glaemscribe 1.1.14 → 1.3.0
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 +5 -5
- data/bin/glaemscribe +21 -17
- data/glaemresources/charsets/cirth_ds.cst +540 -0
- data/glaemresources/charsets/eldamar.cst +210 -0
- data/glaemresources/charsets/sarati_eldamar.cst +256 -0
- data/glaemresources/charsets/tengwar_ds_annatar.cst +2868 -0
- data/glaemresources/charsets/tengwar_ds_eldamar.cst +2729 -0
- data/glaemresources/charsets/tengwar_ds_elfica.cst +2742 -0
- data/glaemresources/charsets/tengwar_ds_parmaite.cst +2726 -0
- data/glaemresources/charsets/tengwar_ds_sindarin.cst +2722 -0
- data/glaemresources/charsets/tengwar_freemono.cst +217 -0
- data/glaemresources/charsets/tengwar_guni_annatar.cst +2948 -0
- data/glaemresources/charsets/tengwar_guni_eldamar.cst +2809 -0
- data/glaemresources/charsets/tengwar_guni_elfica.cst +2809 -0
- data/glaemresources/charsets/tengwar_guni_parmaite.cst +2813 -0
- data/glaemresources/charsets/tengwar_guni_sindarin.cst +2808 -0
- data/glaemresources/charsets/tengwar_telcontar.cst +225 -0
- data/glaemresources/charsets/unicode_gothic.cst +64 -0
- data/glaemresources/charsets/unicode_runes.cst +121 -0
- data/glaemresources/modes/{adunaic.glaem → adunaic-tengwar-glaemscrafu.glaem} +14 -2
- data/glaemresources/modes/{blackspeech.glaem → blackspeech-tengwar-general_use.glaem} +13 -3
- data/glaemresources/modes/english-cirth-espeak.glaem +687 -0
- data/glaemresources/modes/english-tengwar-espeak.glaem +814 -0
- data/glaemresources/modes/japanese-tengwar.glaem +776 -0
- data/glaemresources/modes/{khuzdul.glaem → khuzdul-cirth-moria.glaem} +4 -1
- data/glaemresources/modes/lang_belta-tengwar-dadef.glaem +248 -0
- data/glaemresources/modes/{futhorc.glaem → old_english-futhorc.glaem} +0 -0
- data/glaemresources/modes/{mercian.glaem → old_english-tengwar-mercian.glaem} +22 -12
- data/glaemresources/modes/{westsaxon.glaem → old_english-tengwar-westsaxon.glaem} +20 -11
- data/glaemresources/modes/{futhark-runicus.glaem → old_norse-futhark-runicus.glaem} +0 -0
- data/glaemresources/modes/{futhark-younger.glaem → old_norse-futhark-younger.glaem} +0 -0
- data/glaemresources/modes/{quenya.glaem → quenya-tengwar-classical.glaem} +32 -50
- data/glaemresources/modes/raw-cirth.glaem +154 -0
- data/glaemresources/modes/raw-tengwar.glaem +46 -23
- data/glaemresources/modes/{rlyehian.glaem → rlyehian-tengwar.glaem} +14 -3
- data/glaemresources/modes/{sindarin-daeron.glaem → sindarin-cirth-daeron.glaem} +55 -14
- data/glaemresources/modes/{sindarin-beleriand.glaem → sindarin-tengwar-beleriand.glaem} +154 -28
- data/glaemresources/modes/{sindarin.glaem → sindarin-tengwar-general_use.glaem} +86 -25
- data/glaemresources/modes/{telerin.glaem → telerin-tengwar-glaemscrafu.glaem} +16 -6
- data/glaemresources/modes/{westron.glaem → westron-tengwar-glaemscrafu.glaem} +18 -8
- data/lib/api/charset.rb +67 -7
- data/lib/api/charset_parser.rb +14 -1
- data/lib/api/constants.rb +3 -4
- data/lib/api/fragment.rb +26 -5
- data/lib/api/if_tree.rb +70 -8
- data/lib/api/macro.rb +40 -0
- data/lib/api/mode.rb +66 -19
- data/lib/api/mode_parser.rb +117 -14
- data/lib/api/object_additions.rb +23 -1
- data/lib/api/option.rb +17 -2
- data/lib/api/post_processor/outspace.rb +44 -0
- data/lib/api/post_processor/resolve_virtuals.rb +25 -9
- data/lib/api/resource_manager.rb +1 -0
- data/lib/api/rule_group.rb +170 -26
- data/lib/api/sheaf_chain_iterator.rb +1 -1
- data/lib/api/transcription_pre_post_processor.rb +8 -5
- data/lib/api/transcription_processor.rb +15 -12
- data/lib/api/tts.rb +51 -0
- data/lib/glaemscribe.rb +36 -31
- data/lib_espeak/espeakng.for.glaemscribe.nowasm.sync.js +35 -0
- data/lib_espeak/glaemscribe_tts.js +505 -0
- metadata +76 -24
@@ -43,8 +43,8 @@ module Glaemscribe
|
|
43
43
|
@transcription_tree = TranscriptionTreeNode.new(nil,nil)
|
44
44
|
|
45
45
|
# Add WORD_BOUNDARY and WORD_BREAKER in the tree
|
46
|
-
@transcription_tree.add_subpath(
|
47
|
-
@transcription_tree.add_subpath(WORD_BREAKER,
|
46
|
+
@transcription_tree.add_subpath(WORD_BOUNDARY_TREE, [""])
|
47
|
+
@transcription_tree.add_subpath(WORD_BREAKER, [""])
|
48
48
|
|
49
49
|
rule_groups.each{ |rgname, rg|
|
50
50
|
rg.finalize(trans_options)
|
@@ -73,7 +73,7 @@ module Glaemscribe
|
|
73
73
|
}
|
74
74
|
end
|
75
75
|
|
76
|
-
def apply(l)
|
76
|
+
def apply(l, debug_context)
|
77
77
|
ret = []
|
78
78
|
current_group = nil
|
79
79
|
accumulated_word = ""
|
@@ -81,14 +81,14 @@ module Glaemscribe
|
|
81
81
|
l.split("").each{ |c|
|
82
82
|
case c
|
83
83
|
when " ", "\t"
|
84
|
-
ret += transcribe_word(accumulated_word)
|
84
|
+
ret += transcribe_word(accumulated_word, debug_context)
|
85
85
|
ret += ["*SPACE"]
|
86
86
|
|
87
87
|
accumulated_word = ""
|
88
88
|
when "\r"
|
89
89
|
# Ignore
|
90
90
|
when "\n"
|
91
|
-
ret += transcribe_word(accumulated_word)
|
91
|
+
ret += transcribe_word(accumulated_word, debug_context)
|
92
92
|
ret += ["*LF"]
|
93
93
|
|
94
94
|
accumulated_word = ""
|
@@ -97,24 +97,27 @@ module Glaemscribe
|
|
97
97
|
if c_group == current_group
|
98
98
|
accumulated_word += c
|
99
99
|
else
|
100
|
-
ret += transcribe_word(accumulated_word)
|
100
|
+
ret += transcribe_word(accumulated_word, debug_context)
|
101
101
|
current_group = c_group
|
102
102
|
accumulated_word = c
|
103
103
|
end
|
104
104
|
end
|
105
105
|
}
|
106
106
|
# Just in case
|
107
|
-
ret += transcribe_word(accumulated_word)
|
107
|
+
ret += transcribe_word(accumulated_word, debug_context)
|
108
108
|
ret
|
109
109
|
end
|
110
110
|
|
111
|
-
def transcribe_word(word)
|
111
|
+
def transcribe_word(word, debug_context)
|
112
112
|
res = []
|
113
|
-
word =
|
113
|
+
word = WORD_BOUNDARY_TREE + word + WORD_BOUNDARY_TREE
|
114
114
|
while word.length != 0
|
115
|
-
|
116
|
-
word
|
117
|
-
|
115
|
+
tokens, len = @transcription_tree.transcribe(word)
|
116
|
+
word = word[len..-1]
|
117
|
+
eaten = word[0..len-1]
|
118
|
+
res += tokens
|
119
|
+
|
120
|
+
debug_context.processor_pathes << [eaten, tokens, tokens]
|
118
121
|
end
|
119
122
|
# Return token list
|
120
123
|
res
|
data/lib/api/tts.rb
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
module Glaemscribe
|
2
|
+
module API
|
3
|
+
|
4
|
+
class TTS
|
5
|
+
|
6
|
+
TTS_ENGINE_PATH = File.dirname(__FILE__) + "/../../lib_espeak/espeakng.for.glaemscribe.nowasm.sync.js"
|
7
|
+
TTS_MODULE_PATH = File.dirname(__FILE__) + "/../../lib_espeak/glaemscribe_tts.js"
|
8
|
+
|
9
|
+
def self.loaded?
|
10
|
+
!@context.nil?
|
11
|
+
end
|
12
|
+
|
13
|
+
def self.load_engine
|
14
|
+
return if @context
|
15
|
+
|
16
|
+
@context = ::MiniRacer::Context.new
|
17
|
+
|
18
|
+
@context.attach 'console.log', proc{|o| puts o}
|
19
|
+
@context.attach 'print', proc{|o| puts o}
|
20
|
+
|
21
|
+
espeak_lib = File.open(TTS_ENGINE_PATH,"rb").read
|
22
|
+
@context.eval(espeak_lib)
|
23
|
+
|
24
|
+
tts_module = File.open(TTS_MODULE_PATH,"rb").read
|
25
|
+
@context.eval(tts_module)
|
26
|
+
|
27
|
+
@voice_list = @context.eval("Glaemscribe.TTS.voice_list()")
|
28
|
+
# puts "TTS Engine loaded."
|
29
|
+
end
|
30
|
+
|
31
|
+
def self.voice_list
|
32
|
+
load_engine if !@context
|
33
|
+
@voice_list
|
34
|
+
end
|
35
|
+
|
36
|
+
def self.ipa(text, voice, has_raw_mode)
|
37
|
+
load_engine if !@context
|
38
|
+
@context.eval("var esp = new Glaemscribe.TTS(); esp.synthesize_ipa(#{text.inspect},{voice:'#{voice}', has_raw_mode: #{has_raw_mode}})")
|
39
|
+
end
|
40
|
+
|
41
|
+
def self.wav(text, voice, has_raw_mode)
|
42
|
+
load_engine if !@context
|
43
|
+
@context.eval("var esp = new Glaemscribe.TTS(); esp.synthesize_wav(#{text.inspect},{voice:'#{voice}', has_raw_mode: #{has_raw_mode}})")
|
44
|
+
end
|
45
|
+
|
46
|
+
def self.option_name_to_voice(option_name)
|
47
|
+
option_name.downcase.gsub(/^espeak_voice_/,'').gsub('_','-')
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
data/lib/glaemscribe.rb
CHANGED
@@ -28,46 +28,51 @@ require "FileUtils" if !defined? FileUtils
|
|
28
28
|
|
29
29
|
module Glaemscribe
|
30
30
|
module API
|
31
|
-
API_PATH = File.dirname(__FILE__)
|
31
|
+
API_PATH = File.dirname(__FILE__) + "/api/"
|
32
32
|
|
33
|
-
require API_PATH + "
|
34
|
-
require API_PATH + "
|
35
|
-
require API_PATH + "
|
33
|
+
require API_PATH + "debug.rb"
|
34
|
+
require API_PATH + "constants.rb"
|
35
|
+
require API_PATH + "object_additions.rb"
|
36
36
|
|
37
|
-
require API_PATH + "
|
38
|
-
require API_PATH + "
|
39
|
-
require API_PATH + "
|
40
|
-
require API_PATH + "
|
37
|
+
require API_PATH + "fragment.rb"
|
38
|
+
require API_PATH + "sheaf_chain_iterator.rb"
|
39
|
+
require API_PATH + "sheaf_chain.rb"
|
40
|
+
require API_PATH + "sheaf.rb"
|
41
41
|
|
42
|
-
require API_PATH + "
|
43
|
-
require API_PATH + "
|
44
|
-
require API_PATH + "
|
42
|
+
require API_PATH + "rule.rb"
|
43
|
+
require API_PATH + "sub_rule.rb"
|
44
|
+
require API_PATH + "rule_group.rb"
|
45
|
+
require API_PATH + "macro.rb"
|
45
46
|
|
46
|
-
require API_PATH + "
|
47
|
-
require API_PATH + "
|
47
|
+
require API_PATH + "eval.rb"
|
48
|
+
require API_PATH + "if_tree.rb"
|
48
49
|
|
49
|
-
require API_PATH + "
|
50
|
+
require API_PATH + "transcription_tree_node.rb"
|
50
51
|
|
51
|
-
require API_PATH + "
|
52
|
-
require API_PATH + "
|
52
|
+
require API_PATH + "transcription_pre_post_processor.rb"
|
53
|
+
require API_PATH + "transcription_processor.rb"
|
53
54
|
|
54
|
-
require API_PATH + "
|
55
|
-
require API_PATH + "
|
56
|
-
require API_PATH + "
|
55
|
+
require API_PATH + "charset.rb"
|
56
|
+
require API_PATH + "mode.rb"
|
57
|
+
require API_PATH + "option.rb"
|
57
58
|
|
58
|
-
require API_PATH + "
|
59
|
-
require API_PATH + "
|
60
|
-
require API_PATH + "
|
61
|
-
require API_PATH + "
|
62
|
-
require API_PATH + "
|
59
|
+
require API_PATH + "resource_manager.rb"
|
60
|
+
require API_PATH + "glaeml.rb"
|
61
|
+
require API_PATH + "glaeml_shellwords.rb"
|
62
|
+
require API_PATH + "mode_parser.rb"
|
63
|
+
require API_PATH + "charset_parser.rb"
|
63
64
|
|
64
|
-
require API_PATH + "
|
65
|
-
require API_PATH + "
|
66
|
-
require API_PATH + "
|
67
|
-
require API_PATH + "
|
68
|
-
require API_PATH + "
|
69
|
-
|
70
|
-
require API_PATH + "
|
65
|
+
require API_PATH + "pre_processor/elvish_numbers.rb"
|
66
|
+
require API_PATH + "pre_processor/downcase.rb"
|
67
|
+
require API_PATH + "pre_processor/substitute.rb"
|
68
|
+
require API_PATH + "pre_processor/rxsubstitute.rb"
|
69
|
+
require API_PATH + "pre_processor/up_down_tehta_split.rb"
|
70
|
+
|
71
|
+
require API_PATH + "post_processor/outspace.rb"
|
72
|
+
require API_PATH + "post_processor/reverse.rb"
|
73
|
+
require API_PATH + "post_processor/resolve_virtuals.rb"
|
74
|
+
|
75
|
+
require API_PATH + "tts.rb"
|
71
76
|
|
72
77
|
end
|
73
78
|
end
|