html-to-markdown 2.29.0 → 2.30.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: be0f8ebfe65a05409b2ffd00ec9ef6d4df88a6fbcbaf5ca486066d50581d7343
-  data.tar.gz: 9096699b71d719c2d28d89067b26bafc629f86b3ee2632fa579fdbef2780823c
+  metadata.gz: a59dd088c63edcda3711c276290e4377db037bd7a7cab8beb8bcbe83cf52a6f7
+  data.tar.gz: f49297af30be7e708bbca200099d471dbaadc0c98b2916489f17e83c07644ba7
 SHA512:
-  metadata.gz: ec0f48521c4aa8d5b5c87f39efc2862b60834f81e274a15b402bc387bfad3559564c0d6814b4419b1450b5bdea25a6c5534397634e03b5164ccd9b6433d0d559
-  data.tar.gz: 5ab62d25a86ad609bb5704470618aeae9d6bc5ce2e9a07adb0c88108938e6d893790ab4444847201fe9902671ba70ff0f81adc91e5588ca5823c15feb566e76f
+  metadata.gz: 94a8a04d0c146886a27c184ec5aacd83ed1619611b6666d9a98e3088c1fae5421b38a7b83dc557decb14a49e05f2b70d9ae142d3db61ab8dbf2bde165ee67dcc
+  data.tar.gz: b6676434b9dcf908f84d1803de65e2bbc86c4413eae4bd861d7732acca3b6938f9184ffb6b6e32b5326e7f56003fd44c67b851863f3b63931b69a388fb2bcfa6

data/Gemfile.lock

@@ -1,13 +1,13 @@
 PATH
   remote: .
   specs:
-    html-to-markdown (2.29.0)
+    html-to-markdown (2.30.0)
       rb_sys (>= 0.9, < 1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (8.1.2)
+    activesupport (8.1.3)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.3.1)
@@ -20,8 +20,6 @@ GEM
       securerandom (>= 0.3)
       tzinfo (~> 2.0, >= 2.0.5)
       uri (>= 0.13.1)
-    addressable (2.8.9)
-      public_suffix (>= 2.0.2, < 8.0)
     ast (2.4.3)
     base64 (0.3.0)
     bigdecimal (4.0.1)
@@ -30,18 +28,15 @@ GEM
     csv (3.3.5)
     diff-lcs (1.6.2)
     drb (2.2.3)
-    ffi (1.17.3-aarch64-linux-gnu)
-    ffi (1.17.3-arm64-darwin)
-    ffi (1.17.3-x64-mingw-ucrt)
-    ffi (1.17.3-x86_64-darwin)
-    ffi (1.17.3-x86_64-linux-gnu)
+    ffi (1.17.4-aarch64-linux-gnu)
+    ffi (1.17.4-arm64-darwin)
+    ffi (1.17.4-x64-mingw-ucrt)
+    ffi (1.17.4-x86_64-darwin)
+    ffi (1.17.4-x86_64-linux-gnu)
     fileutils (1.8.0)
     i18n (1.14.8)
       concurrent-ruby (~> 1.0)
-    json (2.19.2)
-    json-schema (6.2.0)
-      addressable (~> 2.8)
-      bigdecimal (>= 3.1, < 5)
+    json (2.19.3)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
     listen (3.10.0)
@@ -49,18 +44,15 @@ GEM
       rb-fsevent (~> 0.10, >= 0.10.3)
       rb-inotify (~> 0.9, >= 0.9.10)
     logger (1.7.0)
-    mcp (0.9.0)
-      json-schema (>= 4.1)
     minitest (6.0.2)
       drb (~> 2.0)
       prism (~> 1.5)
     mutex_m (0.3.0)
     parallel (1.27.0)
-    parser (3.3.10.2)
+    parser (3.3.11.1)
       ast (~> 2.4.1)
       racc
     prism (1.9.0)
-    public_suffix (7.0.5)
     racc (1.8.1)
     rainbow (3.1.1)
     rake (13.3.1)
@@ -72,7 +64,7 @@ GEM
       ffi (~> 1.0)
     rb_sys (0.9.124)
       rake-compiler-dock (= 1.11.0)
-    rbs (3.10.3)
+    rbs (3.10.4)
       logger
       tsort
     regexp_parser (2.11.3)
@@ -89,11 +81,10 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
     rspec-support (3.13.7)
-    rubocop (1.85.1)
+    rubocop (1.86.0)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
-      mcp (~> 0.6)
       parallel (~> 1.10)
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
@@ -156,8 +147,7 @@ DEPENDENCIES
   steep
 
 CHECKSUMS
-  activesupport (8.1.2) sha256=88842578ccd0d40f658289b0e8c842acfe9af751afee2e0744a7873f50b6fdae
-  addressable (2.8.9) sha256=cc154fcbe689711808a43601dee7b980238ce54368d23e127421753e46895485
+  activesupport (8.1.3) sha256=21a5e0dfbd4c3ddd9e1317ec6a4d782fa226e7867dc70b0743acda81a1dca20e
   ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
   base64 (0.3.0) sha256=27337aeabad6ffae05c265c450490628ef3ebd4b67be58257393227588f5a97b
   bigdecimal (4.0.1) sha256=8b07d3d065a9f921c80ceaea7c9d4ae596697295b584c296fe599dd0ad01c4a7
@@ -166,27 +156,24 @@ CHECKSUMS
   csv (3.3.5) sha256=6e5134ac3383ef728b7f02725d9872934f523cb40b961479f69cf3afa6c8e73f
   diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
   drb (2.2.3) sha256=0b00d6fdb50995fe4a45dea13663493c841112e4068656854646f418fda13373
-  ffi (1.17.3-aarch64-linux-gnu) sha256=28ad573df26560f0aedd8a90c3371279a0b2bd0b4e834b16a2baa10bd7a97068
-  ffi (1.17.3-arm64-darwin) sha256=0c690555d4cee17a7f07c04d59df39b2fba74ec440b19da1f685c6579bb0717f
-  ffi (1.17.3-x64-mingw-ucrt) sha256=5f1d7d067a9a1058ad183dba25b05557cd51c85fc1768c49338eabc1cf242d7c
-  ffi (1.17.3-x86_64-darwin) sha256=1f211811eb5cfaa25998322cdd92ab104bfbd26d1c4c08471599c511f2c00bb5
-  ffi (1.17.3-x86_64-linux-gnu) sha256=3746b01f677aae7b16dc1acb7cb3cc17b3e35bdae7676a3f568153fb0e2c887f
+  ffi (1.17.4-aarch64-linux-gnu) sha256=b208f06f91ffd8f5e1193da3cae3d2ccfc27fc36fba577baf698d26d91c080df
+  ffi (1.17.4-arm64-darwin) sha256=19071aaf1419251b0a46852abf960e77330a3b334d13a4ab51d58b31a937001b
+  ffi (1.17.4-x64-mingw-ucrt) sha256=f6ff9618cfccc494138bddade27aa06c74c6c7bc367a1ea1103d80c2fcb9ed35
+  ffi (1.17.4-x86_64-darwin) sha256=aa70390523cf3235096cf64962b709b4cfbd5c082a2cb2ae714eb0fe2ccda496
+  ffi (1.17.4-x86_64-linux-gnu) sha256=9d3db14c2eae074b382fa9c083fe95aec6e0a1451da249eab096c34002bc752d
   fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
-  html-to-markdown (2.29.0)
+  html-to-markdown (2.30.0)
   i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
-  json (2.19.2) sha256=e7e1bd318b2c37c4ceee2444841c86539bc462e81f40d134cf97826cb14e83cf
-  json-schema (6.2.0) sha256=e8bff46ed845a22c1ab2bd0d7eccf831c01fe23bb3920caa4c74db4306813666
+  json (2.19.3) sha256=289b0bb53052a1fa8c34ab33cc750b659ba14a5c45f3fcf4b18762dc67c78646
   language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
   listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
   logger (1.7.0) sha256=196edec7cc44b66cfb40f9755ce11b392f21f7967696af15d274dde7edff0203
-  mcp (0.9.0) sha256=a0a3737b0ac9df0772f4ef7e2b013c260ddbcf217a5d50a66bff0baeddf03e47
   minitest (6.0.2) sha256=db6e57956f6ecc6134683b4c87467d6dd792323c7f0eea7b93f66bd284adbc3d
   mutex_m (0.3.0) sha256=cfcb04ac16b69c4813777022fdceda24e9f798e48092a2b817eb4c0a782b0751
   parallel (1.27.0) sha256=4ac151e1806b755fb4e2dc2332cbf0e54f2e24ba821ff2d3dcf86bf6dc4ae130
-  parser (3.3.10.2) sha256=6f60c84aa4bdcedb6d1a2434b738fe8a8136807b6adc8f7f53b97da9bc4e9357
+  parser (3.3.11.1) sha256=d17ace7aabe3e72c3cc94043714be27cc6f852f104d81aa284c2281aecc65d54
   prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
-  public_suffix (7.0.5) sha256=1a8bb08f1bbea19228d3bed6e5ed908d1cb4f7c2726d18bd9cadf60bc676f623
   racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
   rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
   rake (13.3.1) sha256=8c9e89d09f66a26a01264e7e3480ec0607f0c497a861ef16063604b1b08eb19c
@@ -195,14 +182,14 @@ CHECKSUMS
   rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
   rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
   rb_sys (0.9.124) sha256=513476557b12eaf73764b3da9f8746024558fe8699bda785fb548c9aa3877ae7
-  rbs (3.10.3) sha256=70627f3919016134d554e6c99195552ae3ef6020fe034c8e983facc9c192daa6
+  rbs (3.10.4) sha256=b17d7c4be4bb31a11a3b529830f0aa206a807ca42f2e7921a3027dfc6b7e5ce8
   regexp_parser (2.11.3) sha256=ca13f381a173b7a93450e53459075c9b76a10433caadcb2f1180f2c741fc55a4
   rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
   rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
   rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
   rspec-mocks (3.13.8) sha256=086ad3d3d17533f4237643de0b5c42f04b66348c28bf6b9c2d3f4a3b01af1d47
   rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
-  rubocop (1.85.1) sha256=3dbcf9e961baa4c376eeeb2a03913dca5e3987033b04d38fa538aa1e7406cc77
+  rubocop (1.86.0) sha256=4ff1186fe16ebe9baff5e7aad66bb0ad4cabf5cdcd419f773146dbba2565d186
   rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
   rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
   ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33

data/ext/html-to-markdown-rb/native/Cargo.lock

@@ -155,9 +155,9 @@ checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495"
 
 [[package]]
 name = "cc"
-version = "1.2.57"
+version = "1.2.58"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a0dd1ca384932ff3641c8718a02769f1698e7563dc6974ffd03346116310423"
+checksum = "e1e928d4b69e3077709075a938a05ffbedfa53a84c8f766efbf8220bb1ff60e1"
 dependencies = [
  "find-msvc-tools",
  "shlex",
@@ -452,7 +452,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rb"
-version = "2.28.6"
+version = "2.29.0"
 dependencies = [
  "html-to-markdown-rs",
  "magnus",
@@ -462,7 +462,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "2.28.6"
+version = "2.29.0"
 dependencies = [
  "ahash",
  "astral-tl",
@@ -1143,9 +1143,9 @@ checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
 [[package]]
 name = "simd-adler32"
-version = "0.3.8"
+version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e320a6c5ad31d271ad523dcf3ad13e2767ad8b1cb8f047f75a8aeaf8da139da2"
+checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214"
 
 [[package]]
 name = "siphasher"
@@ -1206,9 +1206,9 @@ dependencies = [
 
 [[package]]
 name = "symbolic-common"
-version = "12.17.2"
+version = "12.17.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "751a2823d606b5d0a7616499e4130a516ebd01a44f39811be2b9600936509c23"
+checksum = "52ca086c1eb5c7ee74b151ba83c6487d5d33f8c08ad991b86f3f58f6629e68d5"
 dependencies = [
  "debugid",
  "memmap2",
@@ -1218,9 +1218,9 @@ dependencies = [
 
 [[package]]
 name = "symbolic-demangle"
-version = "12.17.2"
+version = "12.17.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "79b237cfbe320601dd24b4ac817a5b68bb28f5508e33f08d42be0682cadc8ac9"
+checksum = "baa911a28a62823aaf2cc2e074212492a3ee69d0d926cc8f5b12b4a108ff5c0c"
 dependencies = [
  "cpp_demangle",
  "rustc-demangle",
@@ -1316,9 +1316,9 @@ checksum = "1292c0d970b54115d14f2492fe0170adf21d68a1de108eebc51c1df4f346a091"
 
 [[package]]
 name = "uuid"
-version = "1.22.0"
+version = "1.23.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a68d3c8f01c0cfa54a75291d83601161799e4a89a39e0929f4b0354d88757a37"
+checksum = "5ac8b6f42ead25368cf5b098aeb3dc8a1a2c05a3eee8a9a1a68c640edbfc79d9"
 dependencies = [
  "js-sys",
  "wasm-bindgen",
@@ -1622,9 +1622,9 @@ checksum = "cb8a0807f7c01457d0379ba880ba6322660448ddebc890ce29bb64da71fb40f9"
 
 [[package]]
 name = "zune-jpeg"
-version = "0.5.14"
+version = "0.5.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b7a1c0af6e5d8d1363f4994b7a091ccf963d8b694f7da5b0b9cceb82da2c0a6"
+checksum = "27bc9d5b815bc103f142aa054f561d9187d191692ec7c2d1e2b4737f8dbd7296"
 dependencies = [
  "zune-core",
 ]

data/ext/html-to-markdown-rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rb"
-version = "2.29.0"
+version = "2.30.0"
 edition = "2024"
 authors = ["Na'aman Hirschfeld <naaman@kreuzberg.dev>"]
 license = "MIT"

data/lib/html_to_markdown/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HtmlToMarkdown
-  VERSION = '2.29.0'
+  VERSION = '2.30.0'
 end

data/sig/html_to_markdown.rbs

@@ -62,7 +62,7 @@ module HtmlToMarkdown
     autolinks?: bool,
     default_title?: bool,
     br_in_tables?: bool,
-    hocr_spatial_tables?: bool,
+    hocr_spatial_tables?: bool, # Deprecated since 2.30.0: hOCR support will be removed in v3.
     highlight_style?: highlight_style,
     extract_metadata?: bool,
     whitespace_mode?: whitespace_mode,

data/vendor/Cargo.toml

@@ -3,7 +3,7 @@ members = ["html-to-markdown-rs"]
 resolver = "2"
 
 [workspace.package]
-version = "2.29.0"
+version = "2.30.0"
 edition = "2024"
 rust-version = "1.85"
 authors = ["Na'aman Hirschfeld <naaman@kreuzberg.dev>"]
@@ -17,9 +17,9 @@ async-trait = "0.1"
 base64 = "0.22"
 clap = { version = "4.6", features = ["derive"] }
 clap_complete = "4.6"
-clap_mangen = "0.2"
+clap_mangen = "0.3"
 encoding_rs = "0.8"
-ext-php-rs = "0.15.6"
+ext-php-rs = "0.15.7"
 html5ever = "0.39.0"
 once_cell = "1.21"
 pyo3 = { version = "0.28.2", features = ["abi3-py310"] }

data/vendor/html-to-markdown-rs/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "html-to-markdown-rs"
-version = "2.29.0"
+version = "2.30.0"
 edition = "2024"
 authors = ["Na'aman Hirschfeld <naaman@kreuzberg.dev>"]
 license = "MIT"

data/vendor/html-to-markdown-rs/README.md

@@ -121,7 +121,9 @@ options.preprocessing.remove_forms = true;
 let markdown = convert(scraped_html, Some(options))?;
 ```
 
-## hOCR Table Extraction
+## hOCR Table Extraction (Deprecated)
+
+> **Deprecated since 2.30.0**: hOCR support will be removed in v3.
 
 ```rust
 use html_to_markdown_rs::convert;

data/vendor/html-to-markdown-rs/src/converter/main_helpers.rs

@@ -286,6 +286,7 @@ pub fn is_inline_element(tag_name: &str) -> bool {
 }
 
 /// Handle hOCR document conversion, returning true if handled, false if not hOCR.
+#[allow(deprecated)]
 pub fn handle_hocr_document(
     dom: &tl::VDom<'_>,
     parser: &tl::Parser<'_>,

data/vendor/html-to-markdown-rs/src/hocr/mod.rs

@@ -1,6 +1,8 @@
 #![allow(clippy::cast_precision_loss, clippy::cast_sign_loss, clippy::unused_self)]
 //! hOCR 1.2 document processing.
 //!
+//! **Deprecated since 2.30.0**: hOCR support will be removed in v3.
+//!
 //! Complete hOCR 1.2 specification support for extracting structured content from OCR documents.
 //!
 //! ## Features
@@ -19,13 +21,22 @@
 //! - [`converter`]: hOCR to Markdown conversion
 //! - [`spatial`]: Spatial table reconstruction from bounding boxes
 
+#[allow(deprecated)]
 pub mod converter;
+#[allow(deprecated)]
 pub mod extractor;
+#[allow(deprecated)]
 pub mod parser;
+#[allow(deprecated)]
 pub mod spatial;
+#[allow(deprecated)]
 pub mod types;
 
+#[deprecated(since = "2.30.0", note = "hOCR support will be removed in v3.")]
 pub use converter::{convert_to_markdown, convert_to_markdown_with_options};
+#[deprecated(since = "2.30.0", note = "hOCR support will be removed in v3.")]
 pub use extractor::extract_hocr_document;
+#[deprecated(since = "2.30.0", note = "hOCR support will be removed in v3.")]
 pub use spatial::{HocrWord, extract_hocr_words, reconstruct_table, table_to_markdown};
+#[deprecated(since = "2.30.0", note = "hOCR support will be removed in v3.")]
 pub use types::{BBox, Baseline, HocrElement, HocrElementType, HocrMetadata, HocrProperties};

data/vendor/html-to-markdown-rs/src/options/conversion.rs

@@ -62,7 +62,9 @@ pub struct ConversionOptions {
     /// Use HTML <br> elements in tables instead of spaces for line breaks
     pub br_in_tables: bool,
 
-    /// Enable spatial table reconstruction in hOCR documents (via spatial positioning analysis)
+    /// Enable spatial table reconstruction in hOCR documents (via spatial positioning analysis).
+    ///
+    /// **Deprecated since 2.30.0**: hOCR support will be removed in v3.
     pub hocr_spatial_tables: bool,
 
     /// Highlight style for <mark> elements (`DoubleEqual`, Html, Bold, None)
@@ -176,7 +178,9 @@ pub struct ConversionOptionsUpdate {
     /// Optional HTML <br> usage in tables override
     pub br_in_tables: Option<bool>,
 
-    /// Optional spatial table reconstruction for hOCR documents override
+    /// Optional spatial table reconstruction for hOCR documents override.
+    ///
+    /// **Deprecated since 2.30.0**: hOCR support will be removed in v3.
     pub hocr_spatial_tables: Option<bool>,
 
     /// Optional highlight style override for <mark> elements

data/vendor/html-to-markdown-rs/tests/hocr_compliance_test.rs

@@ -1,4 +1,4 @@
-#![allow(missing_docs, clippy::float_cmp, clippy::items_after_statements)]
+#![allow(missing_docs, clippy::float_cmp, clippy::items_after_statements, deprecated)]
 
 //! hOCR 1.2 compliance integration tests
 //!

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-to-markdown
 version: !ruby/object:Gem::Version
-  version: 2.29.0
+  version: 2.30.0
 platform: ruby
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-03-22 00:00:00.000000000 Z
+date: 2026-03-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys