Changeset 1552

Timestamp:

05/24/10 04:27:25 (15 years ago)

Author:

rsinfu

Message:

Fixed bugzilla 3465: isIdeographic can be wrong in std.xml.

- Applied Michael Rynn's contribution to isChar(), isDigit() and isIdeographic(). Now these functions are hard-coded for performance. Profiling showed that this code was three times faster than the old one.
- IdeographicTable? must be sorted for lookup().

Files:

• trunk/docsrc/changelog.dd (modified) (1 diff)
• trunk/phobos/std/xml.d (modified) (5 diffs)

trunk/docsrc/changelog.dd

@@ -8 +8 @@
-    $(WHATSNEW
-    $(LI std.functional: toDelegate now accepts callable(function pointers, delegates and objects implement opCall) )
-    $(LI std.traits: Added templates to get compile-time information about functions.)
-    $(LI std.typecons: Added tie and AutoImplement.)
-    )
-    $(BUGSFIXED
-    $(LI $(BUGZILLA 2738): Rebindable should work for interfaces.)
-    $(LI $(BUGZILLA 2835): std.socket.TcpSocket doesn't actually connect)
-    $(LI $(BUGZILLA 3088): std.xml.check() fails on xml comments)
-    $(LI $(BUGZILLA 3200): std.xml doesn't follow spec for Tag.text)
+    $(LI $(BUGZILLA 3465): isIdeographic can be wrong in std.xml)
-    $(LI $(BUGZILLA 3873): std.range.repeat should have popBack defined)
-    $(LI $(BUGZILLA 3880): std.regex functions with const/immutable Regex object)
-    $(LI $(BUGZILLA 4109): writeln doesn't work with empty static array)
-    $(LI $(BUGZILLA 4202): Changset 1517 doesn't compile)
-    $(LI $(BUGZILLA 4228): std.array.replace contains 2 bugs)
-    $(LI $(BUGZILLA 4219): hasAliasing does not care about immutable)
-    )
-)
-
-<div id=version>

trunk/phobos/std/xml.d

@@ -130 +130 @@
-/**
- * Returns true if the character is a character according to the XML standard
- *
- * Standards: $(LINK2 http://www.w3.org/TR/1998/REC-xml-19980210, XML 1.0)
- *
- * Params:
- *    c = the character to be tested
- */
-bool isChar(dchar c) // rule 2
-{
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-}
-
-unittest
-{
-//  const CharTable=[0x9,0x9,0xA,0xA,0xD,0xD,0x20,0xD7FF,0xE000,0xFFFD,
-//        0x10000,0x10FFFF];
-    assert(!isChar(cast(dchar)0x8));
-    assert( isChar(cast(dchar)0x9));
-    assert( isChar(cast(dchar)0xA));
-    assert(!isChar(cast(dchar)0xB));
@@ -157 +176 @@
-    assert( isChar(cast(dchar)0xD7FF));
-    assert(!isChar(cast(dchar)0xD800));
-    assert(!isChar(cast(dchar)0xDFFF));
-    assert( isChar(cast(dchar)0xE000));
-    assert( isChar(cast(dchar)0xFFFD));
-    assert(!isChar(cast(dchar)0xFFFE));
-    assert(!isChar(cast(dchar)0xFFFF));
-    assert( isChar(cast(dchar)0x10000));
-    assert( isChar(cast(dchar)0x10FFFF));
-    assert(!isChar(cast(dchar)0x110000));
+
+    debug (stdxml_TestHardcodedChecks)
+    {
+        foreach (c; 0 .. dchar.max + 1)
+            assert(isChar(c) == lookup(CharTable, c));
+    }
-}
-
-/**
- * Returns true if the character is whitespace according to the XML standard
- *
- * Only the following characters are considered whitespace in XML - space, tab,
- * carriage return and linefeed
- *
- * Standards: $(LINK2 http://www.w3.org/TR/1998/REC-xml-19980210, XML 1.0)
- *
@@ -185 +210 @@
-/**
- * Returns true if the character is a digit according to the XML standard
- *
- * Standards: $(LINK2 http://www.w3.org/TR/1998/REC-xml-19980210, XML 1.0)
- *
- * Params:
- *    c = the character to be tested
- */
-bool isDigit(dchar c)
-{
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-}
-
-/**
- * Returns true if the character is a letter according to the XML standard
- *
- * Standards: $(LINK2 http://www.w3.org/TR/1998/REC-xml-19980210, XML 1.0)
- *
- * Params:
- *    c = the character to be tested
- */
@@ -212 +249 @@
- * Returns true if the character is an ideographic character according to the
- * XML standard
- *
- * Standards: $(LINK2 http://www.w3.org/TR/1998/REC-xml-19980210, XML 1.0)
- *
- * Params:
- *    c = the character to be tested
- */
-bool isIdeographic(dchar c)
-{
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-}
-
-/**
- * Returns true if the character is a base character according to the XML
- * standard
- *
- * Standards: $(LINK2 http://www.w3.org/TR/1998/REC-xml-19980210, XML 1.0)
- *
- * Params:
- *    c = the character to be tested
@@ -2822 +2880 @@
-        0x1155,0x1159,0x1159,0x115F,0x1161,0x1163,0x1163,0x1165,0x1165,0x1167,
-        0x1167,0x1169,0x1169,0x116D,0x116E,0x1172,0x1173,0x1175,0x1175,0x119E,
-        0x119E,0x11A8,0x11A8,0x11AB,0x11AB,0x11AE,0x11AF,0x11B7,0x11B8,0x11BA,
-        0x11BA,0x11BC,0x11C2,0x11EB,0x11EB,0x11F0,0x11F0,0x11F9,0x11F9,0x1E00,
-        0x1E9B,0x1EA0,0x1EF9,0x1F00,0x1F15,0x1F18,0x1F1D,0x1F20,0x1F45,0x1F48,
-        0x1F4D,0x1F50,0x1F57,0x1F59,0x1F59,0x1F5B,0x1F5B,0x1F5D,0x1F5D,0x1F5F,
-        0x1F7D,0x1F80,0x1FB4,0x1FB6,0x1FBC,0x1FBE,0x1FBE,0x1FC2,0x1FC4,0x1FC6,
-        0x1FCC,0x1FD0,0x1FD3,0x1FD6,0x1FDB,0x1FE0,0x1FEC,0x1FF2,0x1FF4,0x1FF6,
-        0x1FFC,0x2126,0x2126,0x212A,0x212B,0x212E,0x212E,0x2180,0x2182,0x3041,
-        0x3094,0x30A1,0x30FA,0x3105,0x312C,0xAC00,0xD7A3];
-4E00,0x9FA5,0x3007,0x3007,0x3021,0x3029
+3007,0x3007,0x3021,0x3029,0x4E00,0x9FA5
-    immutable CombiningCharTable=[0x0300,0x0345,0x0360,0x0361,0x0483,0x0486,
-        0x0591,0x05A1,0x05A3,0x05B9,0x05BB,0x05BD,0x05BF,0x05BF,0x05C1,0x05C2,
-        0x05C4,0x05C4,0x064B,0x0652,0x0670,0x0670,0x06D6,0x06DC,0x06DD,0x06DF,
-        0x06E0,0x06E4,0x06E7,0x06E8,0x06EA,0x06ED,0x0901,0x0903,0x093C,0x093C,
-        0x093E,0x094C,0x094D,0x094D,0x0951,0x0954,0x0962,0x0963,0x0981,0x0983,
-        0x09BC,0x09BC,0x09BE,0x09BE,0x09BF,0x09BF,0x09C0,0x09C4,0x09C7,0x09C8,
-        0x09CB,0x09CD,0x09D7,0x09D7,0x09E2,0x09E3,0x0A02,0x0A02,0x0A3C,0x0A3C,
-        0x0A3E,0x0A3E,0x0A3F,0x0A3F,0x0A40,0x0A42,0x0A47,0x0A48,0x0A4B,0x0A4D,
-        0x0A70,0x0A71,0x0A81,0x0A83,0x0ABC,0x0ABC,0x0ABE,0x0AC5,0x0AC7,0x0AC9,
-        0x0ACB,0x0ACD,0x0B01,0x0B03,0x0B3C,0x0B3C,0x0B3E,0x0B43,0x0B47,0x0B48,