rabbit_mq correct pattern
Browse files
__pycache__/inference_svm_model.cpython-310.pyc
CHANGED
Binary files a/__pycache__/inference_svm_model.cpython-310.pyc and b/__pycache__/inference_svm_model.cpython-310.pyc differ
|
|
__pycache__/mineru_single.cpython-310.pyc
CHANGED
Binary files a/__pycache__/mineru_single.cpython-310.pyc and b/__pycache__/mineru_single.cpython-310.pyc differ
|
|
__pycache__/topic_extr.cpython-310.pyc
CHANGED
Binary files a/__pycache__/topic_extr.cpython-310.pyc and b/__pycache__/topic_extr.cpython-310.pyc differ
|
|
__pycache__/worker.cpython-310.pyc
CHANGED
Binary files a/__pycache__/worker.cpython-310.pyc and b/__pycache__/worker.cpython-310.pyc differ
|
|
output/sample_spec_output.md
CHANGED
@@ -1,63 +1,29 @@
|
|
1 |
-
# Paper 1 and Paper 2: Pure Mathematics
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-

|
22 |
-
|
23 |
-

|
24 |
-
|
25 |
-

|
26 |
-
|
27 |
-

|
28 |
-
|
29 |
-

|
30 |
-
|
31 |
-

|
32 |
-
|
33 |
-

|
34 |
-
|
35 |
-

|
36 |
-
|
37 |
-

|
38 |
-
|
39 |
-

|
40 |
-
|
41 |
# Paper 3: Statistics and Mechanics
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-

|
52 |
-
|
53 |
-

|
54 |
-
|
55 |
-

|
56 |
-
|
57 |
-

|
58 |
-
|
59 |
-

|
60 |
-
|
61 |
-

|
62 |
-
|
63 |
-

|
|
|
1 |
+
# Paper 1 and Paper 2: Pure Mathematics
|
2 |
+

|
3 |
+

|
4 |
+

|
5 |
+

|
6 |
+

|
7 |
+

|
8 |
+

|
9 |
+

|
10 |
+

|
11 |
+

|
12 |
+

|
13 |
+

|
14 |
+

|
15 |
+

|
16 |
+

|
17 |
+

|
18 |
+

|
19 |
+

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
# Paper 3: Statistics and Mechanics
|
21 |
+

|
22 |
+

|
23 |
+

|
24 |
+

|
25 |
+

|
26 |
+

|
27 |
+

|
28 |
+

|
29 |
+

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
topic_extr.py
CHANGED
@@ -112,13 +112,10 @@ class TopicExtractionProcessor:
|
|
112 |
try:
|
113 |
key = input_file.get("key", "")
|
114 |
url = input_file.get("url", "")
|
115 |
-
|
116 |
-
|
117 |
-
if not url or not page_field:
|
118 |
-
raise ValueError("Missing required 'url' or 'page' in input file")
|
119 |
|
120 |
-
|
121 |
-
|
122 |
|
123 |
if url.startswith(("http://", "https://")):
|
124 |
response = requests.get(url)
|
@@ -127,8 +124,12 @@ class TopicExtractionProcessor:
|
|
127 |
else:
|
128 |
with open(url, "rb") as f:
|
129 |
pdf_bytes = f.read()
|
|
|
|
|
|
|
|
|
|
|
130 |
|
131 |
-
subset_pdf = self.create_subset_pdf(pdf_bytes, page_indices)
|
132 |
|
133 |
dataset = PymuDocDataset(subset_pdf)
|
134 |
inference = doc_analyze(
|
|
|
112 |
try:
|
113 |
key = input_file.get("key", "")
|
114 |
url = input_file.get("url", "")
|
115 |
+
pages = input_file.get("page", [])
|
|
|
|
|
|
|
116 |
|
117 |
+
if not url or not pages:
|
118 |
+
raise ValueError("Missing required 'url' or 'page' in input file")
|
119 |
|
120 |
if url.startswith(("http://", "https://")):
|
121 |
response = requests.get(url)
|
|
|
124 |
else:
|
125 |
with open(url, "rb") as f:
|
126 |
pdf_bytes = f.read()
|
127 |
+
|
128 |
+
pages = self.parse_page_range(pages)
|
129 |
+
logger.info("Processing %s with pages %s", key, pages)
|
130 |
+
|
131 |
+
subset_pdf = self.create_subset_pdf(pdf_bytes, pages)
|
132 |
|
|
|
133 |
|
134 |
dataset = PymuDocDataset(subset_pdf)
|
135 |
inference = doc_analyze(
|
worker.py
CHANGED
@@ -129,6 +129,7 @@ class RabbitMQWorker:
|
|
129 |
elif pattern == "topic_extraction":
|
130 |
data = body_dict.get("data")
|
131 |
input_files = data.get("input_files")
|
|
|
132 |
logger.info("[Worker %s] Found %d file(s) for topic extraction.", thread_id, len(input_files))
|
133 |
|
134 |
for file in input_files:
|
|
|
129 |
elif pattern == "topic_extraction":
|
130 |
data = body_dict.get("data")
|
131 |
input_files = data.get("input_files")
|
132 |
+
# contexts = []
|
133 |
logger.info("[Worker %s] Found %d file(s) for topic extraction.", thread_id, len(input_files))
|
134 |
|
135 |
for file in input_files:
|