From ee390387df77fcc24bf4beeb439d240a653763aa Mon Sep 17 00:00:00 2001
From: Martijn Vermaat <martijn@vermaat.name>
Date: Sun, 31 May 2015 17:34:45 +0200
Subject: [PATCH] Configurable maximum input length for description extractor
Adds a `EXTRACTOR_MAX_INPUT_LENGTH` configuration setting, defaulting
to 50 Kbp.
---
mutalyzer/config/default_settings.py | 3 ++
mutalyzer/services/rpc.py | 7 +++--
.../templates/description-extractor.html | 6 ++--
mutalyzer/website/views.py | 10 +++++--
tests/test_services_json.py | 19 ++++++++++++
tests/test_website.py | 29 +++++++++++++++++++
6 files changed, 65 insertions(+), 9 deletions(-)
diff --git a/mutalyzer/config/default_settings.py b/mutalyzer/config/default_settings.py
index 00dc9b2e..c01d47a5 100644
--- a/mutalyzer/config/default_settings.py
+++ b/mutalyzer/config/default_settings.py
@@ -25,6 +25,9 @@ CACHE_DIR = '/tmp'
# Maximum size for uploaded and downloaded files (in bytes).
MAX_FILE_SIZE = 10 * 1048576 # 10 MB
+# Maximum sequence length for description extractor (in bases).
+EXTRACTOR_MAX_INPUT_LENGTH = 50 * 1000 # 50 Kbp
+
# The WSGI application runs behind a reverse proxy (e.g., nginx using
# proxy_pass). This needs to be set if the application is mapped to a URL
# other than / or a different HTTP scheme is used by the reverse proxy.
diff --git a/mutalyzer/services/rpc.py b/mutalyzer/services/rpc.py
index 6fce0a8f..d0315fd1 100644
--- a/mutalyzer/services/rpc.py
+++ b/mutalyzer/services/rpc.py
@@ -1242,10 +1242,11 @@ class MutalyzerService(ServiceBase):
stats.increment_counter('description-extractor/webservice')
- if not settings.TESTING and (len(reference) > 1000 or
- len(observed) > 1000):
+ if (len(reference) > settings.EXTRACTOR_MAX_INPUT_LENGTH or
+ len(observed) > settings.EXTRACTOR_MAX_INPUT_LENGTH):
raise Fault('EMAXSIZE',
- 'Input sequences are restricted to 1000bp.')
+ 'Input sequences are restricted to {} bp.'
+ .format(settings.EXTRACTOR_MAX_INPUT_LENGTH))
allele = extractor.describe_dna(reference, observed)
diff --git a/mutalyzer/website/templates/description-extractor.html b/mutalyzer/website/templates/description-extractor.html
index ec096feb..631de1d4 100644
--- a/mutalyzer/website/templates/description-extractor.html
+++ b/mutalyzer/website/templates/description-extractor.html
@@ -7,7 +7,7 @@
<p class="alert alert-warning">
Please note that this is an experimental service and we are currently limiting
-input sequences to 1000bp.
+input sequences to {{ '{:,}'.format(extractor_max_input_length) }} bp.
</p>
<p>
@@ -88,7 +88,7 @@ Please supply a reference sequence and an observed sequence.
<div class="form-group">
<label for="reference_accession_number">Reference accession number</label>
<input type="text" name="reference_accession_number" id="reference_accession_number" value="{{ reference_accession_number }}" class="form-control form-pre" placeholder="Reference accession number">
- <p>Example: <code class="example-input" data-for="reference_accession_number">NM_198697.1</code></p>
+ <p>Example: <code class="example-input" data-for="reference_accession_number">NM_004006.1</code></p>
</div>
</div>
</div>
@@ -143,7 +143,7 @@ Please supply a reference sequence and an observed sequence.
<div class="form-group">
<label for="sample_accession_number">Sample accession number</label>
<input type="text" name="sample_accession_number" id="sample_accession_number" value="{{ sample_accession_number }}" class="form-control form-pre" placeholder="Sample accession number">
- <p>Example: <code class="example-input" data-for="sample_accession_number">NM_198697.2</code></p>
+ <p>Example: <code class="example-input" data-for="sample_accession_number">NM_004006.2</code></p>
</div>
</div>
</div>
diff --git a/mutalyzer/website/views.py b/mutalyzer/website/views.py
index 830781b6..bc0a339e 100644
--- a/mutalyzer/website/views.py
+++ b/mutalyzer/website/views.py
@@ -682,7 +682,8 @@ def description_extractor():
"""
Description extractor loader form.
"""
- return render_template('description-extractor.html')
+ return render_template('description-extractor.html',
+ extractor_max_input_length=settings.EXTRACTOR_MAX_INPUT_LENGTH)
@website.route('/description-extractor', methods=['POST'])
@@ -788,9 +789,11 @@ def description_extractor_submit():
raw_vars = None
if r and s:
- if not settings.TESTING and (len(r) > 1000 or len(s) > 1000):
+ if (len(r) > settings.EXTRACTOR_MAX_INPUT_LENGTH or
+ len(s) > settings.EXTRACTOR_MAX_INPUT_LENGTH):
output.addMessage(__file__, 3, 'EMAXSIZE',
- 'Input sequences are restricted to 1000bp.')
+ 'Input sequences are restricted to {:,} bp.'
+ .format(settings.EXTRACTOR_MAX_INPUT_LENGTH))
else:
raw_vars = extractor.describe_dna(r, s)
@@ -801,6 +804,7 @@ def description_extractor_submit():
'Finished Description Extract request')
return render_template('description-extractor.html',
+ extractor_max_input_length=settings.EXTRACTOR_MAX_INPUT_LENGTH,
reference_sequence=reference_sequence or '',
sample_sequence=sample_sequence or '',
reference_accession_number=reference_accession_number or '',
diff --git a/tests/test_services_json.py b/tests/test_services_json.py
index 843ca8ea..259fad6b 100644
--- a/tests/test_services_json.py
+++ b/tests/test_services_json.py
@@ -12,6 +12,7 @@ from spyne.server.null import NullServer
import mutalyzer
from mutalyzer import announce
+from mutalyzer.config import settings
from mutalyzer import Scheduler
from mutalyzer.services.json import application
@@ -298,3 +299,21 @@ class TestServicesJson(MutalyzerTest):
'sample_start_offset': 0,
'sample_end_offset': 0}],
'description': '[5_6insTT;17del;26A>C;35dup]'}
+
+ def test_description_extract_ref_too_long(self):
+ """
+ Test output of descriptionExtract with too long reference sequence.
+ """
+ with pytest.raises(Fault):
+ self._call('descriptionExtract',
+ 'A' * (settings.EXTRACTOR_MAX_INPUT_LENGTH + 1),
+ 'A')
+
+ def test_description_extract_sample_too_long(self):
+ """
+ Test output of descriptionExtract with too long sample sequence.
+ """
+ with pytest.raises(Fault):
+ self._call('descriptionExtract',
+ 'A' * (settings.EXTRACTOR_MAX_INPUT_LENGTH),
+ 'A' * (settings.EXTRACTOR_MAX_INPUT_LENGTH + 1))
diff --git a/tests/test_website.py b/tests/test_website.py
index bb3ff5af..3392d1fa 100644
--- a/tests/test_website.py
+++ b/tests/test_website.py
@@ -17,6 +17,7 @@ from Bio import Entrez
import lxml.html
from mutalyzer import announce, Scheduler
+from mutalyzer.config import settings
from mutalyzer.db import models
from mutalyzer.website import create_app
@@ -178,6 +179,34 @@ class TestWebsite(MutalyzerTest):
'sample_file': (open(path), 'extractor_input.txt')})
assert '[5_6insTT;17del;26A>C;35dup]' in r.data
+ def test_description_extractor_ref_too_long(self):
+ """
+ Submit a reference sequence exceeding the maximum length to the variant
+ description extractor.
+ """
+ r = self.app.post('/description-extractor', data={
+ 'reference_method': 'raw_method',
+ 'sample_method': 'raw_method',
+ 'reference_sequence': 'A' * (settings.EXTRACTOR_MAX_INPUT_LENGTH + 1),
+ 'sample_sequence': 'A'})
+ assert '2_{}del'.format(settings.EXTRACTOR_MAX_INPUT_LENGTH + 1) not in r.data
+ assert 'Input sequences are restricted to ' in r.data
+ assert '1 Error, 0 Warnings.' in r.data
+
+ def test_description_extractor_sample_too_long(self):
+ """
+ Submit a sample sequence exceeding the maximum length to the variant
+ description extractor.
+ """
+ r = self.app.post('/description-extractor', data={
+ 'reference_method': 'raw_method',
+ 'sample_method': 'raw_method',
+ 'reference_sequence': 'A' * (settings.EXTRACTOR_MAX_INPUT_LENGTH),
+ 'sample_sequence': 'A' * (settings.EXTRACTOR_MAX_INPUT_LENGTH + 1)})
+ assert '{}dup'.format(settings.EXTRACTOR_MAX_INPUT_LENGTH) not in r.data
+ assert 'Input sequences are restricted to ' in r.data
+ assert '1 Error, 0 Warnings.' in r.data
+
def test_checksyntax_valid(self):
"""
Submit the check syntax form with a valid variant.
--
GitLab