Merge branch 'jc/whitespace'

* jc/whitespace:
  git-apply: second war on whitespace.
  diff.c: second war on whitespace.

builtin-apply.c

@@ -854,6 +854,49 @@ static int find_header(char *line, unsigned long size, int *hdrsize, struct patc
 	return -1;
 }
 
+static void check_whitespace(const char *line, int len)
+{
+	const char *err = "Adds trailing whitespace";
+	int seen_space = 0;
+	int i;
+
+	/*
+	 * We know len is at least two, since we have a '+' and we
+	 * checked that the last character was a '\n' before calling
+	 * this function.  That is, an addition of an empty line would
+	 * check the '+' here.  Sneaky...
+	 */
+	if (isspace(line[len-2]))
+		goto error;
+
+	/*
+	 * Make sure that there is no space followed by a tab in
+	 * indentation.
+	 */
+	err = "Space in indent is followed by a tab";
+	for (i = 1; i < len; i++) {
+		if (line[i] == '\t') {
+			if (seen_space)
+				goto error;
+		}
+		else if (line[i] == ' ')
+			seen_space = 1;
+		else
+			break;
+	}
+	return;
+
+ error:
+	whitespace_error++;
+	if (squelch_whitespace_errors &&
+	    squelch_whitespace_errors < whitespace_error)
+		;
+	else
+		fprintf(stderr, "%s.\n%s:%d:%.*s\n",
+			err, patch_input_file, linenr, len-2, line+1);
+}
+
+
 /*
  * Parse a unified diff. Note that this really needs to parse each
  * fragment separately, since the only way to know the difference
@@ -904,25 +947,8 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s
 			trailing = 0;
 			break;
 		case '+':
-			/*
-			 * We know len is at least two, since we have a '+' and
-			 * we checked that the last character was a '\n' above.
-			 * That is, an addition of an empty line would check
-			 * the '+' here.  Sneaky...
-			 */
-			if ((new_whitespace != nowarn_whitespace) &&
-			    isspace(line[len-2])) {
-				whitespace_error++;
-				if (squelch_whitespace_errors &&
-				    squelch_whitespace_errors <
-				    whitespace_error)
-					;
-				else {
-					fprintf(stderr, "Adds trailing whitespace.\n%s:%d:%.*s\n",
-						patch_input_file,
-						linenr, len-2, line+1);
-				}
-			}
+			if (new_whitespace != nowarn_whitespace)
+				check_whitespace(line, len);
 			added++;
 			newlines--;
 			trailing = 0;
@@ -1494,22 +1520,68 @@ static int apply_line(char *output, const char *patch, int plen)
 {
 	/* plen is number of bytes to be copied from patch,
 	 * starting at patch+1 (patch[0] is '+').  Typically
-	 * patch[plen] is '\n'.
+	 * patch[plen] is '\n', unless this is the incomplete
+	 * last line.
 	 */
+	int i;
 	int add_nl_to_tail = 0;
-	if ((new_whitespace == strip_whitespace) &&
-	    1 < plen && isspace(patch[plen-1])) {
+	int fixed = 0;
+	int last_tab_in_indent = -1;
+	int last_space_in_indent = -1;
+	int need_fix_leading_space = 0;
+	char *buf;
+
+	if ((new_whitespace != strip_whitespace) || !whitespace_error) {
+		memcpy(output, patch + 1, plen);
+		return plen;
+	}
+
+	if (1 < plen && isspace(patch[plen-1])) {
 		if (patch[plen] == '\n')
 			add_nl_to_tail = 1;
 		plen--;
 		while (0 < plen && isspace(patch[plen]))
 			plen--;
-		applied_after_stripping++;
+		fixed = 1;
 	}
-	memcpy(output, patch + 1, plen);
+
+	for (i = 1; i < plen; i++) {
+		char ch = patch[i];
+		if (ch == '\t') {
+			last_tab_in_indent = i;
+			if (0 <= last_space_in_indent)
+				need_fix_leading_space = 1;
+		}
+		else if (ch == ' ')
+			last_space_in_indent = i;
+		else
+			break;
+	}
+
+	buf = output;
+	if (need_fix_leading_space) {
+		/* between patch[1..last_tab_in_indent] strip the
+		 * funny spaces, updating them to tab as needed.
+		 */
+		for (i = 1; i < last_tab_in_indent; i++, plen--) {
+			char ch = patch[i];
+			if (ch != ' ')
+				*output++ = ch;
+			else if ((i % 8) == 0)
+				*output++ = '\t';
+		}
+		fixed = 1;
+		i = last_tab_in_indent;
+	}
+	else
+		i = 1;
+
+	memcpy(output, patch + i, plen);
 	if (add_nl_to_tail)
 		output[plen++] = '\n';
-	return plen;
+	if (fixed)
+		applied_after_stripping++;
+	return output + plen - buf;
 }
 
 static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag, int inaccurate_eof)

diff.c

@@ -20,12 +20,13 @@ static int diff_use_color_default;
 
 static char diff_colors[][COLOR_MAXLEN] = {
 	"\033[m",	/* reset */
-	"",		/* normal */
-	"\033[1m",	/* bold */
-	"\033[36m",	/* cyan */
-	"\033[31m",	/* red */
-	"\033[32m",	/* green */
-	"\033[33m"	/* yellow */
+	"",		/* PLAIN (normal) */
+	"\033[1m",	/* METAINFO (bold) */
+	"\033[36m",	/* FRAGINFO (cyan) */
+	"\033[31m",	/* OLD (red) */
+	"\033[32m",	/* NEW (green) */
+	"\033[33m",	/* COMMIT (yellow) */
+	"\033[41m",	/* WHITESPACE (red background) */
 };
 
 static int parse_diff_color_slot(const char *var, int ofs)
@@ -42,6 +43,8 @@ static int parse_diff_color_slot(const char *var, int ofs)
 		return DIFF_FILE_NEW;
 	if (!strcasecmp(var+ofs, "commit"))
 		return DIFF_COMMIT;
+	if (!strcasecmp(var+ofs, "whitespace"))
+		return DIFF_WHITESPACE;
 	die("bad config variable '%s'", var);
 }
 
@@ -383,9 +386,89 @@ const char *diff_get_color(int diff_use_color, enum color_diff ix)
 	return "";
 }
 
+static void emit_line(const char *set, const char *reset, const char *line, int len)
+{
+	if (len > 0 && line[len-1] == '\n')
+		len--;
+	fputs(set, stdout);
+	fwrite(line, len, 1, stdout);
+	puts(reset);
+}
+
+static void emit_add_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len)
+{
+	int col0 = ecbdata->nparents;
+	int last_tab_in_indent = -1;
+	int last_space_in_indent = -1;
+	int i;
+	int tail = len;
+	int need_highlight_leading_space = 0;
+	const char *ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE);
+	const char *set = diff_get_color(ecbdata->color_diff, DIFF_FILE_NEW);
+
+	if (!*ws) {
+		emit_line(set, reset, line, len);
+		return;
+	}
+
+	/* The line is a newly added line.  Does it have funny leading
+	 * whitespaces?  In indent, SP should never precede a TAB.
+	 */
+	for (i = col0; i < len; i++) {
+		if (line[i] == '\t') {
+			last_tab_in_indent = i;
+			if (0 <= last_space_in_indent)
+				need_highlight_leading_space = 1;
+		}
+		else if (line[i] == ' ')
+			last_space_in_indent = i;
+		else
+			break;
+	}
+	fputs(set, stdout);
+	fwrite(line, col0, 1, stdout);
+	fputs(reset, stdout);
+	if (((i == len) || line[i] == '\n') && i != col0) {
+		/* The whole line was indent */
+		emit_line(ws, reset, line + col0, len - col0);
+		return;
+	}
+	i = col0;
+	if (need_highlight_leading_space) {
+		while (i < last_tab_in_indent) {
+			if (line[i] == ' ') {
+				fputs(ws, stdout);
+				putchar(' ');
+				fputs(reset, stdout);
+			}
+			else
+				putchar(line[i]);
+			i++;
+		}
+	}
+	tail = len - 1;
+	if (line[tail] == '\n' && i < tail)
+		tail--;
+	while (i < tail) {
+		if (!isspace(line[tail]))
+			break;
+		tail--;
+	}
+	if ((i < tail && line[tail + 1] != '\n')) {
+		/* This has whitespace between tail+1..len */
+		fputs(set, stdout);
+		fwrite(line + i, tail - i + 1, 1, stdout);
+		fputs(reset, stdout);
+		emit_line(ws, reset, line + tail + 1, len - tail - 1);
+	}
+	else
+		emit_line(set, reset, line + i, len - i);
+}
+
 static void fn_out_consume(void *priv, char *line, unsigned long len)
 {
 	int i;
+	int color;
 	struct emit_callback *ecbdata = priv;
 	const char *set = diff_get_color(ecbdata->color_diff, DIFF_METAINFO);
 	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
@@ -403,45 +486,52 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		;
 	if (2 <= i && i < len && line[i] == ' ') {
 		ecbdata->nparents = i - 1;
-		set = diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO);
+		emit_line(diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO),
+			  reset, line, len);
+		return;
 	}
-	else if (len < ecbdata->nparents)
+
+	if (len < ecbdata->nparents) {
 		set = reset;
-	else {
-		int nparents = ecbdata->nparents;
-		int color = DIFF_PLAIN;
-		if (ecbdata->diff_words && nparents != 1)
-			/* fall back to normal diff */
-			free_diff_words_data(ecbdata);
-		if (ecbdata->diff_words) {
-			if (line[0] == '-') {
-				diff_words_append(line, len,
-						&ecbdata->diff_words->minus);
-				return;
-			} else if (line[0] == '+') {
-				diff_words_append(line, len,
-						&ecbdata->diff_words->plus);
-				return;
-			}
-			if (ecbdata->diff_words->minus.text.size ||
-					ecbdata->diff_words->plus.text.size)
-				diff_words_show(ecbdata->diff_words);
-			line++;
-			len--;
-		} else
-			for (i = 0; i < nparents && len; i++) {
-				if (line[i] == '-')
-					color = DIFF_FILE_OLD;
-				else if (line[i] == '+')
-					color = DIFF_FILE_NEW;
-			}
-		set = diff_get_color(ecbdata->color_diff, color);
+		emit_line(reset, reset, line, len);
+		return;
 	}
-	if (len > 0 && line[len-1] == '\n')
+
+	color = DIFF_PLAIN;
+	if (ecbdata->diff_words && ecbdata->nparents != 1)
+		/* fall back to normal diff */
+		free_diff_words_data(ecbdata);
+	if (ecbdata->diff_words) {
+		if (line[0] == '-') {
+			diff_words_append(line, len,
+					  &ecbdata->diff_words->minus);
+			return;
+		} else if (line[0] == '+') {
+			diff_words_append(line, len,
+					  &ecbdata->diff_words->plus);
+			return;
+		}
+		if (ecbdata->diff_words->minus.text.size ||
+		    ecbdata->diff_words->plus.text.size)
+			diff_words_show(ecbdata->diff_words);
+		line++;
 		len--;
-	fputs (set, stdout);
-	fwrite (line, len, 1, stdout);
-	puts (reset);
+		emit_line(set, reset, line, len);
+		return;
+	}
+	for (i = 0; i < ecbdata->nparents && len; i++) {
+		if (line[i] == '-')
+			color = DIFF_FILE_OLD;
+		else if (line[i] == '+')
+			color = DIFF_FILE_NEW;
+	}
+
+	if (color != DIFF_FILE_NEW) {
+		emit_line(diff_get_color(ecbdata->color_diff, color),
+			  reset, line, len);
+		return;
+	}
+	emit_add_line(reset, ecbdata, line, len);
 }
 
 static char *pprint_rename(const char *a, const char *b)

diff.h

@@ -86,6 +86,7 @@ enum color_diff {
 	DIFF_FILE_OLD = 4,
 	DIFF_FILE_NEW = 5,
 	DIFF_COMMIT = 6,
+	DIFF_WHITESPACE = 7,
 };
 const char *diff_get_color(int diff_use_color, enum color_diff ix);