Merge branch 'js/mailinfo'

* js/mailinfo:
  mailsplit: minor clean-up in read_line_with_nul()
  mailinfo: apply the same fix not to lose NULs in BASE64 and QP codepaths
  mailsplit and mailinfo: gracefully handle NUL characters

builtin-mailinfo.c

@@ -434,6 +434,7 @@ static int read_one_header_line(char *line, int sz, FILE *in)
 
 static int decode_q_segment(char *in, char *ot, unsigned otsize, char *ep, int rfc2047)
 {
+	char *otbegin = ot;
 	char *otend = ot + otsize;
 	int c;
 	while ((c = *in++) != 0 && (in <= ep)) {
@@ -453,13 +454,14 @@ static int decode_q_segment(char *in, char *ot, unsigned otsize, char *ep, int r
 		*ot++ = c;
 	}
 	*ot = 0;
-	return 0;
+	return (ot - otbegin);
 }
 
 static int decode_b_segment(char *in, char *ot, unsigned otsize, char *ep)
 {
 	/* Decode in..ep, possibly in-place to ot */
 	int c, pos = 0, acc = 0;
+	char *otbegin = ot;
 	char *otend = ot + otsize;
 
 	while ((c = *in++) != 0 && (in <= ep)) {
@@ -505,7 +507,7 @@ static int decode_b_segment(char *in, char *ot, unsigned otsize, char *ep)
 		}
 	}
 	*ot = 0;
-	return 0;
+	return (ot - otbegin);
 }
 
 /*
@@ -623,25 +625,24 @@ static void decode_header(char *it, unsigned itsize)
 		convert_to_utf8(it, itsize, "");
 }
 
-static void decode_transfer_encoding(char *line, unsigned linesize)
+static int decode_transfer_encoding(char *line, unsigned linesize, int inputlen)
 {
 	char *ep;
 
 	switch (transfer_encoding) {
 	case TE_QP:
-		ep = line + strlen(line);
-		decode_q_segment(line, line, linesize, ep, 0);
-		break;
+		ep = line + inputlen;
+		return decode_q_segment(line, line, linesize, ep, 0);
 	case TE_BASE64:
-		ep = line + strlen(line);
-		decode_b_segment(line, line, linesize, ep);
-		break;
+		ep = line + inputlen;
+		return decode_b_segment(line, line, linesize, ep);
 	case TE_DONTCARE:
-		break;
+	default:
+		return inputlen;
 	}
 }
 
-static int handle_filter(char *line, unsigned linesize);
+static int handle_filter(char *line, unsigned linesize, int linelen);
 
 static int find_boundary(void)
 {
@@ -669,7 +670,7 @@ again:
 					"can't recover\n");
 			exit(1);
 		}
-		handle_filter(newline, sizeof(newline));
+		handle_filter(newline, sizeof(newline), strlen(newline));
 
 		/* skip to the next boundary */
 		if (!find_boundary())
@@ -759,14 +760,14 @@ static int handle_commit_msg(char *line, unsigned linesize)
 	return 0;
 }
 
-static int handle_patch(char *line)
+static int handle_patch(char *line, int len)
 {
-	fputs(line, patchfile);
+	fwrite(line, 1, len, patchfile);
 	patch_lines++;
 	return 0;
 }
 
-static int handle_filter(char *line, unsigned linesize)
+static int handle_filter(char *line, unsigned linesize, int linelen)
 {
 	static int filter = 0;
 
@@ -779,7 +780,7 @@ static int handle_filter(char *line, unsigned linesize)
 			break;
 		filter++;
 	case 1:
-		if (!handle_patch(line))
+		if (!handle_patch(line, linelen))
 			break;
 		filter++;
 	default:
@@ -794,6 +795,7 @@ static void handle_body(void)
 	int rc = 0;
 	static char newline[2000];
 	static char *np = newline;
+	int len = strlen(line);
 
 	/* Skip up to the first boundary */
 	if (content_top->boundary) {
@@ -805,16 +807,19 @@ static void handle_body(void)
 		/* process any boundary lines */
 		if (content_top->boundary && is_multipart_boundary(line)) {
 			/* flush any leftover */
-			if ((transfer_encoding == TE_BASE64)  &&
-			    (np != newline)) {
-				handle_filter(newline, sizeof(newline));
-			}
+			if (np != newline)
+				handle_filter(newline, sizeof(newline),
+					      np - newline);
 			if (!handle_boundary())
 				return;
 		}
 
 		/* Unwrap transfer encoding */
-		decode_transfer_encoding(line, sizeof(line));
+		len = decode_transfer_encoding(line, sizeof(line), len);
+		if (len < 0) {
+			error("Malformed input line");
+			return;
+		}
 
 		switch (transfer_encoding) {
 		case TE_BASE64:
@@ -824,39 +829,40 @@ static void handle_body(void)
 
 			/* binary data most likely doesn't have newlines */
 			if (message_type != TYPE_TEXT) {
-				rc = handle_filter(line, sizeof(newline));
+				rc = handle_filter(line, sizeof(line), len);
 				break;
 			}
 
-			/* this is a decoded line that may contain
+			/*
+			 * This is a decoded line that may contain
 			 * multiple new lines.  Pass only one chunk
 			 * at a time to handle_filter()
 			 */
-
 			do {
-				while (*op != '\n' && *op != 0)
+				while (op < line + len && *op != '\n')
 					*np++ = *op++;
 				*np = *op;
 				if (*np != 0) {
 					/* should be sitting on a new line */
 					*(++np) = 0;
 					op++;
-					rc = handle_filter(newline, sizeof(newline));
+					rc = handle_filter(newline, sizeof(newline), np - newline);
 					np = newline;
 				}
-			} while (*op != 0);
-			/* the partial chunk is saved in newline and
-			 * will be appended by the next iteration of fgets
+			} while (op < line + len);
+			/*
+			 * The partial chunk is saved in newline and will be
+			 * appended by the next iteration of read_line_with_nul().
 			 */
 			break;
 		}
 		default:
-			rc = handle_filter(line, sizeof(newline));
+			rc = handle_filter(line, sizeof(line), len);
 		}
 		if (rc)
 			/* nothing left to filter */
 			break;
-	} while (fgets(line, sizeof(line), fin));
+	} while ((len = read_line_with_nul(line, sizeof(line), fin)));
 
 	return;
 }

builtin-mailsplit.c

@@ -45,6 +45,24 @@ static int is_from_line(const char *line, int len)
 /* Could be as small as 64, enough to hold a Unix "From " line. */
 static char buf[4096];
 
+/* We cannot use fgets() because our lines can contain NULs */
+int read_line_with_nul(char *buf, int size, FILE *in)
+{
+	int len = 0, c;
+
+	for (;;) {
+		c = getc(in);
+		if (c == EOF)
+			break;
+		buf[len++] = c;
+		if (c == '\n' || len + 1 >= size)
+			break;
+	}
+	buf[len] = '\0';
+
+	return len;
+}
+
 /* Called with the first line (potentially partial)
  * already in buf[] -- normally that should begin with
  * the Unix "From " line.  Write it into the specified
@@ -70,19 +88,19 @@ static int split_one(FILE *mbox, const char *name, int allow_bare)
 	 * "From " and having something that looks like a date format.
 	 */
 	for (;;) {
-		int is_partial = (buf[len-1] != '\n');
+		int is_partial = len && buf[len-1] != '\n';
 
-		if (fputs(buf, output) == EOF)
+		if (fwrite(buf, 1, len, output) != len)
 			die("cannot write output");
 
-		if (fgets(buf, sizeof(buf), mbox) == NULL) {
+		len = read_line_with_nul(buf, sizeof(buf), mbox);
+		if (len == 0) {
 			if (feof(mbox)) {
 				status = 1;
 				break;
 			}
 			die("cannot read mbox");
 		}
-		len = strlen(buf);
 		if (!is_partial && !is_bare && is_from_line(buf, len))
 			break; /* done with one message */
 	}

builtin.h

@@ -9,6 +9,7 @@ extern const char git_usage_string[];
 extern void list_common_cmds_help(void);
 extern void help_unknown_cmd(const char *cmd);
 extern void prune_packed_objects(int);
+extern int read_line_with_nul(char *buf, int size, FILE *file);
 
 extern int cmd_add(int argc, const char **argv, const char *prefix);
 extern int cmd_annotate(int argc, const char **argv, const char *prefix);

t/t5100-mailinfo.sh

@@ -25,4 +25,22 @@ do
 		diff ../t5100/info$mail info$mail"
 done
 
+test_expect_success 'respect NULs' '
+
+	git mailsplit -d3 -o. ../t5100/nul &&
+	cmp ../t5100/nul 001 &&
+	(cat 001 | git mailinfo msg patch) &&
+	test 4 = $(wc -l < patch)
+
+'
+
+test_expect_success 'Preserve NULs out of MIME encoded message' '
+
+	git mailsplit -d5 -o. ../t5100/nul-b64.in &&
+	cmp ../t5100/nul-b64.in 00001 &&
+	git mailinfo msg patch <00001 &&
+	cmp ../t5100/nul-b64.expect patch
+
+'
+
 test_done

t/t5100/nul-b64.in

@@ -0,0 +1,37 @@
+From 667d8940e719cddee1cfe237cbbe215e20270b09 Mon Sep 17 00:00:00 2001
+From: Junio C Hamano <gitster@pobox.com>
+Date: Sun, 25 May 2008 00:38:18 -0700
+Subject: [PATCH] second
+Content-Transfer-Encoding: base64
+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==