unicode 0.4.2-x86-mswin32-60 → 0.4.3-x86-mswin32-60

data/ext/unicode/wstring.c

@@ -43,7 +43,10 @@ WStr_free(WString* str)
 {
   str->size = 0;
   str->len = 0;
-  free(str->str);
+  if (str->str) {
+    free(str->str);
+    str->str = NULL;
+  }
 }
 
 int
@@ -164,6 +167,59 @@ WStr_allocWithUTF8(WString* s, const char* in)
   return s;
 }
 
+WString*
+WStr_allocWithUTF8L(WString* s, const char* in, int len)
+{
+  int i;
+  int u = 0;
+  int rest = 0;
+
+  WStr_alloc(s);
+  if (in == NULL)
+    return s;
+  for (i = 0; i < len; i++) {
+    unsigned char c = in[i];
+    if ((c & 0xc0) == 0x80) {
+      if (rest == 0)
+	return NULL;
+      u = (u << 6) | (c & 63);
+      rest--;
+      if (rest == 0) {
+	WStr_addWChar(s, u);
+      }
+    }
+    else if ((c & 0x80) == 0) {      /* 0b0nnnnnnn (7bit) */
+      WStr_addWChar(s, c);
+      rest = 0;
+    }
+    else if ((c & 0xe0) == 0xc0) {      /* 0b110nnnnn (11bit) */
+      rest = 1;
+      u = c & 31;
+    }
+    else if ((c & 0xf0) == 0xe0) {      /* 0b1110nnnn (16bit) */
+      rest = 2;
+      u = c & 15;
+    }
+    else if ((c & 0xf8) == 0xf0) {      /* 0b11110nnn (21bit) */
+      rest = 3;
+      u = c & 7;
+    }
+    else if ((c & 0xfc) == 0xf8) {      /* 0b111110nn (26bit) */
+      rest = 4;
+      u = c & 3;
+    }
+    else if ((c & 0xfe) == 0xfc) {      /* 0b1111110n (31bit) */
+      rest = 5;
+      u = c & 1;
+    }
+    else {
+      return NULL;
+    }
+  }
+
+  return s;
+}
+
 UString*
 WStr_convertIntoUString(WString* wstr, UString* ustr)
 {
@@ -176,6 +232,18 @@ WStr_convertIntoUString(WString* wstr, UString* ustr)
   return ustr;
 }
 
+UString*
+WStr_convertIntoUString2(WString* wstr, int start, int len, UString* ustr)
+{
+  int i;
+
+  for (i = start; i < wstr->len && i < start + len; i++) {
+    UniStr_addWChar(ustr, wstr->str[i]);
+  }
+
+  return ustr;
+}
+
 void
 WStr_dump(WString* s)
 {

data/ext/unicode/wstring.h

@@ -24,6 +24,7 @@ typedef struct _WString {
 
 WString* WStr_alloc(WString* str);
 WString* WStr_allocWithUTF8(WString* s, const char* u);
+WString* WStr_allocWithUTF8L(WString* s, const char* u, int len);
 WString* WStr_enlarge(WString* str, int size);
 void WStr_free(WString* str);
 int WStr_addWChars(WString* s, const int* a, int len);
@@ -32,6 +33,7 @@ int WStr_pushWString(WString* s, const WString* add);
 int WStr_addWChar2(WString* s, int a1, int a2);
 int WStr_addWChar3(WString* s, int a1, int a2, int a3);
 UString* WStr_convertIntoUString(WString* wstr, UString* ustr);
+UString* WStr_convertIntoUString2(WString* wstr, int start, int len, UString* ustr);
 void WStr_dump(WString* s);
 
 #ifdef __cplusplus

data/tools/README

@@ -1,6 +1,7 @@
 The bundled unidata.map is created from UnicodeData.txt,
-DerivedNormalizationProps.txt and SpecialCasing.txt of Unicode 6.0.
+DerivedNormalizationProps.txt, SpecialCasing.txt and EastAsianWidth.txt
+of Unicode 6.0.
 
 To update unidata.map,
 
-  ruby mkunidata.rb UnicodeData.txt DerivedNormalizationProps.txt SpecialCasing.txt > unidata.map
+  ruby mkunidata.rb UnicodeData.txt DerivedNormalizationProps.txt SpecialCasing.txt EastAsianWidth.txt  > unidata.map

data/tools/mkunidata.rb

@@ -7,22 +7,102 @@
 HEAD=<<EOS
 /*
  * UnicodeData
- * Copyright 1999, 2004, 2010 by yoshidam
+ * Copyright 1999, 2004, 2010, 2012 by yoshidam
  *
  */
 
 #ifndef _UNIDATA_MAP
 #define _UNIDATA_MAP
 
+EOS
+
+HEAD1=<<EOS
+
+enum GeneralCategory {
+  /* Letter */
+  c_Lu = 1, c_Ll, c_Lt, c_LC, c_Lm, c_Lo,
+  /* Mark */
+  c_Mn, c_Mc, c_Me,
+  /* Number */
+  c_Nd, c_Nl, c_No,
+  /* Punctuation */
+  c_Pc, c_Pd, c_Ps, c_Pe, c_Pi, c_Pf, c_Po,
+  /* Symbol */
+  c_Sm, c_Sc, c_Sk, c_So,
+  /* Separator */
+  c_Zs, c_Zl, c_Zp,
+  /* Other */
+  c_Cc, c_Cf, c_Cs, c_Co, c_Cn
+};
+
+const char* const gencat_abbr[] = {
+  "", /* 0 */
+  /* Letter */
+  "Lu", "Ll", "Lt", "LC", "Lm", "Lo",
+  /* Mark */
+  "Mn", "Mc", "Me",
+  /* Number */
+  "Nd", "Nl", "No",
+  /* Punctuation */
+  "Pc", "Pd", "Ps", "Pe", "Pi", "Pf", "Po",
+  /* Symbol */
+  "Sm", "Sc", "Sk", "So",
+  /* Separator */
+  "Zs", "Zl", "Zp",
+  /* Other */
+  "Cc", "Cf", "Cs", "Co", "Cn"
+};
+
+const char* const gencat_long[] = {
+  "",
+  "Uppercase_Letter",
+  "Lowercase_Letter",
+  "Titlecase_Letter",
+  "Cased_Letter",
+  "Modifier_Letter",
+  "Other_Letter",
+  "Nonspacing_Mark",
+  "Spacing_Mark",
+  "Enclosing_Mark",
+  "Decimal_Number",
+  "Letter_Number",
+  "Other_Number",
+  "Connector_Punctuation",
+  "Dash_Punctuation",
+  "Open_Punctuation",
+  "Close_Punctuation",
+  "Initial_Punctuation",
+  "Final_Punctuation",
+  "Other_Punctuation",
+  "Math_Symbol",
+  "Currency_Symbol",
+  "Modifier_Symbol",
+  "Other_Symbol",
+  "Space_Separator",
+  "Line_Separator",
+  "Paragraph_Separator",
+  "Control",
+  "Format",
+  "Surrogate",
+  "Private_Use",
+  "Unassigned"
+};
+
+enum EastAsianWidth {
+  w_N = 1, w_A, w_H, w_W, w_F, w_Na
+};
+
 struct unicode_data {
   const int code;
-  const int combining_class;
-  const int exclusion;
   const char* const canon;
   const char* const compat;
-  const char* uppercase;
-  const char* lowercase;
-  const char* titlecase;
+  const char* const uppercase;
+  const char* const lowercase;
+  const char* const titlecase;
+  const unsigned char combining_class;
+  const unsigned char exclusion;
+  const unsigned char general_category;
+  const unsigned char east_asian_width;
 };
 
 static const struct unicode_data unidata[] = {
@@ -81,6 +161,11 @@ def printstr(str)
   return '"' + ret + '"'
 end
 
+if ARGV.length != 4
+  puts "Usage: #{$0} <UnicodeData.txt> <DerivedNormalizationProps.txt> <SpecialCasing.txt> <EastAsianWidth.txt>"
+  exit 0
+end
+
 ## scan Composition Exclusions
 exclusion = {}
 open(ARGV[1]) do |f|
@@ -123,6 +208,7 @@ end
 
 ## scan UnicodeData
 udata = {}
+range_data = []
 open(ARGV[0]) do |f|
   while l = f.gets
     l.chomp!
@@ -135,13 +221,46 @@ open(ARGV[0]) do |f|
     upcase = hex_or_nil(upcase)
     lowcase = hex_or_nil(lowcase)
     titlecase = hex_or_nil(titlecase)
-    udata[code] = [ccclass, canon, compat, upcase, lowcase, titlecase]
+    udata[code] = [ccclass, canon, compat, upcase, lowcase, titlecase, gencat]
+    if charname =~ /^<(.*, (First|Last))>$/
+      charname = $1.upcase.gsub(/,? /, '_')
+      range_data << [charname, code]
+    end
+  end
+end
+
+## scan EastAsianWidth
+ea_width = {}
+open(ARGV[3]) do |f|
+  while l = f.gets
+    l.chomp!
+    next if l =~ /^\#/ || l =~ /^$/
+    l =~ /^(.*)\s+#\s*(.*)$/
+    l = $1
+    comment = $2
+    code,width = l.split(/;/)
+    if code =~ /\.\./
+      start_code, end_code = code.split('..')
+      start_code = start_code.hex
+      end_code = end_code.hex
+      (start_code..end_code).each do |code|
+        ea_width[code] = width
+      end
+      next
+    end
+    code = code.hex
+    ea_width[code] = width
   end
 end
 
 print HEAD
+range_data.each do |charname, code|
+  printf("#define %s\t(0x%04x)\n", charname, code)
+end
+
+print HEAD1
 udata.sort.each do |code, data|
-  ccclass, canon, compat, upcase, lowcase, titlecase = data
+  ccclass, canon, compat, upcase, lowcase, titlecase, gencat = data
   ## Exclusions
   ex = 0
   if exclusion[code]  ## Script-specifics or Post Composition Version
@@ -160,10 +279,15 @@ udata.sort.each do |code, data|
     titlecase = casing[code][1] if casing[code][1]
     upcase = casing[code][2] if casing[code][2]
   end
-  printf("  { 0x%04x, %d, %d, %s, %s, %s, %s, %s }, \n",
-         code, ccclass, ex, printstr(canon),
+  width = 'N'
+  if ea_width[code]
+    width = ea_width[code]
+  end
+
+  printf("  { 0x%04x, %s, %s, %s, %s, %s, %d, %d, c_%s, w_%s }, \n",
+         code, printstr(canon),
          printstr(compat), printstr(upcase), printstr(lowcase),
-         printstr(titlecase))
+         printstr(titlecase), ccclass, ex, gencat, width)
 end
-printf("  { -1, 0, 0, NULL, NULL, NULL, NULL, NULL }\n")
+printf("  { -1, NULL, NULL, NULL, NULL, NULL, 0, 0, 0, 0 }\n")
 print TAIL

data/unicode.gemspec

@@ -2,11 +2,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{unicode}
-  s.version = "0.4.2"
+  s.version = "0.4.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = [%q{Yoshida Masato}]
-  s.date = %q{2011-02-03}
+  s.date = %q{2012-08-07}
   s.email = %q{yoshidam@yoshidam.net}
   s.extensions = [%q{ext/unicode/extconf.rb}]
   s.extra_rdoc_files = [%q{README}]

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: unicode
 version: !ruby/object:Gem::Version 
-  hash: 11
+  hash: 9
   prerelease: 
   segments: 
   - 0
   - 4
-  - 2
-  version: 0.4.2
+  - 3
+  version: 0.4.3
 platform: x86-mswin32-60
 authors: 
 - Yoshida Masato
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-02-03 00:00:00 Z
+date: 2012-08-07 00:00:00 Z
 dependencies: []
 
 description: Unicode normalization library.
@@ -73,7 +73,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.8.17
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Unicode normalization library.