Canonicalize gurl

.gitignore

@@ -7,4 +7,11 @@
 /tmp
 /MANIFEST
 /urlparse4/*.html
-/dist
+/dist
+
+# Unit test / coverage reports
+.coverage
+.tox
+nosetests.xml
+htmlcov
+.pytest_cache

.travis.yml

@@ -0,0 +1,17 @@
+language: python
+sudo: false
+branches:
+  only:
+    - master
+    - /^\d\.\d+$/
+    - /^\d\.\d+\.\d+(rc\d+|\.dev\d+)?$/
+matrix:
+  include:
+    - python: 3.5
+      env: TOXENV=py35
+    - python: 3.6
+      env: TOXENV=py36
+install:
+    - pip install -U pip tox
+script:
+    - tox

benchmarks/performance_test.py

@@ -0,0 +1,69 @@
+from urlparse4 import urlsplit, urljoin, urlparse
+from timeit import default_timer as timer
+
+import argparse
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Measure the time of urlsplit and urljoin')
+    parser.add_argument('--encode', action='store_true',
+                    help='encode the urls (default: False)')
+    args = parser.parse_args()
+
+    encode = args.encode
+
+    urlparse_time = 0
+
+    for i in range(5):
+        with open('urls/chromiumUrls.txt') as f:
+            for url in f:
+                if encode:
+                    url = url.encode()
+
+                start = timer()
+                a = urlparse(url)
+                end = timer()
+
+                urlparse_time += end - start
+
+    print("the urlparse time is", urlparse_time / 5, "seconds")
+
+    urlsplit_time = 0
+
+    for i in range(5):
+        with open('urls/chromiumUrls.txt') as f:
+            for url in f:
+                if encode:
+                    url = url.encode()
+
+                start = timer()
+                a = urlsplit(url)
+                end = timer()
+
+                urlsplit_time += end - start
+
+    print("the urlsplit time is", urlsplit_time / 5, "seconds")
+
+
+    urljoin_time = 0
+
+    for i in range(5):
+        with open('urls/chromiumUrls.txt') as f:
+            for url in f:
+                partial_url = "/asd"
+
+                if encode:
+                    url = url.encode()
+                    partial_url = partial_url.encode()
+
+                start = timer()
+                a = urljoin(url, partial_url)
+                end = timer()
+
+                urljoin_time += end - start
+
+    print("the urljoin time is", urljoin_time / 5, "seconds")
+
+
+if __name__ == "__main__":
+    main()

benchmarks/urls.py

@@ -27,7 +27,7 @@
 
 URLS = []
 for fp in os.listdir("tests/urls/"):
-    with open("tests/urls/%s" % fp) as f:
+    with open("urls/%s" % fp) as f:
         URLS += f.readlines()
 
 data = []