Mercurial Repositories > eric / file comparison
comparison: ThirdParty/Pygments/pygments/formatters/rtf.py
ThirdParty/Pygments/pygments/formatters/rtf.py
- changeset 4172
- 4f20dba37ab6
- parent 3079
- 0233bbe9a9c4
- child 4697
- c2e9bf425554
equal
deleted
inserted
replaced
| 4170:8bc578136279 | 4172:4f20dba37ab6 |
|---|---|
| 3 pygments.formatters.rtf | 3 pygments.formatters.rtf |
| 4 ~~~~~~~~~~~~~~~~~~~~~~~ | 4 ~~~~~~~~~~~~~~~~~~~~~~~ |
| 5 | 5 |
| 6 A formatter that generates RTF files. | 6 A formatter that generates RTF files. |
| 7 | 7 |
| 8 :copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS. | 8 :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. |
| 9 :license: BSD, see LICENSE for details. | 9 :license: BSD, see LICENSE for details. |
| 10 """ | 10 """ |
| 11 | 11 |
| 12 from pygments.formatter import Formatter | 12 from pygments.formatter import Formatter |
| 13 from pygments.util import get_int_opt, _surrogatepair | |
| 13 | 14 |
| 14 | 15 |
| 15 __all__ = ['RtfFormatter'] | 16 __all__ = ['RtfFormatter'] |
| 16 | 17 |
| 17 | 18 |
| 18 class RtfFormatter(Formatter): | 19 class RtfFormatter(Formatter): |
| 19 """ | 20 """ |
| 20 Format tokens as RTF markup. This formatter automatically outputs full RTF | 21 Format tokens as RTF markup. This formatter automatically outputs full RTF |
| 21 documents with color information and other useful stuff. Perfect for Copy and | 22 documents with color information and other useful stuff. Perfect for Copy and |
| 22 Paste into Microsoft® Word® documents. | 23 Paste into Microsoft(R) Word(R) documents. |
| 23 | 24 |
| 24 *New in Pygments 0.6.* | 25 Please note that ``encoding`` and ``outencoding`` options are ignored. |
| 26 The RTF format is ASCII natively, but handles unicode characters correctly | |
| 27 thanks to escape sequences. | |
| 28 | |
| 29 .. versionadded:: 0.6 | |
| 25 | 30 |
| 26 Additional options accepted: | 31 Additional options accepted: |
| 27 | 32 |
| 28 `style` | 33 `style` |
| 29 The style to use, can be a string or a Style subclass (default: | 34 The style to use, can be a string or a Style subclass (default: |
| 30 ``'default'``). | 35 ``'default'``). |
| 31 | 36 |
| 32 `fontface` | 37 `fontface` |
| 33 The used font famliy, for example ``Bitstream Vera Sans``. Defaults to | 38 The used font famliy, for example ``Bitstream Vera Sans``. Defaults to |
| 34 some generic font which is supposed to have fixed width. | 39 some generic font which is supposed to have fixed width. |
| 40 | |
| 41 `fontsize` | |
| 42 Size of the font used. Size is specified in half points. The | |
| 43 default is 24 half-points, giving a size 12 font. | |
| 44 | |
| 45 .. versionadded:: 2.0 | |
| 35 """ | 46 """ |
| 36 name = 'RTF' | 47 name = 'RTF' |
| 37 aliases = ['rtf'] | 48 aliases = ['rtf'] |
| 38 filenames = ['*.rtf'] | 49 filenames = ['*.rtf'] |
| 39 | 50 |
| 40 unicodeoutput = False | |
| 41 | |
| 42 def __init__(self, **options): | 51 def __init__(self, **options): |
| 43 """ | 52 r""" |
| 44 Additional options accepted: | 53 Additional options accepted: |
| 45 | 54 |
| 46 ``fontface`` | 55 ``fontface`` |
| 47 Name of the font used. Could for example be ``'Courier New'`` | 56 Name of the font used. Could for example be ``'Courier New'`` |
| 48 to further specify the default which is ``'\fmodern'``. The RTF | 57 to further specify the default which is ``'\fmodern'``. The RTF |
| 49 specification claims that ``\fmodern`` are "Fixed-pitch serif | 58 specification claims that ``\fmodern`` are "Fixed-pitch serif |
| 50 and sans serif fonts". Hope every RTF implementation thinks | 59 and sans serif fonts". Hope every RTF implementation thinks |
| 51 the same about modern... | 60 the same about modern... |
| 61 | |
| 52 """ | 62 """ |
| 53 Formatter.__init__(self, **options) | 63 Formatter.__init__(self, **options) |
| 54 self.fontface = options.get('fontface') or '' | 64 self.fontface = options.get('fontface') or '' |
| 65 self.fontsize = get_int_opt(options, 'fontsize', 0) | |
| 55 | 66 |
| 56 def _escape(self, text): | 67 def _escape(self, text): |
| 57 return text.replace('\\', '\\\\') \ | 68 return text.replace(u'\\', u'\\\\') \ |
| 58 .replace('{', '\\{') \ | 69 .replace(u'{', u'\\{') \ |
| 59 .replace('}', '\\}') | 70 .replace(u'}', u'\\}') |
| 60 | 71 |
| 61 def _escape_text(self, text): | 72 def _escape_text(self, text): |
| 62 # empty strings, should give a small performance improvment | 73 # empty strings, should give a small performance improvment |
| 63 if not text: | 74 if not text: |
| 64 return '' | 75 return u'' |
| 65 | 76 |
| 66 # escape text | 77 # escape text |
| 67 text = self._escape(text) | 78 text = self._escape(text) |
| 68 if self.encoding in ('utf-8', 'utf-16', 'utf-32'): | |
| 69 encoding = 'iso-8859-15' | |
| 70 else: | |
| 71 encoding = self.encoding or 'iso-8859-15' | |
| 72 | 79 |
| 73 buf = [] | 80 buf = [] |
| 74 for c in text: | 81 for c in text: |
| 75 if ord(c) > 128: | 82 cn = ord(c) |
| 76 ansic = c.encode(encoding, 'ignore') or '?' | 83 if cn < (2**7): |
| 77 if ord(ansic) > 128: | 84 # ASCII character |
| 78 ansic = '\\\'%x' % ord(ansic) | |
| 79 else: | |
| 80 ansic = c | |
| 81 buf.append(r'\ud{\u%d%s}' % (ord(c), ansic)) | |
| 82 else: | |
| 83 buf.append(str(c)) | 85 buf.append(str(c)) |
| 86 elif (2**7) <= cn < (2**16): | |
| 87 # single unicode escape sequence | |
| 88 buf.append(u'{\\u%d}' % cn) | |
| 89 elif (2**16) <= cn: | |
| 90 # RTF limits unicode to 16 bits. | |
| 91 # Force surrogate pairs | |
| 92 buf.append(u'{\\u%d}{\\u%d}' % _surrogatepair(cn)) | |
| 84 | 93 |
| 85 return ''.join(buf).replace('\n', '\\par\n') | 94 return u''.join(buf).replace(u'\n', u'\\par\n') |
| 86 | 95 |
| 87 def format_unencoded(self, tokensource, outfile): | 96 def format_unencoded(self, tokensource, outfile): |
| 88 # rtf 1.8 header | 97 # rtf 1.8 header |
| 89 outfile.write(r'{\rtf1\ansi\deff0' | 98 outfile.write(u'{\\rtf1\\ansi\\uc0\\deff0' |
| 90 r'{\fonttbl{\f0\fmodern\fprq1\fcharset0%s;}}' | 99 u'{\\fonttbl{\\f0\\fmodern\\fprq1\\fcharset0%s;}}' |
| 91 r'{\colortbl;' % (self.fontface and | 100 u'{\\colortbl;' % (self.fontface and |
| 92 ' ' + self._escape(self.fontface) or | 101 u' ' + self._escape(self.fontface) or |
| 93 '')) | 102 u'')) |
| 94 | 103 |
| 95 # convert colors and save them in a mapping to access them later. | 104 # convert colors and save them in a mapping to access them later. |
| 96 color_mapping = {} | 105 color_mapping = {} |
| 97 offset = 1 | 106 offset = 1 |
| 98 for _, style in self.style: | 107 for _, style in self.style: |
| 99 for color in style['color'], style['bgcolor'], style['border']: | 108 for color in style['color'], style['bgcolor'], style['border']: |
| 100 if color and color not in color_mapping: | 109 if color and color not in color_mapping: |
| 101 color_mapping[color] = offset | 110 color_mapping[color] = offset |
| 102 outfile.write(r'\red%d\green%d\blue%d;' % ( | 111 outfile.write(u'\\red%d\\green%d\\blue%d;' % ( |
| 103 int(color[0:2], 16), | 112 int(color[0:2], 16), |
| 104 int(color[2:4], 16), | 113 int(color[2:4], 16), |
| 105 int(color[4:6], 16) | 114 int(color[4:6], 16) |
| 106 )) | 115 )) |
| 107 offset += 1 | 116 offset += 1 |
| 108 outfile.write(r'}\f0') | 117 outfile.write(u'}\\f0 ') |
| 118 if self.fontsize: | |
| 119 outfile.write(u'\\fs%d' % (self.fontsize)) | |
| 109 | 120 |
| 110 # highlight stream | 121 # highlight stream |
| 111 for ttype, value in tokensource: | 122 for ttype, value in tokensource: |
| 112 while not self.style.styles_token(ttype) and ttype.parent: | 123 while not self.style.styles_token(ttype) and ttype.parent: |
| 113 ttype = ttype.parent | 124 ttype = ttype.parent |
| 114 style = self.style.style_for_token(ttype) | 125 style = self.style.style_for_token(ttype) |
| 115 buf = [] | 126 buf = [] |
| 116 if style['bgcolor']: | 127 if style['bgcolor']: |
| 117 buf.append(r'\cb%d' % color_mapping[style['bgcolor']]) | 128 buf.append(u'\\cb%d' % color_mapping[style['bgcolor']]) |
| 118 if style['color']: | 129 if style['color']: |
| 119 buf.append(r'\cf%d' % color_mapping[style['color']]) | 130 buf.append(u'\\cf%d' % color_mapping[style['color']]) |
| 120 if style['bold']: | 131 if style['bold']: |
| 121 buf.append(r'\b') | 132 buf.append(u'\\b') |
| 122 if style['italic']: | 133 if style['italic']: |
| 123 buf.append(r'\i') | 134 buf.append(u'\\i') |
| 124 if style['underline']: | 135 if style['underline']: |
| 125 buf.append(r'\ul') | 136 buf.append(u'\\ul') |
| 126 if style['border']: | 137 if style['border']: |
| 127 buf.append(r'\chbrdr\chcfpat%d' % | 138 buf.append(u'\\chbrdr\\chcfpat%d' % |
| 128 color_mapping[style['border']]) | 139 color_mapping[style['border']]) |
| 129 start = ''.join(buf) | 140 start = u''.join(buf) |
| 130 if start: | 141 if start: |
| 131 outfile.write('{%s ' % start) | 142 outfile.write(u'{%s ' % start) |
| 132 outfile.write(self._escape_text(value)) | 143 outfile.write(self._escape_text(value)) |
| 133 if start: | 144 if start: |
| 134 outfile.write('}') | 145 outfile.write(u'}') |
| 135 | 146 |
| 136 outfile.write('}') | 147 outfile.write(u'}') |
