2019-05-02 22:45:40 +00:00
|
|
|
|
/*
|
|
|
|
|
* Copyright 2019 faddenSoft
|
|
|
|
|
*
|
|
|
|
|
* Licensed 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
|
|
|
|
|
*
|
|
|
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
|
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
|
* See the License for the specific language governing permissions and
|
|
|
|
|
* limitations under the License.
|
|
|
|
|
*/
|
|
|
|
|
using System;
|
|
|
|
|
using System.Collections.Generic;
|
|
|
|
|
using System.Diagnostics;
|
|
|
|
|
|
2019-07-20 20:28:10 +00:00
|
|
|
|
namespace SourceGen {
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// <summary>
|
|
|
|
|
/// Format descriptor for data items and instruction operands. Instances are immutable.
|
2019-08-12 00:59:20 +00:00
|
|
|
|
///
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// A list of these is saved as part of the project definition. Code and data that
|
|
|
|
|
/// doesn't have one of these will be formatted with default behavior. For data that
|
|
|
|
|
/// means a single hexadecimal byte.
|
2019-08-12 00:59:20 +00:00
|
|
|
|
///
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// These are referenced from the project and the Anattribs array. Entries in the
|
|
|
|
|
/// latter may come from the project (as specified by the user), or be auto-generated
|
|
|
|
|
/// by the data analysis pass.
|
2019-08-12 00:59:20 +00:00
|
|
|
|
///
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// There may be a large number of these, so try to keep the size down. These are usually
|
|
|
|
|
/// stored in lists, not arrays, so declaring as a struct wouldn't help with that.
|
2019-08-12 00:59:20 +00:00
|
|
|
|
///
|
Various improvements
The PseudoOpNames class is increasingly being used in situations
where mutability is undesirable. This change makes instances
immutable, eliminating the Copy() method and adding a constructor
that takes a Dictionary. The serialization code now operates on a
Dictionary instead of the class properties, but the JSON encoding is
identical, so this doesn't invalidate app settings file data.
Added an equality test to PseudoOpNames. In LineListGen, don't
reset the line list if the names haven't actually changed.
Use a table lookup for C64 character conversions. I figure that
should be faster than multiple conditionals on a modern x64 system.
Fixed a 64tass generator issue where we tried to query project
properties in a call that might not have a project available
(specifically, getting FormatConfig values out of the generator for
use in the "quick set" buttons for Display Format).
Fixed a regression test harness issue where, if the assembler reported
success but didn't actually generate output, an exception would be
thrown that halted the tests.
Increased the width of text entry fields on the Pseudo-Op tab of app
settings. The previous 8-character limit wasn't wide enough to hold
ACME's "!pseudopc". Also, use TrimEnd() to remove trailing spaces
(leading spaces are still allowed).
In the last couple of months, Win10 started stalling for a fraction
of a second when executing assemblers. It doesn't do this every
time; mostly it happens if it has been a while since the assembler
was run. My guess is this has to do with changes to the built-in
malware scanner. Whatever the case, we now change the mouse pointer
to a wait cursor while updating the assembler version cache.
2019-08-17 18:14:05 +00:00
|
|
|
|
/// IMPORTANT: The stringified names of the enum values are currently serialized into
|
|
|
|
|
/// the project file. DO NOT rename members of the enumerations without creating an
|
|
|
|
|
/// upgrade path. If new values are added, the project file version number should
|
|
|
|
|
/// be incremented.
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// </summary>
|
|
|
|
|
public class FormatDescriptor {
|
|
|
|
|
/// <summary>
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
/// General data type. Generally corresponds to the pseudo-opcode.
|
2019-05-02 22:45:40 +00:00
|
|
|
|
///
|
|
|
|
|
/// The UI only allows big-endian values in certain situations. Internally we want
|
|
|
|
|
/// to be orthogonal in case the policy changes.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public enum Type : byte {
|
|
|
|
|
Unknown = 0,
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
REMOVE, // special type, only used by operand editor
|
|
|
|
|
Default, // means "unformatted", same as not having a FormatDescriptor
|
|
|
|
|
|
|
|
|
|
NumericLE, // 1-4 byte number, little-endian
|
|
|
|
|
NumericBE, // 1-4 byte number, big-endian
|
|
|
|
|
|
|
|
|
|
StringGeneric, // character string
|
|
|
|
|
StringReverse, // character string, in reverse order
|
|
|
|
|
StringNullTerm, // C-style null-terminated string
|
|
|
|
|
StringL8, // string with 8-bit length prefix
|
|
|
|
|
StringL16, // string with 16-bit length prefix
|
|
|
|
|
StringDci, // string terminated by flipped high bit (Dextral Char Inverted)
|
|
|
|
|
|
|
|
|
|
Dense, // raw data, represented as compactly as possible
|
|
|
|
|
Fill // fill memory with a value
|
2019-05-02 22:45:40 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
/// Additional data type detail. Generally affects the operand.
|
2019-05-02 22:45:40 +00:00
|
|
|
|
///
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
/// Some things are extracted from the data itself, e.g. we don't need to specify
|
|
|
|
|
/// what value to use for Fill.
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// </summary>
|
|
|
|
|
public enum SubType : byte {
|
|
|
|
|
None = 0,
|
2019-08-10 21:24:19 +00:00
|
|
|
|
ASCII_GENERIC, // internal place-holder, used when loading older projects
|
2019-05-02 22:45:40 +00:00
|
|
|
|
|
|
|
|
|
// NumericLE/BE; default is "raw", which can have a context-specific display format
|
|
|
|
|
Hex,
|
|
|
|
|
Decimal,
|
|
|
|
|
Binary,
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
Address, // wants to be an address, but no symbol defined
|
|
|
|
|
Symbol, // symbolic ref; replace with Expression, someday?
|
|
|
|
|
|
|
|
|
|
// Strings and NumericLE/BE (single character)
|
2019-08-12 00:59:20 +00:00
|
|
|
|
Ascii, // ASCII (high bit clear)
|
2019-08-10 21:24:19 +00:00
|
|
|
|
HighAscii, // ASCII (high bit set)
|
|
|
|
|
C64Petscii, // C64 PETSCII (lower case $41-5a, upper case $c1-da)
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
C64Screen, // C64 screen code
|
2019-05-02 22:45:40 +00:00
|
|
|
|
|
|
|
|
|
// Dense; no sub-types
|
|
|
|
|
|
|
|
|
|
// Fill; default is non-ignore
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
Ignore // TODO(someday): use this for "don't care" sections
|
2019-05-02 22:45:40 +00:00
|
|
|
|
}
|
|
|
|
|
|
2019-08-10 21:24:19 +00:00
|
|
|
|
// Maximum length of a NumericLE/BE item (32-bit value or 4-byte instruction).
|
|
|
|
|
public const int MAX_NUMERIC_LEN = 4;
|
2019-05-02 22:45:40 +00:00
|
|
|
|
|
|
|
|
|
// Create some "stock" descriptors. For simple cases we return one of these
|
|
|
|
|
// instead of allocating a new object.
|
|
|
|
|
private static FormatDescriptor ONE_DEFAULT = new FormatDescriptor(1,
|
|
|
|
|
Type.Default, SubType.None);
|
|
|
|
|
private static FormatDescriptor ONE_NONE = new FormatDescriptor(1,
|
|
|
|
|
Type.NumericLE, SubType.None);
|
|
|
|
|
private static FormatDescriptor ONE_HEX = new FormatDescriptor(1,
|
|
|
|
|
Type.NumericLE, SubType.Hex);
|
|
|
|
|
private static FormatDescriptor ONE_DECIMAL = new FormatDescriptor(1,
|
|
|
|
|
Type.NumericLE, SubType.Decimal);
|
|
|
|
|
private static FormatDescriptor ONE_BINARY = new FormatDescriptor(1,
|
|
|
|
|
Type.NumericLE, SubType.Binary);
|
2019-08-10 21:24:19 +00:00
|
|
|
|
private static FormatDescriptor ONE_LOW_ASCII = new FormatDescriptor(1,
|
2019-08-12 00:59:20 +00:00
|
|
|
|
Type.NumericLE, SubType.Ascii);
|
2019-05-02 22:45:40 +00:00
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Length, in bytes, of the data to be formatted.
|
|
|
|
|
///
|
|
|
|
|
/// For an instruction, this must match what the code analyzer found as the length
|
|
|
|
|
/// of the entire instruction, or the descriptor will be ignored.
|
|
|
|
|
///
|
|
|
|
|
/// For data items, this determines the length of the formatted region.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public int Length { get; private set; }
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Primary format. The actual data must match the format:
|
|
|
|
|
/// - Numeric values must be 1-4 bytes.
|
|
|
|
|
/// - String values must be ASCII characters with a common high bit (although
|
|
|
|
|
/// the start or end may diverge from this based on the sub-type).
|
|
|
|
|
/// - Fill areas must contain identical bytes.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public Type FormatType { get; private set; }
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Sub-format specifier. Each primary format has specific sub-formats, but we
|
|
|
|
|
/// lump them all together for convenience.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public SubType FormatSubType { get; private set; }
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Symbol reference for Type=Numeric SubType=Symbol. null otherwise.
|
|
|
|
|
///
|
|
|
|
|
/// Numeric values, such as addresses and constants, can be generated with an
|
|
|
|
|
/// expression. Currently we only support using a single symbol, but the goal
|
|
|
|
|
/// is to allow free-form expressions like "(sym1+sym2+$80)/3".
|
|
|
|
|
///
|
|
|
|
|
/// If the symbol exists, the symbol's name will be shown, possibly with an adjustment
|
|
|
|
|
/// to make the symbol value match the operand or data item.
|
|
|
|
|
///
|
|
|
|
|
/// Note this reference has a "part" modifier, so we can use it for e.g. "#>label".
|
|
|
|
|
/// </summary>
|
|
|
|
|
public WeakSymbolRef SymbolRef { get; private set; }
|
|
|
|
|
|
|
|
|
|
// Crude attempt to see how effective the prefab object creation is. Note we create
|
|
|
|
|
// these for DefSymbols, so there will be one prefab for every platform symbol entry.
|
|
|
|
|
public static int DebugCreateCount { get; private set; }
|
|
|
|
|
public static int DebugPrefabCount { get; private set; }
|
|
|
|
|
public static void DebugPrefabBump(int adj=1) {
|
|
|
|
|
DebugCreateCount += adj;
|
|
|
|
|
DebugPrefabCount += adj;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Constructor for base type data item.
|
|
|
|
|
/// </summary>
|
Allow explicit widths in project/platform symbols, part 1
The ability to give explicit widths to local variables worked out
pretty well, so we're going to try adding the same thing to project
and platform symbols.
The first step is to allow widths to be specified in platform files,
and set with the project symbol editor. The DefSymbol editor is
also used for local variables, so a bit of dancing is required.
For platform/project symbols the width is optional, and is totally
ignored for constants. (For variables, constants are used for the
StackRel args, so the width is meaningful and required.)
We also now show the symbol's type (address or constant) and width
in the listing. This gets really distracting when overused, so we
only show it when the width is explicitly set. The default width
is 1, which most things will be, so users can make an aesthetic
choice there. (The place where widths make very little sense is when
the symbol represents a code entry point, rather than a data item.)
The maximum width of a local variable is now 256, but it's not
allowed to overlap with other variables or run of the end of the
direct page. The maximum width of a platform/project symbol is
65536, with bank-wrap behavior TBD.
The local variable table editor now refers to stack-relative
constants as such, rather than simply "constant", to make it clear
that it's not just defining an 8-bit constant.
Widths have been added to a handful of Apple II platform defs.
2019-10-01 21:58:24 +00:00
|
|
|
|
/// <param name="length">Length, in bytes.</param>
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// <param name="fmt">Format type.</param>
|
|
|
|
|
/// <param name="subFmt">Format sub-type.</param>
|
|
|
|
|
private FormatDescriptor(int length, Type fmt, SubType subFmt) {
|
|
|
|
|
Debug.Assert(length > 0);
|
|
|
|
|
Debug.Assert(length <= MAX_NUMERIC_LEN || !IsNumeric);
|
|
|
|
|
Debug.Assert(fmt != Type.Default || length == 1);
|
|
|
|
|
|
|
|
|
|
Length = length;
|
|
|
|
|
FormatType = fmt;
|
|
|
|
|
FormatSubType = subFmt;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Constructor for symbol item.
|
|
|
|
|
/// </summary>
|
|
|
|
|
/// <param name="length">Length, in bytes.</param>
|
|
|
|
|
/// <param name="sym">Weak symbol reference.</param>
|
|
|
|
|
/// <param name="isBigEndian">Set to true for big-endian data.</param>
|
|
|
|
|
private FormatDescriptor(int length, WeakSymbolRef sym, bool isBigEndian) {
|
|
|
|
|
Debug.Assert(sym != null);
|
|
|
|
|
Debug.Assert(length > 0 && length <= MAX_NUMERIC_LEN);
|
|
|
|
|
Length = length;
|
|
|
|
|
FormatType = isBigEndian ? Type.NumericBE : Type.NumericLE;
|
|
|
|
|
FormatSubType = SubType.Symbol;
|
|
|
|
|
SymbolRef = sym;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Returns a descriptor with the requested characteristics. For common cases this
|
|
|
|
|
/// returns a pre-allocated object, for less-common cases this allocates a new object.
|
|
|
|
|
///
|
|
|
|
|
/// Objects are immutable and do not specify a file offset, so they may be re-used
|
|
|
|
|
/// by the caller.
|
|
|
|
|
/// </summary>
|
|
|
|
|
/// <param name="length">Length, in bytes.</param>
|
|
|
|
|
/// <param name="fmt">Format type.</param>
|
|
|
|
|
/// <param name="subFmt">Format sub-type.</param>
|
|
|
|
|
/// <returns>New or pre-allocated descriptor.</returns>
|
|
|
|
|
public static FormatDescriptor Create(int length, Type fmt, SubType subFmt) {
|
|
|
|
|
DebugCreateCount++;
|
|
|
|
|
DebugPrefabCount++;
|
|
|
|
|
if (length == 1) {
|
|
|
|
|
if (fmt == Type.Default) {
|
|
|
|
|
Debug.Assert(subFmt == SubType.None);
|
|
|
|
|
return ONE_DEFAULT;
|
|
|
|
|
} else if (fmt == Type.NumericLE) {
|
|
|
|
|
switch (subFmt) {
|
|
|
|
|
case SubType.None:
|
|
|
|
|
return ONE_NONE;
|
|
|
|
|
case SubType.Hex:
|
|
|
|
|
return ONE_HEX;
|
|
|
|
|
case SubType.Decimal:
|
|
|
|
|
return ONE_DECIMAL;
|
|
|
|
|
case SubType.Binary:
|
|
|
|
|
return ONE_BINARY;
|
2019-08-12 00:59:20 +00:00
|
|
|
|
case SubType.Ascii:
|
2019-08-10 21:24:19 +00:00
|
|
|
|
return ONE_LOW_ASCII;
|
2019-05-02 22:45:40 +00:00
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
// For a new file, this will be mostly strings and Fill.
|
|
|
|
|
DebugPrefabCount--;
|
|
|
|
|
return new FormatDescriptor(length, fmt, subFmt);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Returns a descriptor with a symbol.
|
|
|
|
|
/// </summary>
|
|
|
|
|
/// <param name="length">Length, in bytes.</param>
|
|
|
|
|
/// <param name="sym">Weak symbol reference.</param>
|
|
|
|
|
/// <param name="isBigEndian">Set to true for big-endian data.</param>
|
|
|
|
|
/// <returns>New or pre-allocated descriptor.</returns>
|
|
|
|
|
public static FormatDescriptor Create(int length, WeakSymbolRef sym, bool isBigEndian) {
|
|
|
|
|
DebugCreateCount++;
|
|
|
|
|
return new FormatDescriptor(length, sym, isBigEndian);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// True if the descriptor is okay to use on an instruction operand. The CPU only
|
|
|
|
|
/// understands little-endian numeric values, so that's all we allow.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public bool IsValidForInstruction {
|
|
|
|
|
get {
|
|
|
|
|
switch (FormatType) {
|
|
|
|
|
case Type.Default:
|
|
|
|
|
case Type.NumericLE:
|
|
|
|
|
//case Type.NumericBE:
|
|
|
|
|
return true;
|
|
|
|
|
default:
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// True if the FormatDescriptor has a symbol.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public bool HasSymbol {
|
|
|
|
|
get {
|
|
|
|
|
Debug.Assert(SymbolRef == null || (IsNumeric && FormatSubType == SubType.Symbol));
|
|
|
|
|
return SymbolRef != null;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// True if the FormatDescriptor is a numeric type (NumericLE or NumericBE).
|
|
|
|
|
/// </summary>
|
|
|
|
|
public bool IsNumeric {
|
|
|
|
|
get {
|
|
|
|
|
return FormatType == Type.NumericLE || FormatType == Type.NumericBE;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
/// <summary>
|
|
|
|
|
/// True if the FormatDescriptor is a string type.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public bool IsString {
|
|
|
|
|
get {
|
|
|
|
|
switch (FormatType) {
|
|
|
|
|
case Type.StringGeneric:
|
|
|
|
|
case Type.StringReverse:
|
|
|
|
|
case Type.StringNullTerm:
|
|
|
|
|
case Type.StringL8:
|
|
|
|
|
case Type.StringL16:
|
|
|
|
|
case Type.StringDci:
|
|
|
|
|
return true;
|
|
|
|
|
default:
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2019-08-21 20:30:25 +00:00
|
|
|
|
/// <summary>
|
|
|
|
|
/// True if the FormatDescriptor is a string or character.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public bool IsStringOrCharacter {
|
|
|
|
|
get {
|
|
|
|
|
switch (FormatSubType) {
|
|
|
|
|
case SubType.ASCII_GENERIC:
|
|
|
|
|
case SubType.Ascii:
|
|
|
|
|
case SubType.HighAscii:
|
|
|
|
|
case SubType.C64Petscii:
|
|
|
|
|
case SubType.C64Screen:
|
|
|
|
|
return true;
|
|
|
|
|
default:
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2019-05-02 22:45:40 +00:00
|
|
|
|
/// <summary>
|
|
|
|
|
/// True if the FormatDescriptor has a symbol or is Numeric/Address.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public bool HasSymbolOrAddress {
|
|
|
|
|
// Derived from other fields, so you can ignore this in equality tests. This is
|
|
|
|
|
// of interest to undo/redo, since changing a symbol reference can affect data scan.
|
|
|
|
|
get {
|
|
|
|
|
return HasSymbol || FormatSubType == SubType.Address;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Numeric base specific by format/sub-format. Returns 16 when uncertain.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public int NumBase {
|
|
|
|
|
get {
|
|
|
|
|
if (FormatType != Type.NumericLE && FormatType != Type.NumericBE) {
|
|
|
|
|
Debug.Assert(false);
|
|
|
|
|
return 16;
|
|
|
|
|
}
|
|
|
|
|
switch (FormatSubType) {
|
|
|
|
|
case SubType.None:
|
|
|
|
|
case SubType.Hex:
|
|
|
|
|
return 16;
|
|
|
|
|
case SubType.Decimal:
|
|
|
|
|
return 10;
|
|
|
|
|
case SubType.Binary:
|
|
|
|
|
return 2;
|
|
|
|
|
default:
|
|
|
|
|
Debug.Assert(false);
|
|
|
|
|
return 16;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Returns the FormatSubType enum constant for the specified numeric base.
|
|
|
|
|
/// </summary>
|
|
|
|
|
/// <param name="numBase">Base (2, 10, or 16).</param>
|
|
|
|
|
/// <returns>Enum value.</returns>
|
|
|
|
|
public static SubType GetSubTypeForBase(int numBase) {
|
|
|
|
|
switch (numBase) {
|
|
|
|
|
case 2: return SubType.Binary;
|
|
|
|
|
case 10: return SubType.Decimal;
|
|
|
|
|
case 16: return SubType.Hex;
|
|
|
|
|
default:
|
|
|
|
|
Debug.Assert(false);
|
|
|
|
|
return SubType.Hex;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Generates a string describing the format, suitable for use in the UI.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public string ToUiString() {
|
|
|
|
|
// NOTE: this should be made easier to localize
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
|
|
|
|
|
if (IsString) {
|
|
|
|
|
string descr;
|
|
|
|
|
switch (FormatSubType) {
|
2019-08-12 00:59:20 +00:00
|
|
|
|
case SubType.Ascii:
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
descr = "ASCII";
|
|
|
|
|
break;
|
2019-08-10 21:24:19 +00:00
|
|
|
|
case SubType.HighAscii:
|
|
|
|
|
descr = "ASCII (high)";
|
|
|
|
|
break;
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
case SubType.C64Petscii:
|
|
|
|
|
descr = "C64 PETSCII";
|
|
|
|
|
break;
|
|
|
|
|
case SubType.C64Screen:
|
|
|
|
|
descr = "C64 Screen";
|
|
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
descr = "???";
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
switch (FormatType) {
|
|
|
|
|
case Type.StringGeneric:
|
|
|
|
|
descr += " string";
|
|
|
|
|
break;
|
|
|
|
|
case Type.StringReverse:
|
|
|
|
|
descr += " string (reverse)";
|
|
|
|
|
break;
|
|
|
|
|
case Type.StringNullTerm:
|
|
|
|
|
descr += " string (null term)";
|
|
|
|
|
break;
|
|
|
|
|
case Type.StringL8:
|
|
|
|
|
descr += " string (1-byte len)";
|
|
|
|
|
break;
|
|
|
|
|
case Type.StringL16:
|
|
|
|
|
descr += " string (2-byte len)";
|
|
|
|
|
break;
|
|
|
|
|
case Type.StringDci:
|
|
|
|
|
descr += " string (DCI)";
|
|
|
|
|
break;
|
|
|
|
|
default:
|
|
|
|
|
descr += " ???";
|
|
|
|
|
break;
|
|
|
|
|
}
|
2019-08-16 00:53:12 +00:00
|
|
|
|
return descr;
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
}
|
|
|
|
|
|
2019-05-02 22:45:40 +00:00
|
|
|
|
switch (FormatSubType) {
|
|
|
|
|
case SubType.None:
|
|
|
|
|
switch (FormatType) {
|
|
|
|
|
case Type.Default:
|
|
|
|
|
case Type.NumericLE:
|
|
|
|
|
return "Numeric (little-endian)";
|
|
|
|
|
case Type.NumericBE:
|
|
|
|
|
return "Numeric (big-endian)";
|
|
|
|
|
case Type.Dense:
|
|
|
|
|
return "Dense";
|
|
|
|
|
case Type.Fill:
|
|
|
|
|
return "Fill";
|
|
|
|
|
default:
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
// strings handled earlier
|
2019-05-02 22:45:40 +00:00
|
|
|
|
return "???";
|
|
|
|
|
}
|
|
|
|
|
case SubType.Hex:
|
|
|
|
|
return "Numeric, Hex";
|
|
|
|
|
case SubType.Decimal:
|
|
|
|
|
return "Numeric, Decimal";
|
|
|
|
|
case SubType.Binary:
|
|
|
|
|
return "Numeric, Binary";
|
|
|
|
|
case SubType.Address:
|
|
|
|
|
return "Address";
|
|
|
|
|
case SubType.Symbol:
|
2019-08-31 01:33:05 +00:00
|
|
|
|
if (SymbolRef.IsVariable) {
|
|
|
|
|
return "Local var \"" + SymbolRef.Label + "\"";
|
|
|
|
|
} else {
|
|
|
|
|
return "Symbol \"" + SymbolRef.Label + "\"";
|
|
|
|
|
}
|
2019-08-12 00:59:20 +00:00
|
|
|
|
case SubType.Ascii:
|
2019-08-10 21:24:19 +00:00
|
|
|
|
return "Numeric, ASCII";
|
|
|
|
|
case SubType.HighAscii:
|
|
|
|
|
return "Numeric, ASCII (high)";
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
case SubType.C64Petscii:
|
2019-08-10 21:24:19 +00:00
|
|
|
|
return "Numeric, C64 PETSCII";
|
Change the way string formats are defined
We used to use type="String", with the sub-type indicating whether
the string was null-terminated, prefixed with a length, or whatever.
This didn't leave much room for specifying a character encoding,
which is orthogonal to the sub-type.
What we actually want is to have the type specify the string type,
and then have the sub-type determine the character encoding. These
sub-types can also be used with the Numeric type to specify the
encoding of character operands.
This change updates the enum definitions and the various bits of
code that use them, but does not add any code for working with
non-ASCII character encodings.
The project file version number was incremented to 2, since the new
FormatDescriptor serialization is mildly incompatible with the old.
(Won't explode, but it'll post a complaint and ignore the stuff
it doesn't recognize.)
While I was at it, I finished removing DciReverse. It's still part
of the 2005-string-types regression test, which currently fails
because the generated source doesn't match.
2019-08-07 22:23:23 +00:00
|
|
|
|
case SubType.C64Screen:
|
2019-08-10 21:24:19 +00:00
|
|
|
|
return "Numeric, C64 Screen";
|
2019-05-02 22:45:40 +00:00
|
|
|
|
|
|
|
|
|
default:
|
|
|
|
|
return "???";
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
public override string ToString() {
|
|
|
|
|
return "[FmtDesc: len=" + Length + " fmt=" + FormatType + " sub=" + FormatSubType +
|
|
|
|
|
" sym=" + SymbolRef + "]";
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
public static bool operator ==(FormatDescriptor a, FormatDescriptor b) {
|
|
|
|
|
if (ReferenceEquals(a, b)) {
|
|
|
|
|
return true; // same object, or both null
|
|
|
|
|
}
|
|
|
|
|
if (ReferenceEquals(a, null) || ReferenceEquals(b, null)) {
|
|
|
|
|
return false; // one is null
|
|
|
|
|
}
|
|
|
|
|
return a.Length == b.Length && a.FormatType == b.FormatType &&
|
|
|
|
|
a.FormatSubType == b.FormatSubType && a.SymbolRef == b.SymbolRef;
|
|
|
|
|
}
|
|
|
|
|
public static bool operator !=(FormatDescriptor a, FormatDescriptor b) {
|
|
|
|
|
return !(a == b);
|
|
|
|
|
}
|
|
|
|
|
public override bool Equals(object obj) {
|
|
|
|
|
return obj is FormatDescriptor && this == (FormatDescriptor)obj;
|
|
|
|
|
}
|
|
|
|
|
public override int GetHashCode() {
|
|
|
|
|
int hashCode = 0;
|
|
|
|
|
if (SymbolRef != null) {
|
|
|
|
|
hashCode = SymbolRef.GetHashCode();
|
|
|
|
|
}
|
|
|
|
|
hashCode ^= Length;
|
|
|
|
|
hashCode ^= (int)FormatType;
|
|
|
|
|
hashCode ^= (int)FormatSubType;
|
|
|
|
|
return hashCode;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
/// Debugging utility function to dump a sorted list of objects.
|
|
|
|
|
/// </summary>
|
|
|
|
|
public static void DebugDumpSortedList(SortedList<int, FormatDescriptor> list) {
|
|
|
|
|
if (list == null) {
|
|
|
|
|
Debug.WriteLine("FormatDescriptor list is empty");
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
Debug.WriteLine("FormatDescriptor list (" + list.Count + " entries)");
|
|
|
|
|
foreach (KeyValuePair<int, FormatDescriptor> kvp in list) {
|
|
|
|
|
int offset = kvp.Key;
|
|
|
|
|
FormatDescriptor dfd = kvp.Value;
|
|
|
|
|
Debug.WriteLine(" +" + offset.ToString("x6") + ",+" +
|
|
|
|
|
(offset + dfd.Length - 1).ToString("x6") + ": " + dfd.FormatType +
|
|
|
|
|
"(" + dfd.FormatSubType + ")");
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|