html-to-markdown 3.9.2 → 3.10.1
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 +1 -1
- data/ext/html_to_markdown_rb/Cargo.toml +1 -1
- data/ext/html_to_markdown_rb/native/Cargo.lock +47 -14
- data/ext/html_to_markdown_rb/native/Cargo.toml +4 -3
- data/ext/html_to_markdown_rb/src/lib.rs +1 -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: ced27f8f236eab7b37fc15029ef87abfad748cc5adedfd3d62ef8a2605ecc559
|
|
4
|
+
data.tar.gz: 4e780f914e9d876d094a804672d5c42f937a41f34829b4cef1ecc522ca329c16
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: f2e249eb7c77cb463478e85e226bb43d0f30a6d8fbb9792483b299ee252f42dcf7d723c1f2c1568f17327bf3ebd3f1b5a66a74907d510b5c1d3627d0ebae778c
|
|
7
|
+
data.tar.gz: 35e0c43c9fd737cc4514a27310d33042b193e617042e0f6603c6f4905401439bcd530dc056cd6a3b738591459a2ae8580975b91ba38dcefae69e4c211735cade
|
data/README.md
CHANGED
|
@@ -300,7 +300,7 @@ markdown = result[:content]
|
|
|
300
300
|
|
|
301
301
|
## Part of Xberg
|
|
302
302
|
|
|
303
|
-
- [Xberg](https://github.com/xberg-io/xberg) — document intelligence: text, tables, metadata from
|
|
303
|
+
- [Xberg](https://github.com/xberg-io/xberg) — document intelligence: text, tables, metadata from 98+ formats with optional OCR.
|
|
304
304
|
- [Xberg Enterprise](https://github.com/xberg-io/xberg-enterprise) — managed extraction API with SDKs, dashboards, and observability.
|
|
305
305
|
- [crawlberg](https://github.com/xberg-io/crawlberg) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
|
|
306
306
|
- [html-to-markdown](https://github.com/xberg-io/html-to-markdown) — fast, lossless HTML→Markdown engine.
|
|
@@ -53,7 +53,7 @@ checksum = "ae36dc4177970ef04fde5178d3e2429882def40e57a451f919c098f72baa6cec"
|
|
|
53
53
|
dependencies = [
|
|
54
54
|
"proc-macro2",
|
|
55
55
|
"quote",
|
|
56
|
-
"syn 3.0.
|
|
56
|
+
"syn 3.0.3",
|
|
57
57
|
]
|
|
58
58
|
|
|
59
59
|
[[package]]
|
|
@@ -260,7 +260,7 @@ checksum = "46c1ff2d1cbf39efe5af0900ced8a069b5e61557a17544eb0c4a50239937389e"
|
|
|
260
260
|
|
|
261
261
|
[[package]]
|
|
262
262
|
name = "html-to-markdown-rb"
|
|
263
|
-
version = "3.
|
|
263
|
+
version = "3.10.1"
|
|
264
264
|
dependencies = [
|
|
265
265
|
"async-trait",
|
|
266
266
|
"html-to-markdown-rs",
|
|
@@ -269,13 +269,14 @@ dependencies = [
|
|
|
269
269
|
"serde",
|
|
270
270
|
"serde_json",
|
|
271
271
|
"tokio",
|
|
272
|
+
"tracing",
|
|
272
273
|
]
|
|
273
274
|
|
|
274
275
|
[[package]]
|
|
275
276
|
name = "html-to-markdown-rs"
|
|
276
|
-
version = "3.
|
|
277
|
+
version = "3.10.1"
|
|
277
278
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
278
|
-
checksum = "
|
|
279
|
+
checksum = "f542b3eb38aebefdf324b8ad69dba2c95fc5f68c644cd9d8c5261a8f7a05284a"
|
|
279
280
|
dependencies = [
|
|
280
281
|
"ahash",
|
|
281
282
|
"astral-tl",
|
|
@@ -292,6 +293,7 @@ dependencies = [
|
|
|
292
293
|
"serde",
|
|
293
294
|
"serde_json",
|
|
294
295
|
"thiserror",
|
|
296
|
+
"tracing",
|
|
295
297
|
]
|
|
296
298
|
|
|
297
299
|
[[package]]
|
|
@@ -355,9 +357,9 @@ checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
|
|
|
355
357
|
|
|
356
358
|
[[package]]
|
|
357
359
|
name = "libc"
|
|
358
|
-
version = "0.2.
|
|
360
|
+
version = "0.2.189"
|
|
359
361
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
360
|
-
checksum = "
|
|
362
|
+
checksum = "3eaf3ede3fee6db1a4c2ee091bf8a8b4dccdc6d17f656fb07896ee72867612f2"
|
|
361
363
|
|
|
362
364
|
[[package]]
|
|
363
365
|
name = "libloading"
|
|
@@ -763,14 +765,14 @@ checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
|
|
|
763
765
|
dependencies = [
|
|
764
766
|
"proc-macro2",
|
|
765
767
|
"quote",
|
|
766
|
-
"syn 3.0.
|
|
768
|
+
"syn 3.0.3",
|
|
767
769
|
]
|
|
768
770
|
|
|
769
771
|
[[package]]
|
|
770
772
|
name = "serde_json"
|
|
771
|
-
version = "1.0.
|
|
773
|
+
version = "1.0.151"
|
|
772
774
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
773
|
-
checksum = "
|
|
775
|
+
checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
|
|
774
776
|
dependencies = [
|
|
775
777
|
"itoa",
|
|
776
778
|
"memchr",
|
|
@@ -846,9 +848,9 @@ dependencies = [
|
|
|
846
848
|
|
|
847
849
|
[[package]]
|
|
848
850
|
name = "syn"
|
|
849
|
-
version = "3.0.
|
|
851
|
+
version = "3.0.3"
|
|
850
852
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
851
|
-
checksum = "
|
|
853
|
+
checksum = "53e9bae58849f64dfa4f5d5ae372c8341f7305f82a3868709269343628b659a3"
|
|
852
854
|
dependencies = [
|
|
853
855
|
"proc-macro2",
|
|
854
856
|
"quote",
|
|
@@ -881,7 +883,7 @@ checksum = "43cbfe0cf76104d42a574802844187e84a305e531ed54455f11fbde0f10541cd"
|
|
|
881
883
|
dependencies = [
|
|
882
884
|
"proc-macro2",
|
|
883
885
|
"quote",
|
|
884
|
-
"syn 3.0.
|
|
886
|
+
"syn 3.0.3",
|
|
885
887
|
]
|
|
886
888
|
|
|
887
889
|
[[package]]
|
|
@@ -895,13 +897,44 @@ dependencies = [
|
|
|
895
897
|
|
|
896
898
|
[[package]]
|
|
897
899
|
name = "tokio"
|
|
898
|
-
version = "1.53.
|
|
900
|
+
version = "1.53.1"
|
|
899
901
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
900
|
-
checksum = "
|
|
902
|
+
checksum = "202caea871b69668250d242070849eb495be178ed697a3e98aebce5bc81a0bed"
|
|
901
903
|
dependencies = [
|
|
902
904
|
"pin-project-lite",
|
|
903
905
|
]
|
|
904
906
|
|
|
907
|
+
[[package]]
|
|
908
|
+
name = "tracing"
|
|
909
|
+
version = "0.1.44"
|
|
910
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
911
|
+
checksum = "63e71662fa4b2a2c3a26f570f037eb95bb1f85397f3cd8076caed2f026a6d100"
|
|
912
|
+
dependencies = [
|
|
913
|
+
"pin-project-lite",
|
|
914
|
+
"tracing-attributes",
|
|
915
|
+
"tracing-core",
|
|
916
|
+
]
|
|
917
|
+
|
|
918
|
+
[[package]]
|
|
919
|
+
name = "tracing-attributes"
|
|
920
|
+
version = "0.1.31"
|
|
921
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
922
|
+
checksum = "7490cfa5ec963746568740651ac6781f701c9c5ea257c58e057f3ba8cf69e8da"
|
|
923
|
+
dependencies = [
|
|
924
|
+
"proc-macro2",
|
|
925
|
+
"quote",
|
|
926
|
+
"syn 2.0.119",
|
|
927
|
+
]
|
|
928
|
+
|
|
929
|
+
[[package]]
|
|
930
|
+
name = "tracing-core"
|
|
931
|
+
version = "0.1.36"
|
|
932
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
933
|
+
checksum = "db97caf9d906fbde555dd62fa95ddba9eecfd14cb388e4f491a66d74cd5fb79a"
|
|
934
|
+
dependencies = [
|
|
935
|
+
"once_cell",
|
|
936
|
+
]
|
|
937
|
+
|
|
905
938
|
[[package]]
|
|
906
939
|
name = "unicode-ident"
|
|
907
940
|
version = "1.0.24"
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[package]
|
|
2
2
|
name = "html-to-markdown-rb"
|
|
3
|
-
version = "3.
|
|
3
|
+
version = "3.10.1"
|
|
4
4
|
edition = "2024"
|
|
5
5
|
license = "MIT"
|
|
6
6
|
description = "High-performance HTML to Markdown converter"
|
|
@@ -9,7 +9,7 @@ keywords = ["converter", "html", "markdown"]
|
|
|
9
9
|
categories = []
|
|
10
10
|
|
|
11
11
|
[package.metadata.cargo-machete]
|
|
12
|
-
ignored = ["async-trait", "rb-sys", "tokio"]
|
|
12
|
+
ignored = ["async-trait", "rb-sys", "tokio", "tracing"]
|
|
13
13
|
|
|
14
14
|
[lib]
|
|
15
15
|
name = "html_to_markdown_rb"
|
|
@@ -25,9 +25,10 @@ visitor = ["html-to-markdown-rs/visitor"]
|
|
|
25
25
|
|
|
26
26
|
[dependencies]
|
|
27
27
|
async-trait = "0.1"
|
|
28
|
-
html-to-markdown-rs = { version = "3.
|
|
28
|
+
html-to-markdown-rs = { version = "3.10.1", features = ["serde", "metadata", "visitor", "inline-images", "testkit"] }
|
|
29
29
|
magnus = "0.8"
|
|
30
30
|
rb-sys = ">=0.9, <0.9.128"
|
|
31
31
|
serde = { version = "1", features = ["derive"] }
|
|
32
32
|
serde_json = "1"
|
|
33
33
|
tokio = { version = "1", features = ["rt-multi-thread"] }
|
|
34
|
+
tracing = "0.1"
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
// This file is auto-generated by alef. DO NOT EDIT.
|
|
2
|
-
// alef:hash:
|
|
2
|
+
// alef:hash:71adfc2ecb2d01d740d17e422205dfa69c729bb876fe48ab4a3a556d99178b83
|
|
3
3
|
// Re-generate with: alef generate
|
|
4
4
|
#![allow(dead_code, unused_imports, unused_variables)]
|
|
5
5
|
#![allow(
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:71adfc2ecb2d01d740d17e422205dfa69c729bb876fe48ab4a3a556d99178b83
|
|
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:71adfc2ecb2d01d740d17e422205dfa69c729bb876fe48ab4a3a556d99178b83
|
|
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.
|
|
9
|
+
VERSION = "3.10.1"
|
|
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:71adfc2ecb2d01d740d17e422205dfa69c729bb876fe48ab4a3a556d99178b83
|
|
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:71adfc2ecb2d01d740d17e422205dfa69c729bb876fe48ab4a3a556d99178b83
|
|
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.
|
|
4
|
+
version: 3.10.1
|
|
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: 2026-07-31 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rb_sys
|