Add AVX2 Dependency

This reverts commit 5607dcc72c.

.github/ISSUE_TEMPLATE/bug.yml

@@ -0,0 +1,40 @@
+name: Bug Report
+description: Create a report to fix a bug
+labels: [bug]
+title: "[BUG] <title>"
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Reproduction
+      description: Steps to reproduce the behavior.
+    validations:
+      required: true
+  - type: textarea
+    id: expected-behavior
+    attributes:
+      label: Expected Behavior
+      description: A clear and concise description of what you expected to happen.
+    validations:
+      required: true
+  - type: textarea
+    id: actual-behavior
+    attributes:
+      label: Actual Behavior
+      description: A clear and concise description of what actually happened.
+    validations:
+      required: true
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Add any other context about the problem here.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature.yml

@@ -0,0 +1,35 @@
+name: Feature Request
+description: Suggest an idea for this project
+
+title: "[FEATURE] <title>"
+labels: [enhancement]
+
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+    validations:
+      required: true
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: A clear and concise description of what you want to happen.
+    validations:
+      required: true
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives
+      description: A clear and concise description of any alternative solutions or features you've considered.
+    validations:
+      required: false
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Add any other context or screenshots about the feature request here.
+    validations:
+      required: false

.github/workflows/master-build.yml

@@ -19,34 +19,38 @@ jobs:
       - name: Cache Cargo modules
         id: cache-cargo
         uses: actions/cache@v3
-        env:
-          cache-name: cache-cargo-target-debug
+        continue-on-error: false
         with:
-          path: target
-          key: ${{ runner.os }}-${{ env.cache-name }}-${{ hashFiles('**/Cargo.lock') }}
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
           restore-keys: |
-            ${{ runner.os }}-${{ env.cache-name }}-
+            ${{ runner.os }}-cargo-
       - name: Build
-        run: cargo build --verbose
+        run: make debug
       - name: Run tests
         run: cargo test --verbose -p schemsearch-lib
 
   build-release:
+    needs:
+      - build
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
       - name: Cache Cargo modules
         id: cache-cargo
         uses: actions/cache@v3
-        env:
-          cache-name: cache-cargo-target-release
+        continue-on-error: false
         with:
-          path: target
-          key: ${{ runner.os }}-${{ env.cache-name }}-${{ hashFiles('**/Cargo.lock') }}
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
           restore-keys: |
-            ${{ runner.os }}-${{ env.cache-name }}-
+            ${{ runner.os }}-cargo-
       - name: Build
-        run: cargo build --verbose --release -p schemsearch-cli
+        run: make
       - name: Upload a Build Artifact
         uses: actions/upload-artifact@v3.1.2
         with:

.github/workflows/release-build.yml

@@ -22,15 +22,16 @@ jobs:
       - name: Cache Cargo modules
         id: cache-cargo
         uses: actions/cache@v3
-        env:
-          cache-name: cache-cargo-target-release
+        continue-on-error: false
         with:
-          path: target
-          key: ${{ runner.os }}-${{ env.cache-name }}-${{ hashFiles('**/Cargo.lock') }}
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
           restore-keys: |
-            ${{ runner.os }}-${{ env.cache-name }}-
+            ${{ runner.os }}-cargo-
       - name: Build
-        run: cargo build --verbose --release -p schemsearch-cli
+        run: make
       - name: Create Tarball
         if: ${{ matrix.os != 'windows-latest' }}
         run: tar -czvf schemsearch-cli-${{ matrix.os }}.tar.gz -C target/release schemsearch-cli

Makefile

@@ -0,0 +1,28 @@
+default:
+	@echo "Building (Release)...";
+	cargo rustc --release --color=always -p schemsearch-cli -- -C target-feature=+avx2
+
+sql:
+	@echo "Building (Release)...";
+	cargo rustc --release --color=always -p schemsearch-cli --features sql -- -C target-feature=+avx2
+
+debug:
+	@echo "Building (Debug)...";
+	cargo build -p schemsearch-cli
+
+install: default
+	@echo "Installing...";
+	install -Dm755 target/release/schemsearch-cli /usr/bin/schemsearch
+
+uninstall:
+	@echo "Uninstalling...";
+	rm -f /usr/bin/schemsearch
+
+java:
+	@echo "Building Java...";
+	@echo "WARNING: This is WORK IN PROGRESS!";
+	javac SchemSearch.java
+
+clean:
+	@echo "Cleaning...";
+	cargo clean

README.md

@@ -5,10 +5,10 @@
 
 ## WARNING: This is a work in progress and is really simple right now. It will be improved in the future.
 | Feature                   | Status |
-|------------------------|--------|
+|---------------------------|--------|
 | Block search              | ✅      |
 | Block data less search    | ✅      |
-| Tile entities search   | ❌      |
+| Tile entities data search | ❌      |
 | Entities search           | ❌      |
 
 ---
@@ -41,12 +41,13 @@ schemsearch-cli --help
 ---
 
 ## Roadmap
+A list of features that are planned to be implemented in the future. In order of priority.
 
-- [ ] Tile entities search
+- [ ] Full JSON output (Progressbar)
+- [ ] Use AVX2 for faster search
+- [ ] Tile entities data search
 - [ ] Entities search
-- [ ] Better error handling
-- [ ] Web interface
-- [ ] McEdit search
+- [ ] McEdit Schematic support
 
 ---
 

schemsearch-cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "schemsearch-cli"
-version = "0.1.1"
+version = "0.1.2"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 

schemsearch-cli/src/json_output.rs

@@ -1,5 +1,5 @@
 use serde::{Deserialize, Serialize};
-use schemsearch_lib::SearchBehavior;
+use schemsearch_lib::{Match, SearchBehavior};
 
 #[derive(Serialize, Deserialize, Debug)]
 #[serde(tag = "event")]
@@ -12,10 +12,8 @@ pub enum JsonEvent {
 #[derive(Serialize, Deserialize, Debug)]
 pub struct FoundEvent {
     pub name: String,
-    pub x: u16,
-    pub y: u16,
-    pub z: u16,
-    pub percent: f32,
+    #[serde(flatten, rename = "match")]
+    pub match_: Match,
 }
 
 #[derive(Serialize, Deserialize, Debug)]

schemsearch-cli/src/main.rs

@@ -18,6 +18,7 @@
 mod types;
 mod json_output;
 mod sinks;
+mod stderr;
 
 use std::fmt::Debug;
 use std::io::Write;
@@ -25,7 +26,7 @@ use clap::{command, Arg, ArgAction, ValueHint};
 use std::path::PathBuf;
 use std::str::FromStr;
 use clap::error::ErrorKind;
-use schemsearch_lib::{search, SearchBehavior};
+use schemsearch_lib::{Match, search, SearchBehavior};
 use crate::types::{PathSchematicSupplier, SchematicSupplierType};
 #[cfg(feature = "sql")]
 use futures::executor::block_on;
@@ -37,9 +38,10 @@ use schemsearch_sql::filter::SchematicFilter;
 use schemsearch_sql::load_all_schematics;
 #[cfg(feature = "sql")]
 use crate::types::SqlSchematicSupplier;
-use indicatif::{ParallelProgressIterator, ProgressStyle};
+use indicatif::*;
 use schemsearch_files::Schematic;
 use crate::sinks::{OutputFormat, OutputSink};
+use crate::stderr::MaschineStdErr;
 
 fn main() {
     #[allow(unused_mut)]
@@ -94,7 +96,7 @@ fn main() {
         )
         .arg(
             Arg::new("output")
-                .help("The output format and path [Format:Path] available formats: text, json, csv; available paths: std, (file path)")
+                .help("The output format and path [Format:Path] available formats: text, json, csv; available paths: std, err, (file path)")
                 .short('o')
                 .long("output")
                 .action(ArgAction::Append)
@@ -139,6 +141,24 @@ fn main() {
                 .default_value("0")
                 .value_parser(|s: &str| s.parse::<usize>().map_err(|e| e.to_string())),
         )
+        .arg(
+            Arg::new("machine")
+                .help("Output for machines")
+                .short('m')
+                .long("machine")
+                .action(ArgAction::Set)
+                .default_value("0")
+                .value_parser(|s: &str| s.parse::<u16>().map_err(|e| e.to_string()))
+        )
+        .arg(
+            Arg::new("limit")
+                .help("The maximum number of matches to return [0 = Unlimited]")
+                .short('l')
+                .long("limit")
+                .action(ArgAction::Set)
+                .default_value("50")
+                .value_parser(|s: &str| s.parse::<usize>().map_err(|e| e.to_string())),
+        )
         .about("Searches for a pattern in a schematic")
         .bin_name("schemsearch");
 
@@ -246,14 +266,23 @@ fn main() {
 
     ThreadPoolBuilder::new().num_threads(*matches.get_one::<usize>("threads").expect("Could not get threads")).build_global().unwrap();
 
-    let matches: Vec<SearchResult> = schematics.par_iter().progress_with_style(ProgressStyle::with_template("[{elapsed}, ETA: {eta}] {wide_bar} {pos}/{len} {per_sec}").unwrap()).map(|schem| {
+    let bar = ProgressBar::new(schematics.len() as u64); // "maschine"
+    bar.set_style(ProgressStyle::with_template("[{elapsed}, ETA: {eta}] {wide_bar} {pos}/{len} {per_sec}").unwrap());
+    let term_size = *matches.get_one::<u16>("machine").expect("Could not get machine");
+    if term_size != 0 {
+        bar.set_draw_target(ProgressDrawTarget::term_like(Box::new(MaschineStdErr { size: term_size })))
+    }
+
+    let max_matching = *matches.get_one::<usize>("limit").expect("Could not get max-matching");
+
+    let matches: Vec<SearchResult> = schematics.par_iter().progress_with(bar).map(|schem| {
         match schem {
             SchematicSupplierType::PATH(schem) => {
                 let schematic = match load_schem(&schem.path) {
                     Some(x) => x,
                     None => return SearchResult {
                         name: schem.get_name(),
-                        matches: vec![]
+                        matches: Vec::default()
                     }
                 };
                 SearchResult {
@@ -271,12 +300,10 @@ fn main() {
                         }
                     }
                     Err(e) => {
-                        if !output_std && !output_std_csv {
-                            println!("Error while loading schematic ({}): {}", schem.get_name(), e.to_string());
-                        }
+                        eprintln!("Error while loading schematic ({}): {}", schem.get_name(), e.to_string());
                         SearchResult {
                             name: schem.get_name(),
-                            matches: vec![]
+                            matches: Vec::default()
                         }
                     }
                 }
@@ -284,13 +311,19 @@ fn main() {
         }
     }).collect();
 
-    for matching in matches {
+    let mut matches_count = 0;
+
+    'outer: for matching in matches {
         let schem_name = matching.name;
         let matching = matching.matches;
         for x in matching {
             for out in &mut output {
                 write!(out.1, "{}", out.0.found_match(&schem_name, x)).unwrap();
             }
+            matches_count += 1;
+            if max_matching != 0 && matches_count >= max_matching {
+                break 'outer;
+            }
         }
     }
 
@@ -314,6 +347,6 @@ fn load_schem(schem_path: &PathBuf) -> Option<Schematic> {
 #[derive(Debug, Clone)]
 struct SearchResult {
     name: String,
-    matches: Vec<(u16, u16, u16, f32)>,
+    matches: Vec<Match>,
 }
 

schemsearch-cli/src/sinks.rs

@@ -2,12 +2,15 @@ use std::fs::File;
 use std::io::BufWriter;
 use std::str::FromStr;
 use std::io::Write;
-use schemsearch_lib::SearchBehavior;
+use std::time::Duration;
+use indicatif::HumanDuration;
+use schemsearch_lib::{Match, SearchBehavior};
 use crate::json_output::{EndEvent, FoundEvent, InitEvent, JsonEvent};
 
 #[derive(Debug, Clone)]
 pub enum OutputSink {
     Stdout,
+    Stderr,
     File(String),
 }
 
@@ -37,6 +40,7 @@ impl FromStr for OutputSink {
     fn from_str(s: &str) -> Result<Self, Self::Err> {
         match s {
             "std" => Ok(OutputSink::Stdout),
+            "err" => Ok(OutputSink::Stderr),
             _ => Ok(OutputSink::File(s.to_string()))
         }
     }
@@ -45,23 +49,21 @@ impl FromStr for OutputSink {
 impl OutputSink {
     pub fn output(&self) -> Box<dyn Write> {
         match self {
-            OutputSink::Stdout => Box::new(std::io::stdout().lock()),
+            OutputSink::Stdout => Box::new(std::io::stdout()),
+            OutputSink::Stderr => Box::new(std::io::stderr()),
             OutputSink::File(path) => Box::new(BufWriter::new(File::create(path).unwrap()))
         }
     }
 }
 
 impl OutputFormat {
-    pub fn found_match(&self, name: &String, pos: (u16, u16, u16, f32)) -> String {
+    pub fn found_match(&self, name: &String, pos: Match) -> String {
         match self {
-            OutputFormat::Text => format!("Found match in '{}' at x: {}, y: {}, z: {}, % = {}\n", name, pos.0, pos.1, pos.2, pos.3),
-            OutputFormat::CSV => format!("{},{},{},{},{}\n", name, pos.0, pos.1, pos.2, pos.3),
+            OutputFormat::Text => format!("Found match in '{}' at x: {}, y: {}, z: {}, % = {}\n", name, pos.x, pos.y, pos.z, pos.percent),
+            OutputFormat::CSV => format!("{},{},{},{},{}\n", name, pos.x, pos.y, pos.z, pos.percent),
             OutputFormat::JSON => format!("{}\n", serde_json::to_string(&JsonEvent::Found(FoundEvent {
                 name: name.clone(),
-                x: pos.0,
-                y: pos.1,
-                z: pos.2,
-                percent: pos.3,
+                match_: pos,
             })).unwrap())
         }
     }
@@ -80,7 +82,7 @@ impl OutputFormat {
 
     pub fn end(&self, end_time: u128) -> String {
         match self {
-            OutputFormat::Text => format!("Search complete in {}s\n", end_time / 1000),
+            OutputFormat::Text => format!("Search complete in {}\n", HumanDuration(Duration::from_millis(end_time as u64))),
             OutputFormat::CSV => format!("{}\n", end_time),
             OutputFormat::JSON => format!("{}\n", serde_json::to_string(&JsonEvent::End(EndEvent{ end_time })).unwrap())
         }

schemsearch-cli/src/stderr.rs

@@ -0,0 +1,44 @@
+use std::fmt::Debug;
+use std::io::Write;
+use indicatif::TermLike;
+
+#[derive(Debug)]
+pub struct MaschineStdErr { pub(crate) size: u16}
+
+impl TermLike for MaschineStdErr {
+    fn width(&self) -> u16 {
+        self.size
+    }
+
+    fn move_cursor_up(&self, _: usize) -> std::io::Result<()> {
+        Ok(())
+    }
+
+    fn move_cursor_down(&self, _: usize) -> std::io::Result<()> {
+        Ok(())
+    }
+
+    fn move_cursor_right(&self, _: usize) -> std::io::Result<()> {
+        Ok(())
+    }
+
+    fn move_cursor_left(&self, _: usize) -> std::io::Result<()> {
+        Ok(())
+    }
+
+    fn write_line(&self, s: &str) -> std::io::Result<()> {
+        writeln!(std::io::stderr(), "{}", s)
+    }
+
+    fn write_str(&self, s: &str) -> std::io::Result<()> {
+        write!(std::io::stderr(), "{}", s)
+    }
+
+    fn clear_line(&self) -> std::io::Result<()> {
+        Ok(())
+    }
+
+    fn flush(&self) -> std::io::Result<()> {
+        std::io::stderr().flush()
+    }
+}

schemsearch-cli/src/types.rs

@@ -18,6 +18,8 @@
 use std::path::PathBuf;
 #[cfg(feature = "sql")]
 use futures::executor::block_on;
+#[allow(unused_imports)]
+use schemsearch_files::Schematic;
 #[cfg(feature = "sql")]
 use schemsearch_sql::{load_schemdata, SchematicNode};
 

schemsearch-files/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "schemsearch-files"
-version = "0.1.1"
+version = "0.1.2"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

schemsearch-java/src/lib.rs

@@ -45,8 +45,8 @@ pub extern "system" fn Java_SchemSearch_search<'local>(mut env: JNIEnv<'local>,
     });
 
     let mut result = String::new();
-    for (x, y, z, p) in matches {
-        result.push_str(&format!("{}, {}, {}, {};", x, y, z, p));
+    for m in matches {
+        result.push_str(&format!("{}, {}, {}, {};", m.x, m.y, m.z, m.percent));
     }
     result.remove(result.len() - 1);
     let output = env.new_string(result).expect("Couldn't create java string!");

schemsearch-lib/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "schemsearch-lib"
-version = "0.1.1"
+version = "0.1.2"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 
@@ -10,3 +10,4 @@ license = "AGPL-3.0-or-later"
 hematite-nbt = "0.5.2"
 serde = "1.0.152"
 schemsearch-files = { path = "../schemsearch-files" }
+manual-avx2 = { git = "https://github.com/Chaoscaot/manual-avx2", version = "0.1.0" }

schemsearch-lib/src/lib.rs

@@ -36,7 +36,7 @@ pub fn search(
     schem: Schematic,
     pattern_schem: &Schematic,
     search_behavior: SearchBehavior,
-) -> Vec<(u16, u16, u16, f32)> {
+) -> Vec<Match> {
     if schem.width < pattern_schem.width || schem.height < pattern_schem.height || schem.length < pattern_schem.length {
         return vec![];
     }
@@ -47,7 +47,7 @@ pub fn search(
 
     let pattern_schem = match_palette(&schem, &pattern_schem, search_behavior.ignore_block_data);
 
-    let mut matches: Vec<(u16, u16, u16, f32)> = Vec::new();
+    let mut matches: Vec<Match> = Vec::new();
 
     let pattern_data = pattern_schem.block_data.as_slice();
 
@@ -61,7 +61,7 @@ pub fn search(
 
     let air_id = if search_behavior.ignore_air || search_behavior.air_as_any { pattern_schem.palette.get("minecraft:air").unwrap_or(&-1) } else { &-1};
 
-    let pattern_blocks = (pattern_schem.width * pattern_schem.height * pattern_schem.length) as f32;
+    let pattern_blocks = pattern_data.len() as f32;
 
     let pattern_width = pattern_schem.width as usize;
     let pattern_height = pattern_schem.height as usize;
@@ -88,9 +88,20 @@ pub fn search(
                         }
                     }
                 }
+
+                for index in (0..schem_data.len()).step_by(8) {
+                    let pattern_data_slice = schem_data[index..index + 8];
+                    let data = manual_avx2::vec_i::VecInteger::new_i32(&(index..index + 8).map(|i| schem_data[i]).collect::<[i32; 8]>());
+                }
+
                 let matching_percent = matching as f32 / pattern_blocks;
                 if matching_percent >= search_behavior.threshold {
-                    matches.push((x as u16, y as u16, z as u16, matching_percent));
+                    matches.push(Match {
+                        x: x as u16,
+                        y: y as u16,
+                        z: z as u16,
+                        percent: matching_percent,
+                    });
                 }
             }
         }
@@ -99,6 +110,25 @@ pub fn search(
     return matches;
 }
 
+#[derive(Debug, Clone, Copy, Deserialize, Serialize)]
+pub struct Match {
+    pub x: u16,
+    pub y: u16,
+    pub z: u16,
+    pub percent: f32,
+}
+
+impl Default for Match {
+    fn default() -> Self {
+        Self {
+            x: 0,
+            y: 0,
+            z: 0,
+            percent: 0.0,
+        }
+    }
+}
+
 #[inline]
 pub fn normalize_data(data: &str, ignore_data: bool) -> &str {
     if ignore_data {
@@ -196,7 +226,10 @@ mod tests {
 
         println!("{:?}", matches);
         assert_eq!(matches.len(), 1);
-        assert_eq!(matches[0], (1, 0, 3, 1.0));
+        assert_eq!(matches[0].x, 1);
+        assert_eq!(matches[0].y, 0);
+        assert_eq!(matches[0].z, 3);
+        assert_eq!(matches[0].percent, 1.0);
     }
 
     #[test]