因為需要用Qt來顯示程式碼，所以就基於Regular Expression方式，實作了一個簡易的Syntax Highlighting。並且允許客製化顏色主題。
範例程式碼
為了減少程式碼的重複，將必要的部分擷取出來寫成一個 AbsHighlighter，後面實作的 Syntax Highlighting Class 都會繼承這個類別。預設顏色寫在 THEMES["Default"]。
THEMES = {
"Default": {
"constant": format("coral"),
"keyword": format("blue"),
"builtin-func": format("darkCyan"),
"builtin-type": format("darkCyan"),
"operator": format("dimGray"),
"brace": format("darkGray"),
"function": format("black", "bold"),
"class": format("black", "bold"),
"string": format("orchid"),
"string2": format("darkMagenta"),
"method": format("fireBrick"),
"comment": format("darkGreen", "italic"),
"self": format("black", "italic"),
"numbers": format("darkOrange"),
},
# ...
}
class AbsHighlighter(QSyntaxHighlighter):
keywords = []
funcs = []
types = []
operators = []
braces = [r"\{", r"\}", r"\(", r"\)", r"\[", r"\]"]
builtin_values = []
def __init__(self, document, style):
QSyntaxHighlighter.__init__(self, document)
rules = []
# Keyword, operator, and brace rules
rules += [(50, r"\b%s\b" % w, 0, style["keyword"]) for w in self.keywords]
rules += [(50, r"\b%s\b" % w, 0, style["numbers"]) for w in self.builtin_values]
rules += [(50, r"\b%s\b" % o, 0, style["builtin-func"]) for o in self.funcs]
rules += [(50, r"\b%s\b" % o, 0, style["builtin-type"]) for o in self.types]
rules += [(50, r"%s" % o, 0, style["operator"]) for o in self.operators]
rules += [(50, r"%s" % b, 0, style["brace"]) for b in self.braces]
# Numeric literals
rules += [(50, r"\b[+-]?[0-9]+[lL]?\b", 0, style["numbers"])]
rules += [(50, r"\b[+-]?0[xX][0-9A-Fa-f]+[lL]?\b", 0, style["numbers"])]
rules += [
(50, r"\b[+-]?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?\b", 0, style["numbers"])
]
# Build a QRegExp for each pattern
# larger order will be applied later
self.rules = [(order, QRegExp(pat), index, fmt) for (order, pat, index, fmt) in rules]
self.style = style
self.post_init()
self.rules.sort(key=lambda x: x[0])
def post_init(self):
pass
def highlightBlock(self, text):
"""Apply syntax highlighting to the given block of text."""
# Do other syntax formatting
self.pre_highlight(text)
for _, expression, nth, format in self.rules:
index = expression.indexIn(text, 0)
while index >= 0:
# We actually want the index of the nth match
index = expression.pos(nth)
length = len(expression.cap(nth))
self.setFormat(index, length, format)
index = expression.indexIn(text, index + length)
self.post_highlight(text)
def pre_highlight(self, text):
pass
def post_highlight(self, text):
pass
Python Syntax Highlighter
來練習使用 AbsHighlighter 寫一個 Python Syntax Highlighter。
class PythonHighlighter(AbsHighlighter):
"""Syntax highlighter for the Python language."""
# fmt: off
keywords = [
"assert", "and", "break", "class", "continue", "def", "del", "elif",
"else", "except", "exec", "finally", "for", "from", "global", "if", "import",
"in", "is", "not", "or", "pass", "raise", "return", "try",
"lambda", "while", "yield",
]
funcs = [
"abs", "aiter", "all", "any", "anext", "ascii", "bin", "bool", "breakpoint",
"callable", "chr", "classmethod", "compile", "complex", "delattr",
"dir", "divmod", "enumerate", "eval", "exec", "filter", "float", "format",
"frozenset", "getattr", "globals", "hasattr", "hash", "help", "hex", "id",
"input", "isinstance", "issubclass", "iter", "len", "locals",
"max", "memoryview", "min", "next", "object", "oct", "open", "ord",
"pow", "print", "property", "range", "repr", "reversed", "round",
"setattr", "slice", "sorted", "staticmethod", "sum", "super", "type", "vars", "zip",
]
types = [
"bytes", "bytearray", "int", "str", "list",
"map", "dict", "set", "tuple",
]
operators = [
"=",
# Comparison
"==", "!=", "<", "<=", ">", ">=",
# Arithmetic
r"\+", "-", r"\*", "/", "//", r"\%", r"\*\*",
# Bitwise
r"\^", r"\|", r"\&", r"\~", ">>", "<<", # In-place
r"\+=", "-=", r"\*=", "/=", r"\%=", r"\^=", r"\|=", r"\&=", r"\~=", ">>=", "<<=",
]
builtin_values = [
"None", "True", "False",
]
# fmt: on
def post_init(self):
self.rules += [
# decorater
(50, QRegExp(r"^\s*(@).+$"), 1, self.style["keyword"]),
# 'self'
(50, QRegExp(r"\bself\b"), 0, self.style["self"]),
# dot operation method
(50, QRegExp(r"\.(\w+)\(.*\)"), 1, self.style["method"]),
# 'def' followed by an identifier
(50, QRegExp(r"\bdef\b\s*(\w+)"), 1, self.style["function"]),
# 'class' followed by an identifier
(50, QRegExp(r"\bclass\b\s*(\w+)"), 1, self.style["class"]),
(40, QRegExp(r"\b([A-Z]\w+)"), 1, self.style["class"]),
# 'constant'
(50, QRegExp(r"\b[A-Z][A-Z_]*\b"), 0, self.style["constant"]),
# From '#' until a newline, # at the end
(60, QRegExp(r"[^\'\"=\w\[\]\{\}]#[^\n]*"), 0, self.style["comment"]),
# Single-quoted string, possibly containing escape sequences
(50, QRegExp(r"'[^'\\]*(\\.[^'\\]*)*'"), 0, self.style["string"]),
# Double-quoted string, possibly containing escape sequences
(50, QRegExp(r'"[^"\\]*(\\.[^"\\]*)*"'), 0, self.style["string"]),
# From '#' until a newline, # at begining
(60, QRegExp(r"^#[^\n]*"), 0, self.style["comment"]),
]
# Multi-line strings (expression, flag, self.style)
# FIXME: The triple-quotes in these two lines will mess up the
# syntax highlighting from this point onward
self.tri_single = (QRegExp("'''"), 1, self.style["string2"])
self.tri_double = (QRegExp('"""'), 2, self.style["string2"])
def post_highlight(self, text):
self.setCurrentBlockState(0)
# Do multi-line strings
in_multiline = self.match_multiline(text, *self.tri_single)
if not in_multiline:
in_multiline = self.match_multiline(text, *self.tri_double)
def match_multiline(self, text, delimiter, in_state, style):
"""Do highlighting of multi-line strings. ``delimiter`` should be a
``QRegExp`` for triple-single-quotes or triple-double-quotes, and
``in_state`` should be a unique integer to represent the corresponding
state changes when inside those strings. Returns True if we're still
inside a multi-line string when this function is finished.
"""
# If inside triple-single quotes, start at 0
if self.previousBlockState() == in_state:
start = 0
add = 0
# Otherwise, look for the delimiter on this line
else:
start = delimiter.indexIn(text)
# Move past this match
add = delimiter.matchedLength()
# As long as there's a delimiter match on this line...
while start >= 0:
# Look for the ending delimiter
end = delimiter.indexIn(text, start + add)
# Ending delimiter on this line?
if end >= add:
length = end - start + add + delimiter.matchedLength()
self.setCurrentBlockState(0)
# No; multi-line string
else:
self.setCurrentBlockState(in_state)
length = len(text) - start + add
# Apply formatting
self.setFormat(start, length, style)
# Look for the next match
start = delimiter.indexIn(text, start + length)
# Return True if still inside a multi-line string, False otherwise
if self.currentBlockState() == in_state:
return True
else:
return False
使用方法
# get your plaintext editor
editor = QtGui.QPlainTextEdit()
# then apply our syntax highlighter
highlight = PythonHighlighter(editor.document())使用正規表達式，並不能正確地標示出所有程式語法，但對於簡易文字編輯器而言，已足夠。未來有機會可以再研究一下要怎麼搭配 Treesitter。