Module: MaRuKu::In::Markdown::BlockLevelParser

Includes:
Helpers, SpanLevelParser, Strings, REXML
Included in:
MDDocument
Defined in:
lib/amp-front/third_party/maruku.rb,
lib/amp-front/third_party/maruku/input/parse_doc.rb,
lib/amp-front/third_party/maruku/input/linesource.rb,
lib/amp-front/third_party/maruku/input/parse_block.rb

Defined Under Namespace

Classes: BlockContext, LineSource

Constant Summary

Constants included from SpanLevelParser

SpanLevelParser::CharSource, SpanLevelParser::Close_class, SpanLevelParser::EscapedCharInInlineCode, SpanLevelParser::EscapedCharInQuotes, SpanLevelParser::EscapedCharInText, SpanLevelParser::Punct_class, SpanLevelParser::R_REF_ID, SpanLevelParser::Rules, SpanLevelParser::SPACE

Constants included from Strings

Strings::Abbreviation, Strings::AttributeDefinitionList, Strings::Definition, Strings::EMailAddress, Strings::FootnoteText, Strings::HeaderWithAttributes, Strings::HeaderWithId, Strings::IncompleteLink, Strings::InlineAttributeList, Strings::LinkRegex, Strings::MightBeTableHeader, Strings::Sep, Strings::TabSize, Strings::TableSeparator

Instance Method Summary collapse

Methods included from SpanLevelParser

#apply_one_rule, #describe_pos, #educate, #extension_meta, #interpret_extension, #is_ial, #md_al, #merge_ial, #parse_lines_as_span, #parse_span_better, #read_attribute_list, #read_em, #read_email_el, #read_emstrong, #read_footnote_ref, #read_image, #read_inline_code, #read_inline_html, #read_link, #read_quoted, #read_quoted_or_unquoted, #read_ref_id, #read_simple, #read_span, #read_strong, #read_url, #read_url_el, #read_xml_instr_span, #unit_tests_for_attribute_lists

Methods included from Helpers

#md_abbr, #md_abbr_def, #md_ald, #md_br, #md_code, #md_codeblock, #md_el, #md_em, #md_email, #md_emstrong, #md_entity, #md_foot_ref, #md_footnote, #md_header, #md_hrule, #md_html, #md_ial, #md_im_image, #md_im_link, #md_image, #md_li, #md_link, #md_par, #md_quote, #md_ref_def, #md_strong, #md_url, #md_xml_instr

Methods included from Strings

#add_tabs, #dbg_describe_ary, #force_linebreak?, #line_md_type, #normalize_key_and_value, #num_leading_hashes, #number_of_leading_spaces, #parse_email_headers, #sanitize_ref_id, #spaces_before_first_char, #split_lines, #strip_hashes, #strip_indent, #unquote

Instance Method Details

#eventually_comes_a_def_list(src) ⇒ Object

If current line is text, a definition list is coming if 1) text,empty,*,definition



556
557
558
559
560
561
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 556

def eventually_comes_a_def_list(src)
	future = src.tell_me_the_future
	ok = future =~ %r{^t+e?d}x
#		puts "future: #{future} - #{ok}"
	ok
end

#execute_code_blocks ⇒ Object 



161
162
163
164
165
166
167
168
169
170
 
# File 'lib/amp-front/third_party/maruku/input/parse_doc.rb', line 161

def execute_code_blocks
	self.each_element(:xml_instr) do |e|
		if e.target == 'maruku'
			result = safe_execute_code(e, e.code)
			if result.kind_of?(String)
				puts "Result is : #{result.inspect}"
			end
		end
	end
end

#expand_attribute_list(al, result) ⇒ Object

Expands an attribute list in an Hash



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_doc.rb', line 101

def expand_attribute_list(al, result)
	al.each do |k, v|
		case k
		when :class
			if not result[:class]
				result[:class] = v
			else
				result[:class] += " " + v
			end
		when :id; result[:id] = v
		when :ref; 
			if self.ald[v]
				already = (result[:expanded_references] ||= [])
				if not already.include?(v)
					already.push v
					expand_attribute_list(self.ald[v], result)
				else
					already.push  v
					maruku_error "Circular reference between labels.\n\n"+
					"Label #{v.inspect} calls itself via recursion.\nThe recursion is "+
						(already.map{|x| x.inspect}.join(' => ')) 
				end
			else
				if not result[:unresolved_references]
					result[:unresolved_references] = v
				else
					result[:unresolved_references] << " #{v}"
				end
				
			#	$stderr.puts "Unresolved reference #{v.inspect} (avail: #{self.ald.keys.inspect})"
				result[v.to_sym] = true
			end
		else
			result[k.to_sym]=v
		end
	end
end

#parse_blocks(src) ⇒ Object

Input is a LineSource



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 45

def parse_blocks(src)
	output = BlockContext.new
	
	# run state machine
	while src.cur_line
		
		next if check_block_extensions(src, output, src.cur_line)
		
#  Prints detected type (useful for debugging)
#			puts "#{src.cur_line.md_type}|#{src.cur_line}"
		case src.cur_line.md_type
			when :empty; 
				output.push :empty
				src.ignore_line
			when :ial
				m =  InlineAttributeList.match src.shift_line
				content = m[1] ||  "" 
#					puts "Content: #{content.inspect}"
				src2 = CharSource.new(content, src)
				interpret_extension(src2, output, [nil])
			when :ald
				output.push read_ald(src)
			when :text
				# paragraph, or table, or definition list
				read_text_material(src, output)
			when :header2, :hrule
				# hrule
				src.shift_line
				output.push md_hrule()
			when :header3
				output.push read_header3(src)
			when :ulist, :olist
				list_type = src.cur_line.md_type == :ulist ? :ul : :ol
				li = read_list_item(src)
				# append to current list if we have one
				if output.last.kind_of?(MDElement) && 
					output.last.node_type == list_type then
					output.last.children << li
				else
					output.push md_el(list_type, [li])
				end
			when :quote;    output.push read_quote(src)
			when :code;     e = read_code(src); output << e if e
			when :raw_html; e = read_raw_html(src); output << e if e

			when :footnote_text;   output.push read_footnote_text(src)
			when :ref_definition;  
				if src.parent && (src.cur_index == 0)
					read_text_material(src, output)
				else
					read_ref_definition(src, output)
				end
			when :abbreviation;    output.push read_abbreviation(src)
			when :xml_instr;       read_xml_instruction(src, output)
			when :metadata;        
				maruku_error "Please use the new meta-data syntax: \n"+
				"  http://maruku.rubyforge.org/proposal.html\n", src
				src.ignore_line
			else # warn if we forgot something
				md_type = src.cur_line.md_type
				line = src.cur_line
				maruku_error "Ignoring line '#{line}' type = #{md_type}", src
				src.shift_line
		end
	end

	merge_ial(output, src, output)
	output.delete_if {|x| x.kind_of?(MDElement) &&
		x.node_type == :ial}
	
	# get rid of empty line markers
	output.delete_if {|x| x == :empty}
	# See for each list if we can omit the paragraphs and use li_span
	# TODO: do this after
	output.each do |c| 
		# Remove paragraphs that we can get rid of
		if [:ul,:ol].include? c.node_type 
			if c.children.all? {|li| !li.want_my_paragraph} then
				c.children.each do |d|
					d.node_type = :li_span
					d.children = d.children[0].children 
				end
			end
		end 
		if c.node_type == :definition_list
			if c.children.all?{|defi| !defi.want_my_paragraph} then
				c.children.each do |definition| 
					definition.definitions.each do |dd|
						dd.children = dd.children[0].children 
					end
				end
			end
		end 
	end
	
	output
end

#parse_doc(s) ⇒ Object 



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_doc.rb', line 27

def parse_doc(s)
	# FIXME \r\n => \n
	meta2 =  parse_email_headers(s)
	data = meta2[:data]
	meta2.delete :data
	
	self.attributes.merge! meta2
	
=begin maruku_doc
Attribute: encoding
Scope:     document
Summary:   Encoding for the document.

If the `encoding` attribute is specified, then the content
will be converted from the specified encoding to UTF-8.

Conversion happens using the `iconv` library.
=end

	enc = self.attributes[:encoding]
	self.attributes.delete :encoding
	if enc && enc.downcase != 'utf-8'
		converted = Iconv.new('utf-8', enc).iconv(data)
		
#			puts "Data: #{data.inspect}: #{data}"
#			puts "Conv: #{converted.inspect}: #{converted}"
		
		data = converted
	end
	
	@children = parse_text_as_markdown(data)
	
	if true #markdown_extra? 
		self.search_abbreviations
		self.substitute_markdown_inside_raw_html
	end
	
	toc = create_toc

	# use title if not set
	if not self.attributes[:title] and toc.header_element
		title = toc.header_element.to_s
		self.attributes[:title]  = title
#			puts "Set document title to #{title}"
	end
	
	# save for later use
	self.toc = toc
	
	# Now do the attributes magic
	each_element do |e|
		# default attribute list
		if default = self.ald[e.node_type.to_s]
			expand_attribute_list(default, e.attributes)
		end
		expand_attribute_list(e.al, e.attributes)
#			puts "#{e.node_type}: #{e.attributes.inspect}"
	end

=begin maruku_doc
Attribute: unsafe_features
Scope:     global
Summary:   Enables execution of XML instructions.

Disabled by default because of security concerns.
=end

	if Maruku::Globals[:unsafe_features]
		self.execute_code_blocks
		# TODO: remove executed code blocks
	end
end

#parse_text_as_markdown(text) ⇒ Object

Splits the string and calls parse_lines_as_markdown



38
39
40
41
42
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 38

def parse_text_as_markdown(text)
	lines =  split_lines(text)
	src = LineSource.new(lines)
	return parse_blocks(src)
end

#read_abbreviation(src) ⇒ Object 



307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 307

def read_abbreviation(src)
	if not (l=src.shift_line) =~ Abbreviation
		maruku_error "Bug: it's Andrea's fault. Tell him.\n#{l.inspect}"
	end
	
	abbr = $1
	desc = $2
	
	if (not abbr) or (abbr.size==0)
		maruku_error "Bad abbrev. abbr=#{abbr.inspect} desc=#{desc.inspect}"
	end
	
	self.abbreviations[abbr] = desc
	
	return md_abbr_def(abbr, desc)
end

#read_ald(src) ⇒ Object 



163
164
165
166
167
168
169
170
171
172
173
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 163

def read_ald(src)
	if (l=src.shift_line) =~ AttributeDefinitionList
		id = $1;   al=$2;
		al = read_attribute_list(CharSource.new(al,src), context=nil, break_on=[nil])
		self.ald[id] = al;
		return md_ald(id, al)
	else
		maruku_error "Bug Bug:\n#{l.inspect}"
		return nil
	end
end

#read_code(src) ⇒ Object 



433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 433

def read_code(src)
	# collect all indented lines
	lines = []
	while src.cur_line && ([:code, :empty].include? src.cur_line.md_type)
		lines << strip_indent(src.shift_line, 4)
	end
	
	#while lines.last && (lines.last.md_type == :empty )
	while lines.last && lines.last.strip.size == 0
		lines.pop 
	end

	while lines.first && lines.first.strip.size == 0
		lines.shift 
	end
	
	return nil if lines.empty?

	source = lines.join("\n")
	
#		dbg_describe_ary(lines, 'CODE')

	return md_codeblock(source)
end

#read_definition(src) ⇒ Object 



564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 564

def read_definition(src)
	# Read one or more terms
	terms = []
	while  src.cur_line &&  src.cur_line.md_type == :text
		terms << md_el(:definition_term, parse_lines_as_span([src.shift_line]))
	end
#		dbg_describe_ary(terms, 'DT')

	want_my_paragraph = false

	raise "Chunky Bacon!" if not src.cur_line

	# one optional empty
	if src.cur_line.md_type == :empty
		want_my_paragraph = true
		src.shift_line
	end
	
	raise "Chunky Bacon!" if src.cur_line.md_type != :definition
	
	# Read one or more definitions
	definitions = []
	while src.cur_line && src.cur_line.md_type == :definition
		parent_offset = src.cur_index
			
		first = src.shift_line
		first =~ Definition
		first = $1
		
		# I know, it's ugly!!!

		lines, w_m_p = 
			read_indented_content(src,4, [:definition], :definition)
		want_my_paragraph ||= w_m_p
	
		lines.unshift first
		
#			dbg_describe_ary(lines, 'DD')
		src2 = LineSource.new(lines, src, parent_offset)
		children = parse_blocks(src2)
		definitions << md_el(:definition_data, children)
	end
	
	return md_el(:definition, terms+definitions, { 	
		:terms => terms, 
		:definitions => definitions, 
		:want_my_paragraph => want_my_paragraph})
end

#read_footnote_text(src) ⇒ Object 



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 324

def read_footnote_text(src)
	parent_offset = src.cur_index
		
	first = src.shift_line
	
	if not first =~ FootnoteText 
		maruku_error "Bug (it's Andrea's fault)"
	end
	
	id = $1
	text = $2

	# Ugly things going on inside `read_indented_content`
	indentation = 4 #first.size-text.size
	
#		puts "id =_#{id}_; text=_#{text}_ indent=#{indentation}"
	
	break_list = [:footnote_text, :ref_definition, :definition, :abbreviation]
	item_type = :footnote_text
	lines, want_my_paragraph = 
		read_indented_content(src,indentation, break_list, item_type)

	# add first line
	if text && text.strip != "" then lines.unshift text end
	
#		dbg_describe_ary(lines, 'FOOTNOTE')
	src2 = LineSource.new(lines, src, parent_offset)
	children = parse_blocks(src2)
	
	e = md_footnote(id, children)
	self.footnotes[id] = e
	return e
end

#read_header12(src) ⇒ Object

reads a header (with —– or ========)



176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 176

def read_header12(src)
	line = src.shift_line.strip
	al = nil
	# Check if there is an IAL
	if new_meta_data? and line =~ /^(.*)\{(.*)\}\s*$/
		line = $1.strip
		ial = $2
		al  = read_attribute_list(CharSource.new(ial,src), context=nil, break_on=[nil])
	end
	text = parse_lines_as_span [ line ]
	level = src.cur_line.md_type == :header2 ? 2 : 1;  
	src.shift_line
	return md_header(level, text, al)
end

#read_header3(src) ⇒ Object

reads a header like ‘#### header ####’



192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 192

def read_header3(src)
	line = src.shift_line.strip
	al = nil
	# Check if there is an IAL
	if new_meta_data? and line =~ /^(.*)\{(.*)\}\s*$/
		line = $1.strip
		ial = $2
		al  = read_attribute_list(CharSource.new(ial,src), context=nil, break_on=[nil])
	end
	level = num_leading_hashes(line)
	text = parse_lines_as_span [strip_hashes(line)] 
	return md_header(level, text, al)
end

#read_indented_content(src, indentation, break_list, item_type) ⇒ Object

This is the only ugly function in the code base. It is used to read list items, descriptions, footnote text



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
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 361

def read_indented_content(src, indentation, break_list, item_type)
	lines =[]
	# collect all indented lines
	saw_empty = false; saw_anything_after = false
	while src.cur_line 
#			puts "Reading indent = #{indentation} #{src.cur_line.inspect}"
		#puts "#{src.cur_line.md_type} #{src.cur_line.inspect}"
		if src.cur_line.md_type == :empty
			saw_empty = true
			lines << src.shift_line
			next
		end
	
		# after a white line
		if saw_empty
			# we expect things to be properly aligned
			if (ns=number_of_leading_spaces(src.cur_line)) < indentation
				#puts "breaking for spaces, only #{ns}: #{src.cur_line}"
				break
			end
			saw_anything_after = true
		else
#				if src.cur_line[0] != ?\ 
				break if break_list.include? src.cur_line.md_type
#				end
#				break if src.cur_line.md_type != :text
		end
	

		stripped = strip_indent(src.shift_line, indentation)
		lines << stripped

		#puts "Accepted as #{stripped.inspect}"
	
		# You are only required to indent the first line of 
		# a child paragraph.
		if stripped.md_type == :text
			while src.cur_line && (src.cur_line.md_type == :text)
				lines << strip_indent(src.shift_line, indentation)
			end
		end
	end

	want_my_paragraph = saw_anything_after || 
		(saw_empty && (src.cur_line  && (src.cur_line.md_type == item_type))) 

#		dbg_describe_ary(lines, 'LI')
	# create a new context 

	while lines.last && (lines.last.md_type == :empty)
		lines.pop
	end
	
	return lines, want_my_paragraph
end

#read_list_item(src) ⇒ Object

Reads one list item, either ordered or unordered.



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 281

def read_list_item(src)
	parent_offset = src.cur_index
	
	item_type = src.cur_line.md_type
	first = src.shift_line

	indentation = spaces_before_first_char(first)
	break_list = [:ulist, :olist, :ial]
	# Ugly things going on inside `read_indented_content`
	lines, want_my_paragraph = 
		read_indented_content(src,indentation, break_list, item_type)

	# add first line
		# Strip first '*', '-', '+' from first line
		stripped = first[indentation, first.size-1]
	lines.unshift stripped
	
	# dbg_describe_ary(lines, 'LIST ITEM ')

	src2 = LineSource.new(lines, src, parent_offset)
	children = parse_blocks(src2)
	with_par = want_my_paragraph || (children.size>1)
	
	return md_li(children, with_par)
end

#read_metadata(src) ⇒ Object

Reads a series of metadata lines with empty lines in between



459
460
461
462
463
464
465
466
467
468
469
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 459

def read_metadata(src)
	hash = {}
	while src.cur_line 
		case src.cur_line.md_type
			when :empty;  src.shift_line
			when :metadata; hash.merge! parse_metadata(src.shift_line)
			else break
		end
	end
	hash
end

#read_paragraph(src) ⇒ Object 



258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 258

def read_paragraph(src)
	lines = [src.shift_line]
	while src.cur_line 
		# :olist does not break
		case t = src.cur_line.md_type
			when :quote,:header3,:empty,:ref_definition,:ial #,:xml_instr,:raw_html
				break
			when :olist,:ulist
				break if src.next_line.md_type == t
		end
		break if src.cur_line.strip.size == 0			
		break if [:header1,:header2].include? src.next_line.md_type
		break if any_matching_block_extension?(src.cur_line) 
		
		lines << src.shift_line
	end
#		dbg_describe_ary(lines, 'PAR')
	children = parse_lines_as_span(lines, src)

	return md_par(children)
end

#read_quote(src) ⇒ Object 



418
419
420
421
422
423
424
425
426
427
428
429
430
431
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 418

def read_quote(src)
	parent_offset = src.cur_index
		
	lines = []
	# collect all indented lines
	while src.cur_line && src.cur_line.md_type == :quote
		lines << unquote(src.shift_line)
	end
#		dbg_describe_ary(lines, 'QUOTE')

	src2 = LineSource.new(lines, src, parent_offset)
	children = parse_blocks(src2)
	return md_quote(children)
end

#read_raw_html(src) ⇒ Object 



235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 235

def read_raw_html(src)
	h = HTMLHelper.new
	begin 
		h.eat_this(l=src.shift_line)
#			puts "\nBLOCK:\nhtml -> #{l.inspect}"
		while src.cur_line and not h.is_finished? 
			l=src.shift_line
#				puts "html -> #{l.inspect}"
			h.eat_this "\n"+l
		end
	rescue Exception => e
		ex = e.inspect + e.backtrace.join("\n")
		maruku_error "Bad block-level HTML:\n#{add_tabs(ex,1,'|')}\n", src
	end
	if not (h.rest =~ /^\s*$/)
		maruku_error "Could you please format this better?\n"+
			"I see that #{h.rest.inspect} is left after the raw HTML.", src
	end
	raw_html = h.stuff_you_read
	
	return md_html(raw_html)
end

#read_ref_definition(src, out) ⇒ Object 



472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 472

def read_ref_definition(src, out)	
	line = src.shift_line
	
	
	# if link is incomplete, shift next line
	if src.cur_line && !([:footnote_text, :ref_definition, :definition, :abbreviation].include? src.cur_line.md_type) && 
		([1,2,3].include? number_of_leading_spaces(src.cur_line) ) 
		line += " "+ src.shift_line
	end
	
#		puts "total= #{line}"
	
	match = LinkRegex.match(line)
	if not match
		maruku_error "Link does not respect format: '#{line}'"
		return
	end
	
	id = match[1]; url = match[2]; title = match[3]; 
	id = sanitize_ref_id(id)
	
	hash = self.refs[id] = {:url=>url,:title=>title}
	
	stuff=match[4]
	
	if stuff
		stuff.split.each do |couple|
#					puts "found #{couple}"
			k, v = couple.split('=')
			v ||= ""
			if v[0,1]=='"' then v = v[1, v.size-2] end
#					puts "key:_#{k}_ value=_#{v}_"
			hash[k.to_sym] = v
		end
	end
#			puts hash.inspect
	
	out.push md_ref_def(id, url, meta={:title=>title})
end

#read_table(src) ⇒ Object 



518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 518

def read_table(src)
	head = split_cells(src.shift_line).map{|s| md_el(:head_cell, parse_lines_as_span([s])) }
		
	separator=split_cells(src.shift_line)

	align = separator.map { |s|  s =~ Sep
		if $1 and $2 then :center elsif $2 then :right else :left end }
			
	num_columns = align.size
	
	if head.size != num_columns
		maruku_error "Table head does not have #{num_columns} columns: \n#{head.inspect}"
		tell_user "I will ignore this table."
		# XXX try to recover
		return md_br()
	end
			
	rows = []
	
	while src.cur_line && src.cur_line =~ /\|/
		row = split_cells(src.shift_line).map{|s|
			md_el(:cell, parse_lines_as_span([s]))}
		if head.size != num_columns
			maruku_error  "Row does not have #{num_columns} columns: \n#{row.inspect}"
			tell_user "I will ignore this table."
			# XXX try to recover
			return md_br()
		end
		rows << row
	end

	children = (head+rows).flatten
	return md_el(:table, children, {:align => align})
end

#read_text_material(src, output) ⇒ Object 



143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 143

def read_text_material(src, output)
	if src.cur_line =~ MightBeTableHeader and 
		(src.next_line && src.next_line =~ TableSeparator)
		output.push read_table(src)
	elsif [:header1,:header2].include? src.next_line.md_type
		output.push read_header12(src)
	elsif eventually_comes_a_def_list(src)
	 	definition = read_definition(src)
		if output.last.kind_of?(MDElement) && 
			output.last.node_type == :definition_list then
			output.last.children << definition
		else
			output.push md_el(:definition_list, [definition])
		end
	else # Start of a paragraph
		output.push read_paragraph(src)
	end
end

#read_xml_instruction(src, output) ⇒ Object 



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 206

def read_xml_instruction(src, output)
	m = /^\s*<\?((\w+)\s*)?(.*)$/.match src.shift_line
	raise "BugBug" if not m
	target = m[2] || ''
	code = m[3]
	until code =~ /\?>/
		code += "\n"+src.shift_line
	end
	if not code =~ (/\?>\s*$/)
		garbage = (/\?>(.*)$/.match(code))[1]
		maruku_error "Trailing garbage on last line: #{garbage.inspect}:\n"+
			add_tabs(code, 1, '|'), src
	end
	code.gsub!(/\?>\s*$/, '')
	
	if target == 'mrk' && MaRuKu::Globals[:unsafe_features]
		result = safe_execute_code(self, code)	
		if result
			if result.kind_of? String
				raise "Not expected"
			else
				output.push(*result)
			end
		end
	else
		output.push md_xml_instr(target, code)
	end
end

#safe_execute_code(object, code) ⇒ Object 



139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
 
# File 'lib/amp-front/third_party/maruku/input/parse_doc.rb', line 139

def safe_execute_code(object, code)
	begin
		return object.instance_eval(code)
	rescue Exception => e
		maruku_error "Exception while executing this:\n"+
			add_tabs(code, 1, ">")+
			"\nThe error was:\n"+
			add_tabs(e.inspect+"\n"+e.caller.join("\n"), 1, "|")
	rescue RuntimeError => e
		maruku_error "2: Exception while executing this:\n"+
			add_tabs(code, 1, ">")+
			"\nThe error was:\n"+
			add_tabs(e.inspect, 1, "|")
	rescue SyntaxError => e
		maruku_error "2: Exception while executing this:\n"+
			add_tabs(code, 1, ">")+
			"\nThe error was:\n"+
			add_tabs(e.inspect, 1, "|")
	end
	nil
end

#search_abbreviations ⇒ Object 



172
173
174
175
176
177
178
179
180
181
182
183
184
185
 
# File 'lib/amp-front/third_party/maruku/input/parse_doc.rb', line 172

def search_abbreviations
	self.abbreviations.each do |abbrev, title|
		reg = Regexp.new(Regexp.escape(abbrev))
		self.replace_each_string do |s|
			# bug if many abbreviations are present (agorf)
			if m = reg.match(s)
				e = md_abbr(abbrev.dup, title ? title.dup : nil)
				[m.pre_match, e, m.post_match]
			else
				s
			end
		end
	end
end

#split_cells(s) ⇒ Object 



512
513
514
515
516
 
# File 'lib/amp-front/third_party/maruku/input/parse_block.rb', line 512

def split_cells(s)
#		s.strip.split('|').select{|x|x.strip.size>0}.map{|x|x.strip}
# changed to allow empty cells
	s.strip.split('|').select{|x|x.size>0}.map{|x|x.strip}
end

#substitute_markdown_inside_raw_html ⇒ Object

(PHP Markdown extra) Search for elements that have markdown=1 or markdown=block defined



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
 
# File 'lib/amp-front/third_party/maruku/input/parse_doc.rb', line 190

def substitute_markdown_inside_raw_html
	self.each_element(:raw_html) do |e|
		doc = e.instance_variable_get :@parsed_html
		if doc # valid html
			# parse block-level markdown elements in these HTML tags
			block_tags = ['div']

			# use xpath to find elements with 'markdown' attribute
			XPath.match(doc, "//*[attribute::markdown]" ).each do |e|
#					puts "Found #{e}"
				# should we parse block-level or span-level?
				
				how = e.attributes['markdown']
				parse_blocks = (how == 'block') || block_tags.include?(e.name)
				               
				# Select all text elements of e
				XPath.match(e, "//text()" ).each { |original_text| 
					s = original_text.value.strip
					if s.size > 0

				#	    puts "Parsing #{s.inspect} as blocks: #{parse_blocks}  (#{e.name}, #{e.attributes['markdown']})  "

						el = md_el(:dummy,
						 	parse_blocks ? parse_text_as_markdown(s) :
						                  parse_lines_as_span([s]) )
						p = original_text.parent
						el.children_to_html.each do |x|
							p.insert_before(original_text, x)
						end
						p.delete(original_text)
						
					end
				}
				
				
         # remove 'markdown' attribute
         e.delete_attribute 'markdown'
         
			end
			
		end
	end
end