Augment text-mode syntax table for a few special characters

 lips/textmodes/text-mode.el (text-mode-syntax-table): Make some
 punctuation character behave as word-constituent, for more
 compatibility with Unicode.

1 files changed, 17 insertions, 0 deletions

diff --git a/lisp/textmodes/text-mode.el b/lisp/textmodes/text-mode.el
index 5f2f671993c..84b578b5059 100644
--- a/lisp/textmodes/text-mode.el
+++ b/lisp/textmodes/text-mode.el
@@ -45,6 +45,23 @@ Use (derived-mode-p 'text-mode) instead.")
     (modify-syntax-entry ?\\ ".   " st)
     ;; We add `p' so that M-c on 'hello' leads to 'Hello' rather than 'hello'.
     (modify-syntax-entry ?' "w p" st)
+    ;; UAX #29 says HEBREW PUNCTUATION GERESH behaves like a letter
+    ;; for the purposes of finding word boundaries.
+    (modify-syntax-entry #x5f3 "w   ") ; GERESH
+    ;; UAX #29 says HEBREW PUNCTUATION GERSHAYIM should not be a word
+    ;; boundary when surrounded by letters.  Our infrastructure for
+    ;; finding a word boundary doesn't support 3-character
+    ;; definitions, so for now simply make this a word-constituent
+    ;; character.  This leaves a problem of having GERSHAYIM at the
+    ;; beginning or end of a word, where it should be a boundary;
+    ;; FIXME.
+    (modify-syntax-entry #x5f4 "w   ") ; GERSHAYIM
+    ;; These all should not be a word boundary when between letters,
+    ;; according to UAX #29, so they again are prone to the same
+    ;; problem as GERSHAYIM; FIXME.
+    (modify-syntax-entry #xb7 "w   ")   ; MIDDLE DOT
+    (modify-syntax-entry #x2027 "w   ") ; HYPHENATION POINT
+    (modify-syntax-entry #xff1a "w   ") ; FULLWIDTH COLON
     st)
   "Syntax table used while in `text-mode'.")