/*
 * Copyright (C) 2005 Junio C Hamano
 */
#include "cache.h"
#include "quote.h"
#include "diff.h"
#include "diffcore.h"
#include "delta.h"
#include "xdiff-interface.h"
#include "color.h"
#include "attr.h"
#include "run-command.h"
#include "utf8.h"
#include "userdiff.h"
#include "sigchain.h"
#include "submodule.h"
#include "ll-merge.h"

#ifdef NO_FAST_WORKING_DIRECTORY
#define FAST_WORKING_DIRECTORY 0
#else
#define FAST_WORKING_DIRECTORY 1
#endif

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 int diff_no_prefix;
static struct diff_options default_diff_options;

static char diff_colors[][COLOR_MAXLEN] = {
	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 */
	GIT_COLOR_NORMAL,	/* FUNCINFO */
};

static int parse_diff_color_slot(const char *var, int ofs)
{
	if (!strcasecmp(var+ofs, "plain"))
		return DIFF_PLAIN;
	if (!strcasecmp(var+ofs, "meta"))
		return DIFF_METAINFO;
	if (!strcasecmp(var+ofs, "frag"))
		return DIFF_FRAGINFO;
	if (!strcasecmp(var+ofs, "old"))
		return DIFF_FILE_OLD;
	if (!strcasecmp(var+ofs, "new"))
		return DIFF_FILE_NEW;
	if (!strcasecmp(var+ofs, "commit"))
		return DIFF_COMMIT;
	if (!strcasecmp(var+ofs, "whitespace"))
		return DIFF_WHITESPACE;
	if (!strcasecmp(var+ofs, "func"))
		return DIFF_FUNCINFO;
	return -1;
}

static int git_config_rename(const char *var, const char *value)
{
	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;
}

/*
 * These are to give UI layer defaults.
 * The core-level commands such as git-diff-files should
 * never be affected by the setting of diff.renames
 * the user happens to have in the configuration file.
 */
int git_diff_ui_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
		diff_use_color_default = git_config_colorbool(var, value, -1);
		return 0;
	}
	if (!strcmp(var, "diff.renames")) {
		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.noprefix")) {
		diff_no_prefix = git_config_bool(var, value);
		return 0;
	}
	if (!strcmp(var, "diff.external"))
		return git_config_string(&external_diff_cmd_cfg, var, value);
	if (!strcmp(var, "diff.wordregex"))
		return git_config_string(&diff_word_regex_cfg, var, value);

	if (!strcmp(var, "diff.ignoresubmodules"))
		handle_ignore_submodules_arg(&default_diff_options, value);

	return git_diff_basic_config(var, value, cb);
}

int git_diff_basic_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "diff.renamelimit")) {
		diff_rename_limit_default = git_config_int(var, value);
		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 (slot < 0)
			return 0;
		if (!value)
			return config_error_nonbool(var);
		color_parse(value, var, diff_colors[slot]);
		return 0;
	}

	/* 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;
	}

	if (!prefixcmp(var, "submodule."))
		return parse_submodule_config_option(var, value);

	return git_color_default_config(var, value, cb);
}

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 = STRBUF_INIT;

	if (need_one + need_two) {
		strbuf_addch(&res, '"');
		quote_c_style(one, &res, NULL, 1);
		quote_c_style(two, &res, NULL, 1);
		strbuf_addch(&res, '"');
	} else {
		strbuf_addstr(&res, one);
		strbuf_addstr(&res, two);
	}
	return strbuf_detach(&res, NULL);
}

static const char *external_diff(void)
{
	static const char *external_diff_cmd = NULL;
	static int done_preparing = 0;

	if (done_preparing)
		return external_diff_cmd;
	external_diff_cmd = getenv("GIT_EXTERNAL_DIFF");
	if (!external_diff_cmd)
		external_diff_cmd = external_diff_cmd_cfg;
	done_preparing = 1;
	return external_diff_cmd;
}

static struct diff_tempfile {
	const char *name; /* filename external diff should read from */
	char hex[41];
	char mode[10];
	char tmp_path[PATH_MAX];
} diff_temp[2];

typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);

struct emit_callback {
	int color_diff;
	unsigned ws_rule;
	int blank_at_eof_in_preimage;
	int blank_at_eof_in_postimage;
	int lno_in_preimage;
	int lno_in_postimage;
	sane_truncate_fn truncate;
	const char **label_path;
	struct diff_words_data *diff_words;
	struct diff_options *opt;
	int *found_changesp;
	struct strbuf *header;
};

static int count_lines(const char *data, int size)
{
	int count, ch, completely_empty = 1, nl_just_seen = 0;
	count = 0;
	while (0 < size--) {
		ch = *data++;
		if (ch == '\n') {
			count++;
			nl_just_seen = 1;
			completely_empty = 0;
		}
		else {
			nl_just_seen = 0;
			completely_empty = 0;
		}
	}
	if (completely_empty)
		return 0;
	if (!nl_just_seen)
		count++; /* no trailing newline */
	return count;
}

static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
{
	if (!DIFF_FILE_VALID(one)) {
		mf->ptr = (char *)""; /* does not matter */
		mf->size = 0;
		return 0;
	}
	else if (diff_populate_filespec(one, 0))
		return -1;

	mf->ptr = one->data;
	mf->size = one->size;
	return 0;
}

static int count_trailing_blank(mmfile_t *mf, unsigned ws_rule)
{
	char *ptr = mf->ptr;
	long size = mf->size;
	int cnt = 0;

	if (!size)
		return cnt;
	ptr += size - 1; /* pointing at the very end */
	if (*ptr != '\n')
		; /* incomplete line */
	else
		ptr--; /* skip the last LF */
	while (mf->ptr < ptr) {
		char *prev_eol;
		for (prev_eol = ptr; mf->ptr <= prev_eol; prev_eol--)
			if (*prev_eol == '\n')
				break;
		if (!ws_blank_line(prev_eol + 1, ptr - prev_eol, ws_rule))
			break;
		cnt++;
		ptr = prev_eol - 1;
	}
	return cnt;
}

static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
			       struct emit_callback *ecbdata)
{
	int l1, l2, at;
	unsigned ws_rule = ecbdata->ws_rule;
	l1 = count_trailing_blank(mf1, ws_rule);
	l2 = count_trailing_blank(mf2, ws_rule);
	if (l2 <= l1) {
		ecbdata->blank_at_eof_in_preimage = 0;
		ecbdata->blank_at_eof_in_postimage = 0;
		return;
	}
	at = count_lines(mf1->ptr, mf1->size);
	ecbdata->blank_at_eof_in_preimage = (at - l1) + 1;

	at = count_lines(mf2->ptr, mf2->size);
	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
}

static void emit_line_0(struct diff_options *o, const char *set, const char *reset,
			int first, const char *line, int len)
{
	int has_trailing_newline, has_trailing_carriage_return;
	int nofirst;
	FILE *file = o->file;

	if (o->output_prefix) {
		struct strbuf *msg = NULL;
		msg = o->output_prefix(o, o->output_prefix_data);
		assert(msg);
		fwrite(msg->buf, msg->len, 1, file);
	}

	if (len == 0) {
		has_trailing_newline = (first == '\n');
		has_trailing_carriage_return = (!has_trailing_newline &&
						(first == '\r'));
		nofirst = has_trailing_newline || has_trailing_carriage_return;
	} else {
		has_trailing_newline = (len > 0 && line[len-1] == '\n');
		if (has_trailing_newline)
			len--;
		has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
		if (has_trailing_carriage_return)
			len--;
		nofirst = 0;
	}

	if (len || !nofirst) {
		fputs(set, file);
		if (!nofirst)
			fputc(first, file);
		fwrite(line, len, 1, file);
		fputs(reset, file);
	}
	if (has_trailing_carriage_return)
		fputc('\r', file);
	if (has_trailing_newline)
		fputc('\n', file);
}

static void emit_line(struct diff_options *o, const char *set, const char *reset,
		      const char *line, int len)
{
	emit_line_0(o, set, reset, line[0], line+1, len-1);
}

static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
{
	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
	      ecbdata->blank_at_eof_in_preimage &&
	      ecbdata->blank_at_eof_in_postimage &&
	      ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage &&
	      ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage))
		return 0;
	return ws_blank_line(line, len, ecbdata->ws_rule);
}

static void emit_add_line(const char *reset,
			  struct emit_callback *ecbdata,
			  const char *line, int len)
{
	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_0(ecbdata->opt, set, reset, '+', line, len);
	else if (new_blank_line_at_eof(ecbdata, line, len))
		/* Blank line at EOF - paint '+' as well */
		emit_line_0(ecbdata->opt, ws, reset, '+', line, len);
	else {
		/* Emit just the prefix, then the rest. */
		emit_line_0(ecbdata->opt, set, reset, '+', "", 0);
		ws_check_emit(line, len, ecbdata->ws_rule,
			      ecbdata->opt->file, set, reset, ws);
	}
}

static void emit_hunk_header(struct emit_callback *ecbdata,
			     const char *line, int len)
{
	const char *plain = diff_get_color(ecbdata->color_diff, DIFF_PLAIN);
	const char *frag = diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO);
	const char *func = diff_get_color(ecbdata->color_diff, DIFF_FUNCINFO);
	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
	static const char atat[2] = { '@', '@' };
	const char *cp, *ep;
	struct strbuf msgbuf = STRBUF_INIT;
	int org_len = len;
	int i = 1;

	/*
	 * As a hunk header must begin with "@@ -<old>, +<new> @@",
	 * it always is at least 10 bytes long.
	 */
	if (len < 10 ||
	    memcmp(line, atat, 2) ||
	    !(ep = memmem(line + 2, len - 2, atat, 2))) {
		emit_line(ecbdata->opt, plain, reset, line, len);
		return;
	}
	ep += 2; /* skip over @@ */

	/* The hunk header in fraginfo color */
	strbuf_add(&msgbuf, frag, strlen(frag));
	strbuf_add(&msgbuf, line, ep - line);
	strbuf_add(&msgbuf, reset, strlen(reset));

	/*
	 * trailing "\r\n"
	 */
	for ( ; i < 3; i++)
		if (line[len - i] == '\r' || line[len - i] == '\n')
			len--;

	/* blank before the func header */
	for (cp = ep; ep - line < len; ep++)
		if (*ep != ' ' && *ep != '\t')
			break;
	if (ep != cp) {
		strbuf_add(&msgbuf, plain, strlen(plain));
		strbuf_add(&msgbuf, cp, ep - cp);
		strbuf_add(&msgbuf, reset, strlen(reset));
	}

	if (ep < line + len) {
		strbuf_add(&msgbuf, func, strlen(func));
		strbuf_add(&msgbuf, ep, line + len - ep);
		strbuf_add(&msgbuf, reset, strlen(reset));
	}

	strbuf_add(&msgbuf, line + len, org_len - len);
	emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len);
	strbuf_release(&msgbuf);
}

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->opt, 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->opt, 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,
			      struct userdiff_driver *textconv_one,
			      struct userdiff_driver *textconv_two,
			      struct diff_options *o)
{
	int lc_a, lc_b;
	int color_diff = DIFF_OPT_TST(o, COLOR_DIFF);
	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 *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;
	char *data_one, *data_two;
	size_t size_one, size_two;
	struct emit_callback ecbdata;
	char *line_prefix = "";
	struct strbuf *msgbuf;

	if (o && o->output_prefix) {
		msgbuf = o->output_prefix(o, o->output_prefix_data);
		line_prefix = msgbuf->buf;
	}

	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 == '/');
	name_a_tab = strchr(name_a, ' ') ? "\t" : "";
	name_b_tab = strchr(name_b, ' ') ? "\t" : "";

	strbuf_reset(&a_name);
	strbuf_reset(&b_name);
	quote_two_c_style(&a_name, a_prefix, name_a, 0);
	quote_two_c_style(&b_name, b_prefix, name_b, 0);

	size_one = fill_textconv(textconv_one, one, &data_one);
	size_two = fill_textconv(textconv_two, two, &data_two);

	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.opt = o;
	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%s\n%s%s+++ %s%s%s\n%s%s@@ -",
		line_prefix, metainfo, a_name.buf, name_a_tab, reset,
		line_prefix, metainfo, b_name.buf, name_b_tab, reset,
		line_prefix, fraginfo);
	print_line_count(o->file, lc_a);
	fprintf(o->file, " +");
	print_line_count(o->file, lc_b);
	fprintf(o->file, " @@%s\n", reset);
	if (lc_a)
		emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
	if (lc_b)
		emit_rewrite_lines(&ecbdata, '+', data_two, size_two);
	if (textconv_one)
		free((char *)data_one);
	if (textconv_two)
		free((char *)data_two);
}

struct diff_words_buffer {
	mmfile_t text;
	long alloc;
	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)
{
	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_style_elem
{
	const char *prefix;
	const char *suffix;
	const char *color; /* NULL; filled in by the setup code if
			    * color is enabled */
};

struct diff_words_style
{
	enum diff_words_type type;
	struct diff_words_style_elem new, old, ctx;
	const char *newline;
};

struct diff_words_style diff_words_styles[] = {
	{ DIFF_WORDS_PORCELAIN, {"+", "\n"}, {"-", "\n"}, {" ", "\n"}, "~\n" },
	{ DIFF_WORDS_PLAIN, {"{+", "+}"}, {"[-", "-]"}, {"", ""}, "\n" },
	{ DIFF_WORDS_COLOR, {"", ""}, {"", ""}, {"", ""}, "\n" }
};

struct diff_words_data {
	struct diff_words_buffer minus, plus;
	const char *current_plus;
	int last_minus;
	struct diff_options *opt;
	regex_t *word_regex;
	enum diff_words_type type;
	struct diff_words_style *style;
};

static int fn_out_diff_words_write_helper(FILE *fp,
					  struct diff_words_style_elem *st_el,
					  const char *newline,
					  size_t count, const char *buf,
					  const char *line_prefix)
{
	int print = 0;

	while (count) {
		char *p = memchr(buf, '\n', count);
		if (print)
			fputs(line_prefix, fp);
		if (p != buf) {
			if (st_el->color && fputs(st_el->color, fp) < 0)
				return -1;
			if (fputs(st_el->prefix, fp) < 0 ||
			    fwrite(buf, p ? p - buf : count, 1, fp) != 1 ||
			    fputs(st_el->suffix, fp) < 0)
				return -1;
			if (st_el->color && *st_el->color
			    && fputs(GIT_COLOR_RESET, fp) < 0)
				return -1;
		}
		if (!p)
			return 0;
		if (fputs(newline, fp) < 0)
			return -1;
		count -= p + 1 - buf;
		buf = p + 1;
		print = 1;
	}
	return 0;
}

/*
 * '--color-words' algorithm can be described as:
 *
 *   1. collect a the minus/plus lines of a diff hunk, divided into
 *      minus-lines and plus-lines;
 *
 *   2. break both minus-lines and plus-lines into words and
 *      place them into two mmfile_t with one word for each line;
 *
 *   3. use xdiff to run diff on the two mmfile_t to get the words level diff;
 *
 * And for the common parts of the both file, we output the plus side text.
 * diff_words->current_plus is used to trace the current position of the plus file
 * which printed. diff_words->last_minus is used to trace the last minus word
 * printed.
 *
 * For '--graph' to work with '--color-words', we need to output the graph prefix
 * on each line of color words output. Generally, there are two conditions on
 * which we should output the prefix.
 *
 *   1. diff_words->last_minus == 0 &&
 *      diff_words->current_plus == diff_words->plus.text.ptr
 *
 *      that is: the plus text must start as a new line, and if there is no minus
 *      word printed, a graph prefix must be printed.
 *
 *   2. diff_words->current_plus > diff_words->plus.text.ptr &&
 *      *(diff_words->current_plus - 1) == '\n'
 *
 *      that is: a graph prefix must be printed following a '\n'
 */
static int color_words_output_graph_prefix(struct diff_words_data *diff_words)
{
	if ((diff_words->last_minus == 0 &&
		diff_words->current_plus == diff_words->plus.text.ptr) ||
		(diff_words->current_plus > diff_words->plus.text.ptr &&
		*(diff_words->current_plus - 1) == '\n')) {
		return 1;
	} else {
		return 0;
	}
}

static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
{
	struct diff_words_data *diff_words = priv;
	struct diff_words_style *style = diff_words->style;
	int minus_first, minus_len, plus_first, plus_len;
	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
	struct diff_options *opt = diff_words->opt;
	struct strbuf *msgbuf;
	char *line_prefix = "";

	if (line[0] != '@' || parse_hunk_header(line, len,
			&minus_first, &minus_len, &plus_first, &plus_len))
		return;

	assert(opt);
	if (opt->output_prefix) {
		msgbuf = opt->output_prefix(opt, opt->output_prefix_data);
		line_prefix = msgbuf->buf;
	}

	/* 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 (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 (color_words_output_graph_prefix(diff_words)) {
		fputs(line_prefix, diff_words->opt->file);
	}
	if (diff_words->current_plus != plus_begin) {
		fn_out_diff_words_write_helper(diff_words->opt->file,
				&style->ctx, style->newline,
				plus_begin - diff_words->current_plus,
				diff_words->current_plus, line_prefix);
		if (*(plus_begin - 1) == '\n')
			fputs(line_prefix, diff_words->opt->file);
	}
	if (minus_begin != minus_end) {
		fn_out_diff_words_write_helper(diff_words->opt->file,
				&style->old, style->newline,
				minus_end - minus_begin, minus_begin,
				line_prefix);
	}
	if (plus_begin != plus_end) {
		fn_out_diff_words_write_helper(diff_words->opt->file,
				&style->new, style->newline,
				plus_end - plus_begin, plus_begin,
				line_prefix);
	}

	diff_words->current_plus = plus_end;
	diff_words->last_minus = minus_first;
}

/* 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;
	}

	/* find the next word */
	while (*begin < buffer->size && isspace(buffer->ptr[*begin]))
		(*begin)++;
	if (*begin >= buffer->size)
		return -1;

	/* find the end of the word */
	*end = *begin + 1;
	while (*end < buffer->size && !isspace(buffer->ptr[*end]))
		(*end)++;

	return 0;
}

/*
 * 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)
{
	int i, j;
	long alloc = 0;

	out->size = 0;
	out->ptr = NULL;

	/* 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;
	}
}

/* this executes the word diff on the accumulated buffers */
static void diff_words_show(struct diff_words_data *diff_words)
{
	xpparam_t xpp;
	xdemitconf_t xecfg;
	mmfile_t minus, plus;
	struct diff_words_style *style = diff_words->style;

	struct diff_options *opt = diff_words->opt;
	struct strbuf *msgbuf;
	char *line_prefix = "";

	assert(opt);
	if (opt->output_prefix) {
		msgbuf = opt->output_prefix(opt, opt->output_prefix_data);
		line_prefix = msgbuf->buf;
	}

	/* special case: only removal */
	if (!diff_words->plus.text.size) {
		fputs(line_prefix, diff_words->opt->file);
		fn_out_diff_words_write_helper(diff_words->opt->file,
			&style->old, style->newline,
			diff_words->minus.text.size,
			diff_words->minus.text.ptr, line_prefix);
		diff_words->minus.text.size = 0;
		return;
	}

	diff_words->current_plus = diff_words->plus.text.ptr;
	diff_words->last_minus = 0;

	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 = 0;
	/* 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);
	free(minus.ptr);
	free(plus.ptr);
	if (diff_words->current_plus != diff_words->plus.text.ptr +
			diff_words->plus.text.size) {
		if (color_words_output_graph_prefix(diff_words))
			fputs(line_prefix, diff_words->opt->file);
		fn_out_diff_words_write_helper(diff_words->opt->file,
			&style->ctx, style->newline,
			diff_words->plus.text.ptr + diff_words->plus.text.size
			- diff_words->current_plus, diff_words->current_plus,
			line_prefix);
	}
	diff_words->minus.text.size = diff_words->plus.text.size = 0;
}

/* In "color-words" mode, show word-diff of words accumulated in the buffer */
static void diff_words_flush(struct emit_callback *ecbdata)
{
	if (ecbdata->diff_words->minus.text.size ||
	    ecbdata->diff_words->plus.text.size)
		diff_words_show(ecbdata->diff_words);
}

static void free_diff_words_data(struct emit_callback *ecbdata)
{
	if (ecbdata->diff_words) {
		diff_words_flush(ecbdata);
		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);
		if (ecbdata->diff_words->word_regex) {
			regfree(ecbdata->diff_words->word_regex);
			free(ecbdata->diff_words->word_regex);
		}
		free(ecbdata->diff_words);
		ecbdata->diff_words = NULL;
	}
}

const char *diff_get_color(int diff_use_color, enum color_diff ix)
{
	if (diff_use_color)
		return diff_colors[ix];
	return "";
}

static unsigned long sane_truncate_line(struct emit_callback *ecb, char *line, unsigned long len)
{
	const char *cp;
	unsigned long allot;
	size_t l = len;

	if (ecb->truncate)
		return ecb->truncate(line, len);
	cp = line;
	allot = l;
	while (0 < l) {
		(void) utf8_width(&cp, &l);
		if (!cp)
			break; /* truncated in the middle? */
	}
	return allot - l;
}

static void find_lno(const char *line, struct emit_callback *ecbdata)
{
	const char *p;
	ecbdata->lno_in_preimage = 0;
	ecbdata->lno_in_postimage = 0;
	p = strchr(line, '-');
	if (!p)
		return; /* cannot happen */
	ecbdata->lno_in_preimage = strtol(p + 1, NULL, 10);
	p = strchr(p, '+');
	if (!p)
		return; /* cannot happen */
	ecbdata->lno_in_postimage = strtol(p + 1, NULL, 10);
}

static void fn_out_consume(void *priv, char *line, unsigned long len)
{
	struct emit_callback *ecbdata = priv;
	const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO);
	const char *plain = diff_get_color(ecbdata->color_diff, DIFF_PLAIN);
	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
	struct diff_options *o = ecbdata->opt;
	char *line_prefix = "";
	struct strbuf *msgbuf;

	if (o && o->output_prefix) {
		msgbuf = o->output_prefix(o, o->output_prefix_data);
		line_prefix = msgbuf->buf;
	}

	if (ecbdata->header) {
		fprintf(ecbdata->opt->file, "%s", ecbdata->header->buf);
		strbuf_reset(ecbdata->header);
		ecbdata->header = NULL;
	}
	*(ecbdata->found_changesp) = 1;

	if (ecbdata->label_path[0]) {
		const char *name_a_tab, *name_b_tab;

		name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : "";
		name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : "";

		fprintf(ecbdata->opt->file, "%s%s--- %s%s%s\n",
			line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab);
		fprintf(ecbdata->opt->file, "%s%s+++ %s%s%s\n",
			line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab);
		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] == '@') {
		if (ecbdata->diff_words)
			diff_words_flush(ecbdata);
		len = sane_truncate_line(ecbdata, line, len);
		find_lno(line, ecbdata);
		emit_hunk_header(ecbdata, line, len);
		if (line[len-1] != '\n')
			putc('\n', ecbdata->opt->file);
		return;
	}

	if (len < 1) {
		emit_line(ecbdata->opt, reset, reset, line, len);
		if (ecbdata->diff_words
		    && ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN)
			fputs("~\n", ecbdata->opt->file);
		return;
	}

	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;
		}
		diff_words_flush(ecbdata);
		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
			emit_line(ecbdata->opt, plain, reset, line, len);
			fputs("~\n", ecbdata->opt->file);
		} else {
			/* don't print the prefix character */
			emit_line(ecbdata->opt, plain, reset, line+1, len-1);
		}
		return;
	}

	if (line[0] != '+') {
		const char *color =
			diff_get_color(ecbdata->color_diff,
				       line[0] == '-' ? DIFF_FILE_OLD : DIFF_PLAIN);
		ecbdata->lno_in_preimage++;
		if (line[0] == ' ')
			ecbdata->lno_in_postimage++;
		emit_line(ecbdata->opt, color, reset, line, len);
	} else {
		ecbdata->lno_in_postimage++;
		emit_add_line(reset, ecbdata, line + 1, len - 1);
	}
}

static char *pprint_rename(const char *a, const char *b)
{
	const char *old = a;
	const char *new = b;
	struct strbuf name = STRBUF_INIT;
	int pfx_length, sfx_length;
	int len_a = strlen(a);
	int len_b = strlen(b);
	int a_midlen, b_midlen;
	int qlen_a = quote_c_style(a, NULL, NULL, 0);
	int qlen_b = quote_c_style(b, NULL, NULL, 0);

	if (qlen_a || qlen_b) {
		quote_c_style(a, &name, NULL, 0);
		strbuf_addstr(&name, " => ");
		quote_c_style(b, &name, NULL, 0);
		return strbuf_detach(&name, NULL);
	}

	/* Find common prefix */
	pfx_length = 0;
	while (*old && *new && *old == *new) {
		if (*old == '/')
			pfx_length = old - a + 1;
		old++;
		new++;
	}

	/* Find common suffix */
	old = a + len_a;
	new = b + len_b;
	sfx_length = 0;
	while (a <= old && b <= new && *old == *new) {
		if (*old == '/')
			sfx_length = len_a - (old - a);
		old--;
		new--;
	}

	/*
	 * pfx{mid-a => mid-b}sfx
	 * {pfx-a => pfx-b}sfx
	 * pfx{sfx-a => sfx-b}
	 * name-a => name-b
	 */
	a_midlen = len_a - pfx_length - sfx_length;
	b_midlen = len_b - pfx_length - sfx_length;
	if (a_midlen < 0)
		a_midlen = 0;
	if (b_midlen < 0)
		b_midlen = 0;

	strbuf_grow(&name, pfx_length + a_midlen + b_midlen + sfx_length + 7);
	if (pfx_length + sfx_length) {
		strbuf_add(&name, a, pfx_length);
		strbuf_addch(&name, '{');
	}
	strbuf_add(&name, a + pfx_length, a_midlen);
	strbuf_addstr(&name, " => ");
	strbuf_add(&name, b + pfx_length, b_midlen);
	if (pfx_length + sfx_length) {
		strbuf_addch(&name, '}');
		strbuf_add(&name, a + len_a - sfx_length, sfx_length);
	}
	return strbuf_detach(&name, NULL);
}

struct diffstat_t {
	int nr;
	int alloc;
	struct diffstat_file {
		char *from_name;
		char *name;
		char *print_name;
		unsigned is_unmerged:1;
		unsigned is_binary:1;
		unsigned is_renamed:1;
		uintmax_t added, deleted;
	} **files;
};

static struct diffstat_file *diffstat_add(struct diffstat_t *diffstat,
					  const char *name_a,
					  const char *name_b)
{
	struct diffstat_file *x;
	x = xcalloc(sizeof (*x), 1);
	if (diffstat->nr == diffstat->alloc) {
		diffstat->alloc = alloc_nr(diffstat->alloc);
		diffstat->files = xrealloc(diffstat->files,
				diffstat->alloc * sizeof(x));
	}
	diffstat->files[diffstat->nr++] = x;
	if (name_b) {
		x->from_name = xstrdup(name_a);
		x->name = xstrdup(name_b);
		x->is_renamed = 1;
	}
	else {
		x->from_name = NULL;
		x->name = xstrdup(name_a);
	}
	return x;
}

static void diffstat_consume(void *priv, char *line, unsigned long len)
{
	struct diffstat_t *diffstat = priv;
	struct diffstat_file *x = diffstat->files[diffstat->nr - 1];

	if (line[0] == '+')
		x->added++;
	else if (line[0] == '-')
		x->deleted++;
}

const char mime_boundary_leader[] = "------------";

static int scale_linear(int it, int width, int max_change)
{
	/*
	 * make sure that at least one '-' is printed if there were deletions,
	 * and likewise for '+'.
	 */
	if (max_change < 2)
		return it;
	return ((it - 1) * (width - 1) + max_change - 1) / (max_change - 1);
}

static void show_name(FILE *file,
		      const char *prefix, const char *name, int len)
{
	fprintf(file, " %s%-*s |", prefix, len, name);
}

static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset)
{
	if (cnt <= 0)
		return;
	fprintf(file, "%s", set);
	while (cnt--)
		putc(ch, file);
	fprintf(file, "%s", reset);
}

static void fill_print_name(struct diffstat_file *file)
{
	char *pname;

	if (file->print_name)
		return;

	if (!file->is_renamed) {
		struct strbuf buf = STRBUF_INIT;
		if (quote_c_style(file->name, &buf, NULL, 0)) {
			pname = strbuf_detach(&buf, NULL);
		} else {
			pname = file->name;
			strbuf_release(&buf);
		}
	} else {
		pname = pprint_rename(file->from_name, file->name);
	}
	file->print_name = pname;
}

static void show_stats(struct diffstat_t *data, struct diff_options *options)
{
	int i, len, add, del, adds = 0, dels = 0;
	uintmax_t max_change = 0, max_len = 0;
	int total_files = data->nr;
	int width, name_width;
	const char *reset, *set, *add_c, *del_c;
	const char *line_prefix = "";
	struct strbuf *msg = NULL;

	if (data->nr == 0)
		return;

	if (options->output_prefix) {
		msg = options->output_prefix(options, options->output_prefix_data);
		line_prefix = msg->buf;
	}

	width = options->stat_width ? options->stat_width : 80;
	name_width = options->stat_name_width ? options->stat_name_width : 50;

	/* Sanity: give at least 5 columns to the graph,
	 * but leave at least 10 columns for the name.
	 */
	if (width < 25)
		width = 25;
	if (name_width < 10)
		name_width = 10;
	else if (width < name_width + 15)
		name_width = width - 15;

	/* Find the longest filename and max number of changes */
	reset = diff_get_color_opt(options, DIFF_RESET);
	set   = diff_get_color_opt(options, DIFF_PLAIN);
	add_c = diff_get_color_opt(options, DIFF_FILE_NEW);
	del_c = diff_get_color_opt(options, DIFF_FILE_OLD);

	for (i = 0; i < data->nr; i++) {
		struct diffstat_file *file = data->files[i];
		uintmax_t change = file->added + file->deleted;
		fill_print_name(file);
		len = strlen(file->print_name);
		if (max_len < len)
			max_len = len;

		if (file->is_binary || file->is_unmerged)
			continue;
		if (max_change < change)
			max_change = change;
	}

	/* Compute the width of the graph part;
	 * 10 is for one blank at the beginning of the line plus
	 * " | count " between the name and the graph.
	 *
	 * From here on, name_width is the width of the name area,
	 * and width is the width of the graph area.
	 */
	name_width = (name_width < max_len) ? name_width : max_len;
	if (width < (name_width + 10) + max_change)
		width = width - (name_width + 10);
	else
		width = max_change;

	for (i = 0; i < data->nr; i++) {
		const char *prefix = "";
		char *name = data->files[i]->print_name;
		uintmax_t added = data->files[i]->added;
		uintmax_t deleted = data->files[i]->deleted;
		int name_len;

		/*
		 * "scale" the filename
		 */
		len = name_width;
		name_len = strlen(name);
		if (name_width < name_len) {
			char *slash;
			prefix = "...";
			len -= 3;
			name += name_len - len;
			slash = strchr(name, '/');
			if (slash)
				name = slash;
		}

		if (data->files[i]->is_binary) {
			fprintf(options->file, "%s", line_prefix);
			show_name(options->file, prefix, name, len);
			fprintf(options->file, "  Bin ");
			fprintf(options->file, "%s%"PRIuMAX"%s",
				del_c, deleted, reset);
			fprintf(options->file, " -> ");
			fprintf(options->file, "%s%"PRIuMAX"%s",
				add_c, added, reset);
			fprintf(options->file, " bytes");
			fprintf(options->file, "\n");
			continue;
		}
		else if (data->files[i]->is_unmerged) {
			fprintf(options->file, "%s", line_prefix);
			show_name(options->file, prefix, name, len);
			fprintf(options->file, "  Unmerged\n");
			continue;
		}
		else if (!data->files[i]->is_renamed &&
			 (added + deleted == 0)) {
			total_files--;
			continue;
		}

		/*
		 * scale the add/delete
		 */
		add = added;
		del = deleted;
		adds += add;
		dels += del;

		if (width <= max_change) {
			add = scale_linear(add, width, max_change);
			del = scale_linear(del, width, max_change);
		}
		fprintf(options->file, "%s", line_prefix);
		show_name(options->file, prefix, name, len);
		fprintf(options->file, "%5"PRIuMAX"%s", added + deleted,
				added + deleted ? " " : "");
		show_graph(options->file, '+', add, add_c, reset);
		show_graph(options->file, '-', del, del_c, reset);
		fprintf(options->file, "\n");
	}
	fprintf(options->file, "%s", line_prefix);
	fprintf(options->file,
	       " %d files changed, %d insertions(+), %d deletions(-)\n",
	       total_files, adds, dels);
}

static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
{
	int i, adds = 0, dels = 0, total_files = data->nr;

	if (data->nr == 0)
		return;

	for (i = 0; i < data->nr; i++) {
		if (!data->files[i]->is_binary &&
		    !data->files[i]->is_unmerged) {
			int added = data->files[i]->added;
			int deleted= data->files[i]->deleted;
			if (!data->files[i]->is_renamed &&
			    (added + deleted == 0)) {
				total_files--;
			} else {
				adds += added;
				dels += deleted;
			}
		}
	}
	if (options->output_prefix) {
		struct strbuf *msg = NULL;
		msg = options->output_prefix(options,
				options->output_prefix_data);
		fprintf(options->file, "%s", msg->buf);
	}
	fprintf(options->file, " %d files changed, %d insertions(+), %d deletions(-)\n",
	       total_files, adds, dels);
}

static void show_numstat(struct diffstat_t *data, struct diff_options *options)
{
	int i;

	if (data->nr == 0)
		return;

	for (i = 0; i < data->nr; i++) {
		struct diffstat_file *file = data->files[i];

		if (options->output_prefix) {
			struct strbuf *msg = NULL;
			msg = options->output_prefix(options,
					options->output_prefix_data);
			fprintf(options->file, "%s", msg->buf);
		}

		if (file->is_binary)
			fprintf(options->file, "-\t-\t");
		else
			fprintf(options->file,
				"%"PRIuMAX"\t%"PRIuMAX"\t",
				file->added, file->deleted);
		if (options->line_termination) {
			fill_print_name(file);
			if (!file->is_renamed)
				write_name_quoted(file->name, options->file,
						  options->line_termination);
			else {
				fputs(file->print_name, options->file);
				putc(options->line_termination, options->file);
			}
		} else {
			if (file->is_renamed) {
				putc('\0', options->file);
				write_name_quoted(file->from_name, options->file, '\0');
			}
			write_name_quoted(file->name, options->file, '\0');
		}
	}
}

struct dirstat_file {
	const char *name;
	unsigned long changed;
};

struct dirstat_dir {
	struct dirstat_file *files;
	int alloc, nr, percent, cumulative;
};

static long gather_dirstat(struct diff_options *opt, struct dirstat_dir *dir,
		unsigned long changed, const char *base, int baselen)
{
	unsigned long this_dir = 0;
	unsigned int sources = 0;
	const char *line_prefix = "";
	struct strbuf *msg = NULL;

	if (opt->output_prefix) {
		msg = opt->output_prefix(opt, opt->output_prefix_data);
		line_prefix = msg->buf;
	}

	while (dir->nr) {
		struct dirstat_file *f = dir->files;
		int namelen = strlen(f->name);
		unsigned long this;
		char *slash;

		if (namelen < baselen)
			break;
		if (memcmp(f->name, base, baselen))
			break;
		slash = strchr(f->name + baselen, '/');
		if (slash) {
			int newbaselen = slash + 1 - f->name;
			this = gather_dirstat(opt, dir, changed, f->name, newbaselen);
			sources++;
		} else {
			this = f->changed;
			dir->files++;
			dir->nr--;
			sources += 2;
		}
		this_dir += this;
	}

	/*
	 * We don't report dirstat's for
	 *  - the top level
	 *  - or cases where everything came from a single directory
	 *    under this directory (sources == 1).
	 */
	if (baselen && sources != 1) {
		int permille = this_dir * 1000 / changed;
		if (permille) {
			int percent = permille / 10;
			if (percent >= dir->percent) {
				fprintf(opt->file, "%s%4d.%01d%% %.*s\n", line_prefix,
					percent, permille % 10, baselen, base);
				if (!dir->cumulative)
					return 0;
			}
		}
	}
	return this_dir;
}

static int dirstat_compare(const void *_a, const void *_b)
{
	const struct dirstat_file *a = _a;
	const struct dirstat_file *b = _b;
	return strcmp(a->name, b->name);
}

static void show_dirstat(struct diff_options *options)
{
	int i;
	unsigned long changed;
	struct dirstat_dir dir;
	struct diff_queue_struct *q = &diff_queued_diff;

	dir.files = NULL;
	dir.alloc = 0;
	dir.nr = 0;
	dir.percent = options->dirstat_percent;
	dir.cumulative = DIFF_OPT_TST(options, DIRSTAT_CUMULATIVE);

	changed = 0;
	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		const char *name;
		unsigned long copied, added, damage;

		name = p->one->path ? p->one->path : p->two->path;

		if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
			diff_populate_filespec(p->one, 0);
			diff_populate_filespec(p->two, 0);
			diffcore_count_changes(p->one, p->two, NULL, NULL, 0,
					       &copied, &added);
			diff_free_filespec_data(p->one);
			diff_free_filespec_data(p->two);
		} else if (DIFF_FILE_VALID(p->one)) {
			diff_populate_filespec(p->one, 1);
			copied = added = 0;
			diff_free_filespec_data(p->one);
		} else if (DIFF_FILE_VALID(p->two)) {
			diff_populate_filespec(p->two, 1);
			copied = 0;
			added = p->two->size;
			diff_free_filespec_data(p->two);
		} else
			continue;

		/*
		 * Original minus copied is the removed material,
		 * added is the new material.  They are both damages
		 * 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;
		dir.files[dir.nr].changed = damage;
		changed += damage;
		dir.nr++;
	}

	/* This can happen even with many files, if everything was renames */
	if (!changed)
		return;

	/* Show all directories with more than x% of the changes */
	qsort(dir.files, dir.nr, sizeof(dir.files[0]), dirstat_compare);
	gather_dirstat(options, &dir, changed, "", 0);
}

static void free_diffstat_info(struct diffstat_t *diffstat)
{
	int i;
	for (i = 0; i < diffstat->nr; i++) {
		struct diffstat_file *f = diffstat->files[i];
		if (f->name != f->print_name)
			free(f->print_name);
		free(f->name);
		free(f->from_name);
		free(f);
	}
	free(diffstat->files);
}

struct checkdiff_t {
	const char *filename;
	int lineno;
	int conflict_marker_size;
	struct diff_options *o;
	unsigned ws_rule;
	unsigned status;
};

static int is_conflict_marker(const char *line, int marker_size, unsigned long len)
{
	char firstchar;
	int cnt;

	if (len < marker_size + 1)
		return 0;
	firstchar = line[0];
	switch (firstchar) {
	case '=': case '>': case '<': case '|':
		break;
	default:
		return 0;
	}
	for (cnt = 1; cnt < marker_size; cnt++)
		if (line[cnt] != firstchar)
			return 0;
	/* line[1] thru line[marker_size-1] are same as firstchar */
	if (len < marker_size + 1 || !isspace(line[marker_size]))
		return 0;
	return 1;
}

static void checkdiff_consume(void *priv, char *line, unsigned long len)
{
	struct checkdiff_t *data = priv;
	int color_diff = DIFF_OPT_TST(data->o, COLOR_DIFF);
	int marker_size = data->conflict_marker_size;
	const char *ws = diff_get_color(color_diff, DIFF_WHITESPACE);
	const char *reset = diff_get_color(color_diff, DIFF_RESET);
	const char *set = diff_get_color(color_diff, DIFF_FILE_NEW);
	char *err;
	char *line_prefix = "";
	struct strbuf *msgbuf;

	assert(data->o);
	if (data->o->output_prefix) {
		msgbuf = data->o->output_prefix(data->o,
			data->o->output_prefix_data);
		line_prefix = msgbuf->buf;
	}

	if (line[0] == '+') {
		unsigned bad;
		data->lineno++;
		if (is_conflict_marker(line + 1, marker_size, len - 1)) {
			data->status |= 1;
			fprintf(data->o->file,
				"%s%s:%d: leftover conflict marker\n",
				line_prefix, data->filename, data->lineno);
		}
		bad = ws_check(line + 1, len - 1, data->ws_rule);
		if (!bad)
			return;
		data->status |= bad;
		err = whitespace_error_string(bad);
		fprintf(data->o->file, "%s%s:%d: %s.\n",
			line_prefix, data->filename, data->lineno, err);
		free(err);
		emit_line(data->o, set, reset, line, 1);
		ws_check_emit(line + 1, len - 1, data->ws_rule,
			      data->o->file, set, reset, ws);
	} else if (line[0] == ' ') {
		data->lineno++;
	} else if (line[0] == '@') {
		char *plus = strchr(line, '+');
		if (plus)
			data->lineno = strtol(plus, NULL, 10) - 1;
		else
			die("invalid diff");
	}
}

static unsigned char *deflate_it(char *data,
				 unsigned long size,
				 unsigned long *result_size)
{
	int bound;
	unsigned char *deflated;
	z_stream stream;

	memset(&stream, 0, sizeof(stream));
	deflateInit(&stream, zlib_compression_level);
	bound = deflateBound(&stream, size);
	deflated = xmalloc(bound);
	stream.next_out = deflated;
	stream.avail_out = bound;

	stream.next_in = (unsigned char *)data;
	stream.avail_in = size;
	while (deflate(&stream, Z_FINISH) == Z_OK)
		; /* nothing */
	deflateEnd(&stream);
	*result_size = stream.total_out;
	return deflated;
}

static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, char *prefix)
{
	void *cp;
	void *delta;
	void *deflated;
	void *data;
	unsigned long orig_size;
	unsigned long delta_size;
	unsigned long deflate_size;
	unsigned long data_size;

	/* We could do deflated delta, or we could do just deflated two,
	 * whichever is smaller.
	 */
	delta = NULL;
	deflated = deflate_it(two->ptr, two->size, &deflate_size);
	if (one->size && two->size) {
		delta = diff_delta(one->ptr, one->size,
				   two->ptr, two->size,
				   &delta_size, deflate_size);
		if (delta) {
			void *to_free = delta;
			orig_size = delta_size;
			delta = deflate_it(delta, delta_size, &delta_size);
			free(to_free);
		}
	}

	if (delta && delta_size < deflate_size) {
		fprintf(file, "%sdelta %lu\n", prefix, orig_size);
		free(deflated);
		data = delta;
		data_size = delta_size;
	}
	else {
		fprintf(file, "%sliteral %lu\n", prefix, two->size);
		free(delta);
		data = deflated;
		data_size = deflate_size;
	}

	/* emit data encoded in base85 */
	cp = data;
	while (data_size) {
		int bytes = (52 < data_size) ? 52 : data_size;
		char line[70];
		data_size -= bytes;
		if (bytes <= 26)
			line[0] = bytes + 'A' - 1;
		else
			line[0] = bytes - 26 + 'a' - 1;
		encode_85(line + 1, cp, bytes);
		cp = (char *) cp + bytes;
		fprintf(file, "%s", prefix);
		fputs(line, file);
		fputc('\n', file);
	}
	fprintf(file, "%s\n", prefix);
	free(data);
}

static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two, char *prefix)
{
	fprintf(file, "%sGIT binary patch\n", prefix);
	emit_binary_diff_body(file, one, two, prefix);
	emit_binary_diff_body(file, two, one, prefix);
}

static void diff_filespec_load_driver(struct diff_filespec *one)
{
	/* Use already-loaded driver */
	if (one->driver)
		return;

	if (S_ISREG(one->mode))
		one->driver = userdiff_find_by_path(one->path);

	/* Fallback to default settings */
	if (!one->driver)
		one->driver = userdiff_find_by_name("default");
}

int diff_filespec_is_binary(struct diff_filespec *one)
{
	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;
}

static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespec *one)
{
	diff_filespec_load_driver(one);
	return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
}

static const char *userdiff_word_regex(struct diff_filespec *one)
{
	diff_filespec_load_driver(one);
	return one->driver->word_regex;
}

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;
}

struct userdiff_driver *get_textconv(struct diff_filespec *one)
{
	if (!DIFF_FILE_VALID(one))
		return NULL;

	diff_filespec_load_driver(one);
	if (!one->driver->textconv)
		return NULL;

	if (one->driver->textconv_want_cache && !one->driver->textconv_cache) {
		struct notes_cache *c = xmalloc(sizeof(*c));
		struct strbuf name = STRBUF_INIT;

		strbuf_addf(&name, "textconv/%s", one->driver->name);
		notes_cache_init(c, name.buf, one->driver->textconv);
		one->driver->textconv_cache = c;
	}

	return one->driver;
}

static void builtin_diff(const char *name_a,
			 const char *name_b,
			 struct diff_filespec *one,
			 struct diff_filespec *two,
			 const char *xfrm_msg,
			 int must_show_header,
			 struct diff_options *o,
			 int complete_rewrite)
{
	mmfile_t mf1, mf2;
	const char *lbl[2];
	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;
	struct userdiff_driver *textconv_one = NULL;
	struct userdiff_driver *textconv_two = NULL;
	struct strbuf header = STRBUF_INIT;
	struct strbuf *msgbuf;
	char *line_prefix = "";

	if (o->output_prefix) {
		msgbuf = o->output_prefix(o, o->output_prefix_data);
		line_prefix = msgbuf->buf;
	}

	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, two->dirty_submodule,
				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(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";
	strbuf_addf(&header, "%s%sdiff --git %s %s%s\n", line_prefix, set, a_one, b_two, reset);
	if (lbl[0][0] == '/') {
		/* /dev/null */
		strbuf_addf(&header, "%s%snew file mode %06o%s\n", line_prefix, set, two->mode, reset);
		if (xfrm_msg)
			strbuf_addstr(&header, xfrm_msg);
		must_show_header = 1;
	}
	else if (lbl[1][0] == '/') {
		strbuf_addf(&header, "%s%sdeleted file mode %06o%s\n", line_prefix, set, one->mode, reset);
		if (xfrm_msg)
			strbuf_addstr(&header, xfrm_msg);
		must_show_header = 1;
	}
	else {
		if (one->mode != two->mode) {
			strbuf_addf(&header, "%s%sold mode %06o%s\n", line_prefix, set, one->mode, reset);
			strbuf_addf(&header, "%s%snew mode %06o%s\n", line_prefix, set, two->mode, reset);
			must_show_header = 1;
		}
		if (xfrm_msg)
			strbuf_addstr(&header, xfrm_msg);

		/*
		 * we do not run diff between different kind
		 * of objects.
		 */
		if ((one->mode ^ two->mode) & S_IFMT)
			goto free_ab_and_return;
		if (complete_rewrite &&
		    (textconv_one || !diff_filespec_is_binary(one)) &&
		    (textconv_two || !diff_filespec_is_binary(two))) {
			fprintf(o->file, "%s", header.buf);
			strbuf_reset(&header);
			emit_rewrite_diff(name_a, name_b, one, two,
						textconv_one, textconv_two, o);
			o->found_changes = 1;
			goto free_ab_and_return;
		}
	}

	if (!DIFF_OPT_TST(o, TEXT) &&
	    ( (!textconv_one && diff_filespec_is_binary(one)) ||
	      (!textconv_two && diff_filespec_is_binary(two)) )) {
		if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
			die("unable to read files to diff");
		/* Quite common confusing case */
		if (mf1.size == mf2.size &&
		    !memcmp(mf1.ptr, mf2.ptr, mf1.size)) {
			if (must_show_header)
				fprintf(o->file, "%s", header.buf);
			goto free_ab_and_return;
		}
		fprintf(o->file, "%s", header.buf);
		strbuf_reset(&header);
		if (DIFF_OPT_TST(o, BINARY))
			emit_binary_diff(o->file, &mf1, &mf2, line_prefix);
		else
			fprintf(o->file, "%sBinary files %s and %s differ\n",
				line_prefix, lbl[0], lbl[1]);
		o->found_changes = 1;
	}
	else {
		/* Crazy xdl interfaces.. */
		const char *diffopts = getenv("GIT_DIFF_OPTS");
		xpparam_t xpp;
		xdemitconf_t xecfg;
		struct emit_callback ecbdata;
		const struct userdiff_funcname *pe;

		if (!DIFF_XDL_TST(o, WHITESPACE_FLAGS) || must_show_header) {
			fprintf(o->file, "%s", header.buf);
			strbuf_reset(&header);
		}

		mf1.size = fill_textconv(textconv_one, one, &mf1.ptr);
		mf2.size = fill_textconv(textconv_two, two, &mf2.ptr);

		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;
		ecbdata.color_diff = DIFF_OPT_TST(o, COLOR_DIFF);
		ecbdata.found_changesp = &o->found_changes;
		ecbdata.ws_rule = whitespace_rule(name_b ? name_b : name_a);
		if (ecbdata.ws_rule & WS_BLANK_AT_EOF)
			check_blank_at_eof(&mf1, &mf2, &ecbdata);
		ecbdata.opt = o;
		ecbdata.header = header.len ? &header : NULL;
		xpp.flags = 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);
		if (!diffopts)
			;
		else if (!prefixcmp(diffopts, "--unified="))
			xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10);
		else if (!prefixcmp(diffopts, "-u"))
			xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10);
		if (o->word_diff) {
			int i;

			ecbdata.diff_words =
				xcalloc(1, sizeof(struct diff_words_data));
			ecbdata.diff_words->type = o->word_diff;
			ecbdata.diff_words->opt = o;
			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);
			}
			for (i = 0; i < ARRAY_SIZE(diff_words_styles); i++) {
				if (o->word_diff == diff_words_styles[i].type) {
					ecbdata.diff_words->style =
						&diff_words_styles[i];
					break;
				}
			}
			if (DIFF_OPT_TST(o, COLOR_DIFF)) {
				struct diff_words_style *st = ecbdata.diff_words->style;
				st->old.color = diff_get_color_opt(o, DIFF_FILE_OLD);
				st->new.color = diff_get_color_opt(o, DIFF_FILE_NEW);
				st->ctx.color = diff_get_color_opt(o, DIFF_PLAIN);
			}
		}
		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
			      &xpp, &xecfg);
		if (o->word_diff)
			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:
	strbuf_release(&header);
	diff_free_filespec_data(one);
	diff_free_filespec_data(two);
	free(a_one);
	free(b_two);
	return;
}

static void builtin_diffstat(const char *name_a, const char *name_b,
			     struct diff_filespec *one,
			     struct diff_filespec *two,
			     struct diffstat_t *diffstat,
			     struct diff_options *o,
			     int complete_rewrite)
{
	mmfile_t mf1, mf2;
	struct diffstat_file *data;

	data = diffstat_add(diffstat, name_a, name_b);

	if (!one || !two) {
		data->is_unmerged = 1;
		return;
	}
	if (complete_rewrite) {
		diff_populate_filespec(one, 0);
		diff_populate_filespec(two, 0);
		data->deleted = count_lines(one->data, one->size);
		data->added = count_lines(two->data, two->size);
		goto free_and_return;
	}
	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
		die("unable to read files to diff");

	if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
		data->is_binary = 1;
		data->added = mf2.size;
		data->deleted = mf1.size;
	} else {
		/* Crazy xdl interfaces.. */
		xpparam_t xpp;
		xdemitconf_t xecfg;

		memset(&xpp, 0, sizeof(xpp));
		memset(&xecfg, 0, sizeof(xecfg));
		xpp.flags = o->xdl_opts;
		xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat,
			      &xpp, &xecfg);
	}

 free_and_return:
	diff_free_filespec_data(one);
	diff_free_filespec_data(two);
}

static void builtin_checkdiff(const char *name_a, const char *name_b,
			      const char *attr_path,
			      struct diff_filespec *one,
			      struct diff_filespec *two,
			      struct diff_options *o)
{
	mmfile_t mf1, mf2;
	struct checkdiff_t data;

	if (!two)
		return;

	memset(&data, 0, sizeof(data));
	data.filename = name_b ? name_b : name_a;
	data.lineno = 0;
	data.o = o;
	data.ws_rule = whitespace_rule(attr_path);
	data.conflict_marker_size = ll_merge_marker_size(attr_path);

	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
		die("unable to read files to diff");

	/*
	 * All the other codepaths check both sides, but not checking
	 * the "old" side here is deliberate.  We are checking the newly
	 * introduced changes, and as long as the "new" side is text, we
	 * can and should check what it introduces.
	 */
	if (diff_filespec_is_binary(two))
		goto free_and_return;
	else {
		/* Crazy xdl interfaces.. */
		xpparam_t xpp;
		xdemitconf_t xecfg;

		memset(&xpp, 0, sizeof(xpp));
		memset(&xecfg, 0, sizeof(xecfg));
		xecfg.ctxlen = 1; /* at least one context line */
		xpp.flags = 0;
		xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data,
			      &xpp, &xecfg);

		if (data.ws_rule & WS_BLANK_AT_EOF) {
			struct emit_callback ecbdata;
			int blank_at_eof;

			ecbdata.ws_rule = data.ws_rule;
			check_blank_at_eof(&mf1, &mf2, &ecbdata);
			blank_at_eof = ecbdata.blank_at_eof_in_postimage;

			if (blank_at_eof) {
				static char *err;
				if (!err)
					err = whitespace_error_string(WS_BLANK_AT_EOF);
				fprintf(o->file, "%s:%d: %s.\n",
					data.filename, blank_at_eof, err);
				data.status = 1; /* report errors */
			}
		}
	}
 free_and_return:
	diff_free_filespec_data(one);
	diff_free_filespec_data(two);
	if (data.status)
		DIFF_OPT_SET(o, CHECK_FAILED);
}

struct diff_filespec *alloc_filespec(const char *path)
{
	int namelen = strlen(path);
	struct diff_filespec *spec = xmalloc(sizeof(*spec) + namelen + 1);

	memset(spec, 0, sizeof(*spec));
	spec->path = (char *)(spec + 1);
	memcpy(spec->path, path, namelen+1);
	spec->count = 1;
	spec->is_binary = -1;
	return spec;
}

void free_filespec(struct diff_filespec *spec)
{
	if (!--spec->count) {
		diff_free_filespec_data(spec);
		free(spec);
	}
}

void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
		   unsigned short mode)
{
	if (mode) {
		spec->mode = canon_mode(mode);
		hashcpy(spec->sha1, sha1);
		spec->sha1_valid = !is_null_sha1(sha1);
	}
}

/*
 * Given a name and sha1 pair, if the index tells us the file in
 * the work tree has that object contents, return true, so that
 * prepare_temp_file() does not have to inflate and extract.
 */
static int reuse_worktree_file(const char *name, const unsigned char *sha1, int want_file)
{
	struct cache_entry *ce;
	struct stat st;
	int pos, len;

	/*
	 * 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
	 * tree.  This is because most diff-tree comparisons deal with
	 * only a small number of files, while reading the cache is
	 * expensive for a large project, and its cost outweighs the
	 * savings we get by not inflating the object to a temporary
	 * file.  Practically, this code only helps when we are used
	 * by diff-cache --cached, which does read the cache before
	 * calling us.
	 */
	if (!active_cache)
		return 0;

	/* We want to avoid the working directory if our caller
	 * doesn't need the data in a normal file, this system
	 * is rather slow with its stat/open/mmap/close syscalls,
	 * and the object is contained in a pack file.  The pack
	 * is probably already open and will be faster to obtain
	 * the data through than the working directory.  Loose
	 * 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))
		return 0;

	len = strlen(name);
	pos = cache_name_pos(name, len);
	if (pos < 0)
		return 0;
	ce = active_cache[pos];

	/*
	 * This is not the sha1 we are looking for, or
	 * unreusable because it is not a regular file.
	 */
	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) || ce_skip_worktree(ce))
		return 0;

	/*
	 * If ce matches the file in the work tree, we can reuse it.
	 */
	if (ce_uptodate(ce) ||
	    (!lstat(name, &st) && !ce_match_stat(ce, &st, 0)))
		return 1;

	return 0;
}

static int populate_from_stdin(struct diff_filespec *s)
{
	struct strbuf buf = STRBUF_INIT;
	size_t size = 0;

	if (strbuf_read(&buf, 0, 0) < 0)
		return error("error while reading from stdin %s",
				     strerror(errno));

	s->should_munmap = 0;
	s->data = strbuf_detach(&buf, &size);
	s->size = size;
	s->should_free = 1;
	return 0;
}

static int diff_populate_gitlink(struct diff_filespec *s, int size_only)
{
	int len;
	char *data = xmalloc(100), *dirty = "";

	/* Are we looking at the work tree? */
	if (s->dirty_submodule)
		dirty = "-dirty";

	len = snprintf(data, 100,
		       "Subproject commit %s%s\n", sha1_to_hex(s->sha1), dirty);
	s->data = data;
	s->size = len;
	s->should_free = 1;
	if (size_only) {
		s->data = NULL;
		free(data);
	}
	return 0;
}

/*
 * While doing rename detection and pickaxe operation, we may need to
 * grab the data for the blob (or file) for our own in-core comparison.
 * diff_filespec has data and size fields for this purpose.
 */
int diff_populate_filespec(struct diff_filespec *s, int size_only)
{
	int err = 0;
	if (!DIFF_FILE_VALID(s))
		die("internal error: asking to populate invalid file.");
	if (S_ISDIR(s->mode))
		return -1;

	if (s->data)
		return 0;

	if (size_only && 0 < s->size)
		return 0;

	if (S_ISGITLINK(s->mode))
		return diff_populate_gitlink(s, size_only);

	if (!s->sha1_valid ||
	    reuse_worktree_file(s->path, s->sha1, 0)) {
		struct strbuf buf = STRBUF_INIT;
		struct stat st;
		int fd;

		if (!strcmp(s->path, "-"))
			return populate_from_stdin(s);

		if (lstat(s->path, &st) < 0) {
			if (errno == ENOENT) {
			err_empty:
				err = -1;
			empty:
				s->data = (char *)"";
				s->size = 0;
				return err;
			}
		}
		s->size = xsize_t(st.st_size);
		if (!s->size)
			goto empty;
		if (S_ISLNK(st.st_mode)) {
			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;
		s->data = xmmap(NULL, s->size, PROT_READ, MAP_PRIVATE, fd, 0);
		close(fd);
		s->should_munmap = 1;

		/*
		 * Convert from working tree format to canonical git format
		 */
		if (convert_to_git(s->path, s->data, s->size, &buf, safe_crlf)) {
			size_t size = 0;
			munmap(s->data, s->size);
			s->should_munmap = 0;
			s->data = strbuf_detach(&buf, &size);
			s->size = size;
			s->should_free = 1;
		}
	}
	else {
		enum object_type type;
		if (size_only) {
			type = sha1_object_info(s->sha1, &s->size);
			if (type < 0)
				die("unable to read %s", sha1_to_hex(s->sha1));
		} else {
			s->data = read_sha1_file(s->sha1, &type, &s->size);
			if (!s->data)
				die("unable to read %s", sha1_to_hex(s->sha1));
			s->should_free = 1;
		}
	}
	return 0;
}

void diff_free_filespec_blob(struct diff_filespec *s)
{
	if (s->should_free)
		free(s->data);
	else if (s->should_munmap)
		munmap(s->data, s->size);

	if (s->should_free || s->should_munmap) {
		s->should_free = s->should_munmap = 0;
		s->data = NULL;
	}
}

void diff_free_filespec_data(struct diff_filespec *s)
{
	diff_free_filespec_blob(s);
	free(s->cnt_data);
	s->cnt_data = NULL;
}

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, "