GitLab: Tarball Version Test (#2296)

* GitLab: Tarball Version Test

Upload a test demonstrating #2290

* Add GitLab parsing

lib/spack/spack/test/url_parse.py

@@ -154,6 +154,20 @@ def test_version_regular(self):
             'foo-bar', '1.21',
             'http://example.com/foo_bar-1.21.tar.gz')
 
+    def test_version_gitlab(self):
+        self.check(
+             'vtk', '7.0.0',
+             'https://gitlab.kitware.com/vtk/vtk/repository/'
+             'archive.tar.bz2?ref=v7.0.0')
+        self.check(
+             'icet', '1.2.3',
+             'https://gitlab.kitware.com/icet/icet/repository/'
+             'archive.tar.gz?ref=IceT-1.2.3')
+        self.check(
+             'foo', '42.1337',
+             'http://example.com/org/foo/repository/'
+             'archive.zip?ref=42.1337bar')
+
     def test_version_github(self):
         self.check(
             'yajl', '1.0.5',

lib/spack/spack/url.py

@@ -106,19 +106,22 @@ def split_url_extension(path):
 
           1. https://github.com/losalamos/CLAMR/blob/packages/PowerParser_v2.0.7.tgz?raw=true
           2. http://www.apache.org/dyn/closer.cgi?path=/cassandra/1.2.0/apache-cassandra-1.2.0-rc2-bin.tar.gz
+          3. https://gitlab.kitware.com/vtk/vtk/repository/archive.tar.bz2?ref=v7.0.0
 
        In (1), the query string needs to be stripped to get at the
-       extension, but in (2), the filename is IN a single final query
+       extension, but in (2) & (3), the filename is IN a single final query
        argument.
 
        This strips the URL into three pieces: prefix, ext, and suffix.
        The suffix contains anything that was stripped off the URL to
        get at the file extension.  In (1), it will be '?raw=true', but
-       in (2), it will be empty. e.g.:
+       in (2), it will be empty. In (3) the suffix is a parameter that follows
+       after the file extension, e.g.:
 
            1. ('https://github.com/losalamos/CLAMR/blob/packages/PowerParser_v2.0.7', '.tgz', '?raw=true')
            2. ('http://www.apache.org/dyn/closer.cgi?path=/cassandra/1.2.0/apache-cassandra-1.2.0-rc2-bin',
                '.tar.gz', None)
+           3. ('https://gitlab.kitware.com/vtk/vtk/repository/archive', '.tar.bz2', '?ref=v7.0.0')
     """
     prefix, ext, suffix = path, '', ''
 
@@ -203,6 +206,15 @@ def parse_version_offset(path, debug=False):
         # https://github.com/hpc/mpileaks/releases/download/v1.0/mpileaks-1.0.tar.gz
         (r'github.com/[^/]+/[^/]+/releases/download/v?([^/]+)/.*$', path),
 
+        # GitLab syntax:
+        #   {baseUrl}{/organization}{/projectName}/repository/archive.{fileEnding}?ref={gitTag}
+        #   as with github releases, we hope a version can be found in the
+        #   git tag
+        # Search dotted versions:
+        #   e.g., https://gitlab.kitware.com/vtk/vtk/repository/archive.tar.bz2?ref=v7.0.0
+        #   e.g., https://example.com/org/repo/repository/archive.tar.bz2?ref=SomePrefix-2.1.1
+        (r'\?ref=(?:.*-|v)*((\d+\.)+\d+).*$', suffix),
+
         # e.g. boost_1_39_0
         (r'((\d+_)+\d+)$', stem),
 
@@ -291,6 +303,7 @@ def parse_name_offset(path, v=None, debug=False):
         (r'/([^/]+)/(tarball|zipball)/', path),
         (r'/([^/]+)[_.-](bin|dist|stable|src|sources)[_.-]%s' % v, path),
         (r'github.com/[^/]+/([^/]+)/archive', path),
+        (r'[^/]+/([^/]+)/repository/archive', path),  # gitlab
 
         (r'([^/]+)[_.-]v?%s' % v, stem),   # prefer the stem
         (r'([^/]+)%s' % v, stem),