opmac2html 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +14 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +23 -0
- data/Rakefile +1 -0
- data/bin/opmac2html +5 -0
- data/lib/opmac2html/cli.rb +28 -0
- data/lib/opmac2html/converter.rb +58 -0
- data/lib/opmac2html/html_builder.rb +102 -0
- data/lib/opmac2html/list_builder.rb +54 -0
- data/lib/opmac2html/macro_parser.rb +176 -0
- data/lib/opmac2html/par_builder.rb +47 -0
- data/lib/opmac2html/paragraph_parser.rb +158 -0
- data/lib/opmac2html/preprocessor.rb +26 -0
- data/lib/opmac2html/table_builder.rb +38 -0
- data/lib/opmac2html/text_cutter.rb +54 -0
- data/lib/opmac2html/version.rb +4 -0
- data/lib/opmac2html.rb +15 -0
- data/opmac2html.gemspec +27 -0
- metadata +108 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b9625bef7744ab49e28dbc304b224a87f913baef
|
4
|
+
data.tar.gz: 16f7373d2b2cdcfffb60fa7f6f445a22df8ca7a0
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b25cba818ed4691231c8f8886d208673801f820e18f0b23ab50318a560ab3b26035f8a3145c5cbb92cb17f638aa042df1c3eb2878051943efef6aa3eef8827d4
|
7
|
+
data.tar.gz: 884e077bd888e403d3480971512ff7dd566f9dd121bf5fcb78e1cb8129e37d303cdcae99fb7061a9311a5f3062c84f3f515e3fde91508c4646a94814b20755e2
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 Martin Kinčl
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# opmac2html
|
2
|
+
|
3
|
+
opmac2html is a document markup converter from OPmac plainTeX macro set markup to HTML5
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'opmac2html'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install opmac2html
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
$ opmac2html -i input.tex -o output.html
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'bundler/gem_tasks'
|
data/bin/opmac2html
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
require 'slop'
|
2
|
+
require 'opmac2html'
|
3
|
+
require 'opmac2html/converter'
|
4
|
+
|
5
|
+
module Opmac2html
|
6
|
+
# Command line option parser and runner
|
7
|
+
class CLI
|
8
|
+
def initialize
|
9
|
+
opts = Slop.parse(help: true) do |o|
|
10
|
+
o.banner = 'Usage: opmac2html -i <input.tex> -o <output.html>'
|
11
|
+
o.string '-i', '--input', 'Input OPmac file'
|
12
|
+
o.string '-o', '--output', 'Output HTML file'
|
13
|
+
o.on '-h', '--help', 'Shows this message'
|
14
|
+
o.on '-v', '--version', 'Shows application version'
|
15
|
+
end
|
16
|
+
run opts
|
17
|
+
end
|
18
|
+
|
19
|
+
def run(opts)
|
20
|
+
puts "opmac2html, version: #{Opmac2html.version}" if opts[:version]
|
21
|
+
if opts[:input] && opts[:output]
|
22
|
+
Converter.new(opts[:input], opts[:output]).convert
|
23
|
+
else
|
24
|
+
puts opts
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
@@ -0,0 +1,58 @@
|
|
1
|
+
require 'opmac2html/html_builder'
|
2
|
+
require 'opmac2html/list_builder'
|
3
|
+
require 'opmac2html/par_builder'
|
4
|
+
require 'opmac2html/table_builder'
|
5
|
+
require 'opmac2html/preprocessor'
|
6
|
+
require 'opmac2html/text_cutter'
|
7
|
+
require 'opmac2html/paragraph_parser'
|
8
|
+
require 'opmac2html/macro_parser'
|
9
|
+
|
10
|
+
module Opmac2html
|
11
|
+
# Converter from OPmac to html markup
|
12
|
+
class Converter
|
13
|
+
include TextCutter
|
14
|
+
include ParagraphParser
|
15
|
+
include MacroParser
|
16
|
+
|
17
|
+
def initialize(input_file, output_file)
|
18
|
+
@input = read_input input_file
|
19
|
+
@preproc = Preprocessor.new
|
20
|
+
@input = @preproc.run @input
|
21
|
+
@builder = HtmlBuilder.new
|
22
|
+
@output_file = output_file
|
23
|
+
@ttchar = '"'
|
24
|
+
end
|
25
|
+
|
26
|
+
def read_input(filename)
|
27
|
+
File.open(filename, 'r') { |input| input.readlines.join }
|
28
|
+
end
|
29
|
+
|
30
|
+
def write_output(output)
|
31
|
+
File.open(@output_file, 'w') { |file| file << output }
|
32
|
+
end
|
33
|
+
|
34
|
+
def convert
|
35
|
+
until @input.empty?
|
36
|
+
if @input.start_with? '%', "\n"
|
37
|
+
cut_at "\n"
|
38
|
+
else
|
39
|
+
parse
|
40
|
+
end
|
41
|
+
@input.lstrip!
|
42
|
+
end
|
43
|
+
write_output @builder.to_s
|
44
|
+
end
|
45
|
+
|
46
|
+
def parse
|
47
|
+
if @input.start_with? '\\'
|
48
|
+
parse_macro
|
49
|
+
else
|
50
|
+
parse_par
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def err(text)
|
55
|
+
puts "Unsupported control sequence: #{text}"
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
@@ -0,0 +1,102 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Builder for the resulting document
|
3
|
+
class HtmlBuilder
|
4
|
+
attr_reader :anchors
|
5
|
+
|
6
|
+
MATH_JAX = '<meta charset="UTF-8">
|
7
|
+
<script type="text/x-mathjax-config">
|
8
|
+
MathJax.Hub.Config({tex2jax: {inlineMath: [[\'$\',\'$\']]}});
|
9
|
+
</script>
|
10
|
+
<script type="text/javascript"
|
11
|
+
src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?' \
|
12
|
+
'config=TeX-AMS-MML_HTMLorMML">
|
13
|
+
</script>'
|
14
|
+
|
15
|
+
TAIL = "</body>\n</html>\n"
|
16
|
+
|
17
|
+
def initialize
|
18
|
+
@document = []
|
19
|
+
@fnotes = ListBuilder.new 'n'
|
20
|
+
@fnote_count = 0
|
21
|
+
@anchors = []
|
22
|
+
end
|
23
|
+
|
24
|
+
def head(title)
|
25
|
+
"<!DOCTYPE html>\n<head>\n<title>#{title}</title>\n" \
|
26
|
+
"#{MATH_JAX}\n</head>\n<body>\n"
|
27
|
+
end
|
28
|
+
|
29
|
+
def elem(name, text)
|
30
|
+
"<#{name}>#{text}</#{name.partition(' ')[0]}>\n\n"
|
31
|
+
end
|
32
|
+
|
33
|
+
def header(number, title)
|
34
|
+
elem "h#{number}", title
|
35
|
+
end
|
36
|
+
|
37
|
+
def add_title(title)
|
38
|
+
@title ||= title[1]
|
39
|
+
@document << [title[0], title[1]]
|
40
|
+
end
|
41
|
+
|
42
|
+
def add_par(text)
|
43
|
+
@document << ['p', text]
|
44
|
+
end
|
45
|
+
|
46
|
+
def add_verbatim(text)
|
47
|
+
@document << ['pre', text]
|
48
|
+
end
|
49
|
+
|
50
|
+
def add_table(text)
|
51
|
+
@document << ['table', text]
|
52
|
+
end
|
53
|
+
|
54
|
+
def add_list(text)
|
55
|
+
@document << [nil, text]
|
56
|
+
end
|
57
|
+
|
58
|
+
def add_fnote(text)
|
59
|
+
@fnote_count += 1
|
60
|
+
@fnotes.add_item(text, @fnote_count.to_s)
|
61
|
+
@fnote_count
|
62
|
+
end
|
63
|
+
|
64
|
+
def add_img(filename)
|
65
|
+
elem = "<img src=\"#{filename}\" " \
|
66
|
+
"alt=\"#{filename[0...filename.rindex('.')]}\">\n"
|
67
|
+
@document << [nil, elem]
|
68
|
+
end
|
69
|
+
|
70
|
+
def add_figure(filename, caption)
|
71
|
+
img = "<img src=\"#{filename}\" " \
|
72
|
+
"alt=\"#{caption}\">"
|
73
|
+
cap = "<figcaption>#{caption}</figcaption>"
|
74
|
+
@document << ['figure', img + "\n" + cap]
|
75
|
+
end
|
76
|
+
|
77
|
+
def add_anchor(id)
|
78
|
+
@anchors << id
|
79
|
+
@document << ["span id=\"#{id}\"", '']
|
80
|
+
end
|
81
|
+
|
82
|
+
def header?(element)
|
83
|
+
element[0].is_a? Numeric
|
84
|
+
end
|
85
|
+
|
86
|
+
def doc_to_s
|
87
|
+
@document.map do |e|
|
88
|
+
if header?(e)
|
89
|
+
header(*e)
|
90
|
+
elsif !e[0]
|
91
|
+
e[1]
|
92
|
+
else
|
93
|
+
elem(*e)
|
94
|
+
end
|
95
|
+
end.join + "<hr>\n" + @fnotes.to_s
|
96
|
+
end
|
97
|
+
|
98
|
+
def to_s
|
99
|
+
head(@title) + doc_to_s + TAIL
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Builder for lists (items)
|
3
|
+
class ListBuilder
|
4
|
+
def initialize(style)
|
5
|
+
@list = []
|
6
|
+
@list_stack = []
|
7
|
+
begitems style
|
8
|
+
end
|
9
|
+
|
10
|
+
def get_type(style)
|
11
|
+
case style
|
12
|
+
when 'n', 'N'
|
13
|
+
'ol type="1"'
|
14
|
+
when 'i', 'I', 'a', 'A'
|
15
|
+
"ol type=\"#{style}\""
|
16
|
+
else
|
17
|
+
'ul'
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def start_tag(text)
|
22
|
+
@list << "<#{text}>\n"
|
23
|
+
@list_stack << text.partition(' ')[0]
|
24
|
+
end
|
25
|
+
|
26
|
+
def end_tag
|
27
|
+
@list << "</#{@list_stack.pop}>\n"
|
28
|
+
end
|
29
|
+
|
30
|
+
def begitems(style)
|
31
|
+
start_tag get_type style
|
32
|
+
@first = true
|
33
|
+
end
|
34
|
+
|
35
|
+
def enditems
|
36
|
+
2.times { end_tag }
|
37
|
+
end
|
38
|
+
|
39
|
+
def add_item(text, id = nil)
|
40
|
+
if @first
|
41
|
+
@first = false
|
42
|
+
else
|
43
|
+
end_tag
|
44
|
+
end
|
45
|
+
start_tag(id ? "li id=\"#{id}\"" : 'li')
|
46
|
+
@list << text
|
47
|
+
end
|
48
|
+
|
49
|
+
def to_s
|
50
|
+
enditems until @list_stack.empty?
|
51
|
+
@list.join
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,176 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Mixin providing parsing of macro calls
|
3
|
+
module MacroParser
|
4
|
+
TITLES = %w(\\tit \\chap \\sec \\secc)
|
5
|
+
IN_PAR_MACROS = %w(\\TeX \\LaTeX \\csplain)
|
6
|
+
|
7
|
+
def parse_macro
|
8
|
+
title_index = TITLES.index { |t| @input.start_with? t }
|
9
|
+
if title_index
|
10
|
+
parse_title title_index
|
11
|
+
elsif @input.start_with? '\\begtt'
|
12
|
+
parse_verbatim
|
13
|
+
elsif @input.start_with? '\\verbinput'
|
14
|
+
verbinput
|
15
|
+
elsif @input.start_with? '\\begitems'
|
16
|
+
parse_list
|
17
|
+
elsif @input.start_with? '\\activettchar'
|
18
|
+
parse_ttchar
|
19
|
+
elsif IN_PAR_MACROS.any? { |m| @input.start_with? m }
|
20
|
+
parse_par
|
21
|
+
else
|
22
|
+
parse_other
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
def parse_title(index)
|
27
|
+
@min_index ||= index
|
28
|
+
title_text = @preproc.process_text(cut_at("\n\n").partition(' ')[2])
|
29
|
+
@builder.add_title([title_level(index), title_text])
|
30
|
+
end
|
31
|
+
|
32
|
+
def title_level(index)
|
33
|
+
index + 1 - @min_index
|
34
|
+
end
|
35
|
+
|
36
|
+
def parse_verbatim
|
37
|
+
cut_at "\n"
|
38
|
+
@builder.add_verbatim cut_at '\\endtt'
|
39
|
+
end
|
40
|
+
|
41
|
+
def verbinput
|
42
|
+
beg_line, end_line = *verbinput_range
|
43
|
+
file = File.open(cut_at("\n").strip, 'r') { |input| input.readlines }
|
44
|
+
@builder.add_verbatim(file[beg_line - 1..end_line - 1].join)
|
45
|
+
end
|
46
|
+
|
47
|
+
def verbinput_range
|
48
|
+
cut_at '('
|
49
|
+
beg_line = cut_at('-').to_i
|
50
|
+
end_line = cut_at(')').to_i
|
51
|
+
end_line = -1 if end_line == 0
|
52
|
+
[beg_line, end_line]
|
53
|
+
end
|
54
|
+
|
55
|
+
def parse_list
|
56
|
+
list = parse_list_items
|
57
|
+
builder = ListBuilder.new(list[0].partition('\style ')[2][0])
|
58
|
+
list[1..-1].each do |line|
|
59
|
+
process_list_item line, builder
|
60
|
+
end
|
61
|
+
@builder.add_list builder.to_s
|
62
|
+
end
|
63
|
+
|
64
|
+
def parse_list_items
|
65
|
+
list, @input = *(cut_at_matching(@input, '\\begitems', '\\enditems'))
|
66
|
+
list.split("\n").reduce([]) do |a, e|
|
67
|
+
if /\*|\\begitems|\\enditems/.match(e) || a.empty?
|
68
|
+
a << e
|
69
|
+
else
|
70
|
+
a[-1].concat "\n" + e
|
71
|
+
a
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
def process_list_item(line, builder)
|
77
|
+
if line.include? '\\begitems'
|
78
|
+
builder.begitems line.partition('\style ')[2][0]
|
79
|
+
elsif line.include? '\\enditems'
|
80
|
+
builder.enditems
|
81
|
+
else
|
82
|
+
builder.add_item parse_par_macros(line.partition(/\*\s/)[2])
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
def parse_ttchar
|
87
|
+
cut_at 'r'
|
88
|
+
@preproc.ttchar = @ttchar = @input[0]
|
89
|
+
@input = @input[1..-1]
|
90
|
+
end
|
91
|
+
|
92
|
+
def parse_other
|
93
|
+
part_line = @input.partition("\n")
|
94
|
+
if %w(\\table \\caption/t).any? { |s| part_line[0].include? s }
|
95
|
+
parse_table
|
96
|
+
elsif part_line[0].include?('\\inspic')
|
97
|
+
parse_image
|
98
|
+
elsif part_line[0].include?('\\def')
|
99
|
+
part = cut_at_match_with_start(@input, '{', '}')
|
100
|
+
err part[0] + part[1]
|
101
|
+
@input = part[2]
|
102
|
+
elsif part_line[0].start_with?('\\noindent')
|
103
|
+
err cut_at(/\s/)
|
104
|
+
elsif part_line[0].start_with? '\\label'
|
105
|
+
parse_label
|
106
|
+
elsif part_line[0].start_with? '\\centerline'
|
107
|
+
text = cut_at_matching(part_line[0], '{', '}')[0]
|
108
|
+
@builder.add_par parse_par_macros text
|
109
|
+
@input = part_line[2]
|
110
|
+
else
|
111
|
+
err part_line[0]
|
112
|
+
@input = part_line[2]
|
113
|
+
end
|
114
|
+
end
|
115
|
+
|
116
|
+
def parse_table
|
117
|
+
tb = TableBuilder.new
|
118
|
+
parse_table_caption(@input.partition("\n")[0], tb)
|
119
|
+
|
120
|
+
build_table tb
|
121
|
+
|
122
|
+
parse_table_caption(cut_at("\n\n"), tb)
|
123
|
+
|
124
|
+
@builder.add_table tb.to_s
|
125
|
+
end
|
126
|
+
|
127
|
+
def parse_table_caption(line, tb)
|
128
|
+
return unless line.include? '\\caption/t'
|
129
|
+
caption = line.partition('\\caption/t ')[2].partition("\n")[0]
|
130
|
+
tb.add_caption(parse_par_macros(caption))
|
131
|
+
end
|
132
|
+
|
133
|
+
def parse_table_cells
|
134
|
+
text = @input.partition(/\\table\s*\{[^\{]*/)[2]
|
135
|
+
part = cut_at_matching(text, '{', '}')
|
136
|
+
@input = part[1]
|
137
|
+
|
138
|
+
part[0].split(/\\cr.*/).map { |r| r.split(/\s&\s/).map(&:strip) }
|
139
|
+
.reject(&:empty?)
|
140
|
+
end
|
141
|
+
|
142
|
+
def build_table(tb)
|
143
|
+
parse_table_cells.each do |row|
|
144
|
+
tb.add_row(row.map do |cell|
|
145
|
+
if cell.start_with? '\\multispan'
|
146
|
+
cellpart = cell.partition(/\d+/)
|
147
|
+
cellpart[0] + cellpart[1] + parse_par_macros(cellpart[2])
|
148
|
+
else
|
149
|
+
parse_par_macros cell
|
150
|
+
end
|
151
|
+
end)
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
def parse_image
|
156
|
+
img = cut_at_matching(@input, '\\inspic ', "\n")[0]
|
157
|
+
.partition(/ [\n\}]/)[0]
|
158
|
+
part = cut_at("\n\n")
|
159
|
+
if part.include? '\\label'
|
160
|
+
@builder.add_anchor(cut_at_matching(part, '\\label[', ']')[0])
|
161
|
+
end
|
162
|
+
if part.include? '\\caption/f'
|
163
|
+
@builder.add_figure img, cut_at_matching(
|
164
|
+
part, '\\caption/f ', "\n\n")[0]
|
165
|
+
else
|
166
|
+
@builder.add_img img
|
167
|
+
end
|
168
|
+
end
|
169
|
+
|
170
|
+
def parse_label
|
171
|
+
part = cut_at_matching @input, '[', ']'
|
172
|
+
@builder.add_anchor part[0]
|
173
|
+
@input = part[1]
|
174
|
+
end
|
175
|
+
end
|
176
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Paragraph builder
|
3
|
+
class ParBuilder
|
4
|
+
ELEM = -> (name, text) { "<#{name}>#{text}</#{name}>" }
|
5
|
+
ELEM_WITH_ATT = lambda do |name, attname, attval, text|
|
6
|
+
"<#{name} #{attname}=\"#{attval}\">#{text}</#{name}>"
|
7
|
+
end
|
8
|
+
LINK_SUBS = { '\\%' => '%', '\\#' => '#' }
|
9
|
+
|
10
|
+
def initialize
|
11
|
+
@par = []
|
12
|
+
end
|
13
|
+
|
14
|
+
def add_word(word)
|
15
|
+
@par << word
|
16
|
+
end
|
17
|
+
|
18
|
+
def add_code(code)
|
19
|
+
@par << ELEM.call('code', code)
|
20
|
+
end
|
21
|
+
|
22
|
+
def add_quote(quote)
|
23
|
+
@par << "„#{quote}“"
|
24
|
+
end
|
25
|
+
|
26
|
+
def add_em(text)
|
27
|
+
@par << ELEM.call('em', text)
|
28
|
+
end
|
29
|
+
|
30
|
+
def add_strong(text)
|
31
|
+
@par << ELEM.call('strong', text)
|
32
|
+
end
|
33
|
+
|
34
|
+
def add_link(address, text = nil)
|
35
|
+
address.gsub!(/\\[%#]/) { |c| LINK_SUBS[c] }
|
36
|
+
@par << ELEM_WITH_ATT.call('a', 'href', address, text ? text : address)
|
37
|
+
end
|
38
|
+
|
39
|
+
def add_verbatim(text)
|
40
|
+
@par << ELEM.call('pre', text)
|
41
|
+
end
|
42
|
+
|
43
|
+
def to_s
|
44
|
+
@par.join
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
@@ -0,0 +1,158 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Mixin providing parsing of paragraphs and other text elements
|
3
|
+
module ParagraphParser
|
4
|
+
def parse_par
|
5
|
+
slice = cut_at_with_sep(/\n\n|\n\\begtt|\n\\.*skip|\\par[\\ ]/)
|
6
|
+
@builder.add_par(parse_par_macros(slice.gsub(/^%.*/, '')))
|
7
|
+
end
|
8
|
+
|
9
|
+
def parse_par_macros(text)
|
10
|
+
par_builder = ParBuilder.new
|
11
|
+
until text.empty?
|
12
|
+
index = text.index(/#{@ttchar}|\\\w|\{|\$/) || text.length
|
13
|
+
par_builder.add_word @preproc.process_text text[0...index]
|
14
|
+
text = par_special text[index..-1], par_builder
|
15
|
+
end
|
16
|
+
par_builder.to_s
|
17
|
+
end
|
18
|
+
|
19
|
+
def par_special(text, par_builder)
|
20
|
+
case text[0]
|
21
|
+
when @ttchar
|
22
|
+
parse_code text, par_builder
|
23
|
+
when '$'
|
24
|
+
parse_math text, par_builder
|
25
|
+
else
|
26
|
+
par_macro text, par_builder
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def dump_all(text)
|
31
|
+
err text unless text.empty?
|
32
|
+
''
|
33
|
+
end
|
34
|
+
|
35
|
+
def dump_to_space(text)
|
36
|
+
part = text.partition(/\s/)
|
37
|
+
err part[0]
|
38
|
+
part[2]
|
39
|
+
end
|
40
|
+
|
41
|
+
def parse_code(text, par_builder)
|
42
|
+
part = text[1..-1].partition(@ttchar)
|
43
|
+
par_builder.add_code part[0]
|
44
|
+
part[2]
|
45
|
+
end
|
46
|
+
|
47
|
+
def parse_math(text, par_builder)
|
48
|
+
separator = text.start_with?('$$') ? '$$' : '$'
|
49
|
+
part = text[separator.length..-1].partition(separator)
|
50
|
+
par_builder.add_word separator + part[0] + part[1]
|
51
|
+
part[2]
|
52
|
+
end
|
53
|
+
|
54
|
+
def par_macro(text, par_builder)
|
55
|
+
if %w(\\url \\ulink \\fnote \\ref \\pgref).any? { |p| text.start_with? p }
|
56
|
+
parse_clickable text, par_builder
|
57
|
+
elsif text.start_with? '\\begtt'
|
58
|
+
par_verbatim text, par_builder
|
59
|
+
elsif text.start_with? '\\dots'
|
60
|
+
par_builder.add_word '…'
|
61
|
+
text.partition('s')[2]
|
62
|
+
elsif text.index(/(\\\w+)?\{/) == 0
|
63
|
+
part = cut_at_match_with_start(text, '{', '}')
|
64
|
+
if %w(\\TeX \\LaTeX \\csplain).any? { |p| text.start_with? p }
|
65
|
+
par_builder.add_word(@preproc.process_text(part[0] + part[1]))
|
66
|
+
else
|
67
|
+
parse_format_block part[0], par_builder
|
68
|
+
end
|
69
|
+
part[2]
|
70
|
+
elsif %w(\\it \\em \\bf \\tt).any? { |p| text.start_with? p }
|
71
|
+
parse_format_block text, par_builder
|
72
|
+
''
|
73
|
+
elsif text.index(/\\\w*\s/) == 0
|
74
|
+
dump_to_space text
|
75
|
+
else
|
76
|
+
dump_all text
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
def parse_clickable(text, par_builder)
|
81
|
+
if %w(\\url \\ulink).any? { |p| text.start_with? p }
|
82
|
+
parse_link text, par_builder
|
83
|
+
elsif text.start_with? '\\fnote'
|
84
|
+
parse_fnote text, par_builder
|
85
|
+
elsif %w(\\ref \\pgref).any? { |p| text.start_with? p }
|
86
|
+
part = cut_at_matching(text, '[', ']')
|
87
|
+
par_builder.add_link("##{part[0]}", part[0])
|
88
|
+
part[1]
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
def par_verbatim(text, par_builder)
|
93
|
+
part = cut_at_matching(text, '\\begtt', '\\endtt')
|
94
|
+
par_builder.add_verbatim(part[0])
|
95
|
+
part[1]
|
96
|
+
end
|
97
|
+
|
98
|
+
def parse_link(text, par_builder)
|
99
|
+
part = text.partition('}')
|
100
|
+
if text.start_with? '\\url'
|
101
|
+
parse_url part[0], par_builder
|
102
|
+
else
|
103
|
+
parse_ulink part[0], par_builder
|
104
|
+
end
|
105
|
+
part[2]
|
106
|
+
end
|
107
|
+
|
108
|
+
def parse_url(text, par_builder)
|
109
|
+
par_builder.add_link(text.partition('{')[2])
|
110
|
+
end
|
111
|
+
|
112
|
+
def parse_ulink(text, par_builder)
|
113
|
+
add = text[text.index('[') + 1...text.index(']')]
|
114
|
+
txt = text[text.index('{') + 1..-1]
|
115
|
+
par_builder.add_link(add, txt)
|
116
|
+
end
|
117
|
+
|
118
|
+
def parse_format_block(text, par_builder)
|
119
|
+
t = parse_par_macros(text[4..-1]).lstrip if text[4]
|
120
|
+
if text.start_with? '\\uv{'
|
121
|
+
par_builder.add_quote t
|
122
|
+
else
|
123
|
+
parse_format text, par_builder, t
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
def parse_format(text, par_builder, t)
|
128
|
+
case text[0..3]
|
129
|
+
when '\\it ', '\\em ', '{\\it', '{\\em'
|
130
|
+
par_builder.add_em t
|
131
|
+
when '\\bf ', '{\\bf'
|
132
|
+
par_builder.add_strong t
|
133
|
+
when '\\tt ', '{\\tt'
|
134
|
+
par_builder.add_code t
|
135
|
+
else
|
136
|
+
extract_from_braces text, par_builder
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
def extract_from_braces(text, par_builder)
|
141
|
+
if text.index(/\{\\\w/) == 0
|
142
|
+
par_special dump_to_space(text), par_builder
|
143
|
+
elsif text.start_with? '{'
|
144
|
+
par_special cut_at_matching(text, '{', '}')[0], par_builder
|
145
|
+
else
|
146
|
+
dump_all text
|
147
|
+
end
|
148
|
+
end
|
149
|
+
|
150
|
+
def parse_fnote(text, par_builder)
|
151
|
+
part = cut_at_match_with_start(text, '{', '}')
|
152
|
+
fnote = parse_par_macros(part[0][part[0].index('{') + 1..-1])
|
153
|
+
num = @builder.add_fnote(fnote)
|
154
|
+
par_builder.add_link("##{num}", "<sup>#{num}</sup>")
|
155
|
+
part[2]
|
156
|
+
end
|
157
|
+
end
|
158
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# A preprocessor for HTML and TeX special characters
|
3
|
+
class Preprocessor
|
4
|
+
attr_accessor :ttchar
|
5
|
+
G_SUBST = { '<' => '<', '>' => '>', '&' => '&' }
|
6
|
+
|
7
|
+
TEXT_SUBST = { '~' => ' ', '--' => '–', '---' => '&mdash',
|
8
|
+
'\\,' => ' ', '\\-' => '', '\\TeX{}' => 'TeX',
|
9
|
+
'\\LaTeX{}' => 'LaTeX', '\\csplain{}' => 'CSplain' }
|
10
|
+
|
11
|
+
TS_REG = Regexp.new('~|---?|([^\\\\][%].*)|^%.*|\s%.*|\\\\[,-]|' \
|
12
|
+
'\\\\(La)?TeX\{\}|\\\\csplain\{\}|^\{|\s\{|^\}|\s\}')
|
13
|
+
|
14
|
+
def initialize
|
15
|
+
@ttchar = '"'
|
16
|
+
end
|
17
|
+
|
18
|
+
def run(text)
|
19
|
+
text.gsub(/[<>&]/) { |c| G_SUBST[c] }
|
20
|
+
end
|
21
|
+
|
22
|
+
def process_text(text)
|
23
|
+
text.gsub(TS_REG) { |c| TEXT_SUBST[c] }
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Builder for tables
|
3
|
+
class TableBuilder
|
4
|
+
SPAN = '\\multispan'
|
5
|
+
|
6
|
+
def initialize
|
7
|
+
@header = true
|
8
|
+
@table = ["\n"]
|
9
|
+
end
|
10
|
+
|
11
|
+
def add_row(cells)
|
12
|
+
@table << "<tr>\n"
|
13
|
+
cells.each do |cell|
|
14
|
+
span_index = cell.index(SPAN)
|
15
|
+
span = cell[span_index + SPAN.length] if span_index
|
16
|
+
part = cell.partition SPAN
|
17
|
+
newcell = part[0] + (span_index ? part[2][1..-1] : '')
|
18
|
+
@table << cell_to_s([@header, newcell, span])
|
19
|
+
end
|
20
|
+
@table << "</tr>\n"
|
21
|
+
@header = false
|
22
|
+
end
|
23
|
+
|
24
|
+
def add_caption(text)
|
25
|
+
@table.insert 1, "<caption>#{text}</caption>\n"
|
26
|
+
end
|
27
|
+
|
28
|
+
def cell_to_s(cell)
|
29
|
+
tag = cell[0] ? 'th' : 'td'
|
30
|
+
attr = cell[2] ? " colspan=\"#{cell[2]}\"" : ''
|
31
|
+
"<#{tag}#{attr}>#{cell[1]}</#{tag}>\n"
|
32
|
+
end
|
33
|
+
|
34
|
+
def to_s
|
35
|
+
@table.join
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
module Opmac2html
|
2
|
+
# Mixin providing text partitioning
|
3
|
+
module TextCutter
|
4
|
+
def cut_at(separator)
|
5
|
+
part = @input.partition separator
|
6
|
+
@input = part[2]
|
7
|
+
part[0]
|
8
|
+
end
|
9
|
+
|
10
|
+
def cut_at_with_sep(separator)
|
11
|
+
part = @input.partition separator
|
12
|
+
@input = part[1] + part[2]
|
13
|
+
part[0]
|
14
|
+
end
|
15
|
+
|
16
|
+
def cut_at_match_with_start(text, beg_sep, end_sep)
|
17
|
+
return ['', '', ''] if text.empty?
|
18
|
+
index = matching_separator_index text, beg_sep, end_sep
|
19
|
+
el = end_sep.length
|
20
|
+
[text[0...index], text[index, el] || '', text[index + el..-1] || '']
|
21
|
+
end
|
22
|
+
|
23
|
+
def cut_at_matching(text, beg_sep, end_sep)
|
24
|
+
return ['', ''] if text.empty?
|
25
|
+
index = matching_separator_index text, beg_sep, end_sep
|
26
|
+
bi, bl, el = text.index(beg_sep), beg_sep.length, end_sep.length
|
27
|
+
[text[bi + bl...index], text[index + el..-1] || '']
|
28
|
+
end
|
29
|
+
|
30
|
+
protected
|
31
|
+
|
32
|
+
def matching_separator_start(text, beg_sep)
|
33
|
+
index = text.index beg_sep
|
34
|
+
if index
|
35
|
+
index + beg_sep.length
|
36
|
+
else
|
37
|
+
0
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
def matching_separator_index(text, beg_sep, end_sep)
|
42
|
+
level = 1
|
43
|
+
(matching_separator_start(text, beg_sep)...text.length).each do |i|
|
44
|
+
if text[i, beg_sep.length] == beg_sep
|
45
|
+
level += 1
|
46
|
+
elsif text[i, end_sep.length] == end_sep
|
47
|
+
level -= 1
|
48
|
+
end
|
49
|
+
return i if level == 0
|
50
|
+
end
|
51
|
+
text.length
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
data/lib/opmac2html.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'opmac2html/version'
|
2
|
+
require 'opmac2html/converter'
|
3
|
+
|
4
|
+
module Opmac2html
|
5
|
+
# Opmac2html root class/facade
|
6
|
+
class Opmac2html
|
7
|
+
def initialize(input, output)
|
8
|
+
Converter.new(input, output).convert
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.version
|
12
|
+
VERSION
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
data/opmac2html.gemspec
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'opmac2html/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "opmac2html"
|
8
|
+
spec.version = Opmac2html::VERSION
|
9
|
+
spec.authors = ["Martin Kinčl"]
|
10
|
+
spec.summary = %q{Converter from OPmac TeX markup to HTML}
|
11
|
+
spec.description = %q{A converter of TeX documents written using OPmac macro set
|
12
|
+
to HTML5 pages}
|
13
|
+
spec.homepage = "https://github.com/kinclma1/opmac2html"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.required_ruby_version = '>= 2.0'
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
|
26
|
+
spec.add_dependency "slop", "~> 4.0"
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,108 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: opmac2html
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Martin Kinčl
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-06-17 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.7'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.7'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: slop
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '4.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '4.0'
|
55
|
+
description: |-
|
56
|
+
A converter of TeX documents written using OPmac macro set
|
57
|
+
to HTML5 pages
|
58
|
+
email:
|
59
|
+
executables:
|
60
|
+
- opmac2html
|
61
|
+
extensions: []
|
62
|
+
extra_rdoc_files: []
|
63
|
+
files:
|
64
|
+
- ".gitignore"
|
65
|
+
- Gemfile
|
66
|
+
- LICENSE.txt
|
67
|
+
- README.md
|
68
|
+
- Rakefile
|
69
|
+
- bin/opmac2html
|
70
|
+
- lib/opmac2html.rb
|
71
|
+
- lib/opmac2html/cli.rb
|
72
|
+
- lib/opmac2html/converter.rb
|
73
|
+
- lib/opmac2html/html_builder.rb
|
74
|
+
- lib/opmac2html/list_builder.rb
|
75
|
+
- lib/opmac2html/macro_parser.rb
|
76
|
+
- lib/opmac2html/par_builder.rb
|
77
|
+
- lib/opmac2html/paragraph_parser.rb
|
78
|
+
- lib/opmac2html/preprocessor.rb
|
79
|
+
- lib/opmac2html/table_builder.rb
|
80
|
+
- lib/opmac2html/text_cutter.rb
|
81
|
+
- lib/opmac2html/version.rb
|
82
|
+
- opmac2html.gemspec
|
83
|
+
homepage: https://github.com/kinclma1/opmac2html
|
84
|
+
licenses:
|
85
|
+
- MIT
|
86
|
+
metadata: {}
|
87
|
+
post_install_message:
|
88
|
+
rdoc_options: []
|
89
|
+
require_paths:
|
90
|
+
- lib
|
91
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
92
|
+
requirements:
|
93
|
+
- - ">="
|
94
|
+
- !ruby/object:Gem::Version
|
95
|
+
version: '2.0'
|
96
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
97
|
+
requirements:
|
98
|
+
- - ">="
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: '0'
|
101
|
+
requirements: []
|
102
|
+
rubyforge_project:
|
103
|
+
rubygems_version: 2.4.5
|
104
|
+
signing_key:
|
105
|
+
specification_version: 4
|
106
|
+
summary: Converter from OPmac TeX markup to HTML
|
107
|
+
test_files: []
|
108
|
+
has_rdoc:
|