update tests and docs

.gitignore

@@ -158,3 +158,4 @@ output
 **/_SUCCESS
 **/*parquet
 **/checkpoints
+*code-workspace

Makefile

@@ -5,16 +5,17 @@
 # from the environment for the first two.
 SPHINXOPTS    ?=
 SPHINXBUILD   ?= sphinx-build
-SOURCEDIR     = source
-BUILDDIR      = build
+SOURCEDIR     = docs/source
+BUILDDIR      = docs/build
 
-# Put it first so that "make" without argument is like "make help".
-help:
-	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+build:
+	@$(SPHINXBUILD) -b html "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS)
 
-.PHONY: help Makefile
+serve:
+	@$(SPHINXBUILD) -b html "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS)
+	@cd docs/build && python3 -m http.server
 
-# Catch-all target: route all unknown targets to Sphinx using the new
-# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
-%: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+test:
+	coverage run -m pytest --doctest-modules . --ignore deduplicate-text-datasets --ignore docs --ignore text_dedup/minhash_spark.py --ignore reference
+	coverage report -m
+	coverage xml -o cobertura.xml