Prove multiprocessing works, although it is still racy in some places

ocrmypdf/pdfinfo.py

@@ -682,6 +682,7 @@ class PdfInfo:
     
     """
     def __init__(self, infile):
+        self._infile = infile
         self._pages = _pdf_get_all_pageinfo(infile)
 
     @property
@@ -702,6 +703,14 @@ class PdfInfo:
     def __repr__(self):
         return "<PdfInfo('...'), page count={}>".format(len(self))
 
+    # def __getstate__(self):
+    #     state = {'_infile': self._infile}
+    #     return state
+    #
+    # def __setstate__(self, state):
+    #     self._infile = state['_infile']
+    #     self._pages = _pdf_get_all_pageinfo(self._infile)
+
 
 def main():
     import argparse

ocrmypdf/pipeline.py

@@ -52,6 +52,9 @@ class JobContext:
     def __init__(self):
         self.pdfinfo = None
 
+    def generate_pdfinfo(self, infile):
+        self.pdfinfo = PdfInfo(infile)
+
     def get_pdfinfo(self):
         "What we know about the input PDF"
         return self.pdfinfo
@@ -72,8 +75,8 @@ class JobContext:
         self.work_folder = work_folder
 
 
-from multiprocessing.managers import BaseManager
-class JobContextManager(BaseManager):
+from multiprocessing.managers import SyncManager
+class JobContextManager(SyncManager):
     pass
 
 

tests/test_multiprocessing.py

@@ -5,29 +5,43 @@ from multiprocessing import Process
 from multiprocessing.managers import BaseProxy
 
 
-def client(context):
-    assert isinstance(context, BaseProxy)
-    pdfinfo = context.get_pdfinfo()
-    page = pdfinfo[0]
-    page.rotation = 90
-    context.set_pdfinfo(pdfinfo)
-
-
-def test_proxies(resources):
+def test_jobcontext_proxy(resources):
+    # Prove that managers are set up correctly to share state among processes
     manager = JobContextManager()
     manager.register('JobContext', JobContext)
+
+    # Start the manager in a child process (or maybe thread)
     manager.start()
 
+    # Tell the manager process to retrieve pdf info
     context = manager.JobContext()
+    context.generate_pdfinfo(resources / 'graph.pdf')
 
-    pdfinfo = PdfInfo(resources / 'graph.pdf')
+    # Get a copy of that information for this process
+    pdfinfo = context.get_pdfinfo()
+    assert len(pdfinfo) == 1
     assert pdfinfo[0].rotation == 0
+
+    # Update information and send back to manager
+    pdfinfo[0].rotation = 90
     context.set_pdfinfo(pdfinfo)
-    del pdfinfo
+
+    # Retrieve again, ensure it stayed changed
+    pdfinfo2 = context.get_pdfinfo()
+    assert pdfinfo2[0].rotation == 90
+
+    # Start a new process which gets its own proxy object
+    def client(context):
+        assert isinstance(context, BaseProxy)
+        pdfinfo = context.get_pdfinfo()
+        page = pdfinfo[0]
+        assert page.rotation == 90
+        page.rotation += 90
+        context.set_pdfinfo(pdfinfo)
 
     p = Process(target=client, args=(context,))
     p.start()
     p.join()
     assert p.exitcode == 0, "Child process failed"
 
-    assert context.get_pdfinfo()[0].rotation == 90
+    assert context.get_pdfinfo()[0].rotation == 180