Introduce characters utilities in rtl/character.hxx

Signed-off-by: Stephan Bergmann <sbergman@redhat.com>, with slight modifications
to sal/inc/rtl/character.hxx:
* Replaced "#pragma once" with explicit include guard for now.
* Missing includes.
* Cosmetic clean-up.

Change-Id: I94d01cd4e766f92c70f941839a67101fa2c97654

basic/source/sbx/sbxexec.cxx

@@ -20,26 +20,7 @@
 #include <tools/errcode.hxx>
 #include <vcl/svapp.hxx>
 #include <basic/sbx.hxx>
-
-
-
-static bool isAlpha( sal_Unicode c )
-{
-    bool bRet = (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
-    return bRet;
-}
-
-static bool isDigit( sal_Unicode c )
-{
-    bool bRet = (c >= '0' && c <= '9');
-    return bRet;
-}
-
-static bool isAlphaNumeric( sal_Unicode c )
-{
-    bool bRet = isDigit( c ) || isAlpha( c );
-    return bRet;
-}
+#include <rtl/character.hxx>
 
 
 static SbxVariable* Element
@@ -72,7 +53,7 @@ static const sal_Unicode* Symbol( const sal_Unicode* p, OUString& rSym )
     else
     {
         // A symbol had to begin with a alphabetic character or an underline
-        if( !isAlpha( *p ) && *p != '_' )
+        if( !rtl::isAsciiAlpha( *p ) && *p != '_' )
         {
             SbxBase::SetError( SbxERR_SYNTAX );
         }
@@ -80,7 +61,7 @@ static const sal_Unicode* Symbol( const sal_Unicode* p, OUString& rSym )
         {
             rSym = p;
             // The it can contain alphabetic characters, numbers or underlines
-            while( *p && (isAlphaNumeric( *p ) || *p == '_') )
+            while( *p && (rtl::isAsciiAlphanumeric( *p ) || *p == '_') )
             {
                 p++, nLen++;
             }
@@ -103,7 +84,7 @@ static SbxVariable* QualifiedName
 
     SbxVariableRef refVar;
     const sal_Unicode* p = SkipWhitespace( *ppBuf );
-    if( isAlpha( *p ) || *p == '_' || *p == '[' )
+    if( rtl::isAsciiAlpha( *p ) || *p == '_' || *p == '[' )
     {
         // Read in the element
         refVar = Element( pObj, pGbl, &p, t );
@@ -139,8 +120,8 @@ static SbxVariable* Operand
 {
     SbxVariableRef refVar( new SbxVariable );
     const sal_Unicode* p = SkipWhitespace( *ppBuf );
-    if( !bVar && ( isDigit( *p )
-                   || ( *p == '.' && isDigit( *( p+1 ) ) )
+    if( !bVar && ( rtl::isAsciiDigit( *p )
+                   || ( *p == '.' && rtl::isAsciiDigit( *( p+1 ) ) )
                    || *p == '-'
                    || *p == '&' ) )
     {

sal/ZipPackage_sal_odk_headers.mk

@@ -32,6 +32,7 @@ $(eval $(call gb_ZipPackage_add_files,sal_odk_headers,inc/rtl,include/rtl,\
 	rtl/bootstrap.hxx \
 	rtl/byteseq.h \
 	rtl/byteseq.hxx \
+	rtl/character.hxx \
 	rtl/cipher.h \
 	rtl/crc.h \
 	rtl/digest.h \

sal/inc/rtl/character.hxx

+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * This file is part of the LibreOffice project.
+ *
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/.
+ *
+ * This file incorporates work covered by the following license notice:
+ *
+ *   Licensed to the Apache Software Foundation (ASF) under one or more
+ *   contributor license agreements. See the NOTICE file distributed
+ *   with this work for additional information regarding copyright
+ *   ownership. The ASF licenses this file to you under the Apache
+ *   License, Version 2.0 (the "License"); you may not use this file
+ *   except in compliance with the License. You may obtain a copy of
+ *   the License at http://www.apache.org/licenses/LICENSE-2.0 .
+ */
+
+#ifndef INCLUDED_RTL_CHARACTER_HXX
+#define INCLUDED_RTL_CHARACTER_HXX
+
+#include "sal/config.h"
+
+#include "sal/types.h"
+
+namespace rtl
+{
+/** Check for ASCII character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a ASCII character (0x00--0x7F).
+
+    @since LibreOffice 4.1
+ */
+inline bool isAscii(sal_uInt32 nUtf32)
+{
+    return nUtf32 <= 0x7F;
+}
+
+/** Check for ASCII lower case character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a US-ASCII lower case alphabetic character
+    (ASCII 'a'--'z').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiLowerCase(sal_uInt32 nUtf32)
+{
+    return nUtf32 >= 'a' && nUtf32 <= 'z';
+}
+
+/** Check for US-ASCII upper case character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a US-ASCII upper case alphabetic character
+    (US-ASCII 'A'--'Z').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiUpperCase(sal_uInt32 nUtf32)
+{
+    return nUtf32 >= 'A' && nUtf32 <= 'Z';
+}
+
+/** Check for ASCII alphanumeric character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nUtf32 is a US-ASCII alphanumeric character
+    (ASCII '0'--'9', 'A'--'Z' or 'a'--'z').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiAlpha(sal_uInt32 nUtf32)
+{
+    return isAsciiLowerCase(nUtf32) || isAsciiUpperCase(nUtf32);
+}
+
+/** Check for ASCII digit character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a ASCII (decimal) digit character
+    (ASCII '0'--'9').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiDigit(sal_uInt32 nUtf32)
+{
+    return nUtf32 >= '0' && nUtf32 <= '9';
+}
+
+/** Check for US-ASCII alphanumeric character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a US-ASCII alphanumeric character (US-ASCII
+    '0'--'9', 'A'--'Z' or 'a'--'z').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiAlphanumeric(sal_uInt32 nUtf32)
+{
+    return isAsciiDigit(nUtf32) || isAsciiAlpha(nUtf32);
+}
+
+/** Check for US-ASCII canonic hexadecimal digit character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a US-ASCII canonic (i.e., upper case)
+    hexadecimal digit character (US-ASCII '0'--'9' or 'A'--'F').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiCanonicHexDigit(sal_uInt32 nUtf32)
+{
+    return isAsciiDigit(nUtf32) || (nUtf32 >= 'A' && nUtf32 <= 'F');
+}
+
+/** Check for US-ASCII hexadecimal digit character.
+
+    @param nUtf32  Some UCS-4 character.
+
+    @return  True if nChar is a US-ASCII hexadecimal digit character (US-
+    ASCII '0'--'9', 'A'--'F', 'a'--'f').
+
+    @since LibreOffice 4.1
+ */
+inline bool isAsciiHexDigit(sal_uInt32 nUtf32)
+{
+    return isAsciiCanonicHexDigit(nUtf32) || (nUtf32 >= 'a' && nUtf32 <= 'f');
+}
+
+}//rtl namespace
+
+#endif
+
+/* vim:set shiftwidth=4 softtabstop=4 expandtab: */

sal/rtl/math.cxx

@@ -22,6 +22,7 @@
 
 #include "osl/diagnose.h"
 #include "rtl/alloc.h"
+#include "rtl/character.hxx"
 #include "rtl/math.hxx"
 #include "rtl/strbuf.h"
 #include "rtl/string.h"
@@ -689,13 +690,6 @@ inline bool long10Overflow( long& nExp, int nAdd )
     return false;
 }
 
-// We are only concerned about ASCII arabic numerical digits here
-template< typename CharT >
-inline bool isDigit( CharT c )
-{
-    return 0x30 <= c && c <= 0x39;
-}
-
 template< typename CharT >
 inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
                              CharT cDecSeparator, CharT cGroupSeparator,
@@ -755,7 +749,7 @@ inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
         for (; p != pEnd; ++p)
         {
             CharT c = *p;
-            if (isDigit(c))
+            if (rtl::isAsciiDigit(c))
             {
                 fVal = fVal * 10.0 + static_cast< double >( c - CharT('0') );
                 ++nValExp;
@@ -783,7 +777,7 @@ inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
             for (; p != pEnd; ++p)
             {
                 CharT c = *p;
-                if (!isDigit(c))
+                if (!rtl::isAsciiDigit(c))
                     break;
                 if ( nDigs < nSigs )
                 {   // further digits (more than nSigs) don't have any
@@ -821,7 +815,7 @@ inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
             if ( fVal == 0.0 )
             {   // no matter what follows, zero stays zero, but carry on the
                 // offset
-                while (p != pEnd && isDigit(*p))
+                while (p != pEnd && rtl::isAsciiDigit(*p))
                     ++p;
             }
             else
@@ -831,7 +825,7 @@ inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
                 for (; p != pEnd; ++p)
                 {
                     CharT c = *p;
-                    if (!isDigit(c))
+                    if (!rtl::isAsciiDigit(c))
                         break;
                     int i = c - CharT('0');
                     if ( long10Overflow( nExp, i ) )
@@ -876,7 +870,7 @@ inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
                 fVal = HUGE_VAL;
                 eStatus = rtl_math_ConversionStatus_OutOfRange;
                 // Eat any further digits:
-                while (p != pEnd && isDigit(*p))
+                while (p != pEnd && rtl::isAsciiDigit(*p))
                     ++p;
             }
             else if (pEnd - p >= 4 && p[1] == CharT('N') && p[2] == CharT('A')
@@ -897,7 +891,7 @@ inline double stringToDouble(CharT const * pBegin, CharT const * pEnd,
                     bSign = false; // don't negate again
                 }
                 // Eat any further digits:
-                while (p != pEnd && isDigit(*p))
+                while (p != pEnd && rtl::isAsciiDigit(*p))
                     ++p;
             }
         }

sal/rtl/uri.cxx

@@ -20,6 +20,7 @@
 #include "surrogates.hxx"
 
 #include "osl/diagnose.h"
+#include "rtl/character.hxx"
 #include "rtl/strbuf.hxx"
 #include "rtl/textenc.h"
 #include "rtl/textcvt.h"
@@ -39,20 +40,6 @@ std::size_t const nCharClassSize = 128;
 
 sal_Unicode const cEscapePrefix = 0x25; // '%'
 
-inline bool isDigit(sal_uInt32 nUtf32)
-{
-    return nUtf32 >= 0x30 && nUtf32 <= 0x39; // '0'--'9'
-}
-
-inline bool isAlpha(sal_uInt32 nUtf32)
-{
-    // 'A'--'Z', 'a'--'z'
-    return (
-            (nUtf32 >= 0x41 && nUtf32 <= 0x5A) ||
-            (nUtf32 >= 0x61 && nUtf32 <= 0x7A)
-           );
-}
-
 inline bool isHighSurrogate(sal_uInt32 nUtf16)
 {
     return SAL_RTL_IS_HIGH_SURROGATE(nUtf16);
@@ -376,7 +363,7 @@ void parseUriRef(rtl_uString const * pUriRef, Components * pComponents)
     sal_Unicode const * pEnd = pBegin + pUriRef->length;
     sal_Unicode const * pPos = pBegin;
 
-    if (pPos != pEnd && isAlpha(*pPos))
+    if (pPos != pEnd && rtl::isAsciiAlpha(*pPos))
     {
         for (sal_Unicode const * p = pPos + 1; p != pEnd; ++p)
         {
@@ -387,7 +374,7 @@ void parseUriRef(rtl_uString const * pUriRef, Components * pComponents)
                 pPos = p;
                 break;
             }
-            else if (!isAlpha(*p) && !isDigit(*p) && *p != '+' && *p != '-'
+            else if (!rtl::isAsciiAlphanumeric(*p) && *p != '+' && *p != '-'
                      && *p != '.')
             {
                 break;

stoc/source/uriproc/UriReferenceFactory.cxx

@@ -41,6 +41,7 @@
 #include "cppuhelper/implbase2.hxx"
 #include "cppuhelper/weak.hxx"
 #include "osl/diagnose.h"
+#include "rtl/character.hxx"
 #include "rtl/string.h"
 #include "rtl/ustrbuf.hxx"
 #include "rtl/ustring.hxx"
@@ -56,28 +57,8 @@ namespace {
 //TODO: move comphelper::string::misc into something like
 //sal/salhelper and use those instead
 
-bool isDigit(sal_Unicode c) {
-    return c >= '0' && c <= '9';
-}
-
-bool isUpperCase(sal_Unicode c) {
-    return c >= 'A' && c <= 'Z';
-}
-
-bool isLowerCase(sal_Unicode c) {
-    return c >= 'a' && c <= 'z';
-}
-
-bool isAlpha(sal_Unicode c) {
-    return isUpperCase(c) || isLowerCase(c);
-}
-
-bool isHexDigit(sal_Unicode c) {
-    return isDigit(c) || (c >= 'A' && c <= 'F') || (c >= 'a' && c <= 'f');
-}
-
 sal_Unicode toLowerCase(sal_Unicode c) {
-    return isUpperCase(c) ? c + ('a' - 'A') : c;
+    return rtl::isAsciiUpperCase(c) ? c + ('a' - 'A') : c;
 }
 
 bool equalIgnoreCase(sal_Unicode c1, sal_Unicode c2) {
@@ -88,8 +69,8 @@ bool equalIgnoreEscapeCase(OUString const & s1, OUString const & s2) {
     if (s1.getLength() == s2.getLength()) {
         for (sal_Int32 i = 0; i < s1.getLength();) {
             if (s1[i] == '%' && s2[i] == '%' && s1.getLength() - i > 2
-                && isHexDigit(s1[i + 1]) && isHexDigit(s1[i + 2])
-                && isHexDigit(s2[i + 1]) && isHexDigit(s2[i + 2])
+                && rtl::isAsciiHexDigit(s1[i + 1]) && rtl::isAsciiHexDigit(s1[i + 2])
+                && rtl::isAsciiHexDigit(s2[i + 1]) && rtl::isAsciiHexDigit(s2[i + 2])
                 && equalIgnoreCase(s1[i + 1], s2[i + 1])
                 && equalIgnoreCase(s1[i + 2], s2[i + 2]))
             {
@@ -107,12 +88,12 @@ bool equalIgnoreEscapeCase(OUString const & s1, OUString const & s2) {
 }
 
 sal_Int32 parseScheme(OUString const & uriReference) {
-    if (uriReference.getLength() >= 2 && isAlpha(uriReference[0])) {
+    if (uriReference.getLength() >= 2 && rtl::isAsciiAlpha(uriReference[0])) {
         for (sal_Int32 i = 0; i < uriReference.getLength(); ++i) {
             sal_Unicode c = uriReference[i];
             if (c == ':') {
                 return i;
-            } else if (!isAlpha(c) && !isDigit(c) && c != '+' && c != '-'
+            } else if (!rtl::isAsciiAlpha(c) && !rtl::isAsciiDigit(c) && c != '+' && c != '-'
                        && c != '.')
             {
                 break;
@@ -381,7 +362,7 @@ css::uno::Reference< css::uri::XUriReference > Factory::parse(
             RTL_CONSTASCII_STRINGPARAM("com.sun.star.uri.UriSchemeParser_"));
         for (sal_Int32 i = 0; i < scheme.getLength(); ++i) {
             sal_Unicode c = scheme[i];
-            if (isUpperCase(c)) {
+            if (rtl::isAsciiUpperCase(c)) {
                 buf.append(toLowerCase(c));
             } else if (c == '+') {
                 buf.appendAscii(RTL_CONSTASCII_STRINGPARAM("PLUS"));
@@ -390,7 +371,7 @@ css::uno::Reference< css::uri::XUriReference > Factory::parse(
             } else if (c == '.') {
                 buf.appendAscii(RTL_CONSTASCII_STRINGPARAM("DOT"));
             } else {
-                OSL_ASSERT(isLowerCase(c) || isDigit(c));
+                OSL_ASSERT(rtl::isAsciiLowerCase(c) || rtl::isAsciiDigit(c));
                 buf.append(c);
             }
         }

tools/inc/tools/inetmime.hxx

@@ -23,6 +23,7 @@
 
 #include "tools/toolsdllapi.h"
 #include <rtl/alloc.h>
+#include <rtl/character.hxx>
 #include <rtl/string.hxx>
 #include <rtl/strbuf.hxx>
 #include <rtl/tencinfo.h>
@@ -537,7 +538,7 @@ public:
 // static
 inline bool INetMIME::isUSASCII(sal_uInt32 nChar)
 {
-    return nChar <= 0x7F;
+    return rtl::isAscii(nChar);
 }
 
 // static
@@ -567,74 +568,74 @@ inline bool INetMIME::isVisible(sal_uInt32 nChar)
 // static
 inline bool INetMIME::isDigit(sal_uInt32 nChar)
 {
-    return nChar >= '0' && nChar <= '9';
+    return rtl::isAsciiDigit(nChar);
 }
 
 // static
 inline bool INetMIME::isCanonicHexDigit(sal_uInt32 nChar)
 {
-    return isDigit(nChar) || (nChar >= 'A' && nChar <= 'F');
+    return rtl::isAsciiCanonicHexDigit(nChar);
 }
 
 // static
 inline bool INetMIME::isHexDigit(sal_uInt32 nChar)
 {
-    return isCanonicHexDigit(nChar) || (nChar >= 'a' && nChar <= 'f');
+    return rtl::isAsciiHexDigit(nChar);
 }
 
 // static
 inline bool INetMIME::isUpperCase(sal_uInt32 nChar)
 {
-    return nChar >= 'A' && nChar <= 'Z';
+    return rtl::isAsciiUpperCase(nChar);
 }
 
 // static
 inline bool INetMIME::isLowerCase(sal_uInt32 nChar)
 {
-    return nChar >= 'a' && nChar <= 'z';
+    return rtl::isAsciiLowerCase(nChar);
 }
 
 // static
 inline bool INetMIME::isAlpha(sal_uInt32 nChar)
 {
-    return isUpperCase(nChar) || isLowerCase(nChar);
+    return rtl::isAsciiAlpha(nChar);
 }
 
 // static
 inline bool INetMIME::isAlphanumeric(sal_uInt32 nChar)
 {
-    return isAlpha(nChar) || isDigit(nChar);
+    return rtl::isAsciiAlphanumeric(nChar);
 }
 
 // static
 inline bool INetMIME::isBase64Digit(sal_uInt32 nChar)
 {
-    return isUpperCase(nChar) || isLowerCase(nChar) || isDigit(nChar)
+    return rtl::isAsciiUpperCase(nChar) || rtl::isAsciiLowerCase(nChar) || rtl::isAsciiDigit(nChar)
            || nChar == '+' || nChar == '/';
 }
 
 // static
 inline sal_uInt32 INetMIME::toUpperCase(sal_uInt32 nChar)
 {
-    return isLowerCase(nChar) ? nChar - ('a' - 'A') : nChar;
+    return rtl::isAsciiLowerCase(nChar) ? nChar - ('a' - 'A') : nChar;
 }
 
 // static
 inline sal_uInt32 INetMIME::toLowerCase(sal_uInt32 nChar)
 {
-    return isUpperCase(nChar) ? nChar + ('a' - 'A') : nChar;
+    return rtl::isAsciiUpperCase(nChar) ? nChar + ('a' - 'A') : nChar;
 }
 
 // static
 inline int INetMIME::getWeight(sal_uInt32 nChar)
 {
-    return isDigit(nChar) ? int(nChar - '0') : -1;
+    return rtl::isAsciiDigit(nChar) ? int(nChar - '0') : -1;
 }
 
 // static
 inline int INetMIME::getHexWeight(sal_uInt32 nChar)
 {
-    return isDigit(nChar) ? int(nChar - '0') :
+    return rtl::isAsciiDigit(nChar) ? int(nChar - '0') :
            nChar >= 'A' && nChar <= 'F' ? int(nChar - 'A' + 10) :
            nChar >= 'a' && nChar <= 'f' ? int(nChar - 'a' + 10) : -1;
 }
@@ -642,9 +643,9 @@ inline int INetMIME::getHexWeight(sal_uInt32 nChar)
 // static
 inline int INetMIME::getBase64Weight(sal_uInt32 nChar)
 {
-    return isUpperCase(nChar) ? int(nChar - 'A') :
-           isLowerCase(nChar) ? int(nChar - 'a' + 26) :
-           isDigit(nChar) ? int(nChar - '0' + 52) :
+    return rtl::isAsciiUpperCase(nChar) ? int(nChar - 'A') :
+           rtl::isAsciiLowerCase(nChar) ? int(nChar - 'a' + 26) :
+           rtl::isAsciiDigit(nChar) ? int(nChar - '0' + 52) :
            nChar == '+' ? 62 :
            nChar == '/' ? 63 :
            nChar == '=' ? -1 : -2;