Fixing...

🔧 Add invalid_nbt flag.

.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "cargo"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/master-build.yml

@@ -19,32 +19,36 @@ jobs:
       - name: Cache Cargo modules
         id: cache-cargo
         uses: actions/cache@v3
-        env:
+        continue-on-error: false
-          cache-name: cache-cargo-target-debug
         with:
-          path: target
+          path: |
-          key: ${{ runner.os }}-${{ env.cache-name }}-${{ hashFiles('**/Cargo.lock') }}
+            ~/.cargo/registry
+            ~/.cargo/git
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
           restore-keys: |
-            ${{ runner.os }}-${{ env.cache-name }}-
+            ${{ runner.os }}-cargo-
       - name: Build
         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:
+        continue-on-error: false
-          cache-name: cache-cargo-target-release
         with:
-          path: target
+          path: |
-          key: ${{ runner.os }}-${{ env.cache-name }}-${{ hashFiles('**/Cargo.lock') }}
+            ~/.cargo/registry
+            ~/.cargo/git
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
           restore-keys: |
-            ${{ runner.os }}-${{ env.cache-name }}-
+            ${{ runner.os }}-cargo-
       - name: Build
         run: make
       - name: Upload a Build Artifact

.github/workflows/release-build.yml

@@ -22,13 +22,14 @@ jobs:
       - name: Cache Cargo modules
         id: cache-cargo
         uses: actions/cache@v3
-        env:
+        continue-on-error: false
-          cache-name: cache-cargo-target-release
         with:
-          path: target
+          path: |
-          key: ${{ runner.os }}-${{ env.cache-name }}-${{ hashFiles('**/Cargo.lock') }}
+            ~/.cargo/registry
+            ~/.cargo/git
+          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
           restore-keys: |
-            ${{ runner.os }}-${{ env.cache-name }}-
+            ${{ runner.os }}-cargo-
       - name: Build
         run: make
       - name: Create Tarball

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+chaoscaot@zohomail.eu.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

Cargo.toml

@@ -7,6 +7,7 @@ members = [
     "schemsearch-sql",
     "schemsearch-java"
 ]
+resolver = "2"
 
 [profile.small]
 inherits = "release"

README.md

@@ -1,5 +1,5 @@
 # schemsearch
-### A *simple* CLI tool to search in Sponge V2 Schematic files
+### A *simple* CLI tool to search in Sponge Schematic files
 
 ---
 
@@ -43,7 +43,6 @@ schemsearch-cli --help
 ## Roadmap
 A list of features that are planned to be implemented in the future. In order of priority.
 
-- [ ] Full JSON output (Progressbar)
 - [ ] Use AVX2 for faster search
 - [ ] Tile entities data search
 - [ ] Entities search

schemsearch-cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "schemsearch-cli"
-version = "0.1.1"
+version = "0.1.7"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 
@@ -13,7 +13,7 @@ schemsearch-sql = { path = "../schemsearch-sql", optional = true }
 
 clap = { version = "4.1.8", features = ["cargo"] }
 futures = { version = "0.3", optional = true }
-sqlx = { version = "0.6", features = [ "runtime-async-std-native-tls" , "mysql" ], optional = true }
+sqlx = { version = "0.7", features = [ "runtime-async-std-native-tls" , "mysql" ], optional = true }
 rayon = "1.7.0"
 indicatif = { version = "0.17.3", features = ["rayon"] }
 serde = "1.0.157"

schemsearch-cli/src/main.rs

@@ -26,8 +26,8 @@ use clap::{command, Arg, ArgAction, ValueHint};
 use std::path::PathBuf;
 use std::str::FromStr;
 use clap::error::ErrorKind;
-use schemsearch_lib::{Match, search, SearchBehavior};
+use schemsearch_lib::{Match, SearchBehavior};
-use crate::types::{PathSchematicSupplier, SchematicSupplierType};
+use crate::types::{PathSchematicSupplier, SchematicSupplier, SchematicSupplierType};
 #[cfg(feature = "sql")]
 use futures::executor::block_on;
 use rayon::prelude::*;
@@ -39,9 +39,11 @@ use schemsearch_sql::load_all_schematics;
 #[cfg(feature = "sql")]
 use crate::types::SqlSchematicSupplier;
 use indicatif::*;
-use schemsearch_files::Schematic;
+use schemsearch_files::SpongeSchematic;
 use crate::sinks::{OutputFormat, OutputSink};
 use crate::stderr::MaschineStdErr;
+use schemsearch_lib::nbt_search::has_invalid_nbt;
+use schemsearch_lib::search::search;
 
 fn main() {
     #[allow(unused_mut)]
@@ -49,8 +51,8 @@ fn main() {
         .arg(
             Arg::new("pattern")
                 .help("The pattern to search for")
-                .required(true)
                 .value_hint(ValueHint::FilePath)
+                .required_unless_present("invalid-nbt")
                 .action(ArgAction::Set),
         )
         .arg(
@@ -94,6 +96,13 @@ fn main() {
                 .long("air-as-any")
                 .action(ArgAction::SetTrue),
         )
+        .arg(
+            Arg::new("invalid-nbt")
+                .help("Search for Schematics with Invalid or missing NBT data")
+                .short('I')
+                .long("invalid-nbt")
+                .action(ArgAction::SetTrue),
+        )
         .arg(
             Arg::new("output")
                 .help("The output format and path [Format:Path] available formats: text, json, csv; available paths: std, err, (file path)")
@@ -134,7 +143,7 @@ fn main() {
         )
         .arg(
             Arg::new("threads")
-                .help("The number of threads to use [0 = Available Threads]")
+                .help("The number of threads to use [0 = all Available Threads]")
                 .short('T')
                 .long("threads")
                 .action(ArgAction::Set)
@@ -150,6 +159,15 @@ fn main() {
                 .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");
 
@@ -195,18 +213,22 @@ fn main() {
         air_as_any: matches.get_flag("air-as-any"),
         ignore_entities: matches.get_flag("ignore-entities"),
         threshold: *matches.get_one::<f32>("threshold").expect("Couldn't get threshold"),
+        invalid_nbt: matches.get_flag("invalid-nbt"),
     };
 
-    let pattern = match Schematic::load(&PathBuf::from(matches.get_one::<String>("pattern").unwrap())) {
+    let pattern = match matches.get_one::<String>("pattern") {
-        Ok(x) => x,
+        Some(p) => match SpongeSchematic::load(&PathBuf::from(p)) {
+            Ok(x) => Some(x),
             Err(e) => {
                 cmd.error(ErrorKind::Io, format!("Error while loading Pattern: {}", e.to_string())).exit();
             }
+        },
+        None => None,
     };
 
     let mut schematics: Vec<SchematicSupplierType> = Vec::new();
     match matches.get_many::<String>("schematic") {
-        None => {},
+        None => {}
         Some(x) => {
             let paths = x.map(|x| PathBuf::from(x));
             for path in paths {
@@ -217,12 +239,12 @@ fn main() {
                         .filter(|x| x.path().is_file())
                         .filter(|x| x.path().extension().unwrap().to_str().unwrap() == "schem")
                         .for_each(|x| {
-                            schematics.push(SchematicSupplierType::PATH(Box::new(PathSchematicSupplier {
+                            schematics.push(SchematicSupplierType::PATH(PathSchematicSupplier {
                                 path: x.path(),
-                            })))
+                            }))
                         });
                 } else if path.extension().unwrap().to_str().unwrap() == "schem" {
-                    schematics.push(SchematicSupplierType::PATH(Box::new(PathSchematicSupplier { path })));
+                    schematics.push(SchematicSupplierType::PATH(PathSchematicSupplier { path }));
                 }
             }
         }
@@ -264,6 +286,8 @@ fn main() {
         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) => {
@@ -271,28 +295,20 @@ fn main() {
                     Some(x) => x,
                     None => return SearchResult {
                         name: schem.get_name(),
-                        matches: Vec::default()
+                        matches: Vec::default(),
                     }
                 };
-                SearchResult {
+                search_in_schem(schematic, pattern.as_ref(), search_behavior, schem)
-                    name: schem.get_name(),
-                    matches: search(schematic, &pattern, search_behavior)
-                }
             }
             #[cfg(feature = "sql")]
             SchematicSupplierType::SQL(schem) => {
                 match schem.get_schematic() {
-                    Ok(schematic) => {
+                    Ok(schematic) => search_in_schem(schematic, pattern.as_ref(), search_behavior, schem),
-                        SearchResult {
-                            name: schem.get_name(),
-                            matches: search(schematic, &pattern, search_behavior)
-                        }
-                    }
                     Err(e) => {
                         eprintln!("Error while loading schematic ({}): {}", schem.get_name(), e.to_string());
                         SearchResult {
                             name: schem.get_name(),
-                            matches: Vec::default()
+                            matches: Vec::default(),
                         }
                     }
                 }
@@ -300,13 +316,19 @@ 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;
+            }
         }
     }
 
@@ -317,8 +339,34 @@ fn main() {
     }
 }
 
-fn load_schem(schem_path: &PathBuf) -> Option<Schematic> {
+fn search_in_schem(schematic: SpongeSchematic, pattern: Option<&SpongeSchematic>, search_behavior: SearchBehavior, schem: &impl SchematicSupplier) -> SearchResult {
-    match Schematic::load(schem_path) {
+    if search_behavior.invalid_nbt {
+        if has_invalid_nbt(schematic) {
+            SearchResult {
+                name: schem.get_name(),
+                matches: vec![Match {
+                    x: 0,
+                    y: 0,
+                    z: 0,
+                    percent: 1.0,
+                }],
+            }
+        } else {
+            SearchResult {
+                name: schem.get_name(),
+                matches: vec![],
+            }
+        }
+    } else {
+        SearchResult {
+            name: schem.get_name(),
+            matches: search(schematic, pattern.unwrap(), search_behavior),
+        }
+    }
+}
+
+fn load_schem(schem_path: &PathBuf) -> Option<SpongeSchematic> {
+    match SpongeSchematic::load(schem_path) {
         Ok(x) => Some(x),
         Err(e) => {
             println!("Error while loading schematic ({}): {}", schem_path.to_str().unwrap(), e.to_string());

schemsearch-cli/src/sinks.rs

@@ -71,7 +71,7 @@ impl OutputFormat {
     pub fn start(&self, total: u32, search_behavior: &SearchBehavior, start_time: u128) -> String {
         match self {
             OutputFormat::Text => format!("Starting search in {} schematics\n", total),
-            OutputFormat::CSV => format!("Name,X,Y,Z,Percent\n"),
+            OutputFormat::CSV => "Name,X,Y,Z,Percent\n".to_owned(),
             OutputFormat::JSON => format!("{}\n", serde_json::to_string(&JsonEvent::Init(InitEvent {
                 total,
                 search_behavior: search_behavior.clone(),

schemsearch-cli/src/types.rs

@@ -15,26 +15,32 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
+#[cfg(feature = "sql")]
+use std::io::Cursor;
 use std::path::PathBuf;
 #[cfg(feature = "sql")]
 use futures::executor::block_on;
-#[allow(unused_imports)]
+#[cfg(feature = "sql")]
-use schemsearch_files::Schematic;
+use schemsearch_files::SpongeSchematic;
 #[cfg(feature = "sql")]
 use schemsearch_sql::{load_schemdata, SchematicNode};
 
 pub enum SchematicSupplierType {
-    PATH(Box<PathSchematicSupplier>),
+    PATH(PathSchematicSupplier),
     #[cfg(feature = "sql")]
     SQL(SqlSchematicSupplier),
 }
 
+pub trait SchematicSupplier {
+    fn get_name(&self) -> String;
+}
+
 pub struct PathSchematicSupplier {
     pub path: PathBuf,
 }
 
-impl PathSchematicSupplier {
+impl SchematicSupplier for PathSchematicSupplier {
-    pub fn get_name(&self) -> String {
+    fn get_name(&self) -> String {
         self.path.file_stem().unwrap().to_str().unwrap().to_string()
     }
 }
@@ -46,12 +52,17 @@ pub struct SqlSchematicSupplier {
 
 #[cfg(feature = "sql")]
 impl SqlSchematicSupplier {
-    pub fn get_schematic(&self) -> Result<Schematic, String> {
+    pub fn get_schematic(&self) -> Result<SpongeSchematic, String> {
-        let schemdata = block_on(load_schemdata(self.node.id));
+        let mut schemdata = block_on(load_schemdata(self.node.id));
-        Schematic::load_data(schemdata.as_slice())
+        SpongeSchematic::load_data(&mut Cursor::new(schemdata.as_mut_slice()))
+    }
 }
 
-    pub fn get_name(&self) -> String {
+#[cfg(feature = "sql")]
+impl SchematicSupplier for SqlSchematicSupplier {
+    fn get_name(&self) -> String {
         format!("{} ({})", self.node.name, self.node.id)
     }
 }
+
+

schemsearch-faster/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "schemsearch_faster"
-version = "0.1.1"
+version = "0.1.3"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 

schemsearch-faster/src/lib.rs

@@ -16,9 +16,9 @@
  */
 
 use nbt::Map;
-use schemsearch_files::Schematic;
+use schemsearch_files::SpongeV2Schematic;
 
-pub fn convert_to_search_space(schem: &Schematic, palette: &Vec<String>) -> Vec<Vec<u8>> {
+pub fn convert_to_search_space(schem: &SpongeV2Schematic, palette: &Vec<String>) -> Vec<Vec<u8>> {
     let mut data: Vec<Vec<u8>> = Vec::with_capacity(palette.len());
     let block_data = &schem.block_data;
     for name in palette {
@@ -48,26 +48,26 @@ pub fn unwrap_palette(palette: &Map<String, i32>) -> Vec<String> {
 #[cfg(test)]
 mod tests {
     use std::path::{Path, PathBuf};
-    use schemsearch_files::Schematic;
+    use schemsearch_files::SpongeV2Schematic;
     use crate::{convert_to_search_space, unwrap_palette};
 
     //#[test]
     pub fn test() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/Pattern.schem")).unwrap();
+        let schematic = SpongeV2Schematic::load(&PathBuf::from("../tests/Pattern.schem")).unwrap();
         dbg!(convert_to_search_space(&schematic, &unwrap_palette(&schematic.palette)));
     }
 
     //#[test]
     pub fn test_2() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/Pattern.schem")).unwrap();
+        let schematic = SpongeV2Schematic::load(&PathBuf::from("../tests/Pattern.schem")).unwrap();
-        let schematic2 = Schematic::load(&PathBuf::from("../tests/Random.schem")).unwrap();
+        let schematic2 = SpongeV2Schematic::load(&PathBuf::from("../tests/Random.schem")).unwrap();
         println!("{:?}", convert_to_search_space(&schematic2, &unwrap_palette(&schematic.palette)));
     }
 
     //#[test]
     pub fn test_big() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
+        let schematic = SpongeV2Schematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
-        let schematic2 = Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+        let schematic2 = SpongeV2Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
         let _ = convert_to_search_space(&schematic2, &unwrap_palette(&schematic.palette));
     }
 }

schemsearch-files/Cargo.toml

@@ -1,10 +1,11 @@
 [package]
 name = "schemsearch-files"
-version = "0.1.1"
+version = "0.1.5"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-hematite-nbt = "0.5.2"
+flate2 = "1.0.25"
-serde = "1.0.152"
+named-binary-tag = "0.6"
+

schemsearch-files/src/lib.rs

@@ -15,81 +15,176 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
+use std::collections::hash_map::HashMap;
 use std::io::Read;
 use std::path::PathBuf;
-use nbt::{Map, Value};
+use nbt::{CompoundTag, Tag};
-use serde::{Deserialize, Deserializer, Serialize};
 
-#[derive(Serialize, Deserialize, Debug)]
+#[derive(Clone, Debug)]
-pub struct Schematic {
+pub struct SpongeSchematic {
-    #[serde(rename = "Version")]
-    pub version: i32,
-    #[serde(rename = "DataVersion")]
     pub data_version: i32,
-    #[serde(rename = "Metadata")]
+    pub metadata: CompoundTag,
-    pub metadata: Map<String, Value>,
-    #[serde(rename = "Width")]
     pub width: u16,
-    #[serde(rename = "Height")]
     pub height: u16,
-    #[serde(rename = "Length")]
     pub length: u16,
-    #[serde(rename = "Offset")]
     pub offset: [i32; 3],
-    #[serde(rename = "PaletteMax")]
     pub palette_max: i32,
-    #[serde(rename = "Palette")]
+    pub palette: HashMap<String, i32>,
-    pub palette: Map<String, i32>,
-    #[serde(rename = "BlockData", deserialize_with = "read_blockdata")]
     pub block_data: Vec<i32>,
-    #[serde(rename = "BlockEntities")]
     pub block_entities: Vec<BlockEntity>,
-    #[serde(rename = "Entities")]
     pub entities: Option<Vec<Entity>>,
 }
 
-fn read_blockdata<'de, D>(deserializer: D) -> Result<Vec<i32>, D::Error>
+#[derive(Clone, Debug)]
-    where
+pub struct BlockContainer {
-        D: Deserializer<'de>,
+    pub palette: HashMap<String, i32>,
-{
+    pub block_data: Vec<i32>,
-    let s: Vec<i8> = Deserialize::deserialize(deserializer)?;
+    pub block_entities: Vec<BlockEntity>,
-    Ok(read_varint_array(&s))
 }
 
-#[derive(Serialize, Deserialize, Debug, Clone)]
+#[derive(Debug, Clone)]
 pub struct BlockEntity {
-    #[serde(rename = "Id")]
     pub id: String,
-    #[serde(rename = "Pos")]
     pub pos: [i32; 3],
 }
 
-#[derive(Serialize, Deserialize, Debug, Clone)]
+#[derive(Debug, Clone)]
+pub struct BlockEntityV3 {
+    pub id: String,
+    pub pos: [i32; 3],
+    pub data: HashMap<String, Tag>,
+}
+
+#[derive(Debug, Clone)]
 pub struct Entity {
-    #[serde(rename = "Id")]
     pub id: String,
-    #[serde(rename = "Pos")]
     pub pos: [i32; 3],
 }
 
-impl Schematic {
+impl SpongeSchematic {
-    pub fn load_data<R>(data: R) -> Result<Schematic, String> where R: Read {
+    pub fn load_data<R>(data: &mut R) -> Result<SpongeSchematic, String> where R: Read {
-        let schematic: Schematic = match nbt::from_gzip_reader(data) {
+        let nbt: CompoundTag = nbt::decode::read_gzip_compound_tag(data).map_err(|e| e.to_string())?;
-            Ok(schem) => schem,
+        let version = nbt.get_i32("Version").unwrap_or_else(|_| {
-            Err(e) => return Err(format!("Failed to parse schematic: {}", e))
+            return if nbt.contains_key("Blocks") {
+                3
+            } else if nbt.contains_key("BlockEntities") {
+                2
+            } else if nbt.contains_key("TileEntities") {
+                1
+            } else {
+                -1
             };
-        Ok(schematic)
+        });
-    }
 
-    pub fn load(path: &PathBuf) -> Result<Schematic, String> {
+        match version {
-        let file = match std::fs::File::open(path) {
+            1 => SpongeSchematic::from_nbt_1(nbt),
-            Ok(x) => x,
+            2 => SpongeSchematic::from_nbt_2(nbt),
-            Err(_) => return Err(format!("Failed to open file: {}", path.to_str().unwrap()))
+            3 => SpongeSchematic::from_nbt_3(nbt),
-        };
+            _ => Err("Invalid schematic: Unknown Version".to_string()),
-        Schematic::load_data(file)
         }
     }
 
+    pub fn load(path: &PathBuf) -> Result<SpongeSchematic, String> {
+        let mut file = std::fs::File::open(path).map_err(|e| e.to_string())?;
+        Self::load_data(&mut file)
+    }
+
+    pub fn from_nbt_1(nbt: CompoundTag) -> Result<Self, String> {
+        Ok(Self {
+            data_version: 0,
+            metadata: nbt.get_compound_tag("Metadata").map_err(|e| e.to_string())?.clone(),
+            width: nbt.get_i16("Width").map_err(|e| e.to_string())? as u16,
+            height: nbt.get_i16("Height").map_err(|e| e.to_string())? as u16,
+            length: nbt.get_i16("Length").map_err(|e| e.to_string())? as u16,
+            offset: read_offset(nbt.get_i32_vec("Offset").map_err(|e| e.to_string())?)?,
+            palette_max: nbt.get_i32("PaletteMax").map_err(|e| e.to_string())?,
+            palette: read_palette(nbt.get_compound_tag("Palette").map_err(|e| e.to_string())?),
+            block_data: read_blocks(nbt.get_i8_vec("BlockData").map_err(|e| e.to_string())?),
+            block_entities: read_tile_entities(nbt.get_compound_tag_vec("TileEntities").unwrap_or_else(|_| vec![]))?,
+            entities: None,
+        })
+    }
+
+    pub fn from_nbt_2(nbt: CompoundTag) -> Result<Self, String> {
+        Ok(Self{
+            data_version: nbt.get_i32("DataVersion").map_err(|e| e.to_string())?,
+            metadata: nbt.get_compound_tag("Metadata").map_err(|e| e.to_string())?.clone(),
+            width: nbt.get_i16("Width").map_err(|e| e.to_string())? as u16,
+            height: nbt.get_i16("Height").map_err(|e| e.to_string())? as u16,
+            length: nbt.get_i16("Length").map_err(|e| e.to_string())? as u16,
+            offset: read_offset(nbt.get_i32_vec("Offset").map_err(|e| e.to_string())?)?,
+            palette_max: nbt.get_i32("PaletteMax").map_err(|e| e.to_string())?,
+            palette: read_palette(nbt.get_compound_tag("Palette").map_err(|e| e.to_string())?),
+            block_data: read_blocks(nbt.get_i8_vec("BlockData").map_err(|e| e.to_string())?),
+            block_entities: read_tile_entities(nbt.get_compound_tag_vec("BlockEntities").unwrap_or_else(|_| vec![]))?,
+            entities: None,
+        })
+    }
+
+    pub fn from_nbt_3(nbt: CompoundTag) -> Result<Self, String> {
+        let blocks = nbt.get_compound_tag("Blocks").map_err(|e| e.to_string())?;
+        Ok(Self{
+            data_version: nbt.get_i32("DataVersion").map_err(|e| e.to_string())?,
+            metadata: nbt.get_compound_tag("Metadata").map_err(|e| e.to_string())?.clone(),
+            width: nbt.get_i16("Width").map_err(|e| e.to_string())? as u16,
+            height: nbt.get_i16("Height").map_err(|e| e.to_string())? as u16,
+            length: nbt.get_i16("Length").map_err(|e| e.to_string())? as u16,
+            offset: read_offset(nbt.get_i32_vec("Offset").map_err(|e| e.to_string())?)?,
+            palette_max: compute_palette_max(blocks.get_compound_tag("Palette").map_err(|e| e.to_string())?),
+            palette: read_palette(blocks.get_compound_tag("Palette").map_err(|e| e.to_string())?),
+            block_data: read_blocks(blocks.get_i8_vec("BlockData").map_err(|e| e.to_string())?),
+            block_entities: read_tile_entities(blocks.get_compound_tag_vec("BlockEntities").unwrap_or_else(|_| vec![]))?,
+            entities: None,
+        })
+    }
+
+}
+
+fn read_tile_entities(tag: Vec<&CompoundTag>) -> Result<Vec<BlockEntity>, String> {
+let mut tile_entities = Vec::new();
+    for t in tag {
+        tile_entities.push(BlockEntity {
+            id: t.get_str("Id").map_err(|e| e.to_string())?.to_string(),
+            pos: read_offset(t.get("Pos").map_err(|e| e.to_string())?)?,
+        });
+    }
+    Ok(tile_entities)
+}
+
+#[inline]
+fn read_offset(offset: &Vec<i32>) -> Result<[i32; 3], String> {
+    match offset.len() {
+        3 => Ok([offset[0], offset[1], offset[2]]),
+        _ => Err("Invalid schematic: read_offset wrong length".to_string()),
+    }
+}
+
+#[inline]
+fn read_palette(p: &CompoundTag) -> HashMap<String, i32> {
+    let mut palette = HashMap::new();
+    for (key, value) in p.iter() {
+        match value {
+            Tag::Int(n) => { palette.insert(key.clone(), *n); },
+            _ => {},
+        };
+    }
+    palette
+}
+
+#[inline]
+fn compute_palette_max(palette: &CompoundTag) -> i32 {
+    palette.iter().map(|(_, v)| v).filter_map(|v| match v {
+        Tag::Int(n) => Some(*n),
+        _ => None,
+    }).max().unwrap_or(0)
+}
+
+#[inline]
+fn read_blocks(blockdata: &Vec<i8>) -> Vec<i32> {
+    read_varint_array(blockdata)
+}
+
+#[inline]
 pub fn read_varint_array(read: &Vec<i8>) -> Vec<i32> {
     let mut data = Vec::new();
     let mut value: i32 = 0;

schemsearch-java/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "schemsearch-java"
-version = "0.1.1"
+version = "0.1.3"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 

schemsearch-java/src/lib.rs

@@ -21,7 +21,7 @@ use jni::JNIEnv;
 use jni::objects::{JClass, JString};
 
 use jni::sys::jstring;
-use schemsearch_files::Schematic;
+use schemsearch_files::SpongeV2Schematic;
 use schemsearch_lib::{search, SearchBehavior};
 
 #[no_mangle]
@@ -32,8 +32,8 @@ pub extern "system" fn Java_SchemSearch_search<'local>(mut env: JNIEnv<'local>,
     pattern_path: JString<'local>) -> jstring {
     let schematic_path: String = env.get_string(&schematic_path).expect("Couldn't get java string!").into();
     let pattern_path: String = env.get_string(&pattern_path).expect("Couldn't get java string!").into();
-    let schematic = Schematic::load(&PathBuf::from(&schematic_path)).unwrap();
+    let schematic = SpongeV2Schematic::load(&PathBuf::from(&schematic_path)).unwrap();
-    let pattern = Schematic::load(&PathBuf::from(&pattern_path)).unwrap();
+    let pattern = SpongeV2Schematic::load(&PathBuf::from(&pattern_path)).unwrap();
 
     let matches = search(schematic, &pattern, SearchBehavior {
         ignore_block_data: true,

schemsearch-lib/Cargo.toml

@@ -1,12 +1,14 @@
 [package]
 name = "schemsearch-lib"
-version = "0.1.1"
+version = "0.1.7"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-hematite-nbt = "0.5.2"
+serde = { version = "1.0.160", features = ["derive"] }
-serde = "1.0.152"
 schemsearch-files = { path = "../schemsearch-files" }
+named-binary-tag = "0.6"
+libmath = "0.2.1"
+lazy_static = "1.4.0"

schemsearch-lib/src/blocks.txt

@@ -0,0 +1,163 @@
+oak_sign
+oak_wall_sign
+oak_hanging_sign
+oak_wall_hanging_sign
+birch_sign
+birch_wall_sign
+birch_hanging_sign
+birch_wall_hanging_sign
+spruce_sign
+spruce_wall_sign
+spruce_hanging_sign
+spruce_wall_hanging_sign
+jungle_sign
+jungle_wall_sign
+jungle_hanging_sign
+jungle_wall_hanging_sign
+dark_oak_sign
+dark_oak_wall_sign
+dark_oak_hanging_sign
+dark_oak_wall_hanging_sign
+acacia_sign
+acacia_wall_sign
+acacia_hanging_sign
+acacia_wall_hanging_sign
+mangrove_sign
+mangrove_wall_sign
+mangrove_hanging_sign
+mangrove_wall_hanging_sign
+cherry_sign
+cherry_wall_sign
+cherry_hanging_sign
+cherry_wall_hanging_sign
+bamboo_sign
+bamboo_wall_sign
+bamboo_hanging_sign
+bamboo_wall_hanging_sign
+warped_sign
+warped_wall_sign
+warped_hanging_sign
+warped_wall_hanging_sign
+crimson_sign
+crimson_wall_sign
+crimson_hanging_sign
+crimson_wall_hanging_sign
+suspicious_gravel
+suspicious_sand
+white_banner
+light_gray_banner
+gray_banner
+black_banner
+brown_banner
+red_banner
+orange_banner
+yellow_banner
+lime_banner
+green_banner
+cyan_banner
+light_blue_banner
+blue_banner
+purple_banner
+magenta_banner
+pink_banner
+white_wall_banner
+light_gray_wall_banner
+gray_wall_banner
+black_wall_banner
+brown_wall_banner
+red_wall_banner
+orange_wall_banner
+yellow_wall_banner
+lime_wall_banner
+green_wall_banner
+cyan_wall_banner
+light_blue_wall_banner
+blue_wall_banner
+purple_wall_banner
+magenta_wall_banner
+pink_wall_banner
+white_bed
+light_gray_bed
+gray_bed
+black_bed
+brown_bed
+red_bed
+orange_bed
+yellow_bed
+lime_bed
+green_bed
+cyan_bed
+light_blue_bed
+blue_bed
+purple_bed
+magenta_bed
+pink_bed
+shulker_box
+white_shulker_box
+light_gray_shulker_box
+gray_shulker_box
+black_shulker_box
+brown_shulker_box
+red_shulker_box
+orange_shulker_box
+yellow_shulker_box
+lime_shulker_box
+green_shulker_box
+cyan_shulker_box
+light_blue_shulker_box
+blue_shulker_box
+purple_shulker_box
+magenta_shulker_box
+pink_shulker_box
+furnace
+blast_furnace
+smoker
+chest
+trapped_chest
+ender_chest
+enchanting_table
+barrel
+lectern
+jukebox
+bell
+brewing_stand
+bee_nest
+beehive
+decorated_pot
+beacon
+conduit
+campfire
+soul_campfire
+redstone_comparator
+hopper
+dispenser
+dropper
+moving_piston
+daylight_detector
+sculk_sensor
+calibrated_sculk_sensor
+sculk_catalyst
+sculk_shrieker
+player_head
+player_wall_head
+wither_skeleton_skull
+wither_skeleton_wall_skull
+zombie_head
+zombie_wall_head
+skeleton_skull
+skeleton_wall_skull
+creeper_head
+creeper_wall_head
+piglin_head
+piglin_wall_head
+dragon_head
+dragon_wall_head
+chiseled_bookshelf
+command_block
+chain_command_block
+repeating_command_block
+structure_block
+jigsaw_block
+end_portal
+end_gateway
+monster_spawner

schemsearch-lib/src/lib.rs

@@ -16,11 +16,10 @@
  */
 
 pub mod pattern_mapper;
+pub mod search;
+pub mod nbt_search;
 
-use serde::{Deserialize, Serialize};
+use serde::{Serialize, Deserialize};
-use pattern_mapper::match_palette;
-use schemsearch_files::Schematic;
-use crate::pattern_mapper::match_palette_adapt;
 
 #[derive(Debug, Clone, Copy, Deserialize, Serialize)]
 pub struct SearchBehavior {
@@ -30,81 +29,10 @@ pub struct SearchBehavior {
     pub air_as_any: bool,
     pub ignore_entities: bool,
     pub threshold: f32,
+    pub invalid_nbt: bool,
 }
 
-pub fn search(
+#[derive(Debug, Clone, Copy, Default, Deserialize, Serialize)]
-    schem: Schematic,
-    pattern_schem: &Schematic,
-    search_behavior: SearchBehavior,
-) -> Vec<Match> {
-    if schem.width < pattern_schem.width || schem.height < pattern_schem.height || schem.length < pattern_schem.length {
-        return vec![];
-    }
-
-    if pattern_schem.palette.len() > schem.palette.len() {
-        return vec![];
-    }
-
-    let pattern_schem = match_palette(&schem, &pattern_schem, search_behavior.ignore_block_data);
-
-    let mut matches: Vec<Match> = Vec::new();
-
-    let pattern_data = pattern_schem.block_data.as_slice();
-
-    let schem_data = if search_behavior.ignore_block_data {
-        match_palette_adapt(&schem, &pattern_schem.palette, search_behavior.ignore_block_data)
-    } else {
-        schem.block_data
-    };
-
-    let schem_data = schem_data.as_slice();
-
-    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_data.len() as f32;
-
-    let pattern_width = pattern_schem.width as usize;
-    let pattern_height = pattern_schem.height as usize;
-    let pattern_length = pattern_schem.length as usize;
-
-    let schem_width = schem.width as usize;
-    let schem_height = schem.height as usize;
-    let schem_length = schem.length as usize;
-
-    for y in 0..=schem_height - pattern_height {
-        for z in 0..=schem_length - pattern_length {
-            for x in 0..=schem_width - pattern_width {
-                let mut matching = 0;
-                for j in 0..pattern_height {
-                    for k in 0..pattern_length {
-                        for i in 0..pattern_width {
-                            let index = (x + i) + schem_width * ((z + k) + (y + j) * schem_length);
-                            let pattern_index = i + pattern_width * (k + j * pattern_length);
-                            let data = unsafe {schem_data.get_unchecked(index) };
-                            let pattern_data = unsafe { pattern_data.get_unchecked(pattern_index) };
-                            if *data == *pattern_data || (search_behavior.ignore_air && *data == *air_id) || (search_behavior.air_as_any && *pattern_data == *air_id) {
-                                matching += 1;
-                            }
-                        }
-                    }
-                }
-                let matching_percent = matching as f32 / pattern_blocks;
-                if matching_percent >= search_behavior.threshold {
-                    matches.push(Match {
-                        x: x as u16,
-                        y: y as u16,
-                        z: z as u16,
-                        percent: matching_percent,
-                    });
-                }
-            }
-        }
-    }
-
-    return matches;
-}
-
-#[derive(Debug, Clone, Copy, Deserialize, Serialize)]
 pub struct Match {
     pub x: u16,
     pub y: u16,
@@ -112,17 +40,6 @@ pub struct Match {
     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 {
@@ -132,42 +49,34 @@ pub fn normalize_data(data: &str, ignore_data: bool) -> &str {
     }
 }
 
-pub fn parse_schematic(data: &Vec<u8>) -> Schematic {
-    if data[0] == 0x1f && data[1] == 0x8b {
-        // gzip
-        nbt::from_gzip_reader(data.as_slice()).unwrap()
-    } else {
-        // uncompressed
-        nbt::from_reader(data.as_slice()).unwrap()
-    }
-}
-
 #[allow(unused_imports)]
 #[cfg(test)]
 mod tests {
     use std::path::{Path, PathBuf};
-    use schemsearch_files::Schematic;
+    use schemsearch_files::SpongeSchematic;
-    use crate::pattern_mapper::strip_data;
+    use crate::pattern_mapper::{match_palette, strip_data};
+    use crate::search::search;
     use super::*;
 
     #[test]
     fn read_schematic() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+
         assert_eq!(schematic.width as usize * schematic.height as usize * schematic.length as usize, schematic.block_data.len());
         assert_eq!(schematic.palette_max, schematic.palette.len() as i32);
     }
 
     #[test]
     fn test_parse_function() {
-        let file = std::fs::File::open("../tests/simple.schem").expect("Failed to open file");
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
-        let schematic: Schematic = parse_schematic(&std::io::Read::bytes(file).map(|b| b.unwrap()).collect());
+
         assert_eq!(schematic.width as usize * schematic.height as usize * schematic.length as usize, schematic.block_data.len());
         assert_eq!(schematic.palette_max, schematic.palette.len() as i32);
     }
 
     #[test]
     fn test_strip_schem() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
         let stripped = strip_data(&schematic);
 
         assert_eq!(stripped.palette.keys().any(|k| k.contains('[')), false);
@@ -175,24 +84,24 @@ mod tests {
 
     #[test]
     fn test_match_palette() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
-        let endstone = Schematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
+        let endstone = SpongeSchematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
 
         let _ = match_palette(&schematic, &endstone, true);
     }
 
     #[test]
     fn test_match_palette_ignore_data() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
-        let endstone = Schematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
+        let endstone = SpongeSchematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
 
         let _ = match_palette(&schematic, &endstone, false);
     }
 
     #[test]
     pub fn test_big_search() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/simple.schem")).unwrap();
-        let endstone = Schematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
+        let endstone = SpongeSchematic::load(&PathBuf::from("../tests/endstone.schem")).unwrap();
 
         let _ = search(schematic, &endstone, SearchBehavior {
             ignore_block_data: true,
@@ -200,14 +109,15 @@ mod tests {
             ignore_entities: true,
             ignore_air: false,
             air_as_any: false,
-            threshold: 0.9
+            threshold: 0.9,
+            invalid_nbt: false
         });
     }
 
     #[test]
     pub fn test_search() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/Random.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/Random.schem")).unwrap();
-        let pattern = Schematic::load(&PathBuf::from("../tests/Pattern.schem")).unwrap();
+        let pattern = SpongeSchematic::load(&PathBuf::from("../tests/Pattern.schem")).unwrap();
 
         let matches = search(schematic, &pattern, SearchBehavior {
             ignore_block_data: true,
@@ -215,10 +125,10 @@ mod tests {
             ignore_entities: true,
             ignore_air: false,
             air_as_any: false,
-            threshold: 0.9
+            threshold: 0.9,
+            invalid_nbt: false
         });
 
-        println!("{:?}", matches);
         assert_eq!(matches.len(), 1);
         assert_eq!(matches[0].x, 1);
         assert_eq!(matches[0].y, 0);
@@ -228,8 +138,8 @@ mod tests {
 
     #[test]
     pub fn test_search_ws() {
-        let schematic = Schematic::load(&PathBuf::from("../tests/warships/GreyFly-by-Bosslar.schem")).unwrap();
+        let schematic = SpongeSchematic::load(&PathBuf::from("../tests/warships/GreyFly-by-Bosslar.schem")).unwrap();
-        let pattern = Schematic::load(&PathBuf::from("../tests/gray_castle_complex.schem")).unwrap();
+        let pattern = SpongeSchematic::load(&PathBuf::from("../tests/gray_castle_complex.schem")).unwrap();
 
         let matches = search(schematic, &pattern, SearchBehavior {
             ignore_block_data: false,
@@ -237,10 +147,10 @@ mod tests {
             ignore_entities: false,
             ignore_air: false,
             air_as_any: false,
-            threshold: 0.9
+            threshold: 0.9,
+            invalid_nbt: false
         });
 
-        println!("{:?}", matches);
         assert_eq!(matches.len(), 1);
     }
 }

schemsearch-lib/src/nbt_search.rs

@@ -0,0 +1,110 @@
+use std::borrow::ToOwned;
+use std::collections::HashSet;
+use std::iter::Iterator;
+use lazy_static::lazy_static;
+use schemsearch_files::SpongeSchematic;
+
+const NBT_BLOCKS: &str = include_str!("blocks.txt");
+
+lazy_static! {
+    static ref NBT_BLOCKS_SET: HashSet<String> = {
+        NBT_BLOCKS.lines().map(|x| format!("minecraft:{}", x)).collect()
+    };
+}
+
+pub fn has_invalid_nbt(schem: SpongeSchematic) -> bool {
+    if schem.block_entities.is_empty() && schem.palette.keys().any(|v| NBT_BLOCKS_SET.contains(v)) {
+        return true;
+    }
+
+    let nbt_blocks = schem.palette.iter().filter(|(k, _)| NBT_BLOCKS_SET.contains(k.to_owned())).map(|(_, v)| *v).collect::<HashSet<i32>>();
+
+    for (i, block_entity) in schem.block_data.iter().enumerate() {
+        if nbt_blocks.contains(&*block_entity) {
+            // i = x + z * Width + y * Width * Length
+            let x = i % schem.width as usize;
+            let z = (i / schem.width as usize) % schem.length as usize;
+            let y = i / (schem.width as usize * schem.length as usize);
+            if schem.block_entities.iter().any(|e| !e.pos.eq(&[x as i32, y as i32, z as i32])) {
+                return true;
+            }
+        }
+    }
+
+    return false;
+}
+
+#[allow(unused_imports)]
+#[cfg(test)]
+mod tests {
+    use nbt::CompoundTag;
+    use schemsearch_files::{BlockEntity, SpongeSchematic};
+    use super::*;
+
+    #[test]
+    fn test_has_invalid_nbt() {
+        let schem = SpongeSchematic {
+            data_version: 1,
+            metadata: CompoundTag::new(),
+            width: 0,
+            height: 0,
+            length: 0,
+            offset: [0, 0, 0],
+            palette_max: 1,
+            palette: vec![("minecraft:chest".to_owned(), 1)].into_iter().collect(),
+            block_data: vec![1],
+            block_entities: vec![],
+            entities: None,
+        };
+
+        assert_eq!(has_invalid_nbt(schem), true);
+    }
+
+    #[test]
+    fn test_has_invalid_nbt_2() {
+        let schem = SpongeSchematic {
+            data_version: 1,
+            metadata: CompoundTag::new(),
+            width: 1,
+            height: 1,
+            length: 1,
+            offset: [0, 0, 0],
+            palette_max: 1,
+            palette: vec![("minecraft:chest".to_owned(), 1)].into_iter().collect(),
+            block_data: vec![1],
+            block_entities: vec![
+                BlockEntity {
+                    id: "minecraft:chest".to_owned(),
+                    pos: [0, 0, 0],
+                }
+            ],
+            entities: None,
+        };
+
+        assert_eq!(has_invalid_nbt(schem), false);
+    }
+
+    #[test]
+    fn test_has_invalid_nbt_3() {
+        let schem = SpongeSchematic {
+            data_version: 1,
+            metadata: CompoundTag::new(),
+            width: 2,
+            height: 1,
+            length: 1,
+            offset: [0, 0, 0],
+            palette_max: 1,
+            palette: vec![("minecraft:chest".to_owned(), 1), ("minecraft:stone".to_owned(), 2)].into_iter().collect(),
+            block_data: vec![1, 2],
+            block_entities: vec![
+                BlockEntity {
+                    id: "minecraft:chest".to_owned(),
+                    pos: [1, 0, 0],
+                }
+            ],
+            entities: None,
+        };
+
+        assert_eq!(has_invalid_nbt(schem), true);
+    }
+}

schemsearch-lib/src/pattern_mapper.rs

@@ -15,11 +15,12 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-use nbt::Map;
+use std::collections::HashMap;
-use schemsearch_files::Schematic;
+use nbt::CompoundTag;
+use schemsearch_files::SpongeSchematic;
 use crate::normalize_data;
 
-fn create_reverse_palette(schem: &Schematic) -> Vec<&str> {
+fn create_reverse_palette(schem: &SpongeSchematic) -> Vec<&str> {
     let mut reverse_palette = Vec::with_capacity(schem.palette_max as usize);
     (0..schem.palette_max).for_each(|_| reverse_palette.push(""));
     for (key, value) in schem.palette.iter() {
@@ -28,15 +29,15 @@ fn create_reverse_palette(schem: &Schematic) -> Vec<&str> {
     reverse_palette
 }
 
-pub fn strip_data(schem: &Schematic) -> Schematic {
+pub fn strip_data(schem: &SpongeSchematic) -> SpongeSchematic {
     let mut data: Vec<i32> = Vec::new();
 
-    let mut palette: Map<String, i32> = Map::new();
+    let mut palette: HashMap<String, i32> = HashMap::new();
     let mut palette_max: i32 = 0;
     let reverse_palette = create_reverse_palette(schem);
 
     for block in schem.block_data.iter() {
-        let block_name = reverse_palette[*block as usize].clone();
+        let block_name = reverse_palette[*block as usize];
         let block_name = block_name.split('[').next().unwrap().to_string();
 
         let entry = palette.entry(block_name).or_insert_with(|| {
@@ -47,9 +48,8 @@ pub fn strip_data(schem: &Schematic) -> Schematic {
         data.push(*entry);
     }
 
-    Schematic {
+    SpongeSchematic {
-        version: schem.version,
+        data_version: 1,
-        data_version: schem.data_version,
         palette,
         palette_max,
         block_data: data,
@@ -57,17 +57,17 @@ pub fn strip_data(schem: &Schematic) -> Schematic {
         height: schem.height,
         length: schem.length,
         width: schem.width,
-        metadata: schem.metadata.clone(),
+        metadata: CompoundTag::new(),
-        offset: schem.offset.clone(),
+        offset: [0; 3],
         entities: None,
     }
 }
 
-pub fn match_palette_adapt(schem: &Schematic, matching_palette: &Map<String, i32>, ignore_data: bool) -> Vec<i32> {
+pub fn match_palette_adapt(schem: &SpongeSchematic, matching_palette: &HashMap<String, i32>, ignore_data: bool) -> Vec<i32> {
-    let mut data: Vec<i32> = Vec::new();
+    let mut data = Vec::with_capacity(schem.block_data.len());
     let reverse_palette = create_reverse_palette(schem);
 
-    for x in &schem.block_data {
+    for x in schem.block_data.as_slice().iter() {
         let blockname = reverse_palette[*x as usize];
         let blockname = if ignore_data { normalize_data(blockname, ignore_data) } else { blockname };
         let block_id = match matching_palette.get(&*blockname) {
@@ -81,10 +81,10 @@ pub fn match_palette_adapt(schem: &Schematic, matching_palette: &Map<String, i32
 }
 
 pub fn match_palette(
-    schem: &Schematic,
+    schem: &SpongeSchematic,
-    pattern: &Schematic,
+    pattern: &SpongeSchematic,
     ignore_data: bool,
-) -> Schematic {
+) -> SpongeSchematic {
     if ignore_data {
         match_palette_internal(&strip_data(schem), &strip_data(pattern), ignore_data)
     } else {
@@ -93,24 +93,23 @@ pub fn match_palette(
 }
 
 fn match_palette_internal(
-    schem: &Schematic,
+    schem: &SpongeSchematic,
-    pattern: &Schematic,
+    pattern: &SpongeSchematic,
     ignore_data: bool,
-) -> Schematic {
+) -> SpongeSchematic {
     let data_pattern: Vec<i32> = match_palette_adapt(&pattern, &schem.palette, ignore_data);
 
-    Schematic {
+    SpongeSchematic {
-        version: pattern.version.clone(),
+        data_version: 0,
-        data_version: pattern.data_version.clone(),
         palette: schem.palette.clone(),
         palette_max: schem.palette_max,
         block_data: data_pattern,
         block_entities: pattern.block_entities.clone(),
-        height: pattern.height.clone(),
+        height: pattern.height,
-        length: pattern.length.clone(),
+        length: pattern.length,
-        width: pattern.width.clone(),
+        width: pattern.width,
-        metadata: pattern.metadata.clone(),
+        metadata: CompoundTag::new(),
-        offset: pattern.offset.clone(),
+        offset: [0; 3],
         entities: None,
     }
 }

schemsearch-lib/src/search.rs

@@ -0,0 +1,87 @@
+use math::round::ceil;
+use schemsearch_files::SpongeSchematic;
+use crate::{Match, SearchBehavior};
+use crate::pattern_mapper::{match_palette, match_palette_adapt};
+
+pub fn search(
+    schem: SpongeSchematic,
+    pattern_schem: &SpongeSchematic,
+    search_behavior: SearchBehavior,
+) -> Vec<Match> {
+    if schem.width < pattern_schem.width || schem.height < pattern_schem.height || schem.length < pattern_schem.length {
+        return Vec::new();
+    }
+
+    if pattern_schem.palette.len() > schem.palette.len() {
+        return Vec::new();
+    }
+
+    let pattern_schem = match_palette(&schem, &pattern_schem, search_behavior.ignore_block_data);
+
+    let mut matches: Vec<Match> = Vec::with_capacity(4);
+
+    let pattern_data = pattern_schem.block_data.as_ptr();
+
+    let schem_data = if search_behavior.ignore_block_data {
+        match_palette_adapt(&schem, &pattern_schem.palette, search_behavior.ignore_block_data)
+    } else {
+        schem.block_data
+    };
+
+    let schem_data = schem_data.as_ptr();
+
+    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.block_data.len() as f32;
+    let i_pattern_blocks = pattern_blocks as i32;
+
+    let pattern_width = pattern_schem.width as usize;
+    let pattern_height = pattern_schem.height as usize;
+    let pattern_length = pattern_schem.length as usize;
+
+    let schem_width = schem.width as usize;
+    let schem_height = schem.height as usize;
+    let schem_length = schem.length as usize;
+
+    let skip_amount = ceil((pattern_blocks * (1.0 - search_behavior.threshold)) as f64, 0) as i32;
+
+    for y in 0..=schem_height - pattern_height {
+        for z in 0..=schem_length - pattern_length {
+            for x in 0..=schem_width - pattern_width {
+                let mut not_matching = 0;
+                'outer:
+                for j in 0..pattern_height {
+                    for k in 0..pattern_length {
+                        'inner:
+                        for i in 0..pattern_width {
+                            let index = (x + i) + schem_width * ((z + k) + (y + j) * schem_length);
+                            let pattern_index = i + pattern_width * (k + j * pattern_length);
+                            let data = unsafe { *schem_data.add(index) };
+                            let pattern_data = unsafe { *pattern_data.add(pattern_index) };
+                            if (search_behavior.ignore_air && data != *air_id) || (search_behavior.air_as_any && pattern_data != *air_id) {
+                                continue 'inner;
+                            }
+                            if data != pattern_data {
+                                not_matching += 1;
+                                if not_matching >= skip_amount {
+                                    break 'outer;
+                                }
+                            }
+                        }
+                    }
+                }
+
+                if not_matching < skip_amount {
+                    matches.push(Match {
+                        x: x as u16,
+                        y: y as u16,
+                        z: z as u16,
+                        percent: (i_pattern_blocks - not_matching) as f32 / pattern_blocks,
+                    });
+                }
+            }
+        }
+    }
+
+    return matches;
+}

schemsearch-sql/Cargo.toml

@@ -1,13 +1,13 @@
 [package]
 name = "schemsearch-sql"
-version = "0.1.1"
+version = "0.1.3"
 edition = "2021"
 license = "AGPL-3.0-or-later"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-sqlx = { version = "0.6", features = [ "runtime-async-std-native-tls" , "mysql" ] }
+sqlx = { version = "0.7", features = [ "runtime-async-std-native-tls" , "mysql" ] }
 
 schemsearch-lib = { path = "../schemsearch-lib" }
 schemsearch-files = { path = "../schemsearch-files" }