html-to-markdown 3.8.2 → 3.8.3
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 +2 -14
- data/ext/html_to_markdown_rb/Cargo.toml +1 -1
- data/ext/html_to_markdown_rb/native/Cargo.lock +9 -18
- data/ext/html_to_markdown_rb/native/Cargo.toml +3 -5
- data/ext/html_to_markdown_rb/src/lib.rs +9 -1
- data/lib/html_to_markdown/native.rb +1 -1
- data/lib/html_to_markdown/version.rb +2 -2
- data/lib/html_to_markdown.rb +1 -1
- data/lib/html_to_markdown_rb.so +0 -0
- data/sig/types.rbs +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: d2e976c66a01c55fddf84ad733b5e93887614298101080abc65e138f171b6227
|
|
4
|
+
data.tar.gz: 53ed46b395b9c1a48d5f54d9377ed6ee2964b77619efd2e683688391130c3cc4
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 7ddd0e474135f08b95260aee8f97e0312c50d599f353c4fa2b5a21b6d929306b533615df218e8db96bc7e24ddbb77067708c78a6662c320cd4271375aa26559a
|
|
7
|
+
data.tar.gz: 6d5412be2e8a0d6dab84064b7c9f0e7cfb7cacefd0e0a9314cf755d3e7d4e4a65d0a808f7cbc372750eaf37037551414e0d75d0eb3ce200255be81b93814ce80
|
data/README.md
CHANGED
|
@@ -111,23 +111,11 @@ Requires Ruby 3.2+ with Magnus native extension bindings. Published for Linux, m
|
|
|
111
111
|
|
|
112
112
|
Basic conversion:
|
|
113
113
|
|
|
114
|
-
|
|
115
|
-
require 'html_to_markdown'
|
|
116
|
-
|
|
117
|
-
html = "<h1>Hello</h1><p>This is <strong>fast</strong>!</p>"
|
|
118
|
-
result = HtmlToMarkdown.convert(html)
|
|
119
|
-
markdown = result[:content]
|
|
120
|
-
```
|
|
114
|
+
<!-- snippet not found: getting-started/basic_usage.md -->
|
|
121
115
|
|
|
122
116
|
With conversion options:
|
|
123
117
|
|
|
124
|
-
|
|
125
|
-
require 'html_to_markdown'
|
|
126
|
-
|
|
127
|
-
html = "<h1>Hello</h1><p>This is <strong>fast</strong>!</p>"
|
|
128
|
-
result = HtmlToMarkdown.convert(html, heading_style: :atx, code_block_style: :fenced)
|
|
129
|
-
markdown = result[:content]
|
|
130
|
-
```
|
|
118
|
+
<!-- snippet not found: getting-started/with_options.md -->
|
|
131
119
|
|
|
132
120
|
## Architecture
|
|
133
121
|
|
|
@@ -254,16 +254,13 @@ dependencies = [
|
|
|
254
254
|
|
|
255
255
|
[[package]]
|
|
256
256
|
name = "html-escape"
|
|
257
|
-
version = "0.2.
|
|
257
|
+
version = "0.2.14"
|
|
258
258
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
259
|
-
checksum = "
|
|
260
|
-
dependencies = [
|
|
261
|
-
"utf8-width",
|
|
262
|
-
]
|
|
259
|
+
checksum = "46c1ff2d1cbf39efe5af0900ced8a069b5e61557a17544eb0c4a50239937389e"
|
|
263
260
|
|
|
264
261
|
[[package]]
|
|
265
262
|
name = "html-to-markdown-rb"
|
|
266
|
-
version = "3.8.
|
|
263
|
+
version = "3.8.3"
|
|
267
264
|
dependencies = [
|
|
268
265
|
"async-trait",
|
|
269
266
|
"html-to-markdown-rs",
|
|
@@ -276,9 +273,9 @@ dependencies = [
|
|
|
276
273
|
|
|
277
274
|
[[package]]
|
|
278
275
|
name = "html-to-markdown-rs"
|
|
279
|
-
version = "3.8.
|
|
276
|
+
version = "3.8.3"
|
|
280
277
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
281
|
-
checksum = "
|
|
278
|
+
checksum = "c5b47de513bfcc3312a7521bd52ca1a287b0f85614d839c23b9873ff5c1465b7"
|
|
282
279
|
dependencies = [
|
|
283
280
|
"ahash",
|
|
284
281
|
"astral-tl",
|
|
@@ -432,9 +429,9 @@ dependencies = [
|
|
|
432
429
|
|
|
433
430
|
[[package]]
|
|
434
431
|
name = "memchr"
|
|
435
|
-
version = "2.8.
|
|
432
|
+
version = "2.8.3"
|
|
436
433
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
437
|
-
checksum = "
|
|
434
|
+
checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
|
|
438
435
|
|
|
439
436
|
[[package]]
|
|
440
437
|
name = "minimal-lexical"
|
|
@@ -694,9 +691,9 @@ dependencies = [
|
|
|
694
691
|
|
|
695
692
|
[[package]]
|
|
696
693
|
name = "regex"
|
|
697
|
-
version = "1.
|
|
694
|
+
version = "1.13.0"
|
|
698
695
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
699
|
-
checksum = "
|
|
696
|
+
checksum = "2a0e75113e14dc5acb068cd0786884f214f1312650a3d36d269f5c4f3cdee8a2"
|
|
700
697
|
dependencies = [
|
|
701
698
|
"aho-corasick",
|
|
702
699
|
"memchr",
|
|
@@ -907,12 +904,6 @@ version = "0.7.6"
|
|
|
907
904
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
908
905
|
checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
|
|
909
906
|
|
|
910
|
-
[[package]]
|
|
911
|
-
name = "utf8-width"
|
|
912
|
-
version = "0.1.8"
|
|
913
|
-
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
914
|
-
checksum = "1292c0d970b54115d14f2492fe0170adf21d68a1de108eebc51c1df4f346a091"
|
|
915
|
-
|
|
916
907
|
[[package]]
|
|
917
908
|
name = "version_check"
|
|
918
909
|
version = "0.9.5"
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[package]
|
|
2
2
|
name = "html-to-markdown-rb"
|
|
3
|
-
version = "3.8.
|
|
3
|
+
version = "3.8.3"
|
|
4
4
|
edition = "2024"
|
|
5
5
|
license = "MIT"
|
|
6
6
|
description = "High-performance HTML to Markdown converter"
|
|
@@ -9,9 +9,7 @@ keywords = ["converter", "html", "markdown"]
|
|
|
9
9
|
categories = []
|
|
10
10
|
|
|
11
11
|
[package.metadata.cargo-machete]
|
|
12
|
-
|
|
13
|
-
# shim has no direct callsite (same rationale as the pyo3 crate).
|
|
14
|
-
ignored = ["rb-sys", "async-trait", "tokio"]
|
|
12
|
+
ignored = ["async-trait", "rb-sys", "tokio"]
|
|
15
13
|
|
|
16
14
|
[lib]
|
|
17
15
|
name = "html_to_markdown_rb"
|
|
@@ -27,7 +25,7 @@ visitor = ["html-to-markdown-rs/visitor"]
|
|
|
27
25
|
|
|
28
26
|
[dependencies]
|
|
29
27
|
async-trait = "0.1"
|
|
30
|
-
html-to-markdown-rs = { version = "3.8.
|
|
28
|
+
html-to-markdown-rs = { version = "3.8.3", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
|
|
31
29
|
magnus = "0.8"
|
|
32
30
|
rb-sys = ">=0.9, <0.9.128"
|
|
33
31
|
serde = { version = "1", features = ["derive"] }
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
// This file is auto-generated by alef. DO NOT EDIT.
|
|
2
|
-
// alef:hash:
|
|
2
|
+
// alef:hash:22cbc7728e7527feef8e06cb67ad8290c07e3c276a312d04d887bbecdf8f6101
|
|
3
3
|
// Re-generate with: alef generate
|
|
4
4
|
#![allow(dead_code, unused_imports, unused_variables)]
|
|
5
5
|
#![allow(
|
|
@@ -5590,6 +5590,7 @@ impl html_to_markdown_rs::visitor::HtmlVisitor for RbHtmlVisitorBridge {
|
|
|
5590
5590
|
}
|
|
5591
5591
|
}
|
|
5592
5592
|
|
|
5593
|
+
#[allow(clippy::needless_update)]
|
|
5593
5594
|
#[allow(clippy::redundant_closure, clippy::useless_conversion)]
|
|
5594
5595
|
impl From<DocumentMetadata> for html_to_markdown_rs::metadata::DocumentMetadata {
|
|
5595
5596
|
fn from(val: DocumentMetadata) -> Self {
|
|
@@ -5609,6 +5610,7 @@ impl From<DocumentMetadata> for html_to_markdown_rs::metadata::DocumentMetadata
|
|
|
5609
5610
|
.map(|(k, v)| (k.into(), v.into()))
|
|
5610
5611
|
.collect(),
|
|
5611
5612
|
meta_tags: val.meta_tags.into_iter().map(|(k, v)| (k.into(), v.into())).collect(),
|
|
5613
|
+
..Default::default()
|
|
5612
5614
|
}
|
|
5613
5615
|
}
|
|
5614
5616
|
}
|
|
@@ -5740,6 +5742,7 @@ impl From<html_to_markdown_rs::metadata::StructuredData> for StructuredData {
|
|
|
5740
5742
|
}
|
|
5741
5743
|
}
|
|
5742
5744
|
|
|
5745
|
+
#[allow(clippy::needless_update)]
|
|
5743
5746
|
#[allow(clippy::redundant_closure, clippy::useless_conversion)]
|
|
5744
5747
|
impl From<HtmlMetadata> for html_to_markdown_rs::metadata::HtmlMetadata {
|
|
5745
5748
|
fn from(val: HtmlMetadata) -> Self {
|
|
@@ -5749,6 +5752,7 @@ impl From<HtmlMetadata> for html_to_markdown_rs::metadata::HtmlMetadata {
|
|
|
5749
5752
|
links: val.links.into_iter().map(Into::into).collect(),
|
|
5750
5753
|
images: val.images.into_iter().map(Into::into).collect(),
|
|
5751
5754
|
structured_data: val.structured_data.into_iter().map(Into::into).collect(),
|
|
5755
|
+
..Default::default()
|
|
5752
5756
|
}
|
|
5753
5757
|
}
|
|
5754
5758
|
}
|
|
@@ -5921,6 +5925,7 @@ impl From<html_to_markdown_rs::options::ConversionOptionsUpdate> for ConversionO
|
|
|
5921
5925
|
}
|
|
5922
5926
|
}
|
|
5923
5927
|
|
|
5928
|
+
#[allow(clippy::needless_update)]
|
|
5924
5929
|
#[allow(clippy::redundant_closure, clippy::useless_conversion)]
|
|
5925
5930
|
impl From<PreprocessingOptions> for html_to_markdown_rs::options::PreprocessingOptions {
|
|
5926
5931
|
fn from(val: PreprocessingOptions) -> Self {
|
|
@@ -5929,6 +5934,7 @@ impl From<PreprocessingOptions> for html_to_markdown_rs::options::PreprocessingO
|
|
|
5929
5934
|
preset: val.preset.into(),
|
|
5930
5935
|
remove_navigation: val.remove_navigation,
|
|
5931
5936
|
remove_forms: val.remove_forms,
|
|
5937
|
+
..Default::default()
|
|
5932
5938
|
}
|
|
5933
5939
|
}
|
|
5934
5940
|
}
|
|
@@ -6099,6 +6105,7 @@ impl From<html_to_markdown_rs::ConversionResult> for ConversionResult {
|
|
|
6099
6105
|
}
|
|
6100
6106
|
}
|
|
6101
6107
|
|
|
6108
|
+
#[allow(clippy::needless_update)]
|
|
6102
6109
|
#[allow(clippy::redundant_closure, clippy::useless_conversion)]
|
|
6103
6110
|
impl From<TableGrid> for html_to_markdown_rs::TableGrid {
|
|
6104
6111
|
fn from(val: TableGrid) -> Self {
|
|
@@ -6106,6 +6113,7 @@ impl From<TableGrid> for html_to_markdown_rs::TableGrid {
|
|
|
6106
6113
|
rows: val.rows,
|
|
6107
6114
|
cols: val.cols,
|
|
6108
6115
|
cells: val.cells.into_iter().map(Into::into).collect(),
|
|
6116
|
+
..Default::default()
|
|
6109
6117
|
}
|
|
6110
6118
|
}
|
|
6111
6119
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:22cbc7728e7527feef8e06cb67ad8290c07e3c276a312d04d887bbecdf8f6101
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify --exit-code
|
|
5
5
|
# frozen_string_literal: true
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:22cbc7728e7527feef8e06cb67ad8290c07e3c276a312d04d887bbecdf8f6101
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify --exit-code
|
|
5
5
|
# frozen_string_literal: true
|
|
6
6
|
|
|
7
7
|
module HtmlToMarkdown
|
|
8
8
|
## The version string for this package.
|
|
9
|
-
VERSION = "3.8.
|
|
9
|
+
VERSION = "3.8.3"
|
|
10
10
|
end
|
data/lib/html_to_markdown.rb
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:22cbc7728e7527feef8e06cb67ad8290c07e3c276a312d04d887bbecdf8f6101
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify --exit-code
|
|
5
5
|
# frozen_string_literal: true
|
data/lib/html_to_markdown_rb.so
CHANGED
|
Binary file
|
data/sig/types.rbs
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:22cbc7728e7527feef8e06cb67ad8290c07e3c276a312d04d887bbecdf8f6101
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify --exit-code
|
|
5
5
|
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: html-to-markdown
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 3.8.
|
|
4
|
+
version: 3.8.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Na'aman Hirschfeld <naaman@xberg.io>
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-07-
|
|
11
|
+
date: 2026-07-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rb_sys
|