diff --git a/Cargo.lock b/Cargo.lock index 1490ba9..00f5c27 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -214,14 +214,13 @@ dependencies = [ [[package]] name = "epub2mdbook" -version = "0.4.0" +version = "0.5.0" dependencies = [ "clap", "epub", "html2md", "regex", "thiserror 2.0.11", - "url", ] [[package]] @@ -240,15 +239,6 @@ dependencies = [ "miniz_oxide", ] -[[package]] -name = "form_urlencoded" -version = "1.2.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e13624c2627564efccf4934284bdd98cbaa14e79b0b5a141218e507b3a823456" -dependencies = [ - "percent-encoding", -] - [[package]] name = "futf" version = "0.1.5" @@ -299,145 +289,6 @@ dependencies = [ "syn", ] -[[package]] -name = "icu_collections" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "db2fa452206ebee18c4b5c2274dbf1de17008e874b4dc4f0aea9d01ca79e4526" -dependencies = [ - "displaydoc", - "yoke", - "zerofrom", - "zerovec", -] - -[[package]] -name = "icu_locid" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "13acbb8371917fc971be86fc8057c41a64b521c184808a698c02acc242dbf637" -dependencies = [ - "displaydoc", - "litemap", - "tinystr", - "writeable", - "zerovec", -] - -[[package]] -name = "icu_locid_transform" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "01d11ac35de8e40fdeda00d9e1e9d92525f3f9d887cdd7aa81d727596788b54e" -dependencies = [ - "displaydoc", - "icu_locid", - "icu_locid_transform_data", - "icu_provider", - "tinystr", - "zerovec", -] - -[[package]] -name = "icu_locid_transform_data" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "fdc8ff3388f852bede6b579ad4e978ab004f139284d7b28715f773507b946f6e" - -[[package]] -name = "icu_normalizer" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "19ce3e0da2ec68599d193c93d088142efd7f9c5d6fc9b803774855747dc6a84f" -dependencies = [ - "displaydoc", - "icu_collections", - "icu_normalizer_data", - "icu_properties", - "icu_provider", - "smallvec", - "utf16_iter", - "utf8_iter", - "write16", - "zerovec", -] - -[[package]] -name = "icu_normalizer_data" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f8cafbf7aa791e9b22bec55a167906f9e1215fd475cd22adfcf660e03e989516" - -[[package]] -name = "icu_properties" -version = "1.5.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "93d6020766cfc6302c15dbbc9c8778c37e62c14427cb7f6e601d849e092aeef5" -dependencies = [ - "displaydoc", - "icu_collections", - "icu_locid_transform", - "icu_properties_data", - "icu_provider", - "tinystr", - "zerovec", -] - -[[package]] -name = "icu_properties_data" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "67a8effbc3dd3e4ba1afa8ad918d5684b8868b3b26500753effea8d2eed19569" - -[[package]] -name = "icu_provider" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6ed421c8a8ef78d3e2dbc98a973be2f3770cb42b606e3ab18d6237c4dfde68d9" -dependencies = [ - "displaydoc", - "icu_locid", - "icu_provider_macros", - "stable_deref_trait", - "tinystr", - "writeable", - "yoke", - "zerofrom", - "zerovec", -] - -[[package]] -name = "icu_provider_macros" -version = "1.5.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6" -dependencies = [ - "proc-macro2", - "quote", - "syn", -] - -[[package]] -name = "idna" -version = "1.0.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "686f825264d630750a544639377bae737628043f20d38bbc029e8f29ea968a7e" -dependencies = [ - "idna_adapter", - "smallvec", - "utf8_iter", -] - -[[package]] -name = "idna_adapter" -version = "1.2.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "daca1df1c957320b2cf139ac61e7bd64fed304c5040df000a745aa1de3b4ef71" -dependencies = [ - "icu_normalizer", - "icu_properties", -] - [[package]] name = "indexmap" version = "2.7.1" @@ -486,12 +337,6 @@ version = "0.2.169" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a" -[[package]] -name = "litemap" -version = "0.7.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104" - [[package]] name = "lock_api" version = "0.4.12" @@ -548,9 +393,9 @@ checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" [[package]] name = "miniz_oxide" -version = "0.8.4" +version = "0.8.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b3b1c9bd4fe1f0f8b387f6eb9eb3b4a1aa26185e5750efb9140301703f62cd1b" +checksum = "8e3e04debbb59698c15bacbb6d93584a8c0ca9cc3213cb423d31f760d8843ce5" dependencies = [ "adler2", ] @@ -705,9 +550,9 @@ checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c" [[package]] name = "redox_syscall" -version = "0.5.8" +version = "0.5.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "03a862b389f93e68874fbf580b9de08dd02facb9a788ebadaf4a3fd33cf58834" +checksum = "82b568323e98e49e2a0899dcee453dd679fae22d69adf9b11dd508d1549b7e2f" dependencies = [ "bitflags", ] @@ -788,12 +633,6 @@ version = "1.14.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7fcf8323ef1faaee30a44a340193b1ac6814fd9b7b4e88e9d4519a3e4abe1cfd" -[[package]] -name = "stable_deref_trait" -version = "1.2.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" - [[package]] name = "string_cache" version = "0.8.8" @@ -836,17 +675,6 @@ dependencies = [ "unicode-ident", ] -[[package]] -name = "synstructure" -version = "0.13.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971" -dependencies = [ - "proc-macro2", - "quote", - "syn", -] - [[package]] name = "tendril" version = "0.4.3" @@ -898,16 +726,6 @@ dependencies = [ "syn", ] -[[package]] -name = "tinystr" -version = "0.7.6" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9117f5d4db391c1cf6927e7bea3db74b9a1c1add8f7eda9ffd5364f40f57b82f" -dependencies = [ - "displaydoc", - "zerovec", -] - [[package]] name = "toml_datetime" version = "0.6.8" @@ -931,35 +749,12 @@ version = "1.0.17" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "00e2473a93778eb0bad35909dff6a10d28e63f792f16ed15e404fca9d5eeedbe" -[[package]] -name = "url" -version = "2.5.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60" -dependencies = [ - "form_urlencoded", - "idna", - "percent-encoding", -] - [[package]] name = "utf-8" version = "0.7.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9" -[[package]] -name = "utf16_iter" -version = "1.0.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c8232dd3cdaed5356e0f716d285e4b40b932ac434100fe9b7e0e8e935b9e6246" - -[[package]] -name = "utf8_iter" -version = "1.0.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be" - [[package]] name = "utf8parse" version = "0.2.2" @@ -1067,18 +862,6 @@ dependencies = [ "memchr", ] -[[package]] -name = "write16" -version = "1.0.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d1890f4022759daae28ed4fe62859b1236caebfc61ede2f63ed4e695f3f6d936" - -[[package]] -name = "writeable" -version = "0.5.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1e9df38ee2d2c3c5948ea468a8406ff0db0b29ae1ffde1bcf20ef305bcc95c51" - [[package]] name = "xml-rs" version = "0.8.25" @@ -1096,73 +879,6 @@ dependencies = [ "markup5ever", ] -[[package]] -name = "yoke" -version = "0.7.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40" -dependencies = [ - "serde", - "stable_deref_trait", - "yoke-derive", - "zerofrom", -] - -[[package]] -name = "yoke-derive" -version = "0.7.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154" -dependencies = [ - "proc-macro2", - "quote", - "syn", - "synstructure", -] - -[[package]] -name = "zerofrom" -version = "0.1.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cff3ee08c995dee1859d998dea82f7374f2826091dd9cd47def953cae446cd2e" -dependencies = [ - "zerofrom-derive", -] - -[[package]] -name = "zerofrom-derive" -version = "0.1.5" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "595eed982f7d355beb85837f651fa22e90b3c044842dc7f2c2842c086f295808" -dependencies = [ - "proc-macro2", - "quote", - "syn", - "synstructure", -] - -[[package]] -name = "zerovec" -version = "0.10.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "aa2b893d79df23bfb12d5461018d408ea19dfafe76c2c7ef6d4eba614f8ff079" -dependencies = [ - "yoke", - "zerofrom", - "zerovec-derive", -] - -[[package]] -name = "zerovec-derive" -version = "0.10.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6" -dependencies = [ - "proc-macro2", - "quote", - "syn", -] - [[package]] name = "zip" version = "1.1.4" diff --git a/Cargo.toml b/Cargo.toml index c64d5c4..bcc676b 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "epub2mdbook" -version = "0.4.0" +version = "0.5.0" edition = "2024" description = "A tool to convert EPUB files to MDBook format" authors = ["Maverick Liu "] @@ -15,4 +15,3 @@ epub = "2.1.1" html2md = "0.2.15" regex = "1.11.1" thiserror = "2.0.11" -url = "2.5.4" diff --git a/src/lib.rs b/src/lib.rs index b63ecb6..23d2230 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -123,7 +123,7 @@ fn extract_chapters_and_resources( if let Some(parent) = target_path.parent() { fs::create_dir_all(parent)?; } - let html = String::from_utf8(content.clone())?; + let html = String::from_utf8(content)?; let markdown = html2md::parse_html(&html); let markdown = post_process_md(&markdown, html_to_md); fs::write(target_path, markdown)?; @@ -144,28 +144,25 @@ fn extract_chapters_and_resources( /// [ABC]({abc.html}#xxx) /// [ABC]({abc.html}) /// ``` -static LINK_REGEX: LazyLock = +static LINK: LazyLock = LazyLock::new(|| Regex::new(r#"\[[^\]]+\]\(([^#)]+)(?:#[^)]+)?\)"#).expect("unreachable")); - -/// Capture the empty links, eg: -/// ``` -/// [{ABC}]() -/// ``` -static EMPTY_LINK_REGEX: LazyLock = +static EMPTY_LINK: LazyLock = LazyLock::new(|| Regex::new(r#"\[([^\]]+)\]\(\)"#).expect("unreachable")); - +static URL_LINK: LazyLock = + LazyLock::new(|| Regex::new(r"^[a-z][a-z0-9+.-]*:").expect("unreachable")); fn post_process_md(markdown: &str, html_to_md: &HashMap) -> String { let file_name_map = html_to_md .iter() .filter_map(|(k, v)| Some((k.file_name()?, v.file_name()?))) .collect::>(); - let markdown = LINK_REGEX + let markdown = LINK .replace_all(markdown, |caps: &Captures| { // replace [ABC](abc.html#xxx) to [ABC](abc.md#xxx) let origin = &caps[0]; let link = &caps[1]; - if url::Url::parse(link).is_ok() { + // Don't modify links with schemes like `https`. + if URL_LINK.is_match(link) { return origin.to_string(); } let link = match Path::new(&link).file_name() { @@ -184,7 +181,7 @@ fn post_process_md(markdown: &str, html_to_md: &HashMap) -> St .replace(r"![]()", "") .replace(r"[]()", ""); - EMPTY_LINK_REGEX + EMPTY_LINK .replace_all(&markdown, |caps: &Captures| caps[1].to_string()) .to_string() } @@ -210,7 +207,7 @@ mod tests { #[test] fn test_replace_links() { let markdown = r"[hello](hello.html#xxx) [hi](hi.xhtml)"; - let markdown = LINK_REGEX.replace_all(&markdown, |caps: &Captures| { + let markdown = LINK.replace_all(&markdown, |caps: &Captures| { let link = caps[1].to_string(); caps[0].replace(&link, "hello.md") });