summaryrefslogtreecommitdiff
path: root/monkey
diff options
context:
space:
mode:
authorTimotej Lazar <timotej.lazar@araneo.org>2015-02-07 19:47:57 +0100
committerAleš Smodiš <aless@guru.si>2015-08-11 14:26:01 +0200
commit1c1b8f683ee2025497e2733eb0d8bc1e54035487 (patch)
tree0ccb287c65ae57a8049a5a3c51b443085d7e74d3 /monkey
parent4838e37e26c3fb72ad509d7aef7f307cc7ae3ef2 (diff)
Remove all trailing punctuation from lines
Remove trailing sequences of COMMAs and PERIODs when extracting edits from a trace. This is because subgoal order is rarely important in Prolog, and we don't care if the edit happened on the last line or not. This means that we treat for example "conc(A,B)," → "conc(A,B,C)." the same as "conc(A,B)" → "conc(A,B,C)".
Diffstat (limited to 'monkey')
-rw-r--r--monkey/edits.py12
1 files changed, 7 insertions, 5 deletions
diff --git a/monkey/edits.py b/monkey/edits.py
index ad595b6..a920bf5 100644
--- a/monkey/edits.py
+++ b/monkey/edits.py
@@ -146,12 +146,14 @@ def get_paths(root, path=None, done=None):
# edits. Return a dictionary of edits and their frequencies, and also
# submissions and queries in [traces].
def get_edits_from_traces(traces):
- # Helper function to remove trailing punctuation from lines. This is a
- # rather ugly performance-boosting hack.
+ # Helper function to remove trailing punctuation from lines.
def remove_punct(line):
- if line and line[-1].type in ('COMMA', 'PERIOD', 'SEMI', 'FROM'):
- return line[:-1]
- return line
+ i = len(line)
+ while i > 0:
+ if line[i-1].type not in ('COMMA', 'PERIOD', 'SEMI'):
+ break
+ i -= 1
+ return line[:i]
# Return values: counts for observed edits, lines, submissions and queries.
edits = collections.Counter()