Add IntlChar class to intl extension

ext/intl/config.m4

@@ -84,6 +84,7 @@ if test "$PHP_INTL" != "no"; then
     breakiterator/rulebasedbreakiterator_methods.cpp \
     breakiterator/codepointiterator_internal.cpp \
     breakiterator/codepointiterator_methods.cpp \
+    uchar/uchar.c \
     idn/idn.c \
     $icu_spoof_src, $ext_shared,,$ICU_INCS -Wno-write-strings -D__STDC_LIMIT_MACROS -DZEND_ENABLE_STATIC_TSRMLS_CACHE=1)
   PHP_ADD_BUILD_DIR($ext_builddir/collator)
@@ -102,4 +103,5 @@ if test "$PHP_INTL" != "no"; then
   PHP_ADD_BUILD_DIR($ext_builddir/idn)
   PHP_ADD_BUILD_DIR($ext_builddir/spoofchecker)
   PHP_ADD_BUILD_DIR($ext_builddir/breakiterator)
+  PHP_ADD_BUILD_DIR($ext_builddir/uchar)
 fi

ext/intl/config.w32

@@ -72,6 +72,9 @@ if (PHP_INTL != "no") {
 				dateformat_helpers.cpp \
 				dateformat_create.cpp \
 				", "intl");
+		ADD_SOURCES(configure_module_dirname + "/uchar", "\
+				uchar.c",
+				"intl");
 		ADD_SOURCES(configure_module_dirname + "/idn", "\
 				idn.c",
 				"intl");

ext/intl/php_intl.c

@@ -85,6 +85,7 @@
 #include "breakiterator/breakiterator_iterators.h"
 
 #include "idn/idn.h"
+#include "uchar/uchar.h"
 
 #if U_ICU_VERSION_MAJOR_NUM * 1000 + U_ICU_VERSION_MINOR_NUM >= 4002
 # include "spoofchecker/spoofchecker_class.h"
@@ -1003,6 +1004,9 @@ PHP_MINIT_FUNCTION( intl )
 	/* 'Converter' class for codepage conversions */
 	php_converter_minit(INIT_FUNC_ARGS_PASSTHRU);
 
+	/* IntlChar class */
+	php_uchar_minit(INIT_FUNC_ARGS_PASSTHRU);
+
 	return SUCCESS;
 }
 /* }}} */

ext/intl/uchar/tests/basic-functionality.phpt

@@ -0,0 +1,153 @@
+--TEST--
+IntlChar basic functionality
+--FILE--
+<?php
+
+function unicode_info($cp) {
+  $proplist = array(
+    IntlChar::PROPERTY_ALPHABETIC,
+  );
+  $methodList = array(
+    'isUAlphabetic',
+    'isUUppercase', 'isupper',
+    'isULowercase', 'islower',
+    'isUWhiteSpace', 'isWhitespace',
+    'istitle', 'isdigit', 'isalpha', 'isalnum',
+    'isxdigit', 'ispunct', 'ispunct', 'isgraph',
+    'isblank', 'isdefined', 'isspace', 'iscntrl',
+    'isMirrored', 'isIDStart', 'isIDPart',
+    'getBlockCode', 'charName',
+  );
+
+  $ncp = IntlChar::ord($cp);
+  printf("Codepoint U+%04x\n", $ncp);
+
+  foreach($proplist as $prop) {
+    printf("  hasBinaryProperty(%s): %s\n",
+      IntlChar::getPropertyName($prop),
+      IntlChar::hasBinaryProperty($cp, $prop) ? "true" : "false"
+    );
+  }
+  foreach($methodList as $method) {
+    echo "  $method(): ";
+    var_dump(IntlChar::$method($cp));
+  }
+  echo "  charAge(): ", implode('.', IntlChar::charAge($cp)), "\n";
+  echo "\n";
+}
+
+printf("Codepoint range: %04x-%04x\n", IntlChar::CODEPOINT_MIN, IntlChar::CODEPOINT_MAX);
+$codepoints = array('P', 0xDF, 0x2603);
+foreach($codepoints as $cp) {
+  unicode_info($cp);
+}
+echo "Sample range of codepoints: U+2600-U+260F\n";
+IntlChar::enumCharNames(0x2600, 0x2610, function($cp, $nc, $name) {
+  printf("U+%04x %s\n", $cp, $name);
+});
+echo "RECYCLING SYMBOL FOR TYPE-1 PLASTICS => ";
+var_dump(IntlChar::charFromName("RECYCLING SYMBOL FOR TYPE-1 PLASTICS"));
+--EXPECT--
+Codepoint range: 0000-10ffff
+Codepoint U+0050
+  hasBinaryProperty(Alphabetic): true
+  isUAlphabetic(): bool(true)
+  isUUppercase(): bool(true)
+  isupper(): bool(true)
+  isULowercase(): bool(false)
+  islower(): bool(false)
+  isUWhiteSpace(): bool(false)
+  isWhitespace(): bool(false)
+  istitle(): bool(false)
+  isdigit(): bool(false)
+  isalpha(): bool(true)
+  isalnum(): bool(true)
+  isxdigit(): bool(false)
+  ispunct(): bool(false)
+  ispunct(): bool(false)
+  isgraph(): bool(true)
+  isblank(): bool(false)
+  isdefined(): bool(true)
+  isspace(): bool(false)
+  iscntrl(): bool(false)
+  isMirrored(): bool(false)
+  isIDStart(): bool(true)
+  isIDPart(): bool(true)
+  getBlockCode(): int(1)
+  charName(): string(22) "LATIN CAPITAL LETTER P"
+  charAge(): 1.1.0.0
+
+Codepoint U+00df
+  hasBinaryProperty(Alphabetic): true
+  isUAlphabetic(): bool(true)
+  isUUppercase(): bool(false)
+  isupper(): bool(false)
+  isULowercase(): bool(true)
+  islower(): bool(true)
+  isUWhiteSpace(): bool(false)
+  isWhitespace(): bool(false)
+  istitle(): bool(false)
+  isdigit(): bool(false)
+  isalpha(): bool(true)
+  isalnum(): bool(true)
+  isxdigit(): bool(false)
+  ispunct(): bool(false)
+  ispunct(): bool(false)
+  isgraph(): bool(true)
+  isblank(): bool(false)
+  isdefined(): bool(true)
+  isspace(): bool(false)
+  iscntrl(): bool(false)
+  isMirrored(): bool(false)
+  isIDStart(): bool(true)
+  isIDPart(): bool(true)
+  getBlockCode(): int(2)
+  charName(): string(26) "LATIN SMALL LETTER SHARP S"
+  charAge(): 1.1.0.0
+
+Codepoint U+2603
+  hasBinaryProperty(Alphabetic): false
+  isUAlphabetic(): bool(false)
+  isUUppercase(): bool(false)
+  isupper(): bool(false)
+  isULowercase(): bool(false)
+  islower(): bool(false)
+  isUWhiteSpace(): bool(false)
+  isWhitespace(): bool(false)
+  istitle(): bool(false)
+  isdigit(): bool(false)
+  isalpha(): bool(false)
+  isalnum(): bool(false)
+  isxdigit(): bool(false)
+  ispunct(): bool(false)
+  ispunct(): bool(false)
+  isgraph(): bool(true)
+  isblank(): bool(false)
+  isdefined(): bool(true)
+  isspace(): bool(false)
+  iscntrl(): bool(false)
+  isMirrored(): bool(false)
+  isIDStart(): bool(false)
+  isIDPart(): bool(false)
+  getBlockCode(): int(55)
+  charName(): string(7) "SNOWMAN"
+  charAge(): 1.1.0.0
+
+Sample range of codepoints: U+2600-U+260F
+U+2600 BLACK SUN WITH RAYS
+U+2601 CLOUD
+U+2602 UMBRELLA
+U+2603 SNOWMAN
+U+2604 COMET
+U+2605 BLACK STAR
+U+2606 WHITE STAR
+U+2607 LIGHTNING
+U+2608 THUNDERSTORM
+U+2609 SUN
+U+260a ASCENDING NODE
+U+260b DESCENDING NODE
+U+260c CONJUNCTION
+U+260d OPPOSITION
+U+260e BLACK TELEPHONE
+U+260f WHITE TELEPHONE
+RECYCLING SYMBOL FOR TYPE-1 PLASTICS => int(9843)