diff options
| -rw-r--r-- | merge-ort.c | 1248 | ||||
| -rw-r--r-- | merge-ort.h | 9 | ||||
| -rw-r--r-- | tree.c | 2 | ||||
| -rw-r--r-- | tree.h | 2 |
4 files changed, 1256 insertions, 5 deletions
diff --git a/merge-ort.c b/merge-ort.c index b487901d3e..51b049358e 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -17,20 +17,1260 @@ #include "cache.h" #include "merge-ort.h" +#include "cache-tree.h" +#include "diff.h" +#include "diffcore.h" +#include "dir.h" +#include "object-store.h" +#include "strmap.h" +#include "tree.h" +#include "unpack-trees.h" +#include "xdiff-interface.h" + +/* + * We have many arrays of size 3. Whenever we have such an array, the + * indices refer to one of the sides of the three-way merge. This is so + * pervasive that the constants 0, 1, and 2 are used in many places in the + * code (especially in arithmetic operations to find the other side's index + * or to compute a relevant mask), but sometimes these enum names are used + * to aid code clarity. + * + * See also 'filemask' and 'dirmask' in struct conflict_info; the "ith side" + * referred to there is one of these three sides. + */ +enum merge_side { + MERGE_BASE = 0, + MERGE_SIDE1 = 1, + MERGE_SIDE2 = 2 +}; + +struct merge_options_internal { + /* + * paths: primary data structure in all of merge ort. + * + * The keys of paths: + * * are full relative paths from the toplevel of the repository + * (e.g. "drivers/firmware/raspberrypi.c"). + * * store all relevant paths in the repo, both directories and + * files (e.g. drivers, drivers/firmware would also be included) + * * these keys serve to intern all the path strings, which allows + * us to do pointer comparison on directory names instead of + * strcmp; we just have to be careful to use the interned strings. + * + * The values of paths: + * * either a pointer to a merged_info, or a conflict_info struct + * * merged_info contains all relevant information for a + * non-conflicted entry. + * * conflict_info contains a merged_info, plus any additional + * information about a conflict such as the higher orders stages + * involved and the names of the paths those came from (handy + * once renames get involved). + * * a path may start "conflicted" (i.e. point to a conflict_info) + * and then a later step (e.g. three-way content merge) determines + * it can be cleanly merged, at which point it'll be marked clean + * and the algorithm will ignore any data outside the contained + * merged_info for that entry + * * If an entry remains conflicted, the merged_info portion of a + * conflict_info will later be filled with whatever version of + * the file should be placed in the working directory (e.g. an + * as-merged-as-possible variation that contains conflict markers). + */ + struct strmap paths; + + /* + * conflicted: a subset of keys->values from "paths" + * + * conflicted is basically an optimization between process_entries() + * and record_conflicted_index_entries(); the latter could loop over + * ALL the entries in paths AGAIN and look for the ones that are + * still conflicted, but since process_entries() has to loop over + * all of them, it saves the ones it couldn't resolve in this strmap + * so that record_conflicted_index_entries() can iterate just the + * relevant entries. + */ + struct strmap conflicted; + + /* + * current_dir_name: temporary var used in collect_merge_info_callback() + * + * Used to set merged_info.directory_name; see documentation for that + * variable and the requirements placed on that field. + */ + const char *current_dir_name; + + /* call_depth: recursion level counter for merging merge bases */ + int call_depth; +}; + +struct version_info { + struct object_id oid; + unsigned short mode; +}; + +struct merged_info { + /* if is_null, ignore result. otherwise result has oid & mode */ + struct version_info result; + unsigned is_null:1; + + /* + * clean: whether the path in question is cleanly merged. + * + * see conflict_info.merged for more details. + */ + unsigned clean:1; + + /* + * basename_offset: offset of basename of path. + * + * perf optimization to avoid recomputing offset of final '/' + * character in pathname (0 if no '/' in pathname). + */ + size_t basename_offset; + + /* + * directory_name: containing directory name. + * + * Note that we assume directory_name is constructed such that + * strcmp(dir1_name, dir2_name) == 0 iff dir1_name == dir2_name, + * i.e. string equality is equivalent to pointer equality. For this + * to hold, we have to be careful setting directory_name. + */ + const char *directory_name; +}; + +struct conflict_info { + /* + * merged: the version of the path that will be written to working tree + * + * WARNING: It is critical to check merged.clean and ensure it is 0 + * before reading any conflict_info fields outside of merged. + * Allocated merge_info structs will always have clean set to 1. + * Allocated conflict_info structs will have merged.clean set to 0 + * initially. The merged.clean field is how we know if it is safe + * to access other parts of conflict_info besides merged; if a + * conflict_info's merged.clean is changed to 1, the rest of the + * algorithm is not allowed to look at anything outside of the + * merged member anymore. + */ + struct merged_info merged; + + /* oids & modes from each of the three trees for this path */ + struct version_info stages[3]; + + /* pathnames for each stage; may differ due to rename detection */ + const char *pathnames[3]; + + /* Whether this path is/was involved in a directory/file conflict */ + unsigned df_conflict:1; + + /* + * For filemask and dirmask, the ith bit corresponds to whether the + * ith entry is a file (filemask) or a directory (dirmask). Thus, + * filemask & dirmask is always zero, and filemask | dirmask is at + * most 7 but can be less when a path does not appear as either a + * file or a directory on at least one side of history. + * + * Note that these masks are related to enum merge_side, as the ith + * entry corresponds to side i. + * + * These values come from a traverse_trees() call; more info may be + * found looking at tree-walk.h's struct traverse_info, + * particularly the documentation above the "fn" member (note that + * filemask = mask & ~dirmask from that documentation). + */ + unsigned filemask:3; + unsigned dirmask:3; + + /* + * Optimization to track which stages match, to avoid the need to + * recompute it in multiple steps. Either 0 or at least 2 bits are + * set; if at least 2 bits are set, their corresponding stages match. + */ + unsigned match_mask:3; +}; + +/* + * For the next three macros, see warning for conflict_info.merged. + * + * In each of the below, mi is a struct merged_info*, and ci was defined + * as a struct conflict_info* (but we need to verify ci isn't actually + * pointed at a struct merged_info*). + * + * INITIALIZE_CI: Assign ci to mi but only if it's safe; set to NULL otherwise. + * VERIFY_CI: Ensure that something we assigned to a conflict_info* is one. + * ASSIGN_AND_VERIFY_CI: Similar to VERIFY_CI but do assignment first. + */ +#define INITIALIZE_CI(ci, mi) do { \ + (ci) = (!(mi) || (mi)->clean) ? NULL : (struct conflict_info *)(mi); \ +} while (0) +#define VERIFY_CI(ci) assert(ci && !ci->merged.clean); +#define ASSIGN_AND_VERIFY_CI(ci, mi) do { \ + (ci) = (struct conflict_info *)(mi); \ + assert((ci) && !(mi)->clean); \ +} while (0) + +static void free_strmap_strings(struct strmap *map) +{ + struct hashmap_iter iter; + struct strmap_entry *entry; + + strmap_for_each_entry(map, &iter, entry) { + free((char*)entry->key); + } +} + +static int err(struct merge_options *opt, const char *err, ...) +{ + va_list params; + struct strbuf sb = STRBUF_INIT; + + strbuf_addstr(&sb, "error: "); + va_start(params, err); + strbuf_vaddf(&sb, err, params); + va_end(params); + + error("%s", sb.buf); + strbuf_release(&sb); + + return -1; +} + +static void setup_path_info(struct merge_options *opt, + struct string_list_item *result, + const char *current_dir_name, + int current_dir_name_len, + char *fullpath, /* we'll take over ownership */ + struct name_entry *names, + struct name_entry *merged_version, + unsigned is_null, /* boolean */ + unsigned df_conflict, /* boolean */ + unsigned filemask, + unsigned dirmask, + int resolved /* boolean */) +{ + /* result->util is void*, so mi is a convenience typed variable */ + struct merged_info *mi; + + assert(!is_null || resolved); + assert(!df_conflict || !resolved); /* df_conflict implies !resolved */ + assert(resolved == (merged_version != NULL)); + + mi = xcalloc(1, resolved ? sizeof(struct merged_info) : + sizeof(struct conflict_info)); + mi->directory_name = current_dir_name; + mi->basename_offset = current_dir_name_len; + mi->clean = !!resolved; + if (resolved) { + mi->result.mode = merged_version->mode; + oidcpy(&mi->result.oid, &merged_version->oid); + mi->is_null = !!is_null; + } else { + int i; + struct conflict_info *ci; + + ASSIGN_AND_VERIFY_CI(ci, mi); + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + ci->pathnames[i] = fullpath; + ci->stages[i].mode = names[i].mode; + oidcpy(&ci->stages[i].oid, &names[i].oid); + } + ci->filemask = filemask; + ci->dirmask = dirmask; + ci->df_conflict = !!df_conflict; + if (dirmask) + /* + * Assume is_null for now, but if we have entries + * under the directory then when it is complete in + * write_completed_directory() it'll update this. + * Also, for D/F conflicts, we have to handle the + * directory first, then clear this bit and process + * the file to see how it is handled -- that occurs + * near the top of process_entry(). + */ + mi->is_null = 1; + } + strmap_put(&opt->priv->paths, fullpath, mi); + result->string = fullpath; + result->util = mi; +} + +static int collect_merge_info_callback(int n, + unsigned long mask, + unsigned long dirmask, + struct name_entry *names, + struct traverse_info *info) +{ + /* + * n is 3. Always. + * common ancestor (mbase) has mask 1, and stored in index 0 of names + * head of side 1 (side1) has mask 2, and stored in index 1 of names + * head of side 2 (side2) has mask 4, and stored in index 2 of names + */ + struct merge_options *opt = info->data; + struct merge_options_internal *opti = opt->priv; + struct string_list_item pi; /* Path Info */ + struct conflict_info *ci; /* typed alias to pi.util (which is void*) */ + struct name_entry *p; + size_t len; + char *fullpath; + const char *dirname = opti->current_dir_name; + unsigned filemask = mask & ~dirmask; + unsigned match_mask = 0; /* will be updated below */ + unsigned mbase_null = !(mask & 1); + unsigned side1_null = !(mask & 2); + unsigned side2_null = !(mask & 4); + unsigned side1_matches_mbase = (!side1_null && !mbase_null && + names[0].mode == names[1].mode && + oideq(&names[0].oid, &names[1].oid)); + unsigned side2_matches_mbase = (!side2_null && !mbase_null && + names[0].mode == names[2].mode && + oideq(&names[0].oid, &names[2].oid)); + unsigned sides_match = (!side1_null && !side2_null && + names[1].mode == names[2].mode && + oideq(&names[1].oid, &names[2].oid)); + + /* + * Note: When a path is a file on one side of history and a directory + * in another, we have a directory/file conflict. In such cases, if + * the conflict doesn't resolve from renames and deletions, then we + * always leave directories where they are and move files out of the + * way. Thus, while struct conflict_info has a df_conflict field to + * track such conflicts, we ignore that field for any directories at + * a path and only pay attention to it for files at the given path. + * The fact that we leave directories were they are also means that + * we do not need to worry about getting additional df_conflict + * information propagated from parent directories down to children + * (unlike, say traverse_trees_recursive() in unpack-trees.c, which + * sets a newinfo.df_conflicts field specifically to propagate it). + */ + unsigned df_conflict = (filemask != 0) && (dirmask != 0); + + /* n = 3 is a fundamental assumption. */ + if (n != 3) + BUG("Called collect_merge_info_callback wrong"); + + /* + * A bunch of sanity checks verifying that traverse_trees() calls + * us the way I expect. Could just remove these at some point, + * though maybe they are helpful to future code readers. + */ + assert(mbase_null == is_null_oid(&names[0].oid)); + assert(side1_null == is_null_oid(&names[1].oid)); + assert(side2_null == is_null_oid(&names[2].oid)); + assert(!mbase_null || !side1_null || !side2_null); + assert(mask > 0 && mask < 8); + + /* Determine match_mask */ + if (side1_matches_mbase) + match_mask = (side2_matches_mbase ? 7 : 3); + else if (side2_matches_mbase) + match_mask = 5; + else if (sides_match) + match_mask = 6; + + /* + * Get the name of the relevant filepath, which we'll pass to + * setup_path_info() for tracking. + */ + p = names; + while (!p->mode) + p++; + len = traverse_path_len(info, p->pathlen); + + /* +1 in both of the following lines to include the NUL byte */ + fullpath = xmalloc(len + 1); + make_traverse_path(fullpath, len + 1, info, p->path, p->pathlen); + + /* + * If mbase, side1, and side2 all match, we can resolve early. Even + * if these are trees, there will be no renames or anything + * underneath. + */ + if (side1_matches_mbase && side2_matches_mbase) { + /* mbase, side1, & side2 all match; use mbase as resolution */ + setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, + names, names+0, mbase_null, 0, + filemask, dirmask, 1); + return mask; + } + + /* + * Record information about the path so we can resolve later in + * process_entries. + */ + setup_path_info(opt, &pi, dirname, info->pathlen, fullpath, + names, NULL, 0, df_conflict, filemask, dirmask, 0); + + ci = pi.util; + VERIFY_CI(ci); + ci->match_mask = match_mask; + + /* If dirmask, recurse into subdirectories */ + if (dirmask) { + struct traverse_info newinfo; + struct tree_desc t[3]; + void *buf[3] = {NULL, NULL, NULL}; + const char *original_dir_name; + int i, ret; + + ci->match_mask &= filemask; + newinfo = *info; + newinfo.prev = info; + newinfo.name = p->path; + newinfo.namelen = p->pathlen; + newinfo.pathlen = st_add3(newinfo.pathlen, p->pathlen, 1); + /* + * If this directory we are about to recurse into cared about + * its parent directory (the current directory) having a D/F + * conflict, then we'd propagate the masks in this way: + * newinfo.df_conflicts |= (mask & ~dirmask); + * But we don't worry about propagating D/F conflicts. (See + * comment near setting of local df_conflict variable near + * the beginning of this function). + */ + + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + if (i == 1 && side1_matches_mbase) + t[1] = t[0]; + else if (i == 2 && side2_matches_mbase) + t[2] = t[0]; + else if (i == 2 && sides_match) + t[2] = t[1]; + else { + const struct object_id *oid = NULL; + if (dirmask & 1) + oid = &names[i].oid; + buf[i] = fill_tree_descriptor(opt->repo, + t + i, oid); + } + dirmask >>= 1; + } + + original_dir_name = opti->current_dir_name; + opti->current_dir_name = pi.string; + ret = traverse_trees(NULL, 3, t, &newinfo); + opti->current_dir_name = original_dir_name; + + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) + free(buf[i]); + + if (ret < 0) + return -1; + } + + return mask; +} + +static int collect_merge_info(struct merge_options *opt, + struct tree *merge_base, + struct tree *side1, + struct tree *side2) +{ + int ret; + struct tree_desc t[3]; + struct traverse_info info; + const char *toplevel_dir_placeholder = ""; + + opt->priv->current_dir_name = toplevel_dir_placeholder; + setup_traverse_info(&info, toplevel_dir_placeholder); + info.fn = collect_merge_info_callback; + info.data = opt; + info.show_all_errors = 1; + + parse_tree(merge_base); + parse_tree(side1); + parse_tree(side2); + init_tree_desc(t + 0, merge_base->buffer, merge_base->size); + init_tree_desc(t + 1, side1->buffer, side1->size); + init_tree_desc(t + 2, side2->buffer, side2->size); + + ret = traverse_trees(NULL, 3, t, &info); + + return ret; +} + +static int detect_and_process_renames(struct merge_options *opt, + struct tree *merge_base, + struct tree *side1, + struct tree *side2) +{ + int clean = 1; + + /* + * Rename detection works by detecting file similarity. Here we use + * a really easy-to-implement scheme: files are similar IFF they have + * the same filename. Therefore, by this scheme, there are no renames. + * + * TODO: Actually implement a real rename detection scheme. + */ + return clean; +} + +static int string_list_df_name_compare(const char *one, const char *two) +{ + int onelen = strlen(one); + int twolen = strlen(two); + /* + * Here we only care that entries for D/F conflicts are + * adjacent, in particular with the file of the D/F conflict + * appearing before files below the corresponding directory. + * The order of the rest of the list is irrelevant for us. + * + * To achieve this, we sort with df_name_compare and provide + * the mode S_IFDIR so that D/F conflicts will sort correctly. + * We use the mode S_IFDIR for everything else for simplicity, + * since in other cases any changes in their order due to + * sorting cause no problems for us. + */ + int cmp = df_name_compare(one, onelen, S_IFDIR, + two, twolen, S_IFDIR); + /* + * Now that 'foo' and 'foo/bar' compare equal, we have to make sure + * that 'foo' comes before 'foo/bar'. + */ + if (cmp) + return cmp; + return onelen - twolen; +} + +struct directory_versions { + /* + * versions: list of (basename -> version_info) + * + * The basenames are in reverse lexicographic order of full pathnames, + * as processed in process_entries(). This puts all entries within + * a directory together, and covers the directory itself after + * everything within it, allowing us to write subtrees before needing + * to record information for the tree itself. + */ + struct string_list versions; + + /* + * offsets: list of (full relative path directories -> integer offsets) + * + * Since versions contains basenames from files in multiple different + * directories, we need to know which entries in versions correspond + * to which directories. Values of e.g. + * "" 0 + * src 2 + * src/moduleA 5 + * Would mean that entries 0-1 of versions are files in the toplevel + * directory, entries 2-4 are files under src/, and the remaining + * entries starting at index 5 are files under src/moduleA/. + */ + struct string_list offsets; + + /* + * last_directory: directory that previously processed file found in + * + * last_directory starts NULL, but records the directory in which the + * previous file was found within. As soon as + * directory(current_file) != last_directory + * then we need to start updating accounting in versions & offsets. + * Note that last_directory is always the last path in "offsets" (or + * NULL if "offsets" is empty) so this exists just for quick access. + */ + const char *last_directory; + + /* last_directory_len: cached computation of strlen(last_directory) */ + unsigned last_directory_len; +}; + +static int tree_entry_order(const void *a_, const void *b_) +{ + const struct string_list_item *a = a_; + const struct string_list_item *b = b_; + + const struct merged_info *ami = a->util; + const struct merged_info *bmi = b->util; + return base_name_compare(a->string, strlen(a->string), ami->result.mode, + b->string, strlen(b->string), bmi->result.mode); +} + +static void write_tree(struct object_id *result_oid, + struct string_list *versions, + unsigned int offset, + size_t hash_size) +{ + size_t maxlen = 0, extra; + unsigned int nr = versions->nr - offset; + struct strbuf buf = STRBUF_INIT; + struct string_list relevant_entries = STRING_LIST_INIT_NODUP; + int i; + + /* + * We want to sort the last (versions->nr-offset) entries in versions. + * Do so by abusing the string_list API a bit: make another string_list + * that contains just those entries and then sort them. + * + * We won't use relevant_entries again and will let it just pop off the + * stack, so there won't be allocation worries or anything. + */ + relevant_entries.items = versions->items + offset; + relevant_entries.nr = versions->nr - offset; + QSORT(relevant_entries.items, relevant_entries.nr, tree_entry_order); + + /* Pre-allocate some space in buf */ + extra = hash_size + 8; /* 8: 6 for mode, 1 for space, 1 for NUL char */ + for (i = 0; i < nr; i++) { + maxlen += strlen(versions->items[offset+i].string) + extra; + } + strbuf_grow(&buf, maxlen); + + /* Write each entry out to buf */ + for (i = 0; i < nr; i++) { + struct merged_info *mi = versions->items[offset+i].util; + struct version_info *ri = &mi->result; + strbuf_addf(&buf, "%o %s%c", + ri->mode, + versions->items[offset+i].string, '\0'); + strbuf_add(&buf, ri->oid.hash, hash_size); + } + + /* Write this object file out, and record in result_oid */ + write_object_file(buf.buf, buf.len, tree_type, result_oid); + strbuf_release(&buf); +} + +static void record_entry_for_tree(struct directory_versions *dir_metadata, + const char *path, + struct merged_info *mi) +{ + const char *basename; + + if (mi->is_null) + /* nothing to record */ + return; + + basename = path + mi->basename_offset; + assert(strchr(basename, '/') == NULL); + string_list_append(&dir_metadata->versions, + basename)->util = &mi->result; +} + +static void write_completed_directory(struct merge_options *opt, + const char *new_directory_name, + struct directory_versions *info) +{ + const char *prev_dir; + struct merged_info *dir_info = NULL; + unsigned int offset; + + /* + * Some explanation of info->versions and info->offsets... + * + * process_entries() iterates over all relevant files AND + * directories in reverse lexicographic order, and calls this + * function. Thus, an example of the paths that process_entries() + * could operate on (along with the directories for those paths + * being shown) is: + * + * xtract.c "" + * tokens.txt "" + * src/moduleB/umm.c src/moduleB + * src/moduleB/stuff.h src/moduleB + * src/moduleB/baz.c src/moduleB + * src/moduleB src + * src/moduleA/foo.c src/moduleA + * src/moduleA/bar.c src/moduleA + * src/moduleA src + * src "" + * Makefile "" + * + * info->versions: + * + * always contains the unprocessed entries and their + * version_info information. For example, after the first five + * entries above, info->versions would be: + * + * xtract.c <xtract.c's version_info> + * token.txt <token.txt's version_info> + * umm.c <src/moduleB/umm.c's version_info> + * stuff.h <src/moduleB/stuff.h's version_info> + * baz.c <src/moduleB/baz.c's version_info> + * + * Once a subdirectory is completed we remove the entries in + * that subdirectory from info->versions, writing it as a tree + * (write_tree()). Thus, as soon as we get to src/moduleB, + * info->versions would be updated to + * + * xtract.c <xtract.c's version_info> + * token.txt <token.txt's version_info> + * moduleB <src/moduleB's version_info> + * + * info->offsets: + * + * helps us track which entries in info->versions correspond to + * which directories. When we are N directories deep (e.g. 4 + * for src/modA/submod/subdir/), we have up to N+1 unprocessed + * directories (+1 because of toplevel dir). Corresponding to + * the info->versions example above, after processing five entries + * info->offsets will be: + * + * "" 0 + * src/moduleB 2 + * + * which is used to know that xtract.c & token.txt are from the + * toplevel dirctory, while umm.c & stuff.h & baz.c are from the + * src/moduleB directory. Again, following the example above, + * once we need to process src/moduleB, then info->offsets is + * updated to + * + * "" 0 + * src 2 + * + * which says that moduleB (and only moduleB so far) is in the + * src directory. + * + * One unique thing to note about info->offsets here is that + * "src" was not added to info->offsets until there was a path + * (a file OR directory) immediately below src/ that got + * processed. + * + * Since process_entry() just appends new entries to info->versions, + * write_completed_directory() only needs to do work if the next path + * is in a directory that is different than the last directory found + * in info->offsets. + */ + + /* + * If we are working with the same directory as the last entry, there + * is no work to do. (See comments above the directory_name member of + * struct merged_info for why we can use pointer comparison instead of + * strcmp here.) + */ + if (new_directory_name == info->last_directory) + return; + + /* + * If we are just starting (last_directory is NULL), or last_directory + * is a prefix of the current directory, then we can just update + * info->offsets to record the offset where we started this directory + * and update last_directory to have quick access to it. + */ + if (info->last_directory == NULL || + !strncmp(new_directory_name, info->last_directory, + info->last_directory_len)) { + uintptr_t offset = info->versions.nr; + + info->last_directory = new_directory_name; + info->last_directory_len = strlen(info->last_directory); + /* + * Record the offset into info->versions where we will + * start recording basenames of paths found within + * new_directory_name. + */ + string_list_append(&info->offsets, + info->last_directory)->util = (void*)offset; + return; + } + + /* + * The next entry that will be processed will be within + * new_directory_name. Since at this point we know that + * new_directory_name is within a different directory than + * info->last_directory, we have all entries for info->last_directory + * in info->versions and we need to create a tree object for them. + */ + dir_info = strmap_get(&opt->priv->paths, info->last_directory); + assert(dir_info); + offset = (uintptr_t)info->offsets.items[info->offsets.nr-1].util; + if (offset == info->versions.nr) { + /* + * Actually, we don't need to create a tree object in this + * case. Whenever all files within a directory disappear + * during the merge (e.g. unmodified on one side and + * deleted on the other, or files were renamed elsewhere), + * then we get here and the directory itself needs to be + * omitted from its parent tree as well. + */ + dir_info->is_null = 1; + } else { + /* + * Write out the tree to the git object directory, and also + * record the mode and oid in dir_info->result. + */ + dir_info->is_null = 0; + dir_info->result.mode = S_IFDIR; + write_tree(&dir_info->result.oid, &info->versions, offset, + opt->repo->hash_algo->rawsz); + } + + /* + * We've now used several entries from info->versions and one entry + * from info->offsets, so we get rid of those values. + */ + info->offsets.nr--; + info->versions.nr = offset; + + /* + * Now we've taken care of the completed directory, but we need to + * prepare things since future entries will be in + * new_directory_name. (In particular, process_entry() will be + * appending new entries to info->versions.) So, we need to make + * sure new_directory_name is the last entry in info->offsets. + */ + prev_dir = info->offsets.nr == 0 ? NULL : + info->offsets.items[info->offsets.nr-1].string; + if (new_directory_name != prev_dir) { + uintptr_t c = info->versions.nr; + string_list_append(&info->offsets, + new_directory_name)->util = (void*)c; + } + + /* And, of course, we need to update last_directory to match. */ + info->last_directory = new_directory_name; + info->last_directory_len = strlen(info->last_directory); +} + +/* Per entry merge function */ +static void process_entry(struct merge_options *opt, + const char *path, + struct conflict_info *ci, + struct directory_versions *dir_metadata) +{ + VERIFY_CI(ci); + assert(ci->filemask >= 0 && ci->filemask <= 7); + /* ci->match_mask == 7 was handled in collect_merge_info_callback() */ + assert(ci->match_mask == 0 || ci->match_mask == 3 || + ci->match_mask == 5 || ci->match_mask == 6); + + if (ci->dirmask) { + record_entry_for_tree(dir_metadata, path, &ci->merged); + if (ci->filemask == 0) + /* nothing else to handle */ + return; + assert(ci->df_conflict); + } + + if (ci->df_conflict) { + die("Not yet implemented."); + } + + /* + * NOTE: Below there is a long switch-like if-elseif-elseif... block + * which the code goes through even for the df_conflict cases + * above. Well, it will once we don't die-not-implemented above. + */ + if (ci->match_mask) { + ci->merged.clean = 1; + if (ci->match_mask == 6) { + /* stages[1] == stages[2] */ + ci->merged.result.mode = ci->stages[1].mode; + oidcpy(&ci->merged.result.oid, &ci->stages[1].oid); + } else { + /* determine the mask of the side that didn't match */ + unsigned int othermask = 7 & ~ci->match_mask; + int side = (othermask == 4) ? 2 : 1; + + ci->merged.result.mode = ci->stages[side].mode; + ci->merged.is_null = !ci->merged.result.mode; + oidcpy(&ci->merged.result.oid, &ci->stages[side].oid); + + assert(othermask == 2 || othermask == 4); + assert(ci->merged.is_null == + (ci->filemask == ci->match_mask)); + } + } else if (ci->filemask >= 6 && + (S_IFMT & ci->stages[1].mode) != + (S_IFMT & ci->stages[2].mode)) { + /* + * Two different items from (file/submodule/symlink) + */ + die("Not yet implemented."); + } else if (ci->filemask >= 6) { + /* + * TODO: Needs a two-way or three-way content merge, but we're + * just being lazy and copying the version from HEAD and + * leaving it as conflicted. + */ + ci->merged.clean = 0; + ci->merged.result.mode = ci->stages[1].mode; + oidcpy(&ci->merged.result.oid, &ci->stages[1].oid); + } else if (ci->filemask == 3 || ci->filemask == 5) { + /* Modify/delete */ + die("Not yet implemented."); + } else if (ci->filemask == 2 || ci->filemask == 4) { + /* Added on one side */ + int side = (ci->filemask == 4) ? 2 : 1; + ci->merged.result.mode = ci->stages[side].mode; + oidcpy(&ci->merged.result.oid, &ci->stages[side].oid); + ci->merged.clean = !ci->df_conflict; + } else if (ci->filemask == 1) { + /* Deleted on both sides */ + ci->merged.is_null = 1; + ci->merged.result.mode = 0; + oidcpy(&ci->merged.result.oid, &null_oid); + ci->merged.clean = 1; + } + + /* + * If still conflicted, record it separately. This allows us to later + * iterate over just conflicted entries when updating the index instead + * of iterating over all entries. + */ + if (!ci->merged.clean) + strmap_put(&opt->priv->conflicted, path, ci); + record_entry_for_tree(dir_metadata, path, &ci->merged); +} + +static void process_entries(struct merge_options *opt, + struct object_id *result_oid) +{ + struct hashmap_iter iter; + struct strmap_entry *e; + struct string_list plist = STRING_LIST_INIT_NODUP; + struct string_list_item *entry; + struct directory_versions dir_metadata = { STRING_LIST_INIT_NODUP, + STRING_LIST_INIT_NODUP, + NULL, 0 }; + + if (strmap_empty(&opt->priv->paths)) { + oidcpy(result_oid, opt->repo->hash_algo->empty_tree); + return; + } + + /* Hack to pre-allocate plist to the desired size */ + ALLOC_GROW(plist.items, strmap_get_size(&opt->priv->paths), plist.alloc); + + /* Put every entry from paths into plist, then sort */ + strmap_for_each_entry(&opt->priv->paths, &iter, e) { + string_list_append(&plist, e->key)->util = e->value; + } + plist.cmp = string_list_df_name_compare; + string_list_sort(&plist); + + /* + * Iterate over the items in reverse order, so we can handle paths + * below a directory before needing to handle the directory itself. + * + * This allows us to write subtrees before we need to write trees, + * and it also enables sane handling of directory/file conflicts + * (because it allows us to know whether the directory is still in + * the way when it is time to process the file at the same path). + */ + for (entry = &plist.items[plist.nr-1]; entry >= plist.items; --entry) { + char *path = entry->string; + /* + * NOTE: mi may actually be a pointer to a conflict_info, but + * we have to check mi->clean first to see if it's safe to + * reassign to such a pointer type. + */ + struct merged_info *mi = entry->util; + + write_completed_directory(opt, mi->directory_name, + &dir_metadata); + if (mi->clean) + record_entry_for_tree(&dir_metadata, path, mi); + else { + struct conflict_info *ci = (struct conflict_info *)mi; + process_entry(opt, path, ci, &dir_metadata); + } + } + + if (dir_metadata.offsets.nr != 1 || + (uintptr_t)dir_metadata.offsets.items[0].util != 0) { + printf("dir_metadata.offsets.nr = %d (should be 1)\n", + dir_metadata.offsets.nr); + printf("dir_metadata.offsets.items[0].util = %u (should be 0)\n", + (unsigned)(uintptr_t)dir_metadata.offsets.items[0].util); + fflush(stdout); + BUG("dir_metadata accounting completely off; shouldn't happen"); + } + write_tree(result_oid, &dir_metadata.versions, 0, + opt->repo->hash_algo->rawsz); + string_list_clear(&plist, 0); + string_list_clear(&dir_metadata.versions, 0); + string_list_clear(&dir_metadata.offsets, 0); +} + +static int checkout(struct merge_options *opt, + struct tree *prev, + struct tree *next) +{ + /* Switch the index/working copy from old to new */ + int ret; + struct tree_desc trees[2]; + struct unpack_trees_options unpack_opts; + + memset(&unpack_opts, 0, sizeof(unpack_opts)); + unpack_opts.head_idx = -1; + unpack_opts.src_index = opt->repo->index; + unpack_opts.dst_index = opt->repo->index; + + setup_unpack_trees_porcelain(&unpack_opts, "merge"); + + /* + * NOTE: if this were just "git checkout" code, we would probably + * read or refresh the cache and check for a conflicted index, but + * builtin/merge.c or sequencer.c really needs to read the index + * and check for conflicted entries before starting merging for a + * good user experience (no sense waiting for merges/rebases before + * erroring out), so there's no reason to duplicate that work here. + */ + + /* 2-way merge to the new branch */ + unpack_opts.update = 1; + unpack_opts.merge = 1; + unpack_opts.quiet = 0; /* FIXME: sequencer might want quiet? */ + unpack_opts.verbose_update = (opt->verbosity > 2); + unpack_opts.fn = twoway_merge; + if (1/* FIXME: opts->overwrite_ignore*/) { + unpack_opts.dir = xcalloc(1, sizeof(*unpack_opts.dir)); + unpack_opts.dir->flags |= DIR_SHOW_IGNORED; + setup_standard_excludes(unpack_opts.dir); + } + parse_tree(prev); + init_tree_desc(&trees[0], prev->buffer, prev->size); + parse_tree(next); + init_tree_desc(&trees[1], next->buffer, next-&g |