Change charclass.cpp/h to ucd.cpp/h

(bzr r4992)

8 files changed, 282 insertions, 102 deletions

diff --git a/src/dom/Makefile.mingw b/src/dom/Makefile.mingw
index b47437265..987a668af 100644
--- a/src/dom/Makefile.mingw
+++ b/src/dom/Makefile.mingw
@@ -139,7 +139,6 @@ CFLAGS = -Wall -g -DXP_WIN
 LIBS = -lws2_32
 
 DOMOBJ = \
-charclass.o       \
 cssparser.o       \
 domimpl.o         \
 domptr.o          \
@@ -164,6 +163,7 @@ io/socket.o       \
 odf/odfdocument.o \
 svg/svgimpl.o     \
 svg/svgparser.o   \
+ucd.o             \
 util/thread.o     \
 util/ziptool.o
 
diff --git a/src/dom/Makefile_insert b/src/dom/Makefile_insert
index 7777c4250..05f4f254b 100644
--- a/src/dom/Makefile_insert
+++ b/src/dom/Makefile_insert
@@ -1,77 +1,77 @@
-## Makefile.am fragment sourced by src/Makefile.am.

-

-dom/all: dom/libdom.a

-

-dom/clean:

-	rm -f dom/libdom.a $(dom_libdom_a_OBJECTS)

-

-dom_libdom_a_SOURCES =	         \

-	dom/charclass.cpp        \

-	dom/charclass.h          \

-	dom/css.h                \

-	dom/cssparser.cpp        \

-	dom/cssparser.h          \

-	dom/dom.h                \

-        dom/domconfig.h          \

-	dom/domimpl.cpp          \

-	dom/domimpl.h            \

-        dom/domstring.cpp        \

-        dom/domstring.h          \

-        dom/domstringimpl.h      \

-        dom/events.h             \

-        dom/ls.h                 \

-        dom/lsimpl.cpp           \

-        dom/lsimpl.h             \

-        dom/phoebedom.h          \

-        dom/prop-css2.cpp        \

-        dom/prop-css.cpp         \

-        dom/prop-svg.cpp         \

-        dom/smil.h               \

-        dom/smilimpl.cpp         \

-        dom/smilimpl.h           \

-	dom/stylesheets.h        \

-	dom/traversal.h          \

-	dom/uri.cpp              \

-	dom/uri.h                \

-	dom/views.h              \

-	dom/xmlreader.cpp        \

-	dom/xmlreader.h          \

-	dom/xpath.h              \

-	dom/xpathimpl.cpp        \

-	dom/xpathimpl.h          \

-	dom/xpathparser.cpp      \

-	dom/xpathparser.h        \

-        dom/xpathtoken.h         \

-        dom/xpathtoken.cpp       \

-	dom/io/base64stream.cpp  \

-	dom/io/base64stream.h    \

-	dom/io/bufferstream.cpp  \

-	dom/io/bufferstream.h    \

-        dom/io/domstream.cpp     \

-        dom/io/domstream.h       \

-        dom/io/httpclient.h      \

-        dom/io/gzipstream.cpp    \

-        dom/io/gzipstream.h      \

-        dom/io/socket.cpp        \

-        dom/io/socket.h          \

-        dom/io/gzipstream.cpp    \

-        dom/io/gzipstream.h      \

-	dom/io/stringstream.cpp  \

-	dom/io/stringstream.h    \

-	dom/io/uristream.cpp     \

-	dom/io/uristream.h       \

-        dom/odf/odfdocument.cpp  \

-        dom/odf/odfdocument.h    \

-	dom/svg/svg.h            \

-	dom/svg/svgimpl.cpp      \

-	dom/svg/svgimpl.h        \

-	dom/svg/svgparser.cpp    \

-	dom/svg/svgparser.h      \

-	dom/svg/svgtypes.h       \

-        dom/util/digest.h        \

-        dom/util/digest.cpp      \

-        dom/util/thread.h        \

-        dom/util/thread.cpp      \

-        dom/util/ziptool.h       \

-        dom/util/ziptool.cpp

-

+## Makefile.am fragment sourced by src/Makefile.am.
+
+dom/all: dom/libdom.a
+
+dom/clean:
+	rm -f dom/libdom.a $(dom_libdom_a_OBJECTS)
+
+dom_libdom_a_SOURCES =       \
+	dom/css.h                \
+	dom/cssparser.cpp        \
+	dom/cssparser.h          \
+	dom/dom.h                \
+    dom/domconfig.h          \
+	dom/domimpl.cpp          \
+	dom/domimpl.h            \
+    dom/domstring.cpp        \
+    dom/domstring.h          \
+    dom/domstringimpl.h      \
+    dom/events.h             \
+    dom/ls.h                 \
+    dom/lsimpl.cpp           \
+    dom/lsimpl.h             \
+    dom/phoebedom.h          \
+    dom/prop-css2.cpp        \
+    dom/prop-css.cpp         \
+    dom/prop-svg.cpp         \
+    dom/smil.h               \
+    dom/smilimpl.cpp         \
+    dom/smilimpl.h           \
+	dom/stylesheets.h        \
+	dom/traversal.h          \
+	dom/ucd.cpp              \
+	dom/ucd.h                \
+	dom/uri.cpp              \
+	dom/uri.h                \
+	dom/views.h              \
+	dom/xmlreader.cpp        \
+	dom/xmlreader.h          \
+	dom/xpath.h              \
+	dom/xpathimpl.cpp        \
+	dom/xpathimpl.h          \
+	dom/xpathparser.cpp      \
+	dom/xpathparser.h        \
+    dom/xpathtoken.h         \
+    dom/xpathtoken.cpp       \
+	dom/io/base64stream.cpp  \
+	dom/io/base64stream.h    \
+	dom/io/bufferstream.cpp  \
+	dom/io/bufferstream.h    \
+    dom/io/domstream.cpp     \
+    dom/io/domstream.h       \
+    dom/io/httpclient.h      \
+    dom/io/gzipstream.cpp    \
+    dom/io/gzipstream.h      \
+    dom/io/socket.cpp        \
+    dom/io/socket.h          \
+    dom/io/gzipstream.cpp    \
+    dom/io/gzipstream.h      \
+    dom/io/stringstream.cpp  \
+	dom/io/stringstream.h    \
+	dom/io/uristream.cpp     \
+	dom/io/uristream.h       \
+    dom/odf/odfdocument.cpp  \
+    dom/odf/odfdocument.h    \
+	dom/svg/svg.h            \
+	dom/svg/svgimpl.cpp      \
+	dom/svg/svgimpl.h        \
+	dom/svg/svgparser.cpp    \
+	dom/svg/svgparser.h      \
+	dom/svg/svgtypes.h       \
+    dom/util/digest.h        \
+    dom/util/digest.cpp      \
+    dom/util/thread.h        \
+    dom/util/thread.cpp      \
+    dom/util/ziptool.h       \
+    dom/util/ziptool.cpp
+
diff --git a/src/dom/cssparser.cpp b/src/dom/cssparser.cpp
index 78ce4ce9b..83fd92909 100644
--- a/src/dom/cssparser.cpp
+++ b/src/dom/cssparser.cpp
@@ -28,7 +28,7 @@
  */
 
 #include "cssparser.h"
-#include "charclass.h"
+#include "ucd.h"
 
 #include <stdio.h>
 #include <stdarg.h>
diff --git a/src/dom/charclass.cpp b/src/dom/ucd.c
index d2b67a660..dbb0a299f 100644
--- a/src/dom/charclass.cpp
+++ b/src/dom/ucd.c
@@ -1,5 +1,5 @@
 /*
- * Generated by UcdReader at:Fri Mar 07 14:15:18 CST 2008
+ * Generated by UcdReader at:Sat Mar 08 13:42:03 CST 2008
  * block table size:2 (4 bytes)
  * plane table size:6 (64 bytes)
  *
@@ -9,7 +9,8 @@
  *
  *  You might notice that this table is larger than some other implementations.
  *  This is because we included the entire UCD set of codepoints, rather than
- *  truncating it at 16 bits for UTF-16
+ *  truncating it at 16 bits for UTF-16.  It is similar to Java's and JS's, but
+ *  this is our own implementation.
  *
  *  This lookup table should be compared to the raw unfolded table lookup
  *  to make sure that no bits are lost in compression.  This is done internally
@@ -37,24 +38,24 @@
  * G 3 bits     This field is for storing our own lexical information, in addition
  *              to that given by the UCD.  The fields are as follows:
  *              0  may not be part of an identifier
- *              1  ignorable control; may continue a Unicode identifier or JS
+ *              1  ignorable control; may continue a Unicode identifier or C
  *                 identifier
- *              2  may continue a JS identifier but not a Unicode identifier
+ *              2  may continue a C identifier but not a Unicode identifier
  *                 (unused)
- *              3  may continue a Unicode identifier or JS identifier
- *              4  is a JS whitespace character
- *              5  may start or continue a JS identifier;
+ *              3  may continue a Unicode identifier or C identifier
+ *              4  is a C whitespace character
+ *              5  may start or continue a C identifier;
  *                 may continue but not start a Unicode identifier (_)
- *              6  may start or continue a JS identifier but not a Unicode
+ *              6  may start or continue a C identifier but not a Unicode
  *                 identifier ($)
- *              7  may start or continue a Unicode identifier or JS identifier
+ *              7  may start or continue a Unicode identifier or C identifier
  *              Thus:
- *                 5, 6, 7 may start a JS identifier
- *                 1, 2, 3, 5, 6, 7 may continue a JS identifier
+ *                 5, 6, 7 may start a C identifier
+ *                 1, 2, 3, 5, 6, 7 may continue a C identifier
  *                 7 may start a Unicode identifier
  *                 1, 3, 5, 7 may continue a Unicode identifier
  *                 1 is ignorable within an identifier
- *                 4 is JS whitespace
+ *                 4 is C whitespace
  *  H 2 bits    This field is for storing additional information regarding this
  *              codepoint's numeric properties.  The values are:
  *              0  this character has no numeric property
@@ -2006,9 +2007,138 @@ static unsigned int prop[] =
 
 
 /**
+ * Special case mappings, not covered by UnicodeData.txt
+ */
+typedef struct
+{
+    int sourceChar;
+    int nrMaps;
+    int map[3];
+} CaseMapEntry;
+
+static CaseMapEntry caseMap[] =
+{
+    { 0x1fc2, 2, { 0xffff, 0x0159 } },
+    { 0x1fc3, 1, { 0xffff } },
+    { 0x1fc6, 2, { 0x018d, 0x0156 } },
+    { 0x1fc7, 3, { 0x018d, 0x0156, 0x0159 } },
+    { 0x1fc4, 2, { 0x0185, 0x0159 } },
+    { 0x1fcc, 1, { 0xffff } },
+    { 0x1fd3, 3, { 0x018f, 0x0134, 0x012d } },
+    { 0x1fd2, 3, { 0x018f, 0x0134, 0x012c } },
+    { 0x1fd7, 3, { 0x018f, 0x0134, 0x0156 } },
+    { 0x1fd6, 2, { 0x018f, 0x0156 } },
+    { 0x0130, 1, { 0x0082 } },
+    { 0x1fe2, 3, { 0xffff, 0x0134, 0x012c } },
+    { 0x1fe3, 3, { 0xffff, 0x0134, 0x012d } },
+    { 0x1fe4, 2, { 0xffff, 0x0139 } },
+    { 0x1fe6, 2, { 0xffff, 0x0156 } },
+    { 0x1fe7, 3, { 0xffff, 0x0134, 0x0156 } },
+    { 0x0307, 1, { 0x0133 } },
+    { 0x1ff3, 1, { 0xffff } },
+    { 0x1ff2, 2, { 0xffff, 0x0159 } },
+    { 0x1ff4, 2, { 0xffff, 0x0159 } },
+    { 0x1ff7, 3, { 0xffff, 0x0156, 0x0159 } },
+    { 0x1ff6, 2, { 0xffff, 0x0156 } },
+    { 0x0128, 1, { 0x0080 } },
+    { 0x1ffc, 1, { 0xffff } },
+    { 0x012e, 1, { 0xffff } },
+    { 0x1f86, 1, { 0xffff } },
+    { 0x1f87, 1, { 0xffff } },
+    { 0x1f84, 1, { 0xffff } },
+    { 0x1e97, 2, { 0x0036, 0x0134 } },
+    { 0x1f85, 1, { 0xffff } },
+    { 0x1e96, 2, { 0x0030, 0x014b } },
+    { 0x1f82, 1, { 0xffff } },
+    { 0x1f83, 1, { 0xffff } },
+    { 0x1f80, 1, { 0xffff } },
+    { 0x1f81, 1, { 0xffff } },
+    { 0xfb01, 2, { 0x002e, 0x0045 } },
+    { 0x1f8e, 1, { 0xffff } },
+    { 0xfb00, 2, { 0x002e, 0x0042 } },
+    { 0x1f8f, 1, { 0xffff } },
+    { 0xfb03, 3, { 0x002e, 0x0042, 0x0045 } },
+    { 0x1f8c, 1, { 0xffff } },
+    { 0xfb02, 2, { 0x002e, 0xffff } },
+    { 0x1f8d, 1, { 0xffff } },
+    { 0xfb05, 2, { 0x0035, 0x004a } },
+    { 0x1e99, 2, { 0x003b, 0xffff } },
+    { 0x1f8a, 1, { 0xffff } },
+    { 0x0049, 1, { 0x0031 } },
+    { 0xfb04, 3, { 0x002e, 0x0042, 0xffff } },
+    { 0x1e98, 2, { 0x0039, 0xffff } },
+    { 0x1f8b, 1, { 0xffff } },
+    { 0x004a, 1, { 0xffff } },
+    { 0x1f88, 1, { 0xffff } },
+    { 0xfb06, 2, { 0x0035, 0x004a } },
+    { 0x1e9a, 2, { 0x0029, 0xffff } },
+    { 0x1f89, 1, { 0xffff } },
+    { 0x1f97, 1, { 0xffff } },
+    { 0x1f96, 1, { 0xffff } },
+    { 0x1f95, 1, { 0xffff } },
+    { 0x1f94, 1, { 0xffff } },
+    { 0x1f93, 1, { 0xffff } },
+    { 0x1f92, 1, { 0xffff } },
+    { 0x1f91, 1, { 0xffff } },
+    { 0x1f90, 1, { 0xffff } },
+    { 0x1f9f, 1, { 0xffff } },
+    { 0x1f9e, 1, { 0xffff } },
+    { 0x1f9d, 1, { 0xffff } },
+    { 0xfb13, 2, { 0x0220, 0x0240 } },
+    { 0x1f9c, 1, { 0xffff } },
+    { 0xfb14, 2, { 0x0220, 0x0235 } },
+    { 0x1f9b, 1, { 0xffff } },
+    { 0xfb15, 2, { 0x0220, 0xffff } },
+    { 0x1f9a, 1, { 0xffff } },
+    { 0xfb16, 2, { 0xffff, 0x0240 } },
+    { 0x1f99, 1, { 0xffff } },
+    { 0xfb17, 2, { 0x0220, 0xffff } },
+    { 0x0149, 2, { 0xffff, 0xffff } },
+    { 0x1f98, 1, { 0xffff } },
+    { 0x1fa4, 1, { 0xffff } },
+    { 0x1fa5, 1, { 0xffff } },
+    { 0x1fa6, 1, { 0xffff } },
+    { 0x1fa7, 1, { 0xffff } },
+    { 0x1fa0, 1, { 0xffff } },
+    { 0x1fa1, 1, { 0xffff } },
+    { 0x1fa2, 1, { 0xffff } },
+    { 0x1fa3, 1, { 0xffff } },
+    { 0x1fac, 1, { 0xffff } },
+    { 0x1fad, 1, { 0xffff } },
+    { 0x1fae, 1, { 0xffff } },
+    { 0x1faf, 1, { 0xffff } },
+    { 0x1fa8, 1, { 0xffff } },
+    { 0x1fa9, 1, { 0xffff } },
+    { 0x1faa, 1, { 0xffff } },
+    { 0x0069, 1, { 0x0082 } },
+    { 0x1fab, 1, { 0xffff } },
+    { 0x1fb4, 2, { 0x0182, 0x0159 } },
+    { 0x1fb7, 3, { 0x0187, 0x0156, 0x0159 } },
+    { 0x1fb6, 2, { 0x0187, 0x0156 } },
+    { 0x1fb3, 1, { 0xffff } },
+    { 0x1fb2, 2, { 0xffff, 0x0159 } },
+    { 0x1fbc, 1, { 0xffff } },
+    { 0x03b0, 3, { 0xffff, 0x0134, 0x012d } },
+    { 0x1f52, 3, { 0xffff, 0x0139, 0x012c } },
+    { 0x1f50, 2, { 0xffff, 0x0139 } },
+    { 0x1f56, 3, { 0xffff, 0x0139, 0x0156 } },
+    { 0x03a3, 1, { 0xffff } },
+    { 0x1f54, 3, { 0xffff, 0x0139, 0x012d } },
+    { 0x0390, 3, { 0x018f, 0x0134, 0x012d } },
+    { 0x00cd, 1, { 0xffff } },
+    { 0x00cc, 1, { 0xffff } },
+    { 0x00df, 2, { 0x0035, 0x0049 } },
+    { 0x0587, 2, { 0x0217, 0x0246 } },
+    { 0x01f0, 2, { 0xffff, 0xffff } },
+    { 0,  0,  {} }
+};
+
+
+
+/**
  * Look for comments in ucd.h
  */
-#include "charclass.h"
+#include "ucd.h"
 
 
 
@@ -2067,6 +2197,34 @@ int uni_is_space(int ch)
               || c==UNI_PARAGRAPH_SEPARATOR);
 }
 
+int uni_to_lower(int ch)
+{
+    int c = UNI_CODE(ch);
+    if (c == UNI_LOWERCASE_LETTER)
+        return ch;
+    ch -= (c>>18) & 0x1ff;
+    return ch;
+}
+
+int uni_to_upper(int ch)
+{
+    int c = UNI_CODE(ch);
+    if (c == UNI_UPPERCASE_LETTER)
+        return ch;
+    ch += (c>>18) & 0x1ff;
+    return ch;
+}
+
+int uni_to_title(int ch)
+{
+    int c = UNI_CODE(ch);
+    if (c == UNI_TITLECASE_LETTER)
+        return ch;
+    ch += (c>>18) & 0x1ff;
+    return ch;
+}
+
+
 
 
 
diff --git a/src/dom/charclass.h b/src/dom/ucd.h
index 26d5dc265..f9ce2f09c 100644
--- a/src/dom/charclass.h
+++ b/src/dom/ucd.h
@@ -1,12 +1,7 @@
-#ifndef __CHARCLASS_H__
-#define __CHARCLASS_H__
 /**
  *
- * Phoebe DOM Implementation.
+ * NGP Packrat Parser Generator
  *
- * This is a C++ approximation of the W3C DOM model, which follows
- * fairly closely the specifications in the various .idl files, copies of
- * which are provided for reference.  Most important is this one:
  *
  * Authors:
  *   Bob Jamison
@@ -28,6 +23,9 @@
  *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  *
  */
+#ifndef __UCD_H__
+#define __UCD_H__
+
 
 
 /**
@@ -146,8 +144,32 @@ int uni_is_letter_or_digit(int ch);
  */
 int uni_is_space(int ch);
 
+/**
+ * Convert the given codepoint to its lower case mapping.
+ * If there is none, return the codepoint.
+ * @param ch the Unicode codepoint to convert
+ * @return the converted codepoint
+ */
+int uni_to_lower(int ch);
+
+/**
+ * Convert the given codepoint to its upper case mapping.
+ * If there is none, return the codepoint.
+ * @param ch the Unicode codepoint to convert
+ * @return the converted codepoint
+ */
+int uni_to_upper(int ch);
+
+/**
+ * Convert the given codepoint to its title case mapping.
+ * If there is none, return the codepoint.
+ * @param ch the Unicode codepoint to convert
+ * @return the converted codepoint
+ */
+int uni_to_title(int ch);
+
 
 
-#endif /* __CHARCLASS_H__ */
+#endif /* __UCD_H__ */
 
            
diff --git a/src/dom/uri.cpp b/src/dom/uri.cpp
index 8b810e611..db45a2abf 100644
--- a/src/dom/uri.cpp
+++ b/src/dom/uri.cpp
@@ -31,7 +31,7 @@
 
 
 #include "uri.h"
-#include "charclass.h"
+#include "ucd.h"
 
 #include <stdio.h>
 #include <stdarg.h>
diff --git a/src/dom/xmlreader.cpp b/src/dom/xmlreader.cpp
index 32a97e0c0..c6eae8ba3 100644
--- a/src/dom/xmlreader.cpp
+++ b/src/dom/xmlreader.cpp
@@ -30,7 +30,7 @@
 
 
 #include "xmlreader.h"
-#include "charclass.h"
+#include "ucd.h"
 #include "domimpl.h"
 
 #include <stdio.h>
diff --git a/src/dom/xpathparser.cpp b/src/dom/xpathparser.cpp
index f2e000e6d..bbe0fcc40 100644
--- a/src/dom/xpathparser.cpp
+++ b/src/dom/xpathparser.cpp
@@ -28,7 +28,7 @@
  */
 
 
-#include "charclass.h"
+#include "ucd.h"
 #include "xpathparser.h"