feat(filter): per-directory merge rules at the receiver; implement e/n/w/- modifiers

src/shared/filter.h

@@ -25,11 +25,12 @@
  * Modifiers: '/' absolute anchor, '!' negate match, 'C' inject CVS defaults,
  * 's' sender side, 'r' receiver side, 'p' perishable.  The rsync 'x'
  * (xattr-name) modifier is not implemented and is rejected explicitly
- * everywhere.  The merge-file modifiers 'e' (exclude the merge file itself),
- * 'n' (do not inherit the merge file), 'w' (word-split the merge file) and '-'
- * (do not transfer the merge file) are accepted and consumed only on merge/
- * dir-merge rules (rejected on every other rule, matching rsync); their
- * semantics are not implemented and they are otherwise ignored.
+ * everywhere.  The merge-only modifiers are accepted only on merge/dir-merge
+ * rules (rejected on every other rule, matching rsync): 'e' excludes the merge
+ * file itself, 'n' makes the merged rules non-inheriting (they apply only to
+ * the directory that holds the merge file), 'w' word-splits the merge file on
+ * whitespace instead of lines, and '-' reads the merge file as a list of bare
+ * exclude patterns with no rule prefixes.
  * A trailing '/' makes a pattern match directories only.  A leading '/' anchors
  * the pattern to its owner directory.
  */
@@ -55,18 +56,32 @@ typedef struct {
   bool dir_only;       /* pattern had a trailing '/': matches directories only */
   bool negate;         /* '!' modifier: match succeeds when the pattern does not */
   bool perishable;     /* 'p' modifier (ignored in deleted directories) */
+  bool no_inherit;     /* 'n' on the owning dir-merge: applies only in `owner` */
   char* owner;         /* owning directory rel path ("" == transfer root) */
   char* pattern;       /* cleaned glob pattern (no leading '/', no trailing '/') */
 } FilterRule;
 
+/* One per-directory merge-file registration ("dir-merge NAME"/": NAME", "merge
+ * NAME"/". NAME" and -F's .rsync-filter) together with the merge-only modifiers
+ * parsed from the rule.  The scanner reads `name` in every directory it
+ * traverses and applies `no_prefixes`/`include`/`word_split`/`no_inherit`/
+ * `exclude_self` while merging the file's rules. */
+typedef struct {
+  char* name;
+  bool no_prefixes;  /* '-' : file holds only bare exclude patterns */
+  bool include;      /* '+' : file holds only bare include patterns */
+  bool word_split;   /* 'w' : split the file on whitespace, not lines */
+  bool no_inherit;   /* 'n' : the merged rules do not inherit below their dir */
+  bool exclude_self; /* 'e' : exclude the merge file itself from the transfer */
+} FilterDirMerge;
+
 typedef struct FilterRuleList {
   FilterRule** items; /* owned array of rule pointers */
   int count;
   int capacity;
-  /* Per-directory merge-file basenames registered by "dir-merge NAME"/": NAME"
-   * or by -F (.rsync-filter).  Owned strings; the scanner reads each name in
-   * every directory it traverses. */
-  char** dir_merge_names;
+  /* Per-directory merge-file registrations.  Owned; the scanner reads each
+   * name in every directory it traverses. */
+  FilterDirMerge* dir_merges;
   int dir_merge_count;
   int dir_merge_capacity;
 } FilterRuleList;
@@ -83,13 +98,23 @@ typedef struct {
 FilterRule* filter_rule_parse(const char* line, const FilterParseOptions* opts, char* err,
                               size_t err_size);
 void filter_rule_free(FilterRule* rule);
+/* Deep-copy a rule (owned pattern/owner).  Returns NULL on allocation failure. */
+FilterRule* filter_rule_clone(const FilterRule* rule);
 
 FilterRuleList* filter_rule_list_create(void);
 /* Append a fully-parsed rule (takes ownership). Returns false on OOM. */
 bool filter_rule_list_add(FilterRuleList* list, FilterRule* rule);
-/* Register a per-directory merge-file basename (idempotent). Returns false on
- * OOM.  Used by the scanner to read custom "dir-merge" files. */
+/* Register a per-directory merge-file basename (idempotent, no modifiers).
+ * Returns false on OOM.  Used by the scanner to read custom "dir-merge" files. */
 bool filter_rule_list_add_dir_merge(FilterRuleList* list, const char* name);
+/* Register a per-directory merge file with its merge-only modifiers.  On a
+ * duplicate name the existing registration is kept (rsync's first wins) and true
+ * is returned.  When `exclude_self` is set an implicit exclude rule for the
+ * merge file's basename is appended to the list at this position, matching
+ * rsync's `e` modifier.  Returns false on OOM. */
+bool filter_rule_list_add_dir_merge_ex(FilterRuleList* list, const char* name, bool no_prefixes,
+                                       bool include, bool word_split, bool no_inherit,
+                                       bool exclude_self);
 /* Parse `line` and append it.  Handles "clear"/"!" (resets the list), "merge
  * FILE"/". FILE" (splices the file's rules) and "dir-merge NAME"/": NAME"
  * (registers a per-directory filename).  Returns false and fills `err` on bad
@@ -122,6 +147,15 @@ bool filter_file_append(FilterRuleList* list, const char* dir_path, const char*
                         const char* owner_rel, const FilterParseOptions* opts, bool* exists,
                         char* err, size_t err_size);
 
+/* Append a per-directory merge file honoring its merge-only modifiers: `-`
+ * reads every (word-split, when `w`) token as a bare exclude, `+` as a bare
+ * include, and `n` marks each read rule non-inheriting.  A plain name behaves
+ * like filter_file_append.  A missing file yields *exists=false with no error;
+ * returns false only on a parse/allocation failure (message in `err`). */
+bool filter_dir_merge_append(FilterRuleList* list, const char* dir_path, const FilterDirMerge* spec,
+                             const char* owner_rel, const FilterParseOptions* opts, bool* exists,
+                             char* err, size_t err_size);
+
 /* filter_file_read_named with the default ".rsync-filter" name. */
 FilterRuleList* filter_file_read(const char* dir_path, const char* owner_rel, bool* exists,
                                  char* err, size_t err_size);
@@ -135,4 +169,15 @@ FilterRuleList* filter_file_read(const char* dir_path, const char* owner_rel, bo
 FilterAction filter_rules_apply_side(const FilterRuleList* list, const char* rel_path,
                                      const char* leaf, bool is_dir, unsigned side);
 
+/* Evaluate a received per-directory rule set for the receiver side, using
+ * rsync's per-directory-before-ancestors order: the entry's containing
+ * directory's rules are tried first, then each ancestor's, then the receive
+ * root's.  `dir_rules` is a flat list whose rules carry `owner`; a rule applies
+ * only when `owner` is exactly the directory being examined (a no-inherit rule
+ * therefore applies only to that directory's direct children).  Returns the
+ * first matching rule's receiver verdict (PROTECT/RISK) or FILTER_ACTION_NONE.
+ * The caller evaluates the command-line base rules after this chain. */
+FilterAction filter_dir_rules_apply_side(const FilterRuleList* dir_rules, const char* rel_path,
+                                         const char* leaf, bool is_dir);
+
 #endif