Merge branch 'js/neuter-sideband' into seen

Invalidate control characters in sideband messages, to avoid
terminal state getting messed up.

* js/neuter-sideband:
  sideband: offer to configure sanitizing on a per-URL basis
  sideband: add options to allow more control sequences to be passed through
  sideband: do allow ANSI color sequences by default
  sideband: introduce an "escape hatch" to allow control characters
  sideband: mask control characters

Documentation/config.adoc

@@ -523,6 +523,8 @@ include::config/sequencer.adoc[]
 
 include::config/showbranch.adoc[]
 
+include::config/sideband.adoc[]
+
 include::config/sparse.adoc[]
 
 include::config/splitindex.adoc[]

Documentation/config/sideband.adoc

@@ -0,0 +1,28 @@
+sideband.allowControlCharacters::
+	By default, control characters that are delivered via the sideband
+	are masked, except ANSI color sequences. This prevents potentially
+	unwanted ANSI escape sequences from being sent to the terminal. Use
+	this config setting to override this behavior (the value can be
+	a comma-separated list of the following keywords):
++
+--
+	`default`::
+	`color`::
+		Allow ANSI color sequences, line feeds and horizontal tabs,
+		but mask all other control characters. This is the default.
+	`cursor:`:
+		Allow control sequences that move the cursor. This is
+		disabled by default.
+	`erase`::
+		Allow control sequences that erase charactrs. This is
+		disabled by default.
+	`false`::
+		Mask all control characters other than line feeds and
+		horizontal tabs.
+	`true`::
+		Allow all control characters to be sent to the terminal.
+--
+
+sideband.<url>.*::
+	Apply the `sideband.*` option selectively to specific URLs. The
+	same URL matching logic applies as for `http.<url>.*` settings.

sideband.c

@@ -10,6 +10,7 @@
 #include "help.h"
 #include "pkt-line.h"
 #include "write-or-die.h"
+#include "urlmatch.h"
 
 struct keyword_entry {
 	/*
@@ -26,6 +27,87 @@ static struct keyword_entry keywords[] = {
 	{ "error",	GIT_COLOR_BOLD_RED },
 };
 
+static enum {
+	ALLOW_CONTROL_SEQUENCES_UNSET = -1,
+	ALLOW_NO_CONTROL_CHARACTERS   = 0,
+	ALLOW_ANSI_COLOR_SEQUENCES    = 1<<0,
+	ALLOW_ANSI_CURSOR_MOVEMENTS   = 1<<1,
+	ALLOW_ANSI_ERASE              = 1<<2,
+	ALLOW_DEFAULT_ANSI_SEQUENCES  = ALLOW_ANSI_COLOR_SEQUENCES,
+	ALLOW_ALL_CONTROL_CHARACTERS  = 1<<3,
+} allow_control_characters = ALLOW_CONTROL_SEQUENCES_UNSET;
+
+static inline int skip_prefix_in_csv(const char *value, const char *prefix,
+				     const char **out)
+{
+	if (!skip_prefix(value, prefix, &value) ||
+	    (*value && *value != ','))
+		return 0;
+	*out = value + !!*value;
+	return 1;
+}
+
+int sideband_allow_control_characters_config(const char *var, const char *value)
+{
+	switch (git_parse_maybe_bool(value)) {
+	case 0:
+		allow_control_characters = ALLOW_NO_CONTROL_CHARACTERS;
+		return 0;
+	case 1:
+		allow_control_characters = ALLOW_ALL_CONTROL_CHARACTERS;
+		return 0;
+	default:
+		break;
+	}
+
+	allow_control_characters = ALLOW_NO_CONTROL_CHARACTERS;
+	while (*value) {
+		if (skip_prefix_in_csv(value, "default", &value))
+			allow_control_characters |= ALLOW_DEFAULT_ANSI_SEQUENCES;
+		else if (skip_prefix_in_csv(value, "color", &value))
+			allow_control_characters |= ALLOW_ANSI_COLOR_SEQUENCES;
+		else if (skip_prefix_in_csv(value, "cursor", &value))
+			allow_control_characters |= ALLOW_ANSI_CURSOR_MOVEMENTS;
+		else if (skip_prefix_in_csv(value, "erase", &value))
+			allow_control_characters |= ALLOW_ANSI_ERASE;
+		else if (skip_prefix_in_csv(value, "true", &value))
+			allow_control_characters = ALLOW_ALL_CONTROL_CHARACTERS;
+		else if (skip_prefix_in_csv(value, "false", &value))
+			allow_control_characters = ALLOW_NO_CONTROL_CHARACTERS;
+		else
+			warning(_("unrecognized value for '%s': '%s'"), var, value);
+	}
+	return 0;
+}
+
+static int sideband_config_callback(const char *var, const char *value,
+				    const struct config_context *ctx UNUSED,
+				    void *data UNUSED)
+{
+	if (!strcmp(var, "sideband.allowcontrolcharacters"))
+		return sideband_allow_control_characters_config(var, value);
+
+	return 0;
+}
+
+void sideband_apply_url_config(const char *url)
+{
+	struct urlmatch_config config = URLMATCH_CONFIG_INIT;
+	char *normalized_url;
+
+	if (!url)
+		BUG("must not call sideband_apply_url_config(NULL)");
+
+	config.section = "sideband";
+	config.collect_fn = sideband_config_callback;
+
+	normalized_url = url_normalize(url, &config.url);
+	repo_config(the_repository, urlmatch_config_entry, &config);
+	free(normalized_url);
+	string_list_clear(&config.vars, 1);
+	urlmatch_config_release(&config);
+}
+
 /* Returns a color setting (GIT_COLOR_NEVER, etc). */
 static enum git_colorbool use_sideband_colors(void)
 {
@@ -39,6 +121,16 @@ static enum git_colorbool use_sideband_colors(void)
 	if (use_sideband_colors_cached != GIT_COLOR_UNKNOWN)
 		return use_sideband_colors_cached;
 
+	if (allow_control_characters == ALLOW_CONTROL_SEQUENCES_UNSET) {
+		if (!repo_config_get_value(the_repository,
+					   "sideband.allowcontrolcharacters", &value))
+			sideband_allow_control_characters_config(
+				"sideband.allowcontrolcharacters", value);
+
+		if (allow_control_characters == ALLOW_CONTROL_SEQUENCES_UNSET)
+			allow_control_characters = ALLOW_DEFAULT_ANSI_SEQUENCES;
+	}
+
 	if (!repo_config_get_string_tmp(the_repository, key, &value))
 		use_sideband_colors_cached = git_config_colorbool(key, value);
 	else if (!repo_config_get_string_tmp(the_repository, "color.ui", &value))
@@ -66,6 +158,93 @@ void list_config_color_sideband_slots(struct string_list *list, const char *pref
 		list_config_item(list, prefix, keywords[i].keyword);
 }
 
+static int handle_ansi_sequence(struct strbuf *dest, const char *src, int n)
+{
+	int i;
+
+	/*
+	 * Valid ANSI color sequences are of the form
+	 *
+	 * ESC [ [<n> [; <n>]*] m
+	 *
+	 * These are part of the Select Graphic Rendition sequences which
+	 * contain more than just color sequences, for more details see
+	 * https://en.wikipedia.org/wiki/ANSI_escape_code#SGR.
+	 *
+	 * The cursor movement sequences are:
+	 *
+	 * ESC [ n A - Cursor up n lines (CUU)
+	 * ESC [ n B - Cursor down n lines (CUD)
+	 * ESC [ n C - Cursor forward n columns (CUF)
+	 * ESC [ n D - Cursor back n columns (CUB)
+	 * ESC [ n E - Cursor next line, beginning (CNL)
+	 * ESC [ n F - Cursor previous line, beginning (CPL)
+	 * ESC [ n G - Cursor to column n (CHA)
+	 * ESC [ n ; m H - Cursor position (row n, col m) (CUP)
+	 * ESC [ n ; m f - Same as H (HVP)
+	 *
+	 * The sequences to erase characters are:
+	 *
+	 *
+	 * ESC [ 0 J - Clear from cursor to end of screen (ED)
+	 * ESC [ 1 J - Clear from cursor to beginning of screen (ED)
+	 * ESC [ 2 J - Clear entire screen (ED)
+	 * ESC [ 3 J - Clear entire screen + scrollback (ED) - xterm extension
+	 * ESC [ 0 K - Clear from cursor to end of line (EL)
+	 * ESC [ 1 K - Clear from cursor to beginning of line (EL)
+	 * ESC [ 2 K - Clear entire line (EL)
+	 * ESC [ n M - Delete n lines (DL)
+	 * ESC [ n P - Delete n characters (DCH)
+	 * ESC [ n X - Erase n characters (ECH)
+	 *
+	 * For a comprehensive list of common ANSI Escape sequences, see
+	 * https://www.xfree86.org/current/ctlseqs.html
+	 */
+
+	if (n < 3 || src[0] != '\x1b' || src[1] != '[')
+		return 0;
+
+	for (i = 2; i < n; i++) {
+		if (((allow_control_characters & ALLOW_ANSI_COLOR_SEQUENCES) &&
+		     src[i] == 'm') ||
+		    ((allow_control_characters & ALLOW_ANSI_CURSOR_MOVEMENTS) &&
+		     strchr("ABCDEFGHf", src[i])) ||
+		    ((allow_control_characters & ALLOW_ANSI_ERASE) &&
+		     strchr("JKMPX", src[i]))) {
+			strbuf_add(dest, src, i + 1);
+			return i;
+		}
+		if (!isdigit(src[i]) && src[i] != ';')
+			break;
+	}
+
+	return 0;
+}
+
+static void strbuf_add_sanitized(struct strbuf *dest, const char *src, int n)
+{
+	int i;
+
+	if ((allow_control_characters & ALLOW_ALL_CONTROL_CHARACTERS)) {
+		strbuf_add(dest, src, n);
+		return;
+	}
+
+	strbuf_grow(dest, n);
+	for (; n && *src; src++, n--) {
+		if (!iscntrl(*src) || *src == '\t' || *src == '\n') {
+			strbuf_addch(dest, *src);
+		} else if (allow_control_characters != ALLOW_NO_CONTROL_CHARACTERS &&
+			   (i = handle_ansi_sequence(dest, src, n))) {
+			src += i;
+			n -= i;
+		} else {
+			strbuf_addch(dest, '^');
+			strbuf_addch(dest, *src == 0x7f ? '?' : 0x40 + *src);
+		}
+	}
+}
+
 /*
  * Optionally highlight one keyword in remote output if it appears at the start
  * of the line. This should be called for a single line only, which is
@@ -81,7 +260,7 @@ static void maybe_colorize_sideband(struct strbuf *dest, const char *src, int n)
 	int i;
 
 	if (!want_color_stderr(use_sideband_colors())) {
-		strbuf_add(dest, src, n);
+		strbuf_add_sanitized(dest, src, n);
 		return;
 	}
 
@@ -114,7 +293,7 @@ static void maybe_colorize_sideband(struct strbuf *dest, const char *src, int n)
 		}
 	}
 
-	strbuf_add(dest, src, n);
+	strbuf_add_sanitized(dest, src, n);
 }
 
 

sideband.h

@@ -30,4 +30,18 @@ int demultiplex_sideband(const char *me, int status,
 
 void send_sideband(int fd, int band, const char *data, ssize_t sz, int packet_max);
 
+/*
+ * Apply sideband configuration for the given URL. This should be called
+ * when a transport is created to allow URL-specific configuration of
+ * sideband behavior (e.g., sideband.<url>.allowControlCharacters).
+ */
+void sideband_apply_url_config(const char *url);
+
+/*
+ * Parse and set the sideband allow control characters configuration.
+ * The var parameter should be the key name (without section prefix).
+ * Returns 0 if the variable was recognized and handled, non-zero otherwise.
+ */
+int sideband_allow_control_characters_config(const char *var, const char *value);
+
 #endif

t/t5409-colorize-remote-messages.sh

@@ -98,4 +98,96 @@ test_expect_success 'fallback to color.ui' '
 	grep "<BOLD;RED>error<RESET>: error" decoded
 '
 
+test_expect_success 'disallow (color) control sequences in sideband' '
+	write_script .git/color-me-surprised <<-\EOF &&
+	printf "error: Have you \\033[31mread\\033[m this?\\a\\n" >&2
+	exec "$@"
+	EOF
+	test_config_global uploadPack.packObjectsHook ./color-me-surprised &&
+	test_commit need-at-least-one-commit &&
+
+	git clone --no-local . throw-away 2>stderr &&
+	test_decode_color <stderr >decoded &&
+	test_grep RED decoded &&
+	test_grep "\\^G" stderr &&
+	tr -dc "\\007" <stderr >actual &&
+	test_must_be_empty actual &&
+
+	rm -rf throw-away &&
+	git -c sideband.allowControlCharacters=false \
+		clone --no-local . throw-away 2>stderr &&
+	test_decode_color <stderr >decoded &&
+	test_grep ! RED decoded &&
+	test_grep "\\^G" stderr &&
+
+	rm -rf throw-away &&
+	git -c sideband.allowControlCharacters clone --no-local . throw-away 2>stderr &&
+	test_decode_color <stderr >decoded &&
+	test_grep RED decoded &&
+	tr -dc "\\007" <stderr >actual &&
+	test_file_not_empty actual
+'
+
+test_decode_csi() {
+	awk '{
+		while (match($0, /\033/) != 0) {
+			printf "%sCSI ", substr($0, 1, RSTART-1);
+			$0 = substr($0, RSTART + RLENGTH, length($0) - RSTART - RLENGTH + 1);
+		}
+		print
+	}'
+}
+
+test_expect_success 'control sequences in sideband allowed by default' '
+	write_script .git/color-me-surprised <<-\EOF &&
+	printf "error: \\033[31mcolor\\033[m\\033[Goverwrite\\033[Gerase\\033[K\\033?25l\\n" >&2
+	exec "$@"
+	EOF
+	test_config_global uploadPack.packObjectsHook ./color-me-surprised &&
+	test_commit need-at-least-one-commit-at-least &&
+
+	rm -rf throw-away &&
+	git clone --no-local . throw-away 2>stderr &&
+	test_decode_color <stderr >color-decoded &&
+	test_decode_csi <color-decoded >decoded &&
+	test_grep ! "CSI \\[K" decoded &&
+	test_grep ! "CSI \\[G" decoded &&
+	test_grep "\\^\\[?25l" decoded &&
+
+	rm -rf throw-away &&
+	git -c sideband.allowControlCharacters=erase,cursor,color \
+		clone --no-local . throw-away 2>stderr &&
+	test_decode_color <stderr >color-decoded &&
+	test_decode_csi <color-decoded >decoded &&
+	test_grep "RED" decoded &&
+	test_grep "CSI \\[K" decoded &&
+	test_grep "CSI \\[G" decoded &&
+	test_grep ! "\\^\\[\\[K" decoded &&
+	test_grep ! "\\^\\[\\[G" decoded
+'
+
+test_expect_success 'allow all control sequences for a specific URL' '
+	write_script .git/eraser <<-\EOF &&
+	printf "error: Ohai!\\r\\033[K" >&2
+	exec "$@"
+	EOF
+	test_config_global uploadPack.packObjectsHook ./eraser &&
+	test_commit one-more-please &&
+
+	rm -rf throw-away &&
+	git clone --no-local . throw-away 2>stderr &&
+	test_decode_color <stderr >color-decoded &&
+	test_decode_csi <color-decoded >decoded &&
+	test_grep ! "CSI \\[K" decoded &&
+	test_grep "\\^\\[\\[K" decoded &&
+
+	rm -rf throw-away &&
+	git -c "sideband.file://.allowControlCharacters=true" \
+		clone --no-local "file://$PWD" throw-away 2>stderr &&
+	test_decode_color <stderr >color-decoded &&
+	test_decode_csi <color-decoded >decoded &&
+	test_grep "CSI \\[K" decoded &&
+	test_grep ! "\\^\\[\\[K" decoded
+'
+
 test_done

transport.c

@@ -29,6 +29,7 @@
 #include "object-name.h"
 #include "color.h"
 #include "bundle-uri.h"
+#include "sideband.h"
 
 static enum git_colorbool transport_use_color = GIT_COLOR_UNKNOWN;
 static char transport_colors[][COLOR_MAXLEN] = {
@@ -1246,6 +1247,8 @@ struct transport *transport_get(struct remote *remote, const char *url)
 
 	ret->hash_algo = &hash_algos[GIT_HASH_SHA1_LEGACY];
 
+	sideband_apply_url_config(ret->url);
+
 	return ret;
 }