From 6220faeb4e9be16b9dec728e72ea8dff2cfe35ba Mon Sep 17 00:00:00 2001 From: Michal Nazarewicz Date: Wed, 7 Sep 2016 21:00:57 +0200 Subject: casing: don’t assume letters are *either* upper- or lower-case (bug#24603) A compatibility digraph characters, such as Dž, are neither upper- nor lower-case. At the moment however, those are reported as upper-case¹ despite the fact that they change when upper-cased. Stop checking if a character is upper-case before trying to up-case it so that title-case characters are handled correctly. This fixes one of the issues mentioned in bug#24603. ¹ Because they change when converted to lower-case. Notice an asymmetry in that for a character to be considered lower-case it must not be upper-case (plus the usual condition of changing when upper-cased). * src/buffer.h (upcase1): Delete. (upcase): Change to upcase character unconditionally just like downcase does it. This is what upcase1 was. * src/casefiddle.c (casify_object, casify_region): Use upcase instead of upcase1 and don’t check !uppercasep(x) before calling upcase. * src/keyboard.c (read_key_sequence): Don’t check if uppercase(x), just downcase(x) and see if it changed. * test/src/casefiddle-tests.el (casefiddle-tests--characters, casefiddle-tests-casing): Update test cases which are now passing. --- src/buffer.h | 18 +++++++++--------- src/casefiddle.c | 20 +++++++------------- src/keyboard.c | 25 +++++++++++++++---------- 3 files changed, 31 insertions(+), 32 deletions(-) (limited to 'src') diff --git a/src/buffer.h b/src/buffer.h index 4a23e4fdd2e..f53212e3120 100644 --- a/src/buffer.h +++ b/src/buffer.h @@ -1365,28 +1365,28 @@ downcase (int c) return NATNUMP (down) ? XFASTINT (down) : c; } -/* True if C is upper case. */ -INLINE bool uppercasep (int c) { return downcase (c) != c; } - -/* Upcase a character C known to be not upper case. */ +/* Upcase a character C, or make no change if that cannot be done. */ INLINE int -upcase1 (int c) +upcase (int c) { Lisp_Object upcase_table = BVAR (current_buffer, upcase_table); Lisp_Object up = CHAR_TABLE_REF (upcase_table, c); return NATNUMP (up) ? XFASTINT (up) : c; } +/* True if C is upper case. */ +INLINE bool uppercasep (int c) +{ + return downcase (c) != c; +} + /* True if C is lower case. */ INLINE bool lowercasep (int c) { - return !uppercasep (c) && upcase1 (c) != c; + return !uppercasep (c) && upcase (c) != c; } -/* Upcase a character C, or make no change if that cannot be done. */ -INLINE int upcase (int c) { return uppercasep (c) ? c : upcase1 (c); } - INLINE_HEADER_END #endif /* EMACS_BUFFER_H */ diff --git a/src/casefiddle.c b/src/casefiddle.c index 28ffcb298ff..b2b87e7a858 100644 --- a/src/casefiddle.c +++ b/src/casefiddle.c @@ -64,13 +64,9 @@ casify_object (enum case_action flag, Lisp_Object obj) multibyte = 1; if (! multibyte) MAKE_CHAR_MULTIBYTE (c1); - c = downcase (c1); - if (inword) - XSETFASTINT (obj, c | flags); - else if (c == (XFASTINT (obj) & ~flagbits)) + c = flag == CASE_DOWN ? downcase (c1) : upcase (c1); + if (c != c1) { - if (! inword) - c = upcase1 (c1); if (! multibyte) MAKE_CHAR_UNIBYTE (c); XSETFASTINT (obj, c | flags); @@ -95,7 +91,7 @@ casify_object (enum case_action flag, Lisp_Object obj) c = downcase (c); else if (!uppercasep (c) && (!inword || flag != CASE_CAPITALIZE_UP)) - c = upcase1 (c1); + c = upcase (c1); if ((int) flag >= (int) CASE_CAPITALIZE) inword = (SYNTAX (c) == Sword); if (c != c1) @@ -127,9 +123,8 @@ casify_object (enum case_action flag, Lisp_Object obj) c = STRING_CHAR_AND_LENGTH (SDATA (obj) + i_byte, len); if (inword && flag != CASE_CAPITALIZE_UP) c = downcase (c); - else if (!uppercasep (c) - && (!inword || flag != CASE_CAPITALIZE_UP)) - c = upcase1 (c); + else if (!inword || flag != CASE_CAPITALIZE_UP) + c = upcase (c); if ((int) flag >= (int) CASE_CAPITALIZE) inword = (SYNTAX (c) == Sword); o += CHAR_STRING (c, o); @@ -236,9 +231,8 @@ casify_region (enum case_action flag, Lisp_Object b, Lisp_Object e) c2 = c; if (inword && flag != CASE_CAPITALIZE_UP) c = downcase (c); - else if (!uppercasep (c) - && (!inword || flag != CASE_CAPITALIZE_UP)) - c = upcase1 (c); + else if (!inword || flag != CASE_CAPITALIZE_UP) + c = upcase (c); if ((int) flag >= (int) CASE_CAPITALIZE) inword = ((SYNTAX (c) == Sword) && (inword || !syntax_prefix_flag_p (c))); diff --git a/src/keyboard.c b/src/keyboard.c index ed8e71fd0a7..0fad633581d 100644 --- a/src/keyboard.c +++ b/src/keyboard.c @@ -9642,22 +9642,26 @@ read_key_sequence (Lisp_Object *keybuf, int bufsize, Lisp_Object prompt, use the corresponding lower-case letter instead. */ if (NILP (current_binding) && /* indec.start >= t && fkey.start >= t && */ keytran.start >= t - && INTEGERP (key) - && ((CHARACTERP (make_number (XINT (key) & ~CHAR_MODIFIER_MASK)) - && uppercasep (XINT (key) & ~CHAR_MODIFIER_MASK)) - || (XINT (key) & shift_modifier))) + && INTEGERP (key)) { Lisp_Object new_key; + int k = XINT (key); + + if (k & shift_modifier) + XSETINT (new_key, k & ~shift_modifier); + else if (CHARACTERP (make_number (k & ~CHAR_MODIFIER_MASK))) + { + int dc = downcase(k & ~CHAR_MODIFIER_MASK); + if (dc == (k & ~CHAR_MODIFIER_MASK)) + goto not_upcase; + XSETINT (new_key, dc | (k & CHAR_MODIFIER_MASK)); + } + else + goto not_upcase; original_uppercase = key; original_uppercase_position = t - 1; - if (XINT (key) & shift_modifier) - XSETINT (new_key, XINT (key) & ~shift_modifier); - else - XSETINT (new_key, (downcase (XINT (key) & ~CHAR_MODIFIER_MASK) - | (XINT (key) & CHAR_MODIFIER_MASK))); - /* We have to do this unconditionally, regardless of whether the lower-case char is defined in the keymaps, because they might get translated through function-key-map. */ @@ -9668,6 +9672,7 @@ read_key_sequence (Lisp_Object *keybuf, int bufsize, Lisp_Object prompt, goto replay_sequence; } + not_upcase: if (NILP (current_binding) && help_char_p (EVENT_HEAD (key)) && t > 1) { -- cgit v1.2.1