Astral OOM fix + BuildSA reliability/scaling improvements

docs/examples/readme.md

@@ -1,6 +1,6 @@
 # Example configuration and sample outputs
 
-Broader manuals (MS-GF+ CLI, BuildSA, MzID→TSV, changelog, …) are Markdown pages one level up: [`../readme.md`](../readme.md).
+Broader manuals (MS-GF+ CLI, BuildSA, changelog, …) are Markdown pages one level up: [`../readme.md`](../readme.md).
 
 This directory holds **small text examples** shipped with the repository:
 
@@ -12,7 +12,6 @@ This directory holds **small text examples** shipped with the repository:
 | `protocols.txt` | Example custom protocols for `params/protocols.txt`. |
 | `Mods.txt` | Example modification file. |
 | `pxd001819_example.pin` | **Sample Percolator `.pin` output** from a PXD001819 (yeast + UPS1 on LTQ Orbitrap Velos) search. Header + 20 target PSMs + 10 decoy PSMs, chosen for peptide-sequence diversity so every column is represented. Use this to inspect the `.pin` schema without running a full search. Full column reference in [`../output.md`](../output.md). |
-| `test.mzid` | Tiny mzIdentML sample used in static documentation. |
 | `test.tsv`, `test_Unrolled.tsv` | Example TSV exports for documentation. |
 
 **Not stored here:** tutorial spreadsheets, plots, or bundled FASTA/index files. Those are either removed as non-essential bloat or live under `src/test/resources/` for automated tests.

pom.xml

@@ -106,42 +106,20 @@
         </plugins>
     </build>
     <dependencies>
-        <dependency>
-            <groupId>uk.ac.ebi.jmzidml</groupId>
-            <artifactId>jmzidentml</artifactId>
-            <version>1.2.11</version>
-            <exclusions>
-                <exclusion>
-                    <groupId>com.sun.xml.bind</groupId>
-                    <artifactId>jaxb-xjc</artifactId>
-                </exclusion>
-            </exclusions>
-        </dependency>
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
             <version>4.13.1</version>
             <scope>test</scope>
             <type>jar</type>
         </dependency>
-        <dependency>
-            <groupId>javax.xml.bind</groupId>
-            <artifactId>jaxb-api</artifactId>
-            <version>2.3.1</version>
-        </dependency>
-        <dependency>
-            <groupId>org.glassfish.jaxb</groupId>
-            <artifactId>jaxb-runtime</artifactId>
-            <version>2.3.2</version>
-            <scope>runtime</scope>
-        </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-text</artifactId>
             <version>1.11.0</version>
         </dependency>
         <!-- jmzml removed: replaced by StaxMzMLParser -->
-        <!-- fastutil is required at runtime by jmzidentml -->
+        <!-- jmzidml removed: pin-direct output; CvParamInfo replaces uk.ac.ebi.jmzidml types -->
         <dependency>
             <groupId>it.unimi.dsi</groupId>
             <artifactId>fastutil</artifactId>
@@ -175,12 +153,6 @@
             <name>The internal repository</name>
             <url>file:${project.basedir}/repo</url>
         </repository>
-        <repository>
-            <!-- This repo is required for cpdetector (required by jmzidml->pride-xml-handler->xxindex->cpdetector) and related libraries -->
-            <!-- This is supplied here because of an HTTP 301 Permanent Redirect on the old URL that xxindex supplies, which breaks fresh builds. -->
-            <id>sammoa-group</id>
-            <url>https://nexus.nuiton.org/nexus/content/groups/sammoa-group/</url>
-        </repository>
     </repositories>
     <organization>
         <name>Center for Computational Mass Spectrometry, University of California, San Diego</name>

src/main/java/edu/ucsd/msjava/msdbsearch/CompactFastaSequence.java

@@ -540,7 +540,9 @@ private FileSignature readSequence() {
             long lastModified = in.readLong();
 
             sequence = new byte[size];
-            in.read(sequence);
+            // readFully: plain in.read() may return short on large .cseq files,
+            // silently corrupting the in-memory sequence.
+            in.readFully(sequence);
 
             in.close();
             return new FileSignature(formatId, id, lastModified);