repo: Implement ReadmeFinder

It currently resembles the logic from the old markup renderer. The
implementation is based on get_nodes though, so that we should usually only have
one call or at most three calls if the directories "doc" and/or "docs" exist.

A difference is that we now ignore the case, this already simplifies the rule
definition.

rhodecode/tests/models/test_repo_readme.py

@@ -0,0 +1,106 b''
+# -*- coding: utf-8 -*-
+
+# Copyright (C) 2010-2016  RhodeCode GmbH
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License, version 3
+# (only), as published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+# This program is dual-licensed. If you wish to learn more about the
+# RhodeCode Enterprise Edition, including its added features, Support services,
+# and proprietary license terms, please see https://rhodecode.com/licenses/
+
+import pytest
+
+from rhodecode.lib.vcs import nodes
+from rhodecode.model.repo import ReadmeFinder
+
+
[e-mail]
+def commit_util(vcsbackend_stub):
+    """
+    Provide a commit which has certain files in it's tree.
+
+    This is based on the fixture "vcsbackend" and will automatically be
+    parametrized for all vcs backends.
+    """
+    return CommitUtility(vcsbackend_stub)
+
+
+class CommitUtility:
+
+    def __init__(self, vcsbackend):
+        self.vcsbackend = vcsbackend
+
+    def commit_with_files(self, filenames):
+        commits = [
+            {'message': 'Adding all requested files',
+             'added': [
+                 nodes.FileNode(filename, content='')
+                 for filename in filenames
+             ]}]
+        repo = self.vcsbackend.create_repo(commits=commits)
+        return repo.get_commit()
+
+
+def test_no_matching_file_returns_none(commit_util):
+    commit = commit_util.commit_with_files(['LIESMICH'])
+    finder = ReadmeFinder(default_renderer='rst')
+    filename = finder.search(commit)
+    assert filename is None
+
+
+def test_matching_file_returns_the_file_name(commit_util):
+    commit = commit_util.commit_with_files(['README'])
+    finder = ReadmeFinder(default_renderer='rst')
+    filename = finder.search(commit)
+    assert filename == 'README'
+
+
+def test_matching_file_with_extension(commit_util):
+    commit = commit_util.commit_with_files(['README.rst'])
+    finder = ReadmeFinder(default_renderer='rst')
+    filename = finder.search(commit)
+    assert filename == 'README.rst'
+
+
+def test_prefers_readme_without_extension(commit_util):
+    commit = commit_util.commit_with_files(['README.rst', 'Readme'])
+    finder = ReadmeFinder()
+    filename = finder.search(commit)
+    assert filename == 'Readme'
+
+
[e-mail]('renderer, expected', [
+    ('rst', 'readme.rst'),
+    ('markdown', 'readme.md'),
+])
+def test_prefers_renderer_extensions(commit_util, renderer, expected):
+    commit = commit_util.commit_with_files(
+        ['readme.rst', 'readme.md', 'readme.txt'])
+    finder = ReadmeFinder(default_renderer=renderer)
+    filename = finder.search(commit)
+    assert filename == expected
+
+
+def test_finds_readme_in_subdirectory(commit_util):
+    commit = commit_util.commit_with_files(['doc/README.rst', 'LIESMICH'])
+    finder = ReadmeFinder()
+    filename = finder.search(commit)
+    assert filename == 'doc/README.rst'
+
+
+def test_prefers_subdirectory_with_priority(commit_util):
+    commit = commit_util.commit_with_files(
+        ['Doc/Readme.rst', 'Docs/Readme.rst'])
+    finder = ReadmeFinder()
+    filename = finder.search(commit)
+    assert filename == 'Doc/Readme.rst'

rhodecode/model/repo.py

@@ -947,10 +947,97 b' class ReadmeFinder:'
     different.
     """
 
-    def __init__(self, default_renderer):
+    readme_re = re.compile(r'^readme(\.[^\.]+)?$', re.IGNORECASE)
+    path_re = re.compile(r'^docs?', re.IGNORECASE)
+
+    default_priorities = {
+        None: 0,
+        '.text': 2,
+        '.txt': 3,
+        '.rst': 1,
+        '.rest': 2,
+        '.md': 1,
+        '.mkdn': 2,
+        '.mdown': 3,
+        '.markdown': 4,
+    }
+
+    path_priority = {
+        'doc': 0,
+        'docs': 1,
+    }
+
+    FALLBACK_PRIORITY = 99
+
+    RENDERER_TO_EXTENSION = {
+        'rst': ['.rst', '.rest'],
+        'markdown': ['.md', 'mkdn', '.mdown', '.markdown'],
+    }
+
+    def __init__(self, default_renderer=None):
         self._default_renderer = default_renderer
+        self._renderer_extensions = self.RENDERER_TO_EXTENSION.get(
+            default_renderer, [])
 
-    def search(self, commit):
+    def search(self, commit, path='/'):
+        """
+        Find a readme in the given `commit`.
+        """
+        nodes = commit.get_nodes(path)
+        matches = self._match_readmes(nodes)
+        matches = self._sort_according_to_priority(matches)
+        if matches:
+            return matches[0].path
+
+        paths = self._match_paths(nodes)
+        paths = self._sort_paths_according_to_priority(paths)
+        for path in paths:
+            match = self.search(commit, path=path)
+            if match:
+                return match
+
+        return None
+
+    def _match_readmes(self, nodes):
+        for node in nodes:
+            if not node.is_file():
+                continue
+            path = node.path.rsplit('/', 1)[-1]
+            match = self.readme_re.match(path)
+            if match:
+                extension = match.group(1)
+                yield ReadmeMatch(node, match, self._priority(extension))
+
+    def _match_paths(self, nodes):
+        for node in nodes:
+            if not node.is_dir():
+                continue
+            match = self.path_re.match(node.path)
+            if match:
+                yield node.path
+
+    def _priority(self, extension):
+        renderer_priority = (
+            0 if extension in self._renderer_extensions else 1)
+        extension_priority = self.default_priorities.get(
+            extension, self.FALLBACK_PRIORITY)
+        return (renderer_priority, extension_priority)
+
+    def _sort_according_to_priority(self, matches):
+
+        def priority_and_path(match):
+            return (match.priority, match.path)
+
+        return sorted(matches, key=priority_and_path)
+
+    def _sort_paths_according_to_priority(self, paths):
+
+        def priority_and_path(path):
+            return (self.path_priority.get(path, self.FALLBACK_PRIORITY), path)
+
+        return sorted(paths, key=priority_and_path)
+
+    def search_old(self, commit):
         """
         Try to find a readme in the given `commit`.
         """
@@ -966,3 +1053,18 b' class ReadmeFinder:'
                 continue
 
             return f
+
+
+class ReadmeMatch:
+
+    def __init__(self, node, match, priority):
+        self._node = node
+        self._match = match
+        self.priority = priority
+
+    @property
+    def path(self):
+        return self._node.path
+
+    def __repr__(self):
+        return '<ReadmeMatch {} priority={}'.format(self.path, self.priority)