-
Notifications
You must be signed in to change notification settings - Fork 93
/
html_output_buffer.rb
398 lines (354 loc) · 12.6 KB
/
html_output_buffer.rb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
begin
require 'pygments'
rescue LoadError
# Pygments is not supported so we try instead with CodeRay
begin
require 'coderay'
rescue LoadError
# No code syntax highlighting
end
end
module Orgmode
class HtmlOutputBuffer < OutputBuffer
HtmlBlockTag = {
:paragraph => "p",
:ordered_list => "ol",
:unordered_list => "ul",
:list_item => "li",
:definition_list => "dl",
:definition_term => "dt",
:definition_descr => "dd",
:table => "table",
:table_row => "tr",
:quote => "blockquote",
:example => "pre",
:src => "pre",
:inline_example => "pre",
:center => "div",
:heading1 => "h1",
:heading2 => "h2",
:heading3 => "h3",
:heading4 => "h4",
:heading5 => "h5",
:heading6 => "h6"
}
attr_reader :options
def initialize(output, opts = {})
super(output)
if opts[:decorate_title] then
@title_decoration = " class=\"title\""
else
@title_decoration = ""
end
@buffer_tag = "HTML"
@options = opts
@new_paragraph = :start
@footnotes = {}
@unclosed_tags = []
@logger.debug "HTML export options: #{@options.inspect}"
end
# Output buffer is entering a new mode. Use this opportunity to
# write out one of the block tags in the HtmlBlockTag constant to
# put this information in the HTML stream.
def push_mode(mode, indent)
super(mode, indent)
if HtmlBlockTag[mode]
unless ((mode_is_table?(mode) and skip_tables?) or
(mode == :src and defined? Pygments))
css_class = case
when (mode == :src and @block_lang.empty?)
" class=\"src\""
when (mode == :src and not @block_lang.empty?)
" class=\"src\" lang=\"#{@block_lang}\""
when (mode == :example || mode == :inline_example)
" class=\"example\""
when mode == :center
" style=\"text-align: center\""
else
@title_decoration
end
add_paragraph unless @new_paragraph == :start
@new_paragraph = true
@logger.debug "#{mode}: <#{HtmlBlockTag[mode]}#{css_class}>"
@output << "<#{HtmlBlockTag[mode]}#{css_class}>"
# Entering a new mode obliterates the title decoration
@title_decoration = ""
end
end
end
# We are leaving a mode. Close any tags that were opened when
# entering this mode.
def pop_mode(mode = nil)
m = super(mode)
if HtmlBlockTag[m]
unless ((mode_is_table?(m) and skip_tables?) or
(m == :src and defined? Pygments))
add_paragraph if @new_paragraph
@new_paragraph = true
@logger.debug "</#{HtmlBlockTag[m]}>"
@output << "</#{HtmlBlockTag[m]}>"
end
end
@list_indent_stack.pop
end
def flush!
return false if @buffer.empty?
case
when preserve_whitespace?
strip_code_block! if mode_is_code? current_mode
# NOTE: CodeRay and Pygments already escape the html once, so
# no need to escapeHTML
case
when (current_mode == :src and defined? Pygments)
lang = normalize_lang @block_lang
@output << "\n" unless @new_paragraph == :start
@new_paragraph = true
begin
@buffer = Pygments.highlight(@buffer, :lexer => lang)
rescue
# Not supported lexer from Pygments, we fallback on using the text lexer
@buffer = Pygments.highlight(@buffer, :lexer => 'text')
end
when (current_mode == :src and defined? CodeRay)
lang = normalize_lang @block_lang
# CodeRay might throw a warning when unsupported lang is set,
# then fallback to using the text lexer
silence_warnings do
begin
@buffer = CodeRay.scan(@buffer, lang).html(:wrap => nil, :css => :style)
rescue ArgumentError
@buffer = CodeRay.scan(@buffer, 'text').html(:wrap => nil, :css => :style)
end
end
when (current_mode == :html or current_mode == :raw_text)
@buffer.gsub!(/\A\n/, "") if @new_paragraph == :start
@new_paragraph = true
else
# *NOTE* Don't use escape_buffer! through its sensitivity to @<text> forms
@buffer = escapeHTML @buffer
end
# Whitespace is significant in :code mode. Always output the
# buffer and do not do any additional translation.
@logger.debug "FLUSH CODE ==========> #{@buffer.inspect}"
@output << @buffer
when (mode_is_table? current_mode and skip_tables?)
@logger.debug "SKIP ==========> #{current_mode}"
else
@buffer.lstrip!
@new_paragraph = nil
@logger.debug "FLUSH ==========> #{current_mode}"
case current_mode
when :definition_term
d = @buffer.split(/\A(.*[ \t]+|)::(|[ \t]+.*?)$/, 4)
d[1] = d[1].strip
unless d[1].empty?
@output << inline_formatting(d[1])
else
@output << "???"
end
indent = @list_indent_stack.last
pop_mode
@new_paragraph = :start
push_mode(:definition_descr, indent)
@output << inline_formatting(d[2].strip + d[3])
@new_paragraph = nil
# FIXME: Need to restore tags once again (this should be done in escape_buffer!)
@output.gsub!(/@(<[^<>\n]*>)/, "\\1")
when :horizontal_rule
add_paragraph unless @new_paragraph == :start
@new_paragraph = true
@output << "<hr />"
else
@output << inline_formatting(@buffer)
end
end
@buffer = ""
end
def add_line_attributes headline
if @options[:export_heading_number] then
level = headline.level
heading_number = get_next_headline_number(level)
@output << "<span class=\"heading-number heading-number-#{level}\">#{heading_number}</span> "
end
if @options[:export_todo] and headline.keyword then
keyword = headline.keyword
@output << "<span class=\"todo-keyword #{keyword}\">#{keyword}</span> "
end
end
def output_footnotes!
return false unless @options[:export_footnotes] and not @footnotes.empty?
@output << "\n<div id=\"footnotes\">\n<h2 class=\"footnotes\">Footnotes:</h2>\n<div id=\"text-footnotes\">\n"
@footnotes.each do |name, defi|
@buffer = defi
@output << "<p class=\"footnote\"><sup><a class=\"footnum\" name=\"fn.#{name}\" href=\"#fnr.#{name}\">#{name}</a></sup>" \
<< inline_formatting(@buffer) \
<< "</p>\n"
end
@output << "</div>\n</div>"
return true
end
# Test if we're in an output mode in which whitespace is significant.
def preserve_whitespace?
super or current_mode == :html
end
######################################################################
private
def skip_tables?
@options[:skip_tables]
end
def mode_is_table?(mode)
(mode == :table or mode == :table_row or
mode == :table_separator or mode == :table_header)
end
# Escapes any HTML content in the output accumulation buffer @buffer.
def escape_buffer!
@buffer.gsub!(/&/, "&")
# Escapes the left and right angular brackets but construction
# @<text> which is formatted to <text>
@buffer.gsub! /<([^<>\n]*)/ do |match|
if $`[-1..-1] == "@" and $'[0..0] == ">" then $&
else "<#{$1}"
end
end
@buffer.gsub! /([^<>\n]*)>/ do |match|
if $`[-2..-1] == "@<" then $&
else "#{$1}>"
end
end
@buffer.gsub!(/@(<[^<>\n]*>)/, "\\1")
end
def buffer_indentation
indent = " " * @list_indent_stack.length
@buffer << indent
end
def add_paragraph
indent = " " * (@list_indent_stack.length - 1)
@output << "\n" << indent
end
Tags = {
"*" => { :open => "b", :close => "b" },
"/" => { :open => "i", :close => "i" },
"_" => { :open => "span style=\"text-decoration:underline;\"",
:close => "span" },
"=" => { :open => "code", :close => "code" },
"~" => { :open => "code", :close => "code" },
"+" => { :open => "del", :close => "del" }
}
# Applies inline formatting rules to a string.
def inline_formatting(str)
@re_help.rewrite_emphasis str do |marker, s|
if marker == "=" or marker == "~"
s = escapeHTML s
"<#{Tags[marker][:open]}>#{s}</#{Tags[marker][:close]}>"
else
"@<#{Tags[marker][:open]}>#{s}@</#{Tags[marker][:close]}>"
end
end
if @options[:use_sub_superscripts] then
@re_help.rewrite_subp str do |type, text|
if type == "_" then
"@<sub>#{text}@</sub>"
elsif type == "^" then
"@<sup>#{text}@</sup>"
end
end
end
@re_help.rewrite_links str do |link, defi|
[link, defi].compact.each do |text|
# We don't support search links right now. Get rid of it.
text.sub!(/\A(file:[^\s]+)::[^\s]*?\Z/, "\\1")
text.sub!(/\A(file:[^\s]+)\.org\Z/i, "\\1.html")
text.sub!(/\Afile:(?=[^\s]+\Z)/, "")
end
# We don't add a description for images in links, because its
# empty value forces the image to be inlined.
defi ||= link unless link =~ @re_help.org_image_file_regexp
if defi =~ @re_help.org_image_file_regexp
defi = "@<img src=\"#{defi}\" alt=\"#{defi}\" />"
end
if defi
link = @options[:link_abbrevs][link] if @options[:link_abbrevs].has_key? link
"@<a href=\"#{link}\">#{defi}@</a>"
else
"@<img src=\"#{link}\" alt=\"#{link}\" />"
end
end
if @output_type == :table_row
str.gsub!(/^\|\s*/, "@<td>")
str.gsub!(/\s*\|$/, "@</td>")
str.gsub!(/\s*\|\s*/, "@</td>@<td>")
end
if @output_type == :table_header
str.gsub!(/^\|\s*/, "@<th>")
str.gsub!(/\s*\|$/, "@</th>")
str.gsub!(/\s*\|\s*/, "@</th>@<th>")
end
if @options[:export_footnotes] then
@re_help.rewrite_footnote str do |name, defi|
# TODO escape name for url?
@footnotes[name] = defi if defi
"@<sup>@<a class=\"footref\" name=\"fnr.#{name}\" href=\"#fn.#{name}\">#{name}@</a>@</sup>"
end
end
# Two backslashes \\ at the end of the line make a line break without breaking paragraph.
if @output_type != :table_row and @output_type != :table_header then
str.sub!(/\\\\$/, "@<br />")
end
escape_buffer!
Orgmode.special_symbols_to_html str
str = @re_help.restore_code_snippets str
end
def normalize_lang(lang)
case lang
when 'emacs-lisp', 'common-lisp', 'lisp'
'scheme'
when ''
'text'
else
lang
end
end
# Helper method taken from Rails
# https://github.com/rails/rails/blob/c2c8ef57d6f00d1c22743dc43746f95704d67a95/activesupport/lib/active_support/core_ext/kernel/reporting.rb#L10
def silence_warnings
warn_level = $VERBOSE
$VERBOSE = nil
yield
ensure
$VERBOSE = warn_level
end
def strip_code_block!
@code_block_indent ||= 0
strip_regexp = Regexp.new("^" + " " * @code_block_indent)
@buffer.gsub!(strip_regexp, "")
@code_block_indent = nil
# Strip proctective commas generated by Org mode (C-c ')
@buffer.gsub! /^\s*(,)(\s*)([*]|#\+)/ do |match|
"#{$2}#{$3}"
end
end
# The CGI::escapeHTML function backported from the Ruby standard library
# as of commit fd2fc885b43283aa3d76820b2dfa9de19a77012f
#
# Implementation of the cgi module can change among Ruby versions
# so stabilizing on a single one here to avoid surprises.
#
# https://github.com/ruby/ruby/blob/trunk/lib/cgi/util.rb
#
# The set of special characters and their escaped values
TABLE_FOR_ESCAPE_HTML__ = {
"'" => ''',
'&' => '&',
'"' => '"',
'<' => '<',
'>' => '>',
}
# Escape special characters in HTML, namely &\"<>
# escapeHTML('Usage: foo "bar" <baz>')
# # => "Usage: foo "bar" <baz>"
private
def escapeHTML(string)
string.gsub(/['&\"<>]/, TABLE_FOR_ESCAPE_HTML__)
end
end # class HtmlOutputBuffer
end # module Orgmode