latex-decode 0.4.2 → 0.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +40 -7
- data/lib/latex/decode/accents.rb +4 -14
- data/lib/latex/decode/base.rb +8 -11
- data/lib/latex/decode/compatibility.rb +4 -82
- data/lib/latex/decode/diacritics.rb +3 -8
- data/lib/latex/decode/greek.rb +3 -1
- data/lib/latex/decode/maths.rb +469 -9
- data/lib/latex/decode/punctuation.rb +9 -2
- data/lib/latex/decode/symbols.rb +2 -4
- data/lib/latex/decode/version.rb +3 -1
- data/lib/latex/decode.rb +32 -23
- metadata +13 -40
- data/.github/workflows/ci.yml +0 -34
- data/.gitignore +0 -7
- data/.simplecov +0 -18
- data/Gemfile +0 -16
- data/Rakefile +0 -38
- data/cucumber.yml +0 -1
- data/features/brackets.feature +0 -11
- data/features/diacritics.feature +0 -40
- data/features/greek.feature +0 -13
- data/features/maths.feature +0 -9
- data/features/non-latex.feature +0 -15
- data/features/punctuation.feature +0 -50
- data/features/special_characters.feature +0 -21
- data/features/step_definitions/latex.rb +0 -12
- data/features/support/env.rb +0 -13
- data/features/symbols.feature +0 -14
- data/features/umlauts.feature +0 -11
- data/features/whitespace.feature +0 -28
- data/latex-decode.gemspec +0 -27
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b31903b54e1a793967de578a4fbeffed24cea678c9935c223408d133be0a5d5b
|
|
4
|
+
data.tar.gz: b23f75d41c74bc718ab390809f5cd15d7bf7e414c5aeab4d5c37dca9266b381a
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2f49ed520921abfc20d1928771f1a4cac58e5f8624e369f2f575e6e717edd2cc6d612fcc8240630e6a0fa641322b5504a14b9e97d50398b190419cee62e26698
|
|
7
|
+
data.tar.gz: 1e87d5da7b85480ffa54e2604f6fe0633061a466fbe3ad588d2a45506eda81123594a5463bbeee2676d7f2c8a1d82a744a1076f1d304881dc1b140f70579e2c7
|
data/README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
LaTeX::Decode
|
|
2
2
|
=============
|
|
3
|
-
[](https://github.com/inukshuk/latex-decode/actions/workflows/ci.yml)
|
|
4
|
+
[](https://badge.fury.io/rb/latex-decode)
|
|
5
5
|
|
|
6
6
|
LaTeX::Decode is a Ruby gem to convert LaTeX input to Unicode.
|
|
7
7
|
Its original use was as an input filter for [BibTeX-Ruby][]
|
|
@@ -11,16 +11,48 @@ are based on François Charette's equivalent Perl module [LaTeX::Decode][].
|
|
|
11
11
|
|
|
12
12
|
Quickstart
|
|
13
13
|
----------
|
|
14
|
-
$
|
|
14
|
+
$ gem install latex-decode
|
|
15
15
|
$ irb
|
|
16
16
|
>> require 'latex/decode'
|
|
17
17
|
>> LaTeX.decode "dipl\\^{o}me d'\\'{e}tudes sup\\'erieures"
|
|
18
18
|
=> "diplôme d'études supérieures"
|
|
19
19
|
|
|
20
|
+
Math
|
|
21
|
+
----
|
|
22
|
+
Math in `$…$`, `\(…\)`, `$$…$$` or `\[…\]`
|
|
23
|
+
is converted to Unicode if all of it can be represented,
|
|
24
|
+
which covers most math found in bibliographies:
|
|
25
|
+
Greek letters and symbols, sub- and superscripts,
|
|
26
|
+
font letters like `\mathbb`, accents, fractions and roots.
|
|
27
|
+
|
|
28
|
+
>> LaTeX.decode '$\alpha$-decay of $^{13}$C'
|
|
29
|
+
=> "α-decay of ¹³C"
|
|
30
|
+
>> LaTeX.decode 'Sorting in $O(n \log n)$ on $\mathbb{R}^n$'
|
|
31
|
+
=> "Sorting in O(n log n) on ℝⁿ"
|
|
32
|
+
|
|
33
|
+
Math that cannot be converted completely is kept as it is,
|
|
34
|
+
including the delimiters,
|
|
35
|
+
so that it can still be rendered,
|
|
36
|
+
for example, by MathJax or KaTeX.
|
|
37
|
+
Unicode has no subscript f, for instance:
|
|
38
|
+
|
|
39
|
+
>> LaTeX.decode 'Effective temperature $T_{\mathrm{eff}}$'
|
|
40
|
+
=> "Effective temperature $T_{\\mathrm{eff}}$"
|
|
41
|
+
|
|
42
|
+
To keep all math as it is always, pass `math: false`:
|
|
43
|
+
|
|
44
|
+
>> LaTeX.decode '$\alpha$-decay', math: false
|
|
45
|
+
=> "$\\alpha$-decay"
|
|
46
|
+
|
|
47
|
+
Math nested in text inside math,
|
|
48
|
+
like `$a \text{ if $b$} c$`,
|
|
49
|
+
is not currently supported.
|
|
50
|
+
|
|
20
51
|
|
|
21
52
|
Issues
|
|
22
53
|
------
|
|
23
|
-
Please use the tracker of the project's [repository][]
|
|
54
|
+
Please use the tracker of the project's [repository][]
|
|
55
|
+
to report any issues.
|
|
24
56
|
When describing intended behaviour,
|
|
25
57
|
please use the syntax of the Cucumber features used by LaTeX::Decode.
|
|
26
58
|
For instance, you could describe the example above as:
|
|
@@ -36,13 +68,14 @@ For instance, you could describe the example above as:
|
|
|
36
68
|
|
|
37
69
|
Credits
|
|
38
70
|
-------
|
|
39
|
-
Kudos and thanks to all [contributors][]
|
|
71
|
+
Kudos and thanks to all [contributors][]
|
|
72
|
+
who have made LaTeX::Decode possible!
|
|
40
73
|
|
|
41
|
-
Copyright (C) 2011-
|
|
74
|
+
Copyright (C) 2011-2026 Sylvester Keil\
|
|
42
75
|
Copyright (C) 2010 François Charette
|
|
43
76
|
|
|
44
77
|
|
|
45
|
-
[
|
|
78
|
+
[BibTeX-Ruby]: https://rubygems.org/gems/bibtex-ruby
|
|
46
79
|
[LaTeX::Decode]: https://github.com/fc7/LaTeX-Decode
|
|
47
80
|
|
|
48
81
|
[repository]: https://github.com/inukshuk/latex-decode
|
data/lib/latex/decode/accents.rb
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
#
|
|
1
|
+
# frozen_string_literal: true
|
|
2
2
|
|
|
3
3
|
module LaTeX
|
|
4
4
|
module Decode
|
|
@@ -13,21 +13,11 @@ module LaTeX
|
|
|
13
13
|
. \u0307
|
|
14
14
|
'' \u0308
|
|
15
15
|
" \u0308
|
|
16
|
-
}
|
|
16
|
+
}].freeze
|
|
17
17
|
|
|
18
18
|
@patterns = [
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
} ||
|
|
22
|
-
ruby_19 {
|
|
23
|
-
/\\(#{ map.keys.map { |k| Regexp.escape(k) }.join('|') })\{(\p{L}\p{M}*)\}/ou
|
|
24
|
-
},
|
|
25
|
-
ruby_18 {
|
|
26
|
-
/\\(#{ map.keys.map { |k| Regexp.escape(k) }.join('|') })([[:alpha:]])/ou
|
|
27
|
-
} ||
|
|
28
|
-
ruby_19 {
|
|
29
|
-
/\\(#{ map.keys.map { |k| Regexp.escape(k) }.join('|') })(\p{L}\p{M}*)/ou
|
|
30
|
-
}
|
|
19
|
+
/\\(#{ map.keys.map { |k| Regexp.escape(k) }.join('|') })\{(\p{L}\p{M}*)\}/ou,
|
|
20
|
+
/\\(#{ map.keys.map { |k| Regexp.escape(k) }.join('|') })(\p{L}\p{M}*)/ou
|
|
31
21
|
].freeze
|
|
32
22
|
|
|
33
23
|
end
|
data/lib/latex/decode/base.rb
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
#
|
|
1
|
+
# frozen_string_literal: true
|
|
2
2
|
|
|
3
3
|
module LaTeX
|
|
4
4
|
module Decode
|
|
@@ -11,24 +11,21 @@ module LaTeX
|
|
|
11
11
|
name.split('::').last.downcase.to_sym
|
|
12
12
|
end
|
|
13
13
|
|
|
14
|
-
def inherited(base)
|
|
15
|
-
subclasses << base
|
|
16
|
-
end
|
|
17
|
-
|
|
18
|
-
def subclasses
|
|
19
|
-
@subclasses ||= []
|
|
20
|
-
end
|
|
21
|
-
|
|
22
14
|
def decode(string)
|
|
23
15
|
decode!(string.dup)
|
|
24
16
|
end
|
|
25
17
|
|
|
26
18
|
def decode!(string)
|
|
27
19
|
patterns.each do |pattern|
|
|
28
|
-
|
|
20
|
+
decode_pattern!(string, pattern)
|
|
29
21
|
end
|
|
30
22
|
string
|
|
31
23
|
end
|
|
24
|
+
|
|
25
|
+
def decode_pattern!(string, pattern)
|
|
26
|
+
string.gsub!(pattern) { |m| [$2,map[$1],$3].compact.join }
|
|
27
|
+
string
|
|
28
|
+
end
|
|
32
29
|
end
|
|
33
30
|
end
|
|
34
31
|
|
|
@@ -49,7 +46,7 @@ module LaTeX
|
|
|
49
46
|
string.gsub!(/(\\[^\sij&#\$\{\}_~%])\s+([[:alpha:]]+)\b/i, '\1{\2}')
|
|
50
47
|
|
|
51
48
|
# non-breaking spaces
|
|
52
|
-
string.gsub!(/(\A|[^\\])~/,
|
|
49
|
+
string.gsub!(/(\A|[^\\])~/, "\\1\u00a0")
|
|
53
50
|
|
|
54
51
|
string
|
|
55
52
|
end
|
|
@@ -1,26 +1,4 @@
|
|
|
1
|
-
|
|
2
|
-
if RUBY_VERSION < "1.9"
|
|
3
|
-
$KCODE = 'U'
|
|
4
|
-
|
|
5
|
-
module LaTeX
|
|
6
|
-
def self.to_unicode(string)
|
|
7
|
-
string.gsub(/\\?u([\da-f]{4})/i) { |m| [$1.to_i(16)].pack('U') }
|
|
8
|
-
end
|
|
9
|
-
end
|
|
10
|
-
|
|
11
|
-
def ruby_18; yield; end
|
|
12
|
-
def ruby_19; false; end
|
|
13
|
-
else
|
|
14
|
-
|
|
15
|
-
module LaTeX
|
|
16
|
-
def self.to_unicode(string)
|
|
17
|
-
string
|
|
18
|
-
end
|
|
19
|
-
end
|
|
20
|
-
|
|
21
|
-
def ruby_18; false; end
|
|
22
|
-
def ruby_19; yield; end
|
|
23
|
-
end
|
|
1
|
+
# frozen_string_literal: true
|
|
24
2
|
|
|
25
3
|
if RUBY_PLATFORM == 'java'
|
|
26
4
|
require 'java'
|
|
@@ -33,65 +11,9 @@ if RUBY_PLATFORM == 'java'
|
|
|
33
11
|
end
|
|
34
12
|
|
|
35
13
|
else
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
string.unicode_normalize(:nfc)
|
|
40
|
-
end
|
|
41
|
-
end
|
|
42
|
-
else
|
|
43
|
-
begin
|
|
44
|
-
require 'unicode'
|
|
45
|
-
|
|
46
|
-
# Use the Unicode gem
|
|
47
|
-
module LaTeX
|
|
48
|
-
def self.normalize_C(string)
|
|
49
|
-
Unicode::normalize_C(string)
|
|
50
|
-
end
|
|
51
|
-
end
|
|
52
|
-
rescue LoadError
|
|
53
|
-
begin
|
|
54
|
-
require 'active_support/multibyte/chars'
|
|
55
|
-
|
|
56
|
-
# Use ActiveSupport's normalizer
|
|
57
|
-
module LaTeX
|
|
58
|
-
def self.normalize_C(string)
|
|
59
|
-
ActiveSupport::Multibyte::Chars.new(string).normalize(:c).to_s
|
|
60
|
-
end
|
|
61
|
-
end
|
|
62
|
-
rescue LoadError
|
|
63
|
-
fail "Failed to load unicode normalizer: please gem install unicode (or active_support)"
|
|
64
|
-
end
|
|
65
|
-
end
|
|
66
|
-
end
|
|
67
|
-
end
|
|
68
|
-
|
|
69
|
-
module LaTeX
|
|
70
|
-
begin
|
|
71
|
-
require 'ritex'
|
|
72
|
-
|
|
73
|
-
def self.ritex
|
|
74
|
-
Ritex::Parser.new(:mathml)
|
|
75
|
-
end
|
|
76
|
-
|
|
77
|
-
def self.to_math_ml(string)
|
|
78
|
-
ritex.parse string, :nowrap => true, :display => false
|
|
79
|
-
end
|
|
80
|
-
|
|
81
|
-
rescue LoadError
|
|
82
|
-
begin
|
|
83
|
-
require 'math_ml'
|
|
84
|
-
|
|
85
|
-
def self.to_math_ml(string)
|
|
86
|
-
MathML::String.mathml_latex_parser.parse(string, false)
|
|
87
|
-
end
|
|
88
|
-
|
|
89
|
-
rescue LoadError
|
|
90
|
-
# No MathML conversion
|
|
91
|
-
|
|
92
|
-
def self.to_math_ml(string)
|
|
93
|
-
string
|
|
94
|
-
end
|
|
14
|
+
module LaTeX
|
|
15
|
+
def self.normalize_C(string)
|
|
16
|
+
string.unicode_normalize(:nfc)
|
|
95
17
|
end
|
|
96
18
|
end
|
|
97
19
|
end
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
#
|
|
1
|
+
# frozen_string_literal: true
|
|
2
2
|
|
|
3
3
|
module LaTeX
|
|
4
4
|
module Decode
|
|
@@ -17,7 +17,7 @@ module LaTeX
|
|
|
17
17
|
b \u0331
|
|
18
18
|
B \u0335
|
|
19
19
|
t \u0361
|
|
20
|
-
}
|
|
20
|
+
}].freeze
|
|
21
21
|
|
|
22
22
|
@map = @macros.merge(Hash[*%w{
|
|
23
23
|
l ł
|
|
@@ -31,12 +31,7 @@ module LaTeX
|
|
|
31
31
|
}]).freeze
|
|
32
32
|
|
|
33
33
|
@patterns = [
|
|
34
|
-
|
|
35
|
-
/\\(#{ @macros.keys.map { |k| Regexp.escape(k) }.join('|') })\{([[:alpha:]]?)([[:alpha:]]*)\}/ou
|
|
36
|
-
} ||
|
|
37
|
-
ruby_19 {
|
|
38
|
-
/\\(#{ @macros.keys.map { |k| Regexp.escape(k) }.join('|') })\{(\p{L}\p{M}*)([[:alpha:]]*)\}/ou
|
|
39
|
-
},
|
|
34
|
+
/\\(#{ @macros.keys.map { |k| Regexp.escape(k) }.join('|') })\{(\p{L}\p{M}*)([[:alpha:]]*)\}/ou,
|
|
40
35
|
/\\(o|O|l|L|aa|AA|ae|AE)\b/,
|
|
41
36
|
].freeze
|
|
42
37
|
|
data/lib/latex/decode/greek.rb
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
#
|
|
1
|
+
# frozen_string_literal: true
|
|
2
2
|
|
|
3
3
|
module LaTeX
|
|
4
4
|
module Decode
|
|
@@ -19,6 +19,7 @@ module LaTeX
|
|
|
19
19
|
mu μ
|
|
20
20
|
nu ν
|
|
21
21
|
xi ξ
|
|
22
|
+
pi π
|
|
22
23
|
rho ρ
|
|
23
24
|
sigma σ
|
|
24
25
|
tau τ
|
|
@@ -41,6 +42,7 @@ module LaTeX
|
|
|
41
42
|
Mu Μ
|
|
42
43
|
Nu Ν
|
|
43
44
|
Xi Ξ
|
|
45
|
+
Pi Π
|
|
44
46
|
Rho Ρ
|
|
45
47
|
Sigma Σ
|
|
46
48
|
Tau Τ
|