Add model and serd-sort utility

With all the new functionality, the complexity of the serd-pipe command-line
interface is starting to push the limits of available flags. So, instead of
grafting on further options to control a model, this commit adds a new tool,
serd-sort, which acts somewhat like a stripped-down serd-pipe that stores
statements in a model in memory.

This keeps the complexity (including the user-facing complexity) of any one
tool down, since other more focused tools can be used for streaming tasks in a
pipeline.

In other words, abandon Swissarmyknifeism, take a page from the Unix
philosophy, and try to expose the model functionality to the command-line in a
dedicated focused tool.  The model implementation is tested by using this tool
to run a subset of the usual test suites, and a special suite to test statement
sorting.

1 files changed, 16 insertions, 7 deletions

diff --git a/scripts/serd_bench.py b/scripts/serd_bench.py
index db8c1c5b..35869ce6 100755
--- a/scripts/serd_bench.py
+++ b/scripts/serd_bench.py
@@ -76,8 +76,8 @@ def gen(sp2b_dir, n_min, n_max, step):
 
 def write_header(results, progs):
     "Write the header line for TSV output"
-    results.write("n")
-    for prog in progs:
+    results.write("n\tserd-pipe\tserd-sort")
+    for prog in progs[2:]:
         results.write("\t" + os.path.basename(prog.split()[0]))
     results.write("\n")
 
@@ -191,13 +191,18 @@ def run(progs, n_min, n_max, step):
                 cmd = "/usr/bin/time -v " + prog + " " + filename(n)
                 with open(filename(n) + ".out", "w") as out:
                     sys.stderr.write(cmd + "\n")
-                    proc = subprocess.Popen(
-                        cmd.split(), stdout=out, stderr=subprocess.PIPE
+                    proc = subprocess.run(
+                        cmd.split(),
+                        check=True,
+                        stdout=out,
+                        stderr=subprocess.PIPE,
                     )
 
-                    time, memory = parse_time(proc.communicate()[1].decode())
+                    time, memory = parse_time(proc.stderr.decode())
                     rows["time"] += ["%.07f" % time]
-                    rows["throughput"] += ["%d" % (n / time)]
+                    rows["throughput"] += (
+                        ["%d" % (n / time)] if time > 0.0 else ["0"]
+                    )
                     rows["memory"] += [str(memory)]
 
             # Write rows to output files
@@ -272,7 +277,11 @@ example:
     args = ap.parse_args(sys.argv[1:])
 
     serd_opts = "-I turtle -I verbatim -O turtle -O verbatim -O expanded"
-    progs = ["tools/serd-pipe " + serd_opts] + args.run
+    progs = [
+        "tools/serd-pipe " + serd_opts,
+        "tools/serd-sort " + serd_opts,
+    ] + args.run
+
     min_n = int(args.max / args.steps)
     max_n = args.max
     step = min_n