Maintain interval ->position fields correctly in update_interval

Also fix some anomalies in the handling of byte positions in regexp-emacs.c
This fixes bug #34525.

* src/intervals.c (SET_PARENT_POSITION): New macro.
(update_interval): When moving to an interval's parent, set that parent's
->position field, to maintain the consistency of the tree.

* src/intervals.h (struct interval): Amend the comment describing when
->position is valid.

* src/pdumper.c: Update the hash associated with struct interval.

* src/regex-emacs.c: (re_match_2_internal): Only invoke POINTER_TO_OFFSET on a
known character boundary.  Only perform arithmetic on character positions, not
on byte positions.  Correct the argument to an invocation of
UPDATE_SYNTAX_TABLE_FORWARD by adding 1 to it (in case wordend:).

* src/syntax.c: (update_syntax_table): Remove the now redundant code that set
the ->position field of all parents of the interval found by update_interval.

5 files changed, 40 insertions, 34 deletions

diff --git a/src/intervals.c b/src/intervals.c
index 524bb944e51..8f39c45762f 100644
--- a/src/intervals.c
+++ b/src/intervals.c
@@ -713,11 +713,21 @@ previous_interval (register INTERVAL interval)
   return NULL;
 }
 
-/* Find the interval containing POS given some non-NULL INTERVAL
-   in the same tree.  Note that we need to update interval->position
-   if we go down the tree.
-   To speed up the process, we assume that the ->position of
-   I and all its parents is already uptodate.  */
+/* Set the ->position field of I's parent, based on I->position. */
+#define SET_PARENT_POSITION(i)                                  \
+  if (AM_LEFT_CHILD (i))                                        \
+    INTERVAL_PARENT (i)->position =                             \
+      i->position + TOTAL_LENGTH (i) - LEFT_TOTAL_LENGTH (i);   \
+  else                                                          \
+    INTERVAL_PARENT (i)->position =                             \
+      i->position - LEFT_TOTAL_LENGTH (i)                       \
+      - LENGTH (INTERVAL_PARENT (i))
+
+/* Find the interval containing POS, given some non-NULL INTERVAL in
+   the same tree.  Note that we update interval->position in each
+   interval we traverse, assuming it is already correctly set for the
+   argument I.  We don't assume that any other interval already has a
+   correctly set ->position.  */
 INTERVAL
 update_interval (register INTERVAL i, ptrdiff_t pos)
 {
@@ -738,7 +748,10 @@ update_interval (register INTERVAL i, ptrdiff_t pos)
           else if (NULL_PARENT (i))
             error ("Point before start of properties");
           else
-              i = INTERVAL_PARENT (i);
+            {
+              SET_PARENT_POSITION (i);
+              i = INTERVAL_PARENT (i);
+            }
           continue;
         }
       else if (pos >= INTERVAL_LAST_POS (i))
@@ -753,7 +766,10 @@ update_interval (register INTERVAL i, ptrdiff_t pos)
           else if (NULL_PARENT (i))
             error ("Point %"pD"d after end of properties", pos);
           else
-            i = INTERVAL_PARENT (i);
+            {
+              SET_PARENT_POSITION (i);
+              i = INTERVAL_PARENT (i);
+            }
           continue;
         }
       else
diff --git a/src/intervals.h b/src/intervals.h
index 9c5adf33a14..e9166946d9a 100644
--- a/src/intervals.h
+++ b/src/intervals.h
@@ -31,11 +31,15 @@ struct interval
   /* The first group of entries deal with the tree structure.  */
   ptrdiff_t total_length;       /* Length of myself and both children.  */
   ptrdiff_t position;           /* Cache of interval's character position.  */
-                                /* This field is usually updated
-                                   simultaneously with an interval
-                                   traversal, there is no guarantee
-                                   that it is valid for a random
-                                   interval.  */
+                                /* This field is valid in the final
+                                   target interval returned by
+                                   find_interval, next_interval,
+                                   previous_interval and
+                                   update_interval.  It cannot be
+                                   depended upon in any intermediate
+                                   intervals traversed by these
+                                   functions, or any other
+                                   interval. */
   struct interval *left;        /* Intervals which precede me.  */
   struct interval *right;       /* Intervals which succeed me.  */
 
diff --git a/src/pdumper.c b/src/pdumper.c
index 4d35fd1233f..bba43370a14 100644
--- a/src/pdumper.c
+++ b/src/pdumper.c
@@ -2064,7 +2064,7 @@ dump_interval_tree (struct dump_context *ctx,
                     INTERVAL tree,
                     dump_off parent_offset)
 {
-#if CHECK_STRUCTS && !defined (HASH_interval_9110163DA0)
+#if CHECK_STRUCTS && !defined (HASH_interval_1B38941C37)
 # error "interval changed. See CHECK_STRUCTS comment."
 #endif
   // TODO: output tree breadth-first?
diff --git a/src/regex-emacs.c b/src/regex-emacs.c
index b667a43a37f..45b4f8107c7 100644
--- a/src/regex-emacs.c
+++ b/src/regex-emacs.c
@@ -4732,8 +4732,8 @@ re_match_2_internal (struct re_pattern_buffer *bufp, re_char *string1,
                 int c1, c2;
                 int s1, s2;
                 int dummy;
-                ptrdiff_t offset = PTR_TO_OFFSET (d - 1);
-                ptrdiff_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
+                ptrdiff_t offset = PTR_TO_OFFSET (d);
+                ptrdiff_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset) - 1;
                 UPDATE_SYNTAX_TABLE (charpos);
                 GET_CHAR_BEFORE_2 (c1, d, string1, end1, string2, end2);
                 s1 = SYNTAX (c1);
@@ -4811,8 +4811,8 @@ re_match_2_internal (struct re_pattern_buffer *bufp, re_char *string1,
               int c1, c2;
               int s1, s2;
               int dummy;
-              ptrdiff_t offset = PTR_TO_OFFSET (d) - 1;
-              ptrdiff_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
+              ptrdiff_t offset = PTR_TO_OFFSET (d);
+              ptrdiff_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset) - 1;
               UPDATE_SYNTAX_TABLE (charpos);
               GET_CHAR_BEFORE_2 (c1, d, string1, end1, string2, end2);
               s1 = SYNTAX (c1);
@@ -4826,7 +4826,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, re_char *string1,
                 {
                   PREFETCH_NOLIMIT ();
                   GET_CHAR_AFTER (c2, d, dummy);
-                  UPDATE_SYNTAX_TABLE_FORWARD (charpos);
+                  UPDATE_SYNTAX_TABLE_FORWARD (charpos + 1);
                   s2 = SYNTAX (c2);
 
                   /* ... and S2 is Sword, and WORD_BOUNDARY_P (C1, C2)
@@ -4890,8 +4890,8 @@ re_match_2_internal (struct re_pattern_buffer *bufp, re_char *string1,
                  is the character at D, and S2 is the syntax of C2.  */
               int c1, c2;
               int s1, s2;
-              ptrdiff_t offset = PTR_TO_OFFSET (d) - 1;
-              ptrdiff_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset);
+              ptrdiff_t offset = PTR_TO_OFFSET (d);
+              ptrdiff_t charpos = SYNTAX_TABLE_BYTE_TO_CHAR (offset) - 1;
               UPDATE_SYNTAX_TABLE (charpos);
               GET_CHAR_BEFORE_2 (c1, d, string1, end1, string2, end2);
               s1 = SYNTAX (c1);
diff --git a/src/syntax.c b/src/syntax.c
index dd2f56f2cfa..fe1e2d236b9 100644
--- a/src/syntax.c
+++ b/src/syntax.c
@@ -340,20 +340,6 @@ update_syntax_table (ptrdiff_t charpos, EMACS_INT count, bool init,
       invalidate = false;
       if (!i)
         return;
-      /* interval_of updates only ->position of the return value, so
-         update the parents manually to speed up update_interval.  */
-      while (!NULL_PARENT (i))
-        {
-          if (AM_RIGHT_CHILD (i))
-            INTERVAL_PARENT (i)->position = i->position
-              - LEFT_TOTAL_LENGTH (i) + TOTAL_LENGTH (i) /* right end */
-              - TOTAL_LENGTH (INTERVAL_PARENT (i))
-              + LEFT_TOTAL_LENGTH (INTERVAL_PARENT (i));
-          else
-            INTERVAL_PARENT (i)->position = i->position - LEFT_TOTAL_LENGTH (i)
-              + TOTAL_LENGTH (i);
-          i = INTERVAL_PARENT (i);
-        }
       i = gl_state.forward_i;
       gl_state.b_property = i->position - gl_state.offset;
       gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;