/src/git/rerere.c

Source
#define DISABLE_SIGN_COMPARE_WARNINGS

#include "git-compat-util.h"
#include "abspath.h"
#include "config.h"
#include "copy.h"
#include "environment.h"
#include "gettext.h"
#include "hex.h"
#include "lockfile.h"
#include "string-list.h"
#include "read-cache-ll.h"
#include "rerere.h"
#include "xdiff-interface.h"
#include "dir.h"
#include "resolve-undo.h"
#include "merge-ll.h"
#include "path.h"
#include "pathspec.h"
#include "object-file.h"
#include "odb.h"
#include "strmap.h"

#define RESOLVED 0
#define PUNTED 1
#define THREE_STAGED 2
void *RERERE_RESOLVED = &RERERE_RESOLVED;

#define RR_HAS_POSTIMAGE 1
#define RR_HAS_PREIMAGE 2
struct rerere_dir {
  int status_alloc, status_nr;
  unsigned char *status;
  char name[FLEX_ARRAY];
};

void rerere_cache_release(struct rerere_cache *cache)
{
  struct hashmap_iter iter;
  struct strmap_entry *ent;

  strmap_for_each_entry(&cache->dirs, &iter, ent) {
    struct rerere_dir *rr_dir = ent->value;
    free(rr_dir->status);
    free(rr_dir);
  }
  strmap_clear(&cache->dirs, 0);

  rollback_lock_file(&cache->write_lock);
}

static void free_rerere_id(struct string_list_item *item)
{
  free(item->util);
}

static const char *rerere_id_hex(const struct rerere_id *id)
{
  return id->collection->name;
}

static void fit_variant(struct rerere_dir *rr_dir, int variant)
{
  variant++;
  ALLOC_GROW(rr_dir->status, variant, rr_dir->status_alloc);
  if (rr_dir->status_nr < variant) {
    memset(rr_dir->status + rr_dir->status_nr,
           '\0', variant - rr_dir->status_nr);
    rr_dir->status_nr = variant;
  }
}

static void assign_variant(struct rerere_id *id)
{
  int variant;
  struct rerere_dir *rr_dir = id->collection;

  variant = id->variant;
  if (variant < 0) {
    for (variant = 0; variant < rr_dir->status_nr; variant++)
      if (!rr_dir->status[variant])
        break;
  }
  fit_variant(rr_dir, variant);
  id->variant = variant;
}

const char *rerere_path(struct repository *repo,
      struct strbuf *buf, const struct rerere_id *id, const char *file)
{
  if (!file)
    return repo_git_path_replace(repo, buf, "rr-cache/%s",
               rerere_id_hex(id));

  if (id->variant <= 0)
    return repo_git_path_replace(repo, buf, "rr-cache/%s/%s",
               rerere_id_hex(id), file);

  return repo_git_path_replace(repo, buf, "rr-cache/%s/%s.%d",
             rerere_id_hex(id), file, id->variant);
}

static int is_rr_file(const char *name, const char *filename, int *variant)
{
  const char *suffix;
  char *ep;

  if (!strcmp(name, filename)) {
    *variant = 0;
    return 1;
  }
  if (!skip_prefix(name, filename, &suffix) || *suffix != '.')
    return 0;

  errno = 0;
  *variant = strtol(suffix + 1, &ep, 10);
  if (errno || *ep)
    return 0;
  return 1;
}

static void scan_rerere_dir(struct rerere_cache *cache, struct rerere_dir *rr_dir)
{
  struct dirent *de;
  char *path;
  DIR *dir;

  path = repo_git_path(cache->repo, "rr-cache/%s", rr_dir->name);
  dir = opendir(path);
  free(path);
  if (!dir)
    return;
  while ((de = readdir(dir)) != NULL) {
    int variant;

    if (is_rr_file(de->d_name, "postimage", &variant)) {
      fit_variant(rr_dir, variant);
      rr_dir->status[variant] |= RR_HAS_POSTIMAGE;
    } else if (is_rr_file(de->d_name, "preimage", &variant)) {
      fit_variant(rr_dir, variant);
      rr_dir->status[variant] |= RR_HAS_PREIMAGE;
    }
  }
  closedir(dir);
}

static struct rerere_dir *find_rerere_dir(struct rerere_cache *cache,
            const char *hex)
{
  struct rerere_dir *rr_dir;

  rr_dir = strmap_get(&cache->dirs, hex);
  if (!rr_dir) {
    FLEX_ALLOC_STR(rr_dir, name, hex);
    rr_dir->status = NULL;
    rr_dir->status_nr = 0;
    rr_dir->status_alloc = 0;
    strmap_put(&cache->dirs, hex, rr_dir);

    scan_rerere_dir(cache, rr_dir);
  }
  return rr_dir;
}

static int has_rerere_resolution(const struct rerere_id *id)
{
  const int both = RR_HAS_POSTIMAGE|RR_HAS_PREIMAGE;
  int variant = id->variant;

  if (variant < 0)
    return 0;
  return ((id->collection->status[variant] & both) == both);
}

static struct rerere_id *new_rerere_id_hex(struct rerere_cache *cache,
             char *hex)
{
  struct rerere_id *id = xmalloc(sizeof(*id));
  id->collection = find_rerere_dir(cache, hex);
  id->variant = -1; /* not known yet */
  return id;
}

static struct rerere_id *new_rerere_id(struct rerere_cache *cache, unsigned char *hash)
{
  return new_rerere_id_hex(cache, hash_to_hex_algop(hash, cache->repo->hash_algo));
}

/*
 * $GIT_DIR/MERGE_RR file is a collection of records, each of which is
 * "conflict ID", a HT and pathname, terminated with a NUL, and is
 * used to keep track of the set of paths that "rerere" may need to
 * work on (i.e. what is left by the previous invocation of "git
 * rerere" during the current conflict resolution session).
 */
static void read_rr(struct rerere_cache *cache, struct string_list *rr)
{
  struct strbuf buf = STRBUF_INIT;
  FILE *in = fopen_or_warn(git_path_merge_rr(cache->repo), "r");

  if (!in)
    return;
  while (!strbuf_getwholeline(&buf, in, '\0')) {
    char *path;
    unsigned char hash[GIT_MAX_RAWSZ];
    struct rerere_id *id;
    int variant;
    const unsigned hexsz = cache->repo->hash_algo->hexsz;

    /* There has to be the hash, tab, path and then NUL */
    if (buf.len < hexsz + 2 ||
        get_hash_hex_algop(buf.buf, hash, cache->repo->hash_algo))
      die(_("corrupt MERGE_RR"));

    if (buf.buf[hexsz] != '.') {
      variant = 0;
      path = buf.buf + hexsz;
    } else {
      errno = 0;
      variant = strtol(buf.buf + hexsz + 1, &path, 10);
      if (errno)
        die(_("corrupt MERGE_RR"));
    }
    if (*(path++) != '\t')
      die(_("corrupt MERGE_RR"));
    buf.buf[hexsz] = '\0';
    id = new_rerere_id_hex(cache, buf.buf);
    id->variant = variant;
    /*
     * make sure id->collection->status has enough space
     * for the variant we are interested in
     */
    fit_variant(id->collection, variant);
    string_list_insert(rr, path)->util = id;
  }
  strbuf_release(&buf);
  fclose(in);
}

static int write_rr(struct rerere_cache *cache,
        struct string_list *rr, int out_fd)
{
  int i;
  for (i = 0; i < rr->nr; i++) {
    struct strbuf buf = STRBUF_INIT;
    struct rerere_id *id;

    assert(rr->items[i].util != RERERE_RESOLVED);

    id = rr->items[i].util;
    if (!id)
      continue;
    assert(id->variant >= 0);
    if (0 < id->variant)
      strbuf_addf(&buf, "%s.%d\t%s%c",
            rerere_id_hex(id), id->variant,
            rr->items[i].string, 0);
    else
      strbuf_addf(&buf, "%s\t%s%c",
            rerere_id_hex(id),
            rr->items[i].string, 0);

    if (write_in_full(out_fd, buf.buf, buf.len) < 0)
      die(_("unable to write rerere record"));

    strbuf_release(&buf);
  }
  if (commit_lock_file(&cache->write_lock) != 0)
    die(_("unable to write rerere record"));
  return 0;
}

/*
 * "rerere" interacts with conflicted file contents using this I/O
 * abstraction.  It reads a conflicted contents from one place via
 * "getline()" method, and optionally can write it out after
 * normalizing the conflicted hunks to the "output".  Subclasses of
 * rerere_io embed this structure at the beginning of their own
 * rerere_io object.
 */
struct rerere_io {
  int (*getline)(struct strbuf *, struct rerere_io *);
  FILE *output;
  int wrerror;
  /* some more stuff */
};

static void ferr_write(const void *p, size_t count, FILE *fp, int *err)
{
  if (!count || *err)
    return;
  if (fwrite(p, count, 1, fp) != 1)
    *err = errno;
}

static inline void ferr_puts(const char *s, FILE *fp, int *err)
{
  ferr_write(s, strlen(s), fp, err);
}

static void rerere_io_putstr(const char *str, struct rerere_io *io)
{
  if (io->output)
    ferr_puts(str, io->output, &io->wrerror);
}

static void rerere_io_putmem(const char *mem, size_t sz, struct rerere_io *io)
{
  if (io->output)
    ferr_write(mem, sz, io->output, &io->wrerror);
}

/*
 * Subclass of rerere_io that reads from an on-disk file
 */
struct rerere_io_file {
  struct rerere_io io;
  FILE *input;
};

/*
 * ... and its getline() method implementation
 */
static int rerere_file_getline(struct strbuf *sb, struct rerere_io *io_)
{
  struct rerere_io_file *io = (struct rerere_io_file *)io_;
  return strbuf_getwholeline(sb, io->input, '\n');
}

static void rerere_strbuf_putconflict(struct strbuf *buf, int ch, size_t size)
{
  strbuf_addchars(buf, ch, size);
  strbuf_addch(buf, '\n');
}

static int handle_conflict(struct strbuf *out, struct rerere_io *io,
         int marker_size, struct git_hash_ctx *ctx)
{
  enum {
    RR_SIDE_1 = 0, RR_SIDE_2, RR_ORIGINAL
  } hunk = RR_SIDE_1;
  struct strbuf one = STRBUF_INIT, two = STRBUF_INIT;
  struct strbuf buf = STRBUF_INIT, conflict = STRBUF_INIT;
  int has_conflicts = -1;

  while (!io->getline(&buf, io)) {
    int marker = is_conflict_marker_line(buf.buf, buf.len, marker_size);
    if (marker == '<') {
      if (handle_conflict(&conflict, io, marker_size, NULL) < 0)
        break;
      if (hunk == RR_SIDE_1)
        strbuf_addbuf(&one, &conflict);
      else
        strbuf_addbuf(&two, &conflict);
      strbuf_release(&conflict);
    } else if (marker == '|') {
      if (hunk != RR_SIDE_1)
        break;
      hunk = RR_ORIGINAL;
    } else if (marker == '=') {
      if (hunk != RR_SIDE_1 && hunk != RR_ORIGINAL)
        break;
      hunk = RR_SIDE_2;
    } else if (marker == '>') {
      if (hunk != RR_SIDE_2)
        break;
      if (strbuf_cmp(&one, &two) > 0)
        strbuf_swap(&one, &two);
      has_conflicts = 1;
      rerere_strbuf_putconflict(out, '<', marker_size);
      strbuf_addbuf(out, &one);
      rerere_strbuf_putconflict(out, '=', marker_size);
      strbuf_addbuf(out, &two);
      rerere_strbuf_putconflict(out, '>', marker_size);
      if (ctx) {
        git_hash_update(ctx, one.buf, one.len + 1);
        git_hash_update(ctx, two.buf, two.len + 1);
      }
      break;
    } else if (hunk == RR_SIDE_1)
      strbuf_addbuf(&one, &buf);
    else if (hunk == RR_ORIGINAL)
      ; /* discard */
    else if (hunk == RR_SIDE_2)
      strbuf_addbuf(&two, &buf);
  }
  strbuf_release(&one);
  strbuf_release(&two);
  strbuf_release(&buf);

  return has_conflicts;
}

/*
 * Read contents a file with conflicts, normalize the conflicts
 * by (1) discarding the common ancestor version in diff3-style,
 * (2) reordering our side and their side so that whichever sorts
 * alphabetically earlier comes before the other one, while
 * computing the "conflict ID", which is just an SHA-1 hash of
 * one side of the conflict, NUL, the other side of the conflict,
 * and NUL concatenated together.
 *
 * Return 1 if conflict hunks are found, 0 if there are no conflict
 * hunks and -1 if an error occurred.
 */
static int handle_path(struct repository *r,
           unsigned char *hash, struct rerere_io *io, int marker_size)
{
  struct git_hash_ctx ctx;
  struct strbuf buf = STRBUF_INIT, out = STRBUF_INIT;
  int has_conflicts = 0;
  if (hash)
    git_hash_init(&ctx, r->hash_algo);

  while (!io->getline(&buf, io)) {
    if (is_conflict_marker_line(buf.buf, buf.len, marker_size) == '<') {
      has_conflicts = handle_conflict(&out, io, marker_size,
              hash ? &ctx : NULL);
      if (has_conflicts < 0)
        break;
      rerere_io_putmem(out.buf, out.len, io);
      strbuf_reset(&out);
    } else
      rerere_io_putstr(buf.buf, io);
  }
  strbuf_release(&buf);
  strbuf_release(&out);

  if (hash)
    git_hash_final(hash, &ctx);

  return has_conflicts;
}

/*
 * Scan the path for conflicts, do the "handle_path()" thing above, and
 * return the number of conflict hunks found.
 */
static int handle_file(struct index_state *istate,
           const char *path, unsigned char *hash, const char *output)
{
  int has_conflicts = 0;
  struct rerere_io_file io;
  int marker_size = ll_merge_marker_size(istate, path);

  memset(&io, 0, sizeof(io));
  io.io.getline = rerere_file_getline;
  io.input = fopen(path, "r");
  io.io.wrerror = 0;
  if (!io.input)
    return error_errno(_("could not open '%s'"), path);

  if (output) {
    io.io.output = fopen(output, "w");
    if (!io.io.output) {
      error_errno(_("could not write '%s'"), output);
      fclose(io.input);
      return -1;
    }
  }

  has_conflicts = handle_path(istate->repo, hash, (struct rerere_io *)&io, marker_size);

  fclose(io.input);
  if (io.io.wrerror)
    error(_("there were errors while writing '%s' (%s)"),
          path, strerror(io.io.wrerror));
  if (io.io.output && fclose(io.io.output))
    io.io.wrerror = error_errno(_("failed to flush '%s'"), path);

  if (has_conflicts < 0) {
    if (output)
      unlink_or_warn(output);
    return error(_("could not parse conflict hunks in '%s'"), path);
  }
  if (io.io.wrerror) {
    if (output)
      unlink_or_warn(output);
    return -1;
  }
  return has_conflicts;
}

/*
 * Look at a cache entry at "i" and see if it is not conflicting,
 * conflicting and we are willing to handle, or conflicting and
 * we are unable to handle, and return the determination in *type.
 * Return the cache index to be looked at next, by skipping the
 * stages we have already looked at in this invocation of this
 * function.
 */
static int check_one_conflict(struct index_state *istate, int i, int *type)
{
  const struct cache_entry *e = istate->cache[i];

  if (!ce_stage(e)) {
    *type = RESOLVED;
    return i + 1;
  }

  *type = PUNTED;
  while (i < istate->cache_nr && ce_stage(istate->cache[i]) == 1)
    i++;

  /* Only handle regular files with both stages #2 and #3 */
  if (i + 1 < istate->cache_nr) {
    const struct cache_entry *e2 = istate->cache[i];
    const struct cache_entry *e3 = istate->cache[i + 1];
    if (ce_stage(e2) == 2 &&
        ce_stage(e3) == 3 &&
        ce_same_name(e, e3) &&
        S_ISREG(e2->ce_mode) &&
        S_ISREG(e3->ce_mode))
      *type = THREE_STAGED;
  }

  /* Skip the entries with the same name */
  while (i < istate->cache_nr && ce_same_name(e, istate->cache[i]))
    i++;
  return i;
}

/*
 * Scan the index and find paths that have conflicts that rerere can
 * handle, i.e. the ones that have both stages #2 and #3.
 *
 * NEEDSWORK: we do not record or replay a previous "resolve by
 * deletion" for a delete-modify conflict, as that is inherently risky
 * without knowing what modification is being discarded.  The only
 * safe case, i.e. both side doing the deletion and modification that
 * are identical to the previous round, might want to be handled,
 * though.
 */
static int find_conflict(struct repository *r, struct string_list *conflict)
{
  int i;

  if (repo_read_index(r) < 0)
    return error(_("index file corrupt"));

  for (i = 0; i < r->index->cache_nr;) {
    int conflict_type;
    const struct cache_entry *e = r->index->cache[i];
    i = check_one_conflict(r->index, i, &conflict_type);
    if (conflict_type == THREE_STAGED)
      string_list_insert(conflict, (const char *)e->name);
  }
  return 0;
}

/*
 * The merge_rr list is meant to hold outstanding conflicted paths
 * that rerere could handle.  Abuse the list by adding other types of
 * entries to allow the caller to show "rerere remaining".
 *
 * - Conflicted paths that rerere does not handle are added
 * - Conflicted paths that have been resolved are marked as such
 *   by storing RERERE_RESOLVED to .util field (where conflict ID
 *   is expected to be stored).
 *
 * Do *not* write MERGE_RR file out after calling this function.
 *
 * NEEDSWORK: we may want to fix the caller that implements "rerere
 * remaining" to do this without abusing merge_rr.
 */
int rerere_remaining(struct repository *r, struct string_list *merge_rr)
{
  struct rerere_cache cache;
  int ret, i;

  if (rerere_cache_setup(&cache, r, merge_rr, RERERE_READONLY))
    return 0;
  if (repo_read_index(r) < 0) {
    ret = error(_("index file corrupt"));
    goto out;
  }

  for (i = 0; i < r->index->cache_nr;) {
    int conflict_type;
    const struct cache_entry *e = r->index->cache[i];
    i = check_one_conflict(r->index, i, &conflict_type);
    if (conflict_type == PUNTED)
      string_list_insert(merge_rr, (const char *)e->name);
    else if (conflict_type == RESOLVED) {
      struct string_list_item *it;
      it = string_list_lookup(merge_rr, (const char *)e->name);
      if (it) {
        free_rerere_id(it);
        it->util = RERERE_RESOLVED;
      }
    }
  }

  ret = 0;

out:
  rerere_cache_release(&cache);
  return ret;
}

/*
 * Try using the given conflict resolution "ID" to see
 * if that recorded conflict resolves cleanly what we
 * got in the "cur".
 */
static int try_merge(struct index_state *istate,
         const struct rerere_id *id, const char *path,
         mmfile_t *cur, mmfile_t *result)
{
  enum ll_merge_result ret;
  mmfile_t base = {NULL, 0}, other = {NULL, 0};
  struct strbuf buf = STRBUF_INIT;

  if (read_mmfile(&base, rerere_path(istate->repo, &buf, id, "preimage")) ||
      read_mmfile(&other, rerere_path(istate->repo, &buf, id, "postimage"))) {
    ret = LL_MERGE_CONFLICT;
  } else {
    /*
     * A three-way merge. Note that this honors user-customizable
     * low-level merge driver settings.
     */
    ret = ll_merge(result, path, &base, NULL, cur, "", &other, "",
             istate, NULL);
  }

  strbuf_release(&buf);
  free(base.ptr);
  free(other.ptr);

  return ret;
}

/*
 * Find the conflict identified by "id"; the change between its
 * "preimage" (i.e. a previous contents with conflict markers) and its
 * "postimage" (i.e. the corresponding contents with conflicts
 * resolved) may apply cleanly to the contents stored in "path", i.e.
 * the conflict this time around.
 *
 * Returns 0 for successful replay of recorded resolution, or non-zero
 * for failure.
 */
static int merge(struct index_state *istate, const struct rerere_id *id, const char *path)
{
  FILE *f;
  int ret;
  struct strbuf buf = STRBUF_INIT;
  mmfile_t cur = {NULL, 0};
  mmfile_t result = {NULL, 0};

  /*
   * Normalize the conflicts in path and write it out to
   * "thisimage" temporary file.
   */
  if ((handle_file(istate, path, NULL, rerere_path(istate->repo, &buf, id, "thisimage")) < 0) ||
      read_mmfile(&cur, rerere_path(istate->repo, &buf, id, "thisimage"))) {
    ret = 1;
    goto out;
  }

  ret = try_merge(istate, id, path, &cur, &result);
  if (ret)
    goto out;

  /*
   * A successful replay of recorded resolution.
   * Mark that "postimage" was used to help gc.
   */
  if (utime(rerere_path(istate->repo, &buf, id, "postimage"), NULL) < 0)
    warning_errno(_("failed utime() on '%s'"),
            rerere_path(istate->repo, &buf, id, "postimage"));

  /* Update "path" with the resolution */
  f = fopen(path, "w");
  if (!f)
    return error_errno(_("could not open '%s'"), path);
  if (fwrite(result.ptr, result.size, 1, f) != 1)
    error_errno(_("could not write '%s'"), path);
  if (fclose(f))
    return error_errno(_("writing '%s' failed"), path);

out:
  free(cur.ptr);
  free(result.ptr);
  strbuf_release(&buf);

  return ret;
}

static void update_paths(struct repository *r, struct string_list *update)
{
  struct lock_file index_lock = LOCK_INIT;
  int i;

  repo_hold_locked_index(r, &index_lock, LOCK_DIE_ON_ERROR);

  for (i = 0; i < update->nr; i++) {
    struct string_list_item *item = &update->items[i];
    if (add_file_to_index(r->index, item->string, 0))
      exit(128);
    fprintf_ln(stderr, _("Staged '%s' using previous resolution."),
      item->string);
  }

  if (write_locked_index(r->index, &index_lock,
             COMMIT_LOCK | SKIP_IF_UNCHANGED))
    die(_("unable to write new index file"));
}

static void remove_variant(struct repository *r, struct rerere_id *id)
{
  struct strbuf buf = STRBUF_INIT;
  unlink_or_warn(rerere_path(r, &buf, id, "postimage"));
  unlink_or_warn(rerere_path(r, &buf, id, "preimage"));
  id->collection->status[id->variant] = 0;
  strbuf_release(&buf);
}

/*
 * The path indicated by rr_item may still have conflict for which we
 * have a recorded resolution, in which case replay it and optionally
 * update it.  Or it may have been resolved by the user and we may
 * only have the preimage for that conflict, in which case the result
 * needs to be recorded as a resolution in a postimage file.
 */
static void do_rerere_one_path(struct rerere_cache *cache,
             struct string_list_item *rr_item,
             struct string_list *update)
{
  struct index_state *istate = cache->repo->index;
  const char *path = rr_item->string;
  struct rerere_id *id = rr_item->util;
  struct rerere_dir *rr_dir = id->collection;
  struct strbuf buf = STRBUF_INIT;
  int variant;

  variant = id->variant;

  /* Has the user resolved it already? */
  if (variant >= 0) {
    int ret = handle_file(istate, path, NULL, NULL);

    if (ret < 0)
      goto out;
    if (!ret) {
      const int had_postimage =
        id->collection->status[variant] & RR_HAS_POSTIMAGE;
      const char *postimage =
        rerere_path(istate->repo, &buf, id, "postimage");

      if (copy_file(istate->repo,
              postimage,
              path, 0666)) {
        if (!had_postimage)
          unlink_or_warn(postimage);
        error_errno(_("could not copy resolution for '%s'"),
              path);
        goto out;
      }
      id->collection->status[variant] |= RR_HAS_POSTIMAGE;
      fprintf_ln(stderr, _("Recorded resolution for '%s'."), path);
      free_rerere_id(rr_item);
      rr_item->util = NULL;
      goto out;
    }
    /*
     * There may be other variants that can cleanly
     * replay.  Try them and update the variant number for
     * this one.
     */
  }

  /* Does any existing resolution apply cleanly? */
  for (variant = 0; variant < rr_dir->status_nr; variant++) {
    const int both = RR_HAS_PREIMAGE | RR_HAS_POSTIMAGE;
    struct rerere_id vid = *id;

    if ((rr_dir->status[variant] & both) != both)
      continue;

    vid.variant = variant;
    if (merge(istate, &vid, path))
      continue; /* failed to replay */

    /*
     * If there already is a different variant that applies
     * cleanly, there is no point maintaining our own variant.
     */
    if (0 <= id->variant && id->variant != variant)
      remove_variant(istate->repo, id);

    if (cache->autoupdate)
      string_list_insert(update, path);
    else
      fprintf_ln(stderr,
           _("Resolved '%s' using previous resolution."),
           path);
    free_rerere_id(rr_item);
    rr_item->util = NULL;
    goto out;
  }

  /* None of the existing one applies; we need a new variant */
  assign_variant(id);

  variant = id->variant;
  if (handle_file(istate, path, NULL,
      rerere_path(istate->repo, &buf, id, "preimage")) < 0)
    goto out;
  if (id->collection->status[variant] & RR_HAS_POSTIMAGE) {
    const char *path = rerere_path(istate->repo, &buf, id, "postimage");
    if (unlink(path))
      die_errno(_("cannot unlink stray '%s'"), path);
    id->collection->status[variant] &= ~RR_HAS_POSTIMAGE;
  }
  id->collection->status[variant] |= RR_HAS_PREIMAGE;
  fprintf_ln(stderr, _("Recorded preimage for '%s'"), path);

out:
  strbuf_release(&buf);
}

static int do_plain_rerere(struct rerere_cache *cache,
         struct string_list *rr, int fd)
{
  struct string_list conflict = STRING_LIST_INIT_DUP;
  struct string_list update = STRING_LIST_INIT_DUP;
  struct strbuf buf = STRBUF_INIT;
  struct repository *r = cache->repo;
  int i;

  find_conflict(r, &conflict);

  /*
   * MERGE_RR records paths with conflicts immediately after
   * merge failed.  Some of the conflicted paths might have been
   * hand resolved in the working tree since then, but the
   * initial run would catch all and register their preimages.
   */
  for (i = 0; i < conflict.nr; i++) {
    struct rerere_id *id;
    unsigned char hash[GIT_MAX_RAWSZ];
    const char *path = conflict.items[i].string;
    int ret;

    /*
     * Ask handle_file() to scan and assign a
     * conflict ID.  No need to write anything out
     * yet.
     */
    ret = handle_file(r->index, path, hash, NULL);
    if (ret != 0 && string_list_has_string(rr, path)) {
      remove_variant(r, string_list_lookup(rr, path)->util);
      string_list_remove(rr, path, 1);
    }
    if (ret < 1)
      continue;

    id = new_rerere_id(cache, hash);
    string_list_insert(rr, path)->util = id;

    /* Ensure that the directory exists. */
    safe_create_dir_in_gitdir(r, rerere_path(r, &buf, id, NULL));
  }

  for (i = 0; i < rr->nr; i++)
    do_rerere_one_path(cache, &rr->items[i], &update);

  if (update.nr)
    update_paths(r, &update);

  string_list_clear(&conflict, 0);
  string_list_clear(&update, 0);
  strbuf_release(&buf);
  return write_rr(cache, rr, fd);
}

static int is_rerere_enabled(struct repository *r)
{
  int rr_cache_exists;
  char *dir;

  if (r->rerere_cache_enabled != -1)
    return r->rerere_cache_enabled;

  repo_config_get_bool(r, "rerere.enabled", &r->rerere_cache_enabled);
  if (!r->rerere_cache_enabled)
    return 0;

  dir = repo_git_path(r, "rr-cache");

  rr_cache_exists = is_directory(dir);
  if (r->rerere_cache_enabled < 0) {
    r->rerere_cache_enabled = rr_cache_exists;
    goto out;
  }

  if (!rr_cache_exists &&
      safe_create_dir_in_gitdir(r, dir))
    die(_("could not create directory '%s'"), dir);
  r->rerere_cache_enabled = 1;

out:
  free(dir);
  return r->rerere_cache_enabled;
}

int rerere_cache_setup(struct rerere_cache *cache,
           struct repository *r,
           struct string_list *merge_rr,
           int flags)
{
  int lock_timeout_ms = 1000;
  int fd;

  if (!is_rerere_enabled(r))
    return -1;

  memset(cache, 0, sizeof(*cache));
  cache->repo = r;
  strmap_init(&cache->dirs);
  repo_config_get_bool(r, "rerere.autoupdate", &cache->autoupdate);
  repo_config_get_int(r, "rerere.locktimeout", &lock_timeout_ms);

  if (flags & (RERERE_AUTOUPDATE|RERERE_NOAUTOUPDATE))
    cache->autoupdate = !!(flags & RERERE_AUTOUPDATE);
  if ((flags & RERERE_READONLY) && (flags & RERERE_NOWAIT))
    BUG("RERERE_NOWAIT does not apply with RERERE_READONLY");
  if (flags & RERERE_READONLY) {
    fd = 0;
  } else {
    int lock_flags = LOCK_DIE_ON_ERROR;

    if (flags & RERERE_NOWAIT) {
      lock_flags = 0;
      lock_timeout_ms = 0;
    }

    /*
     * Another process may hold the lock for a while, e.g.
     * "git rerere gc" while it prunes rr-cache, so by default
     * wait for it instead of dying right away.
     */
    fd = repo_hold_lock_file_for_update_timeout(r, &cache->write_lock,
                  git_path_merge_rr(r),
                  lock_flags, lock_timeout_ms);
    if (fd < 0)
      return -1;
  }
  read_rr(cache, merge_rr);
  return fd;
}

/*
 * The main entry point that is called internally from codepaths that
 * perform mergy operations, possibly leaving conflicted index entries
 * and working tree files.
 */
int repo_rerere(struct repository *r, int flags)
{
  struct string_list merge_rr = STRING_LIST_INIT_DUP;
  struct rerere_cache cache;
  int fd, status;

  fd = rerere_cache_setup(&cache, r, &merge_rr, flags);
  if (fd < 0)
    return 0;
  status = do_plain_rerere(&cache, &merge_rr, fd);

  rerere_cache_release(&cache);
  string_list_clear(&merge_rr, 1);
  return status;
}

/*
 * Subclass of rerere_io that reads from an in-core buffer that is a
 * strbuf
 */
struct rerere_io_mem {
  struct rerere_io io;
  struct strbuf input;
};

/*
 * ... and its getline() method implementation
 */
static int rerere_mem_getline(struct strbuf *sb, struct rerere_io *io_)
{
  struct rerere_io_mem *io = (struct rerere_io_mem *)io_;
  char *ep;
  size_t len;

  strbuf_release(sb);
  if (!io->input.len)
    return -1;
  ep = memchr(io->input.buf, '\n', io->input.len);
  if (!ep)
    ep = io->input.buf + io->input.len;
  else if (*ep == '\n')
    ep++;
  len = ep - io->input.buf;
  strbuf_add(sb, io->input.buf, len);
  strbuf_remove(&io->input, 0, len);
  return 0;
}

static int handle_cache(struct index_state *istate,
      const char *path, unsigned char *hash, const char *output)
{
  mmfile_t mmfile[3] = {{NULL}};
  mmfile_t result = {NULL, 0};
  const struct cache_entry *ce;
  int pos, len, i, has_conflicts;
  struct rerere_io_mem io;
  int marker_size = ll_merge_marker_size(istate, path);

  /*
   * Reproduce the conflicted merge in-core
   */
  len = strlen(path);
  pos = index_name_pos(istate, path, len);
  if (0 <= pos)
    return -1;
  pos = -pos - 1;

  while (pos < istate->cache_nr) {
    enum object_type type;
    size_t size;

    ce = istate->cache[pos++];
    if (ce_namelen(ce) != len || memcmp(ce->name, path, len))
      break;
    i = ce_stage(ce) - 1;
    if (!mmfile[i].ptr) {
      mmfile[i].ptr = odb_read_object(istate->repo->objects,
              &ce->oid, &type, &size);
      if (!mmfile[i].ptr)
        die(_("unable to read %s"),
            oid_to_hex(&ce->oid));
      mmfile[i].size = size;
    }
  }
  for (i = 0; i < 3; i++)
    if (!mmfile[i].ptr && !mmfile[i].size)
      mmfile[i].ptr = xstrdup("");

  /*
   * NEEDSWORK: handle conflicts from merges with
   * merge.renormalize set, too?
   */
  ll_merge(&result, path, &mmfile[0], NULL,
     &mmfile[1], "ours",
     &mmfile[2], "theirs",
     istate, NULL);
  for (i = 0; i < 3; i++)
    free(mmfile[i].ptr);

  memset(&io, 0, sizeof(io));
  io.io.getline = rerere_mem_getline;
  if (output)
    io.io.output = fopen(output, "w");
  else
    io.io.output = NULL;
  strbuf_init(&io.input, 0);
  strbuf_attach(&io.input, result.ptr, result.size, result.size);

  /*
   * Grab the conflict ID and optionally write the original
   * contents with conflict markers out.
   */
  has_conflicts = handle_path(istate->repo, hash,
            (struct rerere_io *)&io, marker_size);
  strbuf_release(&io.input);
  if (io.io.output)
    fclose(io.io.output);
  return has_conflicts;
}

static int rerere_forget_one_path(struct rerere_cache *cache,
          const char *path,
          struct string_list *rr)
{
  struct index_state *istate = cache->repo->index;
  const char *filename;
  struct rerere_id *id;
  unsigned char hash[GIT_MAX_RAWSZ];
  int ret;
  struct strbuf buf = STRBUF_INIT;
  struct string_list_item *item;

  /*
   * Recreate the original conflict from the stages in the
   * index and compute the conflict ID
   */
  ret = handle_cache(istate, path, hash, NULL);
  if (ret < 1)
    return error(_("could not parse conflict hunks in '%s'"), path);

  /* Nuke the recorded resolution for the conflict */
  id = new_rerere_id(cache, hash);

  for (id->variant = 0;
       id->variant < id->collection->status_nr;
       id->variant++) {
    mmfile_t cur;
    mmfile_t result = {NULL, 0};
    int cleanly_resolved;

    if (!has_rerere_resolution(id))
      continue;

    handle_cache(istate, path, hash, rerere_path(istate->repo, &buf, id, "thisimage"));
    if (read_mmfile(&cur, rerere_path(istate->repo, &buf, id, "thisimage"))) {
      error(_("failed to update conflicted state in '%s'"), path);
      goto fail_exit;
    }
    cleanly_resolved = !try_merge(istate, id, path, &cur, &result);
    free(result.ptr);
    free(cur.ptr);
    if (cleanly_resolved)
      break;
  }

  if (id->collection->status_nr <= id->variant) {
    error(_("no remembered resolution for '%s'"), path);
    goto fail_exit;
  }

  filename = rerere_path(istate->repo, &buf, id, "postimage");
  if (unlink(filename)) {
    if (errno == ENOENT)
      error(_("no remembered resolution for '%s'"), path);
    else
      error_errno(_("cannot unlink '%s'"), filename);
    goto fail_exit;
  }

  /*
   * Update the preimage so that the user can resolve the
   * conflict in the working tree, run us again to record
   * the postimage.
   */
  handle_cache(istate, path, hash, rerere_path(istate->repo, &buf, id, "preimage"));
  fprintf_ln(stderr, _("Updated preimage for '%s'"), path);

  /*
   * And remember that we can record resolution for this
   * conflict when the user is done.
   */
  item = string_list_insert(rr, path);
  free_rerere_id(item);
  item->util = id;
  fprintf(stderr, _("Forgot resolution for '%s'\n"), path);
  strbuf_release(&buf);
  return 0;

fail_exit:
  strbuf_release(&buf);
  free(id);
  return -1;
}

int rerere_forget(struct repository *r, struct pathspec *pathspec)
{
  int i, fd, ret;
  struct string_list conflict = STRING_LIST_INIT_DUP;
  struct string_list merge_rr = STRING_LIST_INIT_DUP;
  struct rerere_cache cache;

  if (repo_read_index(r) < 0)
    return error(_("index file corrupt"));

  fd = rerere_cache_setup(&cache, r, &merge_rr, RERERE_NOAUTOUPDATE);
  if (fd < 0)
    return 0;

  /*
   * The paths may have been resolved (incorrectly);
   * recover the original conflicted state and then
   * find the conflicted paths.
   */
  unmerge_index(r->index, pathspec, 0);
  find_conflict(r, &conflict);
  for (i = 0; i < conflict.nr; i++) {
    struct string_list_item *it = &conflict.items[i];
    if (!match_pathspec(r->index, pathspec, it->string,
            strlen(it->string), 0, NULL, 0))
      continue;
    rerere_forget_one_path(&cache, it->string, &merge_rr);
  }

  ret = write_rr(&cache, &merge_rr, fd);

  string_list_clear(&conflict, 0);
  string_list_clear(&merge_rr, 1);
  rerere_cache_release(&cache);
  return ret;
}

/*
 * Garbage collection support
 */

static timestamp_t rerere_created_at(struct repository *r, struct rerere_id *id)
{
  struct strbuf buf = STRBUF_INIT;
  struct stat st;
  timestamp_t ret;

  ret = stat(rerere_path(r, &buf, id, "preimage"), &st) ? (time_t) 0 : st.st_mtime;

  strbuf_release(&buf);
  return ret;
}

static timestamp_t rerere_last_used_at(struct repository *r, struct rerere_id *id)
{
  struct strbuf buf = STRBUF_INIT;
  struct stat st;
  timestamp_t ret;

  ret = stat(rerere_path(r, &buf, id, "postimage"), &st) ? (time_t) 0 : st.st_mtime;

  strbuf_release(&buf);
  return ret;
}

/*
 * Remove the recorded resolution for a given conflict ID
 */
static void unlink_rr_item(struct repository *r, struct rerere_id *id)
{
  struct strbuf buf = STRBUF_INIT;
  unlink_or_warn(rerere_path(r, &buf, id, "thisimage"));
  remove_variant(r, id);
  id->collection->status[id->variant] = 0;
  strbuf_release(&buf);
}

static void rerere_gc_cutoffs(struct repository *r,
            timestamp_t *cutoff_resolve,
            timestamp_t *cutoff_noresolve)
{
  timestamp_t now = time(NULL);

  if (repo_config_get_expiry_in_days(r, "gc.rerereresolved",
             cutoff_resolve, now))
    *cutoff_resolve = now - 60 * 86400;
  if (repo_config_get_expiry_in_days(r, "gc.rerereunresolved",
             cutoff_noresolve, now))
    *cutoff_noresolve = now - 15 * 86400;
}

static bool rerere_id_is_stale(struct repository *r,
             struct rerere_id *id,
             timestamp_t cutoff_resolve,
             timestamp_t cutoff_noresolve)
{
  timestamp_t then;
  timestamp_t cutoff;

  then = rerere_last_used_at(r, id);
  if (then) {
    cutoff = cutoff_resolve;
  } else {
    then = rerere_created_at(r, id);
    if (!then)
      return false;
    cutoff = cutoff_noresolve;
  }

  return then < cutoff;
}

static void prune_one(struct repository *r, struct rerere_id *id,
          timestamp_t cutoff_resolve, timestamp_t cutoff_noresolve)
{
  if (rerere_id_is_stale(r, id, cutoff_resolve, cutoff_noresolve))
    unlink_rr_item(r, id);
}

/* Does the basename in "path" look plausibly like an rr-cache entry? */
static int is_rr_cache_dirname(struct repository *r, const char *path)
{
  struct object_id oid;
  const char *end;
  return !parse_oid_hex_algop(path, &oid, &end, r->hash_algo) && !*end;
}

bool rerere_gc_needed(struct repository *r, size_t limit)
{
  struct rerere_cache cache = {
    .repo = r,
    .dirs = STRMAP_INIT,
  };
  timestamp_t cutoff_resolve, cutoff_noresolve;
  struct strbuf buf = STRBUF_INIT;
  bool needed = false;
  struct dirent *e;
  size_t count = 0;
  DIR *dir;

  dir = opendir(repo_git_path_replace(r, &buf, "rr-cache"));
  if (!dir)
    goto out;

  rerere_gc_cutoffs(r, &cutoff_resolve, &cutoff_noresolve);

  while ((e = readdir_skip_dot_and_dotdot(dir))) {
    struct rerere_id id;

    /*
     * We estimate the number of stale entries by only considering
     * those starting with "17". This is the same strategy that we
     * use for estimating the number of loose objects.
     */
    if (!starts_with(e->d_name, "17") ||
        !is_rr_cache_dirname(r, e->d_name))
      continue;

    id.collection = find_rerere_dir(&cache, e->d_name);
    for (id.variant = 0;
         id.variant < id.collection->status_nr;
         id.variant++) {
      if (rerere_id_is_stale(r, &id, cutoff_resolve,
                 cutoff_noresolve)) {
        count += 256;
        if (count >= limit) {
          needed = true;
          goto out;
        }
      }
    }
  }

out:
  if (dir)
    closedir(dir);
  rerere_cache_release(&cache);
  strbuf_release(&buf);
  return needed;
}

void rerere_gc(struct repository *r, struct string_list *rr, int flags)
{
  struct rerere_cache cache;
  struct string_list to_remove = STRING_LIST_INIT_DUP;
  DIR *dir;
  struct dirent *e;
  int i;
  timestamp_t cutoff_noresolve;
  timestamp_t cutoff_resolve;
  struct strbuf buf = STRBUF_INIT;

  if (rerere_cache_setup(&cache, r, rr, flags) < 0)
    return;

  rerere_gc_cutoffs(r, &cutoff_resolve, &cutoff_noresolve);

  dir = opendir(repo_git_path_replace(r, &buf, "rr-cache"));
  if (!dir)
    die_errno(_("unable to open rr-cache directory"));
  /* Collect stale conflict IDs ... */
  while ((e = readdir_skip_dot_and_dotdot(dir))) {
    struct rerere_dir *rr_dir;
    struct rerere_id id;
    int now_empty;

    if (!is_rr_cache_dirname(r, e->d_name))
      continue; /* or should we remove e->d_name? */

    rr_dir = find_rerere_dir(&cache, e->d_name);

    now_empty = 1;
    for (id.variant = 0, id.collection = rr_dir;
         id.variant < id.collection->status_nr;
         id.variant++) {
      prune_one(r, &id, cutoff_resolve, cutoff_noresolve);
      if (id.collection->status[id.variant])
        now_empty = 0;
    }
    if (now_empty)
      string_list_append(&to_remove, e->d_name);
  }
  closedir(dir);

  /* ... and then remove the empty directories */
  for (i = 0; i < to_remove.nr; i++)
    rmdir(repo_git_path_replace(r, &buf,
              "rr-cache/%s", to_remove.items[i].string));

  string_list_clear(&to_remove, 0);
  rerere_cache_release(&cache);
  strbuf_release(&buf);
}

/*
 * During a conflict resolution, after "rerere" recorded the
 * preimages, abandon them if the user did not resolve them or
 * record their resolutions.  And drop $GIT_DIR/MERGE_RR.
 *
 * NEEDSWORK: shouldn't we be calling this from "reset --hard"?
 */
void rerere_clear(struct repository *r, struct string_list *merge_rr)
{
  struct rerere_cache cache;
  int i;

  if (rerere_cache_setup(&cache, r, merge_rr, 0) < 0)
    return;

  for (i = 0; i < merge_rr->nr; i++) {
    struct rerere_id *id = merge_rr->items[i].util;
    struct strbuf buf = STRBUF_INIT;

    if (!has_rerere_resolution(id)) {
      unlink_rr_item(r, id);
      rmdir(rerere_path(r, &buf, id, NULL));
    }

    strbuf_release(&buf);
  }
  unlink_or_warn(git_path_merge_rr(r));
  rerere_cache_release(&cache);
}

Coverage Report

Created: 2026-11-12 06:03