sbin/md5: improve compatibility with coreutils -c option

The -c option expects a digest file in either BSD or coreutils format.

The output for matched and mismatched files is identical to that
of the coreutils version.

The review of these changes included test cases that have already
been committed for the functionality that existed before.
Another test script is added to cover the coreutils compatible
extension implemented by this patch.

This commit contains a tests/Makefile that has been cleaned up
compared to the review version, using an implicit rule to apply the
TESTBASE path at build time (and the scripts have been renamed to
have an extension of .SH instead of .sh to trigger this rule).

Reviewed by:    imp
Differential Revision:  https://reviews.freebsd.org/D30812

4 files changed, 209 insertions, 34 deletions

diff --git a/sbin/md5/md5.1 b/sbin/md5/md5.1
index 04f13339e533..da034d1298c5 100644
--- a/sbin/md5/md5.1
+++ b/sbin/md5/md5.1
@@ -1,5 +1,5 @@
 .\" $FreeBSD$
-.Dd June 19, 2021
+.Dd June 24, 2021
 .Dt MD5 1
 .Os
 .Sh NAME
@@ -14,6 +14,7 @@
 .Op Fl c Ar string
 .Op Fl s Ar string
 .Op Ar
+.Pp
 .Nm md5sum
 .Op Fl pqrtx
 .Op Fl c Ar file
@@ -80,13 +81,28 @@ Ignored for compatibility with the coreutils
 .Nm -sum
 programs.
 .It Fl c Ar string
-Compare the digest of the file against this string.
+If the program was called with a name that does not end in
+.Nm sum ,
+compare the digest of the file against this string.
 .Pq Note that this option is not yet useful if multiple files are specified.
-This option causes an error in for the
-.Nm -sum
-programs because it check the checksums listed in a file for the coreutils
-.Nm -sum
-programs that is not yet implemented.
+.It Fl c Ar file
+If the program was called with a name that does end in
+.Nm sum ,
+the file passed as argument must contain digest lines generated by the same digest algorithm
+with or without the
+.Fl r
+option
+.Pq i.e. in either classical BSD format or in GNU coreutils format .
+A line with file name followed by
+.Dq :
+and either OK or FAILED is written for each well-formed line in the digest file.
+If applicable, the number of failed comparisons and the number of lines that were
+skipped since they were not well-formed are printed at the end.
+The
+.Fl q
+option can be used to quiesce the output unless there are mismatched entries in
+the digest.
+.Pp
 .It Fl s Ar string
 Print a checksum of the given
 .Ar string .
@@ -141,8 +157,8 @@ $ echo -n Hello | md5
 Calculate the checksum of multiple files reversing the output:
 .Bd -literal -offset indent
 $ md5 -r /boot/loader.conf /etc/rc.conf
-ada5f60f23af88ff95b8091d6d67bef6 /boot/loader.conf
-d80bf36c332dc0fdc479366ec3fa44cd /etc/rc.conf
+ada5f60f23af88ff95b8091d6d67bef6  /boot/loader.conf
+d80bf36c332dc0fdc479366ec3fa44cd  /etc/rc.conf
 .Ed
 .Pp
 Write the digest for
@@ -165,6 +181,27 @@ which results in a failure.
 $ md5 -c randomstring /boot/loader.conf
 MD5 (/boot/loader.conf) = ada5f60f23af88ff95b8091d6d67bef6 [ Failed ]
 .Ed
+.Pp
+If invoked with a name ending in
+.Nm -sum
+the
+.Fl c
+option does not compare against a hash string passed as parameter.
+Instead, it expects a digest file, as created under the name
+.Pa digest
+for
+.Pa /boot/loader.conf
+in the example above.
+.Bd -literal -offset indent
+$ md5 -c digest /boot/loader.conf
+/boot/loader.conf: OK
+.Ed
+.Pp
+The digest file may contain any number of lines in the format generated with or without the
+.Fl r
+option
+.Pq i.e. in either classical BSD format or in GNU coreutils format .
+If a hash value does not match the file, FAILED is printed instead of OK.
 .Sh SEE ALSO
 .Xr cksum 1 ,
 .Xr md5 3 ,
@@ -203,9 +240,7 @@ The RIPEMD-160 page:
 All of the utilities that end in
 .Sq sum
 are intended to be compatible with the GNU coreutils programs.
-However, the long arguments and the
-.Fl -check
-functionality are not provided.
+However, the long option functionality is not provided.
 .Sh ACKNOWLEDGMENTS
 This program is placed in the public domain for free general use by
 RSA Data Security.
diff --git a/sbin/md5/md5.c b/sbin/md5/md5.c
index e553d4c56e85..d4245d2aad4b 100644
--- a/sbin/md5/md5.c
+++ b/sbin/md5/md5.c
@@ -53,6 +53,7 @@ __FBSDID("$FreeBSD$");
 #define TEST_BLOCK_COUNT 100000
 #define MDTESTCOUNT 8
 
+static int cflag;
 static int pflag;
 static int qflag;
 static int rflag;
@@ -152,12 +153,93 @@ static const struct Algorithm_t Algorithm[] = {
 		(DIGEST_End*)&SKEIN1024_End, &SKEIN1024_Data, &SKEIN1024_Fd }
 };
 
+static unsigned	digest;
+static unsigned	malformed;
+static bool	gnu_emu = false;
+
 static void
 MD5_Update(MD5_CTX *c, const unsigned char *data, size_t len)
 {
 	MD5Update(c, data, len);
 }
 
+struct chksumrec {
+	char	*filename;
+	char	*chksum;
+	struct	chksumrec	*next;
+};
+
+static struct chksumrec *head = NULL;
+static struct chksumrec **next = &head;
+
+#define PADDING	7	/* extra padding for "SHA512t256 (...) = ...\n" style */
+#define CHKFILELINELEN	(HEX_DIGEST_LENGTH + MAXPATHLEN + PADDING)
+
+static int gnu_check(const char *checksumsfile)
+{
+	FILE	*inp;
+	char	linebuf[CHKFILELINELEN];
+	int	linelen;
+	int	lineno;
+	char	*filename;
+	char	*hashstr;
+	struct chksumrec	*rec;
+	const char	*digestname;
+	int	digestnamelen;
+	int	hashstrlen;
+
+	if ((inp = fopen(checksumsfile, "r")) == NULL)
+		err(1, "%s", checksumsfile);
+	digestname = Algorithm[digest].name;
+	digestnamelen = strlen(digestname);
+	hashstrlen = strlen(*(Algorithm[digest].TestOutput[0]));
+	lineno = 1;
+	while (fgets(linebuf, sizeof(linebuf), inp) != NULL) {
+		linelen = strlen(linebuf) - 1;
+		if (linelen <= 0)
+			break;
+		if (linebuf[linelen] != '\n')
+			errx(1, "malformed input line %d (len=%d)", lineno, linelen);
+		linebuf[linelen] = '\0';
+		filename = linebuf + digestnamelen + 2;
+		hashstr = linebuf + linelen - hashstrlen;
+		/*
+		 * supported formats:
+		 * BSD: <DigestName> (<Filename>): <Digest>
+		 * GNU: <Digest> [ *]<Filename>
+		 */
+		if (linelen >= digestnamelen + hashstrlen + 6 &&
+		    strncmp(linebuf, digestname, digestnamelen) == 0 &&
+		    strncmp(filename - 2, " (", 2) == 0 &&
+		    strncmp(hashstr - 4, ") = ", 4) == 0) {
+			*(hashstr - 4) = '\0';
+		} else if (linelen >= hashstrlen + 3 &&
+		    linebuf[hashstrlen] == ' ') {
+			linebuf[hashstrlen] = '\0';
+			hashstr = linebuf;
+			filename = linebuf + hashstrlen + 1;
+			if (*filename == ' ' || *filename == '*')
+				filename++;
+		} else {
+			malformed++;
+			continue;
+		}
+		rec = malloc(sizeof (*rec));
+		if (rec == NULL)
+			errx(1, "malloc failed");
+		rec->chksum = strdup(hashstr);
+		rec->filename = strdup(filename);
+		if (rec->chksum == NULL || rec->filename == NULL)
+			errx(1, "malloc failed");
+		rec->next = NULL;
+		*next = rec;
+		next = &rec->next;
+		lineno++;
+	}
+	fclose(inp);
+	return (lineno - 1);
+}
+
 /* Main driver.
 
 Arguments (may be any combination):
@@ -177,9 +259,9 @@ main(int argc, char *argv[])
 	char   *p, *string;
 	char	buf[HEX_DIGEST_LENGTH];
 	size_t	len;
- 	unsigned	digest;
 	char	*progname;
-	bool	gnu_emu = false;
+	struct chksumrec	*rec;
+	int	numrecs;
 
  	if ((progname = strrchr(argv[0], '/')) == NULL)
  		progname = argv[0];
@@ -199,13 +281,13 @@ main(int argc, char *argv[])
 	 */
 	len = strlen(progname);
 	if (len > 3 && strcmp(progname + len - 3, "sum") == 0) {
-		progname[len - 3] = '\0';
+		len -= 3;
 		rflag = 1;
 		gnu_emu = true;
 	}
 
  	for (digest = 0; digest < sizeof(Algorithm)/sizeof(*Algorithm); digest++)
- 		if (strcasecmp(Algorithm[digest].progname, progname) == 0)
+ 		if (strncasecmp(Algorithm[digest].progname, progname, len) == 0)
  			break;
 
  	if (digest == sizeof(Algorithm)/sizeof(*Algorithm))
@@ -220,9 +302,11 @@ main(int argc, char *argv[])
 		case 'b':
 			break;
 		case 'c':
+			cflag = 1;
 			if (gnu_emu)
-				errx(1, "-c check option not supported");
-			checkAgainst = optarg;
+				numrecs = gnu_check(optarg);
+			else
+				checkAgainst = optarg;
 			break;
 		case 'p':
 			pflag = 1;
@@ -258,6 +342,20 @@ main(int argc, char *argv[])
 		err(1, "unable to limit rights for stdio");
 #endif
 
+	if (cflag && gnu_emu) {
+		/*
+		 * Replace argv by an array of filenames from the digest file
+		 */
+		argc = 0;
+		argv = (char**)calloc(sizeof(char *), numrecs + 1);
+		for (rec = head; rec != NULL; rec = rec->next) {
+			argv[argc] = rec->filename;
+			argc++;
+		}
+		argv[argc] = NULL;
+		rec = head;
+	}
+
 	if (*argv) {
 		do {
 			if ((fd = open(*argv, O_RDONLY)) < 0) {
@@ -279,11 +377,15 @@ main(int argc, char *argv[])
 					err(1, "capsicum");
 #endif
 			}
+			if (cflag && gnu_emu) {
+				checkAgainst = rec->chksum;
+				rec = rec->next;
+			}
 			p = Algorithm[digest].Fd(fd, buf);
 			(void)close(fd);
 			MDOutput(&Algorithm[digest], p, argv);
 		} while (*++argv);
-	} else if (!sflag && !skip) {
+	} else if (!cflag && !sflag && !skip) {
 #ifdef HAVE_CAPSICUM
 		if (caph_limit_stdin() < 0 || caph_enter() < 0)
 			err(1, "capsicum");
@@ -295,7 +397,12 @@ main(int argc, char *argv[])
 		p = Algorithm[digest].Data(string, len, buf);
 		MDOutput(&Algorithm[digest], p, &string);
 	}
-
+	if (gnu_emu) {
+		if (malformed > 0)
+			warnx("WARNING: %d lines are improperly formatted", malformed);
+		if (checksFailed > 0)
+			warnx("WARNING: %d computed checksums did NOT match", checksFailed);
+	}
 	if (failed != 0)
 		return (1);
 	if (checksFailed != 0)
@@ -310,6 +417,8 @@ main(int argc, char *argv[])
 static void
 MDOutput(const Algorithm_t *alg, char *p, char *argv[])
 {
+	bool checkfailed = false;
+
 	if (p == NULL) {
 		warn("%s", *argv);
 		failed++;
@@ -318,21 +427,27 @@ MDOutput(const Algorithm_t *alg, char *p, char *argv[])
 		 * If argv is NULL we are reading from stdin, where the output
 		 * format has always been just the hash.
 		 */
-		if (qflag || argv == NULL)
-			printf("%s", p);
-		else if (rflag)
-			printf("%s %s", p, *argv);
-		else
-			printf("%s (%s) = %s",
-			    alg->name, *argv, p);
-		if (checkAgainst && strcasecmp(checkAgainst, p) != 0)
-		{
-			checksFailed++;
-			if (!qflag)
-				printf(" [ Failed ]");
+		if (cflag && gnu_emu) {
+			checkfailed = strcasecmp(checkAgainst, p) != 0;
+			if (!qflag || checkfailed)
+				printf("%s: %s\n", *argv, checkfailed ? "FAILED" : "OK");
+		} else if (qflag || argv == NULL) {
+			printf("%s\n", p);
+		} else {
+			if (rflag)
+				printf("%s  %s", p, *argv);
+			else
+				printf("%s (%s) = %s", alg->name, *argv, p);
+			if (checkAgainst) {
+				checkfailed = strcasecmp(checkAgainst, p) != 0;
+				if (!qflag && checkfailed)
+					printf(" [ Failed ]");
+			}
+			printf("\n");
 		}
-		printf("\n");
 	}
+	if (checkfailed)
+		checksFailed++;
 }
 
 /*
@@ -559,6 +674,9 @@ static void
 usage(const Algorithm_t *alg)
 {
 
-	fprintf(stderr, "usage: %s [-pqrtx] [-c string] [-s string] [files ...]\n", alg->progname);
+	if (gnu_emu)
+		fprintf(stderr, "usage: %ssum [-pqrtx] [-c file] [-s string] [files ...]\n", alg->progname);
+	else
+		fprintf(stderr, "usage: %s [-pqrtx] [-c string] [-s string] [files ...]\n", alg->progname);
 	exit(1);
 }
diff --git a/sbin/md5/tests/Makefile b/sbin/md5/tests/Makefile
index b37332aa9894..93f3913c687d 100644
--- a/sbin/md5/tests/Makefile
+++ b/sbin/md5/tests/Makefile
@@ -32,6 +32,7 @@ PLAIN_TESTS_SH+=	self-test
 PLAIN_TESTS_SH+=	bsd-c-test
 PLAIN_TESTS_SH+=	bsd-p-test
 PLAIN_TESTS_SH+=	bsd-s-test
+PLAIN_TESTS_SH+=	coreutils-c-test
 
 .SUFFIXES:		.SH
 
diff --git a/sbin/md5/tests/coreutils-c-test.SH b/sbin/md5/tests/coreutils-c-test.SH
new file mode 100644
index 000000000000..5996e533c627
--- /dev/null
+++ b/sbin/md5/tests/coreutils-c-test.SH
@@ -0,0 +1,21 @@
+#!/bin/sh
+
+/bin/cp %%TESTSBASE%%/sbin/md5/*.inp . || exit 127
+
+exitcode=0
+
+testloop () {
+	opt=$1
+
+	while read algorithm; do
+		${algorithm}sum -c %%TESTSBASE%%/sbin/md5/${algorithm}.digest || exitcode=1
+		${algorithm}sum -c %%TESTSBASE%%/sbin/md5/${algorithm}sum.digest || exitcode=1
+	done < %%TESTSBASE%%/sbin/md5/algorithms.txt
+}
+
+testloop ""
+testloop -q
+testloop -r
+testloop -qr
+
+exit $exitcode