html-to-markdown 2.5.6-x86_64-linux → 2.29.0-x86_64-linux
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/.bundle/config +2 -0
- data/.gitignore +3 -0
- data/.rubocop.yml +29 -0
- data/Gemfile +17 -0
- data/Gemfile.lock +223 -0
- data/README.md +271 -133
- data/Rakefile +32 -0
- data/Steepfile +26 -0
- data/bin/benchmark.rb +232 -0
- data/html-to-markdown-rb.gemspec +99 -0
- data/lib/html_to_markdown/cli_proxy.rb +7 -4
- data/lib/html_to_markdown/version.rb +1 -1
- data/lib/html_to_markdown.rb +190 -3
- data/lib/html_to_markdown_rb.so +0 -0
- data/sig/html_to_markdown/cli.rbs +24 -0
- data/sig/html_to_markdown/cli_proxy.rbs +48 -0
- data/sig/html_to_markdown.rbs +498 -0
- data/sig/open3.rbs +12 -0
- data/spec/convert_spec.rb +48 -0
- data/spec/convert_with_tables_spec.rb +194 -0
- data/spec/metadata_extraction_spec.rb +437 -0
- data/spec/visitor_issue_187_spec.rb +605 -0
- data/spec/visitor_spec.rb +1149 -0
- metadata +29 -89
- data/lib/bin/html-to-markdown +0 -0
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 49299fdb1105ea4dbec8393ac879dd0f8928064543f6c4ff743aa82e94d63f88
|
|
4
|
+
data.tar.gz: 9896cb02971863cb1e99ba5e84bbba8419b16b0edf50496f23db7d6ba6138fc1
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: fb71dbe83523eff32aa73642276468f7f2fe5fc8707f339c39097ad9946b6da5924930e1515986dbb3c1b091b58e1f9e4bf71805bc9d2890bf8678b7d0ae08bf
|
|
7
|
+
data.tar.gz: ed4c79f974c170565c46b7ef836d3f11e4e4826d8b9cc98dce76f7f9792a12d5090c377f00a981cb3b10a3020ca6cbe6cb103c343ca646a2ea66e56fbbec0199
|
data/.bundle/config
ADDED
data/.gitignore
ADDED
data/.rubocop.yml
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
plugins:
|
|
2
|
+
- rubocop-rspec
|
|
3
|
+
|
|
4
|
+
AllCops:
|
|
5
|
+
NewCops: enable
|
|
6
|
+
TargetRubyVersion: 3.2
|
|
7
|
+
Exclude:
|
|
8
|
+
- "tmp/**/*"
|
|
9
|
+
- "vendor/**/*"
|
|
10
|
+
|
|
11
|
+
Style/Documentation:
|
|
12
|
+
Enabled: false
|
|
13
|
+
|
|
14
|
+
Metrics/BlockLength:
|
|
15
|
+
Exclude:
|
|
16
|
+
- "spec/**/*"
|
|
17
|
+
- "*.gemspec"
|
|
18
|
+
|
|
19
|
+
Metrics/MethodLength:
|
|
20
|
+
Max: 15
|
|
21
|
+
|
|
22
|
+
RSpec/MultipleExpectations:
|
|
23
|
+
Enabled: false
|
|
24
|
+
|
|
25
|
+
RSpec/ExampleLength:
|
|
26
|
+
Enabled: false
|
|
27
|
+
|
|
28
|
+
RSpec/SpecFilePathFormat:
|
|
29
|
+
Enabled: false
|
data/Gemfile
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
source 'https://rubygems.org'
|
|
4
|
+
|
|
5
|
+
ruby '>= 3.2'
|
|
6
|
+
|
|
7
|
+
gemspec
|
|
8
|
+
|
|
9
|
+
group :development, :test do
|
|
10
|
+
gem 'rake-compiler'
|
|
11
|
+
gem 'rbs', require: false
|
|
12
|
+
gem 'rb_sys' # provides build tooling when developing locally
|
|
13
|
+
gem 'rspec'
|
|
14
|
+
gem 'rubocop', require: false
|
|
15
|
+
gem 'rubocop-rspec', require: false
|
|
16
|
+
gem 'steep', require: false
|
|
17
|
+
end
|
data/Gemfile.lock
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
1
|
+
PATH
|
|
2
|
+
remote: .
|
|
3
|
+
specs:
|
|
4
|
+
html-to-markdown (2.29.0)
|
|
5
|
+
rb_sys (>= 0.9, < 1.0)
|
|
6
|
+
|
|
7
|
+
GEM
|
|
8
|
+
remote: https://rubygems.org/
|
|
9
|
+
specs:
|
|
10
|
+
activesupport (8.1.2)
|
|
11
|
+
base64
|
|
12
|
+
bigdecimal
|
|
13
|
+
concurrent-ruby (~> 1.0, >= 1.3.1)
|
|
14
|
+
connection_pool (>= 2.2.5)
|
|
15
|
+
drb
|
|
16
|
+
i18n (>= 1.6, < 2)
|
|
17
|
+
json
|
|
18
|
+
logger (>= 1.4.2)
|
|
19
|
+
minitest (>= 5.1)
|
|
20
|
+
securerandom (>= 0.3)
|
|
21
|
+
tzinfo (~> 2.0, >= 2.0.5)
|
|
22
|
+
uri (>= 0.13.1)
|
|
23
|
+
addressable (2.8.9)
|
|
24
|
+
public_suffix (>= 2.0.2, < 8.0)
|
|
25
|
+
ast (2.4.3)
|
|
26
|
+
base64 (0.3.0)
|
|
27
|
+
bigdecimal (4.0.1)
|
|
28
|
+
concurrent-ruby (1.3.6)
|
|
29
|
+
connection_pool (3.0.2)
|
|
30
|
+
csv (3.3.5)
|
|
31
|
+
diff-lcs (1.6.2)
|
|
32
|
+
drb (2.2.3)
|
|
33
|
+
ffi (1.17.3-aarch64-linux-gnu)
|
|
34
|
+
ffi (1.17.3-arm64-darwin)
|
|
35
|
+
ffi (1.17.3-x64-mingw-ucrt)
|
|
36
|
+
ffi (1.17.3-x86_64-darwin)
|
|
37
|
+
ffi (1.17.3-x86_64-linux-gnu)
|
|
38
|
+
fileutils (1.8.0)
|
|
39
|
+
i18n (1.14.8)
|
|
40
|
+
concurrent-ruby (~> 1.0)
|
|
41
|
+
json (2.19.2)
|
|
42
|
+
json-schema (6.2.0)
|
|
43
|
+
addressable (~> 2.8)
|
|
44
|
+
bigdecimal (>= 3.1, < 5)
|
|
45
|
+
language_server-protocol (3.17.0.5)
|
|
46
|
+
lint_roller (1.1.0)
|
|
47
|
+
listen (3.10.0)
|
|
48
|
+
logger
|
|
49
|
+
rb-fsevent (~> 0.10, >= 0.10.3)
|
|
50
|
+
rb-inotify (~> 0.9, >= 0.9.10)
|
|
51
|
+
logger (1.7.0)
|
|
52
|
+
mcp (0.9.0)
|
|
53
|
+
json-schema (>= 4.1)
|
|
54
|
+
minitest (6.0.2)
|
|
55
|
+
drb (~> 2.0)
|
|
56
|
+
prism (~> 1.5)
|
|
57
|
+
mutex_m (0.3.0)
|
|
58
|
+
parallel (1.27.0)
|
|
59
|
+
parser (3.3.10.2)
|
|
60
|
+
ast (~> 2.4.1)
|
|
61
|
+
racc
|
|
62
|
+
prism (1.9.0)
|
|
63
|
+
public_suffix (7.0.5)
|
|
64
|
+
racc (1.8.1)
|
|
65
|
+
rainbow (3.1.1)
|
|
66
|
+
rake (13.3.1)
|
|
67
|
+
rake-compiler (1.3.1)
|
|
68
|
+
rake
|
|
69
|
+
rake-compiler-dock (1.11.0)
|
|
70
|
+
rb-fsevent (0.11.2)
|
|
71
|
+
rb-inotify (0.11.1)
|
|
72
|
+
ffi (~> 1.0)
|
|
73
|
+
rb_sys (0.9.124)
|
|
74
|
+
rake-compiler-dock (= 1.11.0)
|
|
75
|
+
rbs (3.10.3)
|
|
76
|
+
logger
|
|
77
|
+
tsort
|
|
78
|
+
regexp_parser (2.11.3)
|
|
79
|
+
rspec (3.13.2)
|
|
80
|
+
rspec-core (~> 3.13.0)
|
|
81
|
+
rspec-expectations (~> 3.13.0)
|
|
82
|
+
rspec-mocks (~> 3.13.0)
|
|
83
|
+
rspec-core (3.13.6)
|
|
84
|
+
rspec-support (~> 3.13.0)
|
|
85
|
+
rspec-expectations (3.13.5)
|
|
86
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
|
87
|
+
rspec-support (~> 3.13.0)
|
|
88
|
+
rspec-mocks (3.13.8)
|
|
89
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
|
90
|
+
rspec-support (~> 3.13.0)
|
|
91
|
+
rspec-support (3.13.7)
|
|
92
|
+
rubocop (1.85.1)
|
|
93
|
+
json (~> 2.3)
|
|
94
|
+
language_server-protocol (~> 3.17.0.2)
|
|
95
|
+
lint_roller (~> 1.1.0)
|
|
96
|
+
mcp (~> 0.6)
|
|
97
|
+
parallel (~> 1.10)
|
|
98
|
+
parser (>= 3.3.0.2)
|
|
99
|
+
rainbow (>= 2.2.2, < 4.0)
|
|
100
|
+
regexp_parser (>= 2.9.3, < 3.0)
|
|
101
|
+
rubocop-ast (>= 1.49.0, < 2.0)
|
|
102
|
+
ruby-progressbar (~> 1.7)
|
|
103
|
+
unicode-display_width (>= 2.4.0, < 4.0)
|
|
104
|
+
rubocop-ast (1.49.1)
|
|
105
|
+
parser (>= 3.3.7.2)
|
|
106
|
+
prism (~> 1.7)
|
|
107
|
+
rubocop-rspec (3.9.0)
|
|
108
|
+
lint_roller (~> 1.1)
|
|
109
|
+
rubocop (~> 1.81)
|
|
110
|
+
ruby-progressbar (1.13.0)
|
|
111
|
+
securerandom (0.4.1)
|
|
112
|
+
steep (1.10.0)
|
|
113
|
+
activesupport (>= 5.1)
|
|
114
|
+
concurrent-ruby (>= 1.1.10)
|
|
115
|
+
csv (>= 3.0.9)
|
|
116
|
+
fileutils (>= 1.1.0)
|
|
117
|
+
json (>= 2.1.0)
|
|
118
|
+
language_server-protocol (>= 3.17.0.4, < 4.0)
|
|
119
|
+
listen (~> 3.0)
|
|
120
|
+
logger (>= 1.3.0)
|
|
121
|
+
mutex_m (>= 0.3.0)
|
|
122
|
+
parser (>= 3.1)
|
|
123
|
+
rainbow (>= 2.2.2, < 4.0)
|
|
124
|
+
rbs (~> 3.9)
|
|
125
|
+
securerandom (>= 0.1)
|
|
126
|
+
strscan (>= 1.0.0)
|
|
127
|
+
terminal-table (>= 2, < 5)
|
|
128
|
+
uri (>= 0.12.0)
|
|
129
|
+
strscan (3.1.7)
|
|
130
|
+
terminal-table (4.0.0)
|
|
131
|
+
unicode-display_width (>= 1.1.1, < 4)
|
|
132
|
+
tsort (0.2.0)
|
|
133
|
+
tzinfo (2.0.6)
|
|
134
|
+
concurrent-ruby (~> 1.0)
|
|
135
|
+
unicode-display_width (3.2.0)
|
|
136
|
+
unicode-emoji (~> 4.1)
|
|
137
|
+
unicode-emoji (4.2.0)
|
|
138
|
+
uri (1.1.1)
|
|
139
|
+
|
|
140
|
+
PLATFORMS
|
|
141
|
+
aarch64-linux
|
|
142
|
+
arm64-darwin
|
|
143
|
+
x64-mingw-ucrt
|
|
144
|
+
x86_64-darwin
|
|
145
|
+
x86_64-linux
|
|
146
|
+
x86_64-linux-gnu
|
|
147
|
+
|
|
148
|
+
DEPENDENCIES
|
|
149
|
+
html-to-markdown!
|
|
150
|
+
rake-compiler
|
|
151
|
+
rb_sys
|
|
152
|
+
rbs
|
|
153
|
+
rspec
|
|
154
|
+
rubocop
|
|
155
|
+
rubocop-rspec
|
|
156
|
+
steep
|
|
157
|
+
|
|
158
|
+
CHECKSUMS
|
|
159
|
+
activesupport (8.1.2) sha256=88842578ccd0d40f658289b0e8c842acfe9af751afee2e0744a7873f50b6fdae
|
|
160
|
+
addressable (2.8.9) sha256=cc154fcbe689711808a43601dee7b980238ce54368d23e127421753e46895485
|
|
161
|
+
ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
|
|
162
|
+
base64 (0.3.0) sha256=27337aeabad6ffae05c265c450490628ef3ebd4b67be58257393227588f5a97b
|
|
163
|
+
bigdecimal (4.0.1) sha256=8b07d3d065a9f921c80ceaea7c9d4ae596697295b584c296fe599dd0ad01c4a7
|
|
164
|
+
concurrent-ruby (1.3.6) sha256=6b56837e1e7e5292f9864f34b69c5a2cbc75c0cf5338f1ce9903d10fa762d5ab
|
|
165
|
+
connection_pool (3.0.2) sha256=33fff5ba71a12d2aa26cb72b1db8bba2a1a01823559fb01d29eb74c286e62e0a
|
|
166
|
+
csv (3.3.5) sha256=6e5134ac3383ef728b7f02725d9872934f523cb40b961479f69cf3afa6c8e73f
|
|
167
|
+
diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
|
|
168
|
+
drb (2.2.3) sha256=0b00d6fdb50995fe4a45dea13663493c841112e4068656854646f418fda13373
|
|
169
|
+
ffi (1.17.3-aarch64-linux-gnu) sha256=28ad573df26560f0aedd8a90c3371279a0b2bd0b4e834b16a2baa10bd7a97068
|
|
170
|
+
ffi (1.17.3-arm64-darwin) sha256=0c690555d4cee17a7f07c04d59df39b2fba74ec440b19da1f685c6579bb0717f
|
|
171
|
+
ffi (1.17.3-x64-mingw-ucrt) sha256=5f1d7d067a9a1058ad183dba25b05557cd51c85fc1768c49338eabc1cf242d7c
|
|
172
|
+
ffi (1.17.3-x86_64-darwin) sha256=1f211811eb5cfaa25998322cdd92ab104bfbd26d1c4c08471599c511f2c00bb5
|
|
173
|
+
ffi (1.17.3-x86_64-linux-gnu) sha256=3746b01f677aae7b16dc1acb7cb3cc17b3e35bdae7676a3f568153fb0e2c887f
|
|
174
|
+
fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
|
|
175
|
+
html-to-markdown (2.29.0)
|
|
176
|
+
i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
|
|
177
|
+
json (2.19.2) sha256=e7e1bd318b2c37c4ceee2444841c86539bc462e81f40d134cf97826cb14e83cf
|
|
178
|
+
json-schema (6.2.0) sha256=e8bff46ed845a22c1ab2bd0d7eccf831c01fe23bb3920caa4c74db4306813666
|
|
179
|
+
language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
|
|
180
|
+
lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
|
|
181
|
+
listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
|
|
182
|
+
logger (1.7.0) sha256=196edec7cc44b66cfb40f9755ce11b392f21f7967696af15d274dde7edff0203
|
|
183
|
+
mcp (0.9.0) sha256=a0a3737b0ac9df0772f4ef7e2b013c260ddbcf217a5d50a66bff0baeddf03e47
|
|
184
|
+
minitest (6.0.2) sha256=db6e57956f6ecc6134683b4c87467d6dd792323c7f0eea7b93f66bd284adbc3d
|
|
185
|
+
mutex_m (0.3.0) sha256=cfcb04ac16b69c4813777022fdceda24e9f798e48092a2b817eb4c0a782b0751
|
|
186
|
+
parallel (1.27.0) sha256=4ac151e1806b755fb4e2dc2332cbf0e54f2e24ba821ff2d3dcf86bf6dc4ae130
|
|
187
|
+
parser (3.3.10.2) sha256=6f60c84aa4bdcedb6d1a2434b738fe8a8136807b6adc8f7f53b97da9bc4e9357
|
|
188
|
+
prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
|
|
189
|
+
public_suffix (7.0.5) sha256=1a8bb08f1bbea19228d3bed6e5ed908d1cb4f7c2726d18bd9cadf60bc676f623
|
|
190
|
+
racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
|
|
191
|
+
rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
|
|
192
|
+
rake (13.3.1) sha256=8c9e89d09f66a26a01264e7e3480ec0607f0c497a861ef16063604b1b08eb19c
|
|
193
|
+
rake-compiler (1.3.1) sha256=6b351612b6e2d73ddd5563ee799bb58685176e05363db6758504bd11573d670a
|
|
194
|
+
rake-compiler-dock (1.11.0) sha256=eab51f2cd533eb35cea6b624a75281f047123e70a64c58b607471bb49428f8c2
|
|
195
|
+
rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
|
|
196
|
+
rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
|
|
197
|
+
rb_sys (0.9.124) sha256=513476557b12eaf73764b3da9f8746024558fe8699bda785fb548c9aa3877ae7
|
|
198
|
+
rbs (3.10.3) sha256=70627f3919016134d554e6c99195552ae3ef6020fe034c8e983facc9c192daa6
|
|
199
|
+
regexp_parser (2.11.3) sha256=ca13f381a173b7a93450e53459075c9b76a10433caadcb2f1180f2c741fc55a4
|
|
200
|
+
rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
|
|
201
|
+
rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
|
|
202
|
+
rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
|
|
203
|
+
rspec-mocks (3.13.8) sha256=086ad3d3d17533f4237643de0b5c42f04b66348c28bf6b9c2d3f4a3b01af1d47
|
|
204
|
+
rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
|
|
205
|
+
rubocop (1.85.1) sha256=3dbcf9e961baa4c376eeeb2a03913dca5e3987033b04d38fa538aa1e7406cc77
|
|
206
|
+
rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
|
|
207
|
+
rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
|
|
208
|
+
ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
|
|
209
|
+
securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
|
|
210
|
+
steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
|
|
211
|
+
strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
|
|
212
|
+
terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2
|
|
213
|
+
tsort (0.2.0) sha256=9650a793f6859a43b6641671278f79cfead60ac714148aabe4e3f0060480089f
|
|
214
|
+
tzinfo (2.0.6) sha256=8daf828cc77bcf7d63b0e3bdb6caa47e2272dcfaf4fbfe46f8c3a9df087a829b
|
|
215
|
+
unicode-display_width (3.2.0) sha256=0cdd96b5681a5949cdbc2c55e7b420facae74c4aaf9a9815eee1087cb1853c42
|
|
216
|
+
unicode-emoji (4.2.0) sha256=519e69150f75652e40bf736106cfbc8f0f73aa3fb6a65afe62fefa7f80b0f80f
|
|
217
|
+
uri (1.1.1) sha256=379fa58d27ffb1387eaada68c749d1426738bd0f654d812fcc07e7568f5c57c6
|
|
218
|
+
|
|
219
|
+
RUBY VERSION
|
|
220
|
+
ruby 3.4.8
|
|
221
|
+
|
|
222
|
+
BUNDLED WITH
|
|
223
|
+
4.0.3
|