simple compiler (most intermediate language generation missing)

.clang-format

@@ -0,0 +1,205 @@
+---
+Language:        Cpp
+# BasedOnStyle:  Google
+AccessModifierOffset: -1
+AlignAfterOpenBracket: Align
+AlignArrayOfStructures: None
+AlignConsecutiveMacros: None
+AlignConsecutiveAssignments: None
+AlignConsecutiveBitFields: None
+AlignConsecutiveDeclarations: None
+AlignEscapedNewlines: Left
+AlignOperands:   Align
+AlignTrailingComments: true
+AllowAllArgumentsOnNextLine: true
+AllowAllParametersOfDeclarationOnNextLine: true
+AllowShortEnumsOnASingleLine: false
+AllowShortBlocksOnASingleLine: Never
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Empty
+AllowShortLambdasOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: Never
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: Yes
+AttributeMacros:
+  - __capability
+BinPackArguments: true
+BinPackParameters: true
+BraceWrapping:
+  AfterCaseLabel:  false
+  AfterClass:      false
+  AfterControlStatement: Never
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  AfterExternBlock: false
+  BeforeCatch:     false
+  BeforeElse:      false
+  BeforeLambdaBody: false
+  BeforeWhile:     false
+  IndentBraces:    false
+  SplitEmptyFunction: true
+  SplitEmptyRecord: true
+  SplitEmptyNamespace: true
+BreakBeforeBinaryOperators: None
+BreakBeforeConceptDeclarations: true
+BreakBeforeBraces: Attach
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: BeforeColon
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakConstructorInitializers: BeforeColon
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: true
+ColumnLimit:     80
+CommentPragmas:  '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DeriveLineEnding: true
+DerivePointerAlignment: true
+DisableFormat:   false
+EmptyLineAfterAccessModifier: Never
+EmptyLineBeforeAccessModifier: LogicalBlock
+ExperimentalAutoDetectBinPacking: false
+BasedOnStyle:    ''
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+AllowAllConstructorInitializersOnNextLine: true
+FixNamespaceComments: true
+ForEachMacros:
+  - foreach
+  - Q_FOREACH
+  - BOOST_FOREACH
+IfMacros:
+  - KJ_IF_MAYBE
+IncludeBlocks:   Regroup
+IncludeCategories:
+  - Regex:           '^<xlang.*\.h>$'
+    Priority:        3
+  - Regex:           '^<sys/.*\.h>$'
+    Priority:        1
+  - Regex:           '^<.*\.h>$'
+    Priority:        2
+  - Regex:           '.*'
+    Priority:        3
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeIsMainSourceRegex: ''
+IndentAccessModifiers: false
+IndentCaseLabels: true
+IndentCaseBlocks: false
+IndentGotoLabels: true
+IndentPPDirectives: None
+IndentExternBlock: AfterExternBlock
+IndentRequires:  false
+IndentWidth:     2
+IndentWrappedFunctionNames: false
+InsertTrailingCommas: None
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+LambdaBodyIndentation: Signature
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBinPackProtocolList: Never
+ObjCBlockIndentWidth: 2
+ObjCBreakBeforeNestedBlockParam: true
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: true
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PenaltyIndentedWhitespace: 0
+PointerAlignment: Left
+PPIndentWidth:   -1
+RawStringFormats:
+  - Language:        Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+    BasedOnStyle:    google
+  - Language:        TextProto
+    Delimiters:
+      - pb
+      - PB
+      - proto
+      - PROTO
+    EnclosingFunctions:
+      - EqualsProto
+      - EquivToProto
+      - PARSE_PARTIAL_TEXT_PROTO
+      - PARSE_TEST_PROTO
+      - PARSE_TEXT_PROTO
+      - ParseTextOrDie
+      - ParseTextProtoOrDie
+      - ParseTestProto
+      - ParsePartialTestProto
+    CanonicalDelimiter: pb
+    BasedOnStyle:    google
+ReferenceAlignment: Pointer
+ReflowComments:  true
+ShortNamespaceLines: 1
+SortIncludes:    CaseSensitive
+SortJavaStaticImport: Before
+SortUsingDeclarations: true
+SpaceAfterCStyleCast: false
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCaseColon: false
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceAroundPointerQualifiers: Default
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyBlock: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles:  Never
+SpacesInConditionalStatement: false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInLineCommentPrefix:
+  Minimum:         1
+  Maximum:         -1
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+SpaceBeforeSquareBrackets: false
+BitFieldColonSpacing: Both
+Standard:        Auto
+StatementAttributeLikeMacros:
+  - Q_EMIT
+StatementMacros:
+  - Q_UNUSED
+  - QT_REQUIRE_VERSION
+TabWidth:        8
+UseCRLF:         false
+UseTab:          Never
+WhitespaceSensitiveMacros:
+  - STRINGIZE
+  - PP_STRINGIZE
+  - BOOST_PP_STRINGIZE
+  - NS_SWIFT_NAME
+  - CF_SWIFT_NAME
+...
+

.clang-format-include

@@ -0,0 +1 @@
+bootstrap/**/*

.editorconfig

@@ -0,0 +1,10 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+charset = utf-8
+indent_style = space
+indent_size = 2
+max_line_length = 80

bootstrap/emit.cc

@@ -0,0 +1,38 @@
+#include <emit.hh>
+#include <iostream>
+
+namespace xlang {
+
+EmitListener::EmitListener(std::string_view outputfile) : output{outputfile} {}
+
+void EmitListener::enterFile(xlangParser::FileContext *ctx) {
+  output << "data $printformat = { b \"%ld\\n\", b 0 }" << std::endl;
+  (void)ctx;
+}
+
+void EmitListener::enterFunction(xlangParser::FunctionContext *ctx) {
+  output << std::endl
+         << "export function w $" << ctx->Identifier()->getSymbol()->getText()
+         << "()" << std::endl
+         << "{" << std::endl
+         << "@start" << std::endl;
+}
+
+void EmitListener::exitFunction(xlangParser::FunctionContext *ctx) {
+  output << "  ret 0" << std::endl << "}" << std::endl;
+  (void)ctx;
+}
+
+void EmitListener::exitStatement(xlangParser::StatementContext *ctx) {
+  if (ctx->Print()) {
+    output << "  call $printf(l $printformat, ..., w %v)" << std::endl;
+  }
+}
+
+void EmitListener::exitFactor(xlangParser::FactorContext *ctx) {
+  if (auto integer = ctx->Integer()) {
+    output << "  %v = w copy " << integer->getSymbol()->getText() << std::endl;
+  }
+}
+
+}  // namespace xlang

bootstrap/emit.hh

@@ -0,0 +1,22 @@
+#pragma once
+
+#include <fstream>
+#include <string_view>
+#include <xlangBaseListener.h>
+
+namespace xlang {
+
+class EmitListener : public xlangBaseListener {
+  std::ofstream output;
+
+ public:
+  EmitListener(std::string_view outputfile);
+
+  void enterFile(xlangParser::FileContext *ctx) override;
+  void enterFunction(xlangParser::FunctionContext *ctx) override;
+  void exitFunction(xlangParser::FunctionContext *ctx) override;
+  void exitStatement(xlangParser::StatementContext *ctx) override;
+  void exitFactor(xlangParser::FactorContext *ctx) override;
+};
+
+}  // namespace xlang

bootstrap/main.cc

@@ -0,0 +1,49 @@
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <emit.hh>
+#include <iostream>
+#include <string>
+#include <xlangLexer.h>
+#include <xlangParser.h>
+
+static void usage() {
+  std::cerr << getprogname() << " [-o output.ssa] input.x" << std::endl;
+  exit(1);
+}
+
+int main(int argc, char **argv) {
+  int opt;
+  std::string inputfile;
+  std::string outputfile;
+
+  while ((opt = getopt(argc, argv, "o:")) != -1) {
+    switch (opt) {
+      case 'o':
+        outputfile = optarg;
+        break;
+      default:
+        usage();
+    }
+  }
+  argc -= optind;
+  argv += optind;
+  if (argc != 1) {
+    usage();
+  }
+  inputfile = argv[0];
+  if (!outputfile.length()) {
+    outputfile = "/dev/stdout";
+  }
+
+  std::ifstream inputstream{inputfile};
+  antlr4::ANTLRInputStream input{inputstream};
+  xlang::xlangLexer lexer{&input};
+  antlr4::CommonTokenStream tokens{&lexer};
+  xlang::xlangParser parser{&tokens};
+  auto *tree = parser.file();
+
+  xlang::EmitListener emit{outputfile};
+  antlr4::tree::ParseTreeWalker::DEFAULT.walk(&emit, tree);
+  return 0;
+}

bootstrap/meson.build

@@ -0,0 +1,13 @@
+xc_exe = executable('xc',
+  sources : [
+      'main.cc',
+      'emit.cc',
+      antlr4.process('xlang.g4'),
+    ],
+  dependencies : [
+      antlr4_runtime_dep,
+    ],
+  install : true)
+xc = generator(xc_exe,
+  arguments : ['-o', '@OUTPUT@', '@INPUT@'],
+  output : '@BASENAME@.ssa')

bootstrap/xlang.g4

@@ -0,0 +1,52 @@
+grammar xlang;
+
+file  : function+ EOF;
+function  : Identifier LeftParen argumentList? RightParen block;
+argumentList  : Identifier (Comma Identifier)*;
+block : LeftBrace statement* RightBrace;
+statement : Identifier Assign expr Semicolon
+          | If expr block (Else block)?
+          | While expr block
+          | Return expr Semicolon
+          | Print expr Semicolon
+          | expr Semicolon
+          ;
+expr  : sum ((Less|LessEqual|Greater|GreaterEqual|Equal|NotEqual) sum)*;
+sum : term ((Plus|Minus) term)*;
+term  : factor ((Mul|Div) factor)*;
+factor  : Integer
+        | Identifier
+        | Identifier LeftParen exprList? RightParen
+        | LeftParen expr RightParen
+        ;
+exprList  : expr (Comma expr)*;
+
+If  : 'if';
+Else  : 'else';
+While : 'while';
+Return  : 'return';
+Print : 'print';
+
+LeftParen : '(';
+RightParen  : ')';
+LeftBrace : '{';
+RightBrace  : '}';
+Assign  : '=';
+Less  : '<';
+LessEqual : '<=';
+Greater : '>';
+GreaterEqual  : '>=';
+Equal : '==';
+NotEqual  : '!=';
+Plus  : '+';
+Minus : '-';
+Mul : '*';
+Div : '/';
+Comma : ',';
+Semicolon : ';';
+
+Identifier  : [a-zA-Z][a-zA-Z0-9]*;
+Integer : [0-9]+;
+
+Comment : '//' ~[\n]* '\n' -> skip;
+Whitespace  : [ \t\r\n]+ -> skip;

meson.build

@@ -0,0 +1,40 @@
+project('xlang', ['cpp', 'c'],
+  version : '0.1',
+  license : 'ISC',
+  default_options : ['buildtype=debugoptimized',
+                     'warning_level=3',
+                     'cpp_std=c++20'])
+
+antlr4_runtime_dep = dependency('antlr4-runtime', modules : ['antlr4_shared'])
+antlr4_exe = find_program('antlr4')
+antlr4 = generator(antlr4_exe,
+  arguments : [
+      '-o', '@BUILD_DIR@',
+      '-package', meson.project_name(),
+      '-visitor',
+      '-Dlanguage=Cpp',
+      '-Xexact-output-dir',
+      '@INPUT@',
+    ],
+  output : [
+      '@BASENAME@Lexer.h',
+      '@BASENAME@Lexer.cpp',
+      '@BASENAME@Parser.h',
+      '@BASENAME@Parser.cpp',
+      '@BASENAME@Visitor.h',
+      '@BASENAME@Visitor.cpp',
+      '@BASENAME@BaseVisitor.h',
+      '@BASENAME@BaseVisitor.cpp',
+      '@BASENAME@Listener.h',
+      '@BASENAME@Listener.cpp',
+      '@BASENAME@BaseListener.h',
+      '@BASENAME@BaseListener.cpp',
+    ])
+
+qbe_exe = find_program('qbe')
+qbe = generator(qbe_exe,
+  arguments : ['-o', '@OUTPUT@', '@INPUT@'],
+  output : '@BASENAME@.S')
+
+subdir('bootstrap')
+subdir('test')

test/42.x

@@ -0,0 +1,3 @@
+main() {
+  print 42;
+}

test/fib.x

@@ -0,0 +1,18 @@
+main() {
+  // print 5th fibonacci number
+  print fib(5);
+  return 0;
+}
+
+fib(n) {
+  x0 = 1;
+  x1 = 1;
+  i = 0;
+  while i < n {
+    t = x0 + x1;
+    x0 = x1;
+    x1 = t;
+    i = i + 1;
+  }
+  return x0;
+}

test/hello.ssa

@@ -0,0 +1,9 @@
+# Define the string constant.
+data $str = { b "hello world", b 0 }
+
+export function w $main() {
+@start
+  # Call the puts function with $str as argument.
+  %r = w call $puts(l $str)
+  ret 0
+}

test/meson.build

@@ -0,0 +1,21 @@
+executable('hello',
+  sources : qbe.process('hello.ssa'),
+  link_args : ['-static'])
+
+# XXX why is this needed?
+custom_target('42.ssa',
+  command : ['cp', '@INPUT@', '@OUTPUT@'],
+  input : xc.process('42.x'),
+  output : '@BASENAME@.ssa')
+executable('42',
+  sources : qbe.process(xc.process('42.x')),
+  link_args : ['-static'])
+
+# XXX why is this needed?
+custom_target('fib.ssa',
+  command : ['cp', '@INPUT@', '@OUTPUT@'],
+  input : xc.process('fib.x'),
+  output : '@BASENAME@.ssa')
+executable('fib',
+  sources : qbe.process(xc.process('fib.x')),
+  link_args : ['-static'])