summary refs log tree commit diff stats
diff options
context:
space:
mode:
authorChristian Krinitsin <mail@krinitsin.com>2025-06-03 12:02:49 +0000
committerChristian Krinitsin <mail@krinitsin.com>2025-06-03 12:02:49 +0000
commita5b92ee80186380eba06febb8fbf3059136eaa63 (patch)
treeead23f5926157e284679da846489a430e61881f2
parente5317707f115fc8d6423e1d850c6b52d1f9edbb0 (diff)
downloadqemu-analysis-a5b92ee80186380eba06febb8fbf3059136eaa63.tar.gz
qemu-analysis-a5b92ee80186380eba06febb8fbf3059136eaa63.zip
add option to parse all bugs
-rwxr-xr-xclassification/main.py13
1 files changed, 12 insertions, 1 deletions
diff --git a/classification/main.py b/classification/main.py
index 3f16a2818..ea4724759 100755
--- a/classification/main.py
+++ b/classification/main.py
@@ -1,5 +1,10 @@
 from transformers import pipeline
 from os import path, listdir, makedirs
+from argparse import ArgumentParser
+
+parser = ArgumentParser(prog='main.py')
+parser.add_argument('-m', '--minimal', action='store_true')
+args = parser.parse_args()
 
 positive_categories = ['semantic', 'mistranslation', 'instruction', 'assembly'] # to add: register
 negative_categories = ['other', 'boot', 'network', 'KVM', 'vnc', 'graphic', 'device', 'socket'] # to add: performance
@@ -30,7 +35,13 @@ def main():
     classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 
     bugs = list_files_recursive("../results/scraper/mailinglist")
-    bugs = bugs + list_files_recursive("./semantic_issues")
+    if args.minimal:
+        bugs = bugs + list_files_recursive("./semantic_issues")
+    else:
+        bugs = bugs + list_files_recursive("../results/scraper/launchpad")
+        bugs = bugs + list_files_recursive("../results/scraper/gitlab/issues_text")
+
+    print(f"{len(bugs)} number of bugs will be processed")
     for bug in bugs:
         print(f"Processing {bug}")
         with open(bug, "r") as file: