From 7cc0b6e320e45b9ce442425a04ac4708fb3df077 Mon Sep 17 00:00:00 2001 From: Gertjan van den Burg Date: Mon, 11 May 2020 17:32:21 +0100 Subject: Allow underscore in urls --- paper2remarkable/utils.py | 2 +- tests/test_ui.py | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/paper2remarkable/utils.py b/paper2remarkable/utils.py index 97ff713..c2917d5 100644 --- a/paper2remarkable/utils.py +++ b/paper2remarkable/utils.py @@ -163,7 +163,7 @@ def upload_to_remarkable(filepath, remarkable_dir="/", rmapi_path="rmapi"): def is_url(string): # pattern adapted from CleverCSV - pattern = "((https?|ftp):\/\/(?!\-))?(((([\p{L}\p{N}]*\-?[\p{L}\p{N}]+)+\.)+([a-z]{2,}|local)(\.[a-z]{2,3})?)|localhost|(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(\:\d{1,5})?))(\/[\p{L}\p{N}_\/()~?=&%\-\#\.:+]*)?(\.[a-z]+)?" + pattern = "((https?|ftp):\/\/(?!\-))?(((([\p{L}\p{N}]*[\-\_]?[\p{L}\p{N}]+)+\.)+([a-z]{2,}|local)(\.[a-z]{2,3})?)|localhost|(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(\:\d{1,5})?))(\/[\p{L}\p{N}_\/()~?=&%\-\#\.:+]*)?(\.[a-z]+)?" string = string.strip(" ") match = regex.fullmatch(pattern, string) return match is not None diff --git a/tests/test_ui.py b/tests/test_ui.py index 11ed87a..7ae1e79 100644 --- a/tests/test_ui.py +++ b/tests/test_ui.py @@ -99,6 +99,11 @@ class TestUI(unittest.TestCase): "https://gertjanvandenburg.com/papers/VandenBurg_Nazabal_Sutton_-_Wrangling_Messy_CSV_Files_by_Detecting_Row_and_Type_Patterns_2019.pdf", "https://gertjanvandenburg.com/papers/VandenBurg_Nazabal_Sutton_-_Wrangling_Messy_CSV_Files_by_Detecting_Row_and_Type_Patterns_2019.pdf", ), + ( + PdfUrl, + "https://confcats_isif.s3.amazonaws.com/web-files/journals/entries/Nonlinear%20Kalman%20Filters.pdf", + "https://confcats_isif.s3.amazonaws.com/web-files/journals/entries/Nonlinear%20Kalman%20Filters.pdf", + ), ( JMLR, "http://www.jmlr.org/papers/volume17/14-526/14-526.pdf", -- cgit v1.2.3