fix: limit number of particles using the eventinfo

README.md

@@ -56,6 +56,38 @@ event.graph.render(filename="test", format="png", cleanup=True)
 event.graph.render(filename="test", format="pdf", cleanup=True)
 ```
 
+## Get started
+
+The example below provides a simple overview.
+Full functionality can be inspected from the functions provided in the `pylhe` module.
+
+```python
+import itertools
+
+# You can use LHE files from scikit-hep-testdata
+from skhep_testdata import data_path
+
+import pylhe
+
+lhe_file = data_path("pylhe-testlhef3.lhe")
+events = pylhe.read_lhe_with_attributes(lhe_file)
+print(f"Number of events: {pylhe.read_num_events(lhe_file)}")
+
+# Get event 1
+event = next(itertools.islice(events, 1, 2))
+
+# A DOT language graph of the event can be inspected as follows
+print(event.graph.source)
+
+# The graph is nicely displayed as SVG in Jupyter notebooks
+event
+
+# To save a DOT graph render the graph to a supported image format
+# (refer to the Graphviz documentation for more)
+event.graph.render(filename="test", format="png", cleanup=True)
+event.graph.render(filename="test", format="pdf", cleanup=True)
+```
+
 ## Citation
 
 The preferred BibTeX entry for citation of `pylhe` is

src/pylhe/__init__.py

@@ -283,9 +283,10 @@ def read_lhe(filepath):
         with _extract_fileobj(filepath) as fileobj:
             for event, element in ET.iterparse(fileobj, events=["end"]):
                 if element.tag == "event":
-                    data = element.text.split("\n")[1:-1]
+                    data = element.text.strip().split("\n")
                     eventdata, particles = data[0], data[1:]
                     eventinfo = LHEEventInfo.fromstring(eventdata)
+                    particles = particles[: int(eventinfo.nparticles)]
                     particle_objs = [LHEParticle.fromstring(p) for p in particles]
                     yield LHEEvent(eventinfo, particle_objs)
     except ET.ParseError as excep:
@@ -303,7 +304,7 @@ def read_lhe_with_attributes(filepath):
             for event, element in ET.iterparse(fileobj, events=["end"]):
                 if element.tag == "event":
                     eventdict = {}
-                    data = element.text.split("\n")[1:-1]
+                    data = element.text.strip().split("\n")
                     eventdata, particles = data[0], data[1:]
                     eventdict["eventinfo"] = LHEEventInfo.fromstring(eventdata)
                     eventdict["particles"] = []

tests/test_lhe_reader.py

@@ -66,5 +66,25 @@ def test_lhe_init(testdata_gzip_file):
 
 
 def test_read_lhe(testdata_gzip_file):
-    assert pylhe.read_lhe(TEST_FILE)
     assert pylhe.read_lhe(testdata_gzip_file)
+
+
+def test_read_lhe_internals():
+    events = pylhe.read_lhe(TEST_FILE)
+
+    assert events
+    for e in events:
+        assert e is not None
+
+
+def test_issue_102():
+    """
+    Test a file containing lines starting with "#aMCatNLO".
+    """
+    test_file = skhep_testdata.data_path("pylhe-testlhef3.lhe")
+
+    assert pylhe.read_num_events(test_file) == 59
+    assert (
+        pylhe.read_lhe(test_file).__sizeof__()
+        == pylhe.read_lhe_with_attributes(test_file).__sizeof__()
+    )