html-to-markdown 2.3.4__tar.gz → 2.4.1__tar.gz

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/Cargo.lock

@@ -116,9 +116,9 @@ checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
 [[package]]
 name = "bitflags"
-version = "2.9.4"
+version = "2.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2261d10cca569e4643e526d8dc2e62e433cc8aba21ab764233731f8d369bf394"
+checksum = "812e12b5285cc515a9c72a5c1d3b6d46a19dac5acfef5265968c166106e31dd3"
 
 [[package]]
 name = "bstr"
@@ -167,9 +167,9 @@ dependencies = [
 
 [[package]]
 name = "cfg-if"
-version = "1.0.3"
+version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2fd1289c04a9ea8cb22300a459a72a385d7c73d3259e2ed7dcb2af674838cfa9"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
 
 [[package]]
 name = "ciborium"
@@ -200,9 +200,9 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.5.49"
+version = "4.5.50"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4512b90fa68d3a9932cea5184017c5d200f5921df706d45e853537dea51508f"
+checksum = "0c2cfd7bf8a6017ddaa4e32ffe7403d547790db06bd171c1c53926faab501623"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -210,9 +210,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.5.49"
+version = "4.5.50"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0025e98baa12e766c67ba13ff4695a887a1eba19569aad00a472546795bd6730"
+checksum = "0a4c05b9e80c5ccd3a7ef080ad7b6ba7d6fc00a985b8b157197075677c82c7a0"
 dependencies = [
  "anstream",
  "anstyle",
@@ -299,25 +299,22 @@ dependencies = [
 
 [[package]]
 name = "criterion"
-version = "0.5.1"
+version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f"
+checksum = "e1c047a62b0cc3e145fa84415a3191f628e980b194c2755aa12300a4e6cbd928"
 dependencies = [
  "anes",
  "cast",
  "ciborium",
  "clap",
  "criterion-plot",
- "is-terminal",
  "itertools",
  "num-traits",
- "once_cell",
  "oorandom",
  "plotters",
  "rayon",
  "regex",
  "serde",
- "serde_derive",
  "serde_json",
  "tinytemplate",
  "walkdir",
@@ -325,9 +322,9 @@ dependencies = [
 
 [[package]]
 name = "criterion-plot"
-version = "0.5.0"
+version = "0.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
+checksum = "9b1bcc0dc7dfae599d84ad0b1a55f80cde8af3725da8313b528da95ef783e338"
 dependencies = [
  "cast",
  "itertools",
@@ -548,27 +545,16 @@ dependencies = [
 
 [[package]]
 name = "getrandom"
-version = "0.2.16"
+version = "0.3.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
 dependencies = [
  "cfg-if",
  "js-sys",
  "libc",
- "wasi 0.11.1+wasi-snapshot-preview1",
- "wasm-bindgen",
-]
-
-[[package]]
-name = "getrandom"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
-dependencies = [
- "cfg-if",
- "libc",
  "r-efi",
- "wasi 0.14.7+wasi-0.2.4",
+ "wasip2",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -598,12 +584,6 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
-[[package]]
-name = "hermit-abi"
-version = "0.5.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
-
 [[package]]
 name = "html-escape"
 version = "0.2.13"
@@ -615,7 +595,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-cli"
-version = "2.3.4"
+version = "2.4.1"
 dependencies = [
  "assert_cmd",
  "clap",
@@ -629,7 +609,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-node"
-version = "2.3.4"
+version = "2.4.1"
 dependencies = [
  "html-to-markdown-rs",
  "mimalloc-rust",
@@ -640,7 +620,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-py"
-version = "2.3.4"
+version = "2.4.1"
 dependencies = [
  "base64",
  "html-to-markdown-rs",
@@ -650,7 +630,7 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-rs"
-version = "2.3.4"
+version = "2.4.1"
 dependencies = [
  "ammonia",
  "base64",
@@ -667,10 +647,10 @@ dependencies = [
 
 [[package]]
 name = "html-to-markdown-wasm"
-version = "2.3.4"
+version = "2.4.1"
 dependencies = [
  "console_error_panic_hook",
- "getrandom 0.2.16",
+ "getrandom",
  "html-to-markdown-rs",
  "js-sys",
  "serde",
@@ -827,32 +807,24 @@ dependencies = [
 
 [[package]]
 name = "indoc"
-version = "2.0.6"
+version = "2.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
-
-[[package]]
-name = "is-terminal"
-version = "0.4.16"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e04d7f318608d35d4b61ddd75cbdaee86b023ebe2bd5a66ee0915f0bf93095a9"
+checksum = "79cf5c93f93228cf8efb3ba362535fb11199ac548a09ce117c9b1adc3030d706"
 dependencies = [
- "hermit-abi",
- "libc",
- "windows-sys 0.59.0",
+ "rustversion",
 ]
 
 [[package]]
 name = "is_terminal_polyfill"
-version = "1.70.1"
+version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
+checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
 
 [[package]]
 name = "itertools"
-version = "0.10.5"
+version = "0.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
 dependencies = [
  "either",
 ]
@@ -1106,9 +1078,9 @@ checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
 
 [[package]]
 name = "once_cell_polyfill"
-version = "1.70.1"
+version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4895175b425cb1f87721b59f0f286c2092bd4af812243672510e1ac53e2e0ad"
+checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
 [[package]]
 name = "oorandom"
@@ -1309,9 +1281,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3"
-version = "0.26.0"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7ba0117f4212101ee6544044dae45abe1083d30ce7b29c4b5cbdfa2354e07383"
+checksum = "37a6df7eab65fc7bee654a421404947e10a0f7085b6951bf2ea395f4659fb0cf"
 dependencies = [
  "indoc",
  "libc",
@@ -1326,18 +1298,18 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.26.0"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4fc6ddaf24947d12a9aa31ac65431fb1b851b8f4365426e182901eabfb87df5f"
+checksum = "f77d387774f6f6eec64a004eac0ed525aab7fa1966d94b42f743797b3e395afb"
 dependencies = [
  "target-lexicon",
 ]
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.26.0"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "025474d3928738efb38ac36d4744a74a400c901c7596199e20e45d98eb194105"
+checksum = "2dd13844a4242793e02df3e2ec093f540d948299a6a77ea9ce7afd8623f542be"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -1345,9 +1317,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.26.0"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2e64eb489f22fe1c95911b77c44cc41e7c19f3082fc81cce90f657cdc42ffded"
+checksum = "eaf8f9f1108270b90d3676b8679586385430e5c0bb78bb5f043f95499c821a71"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
@@ -1357,9 +1329,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.26.0"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "100246c0ecf400b475341b8455a9213344569af29a3c841d29270e53102e0fcf"
+checksum = "70a3b2274450ba5288bc9b8c1b69ff569d1d61189d4bff38f8d22e03d17f932b"
 dependencies = [
  "heck",
  "proc-macro2",
@@ -1637,9 +1609,9 @@ checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
 
 [[package]]
 name = "syn"
-version = "2.0.106"
+version = "2.0.107"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ede7c438028d4436d71104916910f5bb611972c5cfd7f89b8300a8186e6fada6"
+checksum = "2a26dbd934e5451d21ef060c018dae56fc073894c5a7896f882928a76e6d081b"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1670,7 +1642,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2d31c77bdf42a745371d260a26ca7163f1e0924b64afa0b688e61b5a9fa02f16"
 dependencies = [
  "fastrand",
- "getrandom 0.3.3",
+ "getrandom",
  "once_cell",
  "rustix",
  "windows-sys 0.61.2",
@@ -1741,9 +1713,9 @@ checksum = "b130bd8a58c163224b44e217b4239ca7b927d82bf6cc2fea1fc561d15056e3f7"
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.19"
+version = "1.0.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d"
+checksum = "462eeb75aeb73aea900253ce739c8e18a67423fadf006037cd3ff27e82748a06"
 
 [[package]]
 name = "unicode-segmentation"
@@ -1812,21 +1784,6 @@ dependencies = [
  "winapi-util",
 ]
 
-[[package]]
-name = "wasi"
-version = "0.11.1+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
-
-[[package]]
-name = "wasi"
-version = "0.14.7+wasi-0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "883478de20367e224c0090af9cf5f9fa85bed63a95c1abf3afc5c083ebc06e8c"
-dependencies = [
- "wasip2",
-]
-
 [[package]]
 name = "wasip2"
 version = "1.0.1+wasi-0.2.4"
@@ -1975,22 +1932,13 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
 
-[[package]]
-name = "windows-sys"
-version = "0.59.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
-dependencies = [
- "windows-targets 0.52.6",
-]
-
 [[package]]
 name = "windows-sys"
 version = "0.60.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f2f500e4d28234f72040990ec9d39e3a6b950f9f22d3dba18416c35882612bcb"
 dependencies = [
- "windows-targets 0.53.5",
+ "windows-targets",
 ]
 
 [[package]]
@@ -2002,22 +1950,6 @@ dependencies = [
  "windows-link",
 ]
 
-[[package]]
-name = "windows-targets"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
-dependencies = [
- "windows_aarch64_gnullvm 0.52.6",
- "windows_aarch64_msvc 0.52.6",
- "windows_i686_gnu 0.52.6",
- "windows_i686_gnullvm 0.52.6",
- "windows_i686_msvc 0.52.6",
- "windows_x86_64_gnu 0.52.6",
- "windows_x86_64_gnullvm 0.52.6",
- "windows_x86_64_msvc 0.52.6",
-]
-
 [[package]]
 name = "windows-targets"
 version = "0.53.5"
@@ -2025,106 +1957,58 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4945f9f551b88e0d65f3db0bc25c33b8acea4d9e41163edf90dcd0b19f9069f3"
 dependencies = [
  "windows-link",
- "windows_aarch64_gnullvm 0.53.1",
- "windows_aarch64_msvc 0.53.1",
- "windows_i686_gnu 0.53.1",
- "windows_i686_gnullvm 0.53.1",
- "windows_i686_msvc 0.53.1",
- "windows_x86_64_gnu 0.53.1",
- "windows_x86_64_gnullvm 0.53.1",
- "windows_x86_64_msvc 0.53.1",
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
 ]
 
-[[package]]
-name = "windows_aarch64_gnullvm"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
-
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a9d8416fa8b42f5c947f8482c43e7d89e73a173cead56d044f6a56104a6d1b53"
 
-[[package]]
-name = "windows_aarch64_msvc"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
-
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b9d782e804c2f632e395708e99a94275910eb9100b2114651e04744e9b125006"
 
-[[package]]
-name = "windows_i686_gnu"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
-
 [[package]]
 name = "windows_i686_gnu"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "960e6da069d81e09becb0ca57a65220ddff016ff2d6af6a223cf372a506593a3"
 
-[[package]]
-name = "windows_i686_gnullvm"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
-
 [[package]]
 name = "windows_i686_gnullvm"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fa7359d10048f68ab8b09fa71c3daccfb0e9b559aed648a8f95469c27057180c"
 
-[[package]]
-name = "windows_i686_msvc"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
-
 [[package]]
 name = "windows_i686_msvc"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e7ac75179f18232fe9c285163565a57ef8d3c89254a30685b57d83a38d326c2"
 
-[[package]]
-name = "windows_x86_64_gnu"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
-
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c3842cdd74a865a8066ab39c8a7a473c0778a3f29370b5fd6b4b9aa7df4a499"
 
-[[package]]
-name = "windows_x86_64_gnullvm"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
-
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0ffa179e2d07eee8ad8f57493436566c7cc30ac536a3379fdf008f47f6bb7ae1"
 
-[[package]]
-name = "windows_x86_64_msvc"
-version = "0.52.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
-
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.53.1"

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/Cargo.toml

@@ -3,7 +3,7 @@ resolver = "2"
 members = ["crates/html-to-markdown-py"]
 
 [workspace.package]
-version = "2.3.4"
+version = "2.4.1"
 edition = "2021"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
 license = "MIT"
@@ -15,7 +15,7 @@ rust-version = "1.80"
 
 [workspace.dependencies]
 # Core library
-html-to-markdown-rs = { version = "2.3.4", path = "crates/html-to-markdown" }
+html-to-markdown-rs = { version = "2.4.1", path = "crates/html-to-markdown" }
 
 # HTML parsing and sanitization
 tl = "0.7"
@@ -34,7 +34,7 @@ clap_complete = "4.5"
 clap_mangen = "0.2"
 
 # Python bindings
-pyo3 = { version = "0.26.0", features = ["abi3-py310"] }
+pyo3 = { version = "0.27.1", features = ["abi3-py310"] }
 
 [profile.release]
 lto = "thin"

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 2.3.4
+Version: 2.4.1
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/crates/html-to-markdown/Cargo.toml

@@ -33,7 +33,7 @@ image = { version = "0.25", default-features = false, features = ["gif", "jpeg",
 [dev-dependencies]
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
-criterion = { version = "0.5", features = ["html_reports"] }
+criterion = { version = "0.7", features = ["html_reports"] }
 
 [[bench]]
 name = "conversion_benchmark"

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/crates/html-to-markdown/src/converter.rs

@@ -47,6 +47,9 @@ use std::collections::BTreeMap;
 #[cfg(feature = "inline-images")]
 use std::rc::Rc;
 
+use std::borrow::Cow;
+use std::str;
+
 use crate::error::Result;
 #[cfg(feature = "inline-images")]
 use crate::inline_images::{InlineImageCollector, InlineImageFormat, InlineImageSource};
@@ -971,7 +974,9 @@ fn convert_html_impl(
         .replace("<hr/>", "<hr>")
         .replace("<img/>", "<img>");
 
-    let dom = tl::parse(&html, tl::ParserOptions::default())
+    let html = strip_script_and_style_sections(&html);
+
+    let dom = tl::parse(html.as_ref(), tl::ParserOptions::default())
         .map_err(|_| crate::error::ConversionError::ParseError("Failed to parse HTML".to_string()))?;
 
     let parser = dom.parser();
@@ -1075,6 +1080,161 @@ fn convert_html_impl(
     }
 }
 
+fn strip_script_and_style_sections(input: &str) -> Cow<'_, str> {
+    const TAGS: [&[u8]; 2] = [b"script", b"style"];
+    const SVG: &[u8] = b"svg";
+
+    let bytes = input.as_bytes();
+    let len = bytes.len();
+    let mut idx = 0;
+    let mut last = 0;
+    let mut output: Option<String> = None;
+    let mut svg_depth = 0usize;
+
+    while idx < len {
+        if bytes[idx] == b'<' {
+            if matches_tag_start(bytes, idx + 1, SVG) {
+                if let Some(open_end) = find_tag_end(bytes, idx + 1 + SVG.len()) {
+                    svg_depth += 1;
+                    idx = open_end;
+                    continue;
+                }
+            } else if matches_end_tag_start(bytes, idx + 1, SVG) {
+                if let Some(close_end) = find_tag_end(bytes, idx + 2 + SVG.len()) {
+                    if svg_depth > 0 {
+                        svg_depth = svg_depth.saturating_sub(1);
+                    }
+                    idx = close_end;
+                    continue;
+                }
+            }
+
+            if svg_depth == 0 {
+                let mut handled = false;
+                for tag in TAGS {
+                    if matches_tag_start(bytes, idx + 1, tag) {
+                        if let Some(open_end) = find_tag_end(bytes, idx + 1 + tag.len()) {
+                            let remove_end = find_closing_tag(bytes, open_end, tag).unwrap_or(len);
+                            let out = output.get_or_insert_with(|| String::with_capacity(input.len()));
+                            out.push_str(&input[last..idx]);
+                            out.push_str(&input[idx..open_end]);
+                            out.push_str("</");
+                            out.push_str(str::from_utf8(tag).unwrap());
+                            out.push('>');
+
+                            last = remove_end;
+                            idx = remove_end;
+                            handled = true;
+                        }
+                    }
+
+                    if handled {
+                        break;
+                    }
+                }
+
+                if handled {
+                    continue;
+                }
+            }
+        }
+
+        idx += 1;
+    }
+
+    if let Some(mut out) = output {
+        if last < input.len() {
+            out.push_str(&input[last..]);
+        }
+        Cow::Owned(out)
+    } else {
+        Cow::Borrowed(input)
+    }
+}
+
+fn matches_tag_start(bytes: &[u8], mut start: usize, tag: &[u8]) -> bool {
+    if start >= bytes.len() {
+        return false;
+    }
+
+    if start + tag.len() > bytes.len() {
+        return false;
+    }
+
+    if !bytes[start..start + tag.len()].eq_ignore_ascii_case(tag) {
+        return false;
+    }
+
+    start += tag.len();
+
+    match bytes.get(start) {
+        Some(b'>' | b'/' | b' ' | b'\t' | b'\n' | b'\r') => true,
+        Some(_) => false,
+        None => true,
+    }
+}
+
+fn find_tag_end(bytes: &[u8], mut idx: usize) -> Option<usize> {
+    let len = bytes.len();
+    let mut in_quote: Option<u8> = None;
+
+    while idx < len {
+        match bytes[idx] {
+            b'"' | b'\'' => {
+                if let Some(current) = in_quote {
+                    if current == bytes[idx] {
+                        in_quote = None;
+                    }
+                } else {
+                    in_quote = Some(bytes[idx]);
+                }
+            }
+            b'>' if in_quote.is_none() => return Some(idx + 1),
+            _ => {}
+        }
+        idx += 1;
+    }
+
+    None
+}
+
+fn find_closing_tag(bytes: &[u8], mut idx: usize, tag: &[u8]) -> Option<usize> {
+    let len = bytes.len();
+    let mut depth = 1usize;
+
+    while idx < len {
+        if bytes[idx] == b'<' {
+            if matches_tag_start(bytes, idx + 1, tag) {
+                if let Some(next) = find_tag_end(bytes, idx + 1 + tag.len()) {
+                    depth += 1;
+                    idx = next;
+                    continue;
+                }
+            } else if matches_end_tag_start(bytes, idx + 1, tag) {
+                if let Some(close) = find_tag_end(bytes, idx + 2 + tag.len()) {
+                    depth -= 1;
+                    if depth == 0 {
+                        return Some(close);
+                    }
+                    idx = close;
+                    continue;
+                }
+            }
+        }
+
+        idx += 1;
+    }
+
+    None
+}
+
+fn matches_end_tag_start(bytes: &[u8], start: usize, tag: &[u8]) -> bool {
+    if start >= bytes.len() || bytes[start] != b'/' {
+        return false;
+    }
+    matches_tag_start(bytes, start + 1, tag)
+}
+
 /// Check if an element is inline (not block-level).
 fn is_inline_element(tag_name: &str) -> bool {
     matches!(
@@ -4002,6 +4162,22 @@ mod tests {
         assert_eq!(calculate_list_continuation_indent(4), 7);
     }
 
+    #[test]
+    fn strips_script_sections_without_removing_following_content() {
+        let input = "<div>before</div><script>1 < 2</script><p>after</p>";
+        let stripped = strip_script_and_style_sections(input);
+        assert_eq!(stripped, "<div>before</div><script></script><p>after</p>");
+    }
+
+    #[test]
+    fn strips_multiline_script_sections() {
+        let input = "<html>\n<script>1 < 2</script>\nContent\n</html>";
+        let stripped = strip_script_and_style_sections(input);
+        assert!(stripped.contains("Content"));
+        assert!(stripped.contains("<script"));
+        assert!(!stripped.contains("1 < 2"));
+    }
+
     #[test]
     fn test_add_list_continuation_indent_blank_line() {
         let opts = ConversionOptions::default();

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/crates/html-to-markdown/src/hocr/converter.rs

@@ -92,6 +92,7 @@ pub fn convert_to_markdown_with_options(
         );
     }
 
+    collapse_extra_newlines(&mut output);
     output.trim().to_string()
 }
 
@@ -185,7 +186,7 @@ fn convert_element(
             if enable_spatial_tables {
                 if let Some(table_markdown) = try_spatial_table_reconstruction(element) {
                     output.push_str(&table_markdown);
-                    output.push_str("\n\n");
+                    ensure_trailing_blank_line(output);
                     return;
                 }
             }
@@ -324,7 +325,7 @@ fn convert_element(
             if enable_spatial_tables {
                 if let Some(table_markdown) = try_spatial_table_reconstruction(element) {
                     output.push_str(&table_markdown);
-                    output.push_str("\n\n");
+                    ensure_trailing_blank_line(output);
                 } else {
                     // Fallback: process children normally
                     let mut sorted_children: Vec<_> = element.children.iter().collect();
@@ -334,7 +335,7 @@ fn convert_element(
                     for child in sorted_children {
                         convert_element(child, output, depth + 1, preserve_structure, enable_spatial_tables, ctx);
                     }
-                    output.push_str("\n\n");
+                    ensure_trailing_blank_line(output);
                 }
             } else {
                 // Fallback: process children normally
@@ -345,7 +346,7 @@ fn convert_element(
                 for child in sorted_children {
                     convert_element(child, output, depth + 1, preserve_structure, enable_spatial_tables, ctx);
                 }
-                output.push_str("\n\n");
+                ensure_trailing_blank_line(output);
             }
         }
 
@@ -361,7 +362,7 @@ fn convert_element(
             for child in sorted_children {
                 convert_element(child, output, depth + 1, preserve_structure, enable_spatial_tables, ctx);
             }
-            output.push_str("\n\n");
+            ensure_trailing_blank_line(output);
         }
 
         // Images - markdown image placeholder or alt text
@@ -463,6 +464,41 @@ fn convert_element(
     }
 }
 
+fn ensure_trailing_blank_line(output: &mut String) {
+    while output.ends_with("\n\n\n") {
+        output.pop();
+    }
+    if output.ends_with("\n\n") {
+        return;
+    }
+    if output.ends_with('\n') {
+        output.push('\n');
+    } else {
+        output.push_str("\n\n");
+    }
+}
+
+fn collapse_extra_newlines(output: &mut String) {
+    let mut collapsed = String::with_capacity(output.len());
+    let mut newline_count = 0;
+
+    for ch in output.chars() {
+        if ch == '\n' {
+            newline_count += 1;
+            if newline_count <= 2 {
+                collapsed.push('\n');
+            }
+        } else {
+            newline_count = 0;
+            collapsed.push(ch);
+        }
+    }
+
+    if collapsed.len() != output.len() {
+        *output = collapsed;
+    }
+}
+
 fn append_text_and_children(
     element: &HocrElement,
     output: &mut String,

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/html_to_markdown/__init__.py

@@ -49,4 +49,4 @@ __all__ = [
     "markdownify",
 ]
 
-__version__ = "2.3.4"
+__version__ = "2.4.1"

{html_to_markdown-2.3.4 → html_to_markdown-2.4.1}/pyproject.toml

@@ -7,7 +7,7 @@ requires = [
 
 [project]
 name = "html-to-markdown"
-version = "2.3.4"
+version = "2.4.1"
 description = "High-performance HTML to Markdown converter powered by Rust with a clean Python API"
 readme = "README_PYPI.md"
 keywords = [
@@ -54,15 +54,15 @@ urls.Repository = "https://github.com/Goldziher/html-to-markdown.git"
 [dependency-groups]
 dev = [
   "covdefaults>=2.3",
-  "memray>=1.18; sys_platform!='win32'",
+  "memray>=1.19.1; sys_platform!='win32'",
   "mypy>=1.18.2",
   "pre-commit>=4.3",
-  "psutil>=7.1; sys_platform!='win32'",
+  "psutil>=7.1.1; sys_platform!='win32'",
   "pytest>=8.4.2",
   "pytest-benchmark>=5.1",
   "pytest-cov>=7",
   "pytest-mock>=3.15.1",
-  "ruff>=0.13.3",
+  "ruff>=0.14.1",
   "types-psutil>=7.0.0.20251001",
   "uv-bump",
 ]