gitubuntu/git_repository: abstract pristine-tar manipulation

We expose three new APIs:

1) pristine_tar_branches - a context manager that manipulates the
per-distro pristine-tar branches

2) pristine_tar_list - returns a list of imported tarballs for a given
distro

3) pristine_tar_extract - obtains the pristine-tar tarball corresponding
to a given srcpkg and version (the srcpkg is necessary as it is in the
tarball name) in a distro

1 files changed, 149 insertions, 0 deletions

diff --git a/gitubuntu/git_repository.py b/gitubuntu/git_repository.py
index a9f2907..7e6c083 100644
--- a/gitubuntu/git_repository.py
+++ b/gitubuntu/git_repository.py
@@ -2,6 +2,7 @@
 ### XXX: is any of this data in lp already?
 
 import collections
+from contextlib import contextmanager
 from copy import copy
 from enum import Enum, unique
 import functools
@@ -45,6 +46,15 @@ def memoize(obj):
 class GitUbuntuChangelogError(Exception):
     pass
 
+class PristineTarError(Exception):
+    pass
+
+class PristineTarNotFoundError(PristineTarError):
+    pass
+
+class MultiplePristineTarFoundError(PristineTarError):
+    pass
+
 
 @unique
 class ChangelogField(Enum):
@@ -161,6 +171,145 @@ class GitUbuntuRepository:
                                   'Initial Debian pristine-tar branch.'
                                  )
 
+    @contextmanager
+    def pristine_tar_branches(self, dist, namespace='pkg', move=False):
+        """Context manager wrapping pristine-tar branch manipulation
+
+        In this context, the repository pristine-tar branch will point to
+        the pristine-tar branch for @dist distribution in @namespace.
+        If a local branch named pristine-tar exists already, it will be
+        moved to a (hopefully) safe name.
+        If @move is True, then the pristine-tar branch will be moved
+        rather than simply started from the parameter-specified point.
+        """
+        pt_branch = '%s/importer/%s/pristine-tar' % (namespace, dist)
+        old_pt_branch = self.raw_repo.lookup_branch('pristine-tar')
+        if old_pt_branch:
+            self.git_run(['branch', '-M', 'pristine-tar', 'pristine-tar.bak'])
+        cmd = ['branch']
+        if move:
+            cmd.extend(['-M', pt_branch, 'pristine-tar'])
+        else:
+            cmd.extend(['pristine-tar', pt_branch])
+        self.git_run(cmd)
+        yield
+        cmd = ['branch']
+        if move:
+            cmd.extend(['-M', 'pristine-tar', pt_branch])
+        else:
+            cmd.extend(['-D', 'pristine-tar'])
+        self.git_run(cmd)
+        if old_pt_branch:
+            self.git_run(['branch', '-M', 'pristine-tar.bak', 'pristine-tar'])
+
+    def pristine_tar_list(self, dist, namespace='pkg'):
+        with self.pristine_tar_branches(dist, namespace):
+            cp = run(['pristine-tar', 'list'])
+            return decode_binary(cp.stdout).strip().splitlines()
+
+    def pristine_tar_extract(self, pkgname, version, dist=None, namespace='pkg'):
+        '''Extract orig tarballs for a given package and upstream version
+
+        returns: list of tarball paths that are now present on the filesystem
+        throws:
+        - PristineTarNotFoundError if no suitable tarballs are found
+        - MultiplePristineTarFoundError if multiple distinct suitable tarballs
+          are found
+
+        '''
+        dists = [dist] if dist else ['debian', 'ubuntu']
+        for dist in dists:
+            main_tarball = '%s_%s.orig.tar' % (pkgname, version)
+
+            all_tarballs = self.pristine_tar_list(dist, namespace)
+
+            potential_main_tarballs = [tarball for tarball
+                in all_tarballs if tarball.startswith(main_tarball)]
+            if len(potential_main_tarballs) == 0:
+                continue
+            if len(potential_main_tarballs) > 1:
+                # This will need some extension/flag for the case of there
+                # being multiple imports with varying compression
+                raise MultiplePristineTarFoundError(
+                    'More than one pristine-tar tarball found for %s: %s' %
+                    (version, potential_main_tarballs)
+                )
+            ext = os.path.splitext(potential_main_tarballs[0])[1]
+            tarballs = []
+            tarballs.append(os.path.join('..', potential_main_tarballs[0]))
+            cmd = ['gbp', 'buildpackage', '--git-builder=/bin/true',
+                   '--git-pristine-tar', '--git-ignore-branch',
+                   '--git-upstream-tag=%s/upstream/%s/%%(version)s%s' %
+                   (namespace, dist, ext)]
+            orig_re = re.compile(
+                r'^%s_%s\.orig-(?P<component>[^.]+)\.tar\.[^.]+$' %
+                (re.escape(pkgname), re.escape(version))
+            )
+            # This will probably break if the component tarballs get
+            # compressed differently, as each component tarball will show up
+            # multiple times
+            # Breaks may be too strong -- we will 'over cache' tarballs, and
+            # then it's up to dpkg-buildpackage to use the 'correct' one
+            potential_component_tarballs = {
+                orig_re.match(tarball).group('component') : tarball for tarball
+                in all_tarballs if orig_re.match(tarball)
+            }
+            tarballs.extend(map(lambda x : os.path.join('..', x),
+                list(potential_component_tarballs.values()))
+            )
+            cmd.extend(map(lambda x : '--git-component=%s' % x,
+                list(potential_component_tarballs.keys()))
+            )
+            with self.pristine_tar_branches(dist, namespace):
+                run(cmd)
+            return tarballs
+
+        raise PristineTarNotFoundError(
+            'No pristine-tar tarball found for %s' % version
+        )
+
+    def pristine_tar_exists(self, pkgname, version, namespace='pkg'):
+        '''Report distributions that contain pristine-tar data for @version
+        '''
+        results = []
+        for dist in ('debian', 'ubuntu'):
+            main_tarball = '%s_%s.orig.tar' % (pkgname, version)
+
+            all_tarballs = self.pristine_tar_list(dist, namespace)
+
+            potential_main_tarballs = [tarball for tarball
+                in all_tarballs if tarball.startswith(main_tarball)]
+            if len(potential_main_tarballs) == 0:
+                continue
+            if len(potential_main_tarballs) > 1:
+                # This will need some extension/flag for the case of there
+                # being multiple imports with varying compression
+                raise MultiplePristineTarFoundError(
+                    'More than one pristine-tar tarball found for %s: %s' %
+                    (version, potential_main_tarballs)
+                )
+            results.append(dist)
+
+        return results
+
+    def verify_pristine_tar(self, tarball_paths, dist, namespace='pkg'):
+        '''Verify the pristine-tar data matches for a set of paths
+        '''
+        all_tarballs = self.pristine_tar_list(dist, namespace)
+        for path in tarball_paths:
+            if os.path.basename(path) not in all_tarballs:
+                break
+            try:
+                with self.pristine_tar_branches(dist, namespace):
+                    # need to handle this not existing
+                    run(['pristine-tar', 'verify', path])
+            except CalledProcessError as e:
+                raise PristineTarError('Tarball at %s failed to verify')
+        else:
+            return True
+
+        return False
+
     def set_git_attributes(self):
         git_attr_path = os.path.join(self.raw_repo.path,
                                      'info',