize temporary output buffer. */
The match_count check is so not to break
echo "hi" | busybox sed 's/^/!/g' */
if (!G.regmatch[0].rm_so && !G.regmatch[0].rm_eo && match_count) {
- pipe_putc(*oldline++);
+ pipe_putc(*line++);
continue;
}
&& (sed_cmd->which_match != match_count)
) {
for (i = 0; i < G.regmatch[0].rm_eo; i++)
- pipe_putc(*oldline++);
+ pipe_putc(*line++);
continue;
}
/* print everything before the match */
for (i = 0; i < G.regmatch[0].rm_so; i++)
- pipe_putc(oldline[i]);
+ pipe_putc(line[i]);
/* then print the substitution string */
- do_subst_w_backrefs(oldline, sed_cmd->string);
+ do_subst_w_backrefs(line, sed_cmd->string);
/* advance past the match */
- oldline += G.regmatch[0].rm_eo;
+ line += G.regmatch[0].rm_eo;
/* flag that something has changed */
altered++;
/* if we're not doing this globally, get out now */
if (sed_cmd->which_match)
break;
- } while (*oldline && (regexec(current_regex, oldline, 10, G.regmatch, 0) != REG_NOMATCH));
- /* Copy rest of string into output pipeline */
+//maybe (G.regmatch[0].rm_eo ? REG_NOTBOL : 0) instead of unconditional REG_NOTBOL?
+ } while (*line && regexec(current_regex, line, 10, G.regmatch, REG_NOTBOL) != REG_NOMATCH);
- while (*oldline)
- pipe_putc(*oldline++);
- pipe_putc(0);
+ /* Copy rest of string into output pipeline */
+ while (1) {
+ char c = *line++;
+ pipe_putc(c);
+ if (c == '\0')
+ break;
+ }
- free(*line);
- *line = G.pipeline.buf;
+ free(*line_p);
+ *line_p = G.pipeline.buf;
return altered;
}
old_matched = sed_cmd->in_match;
/* Determine if this command matches this line: */
- /* Are we continuing a previous multi-line match? */
+
+ //bb_error_msg("match1:%d", sed_cmd->in_match);
+ //bb_error_msg("match2:%d", (!sed_cmd->beg_line && !sed_cmd->end_line
+ // && !sed_cmd->beg_match && !sed_cmd->end_match));
+ //bb_error_msg("match3:%d", (sed_cmd->beg_line > 0
+ // && (sed_cmd->end_line || sed_cmd->end_match
+ // ? (sed_cmd->beg_line <= linenum)
+ // : (sed_cmd->beg_line == linenum)
+ // )
+ // )
+ //bb_error_msg("match4:%d", (beg_match(sed_cmd, pattern_space)));
+ //bb_error_msg("match5:%d", (sed_cmd->beg_line == -1 && next_line == NULL));
+
+ /* Are we continuing a previous multi-line match? */
sed_cmd->in_match = sed_cmd->in_match
/* Or is no range necessary? */
|| (!sed_cmd->beg_line && !sed_cmd->end_line
&& !sed_cmd->beg_match && !sed_cmd->end_match)
/* Or did we match the start of a numerical range? */
|| (sed_cmd->beg_line > 0
- && (sed_cmd->beg_line == linenum
- /* GNU sed compat:
- * "shadowed beginning" case: "1d;1,ENDp" - p still matches at line 2
- * even though 1d skipped line 1 which is a start line for p */
- || (sed_cmd->beg_line < linenum && (sed_cmd->end_line > 0 || sed_cmd->end_match))
- )
- )
+ && (sed_cmd->end_line || sed_cmd->end_match
+ /* note: even if end is numeric and is < linenum too,
+ * GNU sed matches! We match too */
+ ? (sed_cmd->beg_line <= linenum) /* N,end */
+ : (sed_cmd->beg_line == linenum) /* N */
+ )
+ )
/* Or does this line match our begin address regex? */
|| (beg_match(sed_cmd, pattern_space))
/* Or did we match last line of input? */
|| (sed_cmd->beg_line == -1 && next_line == NULL);
+ /* Snapshot the value */
matched = sed_cmd->in_match;
//bb_error_msg("cmd:'%c' matched:%d beg_line:%d end_line:%d linenum:%d",
//sed_cmd->cmd, matched, sed_cmd->beg_line, sed_cmd->end_line, linenum);
/* Is this line the end of the current match? */
+
if (matched) {
- int n = (
+ /* once matched, "n,xxx" range is dead, disabling it */
+ if (sed_cmd->beg_line > 0
+ && !(option_mask32 & OPT_in_place) /* but not for -i */
+ ) {
+ sed_cmd->beg_line = -2;
+ }
+ sed_cmd->in_match = !(
/* has the ending line come, or is this a single address command? */
- sed_cmd->end_line ?
+ (sed_cmd->end_line ?
sed_cmd->end_line == -1 ?
!next_line
: (sed_cmd->end_line <= linenum)
: !sed_cmd->end_match
- );
- if (!n) {
+ )
/* or does this line matches our last address regex */
- n = (sed_cmd->end_match
- && old_matched
+ || (sed_cmd->end_match && old_matched
&& (regexec(sed_cmd->end_match,
- pattern_space, 0, NULL, 0) == 0)
- );
- }
- if (n && sed_cmd->beg_line > 0) {
- /* once matched, "n,xxx" range is dead, disabling it */
- sed_cmd->beg_line = -2;
- }
- sed_cmd->in_match = !n;
+ pattern_space, 0, NULL, 0) == 0))
+ );
}
/* Skip blocks of commands we didn't match */
if (sed_cmd->cmd == '{') {
if (sed_cmd->invert ? matched : !matched) {
- while (sed_cmd->cmd != '}') {
+ unsigned nest_cnt = 0;
+ while (1) {
+ if (sed_cmd->cmd == '{')
+ nest_cnt++;
+ if (sed_cmd->cmd == '}') {
+ nest_cnt--;
+ if (nest_cnt == 0)
+ break;
+ }
sed_cmd = sed_cmd->next;
if (!sed_cmd)
bb_error_msg_and_die("unterminated {");
}
/* actual sedding */
+ //bb_error_msg("pattern_space:'%s' next_line:'%s' cmd:%c",
+ //pattern_space, next_line, sed_cmd->cmd);
switch (sed_cmd->cmd) {
/* Print line number */
case 'P':
{
char *tmp = strchr(pattern_space, '\n');
-
if (tmp) {
*tmp = '\0';
/* TODO: explain why '\n' below */
case 'D':
{
char *tmp = strchr(pattern_space, '\n');
-
if (tmp) {
- tmp = xstrdup(tmp+1);
- free(pattern_space);
- pattern_space = tmp;
+ overlapping_strcpy(pattern_space, tmp + 1);
goto restart;
}
}
case 'c':
/* Only triggers on last line of a matching range. */
if (!sed_cmd->in_match)
- sed_puts(sed_cmd->string, NO_EOL_CHAR);
+ sed_puts(sed_cmd->string, '\n');
goto discard_line;
/* Read file, append contents to output */
case 'r':
{
FILE *rfile;
-
rfile = fopen_for_read(sed_cmd->string);
if (rfile) {
char *line;
{
int len;
/* If no next line, jump to end of script and exit. */
+ /* http://www.gnu.org/software/sed/manual/sed.html:
+ * "Most versions of sed exit without printing anything
+ * when the N command is issued on the last line of
+ * a file. GNU sed prints pattern space before exiting
+ * unless of course the -n command switch has been
+ * specified. This choice is by design."
+ */
if (next_line == NULL) {
- /* Jump to end of script and exit */
- free(next_line);
- next_line = NULL;
- goto discard_line;
- /* append next_line, read new next_line. */
+ //goto discard_line;
+ goto discard_commands; /* GNU behavior */
}
+ /* Append next_line, read new next_line. */
len = strlen(pattern_space);
- pattern_space = realloc(pattern_space, len + strlen(next_line) + 2);
+ pattern_space = xrealloc(pattern_space, len + strlen(next_line) + 2);
pattern_space[len] = '\n';
strcpy(pattern_space + len+1, next_line);
last_gets_char = next_gets_char;
case 'y':
{
int i, j;
-
for (i = 0; pattern_space[i]; i++) {
for (j = 0; sed_cmd->string[j]; j += 2) {
if (pattern_space[i] == sed_cmd->string[j]) {
case 'x': /* Exchange hold and pattern space */
{
char *tmp = pattern_space;
- pattern_space = G.hold_space ? : xzalloc(1);
+ pattern_space = G.hold_space ? G.hold_space : xzalloc(1);
last_gets_char = '\n';
G.hold_space = tmp;
break;
int sed_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
int sed_main(int argc UNUSED_PARAM, char **argv)
{
- enum {
- OPT_in_place = 1 << 0,
- };
unsigned opt;
llist_t *opt_e, *opt_f;
int status = EXIT_SUCCESS;
opt_e = opt_f = NULL;
opt_complementary = "e::f::" /* can occur multiple times */
"nn"; /* count -n */
+ /* -i must be first, to match OPT_in_place definition */
opt = getopt32(argv, "irne:f:", &opt_e, &opt_f,
&G.be_quiet); /* counter for -n */
//argc -= optind;
if (opt & OPT_in_place)
bb_error_msg_and_die(bb_msg_requires_arg, "-i");
add_input_file(stdin);
- process_files();
} else {
int i;
FILE *file;
G.outname = xasprintf("%sXXXXXX", argv[i]);
nonstdoutfd = mkstemp(G.outname);
if (-1 == nonstdoutfd)
- bb_perror_msg_and_die("cannot create temp file %s", G.outname);
- G.nonstdout = fdopen(nonstdoutfd, "w");
-
- /* Set permissions of output file */
+ bb_perror_msg_and_die("can't create temp file %s", G.outname);
+ G.nonstdout = xfdopen_for_write(nonstdoutfd);
+ /* Set permissions/owner of output file */
fstat(fileno(file), &statbuf);
+ /* chmod'ing AFTER chown would preserve suid/sgid bits,
+ * but GNU sed 4.2.1 does not preserve them either */
fchmod(nonstdoutfd, statbuf.st_mode);
+ fchown(nonstdoutfd, statbuf.st_uid, statbuf.st_gid);
add_input_file(file);
process_files();
fclose(G.nonstdout);
free(G.outname);
G.outname = NULL;
}
- if (G.input_file_count > G.current_input_file)
- process_files();
+ /* Here, to handle "sed 'cmds' nonexistent_file" case we did:
+ * if (G.current_input_file >= G.input_file_count)
+ * return status;
+ * but it's not needed since process_files() works correctly
+ * in this case too. */
}
+ process_files();
return status;
}
projects / oweals / busybox.git / blobdiff