1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__author__ = "G.J.J. van den Burg"
"""Tests"""
import hashlib
import os
import pdfplumber
import shutil
import tempfile
import unittest
from paper2remarkable.providers import (
ACM,
Arxiv,
CiteSeerX,
HTML,
JMLR,
LocalFile,
NBER,
NeurIPS,
OpenReview,
PMLR,
PdfUrl,
PubMed,
SagePub,
Springer,
SemanticScholar,
)
VERBOSE = False
def md5sum(filename):
blocksize = 65536
hasher = hashlib.md5()
with open(filename, "rb") as fid:
buf = fid.read(blocksize)
while len(buf) > 0:
hasher.update(buf)
buf = fid.read(blocksize)
return hasher.hexdigest()
class TestProviders(unittest.TestCase):
@classmethod
def setUpClass(cls):
cls.original_dir = os.getcwd()
def setUp(self):
self.test_dir = tempfile.mkdtemp()
os.chdir(self.test_dir)
def tearDown(self):
os.chdir(self.original_dir)
shutil.rmtree(self.test_dir)
def test_arxiv_1(self):
# check with qpdf
prov = Arxiv(upload=False, verbose=VERBOSE, pdftk_path=None)
url = "https://arxiv.org/abs/1811.11242v1"
exp_filename = "Burg_Nazabal_Sutton_-_Wrangling_Messy_CSV_Files_by_Detecting_Row_and_Type_Patterns_2018.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_arxiv_2(self):
prov = Arxiv(upload=False, verbose=VERBOSE)
url = "http://arxiv.org/abs/arXiv:1908.03213"
exp_filename = "Ecker_et_al_-_Gravitational_Waves_From_Holographic_Neutron_Star_Mergers_2019.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_arxiv_3(self):
prov = Arxiv(upload=False, verbose=VERBOSE)
url = "https://arxiv.org/abs/math/0309285"
exp_filename = "Jackson_et_al_-_An_Algorithm_for_Optimal_Partitioning_of_Data_on_an_Interval_2003.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_arxiv_4(self):
prov = Arxiv(upload=False, verbose=VERBOSE)
url = "https://arxiv.org/pdf/physics/0605197v1.pdf"
exp_filename = (
"Knuth_-_Optimal_Data-Based_Binning_for_Histograms_2006.pdf"
)
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_arxiv_5(self):
prov = Arxiv(upload=False, verbose=VERBOSE, qpdf_path=None)
url = "https://arxiv.org/abs/2002.11523"
exp_filename = "Ponomarev_Oseledets_Cichocki_-_Using_Reinforcement_Learning_in_the_Algorithmic_Trading_Problem_2020.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_pmc(self):
prov = PubMed(upload=False, verbose=VERBOSE)
url = "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3474301/"
exp_filename = (
"Hoogenboom_Manske_-_How_to_Write_a_Scientific_Article_2012.pdf"
)
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_acm_1(self):
prov = ACM(upload=False, verbose=VERBOSE)
url = "https://dl.acm.org/citation.cfm?id=3025626"
exp_filename = "Kery_Horvath_Myers_-_Variolite_Supporting_Exploratory_Programming_by_Data_Scientists_2017.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_acm_2(self):
prov = ACM(upload=False, verbose=VERBOSE)
url = (
"https://dl.acm.org/doi/pdf/10.1145/3219819.3220081?download=true"
)
exp_filename = "Bateni_Esfandiari_Mirrokni_-_Optimal_Distributed_Submodular_Optimization_via_Sketching_2018.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_openreview(self):
prov = OpenReview(upload=False, verbose=VERBOSE)
url = "https://openreview.net/forum?id=S1x4ghC9tQ"
exp_filename = "Gregor_et_al_-_Temporal_Difference_Variational_Auto-Encoder_2018.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_springer_1(self):
prov = Springer(upload=False, verbose=VERBOSE)
url = "https://link.springer.com/article/10.1007/s10618-019-00631-5"
exp_filename = "Mauw_Ramirez-Cruz_Trujillo-Rasua_-_Robust_Active_Attacks_on_Social_Graphs_2019.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_springer_2(self):
prov = Springer(upload=False, verbose=VERBOSE)
url = "https://link.springer.com/content/pdf/10.1007%2F11681878_14.pdf"
exp_filename = "Dwork_et_al_-_Calibrating_Noise_to_Sensitivity_in_Private_Data_Analysis_2006.pdf"
filename = prov.run(url)
self.assertEqual(exp_filename, os.path.basename(filename))
def test_local(self):
local_filename = "test.pdf"
with open(local_filename, "w") as fp:
fp.write(
"%PDF-1.1\n%¥±ë\n\n1 0 obj\n << /Type /Catalog\n /Pages 2 0 R\n >>\nendobj\n\n2 0 obj\n << /Type /Pages\n /Kids [3 0 R]\n /Count 1\n /MediaBox [0 0 300 144]\n >>\nendobj\n\n3 0 obj\n << /Type /Page\n /Parent 2 0 R\n /Resources\n << /Font\n << /F1\n << /Type /Font\n /Subtype /Type1\n /BaseFont /Times-Roman\n >>\n >>\n >>\n /Contents 4 0 R\n >>\nendobj\n\n4 0 obj\n << /Length 55 >>\nstream\n BT\n /F1 18 Tf\n 0 0 Td\n (Hello World) Tj\n ET\nendstream\nendobj\n\nxref\n0 5\n0000000000 65535 f \n0000000018 00000 n \n0000000077 00000 n \n0000000178 00000 n \n0000000457 00000 n \ntrailer\n << /Root 1 0 R\n /Size 5\n >>\nstartxref\n565\n%%EOF"
)
prov = LocalFile(upload=False, verbose=VERBOSE)
filename = prov.run(local_filename)
self.assertEqual("test_.pdf", os.path.basename(filename))
def test_pdfurl_1(self):
prov = PdfUrl(upload=False, verbose=VERBOSE)
url = "http://www.jmlr.org/papers/volume17/14-526/14-526.pdf"
filename = prov.run(url)
self.assertEqual("14-526.pdf", os.path.basename(filename))
def test_pdfurl_2(self):
prov = PdfUrl(upload=False, verbose=VERBOSE)
url = "https://www.manuelrigger.at/preprints/NoREC.pdf"
filename = prov.run(url)
self.assertEqual("NoREC.pdf", os.path.basename(filename))
def test_jmlr_1(self):
prov = JMLR(upload=False, verbose=VERBOSE)
url = "http://www.jmlr.org/papers/volume17/14-526/14-526.pdf"
exp = "Burg_Groenen_-_GenSVM_a_Generalized_Multiclass_Support_Vector_Machine_2016.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_jmlr_2(self):
prov = JMLR(upload=False, verbose=VERBOSE)
url = "http://www.jmlr.org/papers/v10/xu09a.html"
exp = "Xu_Zhang_-_Refinement_of_Reproducing_Kernels_2009.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_pmlr_1(self):
prov = PMLR(upload=False, verbose=VERBOSE)
url = "http://proceedings.mlr.press/v97/behrmann19a.html"
exp = "Behrmann_et_al_-_Invertible_Residual_Networks_2019.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_pmlr_2(self):
prov = PMLR(upload=False, verbose=VERBOSE)
url = "http://proceedings.mlr.press/v15/maaten11b/maaten11b.pdf"
exp = "Maaten_Welling_Saul_-_Hidden-Unit_Conditional_Random_Fields_2011.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_pmlr_3(self):
prov = PMLR(upload=False, verbose=VERBOSE)
url = "http://proceedings.mlr.press/v48/melnyk16.pdf"
exp = "Melnyk_Banerjee_-_Estimating_Structured_Vector_Autoregressive_Models_2016.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_pmlr_4(self):
prov = PMLR(upload=False, verbose=VERBOSE)
url = "http://proceedings.mlr.press/v48/zhangf16.html"
exp = "Zhang_Paisley_-_Markov_Latent_Feature_Models_2016.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_nber_1(self):
prov = NBER(upload=False, verbose=VERBOSE)
url = "https://www.nber.org/papers/w26752"
exp = "Bhattacharya_Packalen_-_Stagnation_and_Scientific_Incentives_2020.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_nber_2(self):
prov = NBER(upload=False, verbose=VERBOSE)
url = "https://www.nber.org/papers/w19152.pdf"
exp = "Herbst_Schorfheide_-_Sequential_Monte_Carlo_Sampling_for_DSGE_Models_2013.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_neurips_1(self):
prov = NeurIPS(upload=False, verbose=VERBOSE)
url = "https://papers.nips.cc/paper/325-leaning-by-combining-memorization-and-gradient-descent.pdf"
exp = "Platt_-_Leaning_by_Combining_Memorization_and_Gradient_Descent_1991.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_neurips_2(self):
prov = NeurIPS(upload=False, verbose=VERBOSE)
url = "https://papers.nips.cc/paper/7796-middle-out-decoding"
exp = "Mehri_Sigal_-_Middle-Out_Decoding_2018.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_citeseerx_1(self):
prov = CiteSeerX(upload=False, verbose=VERBOSE)
url = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.6548"
exp = "Aaronson_-_Is_P_Versus_NP_Formally_Independent_2003.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_citeseerx_2(self):
prov = CiteSeerX(upload=False, verbose=VERBOSE)
url = "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.123.7607&rep=rep1&type=pdf"
exp = "Kirkpatrick_Gelatt_Vecchi_-_Optimization_by_Simulated_Annealing_1983.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_html_1(self):
prov = HTML(upload=False, verbose=VERBOSE)
url = "https://hbr.org/2019/11/getting-your-team-to-do-more-than-meet-deadlines"
exp = "Getting_Your_Team_to_Do_More_Than_Meet_Deadlines.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_html_2(self):
prov = HTML(upload=False, verbose=VERBOSE)
url = "https://www.nature.com/articles/d41586-020-00176-4"
exp = "Isaac_Asimov_Centenary_of_the_Great_Explainer.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_html_3(self):
prov = HTML(upload=False, verbose=VERBOSE)
url = "https://conclave-team.github.io/conclave-site/"
exp = "Conclave_Case_Study_-_A_Private_and_Secure_Real-Time_Collaborative_Text_Editor.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
# this is a proxy test to check that all images are included
self.assertEqual(32, len(pdfplumber.open(filename).pages))
def test_html_4(self):
prov = HTML(upload=False, verbose=VERBOSE)
url = "https://sirupsen.com/2019/"
filename = prov.run(url)
# this is a proxy test to check that all images are included
self.assertEqual(4, len(pdfplumber.open(filename).pages))
def test_semantic_scholar_1(self):
prov = SemanticScholar(upload=False, verbose=VERBOSE)
url = "https://pdfs.semanticscholar.org/1b01/dea77e9cbf049b4ee8b68dc4d43529d06299.pdf"
exp = "Dong_et_al_-_TableSense_Spreadsheet_Table_Detection_With_Convolutional_Neural_Networks_2019.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_semantic_scholar_2(self):
prov = SemanticScholar(upload=False, verbose=VERBOSE)
url = "https://www.semanticscholar.org/paper/Fast-Meta-Learning-for-Adaptive-Hierarchical-Design-Burg-Hero/90759dc4ab0ce8d3564044ef92a91080a4f3e55f"
exp = "Burg_Hero_-_Fast_Meta-Learning_for_Adaptive_Hierarchical_Classifier_Design_2017.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_sagepub_1(self):
prov = SagePub(upload=False, verbose=VERBOSE)
url = "https://journals.sagepub.com/doi/full/10.1177/0306312714535679"
exp = "Rekdal_-_Academic_Urban_Legends_2014.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
def test_sagepub_2(self):
prov = SagePub(upload=False, verbose=VERBOSE)
url = "https://journals.sagepub.com/doi/pdf/10.1177/1352458517694432"
exp = "Kobelt_et_al_-_New_Insights_Into_the_Burden_and_Costs_of_Multiple_Sclerosis_in_Europe_2017.pdf"
filename = prov.run(url)
self.assertEqual(exp, os.path.basename(filename))
if __name__ == "__main__":
unittest.main()
|
