substrate 0.1.0 → 0.2.0
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/lib/substrate/classify.rb +65 -0
- data/lib/substrate/cli/availability.rb +11 -0
- data/lib/substrate/cli/error.rb +7 -0
- data/lib/substrate/cli/runner.rb +31 -0
- data/lib/substrate/command.rb +24 -0
- data/lib/substrate/configuration.rb +21 -0
- data/lib/substrate/detection/path_resolver.rb +33 -0
- data/lib/substrate/distill.rb +31 -0
- data/lib/substrate/extract_pdf.rb +95 -0
- data/lib/substrate/handlers/article.rb +39 -0
- data/lib/substrate/handlers/pdf.rb +29 -0
- data/lib/substrate/handlers/raw_text.rb +22 -0
- data/lib/substrate/handlers/text_file.rb +26 -0
- data/lib/substrate/handlers/transcript.rb +48 -0
- data/lib/substrate/mediums/pdf/chapter.rb +9 -0
- data/lib/substrate/mediums/pdf/content.rb +13 -0
- data/lib/substrate/mediums/pdf/destination.rb +9 -0
- data/lib/substrate/mediums/pdf/destination_resolver.rb +131 -0
- data/lib/substrate/mediums/pdf/document.rb +46 -0
- data/lib/substrate/mediums/pdf/encrypted_pdf.rb +9 -0
- data/lib/substrate/mediums/pdf/entry.rb +9 -0
- data/lib/substrate/mediums/pdf/invalid_pdf.rb +9 -0
- data/lib/substrate/mediums/pdf/invalid_text.rb +9 -0
- data/lib/substrate/mediums/pdf/limit_exceeded.rb +17 -0
- data/lib/substrate/mediums/pdf/limits.rb +21 -0
- data/lib/substrate/mediums/pdf/named_destinations.rb +94 -0
- data/lib/substrate/mediums/pdf/no_selectable_text.rb +9 -0
- data/lib/substrate/mediums/pdf/outline.rb +9 -0
- data/lib/substrate/mediums/pdf/outline_facts.rb +115 -0
- data/lib/substrate/mediums/pdf/outline_parser.rb +67 -0
- data/lib/substrate/mediums/pdf/page.rb +9 -0
- data/lib/substrate/mediums/pdf/page_extractor.rb +28 -0
- data/lib/substrate/mediums/pdf/reader.rb +40 -0
- data/lib/substrate/mediums/pdf/text_extractor.rb +36 -0
- data/lib/substrate/primitives/article_content.rb +10 -0
- data/lib/substrate/primitives/extraction.rb +5 -0
- data/lib/substrate/primitives/metadata.rb +21 -0
- data/lib/substrate/primitives/page_collection.rb +5 -0
- data/lib/substrate/primitives/pdf_file.rb +5 -0
- data/lib/substrate/primitives/raw_text.rb +5 -0
- data/lib/substrate/primitives/source.rb +5 -0
- data/lib/substrate/primitives/text_content.rb +5 -0
- data/lib/substrate/primitives/text_file.rb +5 -0
- data/lib/substrate/primitives/transcripts/content.rb +11 -0
- data/lib/substrate/primitives/transcripts/metadata.rb +25 -0
- data/lib/substrate/primitives/transcripts/segment.rb +25 -0
- data/lib/substrate/primitives/transcripts/word.rb +23 -0
- data/lib/substrate/primitives/url_candidate.rb +13 -0
- data/lib/substrate/source_ref.rb +5 -0
- data/lib/substrate/sources/article.rb +34 -0
- data/lib/substrate/sources/audio.rb +57 -0
- data/lib/substrate/sources/pdf.rb +35 -0
- data/lib/substrate/sources/text.rb +23 -0
- data/lib/substrate/sources/url.rb +36 -0
- data/lib/substrate/transcribers/deepgram/client.rb +70 -0
- data/lib/substrate/transcribers/deepgram/configuration.rb +41 -0
- data/lib/substrate/transcribers/deepgram/response_parser.rb +102 -0
- data/lib/substrate/transcribers/deepgram.rb +45 -0
- data/lib/substrate/transcribers/whisper_cpp/response_parser.rb +66 -0
- data/lib/substrate/transcribers/whisper_cpp.rb +87 -0
- data/lib/substrate/transcripts/select_time_range.rb +59 -0
- data/lib/substrate/url_resolvers/generic.rb +71 -0
- data/lib/substrate/url_resolvers/resolver_for.rb +35 -0
- data/lib/substrate/version.rb +1 -1
- data/lib/substrate.rb +16 -3
- metadata +106 -1
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Substrate
|
|
4
|
+
module Transcripts
|
|
5
|
+
class SelectTimeRange < Command
|
|
6
|
+
def initialize(content:, range:)
|
|
7
|
+
@content = content
|
|
8
|
+
@range = range
|
|
9
|
+
end
|
|
10
|
+
|
|
11
|
+
def call
|
|
12
|
+
success(payload: Content.new(
|
|
13
|
+
source_ref: content.source_ref,
|
|
14
|
+
segments: selected_segments,
|
|
15
|
+
metadata: content.metadata
|
|
16
|
+
))
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
private
|
|
20
|
+
|
|
21
|
+
attr_reader :content, :range
|
|
22
|
+
|
|
23
|
+
def selected_segments
|
|
24
|
+
content.segments.filter_map do |segment|
|
|
25
|
+
next unless overlaps?(segment)
|
|
26
|
+
|
|
27
|
+
selected_segment(segment)
|
|
28
|
+
end
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def selected_segment(segment)
|
|
32
|
+
words = selected_words(segment.words)
|
|
33
|
+
|
|
34
|
+
Segment.new(
|
|
35
|
+
text: selected_text(segment, words),
|
|
36
|
+
start: [segment.start, range.begin].max,
|
|
37
|
+
end: [segment.end, range.end].min,
|
|
38
|
+
confidence: segment.confidence,
|
|
39
|
+
speaker: segment.speaker,
|
|
40
|
+
words: words
|
|
41
|
+
)
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
def selected_words(words)
|
|
45
|
+
words.select { |word| overlaps?(word) }
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def selected_text(segment, words)
|
|
49
|
+
return words.map(&:text).join(" ") if words.any?
|
|
50
|
+
|
|
51
|
+
segment.text
|
|
52
|
+
end
|
|
53
|
+
|
|
54
|
+
def overlaps?(timed_item)
|
|
55
|
+
timed_item.start < range.end && timed_item.end > range.begin
|
|
56
|
+
end
|
|
57
|
+
end
|
|
58
|
+
end
|
|
59
|
+
end
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Substrate
|
|
4
|
+
module UrlResolvers
|
|
5
|
+
class Generic < Command
|
|
6
|
+
def initialize(url:)
|
|
7
|
+
@url = url
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
def call
|
|
11
|
+
result = Nous.fetch(url, details: true)
|
|
12
|
+
page = result.pages.first
|
|
13
|
+
|
|
14
|
+
return success(payload: []) unless page
|
|
15
|
+
|
|
16
|
+
metadata = build_metadata(page)
|
|
17
|
+
article = build_article(page, metadata)
|
|
18
|
+
candidate = build_candidate(article, page, metadata)
|
|
19
|
+
|
|
20
|
+
success(payload: [candidate])
|
|
21
|
+
rescue
|
|
22
|
+
success(payload: [])
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
private
|
|
26
|
+
|
|
27
|
+
attr_reader :url
|
|
28
|
+
|
|
29
|
+
def build_metadata(page)
|
|
30
|
+
Metadata.new(
|
|
31
|
+
requested_url: page.metadata[:requested_url],
|
|
32
|
+
final_url: page.url,
|
|
33
|
+
redirected: page.metadata[:redirected],
|
|
34
|
+
content_type: page.metadata[:content_type],
|
|
35
|
+
extractor: page.metadata[:extractor]
|
|
36
|
+
)
|
|
37
|
+
end
|
|
38
|
+
|
|
39
|
+
def build_article(page, metadata)
|
|
40
|
+
Sources::Article.new(
|
|
41
|
+
url: url,
|
|
42
|
+
text: page.content,
|
|
43
|
+
title: page.title,
|
|
44
|
+
metadata: metadata
|
|
45
|
+
)
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def build_candidate(article, page, metadata)
|
|
49
|
+
UrlCandidate.new(
|
|
50
|
+
id: candidate_id(url, page),
|
|
51
|
+
kind: :article,
|
|
52
|
+
source: article,
|
|
53
|
+
rank: 1,
|
|
54
|
+
confidence: confidence_for(page),
|
|
55
|
+
label: "Article",
|
|
56
|
+
metadata: metadata
|
|
57
|
+
)
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
def candidate_id(url, page)
|
|
61
|
+
Digest::MD5.hexdigest("#{url}:#{page.title}")
|
|
62
|
+
end
|
|
63
|
+
|
|
64
|
+
def confidence_for(page)
|
|
65
|
+
return 0.5 unless page.title && page.content
|
|
66
|
+
|
|
67
|
+
(page.title.empty? || page.content.empty?) ? 0.5 : 0.8
|
|
68
|
+
end
|
|
69
|
+
end
|
|
70
|
+
end
|
|
71
|
+
end
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "uri"
|
|
4
|
+
|
|
5
|
+
module Substrate
|
|
6
|
+
module UrlResolvers
|
|
7
|
+
class ResolverFor < Command
|
|
8
|
+
class ResolutionError < StandardError; end
|
|
9
|
+
|
|
10
|
+
def initialize(url:)
|
|
11
|
+
@url = url
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
def call
|
|
15
|
+
resolver = resolver_for(uri)
|
|
16
|
+
result = resolver.call(url: url)
|
|
17
|
+
raise ResolutionError, result.error.message unless result.success?
|
|
18
|
+
|
|
19
|
+
success(payload: result.payload)
|
|
20
|
+
end
|
|
21
|
+
|
|
22
|
+
private
|
|
23
|
+
|
|
24
|
+
attr_reader :url
|
|
25
|
+
|
|
26
|
+
def uri
|
|
27
|
+
@uri ||= URI.parse(url)
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
def resolver_for(_uri)
|
|
31
|
+
Generic
|
|
32
|
+
end
|
|
33
|
+
end
|
|
34
|
+
end
|
|
35
|
+
end
|
data/lib/substrate/version.rb
CHANGED
data/lib/substrate.rb
CHANGED
|
@@ -1,8 +1,21 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
require "zeitwerk"
|
|
4
|
+
require "digest"
|
|
5
|
+
require "nous"
|
|
6
|
+
require "uri"
|
|
4
7
|
|
|
5
8
|
module Substrate
|
|
6
|
-
class
|
|
7
|
-
|
|
9
|
+
class << self
|
|
10
|
+
def loader
|
|
11
|
+
@loader ||= begin
|
|
12
|
+
loader = Zeitwerk::Loader.for_gem
|
|
13
|
+
loader.inflector.inflect("pdf" => "Pdf")
|
|
14
|
+
loader.collapse("#{__dir__}/substrate/primitives")
|
|
15
|
+
loader
|
|
16
|
+
end
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
loader.setup
|
|
8
21
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: substrate
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Dan Frenette
|
|
@@ -9,8 +9,36 @@ bindir: bin
|
|
|
9
9
|
cert_chain: []
|
|
10
10
|
date: 1980-01-02 00:00:00.000000000 Z
|
|
11
11
|
dependencies:
|
|
12
|
+
- !ruby/object:Gem::Dependency
|
|
13
|
+
name: faraday
|
|
14
|
+
requirement: !ruby/object:Gem::Requirement
|
|
15
|
+
requirements:
|
|
16
|
+
- - ">="
|
|
17
|
+
- !ruby/object:Gem::Version
|
|
18
|
+
version: '0'
|
|
19
|
+
type: :runtime
|
|
20
|
+
prerelease: false
|
|
21
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
22
|
+
requirements:
|
|
23
|
+
- - ">="
|
|
24
|
+
- !ruby/object:Gem::Version
|
|
25
|
+
version: '0'
|
|
12
26
|
- !ruby/object:Gem::Dependency
|
|
13
27
|
name: hexapdf
|
|
28
|
+
requirement: !ruby/object:Gem::Requirement
|
|
29
|
+
requirements:
|
|
30
|
+
- - "~>"
|
|
31
|
+
- !ruby/object:Gem::Version
|
|
32
|
+
version: 1.11.1
|
|
33
|
+
type: :runtime
|
|
34
|
+
prerelease: false
|
|
35
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
36
|
+
requirements:
|
|
37
|
+
- - "~>"
|
|
38
|
+
- !ruby/object:Gem::Version
|
|
39
|
+
version: 1.11.1
|
|
40
|
+
- !ruby/object:Gem::Dependency
|
|
41
|
+
name: marcel
|
|
14
42
|
requirement: !ruby/object:Gem::Requirement
|
|
15
43
|
requirements:
|
|
16
44
|
- - ">="
|
|
@@ -23,6 +51,20 @@ dependencies:
|
|
|
23
51
|
- - ">="
|
|
24
52
|
- !ruby/object:Gem::Version
|
|
25
53
|
version: '0'
|
|
54
|
+
- !ruby/object:Gem::Dependency
|
|
55
|
+
name: nous
|
|
56
|
+
requirement: !ruby/object:Gem::Requirement
|
|
57
|
+
requirements:
|
|
58
|
+
- - "~>"
|
|
59
|
+
- !ruby/object:Gem::Version
|
|
60
|
+
version: 0.5.0
|
|
61
|
+
type: :runtime
|
|
62
|
+
prerelease: false
|
|
63
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
64
|
+
requirements:
|
|
65
|
+
- - "~>"
|
|
66
|
+
- !ruby/object:Gem::Version
|
|
67
|
+
version: 0.5.0
|
|
26
68
|
- !ruby/object:Gem::Dependency
|
|
27
69
|
name: zeitwerk
|
|
28
70
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -42,6 +84,69 @@ extensions: []
|
|
|
42
84
|
extra_rdoc_files: []
|
|
43
85
|
files:
|
|
44
86
|
- lib/substrate.rb
|
|
87
|
+
- lib/substrate/classify.rb
|
|
88
|
+
- lib/substrate/cli/availability.rb
|
|
89
|
+
- lib/substrate/cli/error.rb
|
|
90
|
+
- lib/substrate/cli/runner.rb
|
|
91
|
+
- lib/substrate/command.rb
|
|
92
|
+
- lib/substrate/configuration.rb
|
|
93
|
+
- lib/substrate/detection/path_resolver.rb
|
|
94
|
+
- lib/substrate/distill.rb
|
|
95
|
+
- lib/substrate/extract_pdf.rb
|
|
96
|
+
- lib/substrate/handlers/article.rb
|
|
97
|
+
- lib/substrate/handlers/pdf.rb
|
|
98
|
+
- lib/substrate/handlers/raw_text.rb
|
|
99
|
+
- lib/substrate/handlers/text_file.rb
|
|
100
|
+
- lib/substrate/handlers/transcript.rb
|
|
101
|
+
- lib/substrate/mediums/pdf/chapter.rb
|
|
102
|
+
- lib/substrate/mediums/pdf/content.rb
|
|
103
|
+
- lib/substrate/mediums/pdf/destination.rb
|
|
104
|
+
- lib/substrate/mediums/pdf/destination_resolver.rb
|
|
105
|
+
- lib/substrate/mediums/pdf/document.rb
|
|
106
|
+
- lib/substrate/mediums/pdf/encrypted_pdf.rb
|
|
107
|
+
- lib/substrate/mediums/pdf/entry.rb
|
|
108
|
+
- lib/substrate/mediums/pdf/invalid_pdf.rb
|
|
109
|
+
- lib/substrate/mediums/pdf/invalid_text.rb
|
|
110
|
+
- lib/substrate/mediums/pdf/limit_exceeded.rb
|
|
111
|
+
- lib/substrate/mediums/pdf/limits.rb
|
|
112
|
+
- lib/substrate/mediums/pdf/named_destinations.rb
|
|
113
|
+
- lib/substrate/mediums/pdf/no_selectable_text.rb
|
|
114
|
+
- lib/substrate/mediums/pdf/outline.rb
|
|
115
|
+
- lib/substrate/mediums/pdf/outline_facts.rb
|
|
116
|
+
- lib/substrate/mediums/pdf/outline_parser.rb
|
|
117
|
+
- lib/substrate/mediums/pdf/page.rb
|
|
118
|
+
- lib/substrate/mediums/pdf/page_extractor.rb
|
|
119
|
+
- lib/substrate/mediums/pdf/reader.rb
|
|
120
|
+
- lib/substrate/mediums/pdf/text_extractor.rb
|
|
121
|
+
- lib/substrate/primitives/article_content.rb
|
|
122
|
+
- lib/substrate/primitives/extraction.rb
|
|
123
|
+
- lib/substrate/primitives/metadata.rb
|
|
124
|
+
- lib/substrate/primitives/page_collection.rb
|
|
125
|
+
- lib/substrate/primitives/pdf_file.rb
|
|
126
|
+
- lib/substrate/primitives/raw_text.rb
|
|
127
|
+
- lib/substrate/primitives/source.rb
|
|
128
|
+
- lib/substrate/primitives/text_content.rb
|
|
129
|
+
- lib/substrate/primitives/text_file.rb
|
|
130
|
+
- lib/substrate/primitives/transcripts/content.rb
|
|
131
|
+
- lib/substrate/primitives/transcripts/metadata.rb
|
|
132
|
+
- lib/substrate/primitives/transcripts/segment.rb
|
|
133
|
+
- lib/substrate/primitives/transcripts/word.rb
|
|
134
|
+
- lib/substrate/primitives/url_candidate.rb
|
|
135
|
+
- lib/substrate/source_ref.rb
|
|
136
|
+
- lib/substrate/sources/article.rb
|
|
137
|
+
- lib/substrate/sources/audio.rb
|
|
138
|
+
- lib/substrate/sources/pdf.rb
|
|
139
|
+
- lib/substrate/sources/text.rb
|
|
140
|
+
- lib/substrate/sources/url.rb
|
|
141
|
+
- lib/substrate/transcribers/deepgram.rb
|
|
142
|
+
- lib/substrate/transcribers/deepgram/client.rb
|
|
143
|
+
- lib/substrate/transcribers/deepgram/configuration.rb
|
|
144
|
+
- lib/substrate/transcribers/deepgram/response_parser.rb
|
|
145
|
+
- lib/substrate/transcribers/whisper_cpp.rb
|
|
146
|
+
- lib/substrate/transcribers/whisper_cpp/response_parser.rb
|
|
147
|
+
- lib/substrate/transcripts/select_time_range.rb
|
|
148
|
+
- lib/substrate/url_resolvers/generic.rb
|
|
149
|
+
- lib/substrate/url_resolvers/resolver_for.rb
|
|
45
150
|
- lib/substrate/version.rb
|
|
46
151
|
licenses: []
|
|
47
152
|
metadata: {}
|