CW Cyrix's Git Repository Mirror
Browse code

Lots of changes in regards to strings, as follows:

* Removed my custom String class, as well as removed the really old
Unicode ConvertUTF, the UTF Converter, and the UTF Encode/Decode
functions.
* Replaced the above with using standard C++ std::wstring_convert and
std::codecvt_utf8.
* Added headers adapted from llvm's libc++ project for allowing the
above C++ classes to exist with GCC and Clang when libc++ isn't being
used.
* Used std::string over std::wstring whenever possible.
* Added header adapted from llvm's libc++ project to create special
versions of the ifstream and ofstream classes that would utilize _wfopen
on non-MSVC Windows compilers, so those compilers could access files on
Windows that use characters outside the current codepage.
* Removed the -static-libgcc and -static-libstdc++ flags from the
Makefile for non-MSVC builds. The generated DLLs will require extra DLLs
from either Cygwin or MinGW (whichever is used to compile), I've only
tested with MinGW and for some reason they crash Winamp on exit, I have
no idea why.

Naram Qashat authored on 2014/09/24 13:58:55
Showing 1 changed files
src/in_xsf_framework/ConvertUTF.h
History View file @ fe3d6ae
1 1 
deleted file mode 100644
... ... 
@@ -1,131 +0,0 @@
1 
-/*
2 
- * Copyright 2001-2004 Unicode, Inc.
3 
- *
4 
- * Disclaimer
5 
- *
6 
- * This source code is provided as is by Unicode, Inc. No claims are
7 
- * made as to fitness for any particular purpose. No warranties of any
8 
- * kind are expressed or implied. The recipient agrees to determine
9 
- * applicability of information provided. If this file has been
10 
- * purchased on magnetic or optical media from Unicode, Inc., the
11 
- * sole remedy for any claim will be exchange of defective media
12 
- * within 90 days of receipt.
13 
- *
14 
- * Limitations on Rights to Redistribute This Code
15 
- *
16 
- * Unicode, Inc. hereby grants the right to freely use the information
17 
- * supplied in this file in the creation of products supporting the
18 
- * Unicode Standard, and to make copies of this file in any form
19 
- * for internal or external distribution as long as this notice
20 
- * remains attached.
21 
- */
22 
-
23 
-/* ---------------------------------------------------------------------
24 
-
25 
-    Conversions between UTF32, UTF-16, and UTF-8.  Header file.
26 
-
27 
-    Several funtions are included here, forming a complete set of
28 
-    conversions between the three formats.  UTF-7 is not included
29 
-    here, but is handled in a separate source file.
30 
-
31 
-    Each of these routines takes pointers to input buffers and output
32 
-    buffers.  The input buffers are const.
33 
-
34 
-    Each routine converts the text between *sourceStart and sourceEnd,
35 
-    putting the result into the buffer between *targetStart and
36 
-    targetEnd. Note: the end pointers are *after* the last item: e.g.
37 
-    *(sourceEnd - 1) is the last item.
38 
-
39 
-    The return result indicates whether the conversion was successful,
40 
-    and if not, whether the problem was in the source or target buffers.
41 
-    (Only the first encountered problem is indicated.)
42 
-
43 
-    After the conversion, *sourceStart and *targetStart are both
44 
-    updated to point to the end of last text successfully converted in
45 
-    the respective buffers.
46 
-
47 
-    Input parameters:
48 
-	sourceStart - pointer to a pointer to the source buffer.
49 
-		The contents of this are modified on return so that
50 
-		it points at the next thing to be converted.
51 
-	targetStart - similarly, pointer to pointer to the target buffer.
52 
-	sourceEnd, targetEnd - respectively pointers to the ends of the
53 
-		two buffers, for overflow checking only.
54 
-
55 
-    These conversion functions take a ConversionFlags argument. When this
56 
-    flag is set to strict, both irregular sequences and isolated surrogates
57 
-    will cause an error.  When the flag is set to lenient, both irregular
58 
-    sequences and isolated surrogates are converted.
59 
-
60 
-    Whether the flag is strict or lenient, all illegal sequences will cause
61 
-    an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
62 
-    or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
63 
-    must check for illegal sequences.
64 
-
65 
-    When the flag is set to lenient, characters over 0x10FFFF are converted
66 
-    to the replacement character; otherwise (when the flag is set to strict)
67 
-    they constitute an error.
68 
-
69 
-    Output parameters:
70 
-	The value "sourceIllegal" is returned from some routines if the input
71 
-	sequence is malformed.  When "sourceIllegal" is returned, the source
72 
-	value will point to the illegal value that caused the problem. E.g.,
73 
-	in UTF-8 when a sequence is malformed, it points to the start of the
74 
-	malformed sequence.
75 
-
76 
-    Author: Mark E. Davis, 1994.
77 
-    Rev History: Rick McGowan, fixes & updates May 2001.
78 
-		 Fixes & updates, Sept 2001.
79 
-
80 
-
81 
-#pragma once
82 
-
83 
-/* ---------------------------------------------------------------------
84 
-    The following 4 definitions are compiler-specific.
85 
-    The C standard does not guarantee that wchar_t has at least
86 
-    16 bits, so wchar_t is no less portable than unsigned short!
87 
-    All should be unsigned values to avoid sign extension during
88 
-    bit mask & shift operations.
89 
-
90 
-typedef unsigned long UTF32; /* at least 32 bits */
91 
-typedef unsigned short UTF16; /* at least 16 bits */
92 
-typedef unsigned char UTF8; /* typically 8 bits */
93 
-
94 
-/* Some fundamental constants */
95 
-static const UTF32 UNI_REPLACEMENT_CHAR = 0x0000FFFD;
96 
-static const UTF32 UNI_MAX_BMP = 0x0000FFFF;
97 
-static const UTF32 UNI_MAX_UTF16 = 0x0010FFFF;
98 
-static const UTF32 UNI_MAX_UTF32 = 0x7FFFFFFF;
99 
-static const UTF32 UNI_MAX_LEGAL_UTF32 = 0x0010FFFF;
100 
-
101 
-enum ConversionResult
102 
-{
103 
-	conversionOK,		/* conversion successful */
104 
-	sourceExhausted,	/* partial character in source, but hit end */
105 
-	targetExhausted,	/* insuff. room in target for conversion */
106 
-	sourceIllegal		/* source sequence is illegal/malformed */
107 
-};
108 
-
109 
-enum ConversionFlags
110 
-{
111 
-	strictConversion,
112 
-	lenientConversion
113 
-};
114 
-
115 
-ConversionResult ConvertUTF8toUTF16(const UTF8 **, const UTF8 *, UTF16 **, UTF16 *, ConversionFlags);
116 
-
117 
-ConversionResult ConvertUTF16toUTF8(const UTF16 **, const UTF16 *, UTF8 **, UTF8 *, ConversionFlags);
118 
-
119 
-ConversionResult ConvertUTF8toUTF32(const UTF8 **, const UTF8 *, UTF32 **, UTF32 *, ConversionFlags);
120 
-
121 
-ConversionResult ConvertUTF32toUTF8(const UTF32 **, const UTF32 *, UTF8 **, UTF8 *, ConversionFlags);
122 
-
123 
-ConversionResult ConvertUTF16toUTF32(const UTF16 **, const UTF16 *, UTF32 **, UTF32 *, ConversionFlags);
124 
-
125 
-ConversionResult ConvertUTF32toUTF16(const UTF32 **, const UTF32 *, UTF16 **, UTF16 *, ConversionFlags);
126 
-
127 
-bool isLegalUTF8Sequence(const UTF8 *, const UTF8 *);
128 
-
129 
-/* --------------------------------------------------------------------- */
Browse code

Use #pragma once instead of include guards.

Naram Qashat authored on 2014/09/08 14:47:36
Showing 1 changed files
src/in_xsf_framework/ConvertUTF.h
History View file @ b6add6e
... ... 
@@ -79,8 +79,7 @@
79 79
80 80 
 ------------------------------------------------------------------------ */
81 81
82 
-#ifndef _CONVERTUTF_H_
83 
-#define _CONVERTUTF_H_
82 
+#pragma once
84 83
85 84 
 /* ---------------------------------------------------------------------
86 85 
     The following 4 definitions are compiler-specific.
... ... 
@@ -130,5 +129,3 @@ ConversionResult ConvertUTF32toUTF16(const UTF32 **, const UTF32 *, UTF16 **, UT
130 129 
 bool isLegalUTF8Sequence(const UTF8 *, const UTF8 *);
131 130
132 131 
 /* --------------------------------------------------------------------- */
133 
-
134 
-#endif
Browse code

Import actual code.

Naram Qashat authored on 2013/03/26 02:41:19
Showing 1 changed files
src/in_xsf_framework/ConvertUTF.h
History View file @ bc076aa
1 1 
new file mode 100644
... ... 
@@ -0,0 +1,134 @@
1 
+/*
2 
+ * Copyright 2001-2004 Unicode, Inc.
3 
+ *
4 
+ * Disclaimer
5 
+ *
6 
+ * This source code is provided as is by Unicode, Inc. No claims are
7 
+ * made as to fitness for any particular purpose. No warranties of any
8 
+ * kind are expressed or implied. The recipient agrees to determine
9 
+ * applicability of information provided. If this file has been
10 
+ * purchased on magnetic or optical media from Unicode, Inc., the
11 
+ * sole remedy for any claim will be exchange of defective media
12 
+ * within 90 days of receipt.
13 
+ *
14 
+ * Limitations on Rights to Redistribute This Code
15 
+ *
16 
+ * Unicode, Inc. hereby grants the right to freely use the information
17 
+ * supplied in this file in the creation of products supporting the
18 
+ * Unicode Standard, and to make copies of this file in any form
19 
+ * for internal or external distribution as long as this notice
20 
+ * remains attached.
21 
+ */
22 
+
23 
+/* ---------------------------------------------------------------------
24 
+
25 
+    Conversions between UTF32, UTF-16, and UTF-8.  Header file.
26 
+
27 
+    Several funtions are included here, forming a complete set of
28 
+    conversions between the three formats.  UTF-7 is not included
29 
+    here, but is handled in a separate source file.
30 
+
31 
+    Each of these routines takes pointers to input buffers and output
32 
+    buffers.  The input buffers are const.
33 
+
34 
+    Each routine converts the text between *sourceStart and sourceEnd,
35 
+    putting the result into the buffer between *targetStart and
36 
+    targetEnd. Note: the end pointers are *after* the last item: e.g.
37 
+    *(sourceEnd - 1) is the last item.
38 
+
39 
+    The return result indicates whether the conversion was successful,
40 
+    and if not, whether the problem was in the source or target buffers.
41 
+    (Only the first encountered problem is indicated.)
42 
+
43 
+    After the conversion, *sourceStart and *targetStart are both
44 
+    updated to point to the end of last text successfully converted in
45 
+    the respective buffers.
46 
+
47 
+    Input parameters:
48 
+	sourceStart - pointer to a pointer to the source buffer.
49 
+		The contents of this are modified on return so that
50 
+		it points at the next thing to be converted.
51 
+	targetStart - similarly, pointer to pointer to the target buffer.
52 
+	sourceEnd, targetEnd - respectively pointers to the ends of the
53 
+		two buffers, for overflow checking only.
54 
+
55 
+    These conversion functions take a ConversionFlags argument. When this
56 
+    flag is set to strict, both irregular sequences and isolated surrogates
57 
+    will cause an error.  When the flag is set to lenient, both irregular
58 
+    sequences and isolated surrogates are converted.
59 
+
60 
+    Whether the flag is strict or lenient, all illegal sequences will cause
61 
+    an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
62 
+    or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
63 
+    must check for illegal sequences.
64 
+
65 
+    When the flag is set to lenient, characters over 0x10FFFF are converted
66 
+    to the replacement character; otherwise (when the flag is set to strict)
67 
+    they constitute an error.
68 
+
69 
+    Output parameters:
70 
+	The value "sourceIllegal" is returned from some routines if the input
71 
+	sequence is malformed.  When "sourceIllegal" is returned, the source
72 
+	value will point to the illegal value that caused the problem. E.g.,
73 
+	in UTF-8 when a sequence is malformed, it points to the start of the
74 
+	malformed sequence.
75 
+
76 
+    Author: Mark E. Davis, 1994.
77 
+    Rev History: Rick McGowan, fixes & updates May 2001.
78 
+		 Fixes & updates, Sept 2001.
79 
+
80 
+------------------------------------------------------------------------ */
81 
+
82 
+#ifndef _CONVERTUTF_H_
83 
+#define _CONVERTUTF_H_
84 
+
85 
+/* ---------------------------------------------------------------------
86 
+    The following 4 definitions are compiler-specific.
87 
+    The C standard does not guarantee that wchar_t has at least
88 
+    16 bits, so wchar_t is no less portable than unsigned short!
89 
+    All should be unsigned values to avoid sign extension during
90 
+    bit mask & shift operations.
91 
+------------------------------------------------------------------------ */
92 
+
93 
+typedef unsigned long UTF32; /* at least 32 bits */
94 
+typedef unsigned short UTF16; /* at least 16 bits */
95 
+typedef unsigned char UTF8; /* typically 8 bits */
96 
+
97 
+/* Some fundamental constants */
98 
+static const UTF32 UNI_REPLACEMENT_CHAR = 0x0000FFFD;
99 
+static const UTF32 UNI_MAX_BMP = 0x0000FFFF;
100 
+static const UTF32 UNI_MAX_UTF16 = 0x0010FFFF;
101 
+static const UTF32 UNI_MAX_UTF32 = 0x7FFFFFFF;
102 
+static const UTF32 UNI_MAX_LEGAL_UTF32 = 0x0010FFFF;
103 
+
104 
+enum ConversionResult
105 
+{
106 
+	conversionOK,		/* conversion successful */
107 
+	sourceExhausted,	/* partial character in source, but hit end */
108 
+	targetExhausted,	/* insuff. room in target for conversion */
109 
+	sourceIllegal		/* source sequence is illegal/malformed */
110 
+};
111 
+
112 
+enum ConversionFlags
113 
+{
114 
+	strictConversion,
115 
+	lenientConversion
116 
+};
117 
+
118 
+ConversionResult ConvertUTF8toUTF16(const UTF8 **, const UTF8 *, UTF16 **, UTF16 *, ConversionFlags);
119 
+
120 
+ConversionResult ConvertUTF16toUTF8(const UTF16 **, const UTF16 *, UTF8 **, UTF8 *, ConversionFlags);
121 
+
122 
+ConversionResult ConvertUTF8toUTF32(const UTF8 **, const UTF8 *, UTF32 **, UTF32 *, ConversionFlags);
123 
+
124 
+ConversionResult ConvertUTF32toUTF8(const UTF32 **, const UTF32 *, UTF8 **, UTF8 *, ConversionFlags);
125 
+
126 
+ConversionResult ConvertUTF16toUTF32(const UTF16 **, const UTF16 *, UTF32 **, UTF32 *, ConversionFlags);
127 
+
128 
+ConversionResult ConvertUTF32toUTF16(const UTF32 **, const UTF32 *, UTF16 **, UTF16 *, ConversionFlags);
129 
+
130 
+bool isLegalUTF8Sequence(const UTF8 *, const UTF8 *);
131 
+
132 
+/* --------------------------------------------------------------------- */
133 
+
134 
+#endif