html-to-markdown 3.8.0 → 3.8.2
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/ext/html_to_markdown_rb/Cargo.lock +2 -2
- data/ext/html_to_markdown_rb/Cargo.toml +1 -1
- data/ext/html_to_markdown_rb/native/Cargo.lock +3 -3
- data/ext/html_to_markdown_rb/native/Cargo.toml +5 -3
- data/ext/html_to_markdown_rb/src/lib.rs +39 -153
- data/lib/html_to_markdown/native.rb +106 -49
- data/lib/html_to_markdown/version.rb +2 -2
- data/lib/html_to_markdown.rb +10 -1
- data/lib/html_to_markdown_rb.so +0 -0
- data/sig/html_to_markdown/cli.rbs +21 -21
- data/sig/html_to_markdown/cli_proxy.rbs +26 -26
- data/sig/open3.rbs +9 -9
- data/sig/types.rbs +264 -264
- 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: 1d7a7edd4a1918e284d760aadc529b9acfed9a591bdfdbf1f0fc0fd1b904c6ff
|
|
4
|
+
data.tar.gz: 81fe39786ff2525dd7e01e10c458d0ab8fe2300a3eb4df3ca0ea2acc04978736
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 6666a6669196bfe6f50f54d22837e9f952d78c8c5e622a2b36cc53ae420bbc24730e1f99c2823350d31f91b3191853d9e8ad32ddf443bf0e279637049a07b6a8
|
|
7
|
+
data.tar.gz: a4718bcfce1de0383652d97a6fea991629b6d0d07711f1c8d39a266641a6adf38b9527e7160a9e79c3d69038eb0dfd1ea51a5f8e897e5cb669274943594e95b4
|
|
@@ -252,7 +252,7 @@ dependencies = [
|
|
|
252
252
|
|
|
253
253
|
[[package]]
|
|
254
254
|
name = "html-to-markdown-rb"
|
|
255
|
-
version = "3.
|
|
255
|
+
version = "3.8.1"
|
|
256
256
|
dependencies = [
|
|
257
257
|
"html-to-markdown-rs",
|
|
258
258
|
"magnus",
|
|
@@ -262,7 +262,7 @@ dependencies = [
|
|
|
262
262
|
|
|
263
263
|
[[package]]
|
|
264
264
|
name = "html-to-markdown-rs"
|
|
265
|
-
version = "3.
|
|
265
|
+
version = "3.8.1"
|
|
266
266
|
dependencies = [
|
|
267
267
|
"ahash",
|
|
268
268
|
"astral-tl",
|
|
@@ -263,7 +263,7 @@ dependencies = [
|
|
|
263
263
|
|
|
264
264
|
[[package]]
|
|
265
265
|
name = "html-to-markdown-rb"
|
|
266
|
-
version = "3.8.
|
|
266
|
+
version = "3.8.1"
|
|
267
267
|
dependencies = [
|
|
268
268
|
"async-trait",
|
|
269
269
|
"html-to-markdown-rs",
|
|
@@ -276,9 +276,9 @@ dependencies = [
|
|
|
276
276
|
|
|
277
277
|
[[package]]
|
|
278
278
|
name = "html-to-markdown-rs"
|
|
279
|
-
version = "3.8.
|
|
279
|
+
version = "3.8.2"
|
|
280
280
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
281
|
-
checksum = "
|
|
281
|
+
checksum = "bfb98086035f41cf7bcdb6bd1dab14b118e53b035e003e268698a6003c413fa0"
|
|
282
282
|
dependencies = [
|
|
283
283
|
"ahash",
|
|
284
284
|
"astral-tl",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[package]
|
|
2
2
|
name = "html-to-markdown-rb"
|
|
3
|
-
version = "3.8.
|
|
3
|
+
version = "3.8.1"
|
|
4
4
|
edition = "2024"
|
|
5
5
|
license = "MIT"
|
|
6
6
|
description = "High-performance HTML to Markdown converter"
|
|
@@ -9,7 +9,9 @@ keywords = ["converter", "html", "markdown"]
|
|
|
9
9
|
categories = []
|
|
10
10
|
|
|
11
11
|
[package.metadata.cargo-machete]
|
|
12
|
-
|
|
12
|
+
# async-trait / tokio are declared for feature parity but the generated Magnus
|
|
13
|
+
# shim has no direct callsite (same rationale as the pyo3 crate).
|
|
14
|
+
ignored = ["rb-sys", "async-trait", "tokio"]
|
|
13
15
|
|
|
14
16
|
[lib]
|
|
15
17
|
name = "html_to_markdown_rb"
|
|
@@ -25,7 +27,7 @@ visitor = ["html-to-markdown-rs/visitor"]
|
|
|
25
27
|
|
|
26
28
|
[dependencies]
|
|
27
29
|
async-trait = "0.1"
|
|
28
|
-
html-to-markdown-rs = { version = "3.8.
|
|
30
|
+
html-to-markdown-rs = { version = "3.8.2", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
|
|
29
31
|
magnus = "0.8"
|
|
30
32
|
rb-sys = ">=0.9, <0.9.128"
|
|
31
33
|
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:df03cfa1ea58fc063ec7e305db2e9dcdc739bb4b063899fc4750f8584c5bd37e
|
|
3
3
|
// Re-generate with: alef generate
|
|
4
4
|
#![allow(dead_code, unused_imports, unused_variables)]
|
|
5
5
|
#![allow(
|
|
@@ -105,19 +105,7 @@ unsafe impl TryConvertOwned for DocumentMetadata {}
|
|
|
105
105
|
|
|
106
106
|
impl Default for DocumentMetadata {
|
|
107
107
|
fn default() -> Self {
|
|
108
|
-
|
|
109
|
-
title: None,
|
|
110
|
-
description: None,
|
|
111
|
-
keywords: vec![],
|
|
112
|
-
author: None,
|
|
113
|
-
canonical_url: None,
|
|
114
|
-
base_href: None,
|
|
115
|
-
language: None,
|
|
116
|
-
text_direction: None,
|
|
117
|
-
open_graph: Default::default(),
|
|
118
|
-
twitter_card: Default::default(),
|
|
119
|
-
meta_tags: Default::default(),
|
|
120
|
-
}
|
|
108
|
+
html_to_markdown_rs::metadata::DocumentMetadata::default().into()
|
|
121
109
|
}
|
|
122
110
|
}
|
|
123
111
|
|
|
@@ -634,13 +622,7 @@ unsafe impl TryConvertOwned for HtmlMetadata {}
|
|
|
634
622
|
|
|
635
623
|
impl Default for HtmlMetadata {
|
|
636
624
|
fn default() -> Self {
|
|
637
|
-
|
|
638
|
-
document: Default::default(),
|
|
639
|
-
headers: vec![],
|
|
640
|
-
links: vec![],
|
|
641
|
-
images: vec![],
|
|
642
|
-
structured_data: vec![],
|
|
643
|
-
}
|
|
625
|
+
html_to_markdown_rs::metadata::HtmlMetadata::default().into()
|
|
644
626
|
}
|
|
645
627
|
}
|
|
646
628
|
|
|
@@ -774,51 +756,7 @@ unsafe impl TryConvertOwned for ConversionOptions {}
|
|
|
774
756
|
|
|
775
757
|
impl Default for ConversionOptions {
|
|
776
758
|
fn default() -> Self {
|
|
777
|
-
|
|
778
|
-
heading_style: Default::default(),
|
|
779
|
-
list_indent_type: Default::default(),
|
|
780
|
-
list_indent_width: 2,
|
|
781
|
-
bullets: "-*+".to_string(),
|
|
782
|
-
strong_em_symbol: "*".to_string(),
|
|
783
|
-
escape_asterisks: false,
|
|
784
|
-
escape_underscores: false,
|
|
785
|
-
escape_misc: false,
|
|
786
|
-
escape_ascii: false,
|
|
787
|
-
code_language: "".to_string(),
|
|
788
|
-
autolinks: true,
|
|
789
|
-
default_title: false,
|
|
790
|
-
br_in_tables: false,
|
|
791
|
-
compact_tables: false,
|
|
792
|
-
highlight_style: Default::default(),
|
|
793
|
-
extract_metadata: true,
|
|
794
|
-
whitespace_mode: Default::default(),
|
|
795
|
-
strip_newlines: false,
|
|
796
|
-
wrap: false,
|
|
797
|
-
wrap_width: 80,
|
|
798
|
-
convert_as_inline: false,
|
|
799
|
-
sub_symbol: "".to_string(),
|
|
800
|
-
sup_symbol: "".to_string(),
|
|
801
|
-
newline_style: NewlineStyle::Spaces,
|
|
802
|
-
code_block_style: Default::default(),
|
|
803
|
-
keep_inline_images_in: vec![],
|
|
804
|
-
preprocessing: Default::default(),
|
|
805
|
-
encoding: "utf-8".to_string(),
|
|
806
|
-
debug: false,
|
|
807
|
-
strip_tags: vec![],
|
|
808
|
-
preserve_tags: vec![],
|
|
809
|
-
skip_images: false,
|
|
810
|
-
url_escape_style: Default::default(),
|
|
811
|
-
link_style: Default::default(),
|
|
812
|
-
output_format: Default::default(),
|
|
813
|
-
include_document_structure: false,
|
|
814
|
-
extract_images: false,
|
|
815
|
-
max_image_size: 5242880,
|
|
816
|
-
capture_svg: false,
|
|
817
|
-
infer_dimensions: true,
|
|
818
|
-
max_depth: None,
|
|
819
|
-
exclude_selectors: vec![],
|
|
820
|
-
tier_strategy: TierStrategy::Auto,
|
|
821
|
-
}
|
|
759
|
+
html_to_markdown_rs::options::ConversionOptions::default().into()
|
|
822
760
|
}
|
|
823
761
|
}
|
|
824
762
|
|
|
@@ -1255,51 +1193,7 @@ unsafe impl TryConvertOwned for ConversionOptionsUpdate {}
|
|
|
1255
1193
|
|
|
1256
1194
|
impl Default for ConversionOptionsUpdate {
|
|
1257
1195
|
fn default() -> Self {
|
|
1258
|
-
|
|
1259
|
-
heading_style: None,
|
|
1260
|
-
list_indent_type: None,
|
|
1261
|
-
list_indent_width: None,
|
|
1262
|
-
bullets: None,
|
|
1263
|
-
strong_em_symbol: None,
|
|
1264
|
-
escape_asterisks: None,
|
|
1265
|
-
escape_underscores: None,
|
|
1266
|
-
escape_misc: None,
|
|
1267
|
-
escape_ascii: None,
|
|
1268
|
-
code_language: None,
|
|
1269
|
-
autolinks: None,
|
|
1270
|
-
default_title: None,
|
|
1271
|
-
br_in_tables: None,
|
|
1272
|
-
compact_tables: None,
|
|
1273
|
-
highlight_style: None,
|
|
1274
|
-
extract_metadata: None,
|
|
1275
|
-
whitespace_mode: None,
|
|
1276
|
-
strip_newlines: None,
|
|
1277
|
-
wrap: None,
|
|
1278
|
-
wrap_width: None,
|
|
1279
|
-
convert_as_inline: None,
|
|
1280
|
-
sub_symbol: None,
|
|
1281
|
-
sup_symbol: None,
|
|
1282
|
-
newline_style: None,
|
|
1283
|
-
code_block_style: None,
|
|
1284
|
-
keep_inline_images_in: None,
|
|
1285
|
-
preprocessing: None,
|
|
1286
|
-
encoding: None,
|
|
1287
|
-
debug: None,
|
|
1288
|
-
strip_tags: None,
|
|
1289
|
-
preserve_tags: None,
|
|
1290
|
-
skip_images: None,
|
|
1291
|
-
url_escape_style: None,
|
|
1292
|
-
link_style: None,
|
|
1293
|
-
output_format: None,
|
|
1294
|
-
include_document_structure: None,
|
|
1295
|
-
extract_images: None,
|
|
1296
|
-
max_image_size: None,
|
|
1297
|
-
capture_svg: None,
|
|
1298
|
-
infer_dimensions: None,
|
|
1299
|
-
max_depth: None,
|
|
1300
|
-
exclude_selectors: None,
|
|
1301
|
-
tier_strategy: None,
|
|
1302
|
-
}
|
|
1196
|
+
html_to_markdown_rs::options::ConversionOptionsUpdate::default().into()
|
|
1303
1197
|
}
|
|
1304
1198
|
}
|
|
1305
1199
|
|
|
@@ -1655,12 +1549,7 @@ unsafe impl TryConvertOwned for PreprocessingOptions {}
|
|
|
1655
1549
|
|
|
1656
1550
|
impl Default for PreprocessingOptions {
|
|
1657
1551
|
fn default() -> Self {
|
|
1658
|
-
|
|
1659
|
-
enabled: true,
|
|
1660
|
-
preset: Default::default(),
|
|
1661
|
-
remove_navigation: true,
|
|
1662
|
-
remove_forms: true,
|
|
1663
|
-
}
|
|
1552
|
+
html_to_markdown_rs::options::PreprocessingOptions::default().into()
|
|
1664
1553
|
}
|
|
1665
1554
|
}
|
|
1666
1555
|
|
|
@@ -1747,12 +1636,7 @@ unsafe impl TryConvertOwned for PreprocessingOptionsUpdate {}
|
|
|
1747
1636
|
|
|
1748
1637
|
impl Default for PreprocessingOptionsUpdate {
|
|
1749
1638
|
fn default() -> Self {
|
|
1750
|
-
|
|
1751
|
-
enabled: None,
|
|
1752
|
-
preset: None,
|
|
1753
|
-
remove_navigation: None,
|
|
1754
|
-
remove_forms: None,
|
|
1755
|
-
}
|
|
1639
|
+
html_to_markdown_rs::options::PreprocessingOptionsUpdate::default().into()
|
|
1756
1640
|
}
|
|
1757
1641
|
}
|
|
1758
1642
|
|
|
@@ -2211,13 +2095,7 @@ unsafe impl TryConvertOwned for ConversionResult {}
|
|
|
2211
2095
|
|
|
2212
2096
|
impl Default for ConversionResult {
|
|
2213
2097
|
fn default() -> Self {
|
|
2214
|
-
|
|
2215
|
-
content: None,
|
|
2216
|
-
document: None,
|
|
2217
|
-
metadata: Default::default(),
|
|
2218
|
-
tables: vec![],
|
|
2219
|
-
warnings: vec![],
|
|
2220
|
-
}
|
|
2098
|
+
html_to_markdown_rs::ConversionResult::default().into()
|
|
2221
2099
|
}
|
|
2222
2100
|
}
|
|
2223
2101
|
|
|
@@ -2314,11 +2192,7 @@ unsafe impl TryConvertOwned for TableGrid {}
|
|
|
2314
2192
|
|
|
2315
2193
|
impl Default for TableGrid {
|
|
2316
2194
|
fn default() -> Self {
|
|
2317
|
-
|
|
2318
|
-
rows: 0,
|
|
2319
|
-
cols: 0,
|
|
2320
|
-
cells: vec![],
|
|
2321
|
-
}
|
|
2195
|
+
html_to_markdown_rs::TableGrid::default().into()
|
|
2322
2196
|
}
|
|
2323
2197
|
}
|
|
2324
2198
|
|
|
@@ -6647,25 +6521,37 @@ impl From<html_to_markdown_rs::options::OutputFormat> for OutputFormat {
|
|
|
6647
6521
|
impl From<NodeContent> for html_to_markdown_rs::NodeContent {
|
|
6648
6522
|
fn from(val: NodeContent) -> Self {
|
|
6649
6523
|
match val {
|
|
6650
|
-
NodeContent::Heading { level, text } => Self::Heading {
|
|
6651
|
-
|
|
6652
|
-
|
|
6653
|
-
|
|
6524
|
+
NodeContent::Heading { level, text } => Self::Heading {
|
|
6525
|
+
level: level,
|
|
6526
|
+
text: text,
|
|
6527
|
+
},
|
|
6528
|
+
NodeContent::Paragraph { text } => Self::Paragraph { text: text },
|
|
6529
|
+
NodeContent::List { ordered } => Self::List { ordered: ordered },
|
|
6530
|
+
NodeContent::ListItem { text } => Self::ListItem { text: text },
|
|
6654
6531
|
NodeContent::Table { grid } => Self::Table { grid: grid.into() },
|
|
6655
6532
|
NodeContent::Image {
|
|
6656
6533
|
description,
|
|
6657
6534
|
src,
|
|
6658
6535
|
image_index,
|
|
6659
6536
|
} => Self::Image {
|
|
6660
|
-
description,
|
|
6661
|
-
src,
|
|
6662
|
-
image_index,
|
|
6537
|
+
description: description,
|
|
6538
|
+
src: src,
|
|
6539
|
+
image_index: image_index,
|
|
6540
|
+
},
|
|
6541
|
+
NodeContent::Code { text, language } => Self::Code {
|
|
6542
|
+
text: text,
|
|
6543
|
+
language: language,
|
|
6663
6544
|
},
|
|
6664
|
-
NodeContent::Code { text, language } => Self::Code { text, language },
|
|
6665
6545
|
NodeContent::Quote => Self::Quote,
|
|
6666
6546
|
NodeContent::DefinitionList => Self::DefinitionList,
|
|
6667
|
-
NodeContent::DefinitionItem { term, definition } => Self::DefinitionItem {
|
|
6668
|
-
|
|
6547
|
+
NodeContent::DefinitionItem { term, definition } => Self::DefinitionItem {
|
|
6548
|
+
term: term,
|
|
6549
|
+
definition: definition,
|
|
6550
|
+
},
|
|
6551
|
+
NodeContent::RawBlock { format, content } => Self::RawBlock {
|
|
6552
|
+
format: format,
|
|
6553
|
+
content: content,
|
|
6554
|
+
},
|
|
6669
6555
|
NodeContent::MetadataBlock { entries } => Self::MetadataBlock {
|
|
6670
6556
|
entries: entries.into_iter().map(Into::into).collect(),
|
|
6671
6557
|
},
|
|
@@ -6674,9 +6560,9 @@ impl From<NodeContent> for html_to_markdown_rs::NodeContent {
|
|
|
6674
6560
|
heading_level,
|
|
6675
6561
|
heading_text,
|
|
6676
6562
|
} => Self::Group {
|
|
6677
|
-
label,
|
|
6678
|
-
heading_level,
|
|
6679
|
-
heading_text,
|
|
6563
|
+
label: label,
|
|
6564
|
+
heading_level: heading_level,
|
|
6565
|
+
heading_text: heading_text,
|
|
6680
6566
|
},
|
|
6681
6567
|
}
|
|
6682
6568
|
}
|
|
@@ -6686,11 +6572,11 @@ impl From<html_to_markdown_rs::NodeContent> for NodeContent {
|
|
|
6686
6572
|
fn from(val: html_to_markdown_rs::NodeContent) -> Self {
|
|
6687
6573
|
match val {
|
|
6688
6574
|
html_to_markdown_rs::NodeContent::Heading { level, text } => Self::Heading {
|
|
6689
|
-
level,
|
|
6575
|
+
level: level,
|
|
6690
6576
|
text: text.to_string(),
|
|
6691
6577
|
},
|
|
6692
6578
|
html_to_markdown_rs::NodeContent::Paragraph { text } => Self::Paragraph { text: text.to_string() },
|
|
6693
|
-
html_to_markdown_rs::NodeContent::List { ordered } => Self::List { ordered },
|
|
6579
|
+
html_to_markdown_rs::NodeContent::List { ordered } => Self::List { ordered: ordered },
|
|
6694
6580
|
html_to_markdown_rs::NodeContent::ListItem { text } => Self::ListItem { text: text.to_string() },
|
|
6695
6581
|
html_to_markdown_rs::NodeContent::Table { grid } => Self::Table { grid: grid.into() },
|
|
6696
6582
|
html_to_markdown_rs::NodeContent::Image {
|
|
@@ -6700,7 +6586,7 @@ impl From<html_to_markdown_rs::NodeContent> for NodeContent {
|
|
|
6700
6586
|
} => Self::Image {
|
|
6701
6587
|
description: description.map(|v| v.to_string()),
|
|
6702
6588
|
src: src.map(|v| v.to_string()),
|
|
6703
|
-
image_index,
|
|
6589
|
+
image_index: image_index,
|
|
6704
6590
|
},
|
|
6705
6591
|
html_to_markdown_rs::NodeContent::Code { text, language } => Self::Code {
|
|
6706
6592
|
text: text.to_string(),
|
|
@@ -6725,7 +6611,7 @@ impl From<html_to_markdown_rs::NodeContent> for NodeContent {
|
|
|
6725
6611
|
heading_text,
|
|
6726
6612
|
} => Self::Group {
|
|
6727
6613
|
label: label.map(|v| v.to_string()),
|
|
6728
|
-
heading_level,
|
|
6614
|
+
heading_level: heading_level,
|
|
6729
6615
|
heading_text: heading_text.map(|v| v.to_string()),
|
|
6730
6616
|
},
|
|
6731
6617
|
}
|
|
@@ -6743,7 +6629,7 @@ impl From<AnnotationKind> for html_to_markdown_rs::AnnotationKind {
|
|
|
6743
6629
|
AnnotationKind::Subscript => Self::Subscript,
|
|
6744
6630
|
AnnotationKind::Superscript => Self::Superscript,
|
|
6745
6631
|
AnnotationKind::Highlight => Self::Highlight,
|
|
6746
|
-
AnnotationKind::Link { url, title } => Self::Link { url, title },
|
|
6632
|
+
AnnotationKind::Link { url, title } => Self::Link { url: url, title: title },
|
|
6747
6633
|
}
|
|
6748
6634
|
}
|
|
6749
6635
|
}
|