[Emacs-diffs] master d6640d6: Give names to Unicode code points in C code

[Paul Eggert]

branch: master
commit d6640d6e4c4f1a85edf924bca0f8a90d1aa6341a
Author: Paul Eggert <address@hidden>
Commit: Paul Eggert <address@hidden>

    Give names to Unicode code points in C code
    
    * src/character.h (NO_BREAK_SPACE, SOFT_HYPHEN)
    (ZERO_WIDTH_NON_JOINER, ZERO_WIDTH_JOINER, HYPHEN)
    (NON_BREAKING_HYPHEN, LEFT_SINGLE_QUOTATION_MARK)
    (RIGHT_SINGLE_QUOTATION_MARK, PARAGRAPH_SEPARATOR)
    (LEFT_POINTING_ANGLE_BRACKET, RIGHT_POINTING_ANGLE_BRACKET)
    (LEFT_ANGLE_BRACKET, RIGHT_ANGLE_BRACKET)
    (OBJECT_REPLACEMENT_CHARACTER):
    New named constants for Unicode code points.
    * src/bidi.c (bidi_fetch_char, CANONICAL_EQU):
    * src/composite.c (char_composable_p):
    * src/lread.c (readevalloop, read1):
    * src/xdisp.c (get_next_display_element):
    Use them.
    * src/doc.c (LEFT_SINGLE_QUOTATION_POINT):
    Remove; now in character.h.
---
 src/bidi.c      |    8 ++++----
 src/character.h |   19 +++++++++++++++++++
 src/composite.c |    2 +-
 src/doc.c       |    1 -
 src/lread.c     |    8 ++++----
 src/xdisp.c     |    5 +++--
 6 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/src/bidi.c b/src/bidi.c
index e06430c..bcc15b8 100644
--- a/src/bidi.c
+++ b/src/bidi.c
@@ -1313,13 +1313,13 @@ bidi_fetch_char (ptrdiff_t charpos, ptrdiff_t bytepos, 
ptrdiff_t *disp_pos,
          /* `(space ...)' display specs are handled as paragraph
             separators for the purposes of the reordering; see UAX#9
             section 3 and clause HL1 in section 4.3 there.  */
-         ch = 0x2029;
+         ch = PARAGRAPH_SEPARATOR;
        }
       else
        {
          /* All other display specs are handled as the Unicode Object
             Replacement Character.  */
-         ch = 0xFFFC;
+         ch = OBJECT_REPLACEMENT_CHARACTER;
        }
       disp_end_pos = compute_display_string_end (*disp_pos, string);
       if (disp_end_pos < 0)
@@ -2482,8 +2482,8 @@ typedef struct bpa_stack_entry {
 
 #define CANONICAL_EQU(c)                                       \
   ( ASCII_CHAR_P (c) ? c                                       \
-    : (c) == 0x2329 ? 0x3008                                   \
-    : (c) == 0x232a ? 0x3009                                   \
+    : (c) == LEFT_POINTING_ANGLE_BRACKET ? LEFT_ANGLE_BRACKET  \
+    : (c) == RIGHT_POINTING_ANGLE_BRACKET ? RIGHT_ANGLE_BRACKET        \
     : c )
 
 #ifdef ENABLE_CHECKING
diff --git a/src/character.h b/src/character.h
index 859d717..0b2c419 100644
--- a/src/character.h
+++ b/src/character.h
@@ -59,6 +59,25 @@ INLINE_HEADER_BEGIN
 /* Maximum leading code of multibyte characters.  */
 #define MAX_MULTIBYTE_LEADING_CODE 0xF8
 
+/* Unicode character values.  */
+enum
+{
+  NO_BREAK_SPACE = 0x00A0,
+  SOFT_HYPHEN = 0x00AD,
+  ZERO_WIDTH_NON_JOINER = 0x200C,
+  ZERO_WIDTH_JOINER = 0x200D,
+  HYPHEN = 0x2010,
+  NON_BREAKING_HYPHEN = 0x2011,
+  LEFT_SINGLE_QUOTATION_MARK = 0x2018,
+  RIGHT_SINGLE_QUOTATION_MARK = 0x2019,
+  PARAGRAPH_SEPARATOR = 0x2029,
+  LEFT_POINTING_ANGLE_BRACKET = 0x2329,
+  RIGHT_POINTING_ANGLE_BRACKET = 0x232A,
+  LEFT_ANGLE_BRACKET = 0x3008,
+  RIGHT_ANGLE_BRACKET = 0x3009,
+  OBJECT_REPLACEMENT_CHARACTER = 0xFFFC,
+};
+
 /* Nonzero iff C is a character that corresponds to a raw 8-bit
    byte.  */
 #define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR)
diff --git a/src/composite.c b/src/composite.c
index 1c18165..88cef22 100644
--- a/src/composite.c
+++ b/src/composite.c
@@ -927,7 +927,7 @@ char_composable_p (int c)
 {
   Lisp_Object val;
   return (c > ' '
-         && (c == 0x200C || c == 0x200D
+         && (c == ZERO_WIDTH_NON_JOINER || c == ZERO_WIDTH_JOINER
              || (val = CHAR_TABLE_REF (Vunicode_category_table, c),
                  (INTEGERP (val) && (XINT (val) <= UNICODE_CATEGORY_So)))));
 }
diff --git a/src/doc.c b/src/doc.c
index a079cd2..cb52266 100644
--- a/src/doc.c
+++ b/src/doc.c
@@ -689,7 +689,6 @@ the same file name is found in the `doc-directory'.  */)
    "\xE2\x80\x98" and "\xE2\x80\x99", respectively.  */
 enum
   {
-    LEFT_SINGLE_QUOTATION_MARK = 0x2018,
     uLSQM0 = 0xE2, uLSQM1 = 0x80, uLSQM2 = 0x98,
     uRSQM0 = 0xE2, uRSQM1 = 0x80, uRSQM2 = 0x99,
   };
diff --git a/src/lread.c b/src/lread.c
index 11c8d00..fe4d367 100644
--- a/src/lread.c
+++ b/src/lread.c
@@ -1885,7 +1885,7 @@ readevalloop (Lisp_Object readcharfun,
 
       /* Ignore whitespace here, so we can detect eof.  */
       if (c == ' ' || c == '\t' || c == '\n' || c == '\f' || c == '\r'
-         || c == 0xa0)  /* NBSP */
+         || c == NO_BREAK_SPACE)
        goto read_next;
 
       if (!NILP (Vpurify_flag) && c == '(')
@@ -2793,7 +2793,7 @@ read1 (Lisp_Object readcharfun, int *pch, bool 
first_in_list)
          uninterned_symbol = 1;
          c = READCHAR;
          if (!(c > 040
-               && c != 0xa0    /* NBSP */
+               && c != NO_BREAK_SPACE
                && (c >= 0200
                    || strchr ("\"';()[]#`,", c) == NULL)))
            {
@@ -3127,7 +3127,7 @@ read1 (Lisp_Object readcharfun, int *pch, bool 
first_in_list)
     default:
     default_label:
       if (c <= 040) goto retry;
-      if (c == 0xa0) /* NBSP */
+      if (c == NO_BREAK_SPACE)
        goto retry;
 
     read_symbol:
@@ -3167,7 +3167,7 @@ read1 (Lisp_Object readcharfun, int *pch, bool 
first_in_list)
              c = READCHAR;
            }
          while (c > 040
-                && c != 0xa0 /* NBSP */
+                && c != NO_BREAK_SPACE
                 && (c >= 0200
                     || strchr ("\"';()[]#`,", c) == NULL));
 
diff --git a/src/xdisp.c b/src/xdisp.c
index 711fe08..7371216 100644
--- a/src/xdisp.c
+++ b/src/xdisp.c
@@ -6890,9 +6890,10 @@ get_next_display_element (struct it *it)
             non-ASCII spaces and hyphens specially.  */
          if (! ASCII_CHAR_P (c) && ! NILP (Vnobreak_char_display))
            {
-             if (c == 0xA0)
+             if (c == NO_BREAK_SPACE)
                nonascii_space_p = true;
-             else if (c == 0xAD || c == 0x2010 || c == 0x2011)
+             else if (c == SOFT_HYPHEN || c == HYPHEN
+                      || c == NON_BREAKING_HYPHEN)
                nonascii_hyphen_p = true;
            }