update findLongSeqs, now treats U+T identically

.dockerignore

@@ -6,6 +6,6 @@
 !autotax.bash
 !tests.bats
 !getsilvadb.sh
-!filtershortseqs/include/progressbar.h
-!filtershortseqs/CMakeLists.txt
-!filtershortseqs/main.cpp
+!findLongSeqs/include/progressbar.h
+!findLongSeqs/CMakeLists.txt
+!findLongSeqs/main.cpp

.gitmodules

@@ -1,3 +1,6 @@
-[submodule "filtershortseqs"]
-	path = filtershortseqs
-	url = [email protected]:KasperSkytte/filtershortseqs.git
+[submodule "find_longest_sequences"]
+	path = findLongSeqs
+	url = [email protected]:kasperskytte/find_longest_sequences.git
+[submodule "findLongSeqs"]
+	path = findLongSeqs
+	url = [email protected]:kasperskytte/find_longest_sequences.git

Dockerfile

@@ -86,12 +86,12 @@ RUN wget -q https://github.com/bats-core/bats-core/archive/refs/tags/v1.3.0.tar.
 COPY . /opt/autotax/
 RUN chmod +x /opt/autotax/autotax.bash /opt/autotax/getsilvadb.sh
 
-### compile filterShortSeqs from submodule
-RUN cd /opt/autotax/filtershortseqs && \
+### compile findLongSeqs from submodule
+RUN cd /opt/autotax/findLongSeqs && \
   cmake CMakelists.txt && \
   make && \
-  ln -s /opt/autotax/filtershortseqs/filterShortSeqs /usr/local/bin/filterShortSeqs && \
-  chmod +x /usr/local/bin/filterShortSeqs
+  ln -s /opt/autotax/findLongSeqs/findLongSeqs /usr/local/bin/findLongSeqs && \
+  chmod +x /usr/local/bin/findLongSeqs
 
 ### make sure everything is in PATH
 ENV PATH="/opt/autotax:${PATH}"

README.md

@@ -68,7 +68,7 @@ cd AutoTax
  - usearch (11)
  - SINA (1.6 or later)
  - GNU parallel (20161222-1)
- - [filterShortSeqs](https://github.com/KasperSkytte/filtershortseqs/), credit goes to [Nick Green](https://github.com/nickgreensgithub/find_longest_sequences). The initial R implementation was extremely inefficient
+ - [findLongSeqs](https://github.com/KasperSkytte/find_longest_sequences/), credit goes to [Nick Green](https://github.com/nickgreensgithub/find_longest_sequences). The initial R implementation was extremely inefficient
  - R (3.5 or later) with the following packages installed (the script will attempt to install if missing):
    - Biostrings (from Bioconductor through `BiocManager::install()`)
    - doParallel

autotax.bash

@@ -288,7 +288,7 @@ findLongest() {
   done
 
   echoWithHeader "  - Finding the longest representative sequence of identical sequences, filtering the shorter ones..."
-  filterShortSeqs "$input" "$output" "$maxthreads"
+  findLongSeqs "$input" "$output" "$maxthreads"
 
   echoWithHeader "  - Renaming sequences to FLASV(ID).(length)"
   #Rename with new ID's to "FLASV(ID).(length)" fx: "FLASV1.1413"