diff options
Diffstat (limited to 'pygments/formatters/latex.py')
| -rw-r--r-- | pygments/formatters/latex.py | 92 |
1 files changed, 88 insertions, 4 deletions
diff --git a/pygments/formatters/latex.py b/pygments/formatters/latex.py index 0f2397eb..fee177c5 100644 --- a/pygments/formatters/latex.py +++ b/pygments/formatters/latex.py @@ -12,6 +12,7 @@ from __future__ import division from pygments.formatter import Formatter +from pygments.lexer import Lexer from pygments.token import Token, STANDARD_TYPES from pygments.util import get_bool_opt, get_int_opt, StringIO, xrange, \ iteritems @@ -226,6 +227,15 @@ class LatexFormatter(Formatter): ``False``). .. versionadded:: 1.2 + + `escapeinside` + If set to a string of length 2, enables escaping to LaTeX. Text + delimited by these 2 characters is read as LaTeX code and + typeset accordingly. It has no effect in string literals. It has + no effect in comments if `texcomments` or `mathescape` is + set. (default: ``''``). + + .. versionadded:: 2.0 """ name = 'LaTeX' aliases = ['latex', 'tex'] @@ -243,6 +253,13 @@ class LatexFormatter(Formatter): self.commandprefix = options.get('commandprefix', 'PY') self.texcomments = get_bool_opt(options, 'texcomments', False) self.mathescape = get_bool_opt(options, 'mathescape', False) + self.escapeinside = options.get('escapeinside', '') + + if len(self.escapeinside) == 2: + self.left = self.escapeinside[0] + self.right = self.escapeinside[1] + else: + self.escapeinside = '' self._create_stylesheet() @@ -314,14 +331,14 @@ class LatexFormatter(Formatter): realoutfile = outfile outfile = StringIO() - outfile.write(r'\begin{Verbatim}[commandchars=\\\{\}') + outfile.write(u'\\begin{Verbatim}[commandchars=\\\\\\{\\}') if self.linenos: start, step = self.linenostart, self.linenostep outfile.write(u',numbers=left' + (start and u',firstnumber=%d' % start or u'') + (step and u',stepnumber=%d' % step or u'')) - if self.mathescape or self.texcomments: - outfile.write(r',codes={\catcode`\$=3\catcode`\^=7\catcode`\_=8}') + if self.mathescape or self.texcomments or self.escapeinside: + outfile.write(u',codes={\\catcode`\\$=3\\catcode`\\^=7\\catcode`\\_=8}') if self.verboptions: outfile.write(u',' + self.verboptions) outfile.write(u']\n') @@ -350,9 +367,22 @@ class LatexFormatter(Formatter): parts[i] = escape_tex(part, self.commandprefix) in_math = not in_math value = '$'.join(parts) + elif self.escapeinside: + text = value + value = '' + while len(text) > 0: + a,sep1,text = text.partition(self.left) + if len(sep1) > 0: + b,sep2,text = text.partition(self.right) + if len(sep2) > 0: + value = value + escape_tex(a, self.commandprefix) + b + else: + value = value + escape_tex(a + sep1 + b, self.commandprefix) + else: + value = value + escape_tex(a, self.commandprefix) else: value = escape_tex(value, self.commandprefix) - else: + elif not (ttype in Token.Escape): value = escape_tex(value, self.commandprefix) styles = [] while ttype is not Token: @@ -384,3 +414,57 @@ class LatexFormatter(Formatter): encoding = self.encoding or 'latin1', styledefs = self.get_style_defs(), code = outfile.getvalue())) + + +class LatexEmbeddedLexer(Lexer): + r""" + + This lexer takes one lexer as argument, the lexer for the language + being formatted, and the left and right delimiters for escaped text. + + First everything is scanned using the language lexer to obtain + strings and comments. All other consecutive tokens are merged and + the resulting text is scanned for escaped segments, which are given + the Token.Escape type. Finally text that is not escaped is scanned + again with the language lexer. + """ + def __init__(self, left, right, lang, **options): + self.left = left + self.right = right + self.lang = lang + Lexer.__init__(self, **options) + + def get_tokens_unprocessed(self, text): + buf = '' + for i, t, v in self.lang.get_tokens_unprocessed(text): + if t in Token.Comment or t in Token.String: + if buf: + for x in self.get_tokens_aux(idx, buf): + yield x + buf = '' + yield i, t, v + else: + if not buf: + idx = i; + buf += v + if buf: + for x in self.get_tokens_aux(idx, buf): + yield x + + def get_tokens_aux(self, index, text): + while text: + a, sep1, text = text.partition(self.left) + if a: + for i, t, v in self.lang.get_tokens_unprocessed(a): + yield index + i, t, v + index += len(a) + if sep1: + b, sep2, text = text.partition(self.right) + if sep2: + yield index + len(sep1), Token.Escape, b + index += len(sep1) + len(b) + len(sep2) + else: + yield index, Token.Error, sep1 + index += len(sep1) + text = b + |