Replace serdi with more fine-grained tools

Especially with the new functionality, the complexity of the command-line
interface alone was really becoming unmanageable.  The serdi implementation
also had the highest cyclomatic complexity of the entire codebase by a huge
margin.

So, take a page from the Unix philosophy and split serdi into several more
finely-honed tools that can be freely composed.  Though there is still
unfortunately quite a bit of option overlap between them due to the common
details of reading RDF, I think the resulting tools are a lot easier to
understand, both from a user and a developer perspective.

1 files changed, 70 insertions, 1 deletions

diff --git a/test/serd_test_util/__init__.py b/test/serd_test_util/__init__.py
index f0b1c19a..45cc6e64 100644
--- a/test/serd_test_util/__init__.py
+++ b/test/serd_test_util/__init__.py
@@ -3,8 +3,48 @@
 """Utilities for data-driven tests."""
 
 import datetime
+import difflib
+import os
 import re
 import subprocess
+import sys
+
+
+def error(message):
+    """Log an error message to stderr"""
+
+    sys.stderr.write("error: ")
+    sys.stderr.write(message)
+
+
+def test_input_syntax(test_class):
+    """Return the output syntax use for a given test class."""
+
+    if "NTriples" in test_class:
+        return "NTriples"
+
+    if "Turtle" in test_class:
+        return "Turtle"
+
+    if "NQuads" in test_class:
+        return "NQuads"
+
+    if "Trig" in test_class:
+        return "Trig"
+
+    raise Exception("Unknown test class <{}>".format(test_class))
+
+
+def test_output_syntax(test_class):
+    """Return the output syntax use for a given test class."""
+
+    if "NTriples" in test_class or "Turtle" in test_class:
+        return "NTriples"
+
+    if "NQuads" in test_class or "Trig" in test_class:
+        return "NQuads"
+
+    raise Exception("Unknown test class <{}>".format(test_class))
 
 
 def earl_assertion(test, passed, asserter):
@@ -33,7 +73,7 @@ def earl_assertion(test, passed, asserter):
 
 
 def load_rdf(command_prefix, filename):
-    """Load an RDF file as dictionaries via serdi (only supports URIs)."""
+    """Load an RDF file as dictionaries via serd-pipe (only supports URIs)."""
 
     rdf_type = "http://www.w3.org/1999/02/22-rdf-syntax-ns#type"
     model = {}
@@ -61,3 +101,32 @@ def load_rdf(command_prefix, filename):
                     instances[o].update([s])
 
     return model, instances
+
+
+def file_equals(patha, pathb):
+    """Return true if the file at patha is the same as the file at pathb."""
+
+    for path in (patha, pathb):
+        if not os.access(path, os.F_OK):
+            error("missing file {}\n".format(path))
+            return False
+
+    with open(patha, "r", encoding="utf-8") as fa:
+        with open(pathb, "r", encoding="utf-8") as fb:
+            return show_diff(fa.readlines(), fb.readlines(), patha, pathb)
+
+
+def show_diff(from_lines, to_lines, from_filename, to_filename):
+    """Print a diff between files to stderr."""
+
+    same = True
+    for line in difflib.unified_diff(
+        from_lines,
+        to_lines,
+        fromfile=os.path.abspath(from_filename),
+        tofile=os.path.abspath(to_filename),
+    ):
+        sys.stderr.write(line)
+        same = False
+
+    return same