Add basetag property and helper functions

Signed-off-by: Tim van Katwijk <timvankatwijk@hotmail.com>

Author: tim-vk

dockerfile_parse/parser.py

@@ -401,7 +401,7 @@ def parent_images(self, parents):
             lines[instr['startline']:instr['endline']+1] = [instr['content']]
 
         self.lines = lines
-
+    
     @property
     def is_multistage(self):
         return len(self.parent_images) > 1
@@ -428,6 +428,21 @@ def baseimage(self, new_image):
             raise RuntimeError('No stage defined to set base image on')
         images[-1] = new_image
         self.parent_images = images
+    
+    @property
+    def basetag(self):
+        """
+        :return: tag of base image, i.e. tag of base image
+        """
+        _, tag = tag_from(self.baseimage)
+        return tag
+    
+    @basetag.setter
+    def basetag(self, new_tag):
+        """
+        only change the tag of the final stage FROM instruction
+        """
+        self.baseimage = tag_to(self.baseimage, new_tag)
 
     @property
     def cmd(self):
@@ -882,7 +897,42 @@ def image_from(from_value):
     match = re.match(regex, from_value)
     return match.group('image', 'name') if match else (None, None)
 
-
+def tag_from(from_value):
+    """
+    :param from_value: string like "registry:port/image:tag AS name"
+    :return: tuple of the image and tag e.g. ("image", "tag")
+    """
+    
+    image, _ = image_from(from_value)
+    bare, _, tag = image.rpartition(":") if image and ":" in image else (None, None, None)
+    
+    # check if a tag was actually present
+    if not valid_tag(tag) or not bare:
+        return (image, None)
+        
+    return (bare, tag)
+
+def valid_tag(tag):
+    """
+    :param tag to be checked for validity
+    :return: true or false
+    """
+    regex = re.compile(r"""(?x)            # readable, case-insensitive regex
+        ^(?P<tag>[a-zA-Z0-9\_][a-zA-Z0-9\.\_\-]*)$  # valid tag format (alphanumeric characters, numbers . _ and - (. and - not leading))
+        """)
+    match = re.match(regex, tag) if tag else None
+    return True if match and match.group('tag') and len(match.group('tag')) < 128 else False
+    
+def tag_to(image, new_tag):
+    """
+    :param image: string like "image:tag" or "image"
+    :param tag: string like "latest"
+    :return: string like "image:new_tag" or "image" if no tag was given
+    """
+    
+    bare, _ = tag_from(image)
+    return ":".join(filter(None, [bare.strip() if bare else None, new_tag.strip() if new_tag else None]))
+    
 def _endline(line):
     """
     Make sure the line ends with a single newline.

tests/test_parser.py

@@ -20,6 +20,9 @@
 
 from dockerfile_parse import DockerfileParser
 from dockerfile_parse.parser import image_from
+from dockerfile_parse.parser import tag_from
+from dockerfile_parse.parser import tag_to
+from dockerfile_parse.parser import valid_tag
 from dockerfile_parse.constants import COMMENT_INSTRUCTION
 from dockerfile_parse.util import b2u, u2b, Context
 from tests.fixtures import dfparser, instruction
@@ -312,11 +315,22 @@ def test_get_baseimg_from_df(self, dfparser):
                           "LABEL a b\n"]
         assert dfparser.baseimage == 'fedora:latest'
 
+    def test_get_basetag_from_df(self,dfparser):
+        dfparser.lines = ["From fedora:latest\n",
+                          "LABEL a b\n"]
+        assert dfparser.basetag == 'latest'
+        
     def test_get_baseimg_from_arg(self, dfparser):
         dfparser.lines = ["ARG BASE=fedora:latest\n",
                           "FROM $BASE\n",
                           "LABEL a b\n"]
         assert dfparser.baseimage == 'fedora:latest'
+        
+    def test_get_basetag_from_arg(self, dfparser):
+        dfparser.lines = ["ARG BASE=fedora:latest\n",
+                          "FROM $BASE\n",
+                          "LABEL a b\n"]
+        assert dfparser.basetag == 'latest'
 
     def test_get_baseimg_from_build_arg(self, tmpdir):
         tmpdir_path = str(tmpdir.realpath())
@@ -328,6 +342,16 @@ def test_get_baseimg_from_build_arg(self, tmpdir):
         assert dfp.baseimage == 'fedora:latest'
         assert not dfp.args
 
+    def test_get_basetag_from_build_arg(self, tmpdir):
+        tmpdir_path = str(tmpdir.realpath())
+        b_args = {"BASE": "fedora:latest"}
+        dfp = DockerfileParser(tmpdir_path, env_replace=True, build_args=b_args)
+        dfp.lines = ["ARG BASE=centos:latest\n",
+                     "FROM $BASE\n",
+                     "LABEL a b\n"]
+        assert dfp.basetag == 'latest'
+        assert not dfp.args
+        
     def test_set_no_baseimage(self, dfparser):
         dfparser.lines = []
         with pytest.raises(RuntimeError):
@@ -468,6 +492,114 @@ def test_image_from(self, from_value, expect):
         result = image_from(from_value)
         assert result == expect
 
+    @pytest.mark.parametrize(('from_value', 'expect'), [
+        (
+            "",
+            (None, None),
+        ),
+        (
+            "    ",
+            (None, None),
+        ), (
+            "   foo",
+            ('foo', None),
+        ), (
+            "foo:bar as baz   ",
+            ('foo', 'bar'),
+        ), (
+            "foo as baz",
+            ('foo', None),
+        ), (
+            "foo and some other junk",  # we won't judge
+            ('foo', None),
+        ), (
+            "registry.example.com:5000/foo/bar",
+            ('registry.example.com:5000/foo/bar', None),
+        ), (
+            "registry.example.com:5000/foo/bar:baz",
+            ('registry.example.com:5000/foo/bar', "baz"),
+        ), (
+            "localhost:5000/foo/bar:baz",
+            ('localhost:5000/foo/bar', "baz"),
+        )
+    ])
+    def test_tag_from(self, from_value, expect):
+        result = tag_from(from_value)
+        assert result == expect
+        
+    @pytest.mark.parametrize(('from_image', 'from_tag', 'expect'), [
+        (
+            "    ",
+            " ",
+            "",
+        ),(
+            "foo",
+            None,
+            'foo',
+        ), (
+            "foo",
+            "bar",
+            'foo:bar',
+        ), (
+            "foo",
+            "",
+            'foo',
+        ), (
+            "foo:bar",
+            "baz",
+            'foo:baz',
+        ), (
+            "registry.example.com:5000/foo/bar",
+            "baz",
+            'registry.example.com:5000/foo/bar:baz',
+        ),
+        (
+            "localhost:5000/foo/bar",
+            "baz",
+            'localhost:5000/foo/bar:baz',
+        ),
+        (
+            "nonvalid1@%registry.example.com:5000/foo/bar",
+            "baz",
+            'nonvalid1@%registry.example.com:5000/foo/bar:baz',
+        ),
+        (
+            "registry.example.com:5000/foo/bar",
+            "baz",
+            'registry.example.com:5000/foo/bar:baz',
+        ),(
+            "registry.example.com:5000/foo/bar:baz",
+            "bap",
+            'registry.example.com:5000/foo/bar:bap',
+        )
+    ])
+    def test_tag_to(self, from_image, from_tag, expect):
+        result = tag_to(from_image, from_tag)
+        assert result == expect
+        
+        
+    @pytest.mark.parametrize(('tag', 'expect'), [
+        (
+            "Tag",
+            True
+        ),(
+            "tAg.",
+            True
+        ), (
+            "tag-tag",
+            True
+        ), (
+            ".notTag",
+            False
+        ), (
+            "not/tag",
+            False
+        )
+    ])
+    def test_valid_tag(self, tag, expect):
+        result = valid_tag(tag)
+        assert result == expect
+        
     def test_parent_images(self, dfparser):
         FROM = ('my-builder:latest', 'rhel7:7.5')
         template = dedent("""\
@@ -507,8 +639,9 @@ def test_parent_images_missing_from(self, dfparser):
         assert dfparser.content.count('FROM') == 4
 
     def test_modify_instruction(self, dfparser):
-        FROM = ('ubuntu', 'fedora:❤')
+        FROM = ('ubuntu', 'fedora:theBest')
         CMD = ('old❤cmd', 'new❤command')
+        TAG = ('theBest', 'newtag')
         df_content = dedent("""\
             FROM {0}
             CMD {1}""").format(FROM[0], CMD[0])
@@ -518,6 +651,10 @@ def test_modify_instruction(self, dfparser):
         assert dfparser.baseimage == FROM[0]
         dfparser.baseimage = FROM[1]
         assert dfparser.baseimage == FROM[1]
+        
+        assert dfparser.basetag == TAG[0]
+        dfparser.basetag = TAG[1]
+        assert dfparser.basetag == TAG[1]
 
         assert dfparser.cmd == CMD[0]
         dfparser.cmd = CMD[1]