Merge branch 'main' into try-fastagather

.gitignore

@@ -80,3 +80,7 @@ docs/_build/
 
 # pixi
 .pixi/
+
+*.csv
+*.zip
+*.rocksdb

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "sourmash_plugin_branchwater"
-version = "0.9.12"
+version = "0.9.14-dev"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
@@ -9,22 +9,22 @@ name = "sourmash_plugin_branchwater"
 crate-type = ["cdylib"]
 
 [dependencies]
-pyo3 = { version = "0.23.3", features = ["extension-module", "anyhow"] }
+pyo3 = { version = "0.23.4", features = ["extension-module", "anyhow"] }
 rayon = "1.10.0"
-serde = { version = "1.0.216", features = ["derive"] }
+serde = { version = "1.0.217", features = ["derive"] }
 sourmash = { version = "0.18.0", features = ["branchwater"] }
-serde_json = "1.0.134"
+serde_json = "1.0.135"
 niffler = "2.4.0"
 log = "0.4.22"
-env_logger = { version = "0.11.5" }
+env_logger = { version = "0.11.6" }
 simple-error = "0.3.1"
-anyhow = "1.0.94"
+anyhow = "1.0.95"
 zip = { version = "2.0", default-features = false }
-tempfile = "3.14"
+tempfile = "3.15"
 needletail = "0.5.1"
 csv = "1.3.1"
 camino = "1.1.9"
-glob = "0.3.1"
+glob = "0.3.2"
 rustworkx-core = "0.15.1"
 streaming-stats = "0.2.3"
 rust_decimal = { version = "1.36.0", features = ["maths"] }
@@ -35,7 +35,7 @@ getset = "0.1"
 assert_cmd = "2.0.16"
 assert_matches = "1.5.0"
 predicates = "3.1.3"
-tempfile = "3.14.0"
+tempfile = "3.15.0"
 
 [profile.release]
 #target-cpu=native

README.md

@@ -5,6 +5,8 @@
 
 tl;dr Do faster and lower-memory sourmash functions via this plugin.
 
+<p align="center"><img src="https://raw.githubusercontent.com/sourmash-bio/sourmash_plugin_branchwater/main/doc/_static/logo.png" height="256" /></p>
+
 ## Details
 
 [sourmash](https://sourmash.readthedocs.io/en/latest/) is a

doc/README.md

@@ -1,9 +1,11 @@
 # The branchwater plugin for sourmash
 
+<p align="center"><img src="https://raw.githubusercontent.com/sourmash-bio/sourmash_plugin_branchwater/main/doc/_static/logo.png" height="256" /></p>
+
 | command | functionality | docs |
 | -------- | -------- | -------- |
 | `manysketch` | Rapidly build sketches for many input files     | [link](#Running-manysketch)     |
-| `singlesketch` | Sketch a single sequence file | [link](#Running-singlesketch)
+| `singlesketch` | Sketch a single sample | [link](#Running-singlesketch)
 | `fastgather` | Multithreaded `gather` of **one** metagenome against a database| [link](#Running-fastgather)
 | `fastmultigather` | Multithreaded `gather` of **multiple** metagenomes against a database | [link](#Running-fastmultigather)
 | `manysearch` | Multithreaded containment search for many queries in many large metagenomes | [link](#Running-manysearch)
@@ -257,19 +259,21 @@ In this case, three sketches of `protein`, `dayhoff`, and `hp` moltypes were mad
 
 ## Running `singlesketch`
 
-The `singlesketch` command generates a sketch for a single sequence file.
+The `singlesketch` command generates a sketch for a single sample, with one or more input FASTA/FASTQ files.
 
 ### Basic Usage
+
 ```bash
 sourmash scripts singlesketch input.fa -p k=21,scaled=1000,dna -o output.sig --name signature_name
 ```
+
 ### Using `stdin/stdout`
+
 You can use `-` for `stdin` and output the result to `stdout`:
 ```bash
 cat input.fa | sourmash scripts singlesketch - -o -
 ```
 
-
 ### Running `multisearch` and `pairwise`
 
 The `multisearch` command compares one or more query genomes, and one or more subject genomes. It differs from `manysearch` because it loads everything into memory.
@@ -310,9 +314,9 @@ sourmash scripts fastgather query.sig.gz database.zip -o results.csv --cores 4
 
 ### Running `fastmultigather`
 
-`fastmultigather` takes a collection of query metagenomes and a collection of sketches as a database, and outputs many CSVs:
+`fastmultigather` takes a collection of query metagenomes and a collection of sketches as a database, and outputs a CSV file containing all the matches.
 ```
-sourmash scripts fastmultigather queries.manifest.csv database.zip --cores 4 --save-matches
+sourmash scripts fastmultigather queries.manifest.csv database.zip --cores 4 --save-matches -o results.csv
 ```
 
 We suggest using standalone manifest CSVs wherever possible, especially if
@@ -325,32 +329,26 @@ this can be a significant time savings for large databases.
 
 #### Output files for `fastmultigather`
 
-On a database of sketches (but not on RocksDB indexes)
-`fastmultigather` will output two CSV files for each query, a
-`prefetch` file containing all overlapping matches between that query
-and the database, and a `gather` file containing the minimum
-metagenome cover for that query in the database.
+`fastmultigather` will output a gather file containing all results in
+one file, specified with `-o/--output`. `fastmultigather` gather CSVs
+provide the same columns as `fastgather`, above.
 
-The prefetch CSV will be named `{signame}.prefetch.csv`, and the
-gather CSV will be named `{signame}.gather.csv`.  Here, `{signame}` is
-the name of your sourmash signature.
+In addition, on a database of sketches (but not on RocksDB indexes)
+`fastmultigather` will output a `prefetch` file containing all
+overlapping matches between that query and the database. The prefetch
+CSV will be named `{signame}.prefetch.csv`, where `{signame}` is the
+name of your sourmash signature.
 
 `--save-matches` is an optional flag that will save the matched hashes
 for each query in a separate sourmash signature
 `{signame}.matches.sig`. This can be useful for debugging or for
 further analysis.
 
-When searching against a RocksDB index, `fastmultigather` will output
-a single file containing all gather results, specified with
-`-o/--output`. No prefetch results will be output.
-
-`fastmultigather` gather CSVs provide the same columns as `fastgather`, above.
-
 **Warning:** At the moment, if two different queries have the same
-  `{signame}`, the CSVs for one of the queries will be overwritten by
-  the other query. The behavior here is undefined in practice, because
-  of multithreading: we don't know what queries will be executed when
-  or files will be written first.
+  `{signame}`, the output files for one query will be overwritten by
+  the results from the other query. The behavior here is undefined in
+  practice, because of multithreading: we don't know what queries will
+  be executed when or files will be written first.
 
 ### Running `manysearch`
 

environment.yml

@@ -4,7 +4,7 @@ channels:
     - bioconda
     - defaults
 dependencies:
-    - sourmash>=4.8.3,<5
+    - sourmash-minimal>=4.8.14,<5
     - pip
     - rust
     - maturin>=1,<2

pyproject.toml

@@ -2,14 +2,14 @@
 name = "sourmash_plugin_branchwater"
 description = "fast command-line extensions for sourmash"
 readme = "README.md"
-version = "0.9.12"
+version = "0.9.14-dev"
 requires-python = ">=3.10"
 classifiers = [
     "Programming Language :: Rust",
     "Programming Language :: Python :: Implementation :: CPython",
     "Programming Language :: Python :: Implementation :: PyPy",
     ]
-dependencies = ["sourmash>=4.8.10,<5"]
+dependencies = ["sourmash>=4.8.14,<5"]
 
 authors = [
   { name="N. Tessa Pierce-Ward", orcid="0000-0002-2942-5331" },
@@ -60,7 +60,7 @@ libclang = ">=16.0.6,<16.1"
 python = "3.10.*"
 rust = ">=1.80.0,<1.81"
 maturin = ">=1.7.4,<2"
-sourmash-minimal = ">=4.8.10,<5"
+sourmash-minimal = ">=4.8.14,<5"
 
 [tool.pixi.feature.build.target.linux-64.dependencies]
 patchelf = ">=0.17.2,<0.18"

src/check.rs

@@ -1,14 +1,23 @@
 use crate::utils::is_revindex_database;
+use anyhow::Result;
 
 use sourmash::index::revindex::{RevIndex, RevIndexOps};
 
-pub fn check(index: camino::Utf8PathBuf, quick: bool) -> Result<(), Box<dyn std::error::Error>> {
+pub fn check(index: camino::Utf8PathBuf, quick: bool, rw: bool) -> Result<()> {
     if !is_revindex_database(&index) {
         bail!("'{}' is not a valid RevIndex database", index);
     }
 
-    println!("Opening DB");
-    let db = RevIndex::open(index, true, None)?;
+    println!("Opening DB (rw mode? {})", rw);
+    let db = match RevIndex::open(index, !rw, None) {
+        Ok(db) => db,
+        Err(e) => {
+            return Err(anyhow::anyhow!(
+                "cannot open RocksDB database. Error is: {}",
+                e
+            ))
+        }
+    };
 
     println!("Starting check");
     db.check(quick);