pyproject.toml

@@ -6,7 +6,6 @@ readme = "README.md"
 requires-python = ">=3.9"
 dependencies = [
     "deltas>=0.7.0",
-    "mediawiki-utilities>=0.4.18",
     "more-itertools>=10.7.0",
     "mwparserfromhell>=0.6.0",
     "mwpersistence>=0.2.4",
@@ -18,6 +17,17 @@ dependencies = [
     "yamlconf>=0.2.6",
 ]
 
+# Two features carry dependencies that are awkward enough to install that they
+# are kept out of the base install: -p legacy needs mediawiki-utilities, a 2015
+# package that also pulls in a MySQL client, and --diff and -p wikidiff2 need
+# pywikidiff2, which compiles a C++ extension. Everything else, including the
+# default -p sequence, works with neither.
+[project.optional-dependencies]
+legacy = ["mediawiki-utilities>=0.4.18"]
+# A wikidiff2 extra belongs here too, but pywikidiff2 is not yet published to
+# PyPI, so an extra naming it could not resolve. Until it is, wikiq reports the
+# git install command when --diff or -p wikidiff2 is used without it.
+
 [project.scripts]
 wikiq = "wikiq:main"
 

src/wikiq/__init__.py

@@ -67,6 +67,22 @@ def require_pywikidiff2(feature: str):
     return pywikidiff2
 
 
+def require_mw_persistence():
+    """Import and return mw.lib.persistence, or exit explaining how to get it."""
+    try:
+        from mw.lib import persistence
+    except ImportError:
+        raise SystemExit(
+            "-p legacy requires mediawiki-utilities, which wikiq no longer "
+            "installs by default.\n"
+            "Install it with:\n"
+            "    pip install 'mediawiki-dump-tools[legacy]'\n"
+            "This method exists to reproduce results from older research "
+            "projects; -p sequence is the current equivalent."
+        )
+    return persistence
+
+
 def pyarrow_type_to_spark(pa_type):
     """Convert a PyArrow type to Spark JSON schema format."""
     if pa.types.is_int64(pa_type):
@@ -845,7 +861,7 @@ class WikiqParser:
                         wikidiff_matcher, revert_radius=PERSISTENCE_RADIUS
                     )
                 else:
-                    from mw.lib import persistence
+                    persistence = require_mw_persistence()
                     persist_state = persistence.State()
 
             # Pending persistence values waiting for window to fill
@@ -1298,6 +1314,8 @@ def main():
         require_pywikidiff2("--diff")
     if persist == PersistMethod.wikidiff2:
         require_pywikidiff2("-p wikidiff2")
+    elif persist == PersistMethod.legacy:
+        require_mw_persistence()
 
     if args.namespace_filter is not None:
         namespaces = args.namespace_filter