X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=diff.c;h=3ad1f8c31046ee3dae8a8e9bed6dc9f5a5929b78;hb=c51f6ceed6a9a436f16f8b4f17eab1a3d17cffed;hp=07cf04365ca579d8488ae0263e05276d58f17832;hpb=018cff70462eb59779c96a383531c4440fb35b9c;p=git.git

diff --git a/diff.c b/diff.c
index 07cf04365..3ad1f8c31 100644
--- a/diff.c
+++ b/diff.c
@@ -11,6 +11,9 @@
 #include "attr.h"
 #include "run-command.h"
 #include "utf8.h"
+#include "userdiff.h"
+#include "sigchain.h"
+#include "submodule.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -20,21 +23,27 @@
 
 static int diff_detect_rename_default;
 static int diff_rename_limit_default = 200;
+static int diff_suppress_blank_empty;
 int diff_use_color_default = -1;
+static const char *diff_word_regex_cfg;
 static const char *external_diff_cmd_cfg;
 int diff_auto_refresh_index = 1;
+static int diff_mnemonic_prefix;
 
 static char diff_colors[][COLOR_MAXLEN] = {
-	"\033[m",	/* reset */
-	"",		/* 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) */
+	GIT_COLOR_RESET,
+	GIT_COLOR_NORMAL,	/* PLAIN */
+	GIT_COLOR_BOLD,		/* METAINFO */
+	GIT_COLOR_CYAN,		/* FRAGINFO */
+	GIT_COLOR_RED,		/* OLD */
+	GIT_COLOR_GREEN,	/* NEW */
+	GIT_COLOR_YELLOW,	/* COMMIT */
+	GIT_COLOR_BG_RED,	/* WHITESPACE */
 };
 
+static void diff_filespec_load_driver(struct diff_filespec *one);
+static char *run_textconv(const char *, struct diff_filespec *, size_t *);
+
 static int parse_diff_color_slot(const char *var, int ofs)
 {
 	if (!strcasecmp(var+ofs, "plain"))
@@ -54,78 +63,13 @@ static int parse_diff_color_slot(const char *var, int ofs)
 	die("bad config variable '%s'", var);
 }
 
-static struct ll_diff_driver {
-	const char *name;
-	struct ll_diff_driver *next;
-	const char *cmd;
-} *user_diff, **user_diff_tail;
-
-/*
- * Currently there is only "diff.<drivername>.command" variable;
- * because there are "diff.color.<slot>" variables, we are parsing
- * this in a bit convoluted way to allow low level diff driver
- * called "color".
- */
-static int parse_lldiff_command(const char *var, const char *ep, const char *value)
-{
-	const char *name;
-	int namelen;
-	struct ll_diff_driver *drv;
-
-	name = var + 5;
-	namelen = ep - name;
-	for (drv = user_diff; drv; drv = drv->next)
-		if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
-			break;
-	if (!drv) {
-		drv = xcalloc(1, sizeof(struct ll_diff_driver));
-		drv->name = xmemdupz(name, namelen);
-		if (!user_diff_tail)
-			user_diff_tail = &user_diff;
-		*user_diff_tail = drv;
-		user_diff_tail = &(drv->next);
-	}
-
-	return git_config_string(&(drv->cmd), var, value);
-}
-
-/*
- * 'diff.<what>.funcname' attribute can be specified in the configuration
- * to define a customized regexp to find the beginning of a function to
- * be used for hunk header lines of "diff -p" style output.
- */
-struct funcname_pattern_entry {
-	char *name;
-	char *pattern;
-	int cflags;
-};
-static struct funcname_pattern_list {
-	struct funcname_pattern_list *next;
-	struct funcname_pattern_entry e;
-} *funcname_pattern_list;
-
-static int parse_funcname_pattern(const char *var, const char *ep, const char *value, int cflags)
+static int git_config_rename(const char *var, const char *value)
 {
-	const char *name;
-	int namelen;
-	struct funcname_pattern_list *pp;
-
-	name = var + 5; /* "diff." */
-	namelen = ep - name;
-
-	for (pp = funcname_pattern_list; pp; pp = pp->next)
-		if (!strncmp(pp->e.name, name, namelen) && !pp->e.name[namelen])
-			break;
-	if (!pp) {
-		pp = xcalloc(1, sizeof(*pp));
-		pp->e.name = xmemdupz(name, namelen);
-		pp->next = funcname_pattern_list;
-		funcname_pattern_list = pp;
-	}
-	free(pp->e.pattern);
-	pp->e.pattern = xstrdup(value);
-	pp->e.cflags = cflags;
-	return 0;
+	if (!value)
+		return DIFF_DETECT_RENAME;
+	if (!strcasecmp(value, "copies") || !strcasecmp(value, "copy"))
+		return  DIFF_DETECT_COPY;
+	return git_config_bool(var,value) ? DIFF_DETECT_RENAME : 0;
 }
 
 /*
@@ -141,27 +85,21 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 	if (!strcmp(var, "diff.renames")) {
-		if (!value)
-			diff_detect_rename_default = DIFF_DETECT_RENAME;
-		else if (!strcasecmp(value, "copies") ||
-			 !strcasecmp(value, "copy"))
-			diff_detect_rename_default = DIFF_DETECT_COPY;
-		else if (git_config_bool(var,value))
-			diff_detect_rename_default = DIFF_DETECT_RENAME;
+		diff_detect_rename_default = git_config_rename(var, value);
 		return 0;
 	}
 	if (!strcmp(var, "diff.autorefreshindex")) {
 		diff_auto_refresh_index = git_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "diff.mnemonicprefix")) {
+		diff_mnemonic_prefix = git_config_bool(var, value);
+		return 0;
+	}
 	if (!strcmp(var, "diff.external"))
 		return git_config_string(&external_diff_cmd_cfg, var, value);
-	if (!prefixcmp(var, "diff.")) {
-		const char *ep = strrchr(var, '.');
-
-		if (ep != var + 4 && !strcmp(ep, ".command"))
-			return parse_lldiff_command(var, ep, value);
-	}
+	if (!strcmp(var, "diff.wordregex"))
+		return git_config_string(&diff_word_regex_cfg, var, value);
 
 	return git_diff_basic_config(var, value, cb);
 }
@@ -173,6 +111,12 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	switch (userdiff_config(var, value)) {
+		case 0: break;
+		case -1: return -1;
+		default: return 0;
+	}
+
 	if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
 		int slot = parse_diff_color_slot(var, 11);
 		if (!value)
@@ -181,21 +125,12 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	if (!prefixcmp(var, "diff.")) {
-		const char *ep = strrchr(var, '.');
-		if (ep != var + 4) {
-			if (!strcmp(ep, ".funcname")) {
-				if (!value)
-					return config_error_nonbool(var);
-				return parse_funcname_pattern(var, ep, value,
-					0);
-			} else if (!strcmp(ep, ".xfuncname")) {
-				if (!value)
-					return config_error_nonbool(var);
-				return parse_funcname_pattern(var, ep, value,
-					REG_EXTENDED);
-			}
-		}
+	/* like GNU diff's --suppress-blank-empty option  */
+	if (!strcmp(var, "diff.suppressblankempty") ||
+			/* for backwards compatibility */
+			!strcmp(var, "diff.suppress-blank-empty")) {
+		diff_suppress_blank_empty = git_config_bool(var, value);
+		return 0;
 	}
 
 	return git_color_default_config(var, value, cb);
@@ -205,9 +140,8 @@ static char *quote_two(const char *one, const char *two)
 {
 	int need_one = quote_c_style(one, NULL, NULL, 1);
 	int need_two = quote_c_style(two, NULL, NULL, 1);
-	struct strbuf res;
+	struct strbuf res = STRBUF_INIT;
 
-	strbuf_init(&res, 0);
 	if (need_one + need_two) {
 		strbuf_addch(&res, '"');
 		quote_c_style(one, &res, NULL, 1);
@@ -244,7 +178,6 @@ static struct diff_tempfile {
 typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);
 
 struct emit_callback {
-	struct xdiff_emit_state xm;
 	int color_diff;
 	unsigned ws_rule;
 	int blank_at_eof_in_preimage;
@@ -281,43 +214,6 @@ static int count_lines(const char *data, int size)
 	return count;
 }
 
-static void print_line_count(FILE *file, int count)
-{
-	switch (count) {
-	case 0:
-		fprintf(file, "0,0");
-		break;
-	case 1:
-		fprintf(file, "1");
-		break;
-	default:
-		fprintf(file, "1,%d", count);
-		break;
-	}
-}
-
-static void copy_file_with_prefix(FILE *file,
-				  int prefix, const char *data, int size,
-				  const char *set, const char *reset)
-{
-	int ch, nl_just_seen = 1;
-	while (0 < size--) {
-		ch = *data++;
-		if (nl_just_seen) {
-			fputs(set, file);
-			putc(prefix, file);
-		}
-		if (ch == '\n') {
-			nl_just_seen = 1;
-			fputs(reset, file);
-		} else
-			nl_just_seen = 0;
-		putc(ch, file);
-	}
-	if (!nl_just_seen)
-		fprintf(file, "%s\n\\ No newline at end of file\n", reset);
-}
-
 static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
 {
 	if (!DIFF_FILE_VALID(one)) {
@@ -327,6 +223,7 @@ static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
 	}
 	else if (diff_populate_filespec(one, 0))
 		return -1;
+
 	mf->ptr = one->data;
 	mf->size = one->size;
 	return 0;
@@ -447,10 +344,86 @@ static void emit_add_line(const char *reset,
 	}
 }
 
+static struct diff_tempfile *claim_diff_tempfile(void) {
+	int i;
+	for (i = 0; i < ARRAY_SIZE(diff_temp); i++)
+		if (!diff_temp[i].name)
+			return diff_temp + i;
+	die("BUG: diff is failing to clean up its tempfiles");
+}
+
+static int remove_tempfile_installed;
+
+static void remove_tempfile(void)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(diff_temp); i++) {
+		if (diff_temp[i].name == diff_temp[i].tmp_path)
+			unlink_or_warn(diff_temp[i].name);
+		diff_temp[i].name = NULL;
+	}
+}
+
+static void remove_tempfile_on_signal(int signo)
+{
+	remove_tempfile();
+	sigchain_pop(signo);
+	raise(signo);
+}
+
+static void print_line_count(FILE *file, int count)
+{
+	switch (count) {
+	case 0:
+		fprintf(file, "0,0");
+		break;
+	case 1:
+		fprintf(file, "1");
+		break;
+	default:
+		fprintf(file, "1,%d", count);
+		break;
+	}
+}
+
+static void emit_rewrite_lines(struct emit_callback *ecb,
+			       int prefix, const char *data, int size)
+{
+	const char *endp = NULL;
+	static const char *nneof = " No newline at end of file\n";
+	const char *old = diff_get_color(ecb->color_diff, DIFF_FILE_OLD);
+	const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET);
+
+	while (0 < size) {
+		int len;
+
+		endp = memchr(data, '\n', size);
+		len = endp ? (endp - data + 1) : size;
+		if (prefix != '+') {
+			ecb->lno_in_preimage++;
+			emit_line_0(ecb->file, old, reset, '-',
+				    data, len);
+		} else {
+			ecb->lno_in_postimage++;
+			emit_add_line(reset, ecb, data, len);
+		}
+		size -= len;
+		data += len;
+	}
+	if (!endp) {
+		const char *plain = diff_get_color(ecb->color_diff,
+						   DIFF_PLAIN);
+		emit_line_0(ecb->file, plain, reset, '\\',
+			    nneof, strlen(nneof));
+	}
+}
+
 static void emit_rewrite_diff(const char *name_a,
 			      const char *name_b,
 			      struct diff_filespec *one,
 			      struct diff_filespec *two,
+			      const char *textconv_one,
+			      const char *textconv_two,
 			      struct diff_options *o)
 {
 	int lc_a, lc_b;
@@ -458,10 +431,20 @@ static void emit_rewrite_diff(const char *name_a,
 	const char *name_a_tab, *name_b_tab;
 	const char *metainfo = diff_get_color(color_diff, DIFF_METAINFO);
 	const char *fraginfo = diff_get_color(color_diff, DIFF_FRAGINFO);
-	const char *old = diff_get_color(color_diff, DIFF_FILE_OLD);
-	const char *new = diff_get_color(color_diff, DIFF_FILE_NEW);
 	const char *reset = diff_get_color(color_diff, DIFF_RESET);
 	static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
+	const char *a_prefix, *b_prefix;
+	const char *data_one, *data_two;
+	size_t size_one, size_two;
+	struct emit_callback ecbdata;
+
+	if (diff_mnemonic_prefix && DIFF_OPT_TST(o, REVERSE_DIFF)) {
+		a_prefix = o->b_prefix;
+		b_prefix = o->a_prefix;
+	} else {
+		a_prefix = o->a_prefix;
+		b_prefix = o->b_prefix;
+	}
 
 	name_a += (*name_a == '/');
 	name_b += (*name_b == '/');
@@ -470,13 +453,48 @@ static void emit_rewrite_diff(const char *name_a,
 
 	strbuf_reset(&a_name);
 	strbuf_reset(&b_name);
-	quote_two_c_style(&a_name, o->a_prefix, name_a, 0);
-	quote_two_c_style(&b_name, o->b_prefix, name_b, 0);
+	quote_two_c_style(&a_name, a_prefix, name_a, 0);
+	quote_two_c_style(&b_name, b_prefix, name_b, 0);
 
 	diff_populate_filespec(one, 0);
 	diff_populate_filespec(two, 0);
-	lc_a = count_lines(one->data, one->size);
-	lc_b = count_lines(two->data, two->size);
+	if (textconv_one) {
+		data_one = run_textconv(textconv_one, one, &size_one);
+		if (!data_one)
+			die("unable to read files to diff");
+	}
+	else {
+		data_one = one->data;
+		size_one = one->size;
+	}
+	if (textconv_two) {
+		data_two = run_textconv(textconv_two, two, &size_two);
+		if (!data_two)
+			die("unable to read files to diff");
+	}
+	else {
+		data_two = two->data;
+		size_two = two->size;
+	}
+
+	memset(&ecbdata, 0, sizeof(ecbdata));
+	ecbdata.color_diff = color_diff;
+	ecbdata.found_changesp = &o->found_changes;
+	ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a);
+	ecbdata.file = o->file;
+	if (ecbdata.ws_rule & WS_BLANK_AT_EOF) {
+		mmfile_t mf1, mf2;
+		mf1.ptr = (char *)data_one;
+		mf2.ptr = (char *)data_two;
+		mf1.size = size_one;
+		mf2.size = size_two;
+		check_blank_at_eof(&mf1, &mf2, &ecbdata);
+	}
+	ecbdata.lno_in_preimage = 1;
+	ecbdata.lno_in_postimage = 1;
+
+	lc_a = count_lines(data_one, size_one);
+	lc_b = count_lines(data_two, size_two);
 	fprintf(o->file,
 		"%s--- %s%s%s\n%s+++ %s%s%s\n%s@@ -",
 		metainfo, a_name.buf, name_a_tab, reset,
@@ -486,91 +504,146 @@ static void emit_rewrite_diff(const char *name_a,
 	print_line_count(o->file, lc_b);
 	fprintf(o->file, " @@%s\n", reset);
 	if (lc_a)
-		copy_file_with_prefix(o->file, '-', one->data, one->size, old, reset);
+		emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
 	if (lc_b)
-		copy_file_with_prefix(o->file, '+', two->data, two->size, new, reset);
+		emit_rewrite_lines(&ecbdata, '+', data_two, size_two);
 }
 
 struct diff_words_buffer {
 	mmfile_t text;
 	long alloc;
-	long current; /* output pointer */
-	int suppressed_newline;
+	struct diff_words_orig {
+		const char *begin, *end;
+	} *orig;
+	int orig_nr, orig_alloc;
 };
 
 static void diff_words_append(char *line, unsigned long len,
 		struct diff_words_buffer *buffer)
 {
-	if (buffer->text.size + len > buffer->alloc) {
-		buffer->alloc = (buffer->text.size + len) * 3 / 2;
-		buffer->text.ptr = xrealloc(buffer->text.ptr, buffer->alloc);
-	}
+	ALLOC_GROW(buffer->text.ptr, buffer->text.size + len, buffer->alloc);
 	line++;
 	len--;
 	memcpy(buffer->text.ptr + buffer->text.size, line, len);
 	buffer->text.size += len;
+	buffer->text.ptr[buffer->text.size] = '\0';
 }
 
 struct diff_words_data {
-	struct xdiff_emit_state xm;
 	struct diff_words_buffer minus, plus;
+	const char *current_plus;
 	FILE *file;
+	regex_t *word_regex;
 };
 
-static void print_word(FILE *file, struct diff_words_buffer *buffer, int len, int color,
-		int suppress_newline)
+static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 {
-	const char *ptr;
-	int eol = 0;
+	struct diff_words_data *diff_words = priv;
+	int minus_first, minus_len, plus_first, plus_len;
+	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
 
-	if (len == 0)
+	if (line[0] != '@' || parse_hunk_header(line, len,
+			&minus_first, &minus_len, &plus_first, &plus_len))
 		return;
 
-	ptr  = buffer->text.ptr + buffer->current;
-	buffer->current += len;
+	/* POSIX requires that first be decremented by one if len == 0... */
+	if (minus_len) {
+		minus_begin = diff_words->minus.orig[minus_first].begin;
+		minus_end =
+			diff_words->minus.orig[minus_first + minus_len - 1].end;
+	} else
+		minus_begin = minus_end =
+			diff_words->minus.orig[minus_first].end;
 
-	if (ptr[len - 1] == '\n') {
-		eol = 1;
-		len--;
+	if (plus_len) {
+		plus_begin = diff_words->plus.orig[plus_first].begin;
+		plus_end = diff_words->plus.orig[plus_first + plus_len - 1].end;
+	} else
+		plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
+
+	if (diff_words->current_plus != plus_begin)
+		fwrite(diff_words->current_plus,
+				plus_begin - diff_words->current_plus, 1,
+				diff_words->file);
+	if (minus_begin != minus_end)
+		color_fwrite_lines(diff_words->file,
+				diff_get_color(1, DIFF_FILE_OLD),
+				minus_end - minus_begin, minus_begin);
+	if (plus_begin != plus_end)
+		color_fwrite_lines(diff_words->file,
+				diff_get_color(1, DIFF_FILE_NEW),
+				plus_end - plus_begin, plus_begin);
+
+	diff_words->current_plus = plus_end;
+}
+
+/* This function starts looking at *begin, and returns 0 iff a word was found. */
+static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex,
+		int *begin, int *end)
+{
+	if (word_regex && *begin < buffer->size) {
+		regmatch_t match[1];
+		if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) {
+			char *p = memchr(buffer->ptr + *begin + match[0].rm_so,
+					'\n', match[0].rm_eo - match[0].rm_so);
+			*end = p ? p - buffer->ptr : match[0].rm_eo + *begin;
+			*begin += match[0].rm_so;
+			return *begin >= *end;
+		}
+		return -1;
 	}
 
-	fputs(diff_get_color(1, color), file);
-	fwrite(ptr, len, 1, file);
-	fputs(diff_get_color(1, DIFF_RESET), file);
+	/* find the next word */
+	while (*begin < buffer->size && isspace(buffer->ptr[*begin]))
+		(*begin)++;
+	if (*begin >= buffer->size)
+		return -1;
 
-	if (eol) {
-		if (suppress_newline)
-			buffer->suppressed_newline = 1;
-		else
-			putc('\n', file);
-	}
+	/* find the end of the word */
+	*end = *begin + 1;
+	while (*end < buffer->size && !isspace(buffer->ptr[*end]))
+		(*end)++;
+
+	return 0;
 }
 
-static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
+/*
+ * This function splits the words in buffer->text, stores the list with
+ * newline separator into out, and saves the offsets of the original words
+ * in buffer->orig.
+ */
+static void diff_words_fill(struct diff_words_buffer *buffer, mmfile_t *out,
+		regex_t *word_regex)
 {
-	struct diff_words_data *diff_words = priv;
+	int i, j;
+	long alloc = 0;
 
-	if (diff_words->minus.suppressed_newline) {
-		if (line[0] != '+')
-			putc('\n', diff_words->file);
-		diff_words->minus.suppressed_newline = 0;
-	}
+	out->size = 0;
+	out->ptr = NULL;
 
-	len--;
-	switch (line[0]) {
-		case '-':
-			print_word(diff_words->file,
-				   &diff_words->minus, len, DIFF_FILE_OLD, 1);
-			break;
-		case '+':
-			print_word(diff_words->file,
-				   &diff_words->plus, len, DIFF_FILE_NEW, 0);
-			break;
-		case ' ':
-			print_word(diff_words->file,
-				   &diff_words->plus, len, DIFF_PLAIN, 0);
-			diff_words->minus.current += len;
-			break;
+	/* fake an empty "0th" word */
+	ALLOC_GROW(buffer->orig, 1, buffer->orig_alloc);
+	buffer->orig[0].begin = buffer->orig[0].end = buffer->text.ptr;
+	buffer->orig_nr = 1;
+
+	for (i = 0; i < buffer->text.size; i++) {
+		if (find_word_boundaries(&buffer->text, word_regex, &i, &j))
+			return;
+
+		/* store original boundaries */
+		ALLOC_GROW(buffer->orig, buffer->orig_nr + 1,
+				buffer->orig_alloc);
+		buffer->orig[buffer->orig_nr].begin = buffer->text.ptr + i;
+		buffer->orig[buffer->orig_nr].end = buffer->text.ptr + j;
+		buffer->orig_nr++;
+
+		/* store one word */
+		ALLOC_GROW(out->ptr, out->size + j - i + 1, alloc);
+		memcpy(out->ptr + out->size, buffer->text.ptr + i, j - i);
+		out->ptr[out->size + j - i] = '\n';
+		out->size += j - i + 1;
+
+		i = j - 1;
 	}
 }
 
@@ -581,40 +654,36 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	xdemitconf_t xecfg;
 	xdemitcb_t ecb;
 	mmfile_t minus, plus;
-	int i;
 
-	memset(&xecfg, 0, sizeof(xecfg));
-	minus.size = diff_words->minus.text.size;
-	minus.ptr = xmalloc(minus.size);
-	memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
-	for (i = 0; i < minus.size; i++)
-		if (isspace(minus.ptr[i]))
-			minus.ptr[i] = '\n';
-	diff_words->minus.current = 0;
-
-	plus.size = diff_words->plus.text.size;
-	plus.ptr = xmalloc(plus.size);
-	memcpy(plus.ptr, diff_words->plus.text.ptr, plus.size);
-	for (i = 0; i < plus.size; i++)
-		if (isspace(plus.ptr[i]))
-			plus.ptr[i] = '\n';
-	diff_words->plus.current = 0;
+	/* special case: only removal */
+	if (!diff_words->plus.text.size) {
+		color_fwrite_lines(diff_words->file,
+			diff_get_color(1, DIFF_FILE_OLD),
+			diff_words->minus.text.size, diff_words->minus.text.ptr);
+		diff_words->minus.text.size = 0;
+		return;
+	}
 
-	xpp.flags = XDF_NEED_MINIMAL;
-	xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
-	ecb.outf = xdiff_outf;
-	ecb.priv = diff_words;
-	diff_words->xm.consume = fn_out_diff_words_aux;
-	xdi_diff(&minus, &plus, &xpp, &xecfg, &ecb);
+	diff_words->current_plus = diff_words->plus.text.ptr;
 
+	memset(&xpp, 0, sizeof(xpp));
+	memset(&xecfg, 0, sizeof(xecfg));
+	diff_words_fill(&diff_words->minus, &minus, diff_words->word_regex);
+	diff_words_fill(&diff_words->plus, &plus, diff_words->word_regex);
+	xpp.flags = XDF_NEED_MINIMAL;
+	/* as only the hunk header will be parsed, we need a 0-context */
+	xecfg.ctxlen = 0;
+	xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
+		      &xpp, &xecfg, &ecb);
 	free(minus.ptr);
 	free(plus.ptr);
+	if (diff_words->current_plus != diff_words->plus.text.ptr +
+			diff_words->plus.text.size)
+		fwrite(diff_words->current_plus,
+			diff_words->plus.text.ptr + diff_words->plus.text.size
+			- diff_words->current_plus, 1,
+			diff_words->file);
 	diff_words->minus.text.size = diff_words->plus.text.size = 0;
-
-	if (diff_words->minus.suppressed_newline) {
-		putc('\n', diff_words->file);
-		diff_words->minus.suppressed_newline = 0;
-	}
 }
 
 static void free_diff_words_data(struct emit_callback *ecbdata)
@@ -626,7 +695,10 @@ static void free_diff_words_data(struct emit_callback *ecbdata)
 			diff_words_show(ecbdata->diff_words);
 
 		free (ecbdata->diff_words->minus.text.ptr);
+		free (ecbdata->diff_words->minus.orig);
 		free (ecbdata->diff_words->plus.text.ptr);
+		free (ecbdata->diff_words->plus.orig);
+		free(ecbdata->diff_words->word_regex);
 		free(ecbdata->diff_words);
 		ecbdata->diff_words = NULL;
 	}
@@ -694,6 +766,12 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
 	}
 
+	if (diff_suppress_blank_empty
+	    && len == 2 && line[0] == ' ' && line[1] == '\n') {
+		line[0] = '\n';
+		len = 1;
+	}
+
 	if (line[0] == '@') {
 		len = sane_truncate_line(ecbdata, line, len);
 		find_lno(line, ecbdata);
@@ -747,7 +825,7 @@ static char *pprint_rename(const char *a, const char *b)
 {
 	const char *old = a;
 	const char *new = b;
-	struct strbuf name;
+	struct strbuf name = STRBUF_INIT;
 	int pfx_length, sfx_length;
 	int len_a = strlen(a);
 	int len_b = strlen(b);
@@ -755,7 +833,6 @@ static char *pprint_rename(const char *a, const char *b)
 	int qlen_a = quote_c_style(a, NULL, NULL, 0);
 	int qlen_b = quote_c_style(b, NULL, NULL, 0);
 
-	strbuf_init(&name, 0);
 	if (qlen_a || qlen_b) {
 		quote_c_style(a, &name, NULL, 0);
 		strbuf_addstr(&name, " => ");
@@ -812,8 +889,6 @@ static char *pprint_rename(const char *a, const char *b)
 }
 
 struct diffstat_t {
-	struct xdiff_emit_state xm;
-
 	int nr;
 	int alloc;
 	struct diffstat_file {
@@ -876,10 +951,9 @@ static int scale_linear(int it, int width, int max_change)
 }
 
 static void show_name(FILE *file,
-		      const char *prefix, const char *name, int len,
-		      const char *reset, const char *set)
+		      const char *prefix, const char *name, int len)
 {
-	fprintf(file, " %s%s%-*s%s |", set, prefix, len, name, reset);
+	fprintf(file, " %s%-*s |", prefix, len, name);
 }
 
 static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset)
@@ -900,8 +974,7 @@ static void fill_print_name(struct diffstat_file *file)
 		return;
 
 	if (!file->is_renamed) {
-		struct strbuf buf;
-		strbuf_init(&buf, 0);
+		struct strbuf buf = STRBUF_INIT;
 		if (quote_c_style(file->name, &buf, NULL, 0)) {
 			pname = strbuf_detach(&buf, NULL);
 		} else {
@@ -914,9 +987,9 @@ static void fill_print_name(struct diffstat_file *file)
 	file->print_name = pname;
 }
 
-static void show_stats(struct diffstat_t* data, struct diff_options *options)
+static void show_stats(struct diffstat_t *data, struct diff_options *options)
 {
-	int i, len, add, del, total, adds = 0, dels = 0;
+	int i, len, add, del, adds = 0, dels = 0;
 	int max_change = 0, max_len = 0;
 	int total_files = data->nr;
 	int width, name_width;
@@ -994,7 +1067,7 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options)
 		}
 
 		if (data->files[i]->is_binary) {
-			show_name(options->file, prefix, name, len, reset, set);
+			show_name(options->file, prefix, name, len);
 			fprintf(options->file, "  Bin ");
 			fprintf(options->file, "%s%d%s", del_c, deleted, reset);
 			fprintf(options->file, " -> ");
@@ -1004,7 +1077,7 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options)
 			continue;
 		}
 		else if (data->files[i]->is_unmerged) {
-			show_name(options->file, prefix, name, len, reset, set);
+			show_name(options->file, prefix, name, len);
 			fprintf(options->file, "  Unmerged\n");
 			continue;
 		}
@@ -1019,16 +1092,14 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options)
 		 */
 		add = added;
 		del = deleted;
-		total = add + del;
 		adds += add;
 		dels += del;
 
 		if (width <= max_change) {
 			add = scale_linear(add, width, max_change);
 			del = scale_linear(del, width, max_change);
-			total = add + del;
 		}
-		show_name(options->file, prefix, name, len, reset, set);
+		show_name(options->file, prefix, name, len);
 		fprintf(options->file, "%5d%s", added + deleted,
 				added + deleted ? " " : "");
 		show_graph(options->file, '+', add, add_c, reset);
@@ -1036,11 +1107,11 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options)
 		fprintf(options->file, "\n");
 	}
 	fprintf(options->file,
-	       "%s %d files changed, %d insertions(+), %d deletions(-)%s\n",
-	       set, total_files, adds, dels, reset);
+	       " %d files changed, %d insertions(+), %d deletions(-)\n",
+	       total_files, adds, dels);
 }
 
-static void show_shortstats(struct diffstat_t* data, struct diff_options *options)
+static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
 {
 	int i, adds = 0, dels = 0, total_files = data->nr;
 
@@ -1065,7 +1136,7 @@ static void show_shortstats(struct diffstat_t* data, struct diff_options *option
 	       total_files, adds, dels);
 }
 
-static void show_numstat(struct diffstat_t* data, struct diff_options *options)
+static void show_numstat(struct diffstat_t *data, struct diff_options *options)
 {
 	int i;
 
@@ -1208,9 +1279,13 @@ static void show_dirstat(struct diff_options *options)
 		/*
 		 * Original minus copied is the removed material,
 		 * added is the new material.  They are both damages
-		 * made to the preimage.
+		 * made to the preimage. In --dirstat-by-file mode, count
+		 * damaged files, not damaged lines. This is done by
+		 * counting only a single damaged line per file.
 		 */
 		damage = (p->one->size - copied) + added;
+		if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE) && damage > 0)
+			damage = 1;
 
 		ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc);
 		dir.files[dir.nr].name = name;
@@ -1243,7 +1318,6 @@ static void free_diffstat_info(struct diffstat_t *diffstat)
 }
 
 struct checkdiff_t {
-	struct xdiff_emit_state xm;
 	const char *filename;
 	int lineno;
 	struct diff_options *o;
@@ -1411,123 +1485,61 @@ static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two)
 	emit_binary_diff_body(file, two, one);
 }
 
-static void setup_diff_attr_check(struct git_attr_check *check)
+static void diff_filespec_load_driver(struct diff_filespec *one)
 {
-	static struct git_attr *attr_diff;
-
-	if (!attr_diff) {
-		attr_diff = git_attr("diff", 4);
-	}
-	check[0].attr = attr_diff;
+	if (!one->driver)
+		one->driver = userdiff_find_by_path(one->path);
+	if (!one->driver)
+		one->driver = userdiff_find_by_name("default");
 }
 
-static void diff_filespec_check_attr(struct diff_filespec *one)
+int diff_filespec_is_binary(struct diff_filespec *one)
 {
-	struct git_attr_check attr_diff_check;
-	int check_from_data = 0;
-
-	if (one->checked_attr)
-		return;
-
-	setup_diff_attr_check(&attr_diff_check);
-	one->is_binary = 0;
-	one->funcname_pattern_ident = NULL;
-
-	if (!git_checkattr(one->path, 1, &attr_diff_check)) {
-		const char *value;
-
-		/* binaryness */
-		value = attr_diff_check.value;
-		if (ATTR_TRUE(value))
-			;
-		else if (ATTR_FALSE(value))
-			one->is_binary = 1;
-		else
-			check_from_data = 1;
-
-		/* funcname pattern ident */
-		if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
-			;
-		else
-			one->funcname_pattern_ident = value;
-	}
-
-	if (check_from_data) {
-		if (!one->data && DIFF_FILE_VALID(one))
-			diff_populate_filespec(one, 0);
-
-		if (one->data)
-			one->is_binary = buffer_is_binary(one->data, one->size);
+	if (one->is_binary == -1) {
+		diff_filespec_load_driver(one);
+		if (one->driver->binary != -1)
+			one->is_binary = one->driver->binary;
+		else {
+			if (!one->data && DIFF_FILE_VALID(one))
+				diff_populate_filespec(one, 0);
+			if (one->data)
+				one->is_binary = buffer_is_binary(one->data,
+						one->size);
+			if (one->is_binary == -1)
+				one->is_binary = 0;
+		}
 	}
+	return one->is_binary;
 }
 
-int diff_filespec_is_binary(struct diff_filespec *one)
+static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespec *one)
 {
-	diff_filespec_check_attr(one);
-	return one->is_binary;
+	diff_filespec_load_driver(one);
+	return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
 }
 
-static const struct funcname_pattern_entry *funcname_pattern(const char *ident)
-{
-	struct funcname_pattern_list *pp;
-
-	for (pp = funcname_pattern_list; pp; pp = pp->next)
-		if (!strcmp(ident, pp->e.name))
-			return &pp->e;
-	return NULL;
-}
-
-static const struct funcname_pattern_entry builtin_funcname_pattern[] = {
-	{ "java",
-	  "!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
-	  "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$",
-	  REG_EXTENDED },
-	{ "pascal",
-	  "^((procedure|function|constructor|destructor|interface|"
-		"implementation|initialization|finalization)[ \t]*.*)$"
-	  "|"
-	  "^(.*=[ \t]*(class|record).*)$",
-	  REG_EXTENDED },
-	{ "bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
-	  REG_EXTENDED },
-	{ "tex",
-	  "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
-	  REG_EXTENDED },
-	{ "ruby", "^[ \t]*((class|module|def)[ \t].*)$",
-	  REG_EXTENDED },
-};
-
-static const struct funcname_pattern_entry *diff_funcname_pattern(struct diff_filespec *one)
+static const char *userdiff_word_regex(struct diff_filespec *one)
 {
-	const char *ident;
-	const struct funcname_pattern_entry *pe;
-	int i;
-
-	diff_filespec_check_attr(one);
-	ident = one->funcname_pattern_ident;
-
-	if (!ident)
-		/*
-		 * If the config file has "funcname.default" defined, that
-		 * regexp is used; otherwise NULL is returned and xemit uses
-		 * the built-in default.
-		 */
-		return funcname_pattern("default");
-
-	/* Look up custom "funcname.$ident" regexp from config. */
-	pe = funcname_pattern(ident);
-	if (pe)
-		return pe;
+	diff_filespec_load_driver(one);
+	return one->driver->word_regex;
+}
 
-	/*
-	 * And define built-in fallback patterns here.  Note that
-	 * these can be overridden by the user's config settings.
-	 */
-	for (i = 0; i < ARRAY_SIZE(builtin_funcname_pattern); i++)
-		if (!strcmp(ident, builtin_funcname_pattern[i].name))
-			return &builtin_funcname_pattern[i];
+void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
+{
+	if (!options->a_prefix)
+		options->a_prefix = a;
+	if (!options->b_prefix)
+		options->b_prefix = b;
+}
 
-	return NULL;
+static const char *get_textconv(struct diff_filespec *one)
+{
+	if (!DIFF_FILE_VALID(one))
+		return NULL;
+	if (!S_ISREG(one->mode))
+		return NULL;
+	diff_filespec_load_driver(one);
+	return one->driver->textconv;
 }
 
 static void builtin_diff(const char *name_a,
@@ -1543,13 +1555,40 @@ static void builtin_diff(const char *name_a,
 	char *a_one, *b_two;
 	const char *set = diff_get_color_opt(o, DIFF_METAINFO);
 	const char *reset = diff_get_color_opt(o, DIFF_RESET);
+	const char *a_prefix, *b_prefix;
+	const char *textconv_one = NULL, *textconv_two = NULL;
+
+	if (DIFF_OPT_TST(o, SUBMODULE_LOG) &&
+			(!one->mode || S_ISGITLINK(one->mode)) &&
+			(!two->mode || S_ISGITLINK(two->mode))) {
+		const char *del = diff_get_color_opt(o, DIFF_FILE_OLD);
+		const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
+		show_submodule_summary(o->file, one ? one->path : two->path,
+				one->sha1, two->sha1,
+				del, add, reset);
+		return;
+	}
+
+	if (DIFF_OPT_TST(o, ALLOW_TEXTCONV)) {
+		textconv_one = get_textconv(one);
+		textconv_two = get_textconv(two);
+	}
+
+	diff_set_mnemonic_prefix(o, "a/", "b/");
+	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
+		a_prefix = o->b_prefix;
+		b_prefix = o->a_prefix;
+	} else {
+		a_prefix = o->a_prefix;
+		b_prefix = o->b_prefix;
+	}
 
 	/* Never use a non-valid filename anywhere if at all possible */
 	name_a = DIFF_FILE_VALID(one) ? name_a : name_b;
 	name_b = DIFF_FILE_VALID(two) ? name_b : name_a;
 
-	a_one = quote_two(o->a_prefix, name_a + (*name_a == '/'));
-	b_two = quote_two(o->b_prefix, name_b + (*name_b == '/'));
+	a_one = quote_two(a_prefix, name_a + (*name_a == '/'));
+	b_two = quote_two(b_prefix, name_b + (*name_b == '/'));
 	lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null";
 	lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null";
 	fprintf(o->file, "%sdiff --git %s %s%s\n", set, a_one, b_two, reset);
@@ -1577,8 +1616,11 @@ static void builtin_diff(const char *name_a,
 		 */
 		if ((one->mode ^ two->mode) & S_IFMT)
 			goto free_ab_and_return;
-		if (complete_rewrite) {
-			emit_rewrite_diff(name_a, name_b, one, two, o);
+		if (complete_rewrite &&
+		    (textconv_one || !diff_filespec_is_binary(one)) &&
+		    (textconv_two || !diff_filespec_is_binary(two))) {
+			emit_rewrite_diff(name_a, name_b, one, two,
+						textconv_one, textconv_two, o);
 			o->found_changes = 1;
 			goto free_ab_and_return;
 		}
@@ -1588,7 +1630,8 @@ static void builtin_diff(const char *name_a,
 		die("unable to read files to diff");
 
 	if (!DIFF_OPT_TST(o, TEXT) &&
-	    (diff_filespec_is_binary(one) || diff_filespec_is_binary(two))) {
+	    ( (diff_filespec_is_binary(one) && !textconv_one) ||
+	      (diff_filespec_is_binary(two) && !textconv_two) )) {
 		/* Quite common confusing case */
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
@@ -1607,12 +1650,28 @@ static void builtin_diff(const char *name_a,
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 		struct emit_callback ecbdata;
-		const struct funcname_pattern_entry *pe;
+		const struct userdiff_funcname *pe;
+
+		if (textconv_one) {
+			size_t size;
+			mf1.ptr = run_textconv(textconv_one, one, &size);
+			if (!mf1.ptr)
+				die("unable to read files to diff");
+			mf1.size = size;
+		}
+		if (textconv_two) {
+			size_t size;
+			mf2.ptr = run_textconv(textconv_two, two, &size);
+			if (!mf2.ptr)
+				die("unable to read files to diff");
+			mf2.size = size;
+		}
 
 		pe = diff_funcname_pattern(one);
 		if (!pe)
 			pe = diff_funcname_pattern(two);
 
+		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		memset(&ecbdata, 0, sizeof(ecbdata));
 		ecbdata.label_path = lbl;
@@ -1624,6 +1683,7 @@ static void builtin_diff(const char *name_a,
 		ecbdata.file = o->file;
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
 		xecfg.ctxlen = o->context;
+		xecfg.interhunkctxlen = o->interhunkcontext;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
 		if (pe)
 			xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
@@ -1633,17 +1693,35 @@ static void builtin_diff(const char *name_a,
 			xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10);
 		else if (!prefixcmp(diffopts, "-u"))
 			xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10);
-		ecb.outf = xdiff_outf;
-		ecb.priv = &ecbdata;
-		ecbdata.xm.consume = fn_out_consume;
 		if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS)) {
 			ecbdata.diff_words =
 				xcalloc(1, sizeof(struct diff_words_data));
 			ecbdata.diff_words->file = o->file;
+			if (!o->word_regex)
+				o->word_regex = userdiff_word_regex(one);
+			if (!o->word_regex)
+				o->word_regex = userdiff_word_regex(two);
+			if (!o->word_regex)
+				o->word_regex = diff_word_regex_cfg;
+			if (o->word_regex) {
+				ecbdata.diff_words->word_regex = (regex_t *)
+					xmalloc(sizeof(regex_t));
+				if (regcomp(ecbdata.diff_words->word_regex,
+						o->word_regex,
+						REG_EXTENDED | REG_NEWLINE))
+					die ("Invalid regular expression: %s",
+							o->word_regex);
+			}
 		}
-		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
+		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
+			      &xpp, &xecfg, &ecb);
 		if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS))
 			free_diff_words_data(&ecbdata);
+		if (textconv_one)
+			free(mf1.ptr);
+		if (textconv_two)
+			free(mf2.ptr);
+		xdiff_clear_find_func(&xecfg);
 	}
 
  free_ab_and_return:
@@ -1690,11 +1768,11 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 
+		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
-		ecb.outf = xdiff_outf;
-		ecb.priv = diffstat;
-		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
+		xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat,
+			      &xpp, &xecfg, &ecb);
 	}
 
  free_and_return:
@@ -1715,7 +1793,6 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 		return;
 
 	memset(&data, 0, sizeof(data));
-	data.xm.consume = checkdiff_consume;
 	data.filename = name_b ? name_b : name_a;
 	data.lineno = 0;
 	data.o = o;
@@ -1738,12 +1815,12 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 
+		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		xecfg.ctxlen = 1; /* at least one context line */
 		xpp.flags = XDF_NEED_MINIMAL;
-		ecb.outf = xdiff_outf;
-		ecb.priv = &data;
-		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
+		xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data,
+			      &xpp, &xecfg, &ecb);
 
 		if (data.ws_rule & WS_BLANK_AT_EOF) {
 			struct emit_callback ecbdata;
@@ -1779,6 +1856,7 @@ struct diff_filespec *alloc_filespec(const char *path)
 	spec->path = (char *)(spec + 1);
 	memcpy(spec->path, path, namelen+1);
 	spec->count = 1;
+	spec->is_binary = -1;
 	return spec;
 }
 
@@ -1811,7 +1889,8 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 	struct stat st;
 	int pos, len;
 
-	/* We do not read the cache ourselves here, because the
+	/*
+	 * We do not read the cache ourselves here, because the
 	 * benchmark with my previous version that always reads cache
 	 * shows that it makes things worse for diff-tree comparing
 	 * two linux-2.6 kernel trees in an already checked out work
@@ -1835,7 +1914,7 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 	 * objects however would tend to be slower as they need
 	 * to be individually opened and inflated.
 	 */
-	if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1, NULL))
+	if (!FAST_WORKING_DIRECTORY && !want_file && has_sha1_pack(sha1))
 		return 0;
 
 	len = strlen(name);
@@ -1851,6 +1930,13 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 	if (hashcmp(sha1, ce->sha1) || !S_ISREG(ce->ce_mode))
 		return 0;
 
+	/*
+	 * If ce is marked as "assume unchanged", there is no
+	 * guarantee that work tree matches what we are looking for.
+	 */
+	if (ce->ce_flags & CE_VALID)
+		return 0;
+
 	/*
 	 * If ce matches the file in the work tree, we can reuse it.
 	 */
@@ -1863,10 +1949,9 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 
 static int populate_from_stdin(struct diff_filespec *s)
 {
-	struct strbuf buf;
+	struct strbuf buf = STRBUF_INIT;
 	size_t size = 0;
 
-	strbuf_init(&buf, 0);
 	if (strbuf_read(&buf, 0, 0) < 0)
 		return error("error while reading from stdin %s",
 				     strerror(errno));
@@ -1918,7 +2003,7 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 
 	if (!s->sha1_valid ||
 	    reuse_worktree_file(s->path, s->sha1, 0)) {
-		struct strbuf buf;
+		struct strbuf buf = STRBUF_INIT;
 		struct stat st;
 		int fd;
 
@@ -1938,19 +2023,18 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 		s->size = xsize_t(st.st_size);
 		if (!s->size)
 			goto empty;
-		if (size_only)
-			return 0;
 		if (S_ISLNK(st.st_mode)) {
-			int ret;
-			s->data = xmalloc(s->size);
-			s->should_free = 1;
-			ret = readlink(s->path, s->data, s->size);
-			if (ret < 0) {
-				free(s->data);
+			struct strbuf sb = STRBUF_INIT;
+
+			if (strbuf_readlink(&sb, s->path, s->size))
 				goto err_empty;
-			}
+			s->size = sb.len;
+			s->data = strbuf_detach(&sb, NULL);
+			s->should_free = 1;
 			return 0;
 		}
+		if (size_only)
+			return 0;
 		fd = open(s->path, O_RDONLY);
 		if (fd < 0)
 			goto err_empty;
@@ -1961,7 +2045,6 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 		/*
 		 * Convert from working tree format to canonical git format
 		 */
-		strbuf_init(&buf, 0);
 		if (convert_to_git(s->path, s->data, s->size, &buf, safe_crlf)) {
 			size_t size = 0;
 			munmap(s->data, s->size);
@@ -2003,30 +2086,48 @@ void diff_free_filespec_data(struct diff_filespec *s)
 	s->cnt_data = NULL;
 }
 
-static void prep_temp_blob(struct diff_tempfile *temp,
+static void prep_temp_blob(const char *path, struct diff_tempfile *temp,
 			   void *blob,
 			   unsigned long size,
 			   const unsigned char *sha1,
 			   int mode)
 {
 	int fd;
+	struct strbuf buf = STRBUF_INIT;
+	struct strbuf template = STRBUF_INIT;
+	char *path_dup = xstrdup(path);
+	const char *base = basename(path_dup);
+
+	/* Generate "XXXXXX_basename.ext" */
+	strbuf_addstr(&template, "XXXXXX_");
+	strbuf_addstr(&template, base);
 
-	fd = git_mkstemp(temp->tmp_path, PATH_MAX, ".diff_XXXXXX");
+	fd = git_mkstemps(temp->tmp_path, PATH_MAX, template.buf,
+			strlen(base) + 1);
 	if (fd < 0)
-		die("unable to create temp-file: %s", strerror(errno));
+		die_errno("unable to create temp-file");
+	if (convert_to_working_tree(path,
+			(const char *)blob, (size_t)size, &buf)) {
+		blob = buf.buf;
+		size = buf.len;
+	}
 	if (write_in_full(fd, blob, size) != size)
-		die("unable to write temp-file");
+		die_errno("unable to write temp-file");
 	close(fd);
 	temp->name = temp->tmp_path;
 	strcpy(temp->hex, sha1_to_hex(sha1));
 	temp->hex[40] = 0;
 	sprintf(temp->mode, "%06o", mode);
+	strbuf_release(&buf);
+	strbuf_release(&template);
+	free(path_dup);
 }
 
-static void prepare_temp_file(const char *name,
-			      struct diff_tempfile *temp,
-			      struct diff_filespec *one)
+static struct diff_tempfile *prepare_temp_file(const char *name,
+		struct diff_filespec *one)
 {
+	struct diff_tempfile *temp = claim_diff_tempfile();
+
 	if (!DIFF_FILE_VALID(one)) {
 	not_a_valid_file:
 		/* A '-' entry produces this for file-2, and
@@ -2035,7 +2136,13 @@ static void prepare_temp_file(const char *name,
 		temp->name = "/dev/null";
 		strcpy(temp->hex, ".");
 		strcpy(temp->mode, ".");
-		return;
+		return temp;
+	}
+
+	if (!remove_tempfile_installed) {
+		atexit(remove_tempfile);
+		sigchain_push_common(remove_tempfile_on_signal);
+		remove_tempfile_installed = 1;
 	}
 
 	if (!one->sha1_valid ||
@@ -2044,22 +2151,18 @@ static void prepare_temp_file(const char *name,
 		if (lstat(name, &st) < 0) {
 			if (errno == ENOENT)
 				goto not_a_valid_file;
-			die("stat(%s): %s", name, strerror(errno));
+			die_errno("stat(%s)", name);
 		}
 		if (S_ISLNK(st.st_mode)) {
-			int ret;
-			char buf[PATH_MAX + 1]; /* ought to be SYMLINK_MAX */
-			size_t sz = xsize_t(st.st_size);
-			if (sizeof(buf) <= st.st_size)
-				die("symlink too long: %s", name);
-			ret = readlink(name, buf, sz);
-			if (ret < 0)
-				die("readlink(%s)", name);
-			prep_temp_blob(temp, buf, sz,
+			struct strbuf sb = STRBUF_INIT;
+			if (strbuf_readlink(&sb, name, st.st_size) < 0)
+				die_errno("readlink(%s)", name);
+			prep_temp_blob(name, temp, sb.buf, sb.len,
 				       (one->sha1_valid ?
 					one->sha1 : null_sha1),
 				       (one->sha1_valid ?
 					one->mode : S_IFLNK));
+			strbuf_release(&sb);
 		}
 		else {
 			/* we can borrow from the file in the work tree */
@@ -2076,32 +2179,15 @@ static void prepare_temp_file(const char *name,
 			 */
 			sprintf(temp->mode, "%06o", one->mode);
 		}
-		return;
+		return temp;
 	}
 	else {
 		if (diff_populate_filespec(one, 0))
 			die("cannot read data blob for %s", one->path);
-		prep_temp_blob(temp, one->data, one->size,
+		prep_temp_blob(name, temp, one->data, one->size,
 			       one->sha1, one->mode);
 	}
-}
-
-static void remove_tempfile(void)
-{
-	int i;
-
-	for (i = 0; i < 2; i++)
-		if (diff_temp[i].name == diff_temp[i].tmp_path) {
-			unlink(diff_temp[i].name);
-			diff_temp[i].name = NULL;
-		}
-}
-
-static void remove_tempfile_on_signal(int signo)
-{
-	remove_tempfile();
-	signal(SIGINT, SIG_DFL);
-	raise(signo);
+	return temp;
 }
 
 /* An external diff command takes:
@@ -2119,34 +2205,22 @@ static void run_external_diff(const char *pgm,
 			      int complete_rewrite)
 {
 	const char *spawn_arg[10];
-	struct diff_tempfile *temp = diff_temp;
 	int retval;
-	static int atexit_asked = 0;
-	const char *othername;
 	const char **arg = &spawn_arg[0];
 
-	othername = (other? other : name);
-	if (one && two) {
-		prepare_temp_file(name, &temp[0], one);
-		prepare_temp_file(othername, &temp[1], two);
-		if (! atexit_asked &&
-		    (temp[0].name == temp[0].tmp_path ||
-		     temp[1].name == temp[1].tmp_path)) {
-			atexit_asked = 1;
-			atexit(remove_tempfile);
-		}
-		signal(SIGINT, remove_tempfile_on_signal);
-	}
-
 	if (one && two) {
+		struct diff_tempfile *temp_one, *temp_two;
+		const char *othername = (other ? other : name);
+		temp_one = prepare_temp_file(name, one);
+		temp_two = prepare_temp_file(othername, two);
 		*arg++ = pgm;
 		*arg++ = name;
-		*arg++ = temp[0].name;
-		*arg++ = temp[0].hex;
-		*arg++ = temp[0].mode;
-		*arg++ = temp[1].name;
-		*arg++ = temp[1].hex;
-		*arg++ = temp[1].mode;
+		*arg++ = temp_one->name;
+		*arg++ = temp_one->hex;
+		*arg++ = temp_one->mode;
+		*arg++ = temp_two->name;
+		*arg++ = temp_two->hex;
+		*arg++ = temp_two->mode;
 		if (other) {
 			*arg++ = other;
 			*arg++ = xfrm_msg;
@@ -2165,29 +2239,6 @@ static void run_external_diff(const char *pgm,
 	}
 }
 
-static const char *external_diff_attr(const char *name)
-{
-	struct git_attr_check attr_diff_check;
-
-	if (!name)
-		return NULL;
-
-	setup_diff_attr_check(&attr_diff_check);
-	if (!git_checkattr(name, 1, &attr_diff_check)) {
-		const char *value = attr_diff_check.value;
-		if (!ATTR_TRUE(value) &&
-		    !ATTR_FALSE(value) &&
-		    !ATTR_UNSET(value)) {
-			struct ll_diff_driver *drv;
-
-			for (drv = user_diff; drv; drv = drv->next)
-				if (!strcmp(drv->name, value))
-					return drv->cmd;
-		}
-	}
-	return NULL;
-}
-
 static int similarity_index(struct diff_filepair *p)
 {
 	return p->score * 100 / MAX_SCORE;
@@ -2271,9 +2322,9 @@ static void run_diff_cmd(const char *pgm,
 	if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
 		pgm = NULL;
 	else {
-		const char *cmd = external_diff_attr(attr_path);
-		if (cmd)
-			pgm = cmd;
+		struct userdiff_driver *drv = userdiff_find_by_path(attr_path);
+		if (drv && drv->external)
+			pgm = drv->external;
 	}
 
 	if (pgm) {
@@ -2298,9 +2349,9 @@ static void diff_fill_sha1_info(struct diff_filespec *one)
 				return;
 			}
 			if (lstat(one->path, &st) < 0)
-				die("stat %s", one->path);
+				die_errno("stat '%s'", one->path);
 			if (index_path(one->sha1, one->path, &st, 0))
-				die("cannot hash %s\n", one->path);
+				die("cannot hash %s", one->path);
 		}
 	}
 	else
@@ -2427,19 +2478,18 @@ void diff_setup(struct diff_options *options)
 	options->break_opt = -1;
 	options->rename_limit = -1;
 	options->dirstat_percent = 3;
-	DIFF_OPT_CLR(options, DIRSTAT_CUMULATIVE);
 	options->context = 3;
 
 	options->change = diff_change;
 	options->add_remove = diff_addremove;
 	if (diff_use_color_default > 0)
 		DIFF_OPT_SET(options, COLOR_DIFF);
-	else
-		DIFF_OPT_CLR(options, COLOR_DIFF);
 	options->detect_rename = diff_detect_rename_default;
 
-	options->a_prefix = "a/";
-	options->b_prefix = "b/";
+	if (!diff_mnemonic_prefix) {
+		options->a_prefix = "a/";
+		options->b_prefix = "b/";
+	}
 }
 
 int diff_setup_done(struct diff_options *options)
@@ -2596,6 +2646,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	else if (!strcmp(arg, "--cumulative")) {
 		options->output_format |= DIFF_FORMAT_DIRSTAT;
 		DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE);
+	} else if (opt_arg(arg, 0, "dirstat-by-file",
+			   &options->dirstat_percent)) {
+		options->output_format |= DIFF_FORMAT_DIRSTAT;
+		DIFF_OPT_SET(options, DIRSTAT_BY_FILE);
 	}
 	else if (!strcmp(arg, "--check"))
 		options->output_format |= DIFF_FORMAT_CHECKDIFF;
@@ -2665,11 +2719,13 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 
 	/* xdiff options */
 	else if (!strcmp(arg, "-w") || !strcmp(arg, "--ignore-all-space"))
-		options->xdl_opts |= XDF_IGNORE_WHITESPACE;
+		DIFF_XDL_SET(options, IGNORE_WHITESPACE);
 	else if (!strcmp(arg, "-b") || !strcmp(arg, "--ignore-space-change"))
-		options->xdl_opts |= XDF_IGNORE_WHITESPACE_CHANGE;
+		DIFF_XDL_SET(options, IGNORE_WHITESPACE_CHANGE);
 	else if (!strcmp(arg, "--ignore-space-at-eol"))
-		options->xdl_opts |= XDF_IGNORE_WHITESPACE_AT_EOL;
+		DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL);
+	else if (!strcmp(arg, "--patience"))
+		DIFF_XDL_SET(options, PATIENCE_DIFF);
 
 	/* flags options */
 	else if (!strcmp(arg, "--binary")) {
@@ -2690,8 +2746,15 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_OPT_SET(options, COLOR_DIFF);
 	else if (!strcmp(arg, "--no-color"))
 		DIFF_OPT_CLR(options, COLOR_DIFF);
-	else if (!strcmp(arg, "--color-words"))
-		options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
+	else if (!strcmp(arg, "--color-words")) {
+		DIFF_OPT_SET(options, COLOR_DIFF);
+		DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
+	}
+	else if (!prefixcmp(arg, "--color-words=")) {
+		DIFF_OPT_SET(options, COLOR_DIFF);
+		DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
+		options->word_regex = arg + 14;
+	}
 	else if (!strcmp(arg, "--exit-code"))
 		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
 	else if (!strcmp(arg, "--quiet"))
@@ -2700,8 +2763,18 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_OPT_SET(options, ALLOW_EXTERNAL);
 	else if (!strcmp(arg, "--no-ext-diff"))
 		DIFF_OPT_CLR(options, ALLOW_EXTERNAL);
+	else if (!strcmp(arg, "--textconv"))
+		DIFF_OPT_SET(options, ALLOW_TEXTCONV);
+	else if (!strcmp(arg, "--no-textconv"))
+		DIFF_OPT_CLR(options, ALLOW_TEXTCONV);
 	else if (!strcmp(arg, "--ignore-submodules"))
 		DIFF_OPT_SET(options, IGNORE_SUBMODULES);
+	else if (!strcmp(arg, "--submodule"))
+		DIFF_OPT_SET(options, SUBMODULE_LOG);
+	else if (!prefixcmp(arg, "--submodule=")) {
+		if (!strcmp(arg + 12, "log"))
+			DIFF_OPT_SET(options, SUBMODULE_LOG);
+	}
 
 	/* misc options */
 	else if (!strcmp(arg, "-z"))
@@ -2733,6 +2806,9 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		options->b_prefix = arg + 13;
 	else if (!strcmp(arg, "--no-prefix"))
 		options->a_prefix = options->b_prefix = "";
+	else if (opt_arg(arg, '\0', "inter-hunk-context",
+			 &options->interhunkcontext))
+		;
 	else if (!prefixcmp(arg, "--output=")) {
 		options->file = fopen(arg + strlen("--output="), "w");
 		options->close_file = 1;
@@ -2750,7 +2826,7 @@ static int parse_num(const char **cp_p)
 	num = 0;
 	scale = 1;
 	dot = 0;
-	for(;;) {
+	for (;;) {
 		ch = *cp;
 		if ( !dot && ch == '.' ) {
 			scale = 1;
@@ -3152,8 +3228,7 @@ static void diff_summary(FILE *file, struct diff_filepair *p)
 }
 
 struct patch_id_t {
-	struct xdiff_emit_state xm;
-	SHA_CTX *ctx;
+	git_SHA_CTX *ctx;
 	int patchlen;
 };
 
@@ -3181,7 +3256,7 @@ static void patch_id_consume(void *priv, char *line, unsigned long len)
 
 	new_len = remove_space(line, len);
 
-	SHA1_Update(data->ctx, line, new_len);
+	git_SHA1_Update(data->ctx, line, new_len);
 	data->patchlen += new_len;
 }
 
@@ -3190,14 +3265,13 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
 	int i;
-	SHA_CTX ctx;
+	git_SHA_CTX ctx;
 	struct patch_id_t data;
 	char buffer[PATH_MAX * 4 + 20];
 
-	SHA1_Init(&ctx);
+	git_SHA1_Init(&ctx);
 	memset(&data, 0, sizeof(struct patch_id_t));
 	data.ctx = &ctx;
-	data.xm.consume = patch_id_consume;
 
 	for (i = 0; i < q->nr; i++) {
 		xpparam_t xpp;
@@ -3207,6 +3281,7 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 		struct diff_filepair *p = q->queue[i];
 		int len1, len2;
 
+		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		if (p->status == 0)
 			return error("internal diff status error");
@@ -3257,17 +3332,16 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 					len2, p->two->path,
 					len1, p->one->path,
 					len2, p->two->path);
-		SHA1_Update(&ctx, buffer, len1);
+		git_SHA1_Update(&ctx, buffer, len1);
 
 		xpp.flags = XDF_NEED_MINIMAL;
 		xecfg.ctxlen = 3;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
-		ecb.outf = xdiff_outf;
-		ecb.priv = &data;
-		xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
+		xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data,
+			      &xpp, &xecfg, &ecb);
 	}
 
-	SHA1_Final(sha1, &ctx);
+	git_SHA1_Final(sha1, &ctx);
 	return 0;
 }
 
@@ -3341,7 +3415,6 @@ void diff_flush(struct diff_options *options)
 		struct diffstat_t diffstat;
 
 		memset(&diffstat, 0, sizeof(struct diffstat_t));
-		diffstat.xm.consume = diffstat_consume;
 		for (i = 0; i < q->nr; i++) {
 			struct diff_filepair *p = q->queue[i];
 			if (check_pair_status(p))
@@ -3638,3 +3711,33 @@ void diff_unmerge(struct diff_options *options,
 	fill_filespec(one, sha1, mode);
 	diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
 }
+
+static char *run_textconv(const char *pgm, struct diff_filespec *spec,
+		size_t *outsize)
+{
+	struct diff_tempfile *temp;
+	const char *argv[3];
+	const char **arg = argv;
+	struct child_process child;
+	struct strbuf buf = STRBUF_INIT;
+
+	temp = prepare_temp_file(spec->path, spec);
+	*arg++ = pgm;
+	*arg++ = temp->name;
+	*arg = NULL;
+
+	memset(&child, 0, sizeof(child));
+	child.argv = argv;
+	child.out = -1;
+	if (start_command(&child) != 0 ||
+	    strbuf_read(&buf, child.out, 0) < 0 ||
+	    finish_command(&child) != 0) {
+		strbuf_release(&buf);
+		remove_tempfile();
+		error("error running textconv command '%s'", pgm);
+		return NULL;
+	}
+	remove_tempfile();
+
+	return strbuf_detach(&buf, outsize);
+}