使用Python为文本编辑器添加语法高亮功能

Question

我正在创建自己的基于Web的文本编辑器，并希望添加语法高亮功能。首先，我只会为一种语言（可能是Python）进行高亮，但以后我想为想到的每种语言都添加高亮。

如果可能的话，我想找到一个关于此的教程。有人知道在哪里可以找到吗？

另外，如果你有其他提示，那就太好了。

- Brewer

---

够了时间重新发明轮子吗？ :-) - user2665694

有些车轮需要重新发明。我很难想象开着石头车轮的汽车。 - Brewer

Answer 1

请看Pygments。

---

highlight.js

- ba__friend

---

那可能只是你的运气；幸运的是，现在计算机速度非常快，你可以尝试为每个按键进行解析。 - SingleNegationElimination

@Joose：你在使用哪个GUI工具包？我不明白为什么要再次从头开始实现语法高亮。 - s.m.

@sm 我没有使用GUI工具包，文本编辑器是基于Web的。 - Brewer

你为什么不从一开始就说呢？我已经在我的回答中添加了一些内容。 - ba__friend

我编辑了问题以鼓励更多的答案，即使 highlight.js 似乎是这种任务的首选工具。 - s.m.

Answer 2

from PyQt4 import QtGui
import syntax

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

infile = open('syntax.py', 'r')
texter.setPlainText(infile.read())

app.exec_()

#use the program syntax.py to make it work I posted it

- 00JACOB 00STEINER

Answer 3

 # 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

- 00JACOB 00STEINER