From d44ccdffa3d85af01e758f08b07e437c6d6f83f4 Mon Sep 17 00:00:00 2001
From: Dmitry <b4tm4n@mail.ru>
Date: Mon, 12 Sep 2022 20:50:31 +0300
Subject: [PATCH] initial commit

---
 .gitignore  |   3 +
 Cargo.lock  | 456 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 Cargo.toml  |  16 ++
 src/main.rs | 129 +++++++++++++++
 4 files changed, 604 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Cargo.lock
 create mode 100644 Cargo.toml
 create mode 100644 src/main.rs

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..48a0746
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+/target
+baza*.zip
+
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..a372df3
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,456 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "adler"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
+
+[[package]]
+name = "aes"
+version = "0.7.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9e8b47f52ea9bae42228d07ec09eb676433d7c4ed1ebdf0f1d1c29ed446f1ab8"
+dependencies = [
+ "cfg-if",
+ "cipher",
+ "cpufeatures",
+ "opaque-debug",
+]
+
+[[package]]
+name = "base64ct"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a32fd6af2b5827bce66c29053ba0e7c42b9dcab01835835058558c10851a46b"
+
+[[package]]
+name = "block-buffer"
+version = "0.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cce20737498f97b993470a6e536b8523f0af7892a4f928cceb1ac5e52ebe7e"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "byteorder"
+version = "1.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
+
+[[package]]
+name = "bzip2"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6afcd980b5f3a45017c57e57a2fcccbb351cc43a356ce117ef760ef8052b89b0"
+dependencies = [
+ "bzip2-sys",
+ "libc",
+]
+
+[[package]]
+name = "bzip2-sys"
+version = "0.1.11+1.0.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "736a955f3fa7875102d57c82b8cac37ec45224a07fd32d58f9f7a186b6cd4cdc"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+]
+
+[[package]]
+name = "cc"
+version = "1.0.73"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fff2a6927b3bb87f9595d67196a70493f627687a71d87a0d692242c33f58c11"
+dependencies = [
+ "jobserver",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "cipher"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7ee52072ec15386f770805afd189a01c8841be8696bed250fa2f13c4c0d6dfb7"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "constant_time_eq"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "245097e9a4535ee1e3e3931fcfcd55a796a44c643e8596ff6566d68f09b87bbc"
+
+[[package]]
+name = "cpufeatures"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d997bd5e24a5928dd43e46dc529867e207907fe0b239c3477d924f7f2ca320"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crc32fast"
+version = "1.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b540bd8bc810d3885c6ea91e2018302f68baba2129ab3e88f32389ee9370880d"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "51887d4adc7b564537b15adcfb307936f8075dfcd5f00dde9a9f1d29383682bc"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+]
+
+[[package]]
+name = "crypto-common"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
+[[package]]
+name = "digest"
+version = "0.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2fb860ca6fafa5552fb6d0e816a69c8e49f0908bf524e30a90d97c85892d506"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+ "subtle",
+]
+
+[[package]]
+name = "encoding"
+version = "0.2.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b0d943856b990d12d3b55b359144ff341533e516d94098b1d3fc1ac666d36ec"
+dependencies = [
+ "encoding-index-japanese",
+ "encoding-index-korean",
+ "encoding-index-simpchinese",
+ "encoding-index-singlebyte",
+ "encoding-index-tradchinese",
+]
+
+[[package]]
+name = "encoding-index-japanese"
+version = "1.20141219.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04e8b2ff42e9a05335dbf8b5c6f7567e5591d0d916ccef4e0b1710d32a0d0c91"
+dependencies = [
+ "encoding_index_tests",
+]
+
+[[package]]
+name = "encoding-index-korean"
+version = "1.20141219.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4dc33fb8e6bcba213fe2f14275f0963fd16f0a02c878e3095ecfdf5bee529d81"
+dependencies = [
+ "encoding_index_tests",
+]
+
+[[package]]
+name = "encoding-index-simpchinese"
+version = "1.20141219.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d87a7194909b9118fc707194baa434a4e3b0fb6a5a757c73c3adb07aa25031f7"
+dependencies = [
+ "encoding_index_tests",
+]
+
+[[package]]
+name = "encoding-index-singlebyte"
+version = "1.20141219.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3351d5acffb224af9ca265f435b859c7c01537c0849754d3db3fdf2bfe2ae84a"
+dependencies = [
+ "encoding_index_tests",
+]
+
+[[package]]
+name = "encoding-index-tradchinese"
+version = "1.20141219.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fd0e20d5688ce3cab59eb3ef3a2083a5c77bf496cb798dc6fcdb75f323890c18"
+dependencies = [
+ "encoding_index_tests",
+]
+
+[[package]]
+name = "encoding_index_tests"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a246d82be1c9d791c5dfde9a2bd045fc3cbba3fa2b11ad558f27d01712f00569"
+
+[[package]]
+name = "flate2"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f82b0f4c27ad9f8bfd1f3208d882da2b09c301bc1c828fd3a00d0216d2fbbff6"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
+[[package]]
+name = "generic-array"
+version = "0.14.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bff49e947297f3312447abdca79f45f4738097cc82b06e72054d2223f601f1b9"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
+[[package]]
+name = "hmac"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e"
+dependencies = [
+ "digest",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c8af84674fe1f223a982c933a0ee1086ac4d4052aa0fb8060c12c6ad838e754"
+
+[[package]]
+name = "jobserver"
+version = "0.1.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af25a77299a7f711a01975c35a6a424eb6862092cc2d6c72c4ed6cbc56dfc1fa"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.132"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8371e4e5341c3a96db127eb2465ac681ced4c433e01dd0e938adbef26ba93ba5"
+
+[[package]]
+name = "memchr"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "148fab2e51b4f1cfc66da2a7c32981d1d3c083a803978268bb11fe4b86925e7a"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "miniz_oxide"
+version = "0.5.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96590ba8f175222643a85693f33d26e9c8a015f599c216509b1a6894af675d34"
+dependencies = [
+ "adler",
+]
+
+[[package]]
+name = "num_threads"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2819ce041d2ee131036f4fc9d6ae7ae125a3a40e97ba64d04fe799ad9dabbb44"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f7254b99e31cad77da24b08ebf628882739a608578bb1bcdfc1f9c21260d7c0"
+
+[[package]]
+name = "opaque-debug"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "624a8340c38c1b80fd549087862da4ba43e08858af025b236e509b6649fc13d5"
+
+[[package]]
+name = "password-hash"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d791538a6dcc1e7cb7fe6f6b58aca40e7f79403c45b2bc274008b5e647af1d8"
+dependencies = [
+ "base64ct",
+ "rand_core",
+ "subtle",
+]
+
+[[package]]
+name = "pbkdf2"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "271779f35b581956db91a3e55737327a03aa051e90b1c47aeb189508533adfd7"
+dependencies = [
+ "digest",
+ "hmac",
+ "password-hash",
+ "sha2",
+]
+
+[[package]]
+name = "pkg-config"
+version = "0.3.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1df8c4ec4b0627e53bdf214615ad287367e482558cf84b109250b37464dc03ae"
+
+[[package]]
+name = "rand_core"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d34f1408f55294453790c48b2f1ebbb1c5b4b7563eb1f418bcfcfdbb06ebb4e7"
+
+[[package]]
+name = "sha1"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "006769ba83e921b3085caa8334186b00cf92b4cb1a6cf4632fbccc8eff5c7549"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
+[[package]]
+name = "sha2"
+version = "0.10.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf9db03534dff993187064c4e0c05a5708d2a9728ace9a8959b77bedf415dac5"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
+[[package]]
+name = "subtle"
+version = "2.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6bdef32e8150c2a081110b42772ffe7d7c9032b606bc226c8260fd97e0976601"
+
+[[package]]
+name = "textstream"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e7ed81b342f6566026755e7f4b7798810b1c159722e427d212ce72c2c58ffdaa"
+dependencies = [
+ "encoding",
+ "memchr",
+]
+
+[[package]]
+name = "time"
+version = "0.3.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3c3f9a28b618c3a6b9251b6908e9c99e04b9e5c02e6581ccbb67d59c34ef7f9b"
+dependencies = [
+ "itoa",
+ "libc",
+ "num_threads",
+ "time-macros",
+]
+
+[[package]]
+name = "time-macros"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42657b1a6f4d817cda8e7a0ace261fe0cc946cf3a80314390b22cc61ae080792"
+
+[[package]]
+name = "typenum"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dcf81ac59edc17cc8697ff311e8f5ef2d99fcbd9817b34cec66f90b6c3dfd987"
+
+[[package]]
+name = "version_check"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
+
+[[package]]
+name = "zip"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf225bcf73bb52cbb496e70475c7bd7a3f769df699c0020f6c7bd9a96dcf0b8d"
+dependencies = [
+ "aes",
+ "byteorder",
+ "bzip2",
+ "constant_time_eq",
+ "crc32fast",
+ "crossbeam-utils",
+ "flate2",
+ "hmac",
+ "pbkdf2",
+ "sha1",
+ "time",
+ "zstd",
+]
+
+[[package]]
+name = "zstd"
+version = "0.10.2+zstd.1.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5f4a6bd64f22b5e3e94b4e238669ff9f10815c27a5180108b849d24174a83847"
+dependencies = [
+ "zstd-safe",
+]
+
+[[package]]
+name = "zstd-safe"
+version = "4.1.6+zstd.1.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94b61c51bb270702d6167b8ce67340d2754b088d0c091b06e593aa772c3ee9bb"
+dependencies = [
+ "libc",
+ "zstd-sys",
+]
+
+[[package]]
+name = "zstd-sys"
+version = "1.6.3+zstd.1.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc49afa5c8d634e75761feda8c592051e7eeb4683ba827211eb0d731d3402ea8"
+dependencies = [
+ "cc",
+ "libc",
+]
+
+[[package]]
+name = "ztb_recode"
+version = "0.1.0"
+dependencies = [
+ "encoding",
+ "textstream",
+ "zip",
+]
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..d511ae2
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,16 @@
+[package]
+name = "ztb_recode"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+encoding = "0.2.33"
+textstream = "0.1.1"
+zip = "0.6.2"
+
+[profile.release]
+opt-level = 3
+debug = false
+lto = true
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..8207136
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,129 @@
+extern crate encoding;
+extern crate textstream;
+extern crate zip;
+
+use encoding::all::{KOI8_R, UTF_8};
+use encoding::Encoding;
+use encoding::{DecoderTrap, EncoderTrap};
+use std::io::{Read, Seek, Write};
+use std::path::PathBuf;
+use std::{fs, io};
+use textstream::TextReader;
+use zip::write::FileOptions;
+use zip::ZipWriter;
+
+const INPUT_FILENAME: &str = "baza.zip";
+const OUTPUT_FILENAME: &str = "baza_utf8.zip";
+
+struct OutFileDescr<'a> {
+    name: String,
+    options: &'a FileOptions,
+    encoding: &'a dyn Encoding,
+    trap: EncoderTrap,
+}
+
+impl<'a> OutFileDescr<'a> {
+    fn new(
+        name: String,
+        options: &'a FileOptions,
+        enc: &'a dyn Encoding,
+        trap: EncoderTrap,
+    ) -> OutFileDescr<'a> {
+        OutFileDescr {
+            name,
+            options,
+            encoding: enc,
+            trap,
+        }
+    }
+}
+
+fn read_file(file: impl Read, enc: &dyn Encoding) -> Result<String, Box<dyn std::error::Error>> {
+    let buf = io::BufReader::new(file);
+    let mut reader = TextReader::new(buf, enc, DecoderTrap::Ignore);
+    let mut result = String::new();
+    reader.read_to_end(&mut result).or(Err("decode error"))?;
+
+    Ok(result)
+}
+
+fn write_file<T: Seek + Write>(
+    arc: &mut ZipWriter<T>,
+    f: OutFileDescr,
+    data: String,
+) -> Result<(), Box<dyn std::error::Error>> {
+    arc.start_file(f.name, *f.options)?;
+    let data = f.encoding.encode(data.as_str(), f.trap)?;
+    arc.write_all(&data)?;
+    Ok(())
+}
+
+fn process_files(files: &[PathBuf]) {
+    if files.is_empty() {
+        return;
+    }
+
+    let enc_input = KOI8_R;
+    let enc_output = UTF_8;
+    let options = zip::write::FileOptions::default()
+        .compression_method(zip::CompressionMethod::Deflated)
+        .compression_level(Some(9));
+
+    let zip_file = fs::File::open(INPUT_FILENAME).unwrap();
+    let zip_reader = io::BufReader::new(zip_file);
+    let mut archive = zip::ZipArchive::new(zip_reader).unwrap();
+
+    let mut outfile = fs::File::create(OUTPUT_FILENAME).unwrap();
+    let mut zip_writer = ZipWriter::new(&mut outfile);
+
+    files.iter().for_each(|name| {
+        let name_str = name.to_str().unwrap();
+
+        // read string from file in input zip
+        let file = archive.by_name(name_str).unwrap();
+        let data = read_file(file, enc_input).unwrap();
+
+        // write string to file in output zip
+        let out_file = OutFileDescr::new(
+            name_str.to_string(),
+            &options,
+            enc_output,
+            EncoderTrap::Ignore,
+        );
+        write_file(&mut zip_writer, out_file, data).unwrap();
+    });
+
+    zip_writer.finish().unwrap();
+}
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    // open archive just to list files
+    let zip_file = fs::File::open(INPUT_FILENAME)?;
+    let zip_reader = io::BufReader::new(zip_file);
+    let mut archive = zip::ZipArchive::new(zip_reader)?;
+
+    let mut source_files: Vec<PathBuf> = (0..archive.len())
+        .map(|i| archive.by_index(i).unwrap().mangled_name())
+        .filter(|name| {
+            // skip files without "txt" extension
+            match name.extension() {
+                Some(ext) => match ext.to_str() {
+                    Some(ext_str) => ext_str.eq_ignore_ascii_case("txt"),
+                    _ => false, // extension is not valid unicode or not txt
+                },
+                _ => false, // no extension in filename
+            }
+        })
+        .collect();
+    drop(archive);
+
+    println!("processing {} files...", source_files.len());
+
+    source_files.sort();
+    let source_files = source_files;
+
+    process_files(&source_files);
+
+    println!("done");
+    Ok(())
+}