Python syntax highlighting

This commit is contained in:
Bobby Lucero 2024-09-28 23:31:19 -04:00
parent f084c715bf
commit f02815b1aa
7 changed files with 287 additions and 16 deletions

View File

@ -2,6 +2,7 @@ from scene import Scene
from particles import Particles from particles import Particles
from triangles import Triangles from triangles import Triangles
# Palette class (inherits from scene)
class Palette(Scene): class Palette(Scene):
def __init__(self): def __init__(self):

15
python/syntaxTest.py Normal file
View File

@ -0,0 +1,15 @@
#asdlkjasd
test #this is a test
print("test")
9 . 42 .12 9.1.1 80. 80.0123
"" asd
"
"Test"

View File

@ -31,6 +31,8 @@ public:
void StartGameLoop(); void StartGameLoop();
void bindMethods(); void bindMethods();
static std::string loadFileToString(const std::string& filename);
static pkpy::PyObject* getRandomNumber(pkpy::VM* vm, pkpy::ArgsView args); static pkpy::PyObject* getRandomNumber(pkpy::VM* vm, pkpy::ArgsView args);
static pkpy::PyObject* getSin(pkpy::VM* vm, pkpy::ArgsView args); static pkpy::PyObject* getSin(pkpy::VM* vm, pkpy::ArgsView args);
static pkpy::PyObject* getCos(pkpy::VM* vm, pkpy::ArgsView args); static pkpy::PyObject* getCos(pkpy::VM* vm, pkpy::ArgsView args);
@ -39,7 +41,5 @@ public:
static pkpy::PyObject* getKeyDown(pkpy::VM* vm, pkpy::ArgsView args); static pkpy::PyObject* getKeyDown(pkpy::VM* vm, pkpy::ArgsView args);
static pkpy::PyObject* getMousePressed(pkpy::VM* vm, pkpy::ArgsView args); static pkpy::PyObject* getMousePressed(pkpy::VM* vm, pkpy::ArgsView args);
static pkpy::PyObject* getMouseDown(pkpy::VM* vm, pkpy::ArgsView args); static pkpy::PyObject* getMouseDown(pkpy::VM* vm, pkpy::ArgsView args);
static std::string loadFileToString(const std::string& filename);
}; };

View File

@ -17,14 +17,24 @@ EditorState::EditorState(pkpy::VM *vm, Graphics *graphics) : m_vm(vm), m_graphic
std::string randomSource = Pycron::loadFileToString("../python/main.py"); std::string randomSource = Pycron::loadFileToString("../python/main.py");
m_baseBackgroundColor = 59; m_baseBackgroundColor = 56;
m_baseTextColor = 51; m_baseTextColor = 63;
m_lineNumberBackgroundColor = 58; m_lineNumberBackgroundColor = 57;
m_lineNumberTextColor = 61; m_lineNumberTextColor = 6;
m_unknownTextColor = 4;
m_identifierTextColor = 43;
m_keywordTextColor = 31;
m_builtinTextColor = 23;
m_numericalLiteralTextColor = 32;
m_stringLiteralTextColor = 6;
m_punctuationTextColor = 52;
m_operatorTextColor = 45;
m_commentTextColor = 60;
m_topLetterSpacing = 1;
m_topLetterSpacing = 0;
m_bottomLetterSpacing = 1; m_bottomLetterSpacing = 1;
m_leftLetterSpacing = 1; m_leftLetterSpacing = 0;
m_rightLetterSpacing = 1; m_rightLetterSpacing = 1;
m_charWidth = m_leftLetterSpacing + m_graphics->GetCurrentFontWidth() + m_rightLetterSpacing; // Final size of char with spacing. If the literal width of the font is n, the final width is n + spacing. m_charWidth = m_leftLetterSpacing + m_graphics->GetCurrentFontWidth() + m_rightLetterSpacing; // Final size of char with spacing. If the literal width of the font is n, the final width is n + spacing.
@ -37,13 +47,14 @@ EditorState::EditorState(pkpy::VM *vm, Graphics *graphics) : m_vm(vm), m_graphic
m_foregroundIndexBuffer = std::vector<uint8_t>(m_textWidth * m_textHeight); m_foregroundIndexBuffer = std::vector<uint8_t>(m_textWidth * m_textHeight);
m_backgroundIndexBuffer = std::vector<uint8_t>(m_textWidth * m_textHeight); m_backgroundIndexBuffer = std::vector<uint8_t>(m_textWidth * m_textHeight);
m_dirtyFlags = std::vector<bool>(m_textHeight);
Clear(); Clear();
std::string testText = "This is a test\n[Test]\nThis is the end of the test.";
LoadStringToBuffer(randomSource); LoadStringToBuffer(randomSource);
auto tokens = m_pythonTokenizer->tokenizeLine("for i in range(100):");
} }
EditorState::~EditorState() { EditorState::~EditorState() {
@ -52,13 +63,14 @@ EditorState::~EditorState() {
void EditorState::Draw() { void EditorState::Draw() {
m_graphics->Clear(0); m_graphics->Clear(0);
int bg = 28;
for (int i = 0; i < m_characterBuffer.size(); ++i) { for (int i = 0; i < m_characterBuffer.size(); ++i) {
int x = (i % m_textWidth) * m_charWidth; int x = (i % m_textWidth) * m_charWidth;
int y = (i / m_textWidth) * m_charHeight; int y = (i / m_textWidth) * m_charHeight;
m_graphics->Rect(x, y, m_charWidth, m_charHeight, m_backgroundIndexBuffer[i]); m_graphics->Rect(x, y, m_charWidth, m_charHeight, m_backgroundIndexBuffer[i]);
m_graphics->Char(m_characterBuffer[i], x + m_leftLetterSpacing + 1, y + m_topLetterSpacing + 1, 0); m_graphics->Char(m_characterBuffer[i], x + m_leftLetterSpacing + 1, y + m_topLetterSpacing + 1, bg);
m_graphics->Char(m_characterBuffer[i], x + m_leftLetterSpacing, y + m_topLetterSpacing, m_foregroundIndexBuffer[i]); m_graphics->Char(m_characterBuffer[i], x + m_leftLetterSpacing, y + m_topLetterSpacing, m_foregroundIndexBuffer[i]);
} }
@ -66,12 +78,42 @@ void EditorState::Draw() {
Clear(); Clear();
m_dirty = false; m_dirty = false;
for (int i = 0; i < m_text.size(); ++i) { for (int i = 0; i < m_text.size(); ++i) {
// Line numbers TODO: maybe not have this as part of the buffer, instead as a custom bar. (Allows for more custom functionality such as bookmarks)
std::string lineNumber = std::to_string(i); std::string lineNumber = std::to_string(i);
int size = 2; int size = 2;
int diff = size - (int)lineNumber.size(); int diff = size - (int)lineNumber.size();
if(diff > 0) lineNumber = std::string(diff, ' ') + lineNumber; if(diff > 0) lineNumber = std::string(diff, ' ') + lineNumber;
Text(lineNumber, 0, i, m_lineNumberTextColor, m_lineNumberBackgroundColor); Text(lineNumber, 0, i, m_lineNumberTextColor, m_lineNumberBackgroundColor);
Text(m_text[i], size, i, m_baseTextColor, m_baseBackgroundColor);
// Text handling
auto tokens = m_pythonTokenizer->tokenizeLine(m_text[i]);
int currentPos = 0;
for (int j = 0; j < tokens.size(); ++j) {
int color = m_baseTextColor;
TokenType type = tokens[j].type;
if(type == TokenType::Identifier){
color = m_identifierTextColor;
}else if(type == TokenType::Keyword){
color = m_keywordTextColor;
}else if(type == TokenType::Builtin){
color = m_builtinTextColor;
}else if(type == TokenType::NumericalLiteral){
color = m_numericalLiteralTextColor;
}else if(type == TokenType::StringLiteral){
color = m_stringLiteralTextColor;
}else if(type == TokenType::Punctuation){
color = m_punctuationTextColor;
}else if(type == TokenType::Operator){
color = m_operatorTextColor;
}else if(type == TokenType::Comment){
color = m_commentTextColor;
}else if(type == TokenType::Unknown){
color = m_baseTextColor;
}
Text(tokens[j].value, size + currentPos, i, color, m_baseBackgroundColor);
currentPos += tokens[j].value.size();
}
} }
} }

View File

@ -34,12 +34,23 @@ private:
// Text Data // Text Data
std::vector<std::string> m_text; std::vector<std::string> m_text;
std::vector<bool> m_dirtyFlags;
// Theming // Theming
uint8_t m_baseBackgroundColor; uint8_t m_baseBackgroundColor;
uint8_t m_baseTextColor; uint8_t m_baseTextColor;
uint8_t m_lineNumberBackgroundColor; uint8_t m_lineNumberBackgroundColor;
uint8_t m_lineNumberTextColor; uint8_t m_lineNumberTextColor;
uint8_t m_unknownTextColor;
uint8_t m_identifierTextColor;
uint8_t m_keywordTextColor;
uint8_t m_builtinTextColor;
uint8_t m_numericalLiteralTextColor;
uint8_t m_stringLiteralTextColor;
uint8_t m_punctuationTextColor;
uint8_t m_operatorTextColor;
uint8_t m_commentTextColor;
bool m_dirty; bool m_dirty;

View File

@ -2,4 +2,182 @@
// Created by Bobby on 9/28/2024. // Created by Bobby on 9/28/2024.
// //
#include <algorithm>
#include <iostream>
#include "PythonTokenizer.h" #include "PythonTokenizer.h"
PythonTokenizer::PythonTokenizer() {
m_keywords = {"False", "None", "True", "and", "as", "assert", "async", "await", "break", "class", "continue", "def",
"del", "elif", "else", "except", "finally", "for", "from", "global", "if", "import", "in", "is", "lambda",
"nonlocal", "not", "or", "pass", "raise", "return", "try", "while", "with", "yield", "self"};
m_builtins = {"abs", "all", "any", "ascii", "bin", "bool", "breakpoint", "bytearray", "bytes", "callable", "chr", "classmethod",
"compile", "complex", "delattr", "dict", "dir", "divmod", "enumerate", "eval", "exec", "filter", "float", "format",
"frozenset", "getattr", "globals", "hasattr", "hash", "help", "hex", "id", "input", "int", "isinstance", "issubclass",
"iter", "len", "list", "locals", "map", "max", "memoryview", "min", "next", "object", "oct", "open", "ord", "pow",
"print", "property", "range", "repr", "reversed", "round", "set", "setattr", "slice", "sorted", "staticmethod",
"str", "sum", "super", "tuple", "type", "vars", "zip", "__import__", "await", "__init__"};
}
std::vector<Token> PythonTokenizer::tokenizeLine(const std::string &line) {
m_currentPos = 0;
std::vector<Token> tokens;
while(m_currentPos < line.length()){
char currentChar = line[m_currentPos];
if(std::isspace(currentChar))
{
std::string whitespace = readWhitespace(line);
tokens.emplace_back(TokenType::WhiteSpace, whitespace);
}
else if(std::isalpha(currentChar) || currentChar == '_')
{
std::string identifier = readIdentifier(line);
TokenType type;
if(isKeyword(identifier)){
type = TokenType::Keyword;
}else if(isBuiltin(identifier)){
type = TokenType::Builtin;
}else{
type = TokenType::Identifier;
}
tokens.emplace_back(type, identifier);
}
else if(currentChar == '"')
{
std::string identifier = readStringLiteral(line);
tokens.emplace_back(TokenType::StringLiteral, identifier);
}
else if(std::isdigit(currentChar) || currentChar == '.')
{
std::string numericLiteral = readNumericLiteral(line);
if(numericLiteral.empty())
{ // tested the . for any valid numbers, it failed so punctuation it is.
std::string punct(1, currentChar);
tokens.emplace_back(TokenType::Punctuation, punct);
m_currentPos++;
}
tokens.emplace_back(TokenType::NumericalLiteral, numericLiteral);
}
else if(isPunctuation(currentChar))
{
std::string punct(1, currentChar);
tokens.emplace_back(TokenType::Punctuation, punct);
m_currentPos++;
}
else if(isOperator(currentChar))
{
std::string oper(1, currentChar);
tokens.emplace_back(TokenType::Operator, oper);
m_currentPos++;
}
else if(currentChar == '#')
{
std::string comment = readComment(line);
tokens.emplace_back(TokenType::Comment, comment);
}
else
{
tokens.emplace_back(TokenType::Unknown, std::string(1, currentChar));
m_currentPos++;
}
}
return tokens;
}
std::string PythonTokenizer::readWhitespace(const std::string& line) {
size_t start = m_currentPos;
while (m_currentPos < line.length() && std::isspace(line[m_currentPos])) {
m_currentPos++;
}
return line.substr(start, m_currentPos - start);
}
std::string PythonTokenizer::readIdentifier(const std::string &line) {
size_t start = m_currentPos;
while (m_currentPos < line.length() && (std::isalnum(line[m_currentPos]) || line[m_currentPos] == '_')) {
m_currentPos++;
}
return line.substr(start, m_currentPos - start);
}
bool PythonTokenizer::isKeyword(const std::string &identifier) {
return std::find(m_keywords.begin(), m_keywords.end(), identifier) != m_keywords.end();
}
bool PythonTokenizer::isBuiltin(const std::string &identifier) {
return std::find(m_builtins.begin(), m_builtins.end(), identifier) != m_builtins.end();;
}
bool PythonTokenizer::isPunctuation(char c) {
return c == '(' || c == ')' || c == '{' || c == '}' || c == '[' || c == ']' || c == ',' || c == '.';
}
bool PythonTokenizer::isOperator(char c) {
return c == '+' || c == '-' || c == '*' || c == '/' || c == '=';
}
std::string PythonTokenizer::readNumericLiteral(const std::string &line) {
size_t start = m_currentPos;
bool hasDigitsBeforeDecimal = false;
bool hasDigitsAfterDecimal = false;
// Read the integer part (if it exists)
while (m_currentPos < line.length() && std::isdigit(line[m_currentPos])) {
m_currentPos++;
hasDigitsBeforeDecimal = true;
}
// Check for a decimal point
if (m_currentPos < line.length() && line[m_currentPos] == '.') {
size_t decimalStart = m_currentPos;
m_currentPos++; // Move past the decimal point
// Ensure there's at least one digit after the decimal point
if (m_currentPos < line.length() && std::isdigit(line[m_currentPos])) {
hasDigitsAfterDecimal = true; // Mark as valid if we see digits after the decimal
// Continue reading the fractional part
while (m_currentPos < line.length() && std::isdigit(line[m_currentPos])) {
m_currentPos++;
}
} else {
// If there are no digits before or after the decimal, treat the decimal as punctuation
m_currentPos = decimalStart; // Revert to before the decimal point
}
}
// Only return a literal if we've encountered at least one digit
if (hasDigitsBeforeDecimal || hasDigitsAfterDecimal) {
return line.substr(start, m_currentPos - start);
} else {
// Handle error case where no valid number was found
return "";
}
}
std::string PythonTokenizer::readStringLiteral(const std::string &line) {
size_t start = m_currentPos;
m_currentPos++;
while (m_currentPos < line.length() && line[m_currentPos] != '"') {
m_currentPos++;
std::cout << m_currentPos;
}
if(line[m_currentPos] == '"') m_currentPos++;
return line.substr(start, m_currentPos - start);
}
std::string PythonTokenizer::readComment(const std::string &line) {
size_t start = m_currentPos;
while (m_currentPos < line.length()) {
m_currentPos++;
}
return line.substr(start, m_currentPos - start);
}

View File

@ -5,14 +5,18 @@
#pragma once #pragma once
#include <string> #include <string>
#include <vector>
enum TokenType{ enum TokenType{
Keyword, Keyword,
Builtin,
Identifier, Identifier,
Literal, NumericalLiteral,
StringLiteral,
Operator, Operator,
Punctuation, Punctuation,
EndOfFile, WhiteSpace,
Comment,
Unknown Unknown
}; };
@ -25,5 +29,25 @@ struct Token{
}; };
class PythonTokenizer { class PythonTokenizer {
public:
PythonTokenizer();
std::vector<Token> tokenizeLine(const std::string& line);
private:
size_t m_currentPos;
std::vector<std::string> m_keywords;
std::vector<std::string> m_builtins;
bool isKeyword(const std::string& identifier);
bool isBuiltin(const std::string& identifier);
bool isPunctuation(char c);
bool isOperator(char c);
std::string readWhitespace(const std::string& line);
std::string readIdentifier(const std::string& line);
std::string readNumericLiteral(const std::string& line);
std::string readStringLiteral(const std::string& line);
std::string readComment(const std::string& line);
}; };