Module: TWPipeline
- Defined in:
- lib/twpipeline.rb,
lib/twpipeline/cli.rb,
lib/twpipeline/bench.rb,
lib/twpipeline/jsonl.rb,
lib/twpipeline/stage.rb,
lib/twpipeline/rusage.rb,
lib/twpipeline/sorting.rb,
lib/twpipeline/version.rb,
lib/twpipeline/parallel.rb,
lib/twpipeline/frequency.rb,
lib/twpipeline/resources.rb,
lib/twpipeline/segmenter.rb,
lib/twpipeline/sources/hplt.rb,
lib/twpipeline/stages/count.rb,
lib/twpipeline/stages/dedup.rb,
lib/twpipeline/stages/ingest.rb,
lib/twpipeline/stages/script.rb,
lib/twpipeline/stages/lexicon.rb,
lib/twpipeline/stages/segment.rb,
lib/twpipeline/stages/evidence.rb,
lib/twpipeline/stages/tokenize.rb,
lib/twpipeline/stages/normalize.rb,
sig/twpipeline.rbs
Defined Under Namespace
Modules: Bench, Frequency, Jsonl, Parallel, Rusage, Sorting, Sources, Stages
Classes: CLI, Error, MapStage, Resources, Segmenter, Stage
Constant Summary
collapse
- ROOT =
Pathname(__dir__).parent
- VERSION =
"0.1.0"
Class Attribute Summary collapse
Class Method Summary
collapse
Class Attribute Details
38
|
# File 'lib/twpipeline.rb', line 38
def resources = @resources ||= Resources.detect
|
Class Method Details
.data(*parts) ⇒ Pathname
42
|
# File 'lib/twpipeline.rb', line 42
def data(*parts) = ROOT.join("data", *parts)
|
.warm_up ⇒ singleton(TWPipeline)
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
# File 'lib/twpipeline.rb', line 44
def warm_up
TWFilter::Checks::Script.tiers
TWFilter::Checks::Lexicon.hard_terms
TWFilter::Checks::Lexicon.soft_terms
TWFilter::Checks::Lexicon.exceptions
TWFilter::Checks::Lexicon.regional_terms
TWFilter::Checks::Lexicon.foreign_topics
TWFilter::Checks::Lexicon.cantonese_chars
TWFilter::Checks::Erhua.headed
TWFilter::Checks::Erhua.tailed
TWFilter::Checks::Wenyan.markers
TWFilter::Evidence.terms
self
end
|
.work ⇒ Pathname
40
|
# File 'lib/twpipeline.rb', line 40
def work = Pathname(ENV.fetch("TWP_WORK", ROOT.parent.join("work").to_s))
|