bare-x-to-pdf 0.2.0 → 0.3.0

package/core/Cargo.lock

@@ -17,15 +17,6 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "android_system_properties"
-version = "0.1.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ae221649c9976a6f6c56ae1facf410f3ddb33cc661c4b7b61020a912d4237fbc"
-dependencies = [
- "libc",
-]
-
 [[package]]
 name = "approx"
 version = "0.5.1"
@@ -159,24 +150,12 @@ dependencies = [
  "syn 3.0.5",
 ]
 
-[[package]]
-name = "byteorder"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
-
 [[package]]
 name = "byteorder-lite"
 version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f1fe948ff07f4bd06c30984e69f5b4899c516a3ef74f34df92a2df2ab535495"
 
-[[package]]
-name = "bytes"
-version = "1.12.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fc652a48c352aef3ea3aed32080501cf3ef6ed5da78602a020c991775b0aff04"
-
 [[package]]
 name = "cc"
 version = "1.4.6"
@@ -222,19 +201,6 @@ version = "1.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0d1275808335c5583ea45a4141d631dafcb36b79fa8a5e10b00e356b6af3e08a"
 
-[[package]]
-name = "chrono"
-version = "0.4.45"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1aa79e62e7697b8e29b513a68abacf485adcd1fe8284a4316c5ae868e6633327"
-dependencies = [
- "iana-time-zone",
- "js-sys",
- "num-traits",
- "wasm-bindgen",
- "windows-link",
-]
-
 [[package]]
 name = "ciborium"
 version = "0.2.2"
@@ -330,32 +296,6 @@ dependencies = [
  "syn 2.0.119",
 ]
 
-[[package]]
-name = "console_error_panic_hook"
-version = "0.1.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a06aeb73f470f66dcdbf7223caeebb85984942f22f1adb2a088cf9668146bbbc"
-dependencies = [
- "cfg-if",
- "wasm-bindgen",
-]
-
-[[package]]
-name = "console_log"
-version = "1.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "86919cef3e37b9356ccf54d4421208c17ecfda01beae61393e7ffd72916c0ef1"
-dependencies = [
- "log",
- "web-sys",
-]
-
-[[package]]
-name = "core-foundation-sys"
-version = "0.8.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
-
 [[package]]
 name = "core_detect"
 version = "1.0.0"
@@ -866,30 +806,6 @@ version = "0.1.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef68590049bab63a464eee1a1158ac04c6f6613a546d8d90f78636b8b94f171"
 
-[[package]]
-name = "iana-time-zone"
-version = "0.1.65"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
-dependencies = [
- "android_system_properties",
- "core-foundation-sys",
- "iana-time-zone-haiku",
- "js-sys",
- "log",
- "wasm-bindgen",
- "windows-core",
-]
-
-[[package]]
-name = "iana-time-zone-haiku"
-version = "0.1.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
-dependencies = [
- "cc",
-]
-
 [[package]]
 name = "icu_collator"
 version = "2.3.1"
@@ -1160,15 +1076,6 @@ version = "0.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a588916bfdfd92e71cacef98a63d9b1f0d74d6599980d11894290e7ddefffcf7"
 
-[[package]]
-name = "itertools"
-version = "0.15.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8b4baf93f58d4425749ca49a51c50ebab072c5df6994d08fed93541c331481dc"
-dependencies = [
- "either",
-]
-
 [[package]]
 name = "itoa"
 version = "1.0.18"
@@ -1260,16 +1167,6 @@ version = "0.2.189"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3eaf3ede3fee6db1a4c2ee091bf8a8b4dccdc6d17f656fb07896ee72867612f2"
 
-[[package]]
-name = "libloading"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "754ca22de805bb5744484a5b151a9e1a8e837d5dc232c2d7d8c2e3492edc8b60"
-dependencies = [
- "cfg-if",
- "windows-link",
-]
-
 [[package]]
 name = "libm"
 version = "0.2.16"
@@ -1322,12 +1219,6 @@ version = "0.4.34"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f9f8bd3e56ce4dfc153cf470fffbfa98c7620958b312ca5c3a4b8d5181fd13c6"
 
-[[package]]
-name = "maybe-owned"
-version = "0.3.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4facc753ae494aeb6e3c22f839b158aebd4f9270f55cd3c79906c45476c47ab4"
-
 [[package]]
 name = "memchr"
 version = "2.8.3"
@@ -1529,32 +1420,6 @@ dependencies = [
  "ryu",
 ]
 
-[[package]]
-name = "pdfium-render"
-version = "0.9.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8948a803616a9e936b15a6637af2cd48c5fb8ae0fcdeb3c32eac3a540e255a19"
-dependencies = [
- "bitflags",
- "bytemuck",
- "bytes",
- "chrono",
- "console_error_panic_hook",
- "console_log",
- "image",
- "itertools",
- "js-sys",
- "libloading",
- "log",
- "maybe-owned",
- "once_cell",
- "utf16string",
- "vecmath",
- "wasm-bindgen",
- "wasm-bindgen-futures",
- "web-sys",
-]
-
 [[package]]
 name = "peniko"
 version = "0.6.1"
@@ -1639,12 +1504,6 @@ version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
 
-[[package]]
-name = "piston-float"
-version = "1.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad78bf43dcf80e8f950c92b84f938a0fc7590b7f6866fbcbeca781609c115590"
-
 [[package]]
 name = "plist"
 version = "1.10.1"
@@ -1747,6 +1606,17 @@ dependencies = [
  "cc",
 ]
 
+[[package]]
+name = "pulldown-cmark"
+version = "0.13.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e9f068eba8e7071c5f9511831b44f32c740d5adf574e990f946ddb53db2f314e"
+dependencies = [
+ "bitflags",
+ "memchr",
+ "unicase",
+]
+
 [[package]]
 name = "pxfm"
 version = "0.1.30"
@@ -2094,8 +1964,8 @@ version = "0.1.0"
 dependencies = [
  "cfb",
  "encoding_rs",
- "image",
- "pdfium-render",
+ "png",
+ "pulldown-cmark",
  "quick-xml 0.42.0",
  "ttf-parser",
  "typst",
@@ -2808,6 +2678,12 @@ dependencies = [
  "unic-langid-impl",
 ]
 
+[[package]]
+name = "unicase"
+version = "2.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbc4bc3a9f746d862c45cb89d705aa10f187bb96c76001afab07a0d35ce60142"
+
 [[package]]
 name = "unicode-bidi"
 version = "0.3.18"
@@ -2930,15 +2806,6 @@ version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c8232dd3cdaed5356e0f716d285e4b40b932ac434100fe9b7e0e8e935b9e6246"
 
-[[package]]
-name = "utf16string"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b62a1e85e12d5d712bf47a85f426b73d303e2d00a90de5f3004df3596e9d216"
-dependencies = [
- "byteorder",
-]
-
 [[package]]
 name = "utf8_iter"
 version = "1.0.4"
@@ -2955,15 +2822,6 @@ dependencies = [
  "wasm-bindgen",
 ]
 
-[[package]]
-name = "vecmath"
-version = "1.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "956ae1e0d85bca567dee1dcf87fb1ca2e792792f66f87dced8381f99cd91156a"
-dependencies = [
- "piston-float",
-]
-
 [[package]]
 name = "vello_common"
 version = "0.0.8"
@@ -3040,16 +2898,6 @@ dependencies = [
  "wasm-bindgen-shared",
 ]
 
-[[package]]
-name = "wasm-bindgen-futures"
-version = "0.4.78"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ef4c5d3d2cdf5c54f4231181768f5510842e350db025faf1f7163b1030ed928"
-dependencies = [
- "js-sys",
- "wasm-bindgen",
-]
-
 [[package]]
 name = "wasm-bindgen-macro"
 version = "0.2.128"
@@ -3128,16 +2976,6 @@ dependencies = [
  "bitflags",
 ]
 
-[[package]]
-name = "web-sys"
-version = "0.3.105"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fbddc4a036f00ec4f18c83445bd3115cb306a91da554919a099d9222fe4a7f8"
-dependencies = [
- "js-sys",
- "wasm-bindgen",
-]
-
 [[package]]
 name = "web-time"
 version = "1.1.0"
@@ -3163,65 +3001,12 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "windows-core"
-version = "0.62.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
-dependencies = [
- "windows-implement",
- "windows-interface",
- "windows-link",
- "windows-result",
- "windows-strings",
-]
-
-[[package]]
-name = "windows-implement"
-version = "0.60.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.119",
-]
-
-[[package]]
-name = "windows-interface"
-version = "0.59.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.119",
-]
-
 [[package]]
 name = "windows-link"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
 
-[[package]]
-name = "windows-result"
-version = "0.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
-dependencies = [
- "windows-link",
-]
-
-[[package]]
-name = "windows-strings"
-version = "0.5.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
-dependencies = [
- "windows-link",
-]
-
 [[package]]
 name = "windows-sys"
 version = "0.61.2"

package/core/Cargo.toml

@@ -15,10 +15,10 @@ typst-layout = "0.15"
 zip = { version = "8", default-features = false, features = ["deflate"] }
 quick-xml = "0.42"
 ttf-parser = "0.25"
-pdfium-render = "0.9"
 cfb = "0.14"
 encoding_rs = "0.8"
-image = { version = "0.25", default-features = false, features = ["png"] }
+png = "0.18"
+pulldown-cmark = { version = "0.13", default-features = false }
 
 [profile.dev]
 debug = 0

package/core/include/simple_converter.h

@@ -20,7 +20,6 @@ sc_convert(
   const char *from,
   const char *to,
   const char *fonts_dir,
-  const char *pdfium_path,
   sc_buffer_t *out,
   sc_buffer_t *error
 );

package/core/src/doc/mod.rs

@@ -43,6 +43,8 @@ pub fn read(bytes: &[u8]) -> Result<Document, Error> {
 
     let mut doc = Document {
         borders_outside_indent: true,
+        table_at_border_center: true,
+        writer_text_offset: true,
         footnote_separator_width: Some(144.0),
         default_tab: 36.0,
         additive_spacing: false,

package/core/src/docx/mod.rs

@@ -1,7 +1,6 @@
 mod numbering;
 pub use numbering::format_number;
 mod styles;
-pub mod writer;
 
 use crate::error::Error;
 use crate::model::*;
@@ -92,6 +91,8 @@ pub fn read(bytes: &[u8]) -> Result<Document, Error> {
 
     let mut doc = Document {
         borders_outside_indent: true,
+        table_at_border_center: true,
+        writer_text_offset: true,
         footnote_separator_width: Some(144.0),
         default_tab: 36.0,
         ..Document::default()
@@ -114,6 +115,16 @@ pub fn read(bytes: &[u8]) -> Result<Document, Error> {
             .and_then(|c| c.child("doNotUseHTMLParagraphAutoSpacing"))
             .map(flag)
             .unwrap_or(false);
+        let compat_mode = settings
+            .child("compat")
+            .and_then(|c| {
+                c.children("compatSetting")
+                    .find(|s| s.attr("name") == Some("compatibilityMode"))
+            })
+            .and_then(|s| s.attr("val"))
+            .and_then(|v| v.parse::<u32>().ok())
+            .unwrap_or(0);
+        doc.table_at_border_center = compat_mode == 0 || compat_mode >= 15;
     }
 
     let mut blocks = Vec::new();

package/core/src/lib.rs

@@ -1,9 +1,10 @@
 pub mod doc;
 pub mod docx;
 pub mod error;
+pub mod markdown;
 pub mod model;
+pub mod odf_chart;
 pub mod odt;
-pub mod pdf;
 pub mod pptx;
 pub mod typst_backend;
 pub mod xlsx;
@@ -17,13 +18,15 @@ use std::path::Path;
 
 pub struct Options<'a> {
     pub fonts_dir: &'a Path,
-    pub pdfium_path: &'a Path,
-    pub background_scale: f32,
 }
 
 pub fn convert(input: &[u8], from: &str, to: &str, options: &Options) -> Result<Vec<u8>, Error> {
+    let compound = input.starts_with(&[0xD0, 0xCF, 0x11, 0xE0]).then(|| compound_kind(input)).flatten();
     let from = match from {
         "doc" | "dot" if input.starts_with(b"PK") => "docx",
+        "xls" | "xlt" if input.starts_with(b"PK") => "xlsx",
+        "doc" | "dot" | "docx" | "docm" | "dotx" | "dotm" if compound == Some("xls") => "xls",
+        "xls" | "xlt" | "xlsx" | "xlsm" | "xltx" | "xltm" if compound == Some("doc") => "doc",
         "docx" | "docm" | "dotx" | "dotm" if input.starts_with(&[0xD0, 0xCF, 0x11, 0xE0]) => "doc",
         "odt" | "ott" if input.starts_with(b"<") || input.starts_with(&[0xEF, 0xBB, 0xBF]) => "fodt",
         other => other,
@@ -45,18 +48,41 @@ pub fn convert(input: &[u8], from: &str, to: &str, options: &Options) -> Result<
             let document = xlsx::read(input)?;
             typst_backend::render_pdf(&document, options.fonts_dir)
         }
+        ("odp" | "otp" | "fodp", "pdf") => {
+            let document = odt::read_odp(input)?;
+            typst_backend::render_pdf(&document, options.fonts_dir)
+        }
+        ("ods" | "ots" | "fods", "pdf") => {
+            let document = xlsx::read_ods(input)?;
+            typst_backend::render_pdf(&document, options.fonts_dir)
+        }
+        ("xls" | "xlt", "pdf") => {
+            let document = xlsx::read_xls(input)?;
+            typst_backend::render_pdf(&document, options.fonts_dir)
+        }
+        ("md" | "markdown", "pdf") => {
+            let document = markdown::read(input)?;
+            typst_backend::render_pdf(&document, options.fonts_dir)
+        }
         ("pptx", "pdf") => {
             let document = pptx::read(input)?;
             typst_backend::render_pdf(&document, options.fonts_dir)
         }
-        ("pdf", "docx") => {
-            let document = pdf::read(input, options.pdfium_path, options.background_scale)?;
-            docx::writer::write_fixed(&document)
-        }
         _ => Err(Error::new(format!("conversion from {from} to {to} is not supported"))),
     }
 }
 
+fn compound_kind(input: &[u8]) -> Option<&'static str> {
+    let file = cfb::CompoundFile::open(std::io::Cursor::new(input)).ok()?;
+    if file.exists("/WordDocument") {
+        Some("doc")
+    } else if file.exists("/Workbook") || file.exists("/Book") {
+        Some("xls")
+    } else {
+        None
+    }
+}
+
 #[repr(C)]
 pub struct Buffer {
     pub data: *mut u8,
@@ -96,7 +122,6 @@ pub unsafe extern "C" fn sc_convert(
     from: *const c_char,
     to: *const c_char,
     fonts_dir: *const c_char,
-    pdfium_path: *const c_char,
     out: *mut Buffer,
     error: *mut Buffer,
 ) -> i32 {
@@ -115,11 +140,8 @@ pub unsafe extern "C" fn sc_convert(
         let from = c_string(from, "from")?;
         let to = c_string(to, "to")?;
         let fonts_dir = c_string(fonts_dir, "fontsDir")?;
-        let pdfium_path = c_string(pdfium_path, "pdfiumPath")?;
         let options = Options {
             fonts_dir: Path::new(&fonts_dir),
-            pdfium_path: Path::new(&pdfium_path),
-            background_scale: 2.0,
         };
         convert(input, &from, &to, &options)
     }));