remove NameCtypeTable in unicode.c

diff --git a/src/Makefile.am b/src/Makefile.am
index 2154cfc115e39176cce9f19a41f14ba4aabd9c6c..2cd421b24a73606e4d92b2186cebfc55375b67f7 100644 (file)
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -11,7 +11,8 @@ libonig_la_SOURCES = regint.h regparse.h regenc.h st.h \
        regerror.c regparse.c regext.c regcomp.c regexec.c reggnu.c \
        regenc.c regsyntax.c regtrav.c regversion.c st.c \
        regposix.c regposerr.c \
-       unicode.c ascii.c utf8.c \
+       unicode.c unicode_prop.c \
+       ascii.c utf8.c \
        utf16_be.c utf16_le.c \
        utf32_be.c utf32_le.c \
        euc_jp.c euc_jp_prop.c \

diff --git a/src/Makefile.in b/src/Makefile.in
index 1a2cffc2efdae728a900f7cc7161e496f9066e76..1f0571029af5b7ddb7364937fc9f321930db6a3f 100644 (file)
--- a/src/Makefile.in
+++ b/src/Makefile.in
@@ -126,13 +126,14 @@ libonig_la_LIBADD =
 am_libonig_la_OBJECTS = regerror.lo regparse.lo regext.lo regcomp.lo \
        regexec.lo reggnu.lo regenc.lo regsyntax.lo regtrav.lo \
        regversion.lo st.lo regposix.lo regposerr.lo unicode.lo \
-       ascii.lo utf8.lo utf16_be.lo utf16_le.lo utf32_be.lo \
-       utf32_le.lo euc_jp.lo euc_jp_prop.lo sjis.lo sjis_prop.lo \
-       iso8859_1.lo iso8859_2.lo iso8859_3.lo iso8859_4.lo \
-       iso8859_5.lo iso8859_6.lo iso8859_7.lo iso8859_8.lo \
-       iso8859_9.lo iso8859_10.lo iso8859_11.lo iso8859_13.lo \
-       iso8859_14.lo iso8859_15.lo iso8859_16.lo euc_tw.lo euc_kr.lo \
-       big5.lo gb18030.lo koi8_r.lo cp1251.lo onig_init.lo
+       unicode_prop.lo ascii.lo utf8.lo utf16_be.lo utf16_le.lo \
+       utf32_be.lo utf32_le.lo euc_jp.lo euc_jp_prop.lo sjis.lo \
+       sjis_prop.lo iso8859_1.lo iso8859_2.lo iso8859_3.lo \
+       iso8859_4.lo iso8859_5.lo iso8859_6.lo iso8859_7.lo \
+       iso8859_8.lo iso8859_9.lo iso8859_10.lo iso8859_11.lo \
+       iso8859_13.lo iso8859_14.lo iso8859_15.lo iso8859_16.lo \
+       euc_tw.lo euc_kr.lo big5.lo gb18030.lo koi8_r.lo cp1251.lo \
+       onig_init.lo
 libonig_la_OBJECTS = $(am_libonig_la_OBJECTS)
 AM_V_lt = $(am__v_lt_@AM_V@)
 am__v_lt_ = $(am__v_lt_@AM_DEFAULT_V@)
@@ -330,7 +331,8 @@ libonig_la_SOURCES = regint.h regparse.h regenc.h st.h \
        regerror.c regparse.c regext.c regcomp.c regexec.c reggnu.c \
        regenc.c regsyntax.c regtrav.c regversion.c st.c \
        regposix.c regposerr.c \
-       unicode.c ascii.c utf8.c \
+       unicode.c unicode_prop.c \
+       ascii.c utf8.c \
        utf16_be.c utf16_le.c \
        utf32_be.c utf32_le.c \
        euc_jp.c euc_jp_prop.c \
@@ -485,6 +487,7 @@ distclean-compile:
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/sjis_prop.Plo@am__quote@
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/st.Plo@am__quote@
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/unicode.Plo@am__quote@
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/unicode_prop.Plo@am__quote@
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/utf16_be.Plo@am__quote@
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/utf16_le.Plo@am__quote@
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/utf32_be.Plo@am__quote@

diff --git a/src/regenc.h b/src/regenc.h
index 659e96182b2b2062ba59e43bf1ea456437c70c03..2016b5a91995a73d1aa96d5eb7f772119645fb90 100644 (file)
--- a/src/regenc.h
+++ b/src/regenc.h
@@ -147,6 +147,7 @@ ONIG_EXTERN int onigenc_mb4_code_to_mbc P_((OnigEncoding enc, OnigCodePoint code
 ONIG_EXTERN int onigenc_mb4_is_code_ctype P_((OnigEncoding enc, OnigCodePoint code, unsigned int ctype));
 ONIG_EXTERN struct PropertyNameCtype* euc_jp_lookup_property_name P_((register const char *str, register unsigned int len));
 ONIG_EXTERN struct PropertyNameCtype* sjis_lookup_property_name P_((register const char *str, register unsigned int len));
+ONIG_EXTERN struct PropertyNameCtype* unicode_lookup_property_name P_((register const char *str, register unsigned int len));
 
 /* in enc/unicode.c */
 ONIG_EXTERN int onigenc_unicode_is_code_ctype P_((OnigCodePoint code, unsigned int ctype));

diff --git a/src/unicode.c b/src/unicode.c
index 0972139c6f534f2edb253d1fecc2d8ca316c4554..0f7607cf2235ec90427d51f5ef33b7c0a6a70cec 100644 (file)
--- a/src/unicode.c
+++ b/src/unicode.c
@@ -10487,128 +10487,6 @@ static const CaseUnfold_13_Type CaseUnfold_13[] = {
 };
 
 
-static PosixBracketEntryType HashEntryData[] = {
-  { (UChar* )"NEWLINE",                0,  7 },
-  { (UChar* )"Alpha",                  1,  5 },
-  { (UChar* )"Blank",                  2,  5 },
-  { (UChar* )"Cntrl",                  3,  5 },
-  { (UChar* )"Digit",                  4,  5 },
-  { (UChar* )"Graph",                  5,  5 },
-  { (UChar* )"Lower",                  6,  5 },
-  { (UChar* )"Print",                  7,  5 },
-  { (UChar* )"Punct",                  8,  5 },
-  { (UChar* )"Space",                  9,  5 },
-  { (UChar* )"Upper",                 10,  5 },
-  { (UChar* )"XDigit",                11,  6 },
-  { (UChar* )"Word",                  12,  4 },
-  { (UChar* )"Alnum",                 13,  5 },
-  { (UChar* )"ASCII",                 14,  5 },
-
-#ifdef USE_UNICODE_PROPERTIES
-  { (UChar* )"Any",                   15,  3 },
-  { (UChar* )"Assigned",              16,  8 },
-  { (UChar* )"C",                     17,  1 },
-  { (UChar* )"Cc",                    18,  2 },
-  { (UChar* )"Cf",                    19,  2 },
-  { (UChar* )"Cn",                    20,  2 },
-  { (UChar* )"Co",                    21,  2 },
-  { (UChar* )"Cs",                    22,  2 },
-  { (UChar* )"L",                     23,  1 },
-  { (UChar* )"Ll",                    24,  2 },
-  { (UChar* )"Lm",                    25,  2 },
-  { (UChar* )"Lo",                    26,  2 },
-  { (UChar* )"Lt",                    27,  2 },
-  { (UChar* )"Lu",                    28,  2 },
-  { (UChar* )"M",                     29,  1 },
-  { (UChar* )"Mc",                    30,  2 },
-  { (UChar* )"Me",                    31,  2 },
-  { (UChar* )"Mn",                    32,  2 },
-  { (UChar* )"N",                     33,  1 },
-  { (UChar* )"Nd",                    34,  2 },
-  { (UChar* )"Nl",                    35,  2 },
-  { (UChar* )"No",                    36,  2 },
-  { (UChar* )"P",                     37,  1 },
-  { (UChar* )"Pc",                    38,  2 },
-  { (UChar* )"Pd",                    39,  2 },
-  { (UChar* )"Pe",                    40,  2 },
-  { (UChar* )"Pf",                    41,  2 },
-  { (UChar* )"Pi",                    42,  2 },
-  { (UChar* )"Po",                    43,  2 },
-  { (UChar* )"Ps",                    44,  2 },
-  { (UChar* )"S",                     45,  1 },
-  { (UChar* )"Sc",                    46,  2 },
-  { (UChar* )"Sk",                    47,  2 },
-  { (UChar* )"Sm",                    48,  2 },
-  { (UChar* )"So",                    49,  2 },
-  { (UChar* )"Z",                     50,  1 },
-  { (UChar* )"Zl",                    51,  2 },
-  { (UChar* )"Zp",                    52,  2 },
-  { (UChar* )"Zs",                    53,  2 },
-  { (UChar* )"Arabic",                54,  6 },
-  { (UChar* )"Armenian",              55,  8 },
-  { (UChar* )"Bengali",               56,  7 },
-  { (UChar* )"Bopomofo",              57,  8 },
-  { (UChar* )"Braille",               58,  7 },
-  { (UChar* )"Buginese",              59,  8 },
-  { (UChar* )"Buhid",                 60,  5 },
-  { (UChar* )"Canadian_Aboriginal",   61, 19 },
-  { (UChar* )"Cherokee",              62,  8 },
-  { (UChar* )"Common",                63,  6 },
-  { (UChar* )"Coptic",                64,  6 },
-  { (UChar* )"Cypriot",               65,  7 },
-  { (UChar* )"Cyrillic",              66,  8 },
-  { (UChar* )"Deseret",               67,  7 },
-  { (UChar* )"Devanagari",            68, 10 },
-  { (UChar* )"Ethiopic",              69,  8 },
-  { (UChar* )"Georgian",              70,  8 },
-  { (UChar* )"Glagolitic",            71, 10 },
-  { (UChar* )"Gothic",                72,  6 },
-  { (UChar* )"Greek",                 73,  5 },
-  { (UChar* )"Gujarati",              74,  8 },
-  { (UChar* )"Gurmukhi",              75,  8 },
-  { (UChar* )"Han",                   76,  3 },
-  { (UChar* )"Hangul",                77,  6 },
-  { (UChar* )"Hanunoo",               78,  7 },
-  { (UChar* )"Hebrew",                79,  6 },
-  { (UChar* )"Hiragana",              80,  8 },
-  { (UChar* )"Inherited",             81,  9 },
-  { (UChar* )"Kannada",               82,  7 },
-  { (UChar* )"Katakana",              83,  8 },
-  { (UChar* )"Kharoshthi",            84, 10 },
-  { (UChar* )"Khmer",                 85,  5 },
-  { (UChar* )"Lao",                   86,  3 },
-  { (UChar* )"Latin",                 87,  5 },
-  { (UChar* )"Limbu",                 88,  5 },
-  { (UChar* )"Linear_B",              89,  8 },
-  { (UChar* )"Malayalam",             90,  9 },
-  { (UChar* )"Mongolian",             91,  9 },
-  { (UChar* )"Myanmar",               92,  7 },
-  { (UChar* )"New_Tai_Lue",           93, 11 },
-  { (UChar* )"Ogham",                 94,  5 },
-  { (UChar* )"Old_Italic",            95, 10 },
-  { (UChar* )"Old_Persian",           96, 11 },
-  { (UChar* )"Oriya",                 97,  5 },
-  { (UChar* )"Osmanya",               98,  7 },
-  { (UChar* )"Runic",                 99,  5 },
-  { (UChar* )"Shavian",              100,  7 },
-  { (UChar* )"Sinhala",              101,  7 },
-  { (UChar* )"Syloti_Nagri",         102, 12 },
-  { (UChar* )"Syriac",               103,  6 },
-  { (UChar* )"Tagalog",              104,  7 },
-  { (UChar* )"Tagbanwa",             105,  8 },
-  { (UChar* )"Tai_Le",               106,  6 },
-  { (UChar* )"Tamil",                107,  5 },
-  { (UChar* )"Telugu",               108,  6 },
-  { (UChar* )"Thaana",               109,  6 },
-  { (UChar* )"Thai",                 110,  4 },
-  { (UChar* )"Tibetan",              111,  7 },
-  { (UChar* )"Tifinagh",             112,  8 },
-  { (UChar* )"Ugaritic",             113,  8 },
-  { (UChar* )"Yi",                   114,  2 },
-#endif /* USE_UNICODE_PROPERTIES */
-  { (UChar* )NULL,                    -1,  0 }
-};
-
 #ifdef USE_UNICODE_PROPERTIES
 #define CODE_RANGES_NUM     115
 #else
@@ -10780,32 +10658,14 @@ onigenc_utf16_32_get_ctype_code_range(OnigCtype ctype, OnigCodePoint* sb_out,
 
 #define PROPERTY_NAME_MAX_SIZE    20
 
-static st_table* NameCtypeTable;
-
-static int
-init_name_ctype_table(void)
-{
-  PosixBracketEntryType *pb;
-
-  NameCtypeTable = onig_st_init_strend_table_with_size(100);
-  if (ONIG_IS_NULL(NameCtypeTable)) return ONIGERR_MEMORY;
-
-  for (pb = HashEntryData; ONIG_IS_NOT_NULL(pb->name); pb++) {
-    onig_st_insert_strend(NameCtypeTable, pb->name, pb->name + pb->len,
-                         (st_data_t )pb->ctype);
-  }
-
-  return 0;
-}
-
 extern int
 onigenc_unicode_property_name_to_ctype(OnigEncoding enc, UChar* name, UChar* end)
 {
   int len;
-  hash_data_type ctype;
-  UChar buf[PROPERTY_NAME_MAX_SIZE];
   UChar *p;
   OnigCodePoint code;
+  struct PropertyNameCtype* pc;
+  char buf[PROPERTY_NAME_MAX_SIZE];
 
   p = name;
   len = 0;
@@ -10814,7 +10674,7 @@ onigenc_unicode_property_name_to_ctype(OnigEncoding enc, UChar* name, UChar* end
     if (code >= 0x80)
       return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
 
-    buf[len++] = (UChar )code;
+    buf[len++] = (char )code;
     if (len >= PROPERTY_NAME_MAX_SIZE)
       return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
 
@@ -10823,11 +10683,17 @@ onigenc_unicode_property_name_to_ctype(OnigEncoding enc, UChar* name, UChar* end
 
   buf[len] = 0;
 
-  if (onig_st_lookup_strend(NameCtypeTable, buf, buf + len, &ctype) == 0) {
-    return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
+  pc = unicode_lookup_property_name(buf, len);
+  if (pc != 0) {
+#ifndef USE_UNICODE_PROPERTIES
+    if (pc->ctype > ONIGENC_MAX_STD_CTYPE)
+      return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
+#endif
+
+    return pc->ctype;
   }
 
-  return (int )ctype;
+  return ONIGERR_INVALID_CHAR_PROPERTY_NAME;
 }
 
 
@@ -10877,8 +10743,6 @@ static st_table* Unfold3Table;
 extern void
 onigenc_end_unicode(void)
 {
-  if (NameCtypeTable != 0) st_free_table(NameCtypeTable);
-
   if (FoldTable    != 0) st_free_table(FoldTable);
   if (Unfold1Table != 0) st_free_table(Unfold1Table);
   if (Unfold2Table != 0) st_free_table(Unfold2Table);
@@ -11350,10 +11214,6 @@ onigenc_unicode_initialize(void)
   if (unicode_inited != 0)
     return 0;
 
-  r = init_name_ctype_table();
-  if (r != 0)
-    return r;
-
   r = init_case_fold_table();
   if (r != 0)
     return r;

diff --git a/src/unicode_prop.c b/src/unicode_prop.c
new file mode 100644 (file)
index 0000000..d1d9052
--- /dev/null
+++ b/src/unicode_prop.c
@@ -0,0 +1,414 @@
+/* ANSI-C code produced by gperf version 3.0.4 */
+/* Command-line: gperf -pt -T -L ANSI-C -N unicode_lookup_property_name --output-file unicode_prop.c unicode_prop.gperf  */
+/* Computed positions: -k'1,3,$' */
+
+#if !((' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
+      && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
+      && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
+      && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
+      && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
+      && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
+      && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
+      && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
+      && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
+      && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
+      && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
+      && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
+      && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
+      && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
+      && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
+      && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
+      && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
+      && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
+      && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
+      && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
+      && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
+      && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
+      && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126))
+/* The character set is not based on ISO-646.  */
+#error "gperf generated tables don't work with this execution character set. Please report a bug to <bug-gnu-gperf@gnu.org>."
+#endif
+
+#line 1 "unicode_prop.gperf"
+
+#include <string.h>
+#include "regenc.h"
+
+#define TOTAL_KEYWORDS 115
+#define MIN_WORD_LENGTH 1
+#define MAX_WORD_LENGTH 19
+#define MIN_HASH_VALUE 1
+#define MAX_HASH_VALUE 251
+/* maximum key range = 251, duplicates = 0 */
+
+#ifdef __GNUC__
+__inline
+#else
+#ifdef __cplusplus
+inline
+#endif
+#endif
+static unsigned int
+hash (register const char *str, register unsigned int len)
+{
+  static unsigned char asso_values[] =
+    {
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252,  20,   5,   5, 100,   0,
+      252,   0, 105,   0, 252,  85,  50,  20, 120,  65,
+        0, 252,   5,  10,   0,  60, 252,  10,   0, 120,
+      125, 252, 252, 252, 252, 252, 252,  60, 252,  15,
+        2,  70,  47, 100,   0,  40,   7,  90,  65, 100,
+       25,   0,  30,   5,  35,   7,  15,  75,   5,   5,
+       15,   0, 252,   0, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252, 252, 252,
+      252, 252, 252, 252, 252, 252, 252, 252
+    };
+  register int hval = len;
+
+  switch (hval)
+    {
+      default:
+        hval += asso_values[(unsigned char)str[2]+2];
+      /*FALLTHROUGH*/
+      case 2:
+      case 1:
+        hval += asso_values[(unsigned char)str[0]];
+        break;
+    }
+  return hval + asso_values[(unsigned char)str[len - 1]];
+}
+
+#ifdef __GNUC__
+__inline
+#if defined __GNUC_STDC_INLINE__ || defined __GNUC_GNU_INLINE__
+__attribute__ ((__gnu_inline__))
+#endif
+#endif
+struct PropertyNameCtype *
+unicode_lookup_property_name (register const char *str, register unsigned int len)
+{
+  static struct PropertyNameCtype wordlist[] =
+    {
+      {""},
+#line 49 "unicode_prop.gperf"
+      {"P",                     37},
+#line 55 "unicode_prop.gperf"
+      {"Po",                    43},
+      {""},
+#line 51 "unicode_prop.gperf"
+      {"Pd",                    39},
+      {""}, {""},
+#line 33 "unicode_prop.gperf"
+      {"Co",                    21},
+#line 124 "unicode_prop.gperf"
+      {"Tifinagh",             112},
+#line 56 "unicode_prop.gperf"
+      {"Ps",                    44},
+      {""},
+#line 29 "unicode_prop.gperf"
+      {"C",                     17},
+#line 61 "unicode_prop.gperf"
+      {"So",                    49},
+      {""},
+#line 34 "unicode_prop.gperf"
+      {"Cs",                    22},
+      {""}, {""},
+#line 50 "unicode_prop.gperf"
+      {"Pc",                    38},
+#line 93 "unicode_prop.gperf"
+      {"Inherited",             81},
+#line 72 "unicode_prop.gperf"
+      {"Buhid",                 60},
+#line 17 "unicode_prop.gperf"
+      {"Graph",                  5},
+#line 57 "unicode_prop.gperf"
+      {"S",                     45},
+#line 30 "unicode_prop.gperf"
+      {"Cc",                    18},
+#line 27 "unicode_prop.gperf"
+      {"Any",                   15},
+      {""},
+#line 26 "unicode_prop.gperf"
+      {"ASCII",                 14},
+#line 84 "unicode_prop.gperf"
+      {"Gothic",                72},
+#line 58 "unicode_prop.gperf"
+      {"Sc",                    46},
+      {""}, {""},
+#line 81 "unicode_prop.gperf"
+      {"Ethiopic",              69},
+#line 24 "unicode_prop.gperf"
+      {"Word",                  12},
+#line 32 "unicode_prop.gperf"
+      {"Cn",                    20},
+      {""},
+#line 123 "unicode_prop.gperf"
+      {"Tibetan",              111},
+      {""},
+#line 75 "unicode_prop.gperf"
+      {"Common",                63},
+#line 42 "unicode_prop.gperf"
+      {"Mc",                    30},
+#line 82 "unicode_prop.gperf"
+      {"Georgian",              70},
+      {""},
+#line 83 "unicode_prop.gperf"
+      {"Glagolitic",            71},
+#line 41 "unicode_prop.gperf"
+      {"M",                     29},
+#line 54 "unicode_prop.gperf"
+      {"Pi",                    42},
+#line 78 "unicode_prop.gperf"
+      {"Cyrillic",              66},
+      {""}, {""},
+#line 115 "unicode_prop.gperf"
+      {"Syriac",               103},
+#line 44 "unicode_prop.gperf"
+      {"Mn",                    32},
+#line 69 "unicode_prop.gperf"
+      {"Bopomofo",              57},
+#line 53 "unicode_prop.gperf"
+      {"Pf",                    41},
+#line 20 "unicode_prop.gperf"
+      {"Punct",                  8},
+      {""},
+#line 38 "unicode_prop.gperf"
+      {"Lo",                    26},
+#line 67 "unicode_prop.gperf"
+      {"Armenian",              55},
+#line 31 "unicode_prop.gperf"
+      {"Cf",                    19},
+#line 111 "unicode_prop.gperf"
+      {"Runic",                 99},
+#line 66 "unicode_prop.gperf"
+      {"Arabic",                54},
+#line 112 "unicode_prop.gperf"
+      {"Shavian",              100},
+#line 98 "unicode_prop.gperf"
+      {"Lao",                   86},
+#line 122 "unicode_prop.gperf"
+      {"Thai",                 110},
+      {""},
+#line 76 "unicode_prop.gperf"
+      {"Coptic",                64},
+#line 77 "unicode_prop.gperf"
+      {"Cypriot",               65},
+#line 87 "unicode_prop.gperf"
+      {"Gurmukhi",              75},
+      {""}, {""}, {""},
+#line 39 "unicode_prop.gperf"
+      {"Lt",                    27},
+      {""}, {""},
+#line 119 "unicode_prop.gperf"
+      {"Tamil",                107},
+      {""},
+#line 52 "unicode_prop.gperf"
+      {"Pe",                    40},
+      {""}, {""}, {""}, {""},
+#line 104 "unicode_prop.gperf"
+      {"Myanmar",               92},
+      {""}, {""},
+#line 15 "unicode_prop.gperf"
+      {"Cntrl",                  3},
+#line 121 "unicode_prop.gperf"
+      {"Thaana",               109},
+#line 68 "unicode_prop.gperf"
+      {"Bengali",               56},
+      {""},
+#line 103 "unicode_prop.gperf"
+      {"Mongolian",             91},
+#line 99 "unicode_prop.gperf"
+      {"Latin",                 87},
+      {""},
+#line 114 "unicode_prop.gperf"
+      {"Syloti_Nagri",         102},
+      {""}, {""},
+#line 18 "unicode_prop.gperf"
+      {"Lower",                  6},
+      {""},
+#line 43 "unicode_prop.gperf"
+      {"Me",                    31},
+#line 101 "unicode_prop.gperf"
+      {"Linear_B",              89},
+      {""}, {""}, {""},
+#line 70 "unicode_prop.gperf"
+      {"Braille",               58},
+#line 125 "unicode_prop.gperf"
+      {"Ugaritic",             113},
+      {""},
+#line 21 "unicode_prop.gperf"
+      {"Space",                  9},
+#line 35 "unicode_prop.gperf"
+      {"L",                     23},
+#line 59 "unicode_prop.gperf"
+      {"Sk",                    47},
+      {""}, {""},
+#line 28 "unicode_prop.gperf"
+      {"Assigned",              16},
+#line 120 "unicode_prop.gperf"
+      {"Telugu",               108},
+#line 113 "unicode_prop.gperf"
+      {"Sinhala",              101},
+#line 117 "unicode_prop.gperf"
+      {"Tagbanwa",             105},
+      {""},
+#line 19 "unicode_prop.gperf"
+      {"Print",                  7},
+#line 23 "unicode_prop.gperf"
+      {"XDigit",                11},
+#line 60 "unicode_prop.gperf"
+      {"Sm",                    48},
+#line 86 "unicode_prop.gperf"
+      {"Gujarati",              74},
+      {""},
+#line 14 "unicode_prop.gperf"
+      {"Blank",                  2},
+      {""},
+#line 36 "unicode_prop.gperf"
+      {"Ll",                    24},
+#line 91 "unicode_prop.gperf"
+      {"Hebrew",                79},
+#line 73 "unicode_prop.gperf"
+      {"Canadian_Aboriginal",   61},
+#line 13 "unicode_prop.gperf"
+      {"Alpha",                  1},
+      {""},
+#line 48 "unicode_prop.gperf"
+      {"No",                    36},
+#line 71 "unicode_prop.gperf"
+      {"Buginese",              59},
+#line 46 "unicode_prop.gperf"
+      {"Nd",                    34},
+#line 97 "unicode_prop.gperf"
+      {"Khmer",                 85},
+      {""},
+#line 40 "unicode_prop.gperf"
+      {"Lu",                    28},
+      {""}, {""},
+#line 100 "unicode_prop.gperf"
+      {"Limbu",                 88},
+      {""},
+#line 110 "unicode_prop.gperf"
+      {"Osmanya",               98},
+      {""},
+#line 65 "unicode_prop.gperf"
+      {"Zs",                    53},
+#line 22 "unicode_prop.gperf"
+      {"Upper",                 10},
+      {""},
+#line 107 "unicode_prop.gperf"
+      {"Old_Italic",            95},
+      {""}, {""}, {""}, {""},
+#line 90 "unicode_prop.gperf"
+      {"Hanunoo",               78},
+      {""}, {""}, {""}, {""},
+#line 116 "unicode_prop.gperf"
+      {"Tagalog",              104},
+#line 108 "unicode_prop.gperf"
+      {"Old_Persian",           96},
+      {""},
+#line 96 "unicode_prop.gperf"
+      {"Kharoshthi",            84},
+      {""},
+#line 37 "unicode_prop.gperf"
+      {"Lm",                    25},
+      {""},
+#line 102 "unicode_prop.gperf"
+      {"Malayalam",             90},
+#line 25 "unicode_prop.gperf"
+      {"Alnum",                 13},
+      {""},
+#line 64 "unicode_prop.gperf"
+      {"Zp",                    52},
+#line 95 "unicode_prop.gperf"
+      {"Katakana",              83},
+      {""},
+#line 16 "unicode_prop.gperf"
+      {"Digit",                  4},
+      {""},
+#line 126 "unicode_prop.gperf"
+      {"Yi",                   114},
+#line 88 "unicode_prop.gperf"
+      {"Han",                   76},
+      {""},
+#line 80 "unicode_prop.gperf"
+      {"Devanagari",            68},
+#line 118 "unicode_prop.gperf"
+      {"Tai_Le",               106},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+      {""},
+#line 106 "unicode_prop.gperf"
+      {"Ogham",                 94},
+      {""}, {""}, {""}, {""},
+#line 94 "unicode_prop.gperf"
+      {"Kannada",               82},
+#line 74 "unicode_prop.gperf"
+      {"Cherokee",              62},
+      {""}, {""}, {""},
+#line 47 "unicode_prop.gperf"
+      {"Nl",                    35},
+#line 92 "unicode_prop.gperf"
+      {"Hiragana",              80},
+      {""}, {""}, {""},
+#line 63 "unicode_prop.gperf"
+      {"Zl",                    51},
+      {""}, {""},
+#line 85 "unicode_prop.gperf"
+      {"Greek",                 73},
+      {""},
+#line 79 "unicode_prop.gperf"
+      {"Deseret",               67},
+      {""}, {""}, {""},
+#line 105 "unicode_prop.gperf"
+      {"New_Tai_Lue",           93},
+      {""}, {""}, {""}, {""},
+#line 89 "unicode_prop.gperf"
+      {"Hangul",                77},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+      {""}, {""}, {""}, {""},
+#line 109 "unicode_prop.gperf"
+      {"Oriya",                 97},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+      {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""}, {""},
+      {""}, {""},
+#line 45 "unicode_prop.gperf"
+      {"N",                     33},
+      {""}, {""}, {""}, {""}, {""},
+#line 12 "unicode_prop.gperf"
+      {"NEWLINE",                0},
+      {""}, {""}, {""},
+#line 62 "unicode_prop.gperf"
+      {"Z",                     50}
+    };
+
+  if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
+    {
+      register int key = hash (str, len);
+
+      if (key <= MAX_HASH_VALUE && key >= 0)
+        {
+          register const char *s = wordlist[key].name;
+
+          if (*str == *s && !strcmp (str + 1, s + 1))
+            return &wordlist[key];
+        }
+    }
+  return 0;
+}

diff --git a/src/unicode_prop.gperf b/src/unicode_prop.gperf
new file mode 100644 (file)
index 0000000..3b36a02
--- /dev/null
+++ b/src/unicode_prop.gperf
@@ -0,0 +1,126 @@
+%{
+#include <string.h>
+#include "regenc.h"
+%}
+
+struct PropertyNameCtype {
+  char *name;
+  int ctype;
+};
+
+%%
+NEWLINE,                0
+Alpha,                  1
+Blank,                  2
+Cntrl,                  3
+Digit,                  4
+Graph,                  5
+Lower,                  6
+Print,                  7
+Punct,                  8
+Space,                  9
+Upper,                 10
+XDigit,                11
+Word,                  12
+Alnum,                 13
+ASCII,                 14
+Any,                   15
+Assigned,              16
+C,                     17
+Cc,                    18
+Cf,                    19
+Cn,                    20
+Co,                    21
+Cs,                    22
+L,                     23
+Ll,                    24
+Lm,                    25
+Lo,                    26
+Lt,                    27
+Lu,                    28
+M,                     29
+Mc,                    30
+Me,                    31
+Mn,                    32
+N,                     33
+Nd,                    34
+Nl,                    35
+No,                    36
+P,                     37
+Pc,                    38
+Pd,                    39
+Pe,                    40
+Pf,                    41
+Pi,                    42
+Po,                    43
+Ps,                    44
+S,                     45
+Sc,                    46
+Sk,                    47
+Sm,                    48
+So,                    49
+Z,                     50
+Zl,                    51
+Zp,                    52
+Zs,                    53
+Arabic,                54
+Armenian,              55
+Bengali,               56
+Bopomofo,              57
+Braille,               58
+Buginese,              59
+Buhid,                 60
+Canadian_Aboriginal,   61
+Cherokee,              62
+Common,                63
+Coptic,                64
+Cypriot,               65
+Cyrillic,              66
+Deseret,               67
+Devanagari,            68
+Ethiopic,              69
+Georgian,              70
+Glagolitic,            71
+Gothic,                72
+Greek,                 73
+Gujarati,              74
+Gurmukhi,              75
+Han,                   76
+Hangul,                77
+Hanunoo,               78
+Hebrew,                79
+Hiragana,              80
+Inherited,             81
+Kannada,               82
+Katakana,              83
+Kharoshthi,            84
+Khmer,                 85
+Lao,                   86
+Latin,                 87
+Limbu,                 88
+Linear_B,              89
+Malayalam,             90
+Mongolian,             91
+Myanmar,               92
+New_Tai_Lue,           93
+Ogham,                 94
+Old_Italic,            95
+Old_Persian,           96
+Oriya,                 97
+Osmanya,               98
+Runic,                 99
+Shavian,              100
+Sinhala,              101
+Syloti_Nagri,         102
+Syriac,               103
+Tagalog,              104
+Tagbanwa,             105
+Tai_Le,               106
+Tamil,                107
+Telugu,               108
+Thaana,               109
+Thai,                 110
+Tibetan,              111
+Tifinagh,             112
+Ugaritic,             113
+Yi,                   114