Add check_jar function, and use it in the CoreNLP tests

Author: tomaarsen

nltk/parse/corenlp.py

@@ -311,7 +311,8 @@ def tokenize(self, text, properties=None):
         """Tokenize a string of text.
 
         Skip these tests if CoreNLP is likely not ready.
-        >>> if "CLASSPATH" not in os.environ: import pytest; pytest.skip("CoreNLP jars unavailable")
+        >>> from nltk.test.setup_fixt import check_jar
+        >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True)
 
         The CoreNLP server can be started using the following notation, although
         we recommend the `with CoreNLPServer() as server:` context manager notation
@@ -367,7 +368,8 @@ def tag(self, sentence: str) -> List[Tuple[str, str]]:
         :rtype: list(tuple(str, str))
 
         Skip these tests if CoreNLP is likely not ready.
-        >>> if "CLASSPATH" not in os.environ: import pytest; pytest.skip("CoreNLP jars unavailable")
+        >>> from nltk.test.setup_fixt import check_jar
+        >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True)
 
         The CoreNLP server can be started using the following notation, although
         we recommend the `with CoreNLPServer() as server:` context manager notation
@@ -422,7 +424,8 @@ def raw_tag_sents(self, sentences):
 class CoreNLPParser(GenericCoreNLPParser):
     """
     Skip these tests if CoreNLP is likely not ready.
-    >>> if "CLASSPATH" not in os.environ: import pytest; pytest.skip("CoreNLP jars unavailable")
+    >>> from nltk.test.setup_fixt import check_jar
+    >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True)
 
     The recommended usage of `CoreNLPParser` is using the context manager notation:
     >>> with CoreNLPServer() as server:
@@ -586,7 +589,8 @@ class CoreNLPDependencyParser(GenericCoreNLPParser):
     """Dependency parser.
 
     Skip these tests if CoreNLP is likely not ready.
-    >>> if "CLASSPATH" not in os.environ: import pytest; pytest.skip("CoreNLP jars unavailable")
+    >>> from nltk.test.setup_fixt import check_jar
+    >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True)
 
     The recommended usage of `CoreNLPParser` is using the context manager notation:
     >>> with CoreNLPServer() as server:

nltk/test/setup_fixt.py

@@ -1,11 +1,23 @@
-# Skip doctest when a required binary is not available
-from nltk.internals import find_binary
+from nltk.internals import find_binary, find_jar
 
 
-def check_binary(binary):
+def check_binary(binary: str, **args):
+    """Skip a test via `pytest.skip` if the `binary` executable is not found.
+    Keyword arguments are passed to `nltk.internals.find_binary`."""
     import pytest
 
     try:
-        find_binary(binary)
+        find_binary(binary, **args)
     except LookupError:
         pytest.skip(f"Skipping test because the {binary} binary was not found")
+
+
+def check_jar(name_pattern: str, **args):
+    """Skip a test via `pytest.skip` if the `name_pattern` jar is not found.
+    Keyword arguments are passed to `nltk.internals.find_jar`."""
+    import pytest
+
+    try:
+        find_jar(name_pattern, **args)
+    except LookupError:
+        pytest.skip(f"Skipping test because the {name_pattern!r} jar was not found")