Use .arg instead of .trees

.gitignore

@@ -1,6 +1,6 @@
 build-gcc
 .DS_Store
-python/benchmark/*.trees
+python/benchmark/*.arg
 python/benchmark/*.json
 python/benchmark/*.html
 .venv

c/examples/cpp_sorting_example.cpp

@@ -73,7 +73,7 @@ int
 main(int argc, char **argv)
 {
     if (argc != 3) {
-        std::cerr << "Usage: " << argv[0] << " input.trees output.trees\n";
+        std::cerr << "Usage: " << argv[0] << " input.arg output.arg\n";
         std::exit(0);
     }
     const char *infile = argv[1];

c/tskit/tables.h

@@ -4001,7 +4001,7 @@ Options can be specified by providing one or more of the following bitwise
 
     int ret;
     tsk_table_collection_t tables;
-    ret = tsk_table_collection_load(&tables, "data.trees", 0);
+    ret = tsk_table_collection_load(&tables, "data.arg", 0);
     if (ret != 0) {
         fprintf(stderr, "Load error:%s\n", tsk_strerror(ret));
         exit(EXIT_FAILURE);
@@ -4096,7 +4096,7 @@ and well formed files will be written.
     error_check(ret);
     tables.sequence_length = 1.0;
     // Write out the empty tree sequence
-    ret = tsk_table_collection_dump(&tables, "empty.trees", 0);
+    ret = tsk_table_collection_dump(&tables, "empty.arg", 0);
     error_check(ret);
 
 @endrst

c/tskit/trees.h

@@ -338,7 +338,7 @@ that function's documentation for details and options.
 
     int ret;
     tsk_treeseq_t ts;
-    ret = tsk_treeseq_load(&ts, "data.trees", 0);
+    ret = tsk_treeseq_load(&ts, "data.arg 0);
     if (ret != 0) {
         fprintf(stderr, "Load error:%s\n", tsk_strerror(ret));
         exit(EXIT_FAILURE);

docs/c-api.rst

@@ -23,7 +23,7 @@ Do I need the C API?
 The ``tskit`` C API is generally useful in the following situations:
 
 - You want to use the ``tskit`` API in a larger C/C++ application (e.g.,
-  in order to output data in the ``.trees`` format);
+  in order to output data in the ``.arg`` format);
 - You need to perform lots of tree traversals/loops etc. to analyse some
   data that is in tree sequence form.
 
@@ -909,15 +909,15 @@ normally.
 
 Running this program on some tree sequence files we might get::
 
-    $ cat tmp1.trees tmp2.trees | ./build/streaming > no_mutations.trees
+    $ cat tmp1.arg tmp2.arg | ./build/streaming > no_mutations.arg
     Tree sequence 0 had 38 mutations
     Tree sequence 1 had 132 mutations
 
 Then, running this program again on the output of the previous command,
 we see that we now have two tree sequences with their mutations removed
-stored in the file ``no_mutations.trees``::
+stored in the file ``no_mutations.arg``::
 
-    $ ./build/streaming < no_mutations.trees > /dev/null
+    $ ./build/streaming < no_mutations.arg > /dev/null
     Tree sequence 0 had 0 mutations
     Tree sequence 1 had 0 mutations
 

docs/export.md

@@ -41,7 +41,7 @@ If we have a tree sequence file the
 convenient way to convert to VCF:
 
 :::{code-block} bash
-$ tskit vcf example.trees > example.vcf
+$ tskit vcf example.arg > example.vcf
 :::
 
 See the {ref}`sec_export_vcf_compression` section for information
@@ -137,14 +137,14 @@ The simplest way to compress the VCF output is to use the
 and pipe the output to `bgzip`:
 
 :::{code-block} bash
-$ tskit vcf example.trees | bgzip -c > example.vcf.gz
+$ tskit vcf example.arg | bgzip -c > example.vcf.gz
 :::
 A general way to convert VCF data to various formats is to pipe the text
 produced by ``tskit`` into ``bcftools`` using the command
 line interface:
 
 :::{code-block} bash
-$ tskit vcf example.trees | bcftools view -O b > example.bcf
+$ tskit vcf example.arg | bcftools view -O b > example.bcf
 :::
 
 If you need more control over the form of the output (or want to work

docs/file-formats.md

@@ -29,8 +29,8 @@ data on file in a columnar, binary format. The format is based on the
 key-value store for numerical data. There is a one-to-one correspondence
 between the tables described above and the arrays stored in these files.
 
-By convention, these files are given the `.trees` suffix (although this
-is not enforced in any way), and we will sometimes refer to them as ".trees"
+By convention, these files are given the `.arg` suffix (although this
+is not enforced in any way), and we will sometimes refer to them as ".arg"
 files. We also refer to them as "tree sequence files".
 
 :::{todo}

docs/provenance.md

@@ -30,7 +30,7 @@ This documentation serves two distinct purposes:
 1. For developers using `tskit` in their own applications, it provides normative documentation
    for how provenance information should be stored.
 2. For end-users of `tskit`, it provides documentation to allows them to inspect and interpret
-   the provenance information stored in `.trees` files.
+   the provenance information stored in `.arg` files.
 
 Provenance information is encoded using [JSON](https://www.json.org/).
 To standardise the provenance information produced by different software and improve
@@ -167,7 +167,7 @@ here even though it was automatically generated.
 Consider the following invocation of a hypothetical command line program:
 
 ```bash
-$ supersim --sample-size=10 --do-some-stuff -O out.trees
+$ supersim --sample-size=10 --do-some-stuff -O out.arg
 ```
 
 We recommend encoding the parameters provenance as follows (other fields omitted
@@ -177,7 +177,7 @@ for clarity):
 {
   "parameters": {
     "command": "supersim",
-    "args": ["--sample-size=10", "--do-some-stuff", "-O", "out.trees"],
+    "args": ["--sample-size=10", "--do-some-stuff", "-O", "out.arg"],
     "random_seed": 56789
   }
 }
@@ -245,7 +245,7 @@ account for resource usage across pipelines of tools.
 ## Full schema
 
 This schema is formally defined using [JSON Schema](http://json-schema.org/) and
-given in full here. Developers writing provenance information to `.trees` files
+given in full here. Developers writing provenance information to `.arg` files
 should validate the output JSON against this schema.
 
 ```{eval-rst}

docs/quickstart.md

@@ -27,7 +27,7 @@ def basic_sim():
         recombination_rate=1e-7,
         random_seed=665)
     ts = msprime.sim_mutations(ts, rate=2e-7, random_seed=123)
-    ts.dump("data/basic_tree_seq.trees")
+    ts.dump("data/basic_tree_seq.arg")
 
 def create_notebook_data():
     basic_sim()
@@ -53,7 +53,7 @@ sites.
 ```{code-cell}
 import tskit
 
-ts = tskit.load("data/basic_tree_seq.trees")  # Or generate using e.g. msprime.sim_ancestry()
+ts = tskit.load("data/basic_tree_seq.arg")  # Or generate using e.g. msprime.sim_ancestry()
 ts  # In a Jupyter notebook this displays a summary table. Otherwise use print(ts)
 ```
 

python/benchmark/config.yaml

@@ -5,8 +5,8 @@ benchmarks:
   - code: ts = tskit.load("{filename}")
     parameters:
       filename: &files
-        - "tiny.trees"
-        - "bench.trees"
+        - "tiny.arg"
+        - "bench.arg"
 
   - code: ts.dump("/dev/null");"{filename}"
     setup: |
@@ -18,7 +18,7 @@ benchmarks:
     #, site_mask=site_mask, sample_mask=sample_mask)
     setup: |
       import numpy
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tables = ts.tables
       tables.migrations.clear()
       ts = tables.tree_sequence()
@@ -37,7 +37,7 @@ benchmarks:
       tree.seek(pos)
       pos = 0 if pos == 500_000 else 500_000
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tree = ts.first()
       pos = 500_000
 
@@ -48,7 +48,7 @@ benchmarks:
 
   - code: tree.{array}
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tree = ts.first()
     parameters:
       array: &tree_arrays
@@ -62,7 +62,7 @@ benchmarks:
 
   - code: tree.{array}(42);
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tree = ts.first()
     parameters:
       array:
@@ -76,7 +76,7 @@ benchmarks:
 
   - code: tree.{traversal_order}()
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tree = ts.first()
     parameters:
       traversal_order: &traversal_orders
@@ -102,7 +102,7 @@ benchmarks:
       filename: *files
 
   - code: "for row in ts.{table}(): pass"
-    setup: ts = tskit.load("bench.trees")
+    setup: ts = tskit.load("bench.arg")
     parameters:
       table: &tables
         - nodes
@@ -128,7 +128,7 @@ benchmarks:
 
   - code: ts.{table}(1)
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
     parameters:
       table:
         - node
@@ -141,18 +141,18 @@ benchmarks:
         - provenance
 
   - code: ts.tables
-    setup: ts = tskit.load("bench.trees")
+    setup: ts = tskit.load("bench.arg")
 
   - code: tables.{table}
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tables = ts.tables
     parameters:
       table: *tables
 
   - code: x = {table}.{column}
     setup: |
-      ts = tskit.load("bench.trees")
+      ts = tskit.load("bench.arg")
       tables = ts.tables
       {table} = tables.{table}
     parameters: &table_columns

python/benchmark/run.py

@@ -41,7 +41,7 @@ def system_info():
 
 
 def make_file():
-    benchmark_trees = tskit_dir / "benchmark" / "bench.trees"
+    benchmark_trees = tskit_dir / "benchmark" / "bench.arg"
     if not os.path.exists(benchmark_trees):
         print("Generating benchmark trees...")
         demography = msprime.Demography()
@@ -70,7 +70,7 @@ def make_file():
             record_provenance=True,
         )
         ts = msprime.sim_mutations(ts, rate=0.001, random_seed=42)
-        ts.dump(tskit_dir / "benchmark" / "tiny.trees")
+        ts.dump(tskit_dir / "benchmark" / "tiny.arg")
 
 
 def autotime(setup, code):

python/tests/data/SLiM/minimal-example.txt

@@ -10,6 +10,6 @@ initialize() {
     sim.addSubpop("p1", 5);
 }
 3 {
-    sim.treeSeqOutput("tests/data/SLiM/minimal-example.trees");
+    sim.treeSeqOutput("tests/data/SLiM/minimal-example.arg");
     sim.simulationFinished();
 }

python/tests/data/SLiM/single-locus-example.txt

@@ -10,6 +10,6 @@ initialize() {
     sim.addSubpop("p1", 5);
 }
 3 {
-    sim.treeSeqOutput("tests/data/SLiM/single-locus-example.trees");
+    sim.treeSeqOutput("tests/data/SLiM/single-locus-example.arg");
     sim.simulationFinished();
 }

python/tests/ibd.py

@@ -327,7 +327,7 @@ def passes_filters(self, a, b, left, right):
     """
     A simple CLI for running IBDFinder on a command line from the `python`
     subdirectory. Basic usage:
-    > python3 ./tests/ibd.py --infile test.trees
+    > python3 ./tests/ibd.py --infile test.arg
     """
 
     parser = argparse.ArgumentParser(