Port hardsubx utility (#1443)

* set up bindings conversion of hardsubx utility functions (and structs) and set up the module * add low level ffmpeg rust binding * Methods ported: - convert_pts_to_ns - convert_pts_to_ms - convert_pts_to_s A pure rust method was added called _edit_distance_rec that implements levenstein distance calculation using recursion and dynamic programming The port of edit_distance_rec is simply a wrapper that calls above function. This redundancy won't be nevessary as more downstream modules are ported to Rust * put C code of hardsubx_utility under define rust flag * run formatter * make compilation of hardsubx rust modules conditional on the HARDSUBX and the OCR flags. Make ffmpeg a conditional dependency based on those flags * remove namespaced dependency in cargo because that is a nightly feature * add conditioal compilatio of ffmpeg related bindigs in build.rs * make clang argument of -DENABLE_HARDSUBX conditional on cargo feature of hardsubx_ocr * enable specific relevant features for ffmpeg-sys-next * enable hardsubx_ocr feature in windows build * add build feature in ffmpeg-sys-next * ffmpeg build feature is conditional on platform * Revert "ffmpeg build feature is conditional on platform" This reverts commit e456fee942. This is because conditional features do not work in cargo toml * install yasm in the linux build github action for ocr and hardsubx enabled cmake * turn globals to locals to reduce code * remove redundant attributes * style changes * make import of ffmpeg-sys-next conditional on hardsubx_ocr flag * add --all-features flag in clippy for github workflow * run formatter * fix clippy command * install yasm as part of rust format build check * install libtesseract-dev etc. for clippy build test * readability change * declare the function edit_distance as unsafe * remove commented code * formatting changes * combine declaration and assignment * add build command for building hardsubx rust context to issue: #1445 * make hardsubx rust work with autoconf build. For issue: #1445 * update autoconf for mac for issue #1445
2026-07-08 18:06:30 +00:00 · 2022-07-13 14:36:30 +05:30
parent 0bd213e789
commit 170066f046
15 changed files with 280 additions and 58 deletions
--- a/.github/workflows/build_linux.yml
+++ b/.github/workflows/build_linux.yml
@@ -75,7 +75,7 @@ jobs:
    steps:
    - uses: actions/checkout@v3
    - name: dependencies
-      run: sudo apt update && sudo apt install libtesseract-dev libavformat-dev libswscale-dev
+      run: sudo apt update && sudo apt install libtesseract-dev libavformat-dev libswscale-dev yasm
    - name: cmake
      run: mkdir build && cd build && cmake -DWITH_OCR=ON -DWITH_HARDSUBX=ON ../src
    - name: build
--- a/.github/workflows/format.yml
+++ b/.github/workflows/format.yml
@@ -45,7 +45,9 @@ jobs:
          toolchain: 1.56.0
          override: true
          components: rustfmt, clippy
+      - name: dependencies
+        run: sudo apt update && sudo apt install libtesseract-dev libavformat-dev libswscale-dev yasm
      - name: rustfmt
        run: cargo fmt --all -- --check
      - name: clippy
-        run: cargo clippy -- -D warnings
+        run: cargo clippy --all-features -- -D warnings
--- a/linux/Makefile.am
+++ b/linux/Makefile.am
@@ -331,22 +331,6 @@ ccextractor_CPPFLAGS =-I../src/lib_ccx/ -I../src/thirdparty/gpacmp4/ -I../src/th

 ccextractor_LDADD=-lm -lpthread -ldl

-if WITH_RUST
-ccextractor_LDADD += ./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a
-else
-ccextractor_CFLAGS += -DDISABLE_RUST
-ccextractor_CPPFLAGS += -DDISABLE_RUST
-endif
-
-if DEBUG_RELEASE
-CARGO_RELEASE_ARGS=
-else
-CARGO_RELEASE_ARGS=--release
-endif
-
-./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a:
-	cd ../src/rust && \
-	CARGO_TARGET_DIR=../../linux/rust $(CARGO) build $(CARGO_RELEASE_ARGS);

 if SYS_IS_LINUX
 ccextractor_CFLAGS += -O3 -s -DGPAC_CONFIG_LINUX
@@ -361,6 +345,8 @@ if SYS_IS_64_BIT
 ccextractor_CFLAGS += -DGPAC_64_BITS
 endif

+HARDSUBX_FEATURE_RUST=
+
 if HARDSUBX_IS_ENABLED
 ccextractor_CFLAGS += -DENABLE_HARDSUBX
 ccextractor_CPPFLAGS+= ${libavcodec_CFLAGS}
@@ -372,6 +358,7 @@ AV_LIB += ${libavformat_LIBS}
 AV_LIB += ${libavutil_LIBS}
 AV_LIB += ${libswscale_LIBS}
 ccextractor_LDADD += $(AV_LIB)
+HARDSUBX_FEATURE_RUST += --features "hardsubx_ocr"
 endif

 if OCR_IS_ENABLED
@@ -398,5 +385,22 @@ ccextractor_LDADD += $(TESS_LIB)
 ccextractor_LDADD += $(LEPT_LIB)
 endif

+if WITH_RUST
+ccextractor_LDADD += ./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a
+else
+ccextractor_CFLAGS += -DDISABLE_RUST
+ccextractor_CPPFLAGS += -DDISABLE_RUST
+endif
+
+if DEBUG_RELEASE
+CARGO_RELEASE_ARGS=
+else
+CARGO_RELEASE_ARGS=--release
+endif
+
+./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a:
+	cd ../src/rust && \
+	CARGO_TARGET_DIR=../../linux/rust $(CARGO) build $(HARDSUBX_FEATURE_RUST) $(CARGO_RELEASE_ARGS);
+
 EXTRA_DIST = ../src/thirdparty/gpacmp4/gpac/sync_layer.h ../src/lib_ccx/ccfont2.xbm ../src/thirdparty/utf8proc/utf8proc_data.c fonts/ icon/

--- a/linux/build
+++ b/linux/build
@@ -84,7 +84,13 @@ else
    fi 
    
    echo "Building rust files..."
-    (cd ../src/rust && CARGO_TARGET_DIR=../../linux/rust cargo build) || { echo "Failed. " ; exit 1; }
+    echo "${BLD_FLAGS}"
+    tokens=( ${BLD_FLAGS} )
+    if [ ${tokens[0]} = "-DENABLE_HARDSUBX" ]; then
+        (cd ../src/rust && CARGO_TARGET_DIR=../../linux/rust cargo build --features "hardsubx_ocr") || { echo "Failed. " ; exit 1; }
+    else
+        (cd ../src/rust && CARGO_TARGET_DIR=../../linux/rust cargo build) || { echo "Failed. " ; exit 1; }
+    fi
    cp rust/debug/libccx_rust.a ./libccx_rust.a
 fi

--- a/mac/Makefile.am
+++ b/mac/Makefile.am
@@ -331,22 +331,6 @@ ccextractor_CPPFLAGS =-I../src/lib_ccx/ -I../src/thirdparty/gpacmp4/ -I../src/th

 ccextractor_LDADD=-lm -lpthread -ldl

-if WITH_RUST
-ccextractor_LDADD += ./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a
-else
-ccextractor_CFLAGS += -DDISABLE_RUST
-ccextractor_CPPFLAGS += -DDISABLE_RUST
-endif
-
-if DEBUG_RELEASE
-CARGO_RELEASE_ARGS=
-else
-CARGO_RELEASE_ARGS=--release
-endif
-
-./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a:
-	cd ../src/rust && \
-	CARGO_TARGET_DIR=../../linux/rust $(CARGO) build $(CARGO_RELEASE_ARGS);

 if SYS_IS_LINUX
 ccextractor_CFLAGS += -O3 -s -DGPAC_CONFIG_LINUX
@@ -361,6 +345,8 @@ if SYS_IS_64_BIT
 ccextractor_CFLAGS += -DGPAC_64_BITS
 endif

+HARDSUBX_FEATURE_RUST=
+
 if HARDSUBX_IS_ENABLED
 ccextractor_CFLAGS += -DENABLE_HARDSUBX
 ccextractor_CPPFLAGS+= ${libavcodec_CFLAGS}
@@ -372,6 +358,7 @@ AV_LIB += ${libavformat_LIBS}
 AV_LIB += ${libavutil_LIBS}
 AV_LIB += ${libswscale_LIBS}
 ccextractor_LDADD += $(AV_LIB)
+HARDSUBX_FEATURE_RUST += --features "hardsubx_ocr"
 endif

 if OCR_IS_ENABLED
@@ -398,4 +385,22 @@ ccextractor_LDADD += $(TESS_LIB)
 ccextractor_LDADD += $(LEPT_LIB)
 endif

+if WITH_RUST
+ccextractor_LDADD += ./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a
+else
+ccextractor_CFLAGS += -DDISABLE_RUST
+ccextractor_CPPFLAGS += -DDISABLE_RUST
+endif
+
+if DEBUG_RELEASE
+CARGO_RELEASE_ARGS=
+else
+CARGO_RELEASE_ARGS=--release
+endif
+
+./rust/@RUST_TARGET_SUBDIR@/libccx_rust.a:
+	cd ../src/rust && \
+	CARGO_TARGET_DIR=../../linux/rust $(CARGO) build $(HARDSUBX_FEATURE_RUST) $(CARGO_RELEASE_ARGS);
+
 EXTRA_DIST = ../src/thirdparty/gpacmp4/gpac/sync_layer.h ../src/lib_ccx/ccfont2.xbm ../src/thirdparty/utf8proc/utf8proc_data.c fonts/ icon/
+
--- a/src/lib_ccx/hardsubx_utility.c
+++ b/src/lib_ccx/hardsubx_utility.c
@@ -1,7 +1,7 @@
 #include "lib_ccx.h"
 #include "utility.h"

-#ifdef ENABLE_HARDSUBX
+#if defined(ENABLE_HARDSUBX) && defined(DISABLE_RUST)
 //TODO: Correct FFMpeg integration
 #include <libavcodec/avcodec.h>
 #include <libavformat/avformat.h>
--- a/src/rust/CMakeLists.txt
+++ b/src/rust/CMakeLists.txt
@@ -1,8 +1,16 @@
+if (WITH_OCR AND WITH_HARDSUBX)
+    set(FEATURE_ARG "\"hardsubx_ocr\"")
+    set(FEATURE_FLAG "--features")
+else ()
+    set(FEATURE_ARG "")
+    set(FEATURE_FLAG "")
+endif ()
+
 if (CMAKE_BUILD_TYPE STREQUAL "Debug")
-    set(CARGO_CMD cargo build)
+    set(CARGO_CMD cargo build ${FEATURE_FLAG} ${FEATURE_ARG})
    set(TARGET_DIR "debug")
 else ()
-    set(CARGO_CMD cargo build --release)
+    set(CARGO_CMD cargo build ${FEATURE_FLAG} ${FEATURE_ARG} --release)
    set(TARGET_DIR "release")
 endif ()

--- a/src/rust/Cargo.lock
+++ b/src/rust/Cargo.lock
@@ -53,7 +53,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0f8523b410d7187a43085e7e064416ea32ded16bd0a4e6fc025e21616d01258f"
 dependencies = [
 "bitflags",
- "cexpr",
+ "cexpr 0.4.0",
 "clang-sys",
 "clap",
 "env_logger",
@@ -69,18 +69,44 @@ dependencies = [
 "which",
 ]

+[[package]]
+name = "bindgen"
+version = "0.59.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2bd2a9a458e8f4304c52c43ebb0cfbd520289f8379a52e329a38afda99bf8eb8"
+dependencies = [
+ "bitflags",
+ "cexpr 0.6.0",
+ "clang-sys",
+ "lazy_static",
+ "lazycell",
+ "peeking_take_while",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+]
+
 [[package]]
 name = "bitflags"
 version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf1de2fe8c75bc145a2f577add951f8134889b4795d47466a54a5c846d691693"

+[[package]]
+name = "cc"
+version = "1.0.73"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fff2a6927b3bb87f9595d67196a70493f627687a71d87a0d692242c33f58c11"
+
 [[package]]
 name = "ccx_rust"
 version = "0.1.0"
 dependencies = [
- "bindgen",
+ "bindgen 0.58.1",
 "env_logger",
+ "ffmpeg-sys-next",
 "iconv",
 "log",
 "palette",
@@ -92,7 +118,16 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f4aedb84272dbe89af497cf81375129abda4fc0a9e7c5d317498c15cc30c0d27"
 dependencies = [
- "nom",
+ "nom 5.1.2",
+]
+
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom 7.1.1",
 ]

 [[package]]
@@ -146,6 +181,20 @@ dependencies = [
 "termcolor",
 ]

+[[package]]
+name = "ffmpeg-sys-next"
+version = "5.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ba12dea33516e30c160ce557c7e43dd857276368eb1cd0eef4fce6529f2dee5"
+dependencies = [
+ "bindgen 0.59.2",
+ "cc",
+ "libc",
+ "num_cpus",
+ "pkg-config",
+ "vcpkg",
+]
+
 [[package]]
 name = "find-crate"
 version = "0.6.3"
@@ -240,6 +289,12 @@ version = "2.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b16bd47d9e329435e309c58469fe0791c2d0d1ba96ec0954152a5ae2b04387dc"

+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
 [[package]]
 name = "nom"
 version = "5.1.2"
@@ -250,6 +305,16 @@ dependencies = [
 "version_check",
 ]

+[[package]]
+name = "nom"
+version = "7.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a8903e5a29a317527874d0402f867152a3d21c908bb0b933e416c65e301d4c36"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
 [[package]]
 name = "num-traits"
 version = "0.2.15"
@@ -259,6 +324,16 @@ dependencies = [
 "autocfg",
 ]

+[[package]]
+name = "num_cpus"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "19e64526ebdee182341572e50e9ad03965aa510cd94427a4549448f285e957a1"
+dependencies = [
+ "hermit-abi",
+ "libc",
+]
+
 [[package]]
 name = "palette"
 version = "0.6.0"
@@ -333,6 +408,12 @@ dependencies = [
 "siphasher",
 ]

+[[package]]
+name = "pkg-config"
+version = "0.3.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1df8c4ec4b0627e53bdf214615ad287367e482558cf84b109250b37464dc03ae"
+
 [[package]]
 name = "ppv-lite86"
 version = "0.2.16"
@@ -490,6 +571,12 @@ version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"

+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
+
 [[package]]
 name = "vec_map"
 version = "0.8.2"
--- a/src/rust/Cargo.toml
+++ b/src/rust/Cargo.toml
@@ -15,6 +15,10 @@ log = "0.4.0"
 env_logger = "0.8.4"
 iconv = "0.1.1"
 palette = "0.6.0"
+ffmpeg-sys-next = { version = "5.0.1", optional = true, default-features = false, features = ["avcodec", "build"]}

 [build-dependencies]
-bindgen = "0.58.1"
+bindgen = "0.58.1"
+
+[features]
+hardsubx_ocr = ["ffmpeg-sys-next"]
--- a/src/rust/build.rs
+++ b/src/rust/build.rs
@@ -2,19 +2,42 @@ use std::env;
 use std::path::PathBuf;

 fn main() {
+    let mut allowlist_functions = vec![
+        ".*(?i)_?dtvcc_.*",
+        "get_visible_.*",
+        "get_fts",
+        "printdata",
+        "writercwtdata",
+    ];
+
+    #[cfg(feature = "hardsubx_ocr")]
+    allowlist_functions.extend_from_slice(&["edit_distance", "convert_pts_to_.*", "av_rescale_q"]);
+
+    let mut allowlist_types = vec![".*(?i)_?dtvcc_.*", "encoder_ctx", "lib_cc_decode"];
+
+    #[cfg(feature = "hardsubx_ocr")]
+    allowlist_types.extend_from_slice(&["AVRational"]);
+
    let mut builder = bindgen::Builder::default()
        // The input header we would like to generate
        // bindings for.
-        .header("wrapper.h")
-        // Tell cargo to invalidate the built crate whenever any of the
-        // included header files changed.
-        .parse_callbacks(Box::new(bindgen::CargoCallbacks));
+        .header("wrapper.h");

-    for type_name in ALLOWLIST_TYPES {
+    // enable hardsubx if and only if the feature is on
+    #[cfg(feature = "hardsubx_ocr")]
+    {
+        builder = builder.clang_arg("-DENABLE_HARDSUBX");
+    }
+
+    // Tell cargo to invalidate the built crate whenever any of the
+    // included header files changed.
+    builder = builder.parse_callbacks(Box::new(bindgen::CargoCallbacks));
+
+    for type_name in allowlist_types {
        builder = builder.allowlist_type(type_name);
    }

-    for fn_name in ALLOWLIST_FUNCTIONS {
+    for fn_name in allowlist_functions {
        builder = builder.allowlist_function(fn_name);
    }

@@ -35,12 +58,4 @@ fn main() {
        .expect("Couldn't write bindings!");
 }

-const ALLOWLIST_FUNCTIONS: &[&str] = &[
-    ".*(?i)_?dtvcc_.*",
-    "get_visible_.*",
-    "get_fts",
-    "printdata",
-    "writercwtdata",
-];
-const ALLOWLIST_TYPES: &[&str] = &[".*(?i)_?dtvcc_.*", "encoder_ctx", "lib_cc_decode"];
 const RUSTIFIED_ENUMS: &[&str] = &["dtvcc_(window|pen)_.*", "ccx_output_format"];
--- a/src/rust/src/hardsubx/mod.rs
+++ b/src/rust/src/hardsubx/mod.rs
@@ -1 +1,2 @@
 pub mod imgops;
+pub mod utility;
--- a/src/rust/src/hardsubx/utility.rs
+++ b/src/rust/src/hardsubx/utility.rs
@@ -0,0 +1,88 @@
+#[cfg(feature = "hardsubx_ocr")]
+use ffmpeg_sys_next::*;
+use std::os::raw::{c_char, c_int};
+use std::{cmp, ffi};
+
+const AV_TIME_BASE: i32 = 1000000;
+const AV_TIME_BASE_Q: AVRational = AVRational {
+    num: 1,
+    den: AV_TIME_BASE,
+};
+
+#[no_mangle]
+pub extern "C" fn convert_pts_to_ns(pts: i64, time_base: AVRational) -> i64 {
+    unsafe { av_rescale_q(pts, time_base, AV_TIME_BASE_Q) }
+}
+
+#[no_mangle]
+pub extern "C" fn convert_pts_to_ms(pts: i64, time_base: AVRational) -> i64 {
+    unsafe { av_rescale_q(pts, time_base, AV_TIME_BASE_Q) / 1000 }
+}
+
+#[no_mangle]
+pub extern "C" fn convert_pts_to_s(pts: i64, time_base: AVRational) -> i64 {
+    unsafe { av_rescale_q(pts, time_base, AV_TIME_BASE_Q) / 1000000 }
+}
+
+fn _edit_distance_rec(
+    word1: &[u8],
+    word2: &[u8],
+    i: usize,
+    j: usize,
+    dp_array: &mut Vec<Vec<i32>>,
+) -> i32 {
+    // Recursive implementation with DP of Levenshtein distance
+
+    if dp_array.is_empty() || dp_array[0].is_empty() {
+        // in case word1  or word2 has length 0
+
+        cmp::max(i as i32, j as i32)
+    } else if dp_array[i][j] != -1 {
+        dp_array[i][j]
+    } else if cmp::min(i, j) == 0 {
+        dp_array[i][j] = cmp::max(i as i32, j as i32);
+        cmp::max(i as i32, j as i32)
+    } else {
+        let length_branch_one = _edit_distance_rec(word1, word2, i - 1, j, dp_array) + 1;
+        let length_branch_two = _edit_distance_rec(word1, word2, i, j - 1, dp_array) + 1;
+
+        let length_branch_three = _edit_distance_rec(word1, word2, i - 1, j - 1, dp_array)
+            + if word1[i - 1] == word2[j - 1] { 0 } else { 1 };
+        dp_array[i][j] = cmp::min(
+            length_branch_one,
+            cmp::min(length_branch_two, length_branch_three),
+        );
+        dp_array[i][j]
+    }
+}
+
+/// # Safety
+///
+/// Function deals with C string pointers
+/// which might be null
+
+#[no_mangle]
+pub unsafe extern "C" fn edit_distance(
+    word1: *mut c_char,
+    word2: *mut c_char,
+    len1: c_int,
+    len2: c_int,
+) -> c_int {
+    // The actual edit_distance function
+
+    let word1_string: &ffi::CStr = ffi::CStr::from_ptr(word1);
+    let word2_string: &ffi::CStr = ffi::CStr::from_ptr(word2);
+
+    let len1 = len1 as usize;
+    let len2 = len2 as usize;
+
+    let mut dp_array = vec![vec![-1; len2 + 1]; len1 + 1];
+
+    _edit_distance_rec(
+        word1_string.to_bytes(),
+        word2_string.to_bytes(),
+        len1,
+        len2,
+        &mut dp_array,
+    ) as c_int
+}
--- a/src/rust/src/lib.rs
+++ b/src/rust/src/lib.rs
@@ -13,6 +13,7 @@ pub mod bindings {
    include!(concat!(env!("OUT_DIR"), "/bindings.rs"));
 }
 pub mod decoder;
+#[cfg(feature = "hardsubx_ocr")]
 pub mod hardsubx;
 pub mod utils;

--- a/src/rust/wrapper.h
+++ b/src/rust/wrapper.h
@@ -4,4 +4,5 @@
 #include "../lib_ccx/ccx_decoders_708_output.h"
 #include "../lib_ccx/ccx_decoders_708_encoding.h"
 #include "../lib_ccx/ccx_common_timing.h"
-#include "../lib_ccx/lib_ccx.h"
+#include "../lib_ccx/lib_ccx.h"
+#include "../lib_ccx/hardsubx.h"
--- a/windows/rustx86.bat
+++ b/windows/rustx86.bat
@@ -1,6 +1,6 @@
 for /f "delims=" %%i in ('cd') do set output=%%i
 set CARGO_TARGET_DIR=%output%
 cd ..\src\rust
-cargo build --target=i686-pc-windows-msvc
+cargo build --target=i686-pc-windows-msvc --features "hardsubx_ocr"
 cd ..\..\windows
 copy i686-pc-windows-msvc\debug\ccx_rust.lib .\ccx_rust.lib