merge-ort: setup basic internal data structures
Set up some basic internal data structures. The only carry-over from merge-recursive.c is call_depth, though needed_rename_limit will be added later. The central piece of data will definitely be the strmap "paths", which will map every relevant pathname under consideration to either a merged_info or a conflict_info. ("conflicted" is a strmap that is a subset of "paths".) 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). 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). Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Elijah Newren committed
Dec 13, 2020 at 08:04 UTC
5b59c3db059d85306ebeb680c4d322a69ee29fde
1 file changed
+147
merge-ort.c
+147
@@ -17,6 +17,153 @@
17
#include "cache.h"
18
#include "merge-ort.h"
19
20
+#include "strmap.h"
21
+
22
+struct merge_options_internal {
23
+ /*
24
+ * paths: primary data structure in all of merge ort.
25
+ *
26
+ * The keys of paths:
27
+ * * are full relative paths from the toplevel of the repository
28
+ * (e.g. "drivers/firmware/raspberrypi.c").
29
+ * * store all relevant paths in the repo, both directories and
30
+ * files (e.g. drivers, drivers/firmware would also be included)
31
+ * * these keys serve to intern all the path strings, which allows
32
+ * us to do pointer comparison on directory names instead of
33
+ * strcmp; we just have to be careful to use the interned strings.
34
+ *
35
+ * The values of paths:
36
+ * * either a pointer to a merged_info, or a conflict_info struct
37
+ * * merged_info contains all relevant information for a
38
+ * non-conflicted entry.
39
+ * * conflict_info contains a merged_info, plus any additional
40
+ * information about a conflict such as the higher orders stages
41
+ * involved and the names of the paths those came from (handy
42
+ * once renames get involved).
43
+ * * a path may start "conflicted" (i.e. point to a conflict_info)
44
+ * and then a later step (e.g. three-way content merge) determines
45
+ * it can be cleanly merged, at which point it'll be marked clean
46
+ * and the algorithm will ignore any data outside the contained
47
+ * merged_info for that entry
48
+ * * If an entry remains conflicted, the merged_info portion of a
49
+ * conflict_info will later be filled with whatever version of
50
+ * the file should be placed in the working directory (e.g. an
51
+ * as-merged-as-possible variation that contains conflict markers).
52
+ */
53
+ struct strmap paths;
54
+
55
+ /*
56
+ * conflicted: a subset of keys->values from "paths"
57
+ *
58
+ * conflicted is basically an optimization between process_entries()
59
+ * and record_conflicted_index_entries(); the latter could loop over
60
+ * ALL the entries in paths AGAIN and look for the ones that are
61
+ * still conflicted, but since process_entries() has to loop over
62
+ * all of them, it saves the ones it couldn't resolve in this strmap
63
+ * so that record_conflicted_index_entries() can iterate just the
64
+ * relevant entries.
65
+ */
66
+ struct strmap conflicted;
67
+
68
+ /*
69
+ * current_dir_name: temporary var used in collect_merge_info_callback()
70
+ *
71
+ * Used to set merged_info.directory_name; see documentation for that
72
+ * variable and the requirements placed on that field.
73
+ */
74
+ const char *current_dir_name;
75
+
76
+ /* call_depth: recursion level counter for merging merge bases */
77
+ int call_depth;
78
+};
79
+
80
+struct version_info {
81
+ struct object_id oid;
82
+ unsigned short mode;
83
+};
84
+
85
+struct merged_info {
86
+ /* if is_null, ignore result. otherwise result has oid & mode */
87
+ struct version_info result;
88
+ unsigned is_null:1;
89
+
90
+ /*
91
+ * clean: whether the path in question is cleanly merged.
92
+ *
93
+ * see conflict_info.merged for more details.
94
+ */
95
+ unsigned clean:1;
96
+
97
+ /*
98
+ * basename_offset: offset of basename of path.
99
+ *
100
+ * perf optimization to avoid recomputing offset of final '/'
101
+ * character in pathname (0 if no '/' in pathname).
102
+ */
103
+ size_t basename_offset;
104
+
105
+ /*
106
+ * directory_name: containing directory name.
107
+ *
108
+ * Note that we assume directory_name is constructed such that
109
+ * strcmp(dir1_name, dir2_name) == 0 iff dir1_name == dir2_name,
110
+ * i.e. string equality is equivalent to pointer equality. For this
111
+ * to hold, we have to be careful setting directory_name.
112
+ */
113
+ const char *directory_name;
114
+};
115
+
116
+struct conflict_info {
117
+ /*
118
+ * merged: the version of the path that will be written to working tree
119
+ *
120
+ * WARNING: It is critical to check merged.clean and ensure it is 0
121
+ * before reading any conflict_info fields outside of merged.
122
+ * Allocated merge_info structs will always have clean set to 1.
123
+ * Allocated conflict_info structs will have merged.clean set to 0
124
+ * initially. The merged.clean field is how we know if it is safe
125
+ * to access other parts of conflict_info besides merged; if a
126
+ * conflict_info's merged.clean is changed to 1, the rest of the
127
+ * algorithm is not allowed to look at anything outside of the
128
+ * merged member anymore.
129
+ */
130
+ struct merged_info merged;
131
+
132
+ /* oids & modes from each of the three trees for this path */
133
+ struct version_info stages[3];
134
+
135
+ /* pathnames for each stage; may differ due to rename detection */
136
+ const char *pathnames[3];
137
+
138
+ /* Whether this path is/was involved in a directory/file conflict */
139
+ unsigned df_conflict:1;
140
+
141
+ /*
142
+ * For filemask and dirmask, the ith bit corresponds to whether the
143
+ * ith entry is a file (filemask) or a directory (dirmask). Thus,
144
+ * filemask & dirmask is always zero, and filemask | dirmask is at
145
+ * most 7 but can be less when a path does not appear as either a
146
+ * file or a directory on at least one side of history.
147
+ *
148
+ * Note that these masks are related to enum merge_side, as the ith
149
+ * entry corresponds to side i.
150
+ *
151
+ * These values come from a traverse_trees() call; more info may be
152
+ * found looking at tree-walk.h's struct traverse_info,
153
+ * particularly the documentation above the "fn" member (note that
154
+ * filemask = mask & ~dirmask from that documentation).
155
+ */
156
+ unsigned filemask:3;
157
+ unsigned dirmask:3;
158
+
159
+ /*
160
+ * Optimization to track which stages match, to avoid the need to
161
+ * recompute it in multiple steps. Either 0 or at least 2 bits are
162
+ * set; if at least 2 bits are set, their corresponding stages match.
163
+ */
164
+ unsigned match_mask:3;
165
+};
166
+
167
void merge_switch_to_result(struct merge_options *opt,
168
struct tree *head,
169
struct merge_result *result,