diff -B: colour whitespace errors

[git] / diff.c

/*
 * 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"

#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;
int diff_use_color_default = -1;
static const char *external_diff_cmd_cfg;
int diff_auto_refresh_index = 1;

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) */
};

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;
        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)
{
        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;
}

/*
 * 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")) {
                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;
                return 0;
        }
        if (!strcmp(var, "diff.autorefreshindex")) {
                diff_auto_refresh_index = 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);
        }

        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;
        }

        if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
                int slot = parse_diff_color_slot(var, 11);
                if (!value)
                        return config_error_nonbool(var);
                color_parse(value, var, diff_colors[slot]);
                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);
                        }
                }
        }

        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(&res, 0);
        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 {
        struct xdiff_emit_state xm;
        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;
        int *found_changesp;
        FILE *file;
};

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 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 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(FILE *file, const char *set, const char *reset,
                        int first, const char *line, int len)
{
        int has_trailing_newline, has_trailing_carriage_return;
        int nofirst;

        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;
        }

        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(FILE *file, const char *set, const char *reset,
                      const char *line, int len)
{
        emit_line_0(file, 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->file, 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->file, ws, reset, '+', line, len);
        else {
                /* Emit just the prefix, then the rest. */
                emit_line_0(ecbdata->file, set, reset, '+', "", 0);
                ws_check_emit(line, len, ecbdata->ws_rule,
                              ecbdata->file, set, reset, ws);
        }
}

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,
                              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;
        struct emit_callback ecbdata;

        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;
                fill_mmfile(&mf1, one);
                fill_mmfile(&mf2, two);
                check_blank_at_eof(&mf1, &mf2, &ecbdata);
        }
        ecbdata.lno_in_preimage = 1;
        ecbdata.lno_in_postimage = 1;

        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, o->a_prefix, name_a, 0);
        quote_two_c_style(&b_name, o->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);
        fprintf(o->file,
                "%s--- %s%s%s\n%s+++ %s%s%s\n%s@@ -",
                metainfo, a_name.buf, name_a_tab, reset,
                metainfo, b_name.buf, name_b_tab, reset, 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, '-', one->data, one->size);
        if (lc_b)
                emit_rewrite_lines(&ecbdata, '+', two->data, two->size);
}

struct diff_words_buffer {
        mmfile_t text;
        long alloc;
        long current; /* output pointer */
        int suppressed_newline;
};

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);
        }
        line++;
        len--;
        memcpy(buffer->text.ptr + buffer->text.size, line, len);
        buffer->text.size += len;
}

struct diff_words_data {
        struct xdiff_emit_state xm;
        struct diff_words_buffer minus, plus;
        FILE *file;
};

static void print_word(FILE *file, struct diff_words_buffer *buffer, int len, int color,
                int suppress_newline)
{
        const char *ptr;
        int eol = 0;

        if (len == 0)
                return;

        ptr  = buffer->text.ptr + buffer->current;
        buffer->current += len;

        if (ptr[len - 1] == '\n') {
                eol = 1;
                len--;
        }

        fputs(diff_get_color(1, color), file);
        fwrite(ptr, len, 1, file);
        fputs(diff_get_color(1, DIFF_RESET), file);

        if (eol) {
                if (suppress_newline)
                        buffer->suppressed_newline = 1;
                else
                        putc('\n', file);
        }
}

static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
{
        struct diff_words_data *diff_words = priv;

        if (diff_words->minus.suppressed_newline) {
                if (line[0] != '+')
                        putc('\n', diff_words->file);
                diff_words->minus.suppressed_newline = 0;
        }

        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;
        }
}

/* 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;
        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;

        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);

        free(minus.ptr);
        free(plus.ptr);
        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)
{
        if (ecbdata->diff_words) {
                /* flush buffers */
                if (ecbdata->diff_words->minus.text.size ||
                                ecbdata->diff_words->plus.text.size)
                        diff_words_show(ecbdata->diff_words);

                free (ecbdata->diff_words->minus.text.ptr);
                free (ecbdata->diff_words->plus.text.ptr);
                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);

        *(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->file, "%s--- %s%s%s\n",
                        meta, ecbdata->label_path[0], reset, name_a_tab);
                fprintf(ecbdata->file, "%s+++ %s%s%s\n",
                        meta, ecbdata->label_path[1], reset, name_b_tab);
                ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
        }

        if (line[0] == '@') {
                len = sane_truncate_line(ecbdata, line, len);
                find_lno(line, ecbdata);
                emit_line(ecbdata->file,
                          diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO),
                          reset, line, len);
                if (line[len-1] != '\n')
                        putc('\n', ecbdata->file);
                return;
        }

        if (len < 1) {
                emit_line(ecbdata->file, reset, reset, line, len);
                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;
                }
                if (ecbdata->diff_words->minus.text.size ||
                    ecbdata->diff_words->plus.text.size)
                        diff_words_show(ecbdata->diff_words);
                line++;
                len--;
                emit_line(ecbdata->file, plain, reset, line, len);
                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->file, 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;
        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);

        strbuf_init(&name, 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 {
        struct xdiff_emit_state xm;

        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;
                unsigned int 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,
                      const char *reset, const char *set)
{
        fprintf(file, " %s%s%-*s%s |", set, prefix, len, name, reset);
}

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(&buf, 0);
                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, total, adds = 0, dels = 0;
        int max_change = 0, max_len = 0;
        int total_files = data->nr;
        int width, name_width;
        const char *reset, *set, *add_c, *del_c;

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

        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];
                int 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;
                int added = data->files[i]->added;
                int 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) {
                        show_name(options->file, prefix, name, len, reset, set);
                        fprintf(options->file, "  Bin ");
                        fprintf(options->file, "%s%d%s", del_c, deleted, reset);
                        fprintf(options->file, " -> ");
                        fprintf(options->file, "%s%d%s", add_c, added, reset);
                        fprintf(options->file, " bytes");
                        fprintf(options->file, "\n");
                        continue;
                }
                else if (data->files[i]->is_unmerged) {
                        show_name(options->file, prefix, name, len, reset, set);
                        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;
                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);
                fprintf(options->file, "%5d%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 %d files changed, %d insertions(+), %d deletions(-)%s\n",
               set, total_files, adds, dels, reset);
}

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;
                        }
                }
        }
        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 (file->is_binary)
                        fprintf(options->file, "-\t-\t");
                else
                        fprintf(options->file,
                                "%d\t%d\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(FILE *file, struct dirstat_dir *dir, unsigned long changed, const char *base, int baselen)
{
        unsigned long this_dir = 0;
        unsigned int sources = 0;

        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(file, 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(file, "%4d.%01d%% %.*s\n", 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.
                 */
                damage = (p->one->size - copied) + added;

                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->file, &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 {
        struct xdiff_emit_state xm;
        const char *filename;
        int lineno;
        struct diff_options *o;
        unsigned ws_rule;
        unsigned status;
};

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

        if (len < 8)
                return 0;
        firstchar = line[0];
        switch (firstchar) {
        case '=': case '>': case '<':
                break;
        default:
                return 0;
        }
        for (cnt = 1; cnt < 7; cnt++)
                if (line[cnt] != firstchar)
                        return 0;
        /* line[0] thru line[6] are same as firstchar */
        if (firstchar == '=') {
                /* divider between ours and theirs? */
                if (len != 8 || line[7] != '\n')
                        return 0;
        } else if (len < 8 || !isspace(line[7])) {
                /* not divider before ours nor after theirs */
                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);
        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;

        if (line[0] == '+') {
                unsigned bad;
                data->lineno++;
                if (is_conflict_marker(line + 1, len - 1)) {
                        data->status |= 1;
                        fprintf(data->o->file,
                                "%s:%d: leftover conflict marker\n",
                                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:%d: %s.\n",
                        data->filename, data->lineno, err);
                free(err);
                emit_line(data->o->file, 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)
{
        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, "delta %lu\n", orig_size);
                free(deflated);
                data = delta;
                data_size = delta_size;
        }
        else {
                fprintf(file, "literal %lu\n", 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;
                fputs(line, file);
                fputc('\n', file);
        }
        fprintf(file, "\n");
        free(data);
}

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

static void setup_diff_attr_check(struct git_attr_check *check)
{
        static struct git_attr *attr_diff;

        if (!attr_diff) {
                attr_diff = git_attr("diff", 4);
        }
        check[0].attr = attr_diff;
}

static void diff_filespec_check_attr(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);
        }
}

int diff_filespec_is_binary(struct diff_filespec *one)
{
        diff_filespec_check_attr(one);
        return one->is_binary;
}

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)
{
        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;

        /*
         * 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];

        return NULL;
}

static void builtin_diff(const char *name_a,
                         const char *name_b,
                         struct diff_filespec *one,
                         struct diff_filespec *two,
                         const char *xfrm_msg,
                         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);

        /* 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 == '/'));
        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);
        if (lbl[0][0] == '/') {
                /* /dev/null */
                fprintf(o->file, "%snew file mode %06o%s\n", set, two->mode, reset);
                if (xfrm_msg && xfrm_msg[0])
                        fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
        }
        else if (lbl[1][0] == '/') {
                fprintf(o->file, "%sdeleted file mode %06o%s\n", set, one->mode, reset);
                if (xfrm_msg && xfrm_msg[0])
                        fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
        }
        else {
                if (one->mode != two->mode) {
                        fprintf(o->file, "%sold mode %06o%s\n", set, one->mode, reset);
                        fprintf(o->file, "%snew mode %06o%s\n", set, two->mode, reset);
                }
                if (xfrm_msg && xfrm_msg[0])
                        fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
                /*
                 * 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) {
                        emit_rewrite_diff(name_a, name_b, one, two, o);
                        o->found_changes = 1;
                        goto free_ab_and_return;
                }
        }

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

        if (!DIFF_OPT_TST(o, TEXT) &&
            (diff_filespec_is_binary(one) || diff_filespec_is_binary(two))) {
                /* Quite common confusing case */
                if (mf1.size == mf2.size &&
                    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
                        goto free_ab_and_return;
                if (DIFF_OPT_TST(o, BINARY))
                        emit_binary_diff(o->file, &mf1, &mf2);
                else
                        fprintf(o->file, "Binary files %s and %s differ\n",
                                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;
                xdemitcb_t ecb;
                struct emit_callback ecbdata;
                const struct funcname_pattern_entry *pe;

                pe = diff_funcname_pattern(one);
                if (!pe)
                        pe = diff_funcname_pattern(two);

                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.file = o->file;
                xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
                xecfg.ctxlen = o->context;
                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);
                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;
                }
                xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb);
                if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS))
                        free_diff_words_data(&ecbdata);
        }

 free_ab_and_return:
        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;
                xdemitcb_t ecb;

                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);
        }

 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.xm.consume = checkdiff_consume;
        data.filename = name_b ? name_b : name_a;
        data.lineno = 0;
        data.o = o;
        data.ws_rule = whitespace_rule(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;
                xdemitcb_t ecb;

                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);

                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_preimage;

                        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;
        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, NULL))
                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 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;
        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));

        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);
        len = snprintf(data, 100,
                "Subproject commit %s\n", sha1_to_hex(s->sha1));
        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;
                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 (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);
                                goto err_empty;
                        }
                        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
                 */
                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);
                        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);
                else {
                        s->data = read_sha1_file(s->sha1, &type, &s->size);
                        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(struct diff_tempfile *temp,
                           void *blob,
                           unsigned long size,
                           const unsigned char *sha1,
                           int mode)
{
        int fd;

        fd = git_mkstemp(temp->tmp_path, PATH_MAX, ".diff_XXXXXX");
        if (fd < 0)
                die("unable to create temp-file: %s", strerror(errno));
        if (write_in_full(fd, blob, size) != size)
                die("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);
}

static void prepare_temp_file(const char *name,
                              struct diff_tempfile *temp,
                              struct diff_filespec *one)
{
        if (!DIFF_FILE_VALID(one)) {
        not_a_valid_file:
                /* A '-' entry produces this for file-2, and
                 * a '+' entry produces this for file-1.
                 */
                temp->name = "/dev/null";
                strcpy(temp->hex, ".");
                strcpy(temp->mode, ".");
                return;
        }

        if (!one->sha1_valid ||
            reuse_worktree_file(name, one->sha1, 1)) {
                struct stat st;
                if (lstat(name, &st) < 0) {
                        if (errno == ENOENT)
                                goto not_a_valid_file;
                        die("stat(%s): %s", name, strerror(errno));
                }
                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,
                                       (one->sha1_valid ?
                                        one->sha1 : null_sha1),
                                       (one->sha1_valid ?
                                        one->mode : S_IFLNK));
                }
                else {
                        /* we can borrow from the file in the work tree */
                        temp->name = name;
                        if (!one->sha1_valid)
                                strcpy(temp->hex, sha1_to_hex(null_sha1));
                        else
                                strcpy(temp->hex, sha1_to_hex(one->sha1));
                        /* Even though we may sometimes borrow the
                         * contents from the work tree, we always want
                         * one->mode.  mode is trustworthy even when
                         * !(one->sha1_valid), as long as
                         * DIFF_FILE_VALID(one).
                         */
                        sprintf(temp->mode, "%06o", one->mode);
                }
                return;
        }
        else {
                if (diff_populate_filespec(one, 0))
                        die("cannot read data blob for %s", one->path);
                prep_temp_blob(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);
}

/* An external diff command takes:
 *
 * diff-cmd name infile1 infile1-sha1 infile1-mode \
 *               infile2 infile2-sha1 infile2-mode [ rename-to ]
 *
 */
static void run_external_diff(const char *pgm,
                              const char *name,
                              const char *other,
                              struct diff_filespec *one,
                              struct diff_filespec *two,
                              const char *xfrm_msg,
                              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) {
                *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;
                if (other) {
                        *arg++ = other;
                        *arg++ = xfrm_msg;
                }
        } else {
                *arg++ = pgm;
                *arg++ = name;
        }
        *arg = NULL;
        fflush(NULL);
        retval = run_command_v_opt(spawn_arg, 0);
        remove_tempfile();
        if (retval) {
                fprintf(stderr, "external diff died, stopping at %s.\n", name);
                exit(1);
        }
}

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;
}

static void fill_metainfo(struct strbuf *msg,
                          const char *name,
                          const char *other,
                          struct diff_filespec *one,
                          struct diff_filespec *two,
                          struct diff_options *o,
                          struct diff_filepair *p)
{
        strbuf_init(msg, PATH_MAX * 2 + 300);
        switch (p->status) {
        case DIFF_STATUS_COPIED:
                strbuf_addf(msg, "similarity index %d%%", similarity_index(p));
                strbuf_addstr(msg, "\ncopy from ");
                quote_c_style(name, msg, NULL, 0);
                strbuf_addstr(msg, "\ncopy to ");
                quote_c_style(other, msg, NULL, 0);
                strbuf_addch(msg, '\n');
                break;
        case DIFF_STATUS_RENAMED:
                strbuf_addf(msg, "similarity index %d%%", similarity_index(p));
                strbuf_addstr(msg, "\nrename from ");
                quote_c_style(name, msg, NULL, 0);
                strbuf_addstr(msg, "\nrename to ");
                quote_c_style(other, msg, NULL, 0);
                strbuf_addch(msg, '\n');
                break;
        case DIFF_STATUS_MODIFIED:
                if (p->score) {
                        strbuf_addf(msg, "dissimilarity index %d%%\n",
                                    similarity_index(p));
                        break;
                }
                /* fallthru */
        default:
                /* nothing */
                ;
        }
        if (one && two && hashcmp(one->sha1, two->sha1)) {
                int abbrev = DIFF_OPT_TST(o, FULL_INDEX) ? 40 : DEFAULT_ABBREV;

                if (DIFF_OPT_TST(o, BINARY)) {
                        mmfile_t mf;
                        if ((!fill_mmfile(&mf, one) && diff_filespec_is_binary(one)) ||
                            (!fill_mmfile(&mf, two) && diff_filespec_is_binary(two)))
                                abbrev = 40;
                }
                strbuf_addf(msg, "index %.*s..%.*s",
                            abbrev, sha1_to_hex(one->sha1),
                            abbrev, sha1_to_hex(two->sha1));
                if (one->mode == two->mode)
                        strbuf_addf(msg, " %06o", one->mode);
                strbuf_addch(msg, '\n');
        }
        if (msg->len)
                strbuf_setlen(msg, msg->len - 1);
}

static void run_diff_cmd(const char *pgm,
                         const char *name,
                         const char *other,
                         const char *attr_path,
                         struct diff_filespec *one,
                         struct diff_filespec *two,
                         struct strbuf *msg,
                         struct diff_options *o,
                         struct diff_filepair *p)
{
        const char *xfrm_msg = NULL;
        int complete_rewrite = (p->status == DIFF_STATUS_MODIFIED) && p->score;

        if (msg) {
                fill_metainfo(msg, name, other, one, two, o, p);
                xfrm_msg = msg->len ? msg->buf : NULL;
        }

        if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
                pgm = NULL;
        else {
                const char *cmd = external_diff_attr(attr_path);
                if (cmd)
                        pgm = cmd;
        }

        if (pgm) {
                run_external_diff(pgm, name, other, one, two, xfrm_msg,
                                  complete_rewrite);
                return;
        }
        if (one && two)
                builtin_diff(name, other ? other : name,
                             one, two, xfrm_msg, o, complete_rewrite);
        else
                fprintf(o->file, "* Unmerged path %s\n", name);
}

static void diff_fill_sha1_info(struct diff_filespec *one)
{
        if (DIFF_FILE_VALID(one)) {
                if (!one->sha1_valid) {
                        struct stat st;
                        if (!strcmp(one->path, "-")) {
                                hashcpy(one->sha1, null_sha1);
                                return;
                        }
                        if (lstat(one->path, &st) < 0)
                                die("stat %s", one->path);
                        if (index_path(one->sha1, one->path, &st, 0))
                                die("cannot hash %s\n", one->path);
                }
        }
        else
                hashclr(one->sha1);
}

static void strip_prefix(int prefix_length, const char **namep, const char **otherp)
{
        /* Strip the prefix but do not molest /dev/null and absolute paths */
        if (*namep && **namep != '/')
                *namep += prefix_length;
        if (*otherp && **otherp != '/')
                *otherp += prefix_length;
}

static void run_diff(struct diff_filepair *p, struct diff_options *o)
{
        const char *pgm = external_diff();
        struct strbuf msg;
        struct diff_filespec *one = p->one;
        struct diff_filespec *two = p->two;
        const char *name;
        const char *other;
        const char *attr_path;

        name  = p->one->path;
        other = (strcmp(name, p->two->path) ? p->two->path : NULL);
        attr_path = name;
        if (o->prefix_length)
                strip_prefix(o->prefix_length, &name, &other);

        if (DIFF_PAIR_UNMERGED(p)) {
                run_diff_cmd(pgm, name, NULL, attr_path,
                             NULL, NULL, NULL, o, p);
                return;
        }

        diff_fill_sha1_info(one);
        diff_fill_sha1_info(two);

        if (!pgm &&
            DIFF_FILE_VALID(one) && DIFF_FILE_VALID(two) &&
            (S_IFMT & one->mode) != (S_IFMT & two->mode)) {
                /*
                 * a filepair that changes between file and symlink
                 * needs to be split into deletion and creation.
                 */
                struct diff_filespec *null = alloc_filespec(two->path);
                run_diff_cmd(NULL, name, other, attr_path,
                             one, null, &msg, o, p);
                free(null);
                strbuf_release(&msg);

                null = alloc_filespec(one->path);
                run_diff_cmd(NULL, name, other, attr_path,
                             null, two, &msg, o, p);
                free(null);
        }
        else
                run_diff_cmd(pgm, name, other, attr_path,
                             one, two, &msg, o, p);

        strbuf_release(&msg);
}

static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
                         struct diffstat_t *diffstat)
{
        const char *name;
        const char *other;
        int complete_rewrite = 0;

        if (DIFF_PAIR_UNMERGED(p)) {
                /* unmerged */
                builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat, o, 0);
                return;
        }

        name = p->one->path;
        other = (strcmp(name, p->two->path) ? p->two->path : NULL);

        if (o->prefix_length)
                strip_prefix(o->prefix_length, &name, &other);

        diff_fill_sha1_info(p->one);
        diff_fill_sha1_info(p->two);

        if (p->status == DIFF_STATUS_MODIFIED && p->score)
                complete_rewrite = 1;
        builtin_diffstat(name, other, p->one, p->two, diffstat, o, complete_rewrite);
}

static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
{
        const char *name;
        const char *other;
        const char *attr_path;

        if (DIFF_PAIR_UNMERGED(p)) {
                /* unmerged */
                return;
        }

        name = p->one->path;
        other = (strcmp(name, p->two->path) ? p->two->path : NULL);
        attr_path = other ? other : name;

        if (o->prefix_length)
                strip_prefix(o->prefix_length, &name, &other);

        diff_fill_sha1_info(p->one);
        diff_fill_sha1_info(p->two);

        builtin_checkdiff(name, other, attr_path, p->one, p->two, o);
}

void diff_setup(struct diff_options *options)
{
        memset(options, 0, sizeof(*options));

        options->file = stdout;

        options->line_termination = '\n';
        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/";
}

int diff_setup_done(struct diff_options *options)
{
        int count = 0;

        if (options->output_format & DIFF_FORMAT_NAME)
                count++;
        if (options->output_format & DIFF_FORMAT_NAME_STATUS)
                count++;
        if (options->output_format & DIFF_FORMAT_CHECKDIFF)
                count++;
        if (options->output_format & DIFF_FORMAT_NO_OUTPUT)
                count++;
        if (count > 1)
                die("--name-only, --name-status, --check and -s are mutually exclusive");

        if (DIFF_OPT_TST(options, FIND_COPIES_HARDER))
                options->detect_rename = DIFF_DETECT_COPY;

        if (!DIFF_OPT_TST(options, RELATIVE_NAME))
                options->prefix = NULL;
        if (options->prefix)
                options->prefix_length = strlen(options->prefix);
        else
                options->prefix_length = 0;

        if (options->output_format & (DIFF_FORMAT_NAME |
                                      DIFF_FORMAT_NAME_STATUS |
                                      DIFF_FORMAT_CHECKDIFF |
                                      DIFF_FORMAT_NO_OUTPUT))
                options->output_format &= ~(DIFF_FORMAT_RAW |
                                            DIFF_FORMAT_NUMSTAT |
                                            DIFF_FORMAT_DIFFSTAT |
                                            DIFF_FORMAT_SHORTSTAT |
                                            DIFF_FORMAT_DIRSTAT |
                                            DIFF_FORMAT_SUMMARY |
                                            DIFF_FORMAT_PATCH);

        /*
         * These cases always need recursive; we do not drop caller-supplied
         * recursive bits for other formats here.
         */
        if (options->output_format & (DIFF_FORMAT_PATCH |
                                      DIFF_FORMAT_NUMSTAT |
                                      DIFF_FORMAT_DIFFSTAT |
                                      DIFF_FORMAT_SHORTSTAT |
                                      DIFF_FORMAT_DIRSTAT |
                                      DIFF_FORMAT_SUMMARY |
                                      DIFF_FORMAT_CHECKDIFF))
                DIFF_OPT_SET(options, RECURSIVE);
        /*
         * Also pickaxe would not work very well if you do not say recursive
         */
        if (options->pickaxe)
                DIFF_OPT_SET(options, RECURSIVE);

        if (options->detect_rename && options->rename_limit < 0)
                options->rename_limit = diff_rename_limit_default;
        if (options->setup & DIFF_SETUP_USE_CACHE) {
                if (!active_cache)
                        /* read-cache does not die even when it fails
                         * so it is safe for us to do this here.  Also
                         * it does not smudge active_cache or active_nr
                         * when it fails, so we do not have to worry about
                         * cleaning it up ourselves either.
                         */
                        read_cache();
        }
        if (options->abbrev <= 0 || 40 < options->abbrev)
                options->abbrev = 40; /* full */

        /*
         * It does not make sense to show the first hit we happened
         * to have found.  It does not make sense not to return with
         * exit code in such a case either.
         */
        if (DIFF_OPT_TST(options, QUIET)) {
                options->output_format = DIFF_FORMAT_NO_OUTPUT;
                DIFF_OPT_SET(options, EXIT_WITH_STATUS);
        }

        return 0;
}

static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
{
        char c, *eq;
        int len;

        if (*arg != '-')
                return 0;
        c = *++arg;
        if (!c)
                return 0;
        if (c == arg_short) {
                c = *++arg;
                if (!c)
                        return 1;
                if (val && isdigit(c)) {
                        char *end;
                        int n = strtoul(arg, &end, 10);
                        if (*end)
                                return 0;
                        *val = n;
                        return 1;
                }
                return 0;
        }
        if (c != '-')
                return 0;
        arg++;
        eq = strchr(arg, '=');
        if (eq)
                len = eq - arg;
        else
                len = strlen(arg);
        if (!len || strncmp(arg, arg_long, len))
                return 0;
        if (eq) {
                int n;
                char *end;
                if (!isdigit(*++eq))
                        return 0;
                n = strtoul(eq, &end, 10);
                if (*end)
                        return 0;
                *val = n;
        }
        return 1;
}

static int diff_scoreopt_parse(const char *opt);

int diff_opt_parse(struct diff_options *options, const char **av, int ac)
{
        const char *arg = av[0];

        /* Output format options */
        if (!strcmp(arg, "-p") || !strcmp(arg, "-u"))
                options->output_format |= DIFF_FORMAT_PATCH;
        else if (opt_arg(arg, 'U', "unified", &options->context))
                options->output_format |= DIFF_FORMAT_PATCH;
        else if (!strcmp(arg, "--raw"))
                options->output_format |= DIFF_FORMAT_RAW;
        else if (!strcmp(arg, "--patch-with-raw"))
                options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_RAW;
        else if (!strcmp(arg, "--numstat"))
                options->output_format |= DIFF_FORMAT_NUMSTAT;
        else if (!strcmp(arg, "--shortstat"))
                options->output_format |= DIFF_FORMAT_SHORTSTAT;
        else if (opt_arg(arg, 'X', "dirstat", &options->dirstat_percent))
                options->output_format |= DIFF_FORMAT_DIRSTAT;
        else if (!strcmp(arg, "--cumulative")) {
                options->output_format |= DIFF_FORMAT_DIRSTAT;
                DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE);
        }
        else if (!strcmp(arg, "--check"))
                options->output_format |= DIFF_FORMAT_CHECKDIFF;
        else if (!strcmp(arg, "--summary"))
                options->output_format |= DIFF_FORMAT_SUMMARY;
        else if (!strcmp(arg, "--patch-with-stat"))
                options->output_format |= DIFF_FORMAT_PATCH | DIFF_FORMAT_DIFFSTAT;
        else if (!strcmp(arg, "--name-only"))
                options->output_format |= DIFF_FORMAT_NAME;
        else if (!strcmp(arg, "--name-status"))
                options->output_format |= DIFF_FORMAT_NAME_STATUS;
        else if (!strcmp(arg, "-s"))
                options->output_format |= DIFF_FORMAT_NO_OUTPUT;
        else if (!prefixcmp(arg, "--stat")) {
                char *end;
                int width = options->stat_width;
                int name_width = options->stat_name_width;
                arg += 6;
                end = (char *)arg;

                switch (*arg) {
                case '-':
                        if (!prefixcmp(arg, "-width="))
                                width = strtoul(arg + 7, &end, 10);
                        else if (!prefixcmp(arg, "-name-width="))
                                name_width = strtoul(arg + 12, &end, 10);
                        break;
                case '=':
                        width = strtoul(arg+1, &end, 10);
                        if (*end == ',')
                                name_width = strtoul(end+1, &end, 10);
                }

                /* Important! This checks all the error cases! */
                if (*end)
                        return 0;
                options->output_format |= DIFF_FORMAT_DIFFSTAT;
                options->stat_name_width = name_width;
                options->stat_width = width;
        }

        /* renames options */
        else if (!prefixcmp(arg, "-B")) {
                if ((options->break_opt = diff_scoreopt_parse(arg)) == -1)
                        return -1;
        }
        else if (!prefixcmp(arg, "-M")) {
                if ((options->rename_score = diff_scoreopt_parse(arg)) == -1)
                        return -1;
                options->detect_rename = DIFF_DETECT_RENAME;
        }
        else if (!prefixcmp(arg, "-C")) {
                if (options->detect_rename == DIFF_DETECT_COPY)
                        DIFF_OPT_SET(options, FIND_COPIES_HARDER);
                if ((options->rename_score = diff_scoreopt_parse(arg)) == -1)
                        return -1;
                options->detect_rename = DIFF_DETECT_COPY;
        }
        else if (!strcmp(arg, "--no-renames"))
                options->detect_rename = 0;
        else if (!strcmp(arg, "--relative"))
                DIFF_OPT_SET(options, RELATIVE_NAME);
        else if (!prefixcmp(arg, "--relative=")) {
                DIFF_OPT_SET(options, RELATIVE_NAME);
                options->prefix = arg + 11;
        }

        /* xdiff options */
        else if (!strcmp(arg, "-w") || !strcmp(arg, "--ignore-all-space"))
                options->xdl_opts |= XDF_IGNORE_WHITESPACE;
        else if (!strcmp(arg, "-b") || !strcmp(arg, "--ignore-space-change"))
                options->xdl_opts |= XDF_IGNORE_WHITESPACE_CHANGE;
        else if (!strcmp(arg, "--ignore-space-at-eol"))
                options->xdl_opts |= XDF_IGNORE_WHITESPACE_AT_EOL;

        /* flags options */
        else if (!strcmp(arg, "--binary")) {
                options->output_format |= DIFF_FORMAT_PATCH;
                DIFF_OPT_SET(options, BINARY);
        }
        else if (!strcmp(arg, "--full-index"))
                DIFF_OPT_SET(options, FULL_INDEX);
        else if (!strcmp(arg, "-a") || !strcmp(arg, "--text"))
                DIFF_OPT_SET(options, TEXT);
        else if (!strcmp(arg, "-R"))
                DIFF_OPT_SET(options, REVERSE_DIFF);
        else if (!strcmp(arg, "--find-copies-harder"))
                DIFF_OPT_SET(options, FIND_COPIES_HARDER);
        else if (!strcmp(arg, "--follow"))
                DIFF_OPT_SET(options, FOLLOW_RENAMES);
        else if (!strcmp(arg, "--color"))
                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, "--exit-code"))
                DIFF_OPT_SET(options, EXIT_WITH_STATUS);
        else if (!strcmp(arg, "--quiet"))
                DIFF_OPT_SET(options, QUIET);
        else if (!strcmp(arg, "--ext-diff"))
                DIFF_OPT_SET(options, ALLOW_EXTERNAL);
        else if (!strcmp(arg, "--no-ext-diff"))
                DIFF_OPT_CLR(options, ALLOW_EXTERNAL);
        else if (!strcmp(arg, "--ignore-submodules"))
                DIFF_OPT_SET(options, IGNORE_SUBMODULES);

        /* misc options */
        else if (!strcmp(arg, "-z"))
                options->line_termination = 0;
        else if (!prefixcmp(arg, "-l"))
                options->rename_limit = strtoul(arg+2, NULL, 10);
        else if (!prefixcmp(arg, "-S"))
                options->pickaxe = arg + 2;
        else if (!strcmp(arg, "--pickaxe-all"))
                options->pickaxe_opts = DIFF_PICKAXE_ALL;
        else if (!strcmp(arg, "--pickaxe-regex"))
                options->pickaxe_opts = DIFF_PICKAXE_REGEX;
        else if (!prefixcmp(arg, "-O"))
                options->orderfile = arg + 2;
        else if (!prefixcmp(arg, "--diff-filter="))
                options->filter = arg + 14;
        else if (!strcmp(arg, "--abbrev"))
                options->abbrev = DEFAULT_ABBREV;
        else if (!prefixcmp(arg, "--abbrev=")) {
                options->abbrev = strtoul(arg + 9, NULL, 10);
                if (options->abbrev < MINIMUM_ABBREV)
                        options->abbrev = MINIMUM_ABBREV;
                else if (40 < options->abbrev)
                        options->abbrev = 40;
        }
        else if (!prefixcmp(arg, "--src-prefix="))
                options->a_prefix = arg + 13;
        else if (!prefixcmp(arg, "--dst-prefix="))
                options->b_prefix = arg + 13;
        else if (!strcmp(arg, "--no-prefix"))
                options->a_prefix = options->b_prefix = "";
        else if (!prefixcmp(arg, "--output=")) {
                options->file = fopen(arg + strlen("--output="), "w");
                options->close_file = 1;
        } else
                return 0;
        return 1;
}

static int parse_num(const char **cp_p)
{
        unsigned long num, scale;
        int ch, dot;
        const char *cp = *cp_p;

        num = 0;
        scale = 1;
        dot = 0;
        for(;;) {
                ch = *cp;
                if ( !dot && ch == '.' ) {
                        scale = 1;
                        dot = 1;
                } else if ( ch == '%' ) {
                        scale = dot ? scale*100 : 100;
                        cp++;   /* % is always at the end */
                        break;
                } else if ( ch >= '0' && ch <= '9' ) {
                        if ( scale < 100000 ) {
                                scale *= 10;
                                num = (num*10) + (ch-'0');
                        }
                } else {
                        break;
                }
                cp++;
        }
        *cp_p = cp;

        /* user says num divided by scale and we say internally that
         * is MAX_SCORE * num / scale.
         */
        return (int)((num >= scale) ? MAX_SCORE : (MAX_SCORE * num / scale));
}

static int diff_scoreopt_parse(const char *opt)
{
        int opt1, opt2, cmd;

        if (*opt++ != '-')
                return -1;
        cmd = *opt++;
        if (cmd != 'M' && cmd != 'C' && cmd != 'B')
                return -1; /* that is not a -M, -C nor -B option */

        opt1 = parse_num(&opt);
        if (cmd != 'B')
                opt2 = 0;
        else {
                if (*opt == 0)
                        opt2 = 0;
                else if (*opt != '/')
                        return -1; /* we expect -B80/99 or -B80 */
                else {
                        opt++;
                        opt2 = parse_num(&opt);
                }
        }
        if (*opt != 0)
                return -1;
        return opt1 | (opt2 << 16);
}

struct diff_queue_struct diff_queued_diff;

void diff_q(struct diff_queue_struct *queue, struct diff_filepair *dp)
{
        if (queue->alloc <= queue->nr) {
                queue->alloc = alloc_nr(queue->alloc);
                queue->queue = xrealloc(queue->queue,
                                        sizeof(dp) * queue->alloc);
        }
        queue->queue[queue->nr++] = dp;
}

struct diff_filepair *diff_queue(struct diff_queue_struct *queue,
                                 struct diff_filespec *one,
                                 struct diff_filespec *two)
{
        struct diff_filepair *dp = xcalloc(1, sizeof(*dp));
        dp->one = one;
        dp->two = two;
        if (queue)
                diff_q(queue, dp);
        return dp;
}

void diff_free_filepair(struct diff_filepair *p)
{
        free_filespec(p->one);
        free_filespec(p->two);
        free(p);
}

/* This is different from find_unique_abbrev() in that
 * it stuffs the result with dots for alignment.
 */
const char *diff_unique_abbrev(const unsigned char *sha1, int len)
{
        int abblen;
        const char *abbrev;
        if (len == 40)
                return sha1_to_hex(sha1);

        abbrev = find_unique_abbrev(sha1, len);
        abblen = strlen(abbrev);
        if (abblen < 37) {
                static char hex[41];
                if (len < abblen && abblen <= len + 2)
                        sprintf(hex, "%s%.*s", abbrev, len+3-abblen, "..");
                else
                        sprintf(hex, "%s...", abbrev);
                return hex;
        }
        return sha1_to_hex(sha1);
}

static void diff_flush_raw(struct diff_filepair *p, struct diff_options *opt)
{
        int line_termination = opt->line_termination;
        int inter_name_termination = line_termination ? '\t' : '\0';

        if (!(opt->output_format & DIFF_FORMAT_NAME_STATUS)) {
                fprintf(opt->file, ":%06o %06o %s ", p->one->mode, p->two->mode,
                        diff_unique_abbrev(p->one->sha1, opt->abbrev));
                fprintf(opt->file, "%s ", diff_unique_abbrev(p->two->sha1, opt->abbrev));
        }
        if (p->score) {
                fprintf(opt->file, "%c%03d%c", p->status, similarity_index(p),
                        inter_name_termination);
        } else {
                fprintf(opt->file, "%c%c", p->status, inter_name_termination);
        }

        if (p->status == DIFF_STATUS_COPIED ||
            p->status == DIFF_STATUS_RENAMED) {
                const char *name_a, *name_b;
                name_a = p->one->path;
                name_b = p->two->path;
                strip_prefix(opt->prefix_length, &name_a, &name_b);
                write_name_quoted(name_a, opt->file, inter_name_termination);
                write_name_quoted(name_b, opt->file, line_termination);
        } else {
                const char *name_a, *name_b;
                name_a = p->one->mode ? p->one->path : p->two->path;
                name_b = NULL;
                strip_prefix(opt->prefix_length, &name_a, &name_b);
                write_name_quoted(name_a, opt->file, line_termination);
        }
}

int diff_unmodified_pair(struct diff_filepair *p)
{
        /* This function is written stricter than necessary to support
         * the currently implemented transformers, but the idea is to
         * let transformers to produce diff_filepairs any way they want,
         * and filter and clean them up here before producing the output.
         */
        struct diff_filespec *one = p->one, *two = p->two;

        if (DIFF_PAIR_UNMERGED(p))
                return 0; /* unmerged is interesting */

        /* deletion, addition, mode or type change
         * and rename are all interesting.
         */
        if (DIFF_FILE_VALID(one) != DIFF_FILE_VALID(two) ||
            DIFF_PAIR_MODE_CHANGED(p) ||
            strcmp(one->path, two->path))
                return 0;

        /* both are valid and point at the same path.  that is, we are
         * dealing with a change.
         */
        if (one->sha1_valid && two->sha1_valid &&
            !hashcmp(one->sha1, two->sha1))
                return 1; /* no change */
        if (!one->sha1_valid && !two->sha1_valid)
                return 1; /* both look at the same file on the filesystem. */
        return 0;
}

static void diff_flush_patch(struct diff_filepair *p, struct diff_options *o)
{
        if (diff_unmodified_pair(p))
                return;

        if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
            (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
                return; /* no tree diffs in patch format */

        run_diff(p, o);
}

static void diff_flush_stat(struct diff_filepair *p, struct diff_options *o,
                            struct diffstat_t *diffstat)
{
        if (diff_unmodified_pair(p))
                return;

        if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
            (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
                return; /* no tree diffs in patch format */

        run_diffstat(p, o, diffstat);
}

static void diff_flush_checkdiff(struct diff_filepair *p,
                struct diff_options *o)
{
        if (diff_unmodified_pair(p))
                return;

        if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
            (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
                return; /* no tree diffs in patch format */

        run_checkdiff(p, o);
}

int diff_queue_is_empty(void)
{
        struct diff_queue_struct *q = &diff_queued_diff;
        int i;
        for (i = 0; i < q->nr; i++)
                if (!diff_unmodified_pair(q->queue[i]))
                        return 0;
        return 1;
}

#if DIFF_DEBUG
void diff_debug_filespec(struct diff_filespec *s, int x, const char *one)
{
        fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n",
                x, one ? one : "",
                s->path,
                DIFF_FILE_VALID(s) ? "valid" : "invalid",
                s->mode,
                s->sha1_valid ? sha1_to_hex(s->sha1) : "");
        fprintf(stderr, "queue[%d] %s size %lu flags %d\n",
                x, one ? one : "",
                s->size, s->xfrm_flags);
}

void diff_debug_filepair(const struct diff_filepair *p, int i)
{
        diff_debug_filespec(p->one, i, "one");
        diff_debug_filespec(p->two, i, "two");
        fprintf(stderr, "score %d, status %c rename_used %d broken %d\n",
                p->score, p->status ? p->status : '?',
                p->one->rename_used, p->broken_pair);
}

void diff_debug_queue(const char *msg, struct diff_queue_struct *q)
{
        int i;
        if (msg)
                fprintf(stderr, "%s\n", msg);
        fprintf(stderr, "q->nr = %d\n", q->nr);
        for (i = 0; i < q->nr; i++) {
                struct diff_filepair *p = q->queue[i];
                diff_debug_filepair(p, i);
        }
}
#endif

static void diff_resolve_rename_copy(void)
{
        int i;
        struct diff_filepair *p;
        struct diff_queue_struct *q = &diff_queued_diff;

        diff_debug_queue("resolve-rename-copy", q);

        for (i = 0; i < q->nr; i++) {
                p = q->queue[i];
                p->status = 0; /* undecided */
                if (DIFF_PAIR_UNMERGED(p))
                        p->status = DIFF_STATUS_UNMERGED;
                else if (!DIFF_FILE_VALID(p->one))
                        p->status = DIFF_STATUS_ADDED;
                else if (!DIFF_FILE_VALID(p->two))
                        p->status = DIFF_STATUS_DELETED;
                else if (DIFF_PAIR_TYPE_CHANGED(p))
                        p->status = DIFF_STATUS_TYPE_CHANGED;

                /* from this point on, we are dealing with a pair
                 * whose both sides are valid and of the same type, i.e.
                 * either in-place edit or rename/copy edit.
                 */
                else if (DIFF_PAIR_RENAME(p)) {
                        /*
                         * A rename might have re-connected a broken
                         * pair up, causing the pathnames to be the
                         * same again. If so, that's not a rename at
                         * all, just a modification..
                         *
                         * Otherwise, see if this source was used for
                         * multiple renames, in which case we decrement
                         * the count, and call it a copy.
                         */
                        if (!strcmp(p->one->path, p->two->path))
                                p->status = DIFF_STATUS_MODIFIED;
                        else if (--p->one->rename_used > 0)
                                p->status = DIFF_STATUS_COPIED;
                        else
                                p->status = DIFF_STATUS_RENAMED;
                }
                else if (hashcmp(p->one->sha1, p->two->sha1) ||
                         p->one->mode != p->two->mode ||
                         is_null_sha1(p->one->sha1))
                        p->status = DIFF_STATUS_MODIFIED;
                else {
                        /* This is a "no-change" entry and should not
                         * happen anymore, but prepare for broken callers.
                         */
                        error("feeding unmodified %s to diffcore",
                              p->one->path);
                        p->status = DIFF_STATUS_UNKNOWN;
                }
        }
        diff_debug_queue("resolve-rename-copy done", q);
}

static int check_pair_status(struct diff_filepair *p)
{
        switch (p->status) {
        case DIFF_STATUS_UNKNOWN:
                return 0;
        case 0:
                die("internal error in diff-resolve-rename-copy");
        default:
                return 1;
        }
}

static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt)
{
        int fmt = opt->output_format;

        if (fmt & DIFF_FORMAT_CHECKDIFF)
                diff_flush_checkdiff(p, opt);
        else if (fmt & (DIFF_FORMAT_RAW | DIFF_FORMAT_NAME_STATUS))
                diff_flush_raw(p, opt);
        else if (fmt & DIFF_FORMAT_NAME) {
                const char *name_a, *name_b;
                name_a = p->two->path;
                name_b = NULL;
                strip_prefix(opt->prefix_length, &name_a, &name_b);
                write_name_quoted(name_a, opt->file, opt->line_termination);
        }
}

static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs)
{
        if (fs->mode)
                fprintf(file, " %s mode %06o ", newdelete, fs->mode);
        else
                fprintf(file, " %s ", newdelete);
        write_name_quoted(fs->path, file, '\n');
}


static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name)
{
        if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) {
                fprintf(file, " mode change %06o => %06o%c", p->one->mode, p->two->mode,
                        show_name ? ' ' : '\n');
                if (show_name) {
                        write_name_quoted(p->two->path, file, '\n');
                }
        }
}

static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p)
{
        char *names = pprint_rename(p->one->path, p->two->path);

        fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
        free(names);
        show_mode_change(file, p, 0);
}

static void diff_summary(FILE *file, struct diff_filepair *p)
{
        switch(p->status) {
        case DIFF_STATUS_DELETED:
                show_file_mode_name(file, "delete", p->one);
                break;
        case DIFF_STATUS_ADDED:
                show_file_mode_name(file, "create", p->two);
                break;
        case DIFF_STATUS_COPIED:
                show_rename_copy(file, "copy", p);
                break;
        case DIFF_STATUS_RENAMED:
                show_rename_copy(file, "rename", p);
                break;
        default:
                if (p->score) {
                        fputs(" rewrite ", file);
                        write_name_quoted(p->two->path, file, ' ');
                        fprintf(file, "(%d%%)\n", similarity_index(p));
                }
                show_mode_change(file, p, !p->score);
                break;
        }
}

struct patch_id_t {
        struct xdiff_emit_state xm;
        SHA_CTX *ctx;
        int patchlen;
};

static int remove_space(char *line, int len)
{
        int i;
        char *dst = line;
        unsigned char c;

        for (i = 0; i < len; i++)
                if (!isspace((c = line[i])))
                        *dst++ = c;

        return dst - line;
}

static void patch_id_consume(void *priv, char *line, unsigned long len)
{
        struct patch_id_t *data = priv;
        int new_len;

        /* Ignore line numbers when computing the SHA1 of the patch */
        if (!prefixcmp(line, "@@ -"))
                return;

        new_len = remove_space(line, len);

        SHA1_Update(data->ctx, line, new_len);
        data->patchlen += new_len;
}

/* returns 0 upon success, and writes result into sha1 */
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;
        struct patch_id_t data;
        char buffer[PATH_MAX * 4 + 20];

        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;
                xdemitconf_t xecfg;
                xdemitcb_t ecb;
                mmfile_t mf1, mf2;
                struct diff_filepair *p = q->queue[i];
                int len1, len2;

                memset(&xecfg, 0, sizeof(xecfg));
                if (p->status == 0)
                        return error("internal diff status error");
                if (p->status == DIFF_STATUS_UNKNOWN)
                        continue;
                if (diff_unmodified_pair(p))
                        continue;
                if ((DIFF_FILE_VALID(p->one) && S_ISDIR(p->one->mode)) ||
                    (DIFF_FILE_VALID(p->two) && S_ISDIR(p->two->mode)))
                        continue;
                if (DIFF_PAIR_UNMERGED(p))
                        continue;

                diff_fill_sha1_info(p->one);
                diff_fill_sha1_info(p->two);
                if (fill_mmfile(&mf1, p->one) < 0 ||
                                fill_mmfile(&mf2, p->two) < 0)
                        return error("unable to read files to diff");

                len1 = remove_space(p->one->path, strlen(p->one->path));
                len2 = remove_space(p->two->path, strlen(p->two->path));
                if (p->one->mode == 0)
                        len1 = snprintf(buffer, sizeof(buffer),
                                        "diff--gita/%.*sb/%.*s"
                                        "newfilemode%06o"
                                        "---/dev/null"
                                        "+++b/%.*s",
                                        len1, p->one->path,
                                        len2, p->two->path,
                                        p->two->mode,
                                        len2, p->two->path);
                else if (p->two->mode == 0)
                        len1 = snprintf(buffer, sizeof(buffer),
                                        "diff--gita/%.*sb/%.*s"
                                        "deletedfilemode%06o"
                                        "---a/%.*s"
                                        "+++/dev/null",
                                        len1, p->one->path,
                                        len2, p->two->path,
                                        p->one->mode,
                                        len1, p->one->path);
                else
                        len1 = snprintf(buffer, sizeof(buffer),
                                        "diff--gita/%.*sb/%.*s"
                                        "---a/%.*s"
                                        "+++b/%.*s",
                                        len1, p->one->path,
                                        len2, p->two->path,
                                        len1, p->one->path,
                                        len2, p->two->path);
                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);
        }

        SHA1_Final(sha1, &ctx);
        return 0;
}

int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1)
{
        struct diff_queue_struct *q = &diff_queued_diff;
        int i;
        int result = diff_get_patch_id(options, sha1);

        for (i = 0; i < q->nr; i++)
                diff_free_filepair(q->queue[i]);

        free(q->queue);
        q->queue = NULL;
        q->nr = q->alloc = 0;

        return result;
}

static int is_summary_empty(const struct diff_queue_struct *q)
{
        int i;

        for (i = 0; i < q->nr; i++) {
                const struct diff_filepair *p = q->queue[i];

                switch (p->status) {
                case DIFF_STATUS_DELETED:
                case DIFF_STATUS_ADDED:
                case DIFF_STATUS_COPIED:
                case DIFF_STATUS_RENAMED:
                        return 0;
                default:
                        if (p->score)
                                return 0;
                        if (p->one->mode && p->two->mode &&
                            p->one->mode != p->two->mode)
                                return 0;
                        break;
                }
        }
        return 1;
}

void diff_flush(struct diff_options *options)
{
        struct diff_queue_struct *q = &diff_queued_diff;
        int i, output_format = options->output_format;
        int separator = 0;

        /*
         * Order: raw, stat, summary, patch
         * or:    name/name-status/checkdiff (other bits clear)
         */
        if (!q->nr)
                goto free_queue;

        if (output_format & (DIFF_FORMAT_RAW |
                             DIFF_FORMAT_NAME |
                             DIFF_FORMAT_NAME_STATUS |
                             DIFF_FORMAT_CHECKDIFF)) {
                for (i = 0; i < q->nr; i++) {
                        struct diff_filepair *p = q->queue[i];
                        if (check_pair_status(p))
                                flush_one_pair(p, options);
                }
                separator++;
        }

        if (output_format & (DIFF_FORMAT_DIFFSTAT|DIFF_FORMAT_SHORTSTAT|DIFF_FORMAT_NUMSTAT)) {
                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))
                                diff_flush_stat(p, options, &diffstat);
                }
                if (output_format & DIFF_FORMAT_NUMSTAT)
                        show_numstat(&diffstat, options);
                if (output_format & DIFF_FORMAT_DIFFSTAT)
                        show_stats(&diffstat, options);
                if (output_format & DIFF_FORMAT_SHORTSTAT)
                        show_shortstats(&diffstat, options);
                free_diffstat_info(&diffstat);
                separator++;
        }
        if (output_format & DIFF_FORMAT_DIRSTAT)
                show_dirstat(options);

        if (output_format & DIFF_FORMAT_SUMMARY && !is_summary_empty(q)) {
                for (i = 0; i < q->nr; i++)
                        diff_summary(options->file, q->queue[i]);
                separator++;
        }

        if (output_format & DIFF_FORMAT_PATCH) {
                if (separator) {
                        putc(options->line_termination, options->file);
                        if (options->stat_sep) {
                                /* attach patch instead of inline */
                                fputs(options->stat_sep, options->file);
                        }
                }

                for (i = 0; i < q->nr; i++) {
                        struct diff_filepair *p = q->queue[i];
                        if (check_pair_status(p))
                                diff_flush_patch(p, options);
                }
        }

        if (output_format & DIFF_FORMAT_CALLBACK)
                options->format_callback(q, options, options->format_callback_data);

        for (i = 0; i < q->nr; i++)
                diff_free_filepair(q->queue[i]);
free_queue:
        free(q->queue);
        q->queue = NULL;
        q->nr = q->alloc = 0;
        if (options->close_file)
                fclose(options->file);
}

static void diffcore_apply_filter(const char *filter)
{
        int i;
        struct diff_queue_struct *q = &diff_queued_diff;
        struct diff_queue_struct outq;
        outq.queue = NULL;
        outq.nr = outq.alloc = 0;

        if (!filter)
                return;

        if (strchr(filter, DIFF_STATUS_FILTER_AON)) {
                int found;
                for (i = found = 0; !found && i < q->nr; i++) {
                        struct diff_filepair *p = q->queue[i];
                        if (((p->status == DIFF_STATUS_MODIFIED) &&
                             ((p->score &&
                               strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
                              (!p->score &&
                               strchr(filter, DIFF_STATUS_MODIFIED)))) ||
                            ((p->status != DIFF_STATUS_MODIFIED) &&
                             strchr(filter, p->status)))
                                found++;
                }
                if (found)
                        return;

                /* otherwise we will clear the whole queue
                 * by copying the empty outq at the end of this
                 * function, but first clear the current entries
                 * in the queue.
                 */
                for (i = 0; i < q->nr; i++)
                        diff_free_filepair(q->queue[i]);
        }
        else {
                /* Only the matching ones */
                for (i = 0; i < q->nr; i++) {
                        struct diff_filepair *p = q->queue[i];

                        if (((p->status == DIFF_STATUS_MODIFIED) &&
                             ((p->score &&
                               strchr(filter, DIFF_STATUS_FILTER_BROKEN)) ||
                              (!p->score &&
                               strchr(filter, DIFF_STATUS_MODIFIED)))) ||
                            ((p->status != DIFF_STATUS_MODIFIED) &&
                             strchr(filter, p->status)))
                                diff_q(&outq, p);
                        else
                                diff_free_filepair(p);
                }
        }
        free(q->queue);
        *q = outq;
}

/* Check whether two filespecs with the same mode and size are identical */
static int diff_filespec_is_identical(struct diff_filespec *one,
                                      struct diff_filespec *two)
{
        if (S_ISGITLINK(one->mode))
                return 0;
        if (diff_populate_filespec(one, 0))
                return 0;
        if (diff_populate_filespec(two, 0))
                return 0;
        return !memcmp(one->data, two->data, one->size);
}

static void diffcore_skip_stat_unmatch(struct diff_options *diffopt)
{
        int i;
        struct diff_queue_struct *q = &diff_queued_diff;
        struct diff_queue_struct outq;
        outq.queue = NULL;
        outq.nr = outq.alloc = 0;

        for (i = 0; i < q->nr; i++) {
                struct diff_filepair *p = q->queue[i];

                /*
                 * 1. Entries that come from stat info dirtyness
                 *    always have both sides (iow, not create/delete),
                 *    one side of the object name is unknown, with
                 *    the same mode and size.  Keep the ones that
                 *    do not match these criteria.  They have real
                 *    differences.
                 *
                 * 2. At this point, the file is known to be modified,
                 *    with the same mode and size, and the object
                 *    name of one side is unknown.  Need to inspect
                 *    the identical contents.
                 */
                if (!DIFF_FILE_VALID(p->one) || /* (1) */
                    !DIFF_FILE_VALID(p->two) ||
                    (p->one->sha1_valid && p->two->sha1_valid) ||
                    (p->one->mode != p->two->mode) ||
                    diff_populate_filespec(p->one, 1) ||
                    diff_populate_filespec(p->two, 1) ||
                    (p->one->size != p->two->size) ||
                    !diff_filespec_is_identical(p->one, p->two)) /* (2) */
                        diff_q(&outq, p);
                else {
                        /*
                         * The caller can subtract 1 from skip_stat_unmatch
                         * to determine how many paths were dirty only
                         * due to stat info mismatch.
                         */
                        if (!DIFF_OPT_TST(diffopt, NO_INDEX))
                                diffopt->skip_stat_unmatch++;
                        diff_free_filepair(p);
                }
        }
        free(q->queue);
        *q = outq;
}

void diffcore_std(struct diff_options *options)
{
        if (options->skip_stat_unmatch)
                diffcore_skip_stat_unmatch(options);
        if (options->break_opt != -1)
                diffcore_break(options->break_opt);
        if (options->detect_rename)
                diffcore_rename(options);
        if (options->break_opt != -1)
                diffcore_merge_broken();
        if (options->pickaxe)
                diffcore_pickaxe(options->pickaxe, options->pickaxe_opts);
        if (options->orderfile)
                diffcore_order(options->orderfile);
        diff_resolve_rename_copy();
        diffcore_apply_filter(options->filter);

        if (diff_queued_diff.nr)
                DIFF_OPT_SET(options, HAS_CHANGES);
        else
                DIFF_OPT_CLR(options, HAS_CHANGES);
}

int diff_result_code(struct diff_options *opt, int status)
{
        int result = 0;
        if (!DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
            !(opt->output_format & DIFF_FORMAT_CHECKDIFF))
                return status;
        if (DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
            DIFF_OPT_TST(opt, HAS_CHANGES))
                result |= 01;
        if ((opt->output_format & DIFF_FORMAT_CHECKDIFF) &&
            DIFF_OPT_TST(opt, CHECK_FAILED))
                result |= 02;
        return result;
}

void diff_addremove(struct diff_options *options,
                    int addremove, unsigned mode,
                    const unsigned char *sha1,
                    const char *concatpath)
{
        struct diff_filespec *one, *two;

        if (DIFF_OPT_TST(options, IGNORE_SUBMODULES) && S_ISGITLINK(mode))
                return;

        /* This may look odd, but it is a preparation for
         * feeding "there are unchanged files which should
         * not produce diffs, but when you are doing copy
         * detection you would need them, so here they are"
         * entries to the diff-core.  They will be prefixed
         * with something like '=' or '*' (I haven't decided
         * which but should not make any difference).
         * Feeding the same new and old to diff_change()
         * also has the same effect.
         * Before the final output happens, they are pruned after
         * merged into rename/copy pairs as appropriate.
         */
        if (DIFF_OPT_TST(options, REVERSE_DIFF))
                addremove = (addremove == '+' ? '-' :
                             addremove == '-' ? '+' : addremove);

        if (options->prefix &&
            strncmp(concatpath, options->prefix, options->prefix_length))
                return;

        one = alloc_filespec(concatpath);
        two = alloc_filespec(concatpath);

        if (addremove != '+')
                fill_filespec(one, sha1, mode);
        if (addremove != '-')
                fill_filespec(two, sha1, mode);

        diff_queue(&diff_queued_diff, one, two);
        DIFF_OPT_SET(options, HAS_CHANGES);
}

void diff_change(struct diff_options *options,
                 unsigned old_mode, unsigned new_mode,
                 const unsigned char *old_sha1,
                 const unsigned char *new_sha1,
                 const char *concatpath)
{
        struct diff_filespec *one, *two;

        if (DIFF_OPT_TST(options, IGNORE_SUBMODULES) && S_ISGITLINK(old_mode)
                        && S_ISGITLINK(new_mode))
                return;

        if (DIFF_OPT_TST(options, REVERSE_DIFF)) {
                unsigned tmp;
                const unsigned char *tmp_c;
                tmp = old_mode; old_mode = new_mode; new_mode = tmp;
                tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
        }

        if (options->prefix &&
            strncmp(concatpath, options->prefix, options->prefix_length))
                return;

        one = alloc_filespec(concatpath);
        two = alloc_filespec(concatpath);
        fill_filespec(one, old_sha1, old_mode);
        fill_filespec(two, new_sha1, new_mode);

        diff_queue(&diff_queued_diff, one, two);
        DIFF_OPT_SET(options, HAS_CHANGES);
}

void diff_unmerge(struct diff_options *options,
                  const char *path,
                  unsigned mode, const unsigned char *sha1)
{
        struct diff_filespec *one, *two;

        if (options->prefix &&
            strncmp(path, options->prefix, options->prefix_length))
                return;

        one = alloc_filespec(path);
        two = alloc_filespec(path);
        fill_filespec(one, sha1, mode);
        diff_queue(&diff_queued_diff, one, two)->is_unmerged = 1;
}