Python syntax highlighting

转载自 https://wiki.python.org/moin/PyQt/Python%20syntax%20highlighting
如有侵权，请联系删除。

---

Python syntax highlighting

• If you need a code editor with syntax highlighting, but don’t want something as heavyweight as QsciScintilla, you can use the QSyntaxHighlighter class to apply highlighting to a QPlainTextEdit widget.

• This example was based on existing work by Carson Farmer and Christophe Kibleur, and an example on the SciPres wiki. One aspect not addressed by this prior work is handling of Python’s triple-quoted strings, which may span multiple lines; the QSyntaxHighlighter documentation includes an example for C++ comments, but those have different beginning and ending delimiters /* … */, whereas Python’s triple-quoted strings have the same delimiter at the beginning and end. These are handled by the match_multiline method–there may be an easier way to do this, but it seems to work pretty well, although it still has trouble with triple-quotes embedded inside another string (as you’ll see if you run the example editor.py below).

• I have placed this code under the Modified BSD License because I believe the author intended it to be freely used. However, I don’t believe that I originally wrote this example, though I was responsible for migrating it to the Python Wiki. – DavidBoddie 2017-01-19 20:34:17

# syntax.py

import sys

from PyQt4.QtCore import QRegExp
from PyQt4.QtGui import QColor, QTextCharFormat, QFont, QSyntaxHighlighter

def format(color, style=''):
    """Return a QTextCharFormat with the given attributes.
    """
    _color = QColor()
    _color.setNamedColor(color)

    _format = QTextCharFormat()
    _format.setForeground(_color)
    if 'bold' in style:
        _format.setFontWeight(QFont.Bold)
    if 'italic' in style:
        _format.setFontItalic(True)

    return _format


# Syntax styles that can be shared by all languages
STYLES = {
    'keyword': format('blue'),
    'operator': format('red'),
    'brace': format('darkGray'),
    'defclass': format('black', 'bold'),
    'string': format('magenta'),
    'string2': format('darkMagenta'),
    'comment': format('darkGreen', 'italic'),
    'self': format('black', 'italic'),
    'numbers': format('brown'),
}


class PythonHighlighter (QSyntaxHighlighter):
    """Syntax highlighter for the Python language.
    """
    # Python keywords
    keywords = [
        'and', 'assert', 'break', 'class', 'continue', 'def',
        'del', 'elif', 'else', 'except', 'exec', 'finally',
        'for', 'from', 'global', 'if', 'import', 'in',
        'is', 'lambda', 'not', 'or', 'pass', 'print',
        'raise', 'return', 'try', 'while', 'yield',
        'None', 'True', 'False',
    ]

    # Python operators
    operators = [
        '=',
        # Comparison
        '==', '!=', '<', '<=', '>', '>=',
        # Arithmetic
        '\+', '-', '\*', '/', '//', '\%', '\*\*',
        # In-place
        '\+=', '-=', '\*=', '/=', '\%=',
        # Bitwise
        '\^', '\|', '\&', '\~', '>>', '<<',
    ]

    # Python braces
    braces = [
        '\{', '\}', '\(', '\)', '\[', '\]',
    ]
    def __init__(self, document):
        QSyntaxHighlighter.__init__(self, document)

        # Multi-line strings (expression, flag, style)
        # FIXME: The triple-quotes in these two lines will mess up the
        # syntax highlighting from this point onward
        self.tri_single = (QRegExp("'''"), 1, STYLES['string2'])
        self.tri_double = (QRegExp('"""'), 2, STYLES['string2'])

        rules = []

        # Keyword, operator, and brace rules
        rules += [(r'\b%s\b' % w, 0, STYLES['keyword'])
            for w in PythonHighlighter.keywords]
        rules += [(r'%s' % o, 0, STYLES['operator'])
            for o in PythonHighlighter.operators]
        rules += [(r'%s' % b, 0, STYLES['brace'])
            for b in PythonHighlighter.braces]

        # All other rules
        rules += [
            # 'self'
            (r'\bself\b', 0, STYLES['self']),

            # Double-quoted string, possibly containing escape sequences
            (r'"[^"\\]*(\\.[^"\\]*)*"', 0, STYLES['string']),
            # Single-quoted string, possibly containing escape sequences
            (r"'[^'\\]*(\\.[^'\\]*)*'", 0, STYLES['string']),

            # 'def' followed by an identifier
            (r'\bdef\b\s*(\w+)', 1, STYLES['defclass']),
            # 'class' followed by an identifier
            (r'\bclass\b\s*(\w+)', 1, STYLES['defclass']),

            # From '#' until a newline
            (r'#[^\n]*', 0, STYLES['comment']),

            # Numeric literals
            (r'\b[+-]?[0-9]+[lL]?\b', 0, STYLES['numbers']),
            (r'\b[+-]?0[xX][0-9A-Fa-f]+[lL]?\b', 0, STYLES['numbers']),
            (r'\b[+-]?[0-9]+(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?\b', 0, STYLES['numbers']),
        ]

        # Build a QRegExp for each pattern
        self.rules = [(QRegExp(pat), index, fmt)
            for (pat, index, fmt) in rules]


    def highlightBlock(self, text):
        """Apply syntax highlighting to the given block of text.
        """
        # Do other syntax formatting
        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 = expression.cap(nth).length()
                self.setFormat(index, length, format)
                index = expression.indexIn(text, index + length)

        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 = text.length() - 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

• Here’s a simple editor application that demonstrates it (not including save/load features). Really all you need to do is instantiate the syntax.PythonHighlighter class, passing the QPlainTextEdit widget’s document to the constructor:

# editor.py

from PyQt4 import QtGui
import syntax

app = QtGui.QApplication([])
editor = QtGui.QPlainTextEdit()
highlight = syntax.PythonHighlighter(editor.document())
editor.show()

# Load syntax.py into the editor for demo purposes
infile = open('syntax.py', 'r')
editor.setPlainText(infile.read())

app.exec_()